1414 files changed, 92390 insertions, 32520 deletions

diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index b223769d6a5e..3da97996bdf3 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -1266,12 +1266,14 @@ el3_up(struct net_device *dev)
 					pr_cont("Forcing 3c5x9b full-duplex mode");
 					break;
 				}
+				/* fall through */
 			case 8:
 				/* set full-duplex mode based on eeprom config setting */
 				if ((sw_info & 0x000f) && (sw_info & 0x8000)) {
 					pr_cont("Setting 3c5x9b full-duplex mode (from EEPROM configuration bit)");
 					break;
 				}
+				/* fall through */
 			default:
 				/* xcvr=(0 || 4) OR user has an old 3c5x9 non "B" model */
 				pr_cont("Setting 3c5x9/3c5x9B half-duplex mode");
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index b648e3f95c01..b15752267c8d 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -1177,7 +1177,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id)
 				if (inl(ioaddr + DownListPtr) == isa_virt_to_bus(&lp->tx_ring[entry]))
 					break;	/* It still hasn't been processed. */
 				if (lp->tx_skbuff[entry]) {
-					dev_kfree_skb_irq(lp->tx_skbuff[entry]);
+					dev_consume_skb_irq(lp->tx_skbuff[entry]);
 					lp->tx_skbuff[entry] = NULL;
 				}
 				dirty_tx++;
@@ -1192,7 +1192,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id)
 #ifdef VORTEX_BUS_MASTER
 		if (status & DMADone) {
 			outw(0x1000, ioaddr + Wn7_MasterStatus);	/* Ack the event. */
-			dev_kfree_skb_irq(lp->tx_skb);	/* Release the transferred buffer */
+			dev_consume_skb_irq(lp->tx_skb);	/* Release the transferred buffer */
 			netif_wake_queue(dev);
 		}
 #endif
@@ -1521,7 +1521,7 @@ static void update_stats(int ioaddr, struct net_device *dev)
 static void set_rx_mode(struct net_device *dev)
 {
 	int ioaddr = dev->base_addr;
-	short new_mode;
+	unsigned short new_mode;
 
 	if (dev->flags & IFF_PROMISC) {
 		if (corkscrew_debug > 3)
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 40f421dbdf57..147051404194 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -2307,7 +2307,7 @@ _vortex_interrupt(int irq, struct net_device *dev)
 				dma_unmap_single(vp->gendev, vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, DMA_TO_DEVICE);
 				pkts_compl++;
 				bytes_compl += vp->tx_skb->len;
-				dev_kfree_skb_irq(vp->tx_skb); /* Release the transferred buffer */
+				dev_consume_skb_irq(vp->tx_skb); /* Release the transferred buffer */
 				if (ioread16(ioaddr + TxFree) > 1536) {
 					/*
 					 * AKPM: FIXME: I don't think we need this.  If the queue was stopped due to
@@ -2449,7 +2449,7 @@ _boomerang_interrupt(int irq, struct net_device *dev)
 #endif
 					pkts_compl++;
 					bytes_compl += skb->len;
-					dev_kfree_skb_irq(skb);
+					dev_consume_skb_irq(skb);
 					vp->tx_skbuff[entry] = NULL;
 				} else {
 					pr_debug("boomerang_interrupt: no skb!\n");
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 0ac44ef1f7a9..3a6fc99c6f32 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # 3Com Ethernet device configuration
 #
diff --git a/drivers/net/ethernet/8390/8390.c b/drivers/net/ethernet/8390/8390.c
index a43544af257b..78f3e532c600 100644
--- a/drivers/net/ethernet/8390/8390.c
+++ b/drivers/net/ethernet/8390/8390.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 8390 core for usual drivers */
 
 static const char version[] =
diff --git a/drivers/net/ethernet/8390/8390p.c b/drivers/net/ethernet/8390/8390p.c
index 46d2257c4430..6cf36992a2c6 100644
--- a/drivers/net/ethernet/8390/8390p.c
+++ b/drivers/net/ethernet/8390/8390p.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 8390 core for ISA devices needing bus delays */
 
 static const char version[] =
diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig
index f2f0264c58ba..2a3e2450968e 100644
--- a/drivers/net/ethernet/8390/Kconfig
+++ b/drivers/net/ethernet/8390/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # 8390 device configuration
 #
@@ -49,7 +50,7 @@ config XSURF100
 	tristate "Amiga XSurf 100 AX88796/NE2000 clone support"
 	depends on ZORRO
 	select AX88796
-	select ASIX_PHY
+	select AX88796B_PHY
 	help
 	  This driver is for the Individual Computers X-Surf 100 Ethernet
 	  card (based on the Asix AX88796 chip). If you have such a card,
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index 3dcc61821ed5..172947fc051a 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* drivers/net/ethernet/8390/ax88796.c
  *
  * Copyright 2005,2007 Simtec Electronics
@@ -5,10 +6,6 @@
  *
  * Asix AX88796 10/100 Ethernet controller support
  *	Based on ne.c, by Donald Becker, et-al.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c
index 77191a281866..bd22a534b1c0 100644
--- a/drivers/net/ethernet/8390/etherh.c
+++ b/drivers/net/ethernet/8390/etherh.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/drivers/acorn/net/etherh.c
  *
  *  Copyright (C) 2000-2002 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * NS8390 I-cubed EtherH and ANT EtherM specific driver
  * Thanks to I-Cubed for information on their cards.
  * EtherM conversion (C) 1999 Chris Kemp and Tim Watterton
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index 342ae08ec3c2..d60a86aa8aa8 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,8 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
-
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
 static void slow_sane_get_8390_hdr(struct net_device *dev,
 				   struct e8390_pkt_hdr *hdr, int ring_page);
@@ -233,19 +231,26 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres)
 
 static enum mac8390_access mac8390_testio(unsigned long membase)
 {
-	unsigned long outdata = 0xA5A0B5B0;
-	unsigned long indata =  0x00000000;
+	u32 outdata = 0xA5A0B5B0;
+	u32 indata = 0;
+
 	/* Try writing 32 bits */
-	memcpy_toio((void __iomem *)membase, &outdata, 4);
-	/* Now compare them */
-	if (memcmp_withio(&outdata, membase, 4) == 0)
+	nubus_writel(outdata, membase);
+	/* Now read it back */
+	indata = nubus_readl(membase);
+	if (outdata == indata)
 		return ACCESS_32;
+
+	outdata = 0xC5C0D5D0;
+	indata = 0;
+
 	/* Write 16 bit output */
 	word_memcpy_tocard(membase, &outdata, 4);
 	/* Now read it back */
 	word_memcpy_fromcard(&indata, membase, 4);
 	if (outdata == indata)
 		return ACCESS_16;
+
 	return ACCESS_UNKNOWN;
 }
 
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 61e43802b9a5..645efac6310d 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -289,6 +289,11 @@ static struct hw_info *get_hwinfo(struct pcmcia_device *link)
 
     virt = ioremap(link->resource[2]->start,
 	    resource_size(link->resource[2]));
+    if (unlikely(!virt)) {
+	    pcmcia_release_window(link, link->resource[2]);
+	    return NULL;
+    }
+
     for (i = 0; i < NR_INFO; i++) {
 	pcmcia_map_mem_page(link, link->resource[2],
 		hw_info[i].offset & ~(resource_size(link->resource[2])-1));
@@ -1423,6 +1428,11 @@ static int setup_shmem_window(struct pcmcia_device *link, int start_pg,
     /* Try scribbling on the buffer */
     info->base = ioremap(link->resource[3]->start,
 			resource_size(link->resource[3]));
+    if (unlikely(!info->base)) {
+	    ret = -ENOMEM;
+	    goto failed;
+    }
+
     for (i = 0; i < (TX_PAGES<<8); i += 2)
 	__raw_writew((i>>1), info->base+offset+i);
     udelay(100);
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 885e00d17807..93a2d4deb27c 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Ethernet LAN device configuration
 #
@@ -75,6 +76,7 @@ source "drivers/net/ethernet/ezchip/Kconfig"
 source "drivers/net/ethernet/faraday/Kconfig"
 source "drivers/net/ethernet/freescale/Kconfig"
 source "drivers/net/ethernet/fujitsu/Kconfig"
+source "drivers/net/ethernet/google/Kconfig"
 source "drivers/net/ethernet/hisilicon/Kconfig"
 source "drivers/net/ethernet/hp/Kconfig"
 source "drivers/net/ethernet/huawei/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 7b5bf9682066..fb9155cffcff 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_NET_VENDOR_EZCHIP) += ezchip/
 obj-$(CONFIG_NET_VENDOR_FARADAY) += faraday/
 obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/
 obj-$(CONFIG_NET_VENDOR_FUJITSU) += fujitsu/
+obj-$(CONFIG_NET_VENDOR_GOOGLE) += google/
 obj-$(CONFIG_NET_VENDOR_HISILICON) += hisilicon/
 obj-$(CONFIG_NET_VENDOR_HP) += hp/
 obj-$(CONFIG_NET_VENDOR_HUAWEI) += huawei/
diff --git a/drivers/net/ethernet/adaptec/Kconfig b/drivers/net/ethernet/adaptec/Kconfig
index 822cffb4174c..86e02da4f993 100644
--- a/drivers/net/ethernet/adaptec/Kconfig
+++ b/drivers/net/ethernet/adaptec/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Adaptec network device configuration
 #
diff --git a/drivers/net/ethernet/adaptec/Makefile b/drivers/net/ethernet/adaptec/Makefile
index 6c07b758ac0a..d84138c8a9ea 100644
--- a/drivers/net/ethernet/adaptec/Makefile
+++ b/drivers/net/ethernet/adaptec/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Adaptec network device drivers.
 #
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 097467f44b0d..816540e6beac 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -1390,7 +1390,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 					}
 				}
 
-				dev_kfree_skb_irq(skb);
+				dev_consume_skb_irq(skb);
 			}
 			np->tx_done_q[np->tx_done].status = 0;
 			np->tx_done = (np->tx_done + 1) % DONE_Q_SIZE;
diff --git a/drivers/net/ethernet/aeroflex/Kconfig b/drivers/net/ethernet/aeroflex/Kconfig
index 4f4a8d78fd54..2fa0a317266b 100644
--- a/drivers/net/ethernet/aeroflex/Kconfig
+++ b/drivers/net/ethernet/aeroflex/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Aeroflex Gaisler network device configuration
 #
diff --git a/drivers/net/ethernet/aeroflex/Makefile b/drivers/net/ethernet/aeroflex/Makefile
index 6e62a679282f..1b18ef0a5389 100644
--- a/drivers/net/ethernet/aeroflex/Makefile
+++ b/drivers/net/ethernet/aeroflex/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Aeroflex Gaisler network device drivers.
 #
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 47e5984f16fb..010a2f48aea5 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Aeroflex Gaisler GRETH 10/100/1G Ethernet MAC.
  *
@@ -12,11 +13,6 @@
  * The Gigabit version supports scatter/gather DMA, any alignment of
  * buffers and checksum offloading.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
  * Contributors: Kristoffer Glembo
  *               Daniel Hellstrom
  *               Marko Isomaki
@@ -613,7 +609,6 @@ static irqreturn_t greth_interrupt(int irq, void *dev_id)
 		napi_schedule(&greth->napi);
 	}
 
-	mmiowb();
 	spin_unlock(&greth->devlock);
 
 	return retval;
@@ -1459,7 +1454,7 @@ static int greth_of_probe(struct platform_device *ofdev)
 		const u8 *addr;
 
 		addr = of_get_mac_address(ofdev->dev.of_node);
-		if (addr) {
+		if (!IS_ERR(addr)) {
 			for (i = 0; i < 6; i++)
 				macaddr[i] = (unsigned int) addr[i];
 		} else {
diff --git a/drivers/net/ethernet/agere/Kconfig b/drivers/net/ethernet/agere/Kconfig
index b6fe9200355a..084c7190ce2f 100644
--- a/drivers/net/ethernet/agere/Kconfig
+++ b/drivers/net/ethernet/agere/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Agere device configuration
 #
diff --git a/drivers/net/ethernet/agere/Makefile b/drivers/net/ethernet/agere/Makefile
index 027ff9453fe1..8dbdf666b994 100644
--- a/drivers/net/ethernet/agere/Makefile
+++ b/drivers/net/ethernet/agere/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Agere ET-131x ethernet driver
 #
diff --git a/drivers/net/ethernet/alacritech/Kconfig b/drivers/net/ethernet/alacritech/Kconfig
index 09496e18cdc5..212f92c8e6a9 100644
--- a/drivers/net/ethernet/alacritech/Kconfig
+++ b/drivers/net/ethernet/alacritech/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config NET_VENDOR_ALACRITECH
 	bool "Alacritech devices"
 	default y
diff --git a/drivers/net/ethernet/alacritech/Makefile b/drivers/net/ethernet/alacritech/Makefile
index 8790e9ed8496..4378aadf895b 100644
--- a/drivers/net/ethernet/alacritech/Makefile
+++ b/drivers/net/ethernet/alacritech/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Alacritech Slicoss driver
 #
diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 16477aa6d61f..80ef3e15bd22 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -1,19 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Driver for Gigabit Ethernet adapters based on the Session Layer
  * Interface (SLIC) technology by Alacritech. The driver does not
  * support the hardware acceleration features provided by these cards.
  *
  * Copyright (C) 2016 Lino Sanfilippo <LinoSanfilippo@gmx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
  */
 
 #include <linux/kernel.h>
@@ -345,8 +336,6 @@ static void slic_set_rx_mode(struct net_device *dev)
 	if (sdev->promisc != set_promisc) {
 		sdev->promisc = set_promisc;
 		slic_configure_rcv(sdev);
-		/* make sure writes to receiver cant leak out of the lock */
-		mmiowb();
 	}
 	spin_unlock_bh(&sdev->link_lock);
 }
@@ -1461,8 +1450,6 @@ static netdev_tx_t slic_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (slic_get_free_tx_descs(txq) < SLIC_MAX_REQ_TX_DESCS)
 		netif_stop_queue(dev);
-	/* make sure writes to io-memory cant leak out of tx queue lock */
-	mmiowb();
 
 	return NETDEV_TX_OK;
 drop_skb:
diff --git a/drivers/net/ethernet/allwinner/Kconfig b/drivers/net/ethernet/allwinner/Kconfig
index 47da7e7a5b6a..a5e2bcbf2722 100644
--- a/drivers/net/ethernet/allwinner/Kconfig
+++ b/drivers/net/ethernet/allwinner/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Allwinner device configuration
 #
diff --git a/drivers/net/ethernet/allwinner/Makefile b/drivers/net/ethernet/allwinner/Makefile
index 03129f796514..ddd5a5079e8a 100644
--- a/drivers/net/ethernet/allwinner/Makefile
+++ b/drivers/net/ethernet/allwinner/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Allwinner device drivers.
 #
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index e1acafa82214..3434730a7699 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -224,8 +224,8 @@ static int emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 static void emac_get_drvinfo(struct net_device *dev,
 			      struct ethtool_drvinfo *info)
 {
-	strlcpy(info->driver, DRV_NAME, sizeof(DRV_NAME));
-	strlcpy(info->version, DRV_VERSION, sizeof(DRV_VERSION));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 	strlcpy(info->bus_info, dev_name(&dev->dev), sizeof(info->bus_info));
 }
 
@@ -818,7 +818,6 @@ static int emac_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 
 	db = netdev_priv(ndev);
-	memset(db, 0, sizeof(*db));
 
 	db->dev = &pdev->dev;
 	db->ndev = ndev;
@@ -870,8 +869,8 @@ static int emac_probe(struct platform_device *pdev)
 
 	/* Read MAC-address from DT */
 	mac_addr = of_get_mac_address(np);
-	if (mac_addr)
-		memcpy(ndev->dev_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(ndev->dev_addr, mac_addr);
 
 	/* Check if the MAC address is valid, if not get a random one */
 	if (!is_valid_ether_addr(ndev->dev_addr)) {
diff --git a/drivers/net/ethernet/alteon/Kconfig b/drivers/net/ethernet/alteon/Kconfig
index e06ccab354b5..c3f7067d2d10 100644
--- a/drivers/net/ethernet/alteon/Kconfig
+++ b/drivers/net/ethernet/alteon/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Alteon network device configuration
 #
diff --git a/drivers/net/ethernet/alteon/Makefile b/drivers/net/ethernet/alteon/Makefile
index a2ca173f2a50..be5225559b6d 100644
--- a/drivers/net/ethernet/alteon/Makefile
+++ b/drivers/net/ethernet/alteon/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Alteon network device drivers.
 #
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 1827ef1f6d55..46b4207d3266 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * acenic.c: Linux driver for the Alteon AceNIC Gigabit Ethernet card
  *           and other Tigon based cards.
@@ -12,11 +13,6 @@
  * about the driver. Send mail to linux-acenic-help@sunsite.auc.dk to
  * see how to subscribe.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  * Additional credits:
  *   Pete Wyckoff <wyckoff@ca.sandia.gov>: Initial Linux/Alpha and trace
  *       dump support. The trace dump support has not been
diff --git a/drivers/net/ethernet/altera/Kconfig b/drivers/net/ethernet/altera/Kconfig
index fdddba51473e..2690c398d2b2 100644
--- a/drivers/net/ethernet/altera/Kconfig
+++ b/drivers/net/ethernet/altera/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config ALTERA_TSE
 	tristate "Altera Triple-Speed Ethernet MAC support"
 	depends on HAS_DMA
diff --git a/drivers/net/ethernet/altera/Makefile b/drivers/net/ethernet/altera/Makefile
index d4a187e45369..a52db80aee9f 100644
--- a/drivers/net/ethernet/altera/Makefile
+++ b/drivers/net/ethernet/altera/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Altera device drivers.
 #
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
index 0ae723f75341..ac1efd08267a 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.c
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/altera/altera_msgdma.h b/drivers/net/ethernet/altera/altera_msgdma.h
index 42cf61c81057..9813fbfff4d3 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.h
+++ b/drivers/net/ethernet/altera/altera_msgdma.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ALTERA_MSGDMA_H__
diff --git a/drivers/net/ethernet/altera/altera_msgdmahw.h b/drivers/net/ethernet/altera/altera_msgdmahw.h
index 89cd11d86642..019f5a12630e 100644
--- a/drivers/net/ethernet/altera/altera_msgdmahw.h
+++ b/drivers/net/ethernet/altera/altera_msgdmahw.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ALTERA_MSGDMAHW_H__
diff --git a/drivers/net/ethernet/altera/altera_sgdma.c b/drivers/net/ethernet/altera/altera_sgdma.c
index 88ef67a998b4..db97170da8c7 100644
--- a/drivers/net/ethernet/altera/altera_sgdma.c
+++ b/drivers/net/ethernet/altera/altera_sgdma.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/list.h>
diff --git a/drivers/net/ethernet/altera/altera_sgdma.h b/drivers/net/ethernet/altera/altera_sgdma.h
index 584977e29ef9..08afe1c9994f 100644
--- a/drivers/net/ethernet/altera/altera_sgdma.h
+++ b/drivers/net/ethernet/altera/altera_sgdma.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ALTERA_SGDMA_H__
diff --git a/drivers/net/ethernet/altera/altera_sgdmahw.h b/drivers/net/ethernet/altera/altera_sgdmahw.h
index bbd52f02330b..3304518e2cbf 100644
--- a/drivers/net/ethernet/altera/altera_sgdmahw.h
+++ b/drivers/net/ethernet/altera/altera_sgdmahw.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ALTERA_SGDMAHW_H__
diff --git a/drivers/net/ethernet/altera/altera_tse.h b/drivers/net/ethernet/altera/altera_tse.h
index e2feee87180a..f17acfb579a0 100644
--- a/drivers/net/ethernet/altera/altera_tse.h
+++ b/drivers/net/ethernet/altera/altera_tse.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Altera Triple-Speed Ethernet MAC driver
  * Copyright (C) 2008-2014 Altera Corporation. All rights reserved
  *
@@ -14,18 +15,6 @@
  *
  * Original driver contributed by SLS.
  * Major updates contributed by GlobalLogic
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __ALTERA_TSE_H__
diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c
index 7c367713c3e6..23823464f2e7 100644
--- a/drivers/net/ethernet/altera/altera_tse_ethtool.c
+++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Ethtool support for Altera Triple-Speed Ethernet MAC driver
  * Copyright (C) 2008-2014 Altera Corporation. All rights reserved
  *
@@ -13,18 +14,6 @@
  *
  * Original driver contributed by SLS.
  * Major updates contributed by GlobalLogic
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/ethtool.h>
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index aa1d1f5339d2..bb032be7fe31 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Altera Triple-Speed Ethernet MAC driver
  * Copyright (C) 2008-2014 Altera Corporation. All rights reserved
  *
@@ -14,18 +15,6 @@
  *
  * Original driver contributed by SLS.
  * Major updates contributed by GlobalLogic
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/atomic.h>
@@ -1537,7 +1526,7 @@ static int altera_tse_probe(struct platform_device *pdev)
 
 	/* get default MAC address from device tree */
 	macaddr = of_get_mac_address(pdev->dev.of_node);
-	if (macaddr)
+	if (!IS_ERR(macaddr))
 		ether_addr_copy(ndev->dev_addr, macaddr);
 	else
 		eth_hw_addr_random(ndev);
diff --git a/drivers/net/ethernet/altera/altera_utils.c b/drivers/net/ethernet/altera/altera_utils.c
index d7eeb1713ad2..e6a7fc9d8fb1 100644
--- a/drivers/net/ethernet/altera/altera_utils.c
+++ b/drivers/net/ethernet/altera/altera_utils.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "altera_tse.h"
diff --git a/drivers/net/ethernet/altera/altera_utils.h b/drivers/net/ethernet/altera/altera_utils.h
index baf100ccf587..b7d772f2dcbb 100644
--- a/drivers/net/ethernet/altera/altera_utils.h
+++ b/drivers/net/ethernet/altera/altera_utils.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Altera TSE SGDMA and MSGDMA Linux driver
  * Copyright (C) 2014 Altera Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/amazon/Kconfig b/drivers/net/ethernet/amazon/Kconfig
index 9e87d7b8360f..69ca99d8ac26 100644
--- a/drivers/net/ethernet/amazon/Kconfig
+++ b/drivers/net/ethernet/amazon/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Amazon network device configuration
 #
diff --git a/drivers/net/ethernet/amazon/Makefile b/drivers/net/ethernet/amazon/Makefile
index 8e0b73f60d51..f614f23ec549 100644
--- a/drivers/net/ethernet/amazon/Makefile
+++ b/drivers/net/ethernet/amazon/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Amazon network device drivers.
 #
diff --git a/drivers/net/ethernet/amazon/ena/Makefile b/drivers/net/ethernet/amazon/ena/Makefile
index eaeeae06c5d9..f1f752a8f7bb 100644
--- a/drivers/net/ethernet/amazon/ena/Makefile
+++ b/drivers/net/ethernet/amazon/ena/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Elastic Network Adapter (ENA) device drivers.
 #
diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 9f80b73f90b1..d19f2ecf8e84 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -60,6 +60,7 @@ enum ena_admin_aq_feature_id {
 	ENA_ADMIN_MAX_QUEUES_NUM                    = 2,
 	ENA_ADMIN_HW_HINTS                          = 3,
 	ENA_ADMIN_LLQ                               = 4,
+	ENA_ADMIN_MAX_QUEUES_EXT                    = 7,
 	ENA_ADMIN_RSS_HASH_FUNCTION                 = 10,
 	ENA_ADMIN_STATELESS_OFFLOAD_CONFIG          = 11,
 	ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG      = 12,
@@ -421,7 +422,13 @@ struct ena_admin_get_set_feature_common_desc {
 	/* as appears in ena_admin_aq_feature_id */
 	u8 feature_id;
 
-	u16 reserved16;
+	/* The driver specifies the max feature version it supports and the
+	 * device responds with the currently supported feature version. The
+	 * field is zero based
+	 */
+	u8 feature_version;
+
+	u8 reserved8;
 };
 
 struct ena_admin_device_attr_feature_desc {
@@ -524,6 +531,39 @@ struct ena_admin_feature_llq_desc {
 
 	/* the stride control the driver selected to use */
 	u16 descriptors_stride_ctrl_enabled;
+
+	/* Maximum size in bytes taken by llq entries in a single tx burst.
+	 * Set to 0 when there is no such limit.
+	 */
+	u32 max_tx_burst_size;
+};
+
+struct ena_admin_queue_ext_feature_fields {
+	u32 max_tx_sq_num;
+
+	u32 max_tx_cq_num;
+
+	u32 max_rx_sq_num;
+
+	u32 max_rx_cq_num;
+
+	u32 max_tx_sq_depth;
+
+	u32 max_tx_cq_depth;
+
+	u32 max_rx_sq_depth;
+
+	u32 max_rx_cq_depth;
+
+	u32 max_tx_header_size;
+
+	/* Maximum Descriptors number, including meta descriptor, allowed for
+	 * a single Tx packet
+	 */
+	u16 max_per_packet_tx_descs;
+
+	/* Maximum Descriptors number allowed for a single Rx packet */
+	u16 max_per_packet_rx_descs;
 };
 
 struct ena_admin_queue_feature_desc {
@@ -832,6 +872,19 @@ struct ena_admin_get_feat_cmd {
 	u32 raw[11];
 };
 
+struct ena_admin_queue_ext_feature_desc {
+	/* version */
+	u8 version;
+
+	u8 reserved1[3];
+
+	union {
+		struct ena_admin_queue_ext_feature_fields max_queue_ext;
+
+		u32 raw[10];
+	};
+};
+
 struct ena_admin_get_feat_resp {
 	struct ena_admin_acq_common_desc acq_common_desc;
 
@@ -844,6 +897,8 @@ struct ena_admin_get_feat_resp {
 
 		struct ena_admin_queue_feature_desc max_queue;
 
+		struct ena_admin_queue_ext_feature_desc max_queue_ext;
+
 		struct ena_admin_feature_aenq_desc aenq;
 
 		struct ena_admin_get_feature_link_desc link;
@@ -908,7 +963,9 @@ struct ena_admin_aenq_common_desc {
 
 	u16 syndrom;
 
-	/* 0 : phase */
+	/* 0 : phase
+	 * 7:1 : reserved - MBZ
+	 */
 	u8 flags;
 
 	u8 reserved1[3];
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index b17d435de09f..911a2e7a375a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -91,7 +91,7 @@ struct ena_com_stats_ctx {
 	struct ena_admin_acq_get_stats_resp get_resp;
 };
 
-static inline int ena_com_mem_addr_set(struct ena_com_dev *ena_dev,
+static int ena_com_mem_addr_set(struct ena_com_dev *ena_dev,
 				       struct ena_common_mem_addr *ena_addr,
 				       dma_addr_t addr)
 {
@@ -115,7 +115,7 @@ static int ena_com_admin_init_sq(struct ena_com_admin_queue *queue)
 					 GFP_KERNEL);
 
 	if (!sq->entries) {
-		pr_err("memory allocation failed");
+		pr_err("memory allocation failed\n");
 		return -ENOMEM;
 	}
 
@@ -137,7 +137,7 @@ static int ena_com_admin_init_cq(struct ena_com_admin_queue *queue)
 					 GFP_KERNEL);
 
 	if (!cq->entries) {
-		pr_err("memory allocation failed");
+		pr_err("memory allocation failed\n");
 		return -ENOMEM;
 	}
 
@@ -160,7 +160,7 @@ static int ena_com_admin_init_aenq(struct ena_com_dev *dev,
 					   GFP_KERNEL);
 
 	if (!aenq->entries) {
-		pr_err("memory allocation failed");
+		pr_err("memory allocation failed\n");
 		return -ENOMEM;
 	}
 
@@ -190,7 +190,7 @@ static int ena_com_admin_init_aenq(struct ena_com_dev *dev,
 	return 0;
 }
 
-static inline void comp_ctxt_release(struct ena_com_admin_queue *queue,
+static void comp_ctxt_release(struct ena_com_admin_queue *queue,
 				     struct ena_comp_ctx *comp_ctx)
 {
 	comp_ctx->occupied = false;
@@ -277,7 +277,7 @@ static struct ena_comp_ctx *__ena_com_submit_admin_cmd(struct ena_com_admin_queu
 	return comp_ctx;
 }
 
-static inline int ena_com_init_comp_ctxt(struct ena_com_admin_queue *queue)
+static int ena_com_init_comp_ctxt(struct ena_com_admin_queue *queue)
 {
 	size_t size = queue->q_depth * sizeof(struct ena_comp_ctx);
 	struct ena_comp_ctx *comp_ctx;
@@ -285,7 +285,7 @@ static inline int ena_com_init_comp_ctxt(struct ena_com_admin_queue *queue)
 
 	queue->comp_ctx = devm_kzalloc(queue->q_dmadev, size, GFP_KERNEL);
 	if (unlikely(!queue->comp_ctx)) {
-		pr_err("memory allocation failed");
+		pr_err("memory allocation failed\n");
 		return -ENOMEM;
 	}
 
@@ -356,7 +356,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 		}
 
 		if (!io_sq->desc_addr.virt_addr) {
-			pr_err("memory allocation failed");
+			pr_err("memory allocation failed\n");
 			return -ENOMEM;
 		}
 	}
@@ -382,7 +382,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 				devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL);
 
 		if (!io_sq->bounce_buf_ctrl.base_buffer) {
-			pr_err("bounce buffer memory allocation failed");
+			pr_err("bounce buffer memory allocation failed\n");
 			return -ENOMEM;
 		}
 
@@ -396,6 +396,10 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 		       0x0, io_sq->llq_info.desc_list_entry_size);
 		io_sq->llq_buf_ctrl.descs_left_in_line =
 			io_sq->llq_info.descs_num_before_header;
+
+		if (io_sq->llq_info.max_entries_in_tx_burst > 0)
+			io_sq->entries_in_tx_burst_left =
+				io_sq->llq_info.max_entries_in_tx_burst;
 	}
 
 	io_sq->tail = 0;
@@ -436,7 +440,7 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev,
 	}
 
 	if (!io_cq->cdesc_addr.virt_addr) {
-		pr_err("memory allocation failed");
+		pr_err("memory allocation failed\n");
 		return -ENOMEM;
 	}
 
@@ -727,11 +731,14 @@ static int ena_com_config_llq_info(struct ena_com_dev *ena_dev,
 		       supported_feat, llq_info->descs_num_before_header);
 	}
 
+	llq_info->max_entries_in_tx_burst =
+		(u16)(llq_features->max_tx_burst_size /	llq_default_cfg->llq_ring_entry_size_value);
+
 	rc = ena_com_set_llq(ena_dev);
 	if (rc)
 		pr_err("Cannot set LLQ configuration: %d\n", rc);
 
-	return 0;
+	return rc;
 }
 
 static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *comp_ctx,
@@ -755,16 +762,26 @@ static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *com
 		admin_queue->stats.no_completion++;
 		spin_unlock_irqrestore(&admin_queue->q_lock, flags);
 
-		if (comp_ctx->status == ENA_CMD_COMPLETED)
-			pr_err("The ena device have completion but the driver didn't receive any MSI-X interrupt (cmd %d)\n",
-			       comp_ctx->cmd_opcode);
-		else
-			pr_err("The ena device doesn't send any completion for the admin cmd %d status %d\n",
+		if (comp_ctx->status == ENA_CMD_COMPLETED) {
+			pr_err("The ena device sent a completion but the driver didn't receive a MSI-X interrupt (cmd %d), autopolling mode is %s\n",
+			       comp_ctx->cmd_opcode,
+			       admin_queue->auto_polling ? "ON" : "OFF");
+			/* Check if fallback to polling is enabled */
+			if (admin_queue->auto_polling)
+				admin_queue->polling = true;
+		} else {
+			pr_err("The ena device doesn't send a completion for the admin cmd %d status %d\n",
 			       comp_ctx->cmd_opcode, comp_ctx->status);
-
-		admin_queue->running_state = false;
-		ret = -ETIME;
-		goto err;
+		}
+		/* Check if shifted to polling mode.
+		 * This will happen if there is a completion without an interrupt
+		 * and autopolling mode is enabled. Continuing normal execution in such case
+		 */
+		if (!admin_queue->polling) {
+			admin_queue->running_state = false;
+			ret = -ETIME;
+			goto err;
+		}
 	}
 
 	ret = ena_com_comp_status_to_errno(comp_ctx->comp_status);
@@ -822,7 +839,7 @@ static u32 ena_com_reg_bar_read32(struct ena_com_dev *ena_dev, u16 offset)
 	}
 
 	if (read_resp->reg_off != offset) {
-		pr_err("Read failure: wrong offset provided");
+		pr_err("Read failure: wrong offset provided\n");
 		ret = ENA_MMIO_READ_TIMEOUT;
 	} else {
 		ret = read_resp->reg_val;
@@ -961,7 +978,8 @@ static int ena_com_get_feature_ex(struct ena_com_dev *ena_dev,
 				  struct ena_admin_get_feat_resp *get_resp,
 				  enum ena_admin_aq_feature_id feature_id,
 				  dma_addr_t control_buf_dma_addr,
-				  u32 control_buff_size)
+				  u32 control_buff_size,
+				  u8 feature_ver)
 {
 	struct ena_com_admin_queue *admin_queue;
 	struct ena_admin_get_feat_cmd get_cmd;
@@ -992,7 +1010,7 @@ static int ena_com_get_feature_ex(struct ena_com_dev *ena_dev,
 	}
 
 	get_cmd.control_buffer.length = control_buff_size;
-
+	get_cmd.feat_common.feature_version = feature_ver;
 	get_cmd.feat_common.feature_id = feature_id;
 
 	ret = ena_com_execute_admin_command(admin_queue,
@@ -1012,13 +1030,15 @@ static int ena_com_get_feature_ex(struct ena_com_dev *ena_dev,
 
 static int ena_com_get_feature(struct ena_com_dev *ena_dev,
 			       struct ena_admin_get_feat_resp *get_resp,
-			       enum ena_admin_aq_feature_id feature_id)
+			       enum ena_admin_aq_feature_id feature_id,
+			       u8 feature_ver)
 {
 	return ena_com_get_feature_ex(ena_dev,
 				      get_resp,
 				      feature_id,
 				      0,
-				      0);
+				      0,
+				      feature_ver);
 }
 
 static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev)
@@ -1078,7 +1098,7 @@ static int ena_com_indirect_table_allocate(struct ena_com_dev *ena_dev,
 	int ret;
 
 	ret = ena_com_get_feature(ena_dev, &get_resp,
-				  ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG);
+				  ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG, 0);
 	if (unlikely(ret))
 		return ret;
 
@@ -1498,7 +1518,7 @@ int ena_com_set_aenq_config(struct ena_com_dev *ena_dev, u32 groups_flag)
 	struct ena_admin_get_feat_resp get_resp;
 	int ret;
 
-	ret = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_AENQ_CONFIG);
+	ret = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_AENQ_CONFIG, 0);
 	if (ret) {
 		pr_info("Can't get aenq configuration\n");
 		return ret;
@@ -1643,6 +1663,12 @@ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling)
 	ena_dev->admin_queue.polling = polling;
 }
 
+void ena_com_set_admin_auto_polling_mode(struct ena_com_dev *ena_dev,
+					 bool polling)
+{
+	ena_dev->admin_queue.auto_polling = polling;
+}
+
 int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev)
 {
 	struct ena_com_mmio_read *mmio_read = &ena_dev->mmio_read;
@@ -1867,7 +1893,7 @@ void ena_com_destroy_io_queue(struct ena_com_dev *ena_dev, u16 qid)
 int ena_com_get_link_params(struct ena_com_dev *ena_dev,
 			    struct ena_admin_get_feat_resp *resp)
 {
-	return ena_com_get_feature(ena_dev, resp, ENA_ADMIN_LINK_CONFIG);
+	return ena_com_get_feature(ena_dev, resp, ENA_ADMIN_LINK_CONFIG, 0);
 }
 
 int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
@@ -1877,7 +1903,7 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 	int rc;
 
 	rc = ena_com_get_feature(ena_dev, &get_resp,
-				 ENA_ADMIN_DEVICE_ATTRIBUTES);
+				 ENA_ADMIN_DEVICE_ATTRIBUTES, 0);
 	if (rc)
 		return rc;
 
@@ -1885,17 +1911,34 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 	       sizeof(get_resp.u.dev_attr));
 	ena_dev->supported_features = get_resp.u.dev_attr.supported_features;
 
-	rc = ena_com_get_feature(ena_dev, &get_resp,
-				 ENA_ADMIN_MAX_QUEUES_NUM);
-	if (rc)
-		return rc;
+	if (ena_dev->supported_features & BIT(ENA_ADMIN_MAX_QUEUES_EXT)) {
+		rc = ena_com_get_feature(ena_dev, &get_resp,
+					 ENA_ADMIN_MAX_QUEUES_EXT,
+					 ENA_FEATURE_MAX_QUEUE_EXT_VER);
+		if (rc)
+			return rc;
+
+		if (get_resp.u.max_queue_ext.version != ENA_FEATURE_MAX_QUEUE_EXT_VER)
+			return -EINVAL;
+
+		memcpy(&get_feat_ctx->max_queue_ext, &get_resp.u.max_queue_ext,
+		       sizeof(get_resp.u.max_queue_ext));
+		ena_dev->tx_max_header_size =
+			get_resp.u.max_queue_ext.max_queue_ext.max_tx_header_size;
+	} else {
+		rc = ena_com_get_feature(ena_dev, &get_resp,
+					 ENA_ADMIN_MAX_QUEUES_NUM, 0);
+		memcpy(&get_feat_ctx->max_queues, &get_resp.u.max_queue,
+		       sizeof(get_resp.u.max_queue));
+		ena_dev->tx_max_header_size =
+			get_resp.u.max_queue.max_header_size;
 
-	memcpy(&get_feat_ctx->max_queues, &get_resp.u.max_queue,
-	       sizeof(get_resp.u.max_queue));
-	ena_dev->tx_max_header_size = get_resp.u.max_queue.max_header_size;
+		if (rc)
+			return rc;
+	}
 
 	rc = ena_com_get_feature(ena_dev, &get_resp,
-				 ENA_ADMIN_AENQ_CONFIG);
+				 ENA_ADMIN_AENQ_CONFIG, 0);
 	if (rc)
 		return rc;
 
@@ -1903,7 +1946,7 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 	       sizeof(get_resp.u.aenq));
 
 	rc = ena_com_get_feature(ena_dev, &get_resp,
-				 ENA_ADMIN_STATELESS_OFFLOAD_CONFIG);
+				 ENA_ADMIN_STATELESS_OFFLOAD_CONFIG, 0);
 	if (rc)
 		return rc;
 
@@ -1913,7 +1956,7 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 	/* Driver hints isn't mandatory admin command. So in case the
 	 * command isn't supported set driver hints to 0
 	 */
-	rc = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_HW_HINTS);
+	rc = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_HW_HINTS, 0);
 
 	if (!rc)
 		memcpy(&get_feat_ctx->hw_hints, &get_resp.u.hw_hints,
@@ -1924,7 +1967,7 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 	else
 		return rc;
 
-	rc = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_LLQ);
+	rc = ena_com_get_feature(ena_dev, &get_resp, ENA_ADMIN_LLQ, 0);
 	if (!rc)
 		memcpy(&get_feat_ctx->llq, &get_resp.u.llq,
 		       sizeof(get_resp.u.llq));
@@ -2016,7 +2059,6 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data)
 	mb();
 	writel_relaxed((u32)aenq->head,
 		       dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF);
-	mmiowb();
 }
 
 int ena_com_dev_reset(struct ena_com_dev *ena_dev,
@@ -2162,7 +2204,7 @@ int ena_com_get_offload_settings(struct ena_com_dev *ena_dev,
 	struct ena_admin_get_feat_resp resp;
 
 	ret = ena_com_get_feature(ena_dev, &resp,
-				  ENA_ADMIN_STATELESS_OFFLOAD_CONFIG);
+				  ENA_ADMIN_STATELESS_OFFLOAD_CONFIG, 0);
 	if (unlikely(ret)) {
 		pr_err("Failed to get offload capabilities %d\n", ret);
 		return ret;
@@ -2191,11 +2233,11 @@ int ena_com_set_hash_function(struct ena_com_dev *ena_dev)
 
 	/* Validate hash function is supported */
 	ret = ena_com_get_feature(ena_dev, &get_resp,
-				  ENA_ADMIN_RSS_HASH_FUNCTION);
+				  ENA_ADMIN_RSS_HASH_FUNCTION, 0);
 	if (unlikely(ret))
 		return ret;
 
-	if (get_resp.u.flow_hash_func.supported_func & (1 << rss->hash_func)) {
+	if (!(get_resp.u.flow_hash_func.supported_func & BIT(rss->hash_func))) {
 		pr_err("Func hash %d isn't supported by device, abort\n",
 		       rss->hash_func);
 		return -EOPNOTSUPP;
@@ -2251,7 +2293,7 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
 				    ENA_ADMIN_RSS_HASH_FUNCTION,
 				    rss->hash_key_dma_addr,
-				    sizeof(*rss->hash_key));
+				    sizeof(*rss->hash_key), 0);
 	if (unlikely(rc))
 		return rc;
 
@@ -2280,6 +2322,7 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
 		return -EINVAL;
 	}
 
+	rss->hash_func = func;
 	rc = ena_com_set_hash_function(ena_dev);
 
 	/* Restore the old function */
@@ -2302,7 +2345,7 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
 	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
 				    ENA_ADMIN_RSS_HASH_FUNCTION,
 				    rss->hash_key_dma_addr,
-				    sizeof(*rss->hash_key));
+				    sizeof(*rss->hash_key), 0);
 	if (unlikely(rc))
 		return rc;
 
@@ -2327,7 +2370,7 @@ int ena_com_get_hash_ctrl(struct ena_com_dev *ena_dev,
 	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
 				    ENA_ADMIN_RSS_HASH_INPUT,
 				    rss->hash_ctrl_dma_addr,
-				    sizeof(*rss->hash_ctrl));
+				    sizeof(*rss->hash_ctrl), 0);
 	if (unlikely(rc))
 		return rc;
 
@@ -2563,7 +2606,7 @@ int ena_com_indirect_table_get(struct ena_com_dev *ena_dev, u32 *ind_tbl)
 	rc = ena_com_get_feature_ex(ena_dev, &get_resp,
 				    ENA_ADMIN_RSS_REDIRECTION_TABLE_CONFIG,
 				    rss->rss_ind_tbl_dma_addr,
-				    tbl_size);
+				    tbl_size, 0);
 	if (unlikely(rc))
 		return rc;
 
@@ -2778,7 +2821,7 @@ int ena_com_init_interrupt_moderation(struct ena_com_dev *ena_dev)
 	int rc;
 
 	rc = ena_com_get_feature(ena_dev, &get_resp,
-				 ENA_ADMIN_INTERRUPT_MODERATION);
+				 ENA_ADMIN_INTERRUPT_MODERATION, 0);
 
 	if (rc) {
 		if (rc == -EOPNOTSUPP) {
@@ -2802,7 +2845,11 @@ int ena_com_init_interrupt_moderation(struct ena_com_dev *ena_dev)
 	/* if moderation is supported by device we set adaptive moderation */
 	delay_resolution = get_resp.u.intr_moderation.intr_delay_resolution;
 	ena_com_update_intr_delay_resolution(ena_dev, delay_resolution);
-	ena_com_enable_adaptive_moderation(ena_dev);
+
+	/* Disable adaptive moderation by default - can be enabled from
+	 * ethtool
+	 */
+	ena_com_disable_adaptive_moderation(ena_dev);
 
 	return 0;
 err:
@@ -2909,8 +2956,8 @@ int ena_com_config_dev_mode(struct ena_com_dev *ena_dev,
 			    struct ena_admin_feature_llq_desc *llq_features,
 			    struct ena_llq_configurations *llq_default_cfg)
 {
+	struct ena_com_llq_info *llq_info = &ena_dev->llq_info;
 	int rc;
-	int size;
 
 	if (!llq_features->max_llq_num) {
 		ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
@@ -2921,12 +2968,10 @@ int ena_com_config_dev_mode(struct ena_com_dev *ena_dev,
 	if (rc)
 		return rc;
 
-	/* Validate the descriptor is not too big */
-	size = ena_dev->tx_max_header_size;
-	size += ena_dev->llq_info.descs_num_before_header *
-		sizeof(struct ena_eth_io_tx_desc);
+	ena_dev->tx_max_header_size = llq_info->desc_list_entry_size -
+		(llq_info->descs_num_before_header * sizeof(struct ena_eth_io_tx_desc));
 
-	if (unlikely(ena_dev->llq_info.desc_list_entry_size < size)) {
+	if (unlikely(ena_dev->tx_max_header_size == 0)) {
 		pr_err("the size of the LLQ entry is smaller than needed\n");
 		return -EINVAL;
 	}
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 078d6f2b4f39..0d3664fe260d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -101,6 +101,8 @@
 
 #define ENA_HW_HINTS_NO_TIMEOUT				0xFFFF
 
+#define ENA_FEATURE_MAX_QUEUE_EXT_VER	1
+
 enum ena_intr_moder_level {
 	ENA_INTR_MODER_LOWEST = 0,
 	ENA_INTR_MODER_LOW,
@@ -159,6 +161,7 @@ struct ena_com_llq_info {
 	u16 desc_list_entry_size;
 	u16 descs_num_before_header;
 	u16 descs_per_entry;
+	u16 max_entries_in_tx_burst;
 };
 
 struct ena_com_io_cq {
@@ -238,6 +241,7 @@ struct ena_com_io_sq {
 	u8 phase;
 	u8 desc_entry_size;
 	u8 dma_addr_bits;
+	u16 entries_in_tx_burst_left;
 } ____cacheline_aligned;
 
 struct ena_com_admin_cq {
@@ -281,6 +285,9 @@ struct ena_com_admin_queue {
 	/* Indicate if the admin queue should poll for completion */
 	bool polling;
 
+	/* Define if fallback to polling mode should occur */
+	bool auto_polling;
+
 	u16 curr_cmd_id;
 
 	/* Indicate that the ena was initialized and can
@@ -377,6 +384,7 @@ struct ena_com_dev {
 
 struct ena_com_dev_get_features_ctx {
 	struct ena_admin_queue_feature_desc max_queues;
+	struct ena_admin_queue_ext_feature_desc max_queue_ext;
 	struct ena_admin_device_attr_feature_desc dev_attr;
 	struct ena_admin_feature_aenq_desc aenq;
 	struct ena_admin_feature_offload_desc offload;
@@ -536,6 +544,17 @@ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling);
  */
 bool ena_com_get_ena_admin_polling_mode(struct ena_com_dev *ena_dev);
 
+/* ena_com_set_admin_auto_polling_mode - Enable autoswitch to polling mode
+ * @ena_dev: ENA communication layer struct
+ * @polling: Enable/Disable polling mode
+ *
+ * Set the autopolling mode.
+ * If autopolling is on:
+ * In case of missing interrupt when data is available switch to polling.
+ */
+void ena_com_set_admin_auto_polling_mode(struct ena_com_dev *ena_dev,
+					 bool polling);
+
 /* ena_com_admin_q_comp_intr_handler - admin queue interrupt handler
  * @ena_dev: ENA communication layer struct
  *
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
index f6c2d3855be8..38046bf0ff44 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c
@@ -32,7 +32,7 @@
 
 #include "ena_eth_com.h"
 
-static inline struct ena_eth_io_rx_cdesc_base *ena_com_get_next_rx_cdesc(
+static struct ena_eth_io_rx_cdesc_base *ena_com_get_next_rx_cdesc(
 	struct ena_com_io_cq *io_cq)
 {
 	struct ena_eth_io_rx_cdesc_base *cdesc;
@@ -59,7 +59,7 @@ static inline struct ena_eth_io_rx_cdesc_base *ena_com_get_next_rx_cdesc(
 	return cdesc;
 }
 
-static inline void *get_sq_desc_regular_queue(struct ena_com_io_sq *io_sq)
+static void *get_sq_desc_regular_queue(struct ena_com_io_sq *io_sq)
 {
 	u16 tail_masked;
 	u32 offset;
@@ -71,7 +71,7 @@ static inline void *get_sq_desc_regular_queue(struct ena_com_io_sq *io_sq)
 	return (void *)((uintptr_t)io_sq->desc_addr.virt_addr + offset);
 }
 
-static inline int ena_com_write_bounce_buffer_to_dev(struct ena_com_io_sq *io_sq,
+static int ena_com_write_bounce_buffer_to_dev(struct ena_com_io_sq *io_sq,
 						     u8 *bounce_buffer)
 {
 	struct ena_com_llq_info *llq_info = &io_sq->llq_info;
@@ -82,6 +82,17 @@ static inline int ena_com_write_bounce_buffer_to_dev(struct ena_com_io_sq *io_sq
 	dst_tail_mask = io_sq->tail & (io_sq->q_depth - 1);
 	dst_offset = dst_tail_mask * llq_info->desc_list_entry_size;
 
+	if (is_llq_max_tx_burst_exists(io_sq)) {
+		if (unlikely(!io_sq->entries_in_tx_burst_left)) {
+			pr_err("Error: trying to send more packets than tx burst allows\n");
+			return -ENOSPC;
+		}
+
+		io_sq->entries_in_tx_burst_left--;
+		pr_debug("decreasing entries_in_tx_burst_left of queue %d to %d\n",
+			 io_sq->qid, io_sq->entries_in_tx_burst_left);
+	}
+
 	/* Make sure everything was written into the bounce buffer before
 	 * writing the bounce buffer to the device
 	 */
@@ -100,7 +111,7 @@ static inline int ena_com_write_bounce_buffer_to_dev(struct ena_com_io_sq *io_sq
 	return 0;
 }
 
-static inline int ena_com_write_header_to_bounce(struct ena_com_io_sq *io_sq,
+static int ena_com_write_header_to_bounce(struct ena_com_io_sq *io_sq,
 						 u8 *header_src,
 						 u16 header_len)
 {
@@ -131,7 +142,7 @@ static inline int ena_com_write_header_to_bounce(struct ena_com_io_sq *io_sq,
 	return 0;
 }
 
-static inline void *get_sq_desc_llq(struct ena_com_io_sq *io_sq)
+static void *get_sq_desc_llq(struct ena_com_io_sq *io_sq)
 {
 	struct ena_com_llq_pkt_ctrl *pkt_ctrl = &io_sq->llq_buf_ctrl;
 	u8 *bounce_buffer;
@@ -151,7 +162,7 @@ static inline void *get_sq_desc_llq(struct ena_com_io_sq *io_sq)
 	return sq_desc;
 }
 
-static inline int ena_com_close_bounce_buffer(struct ena_com_io_sq *io_sq)
+static int ena_com_close_bounce_buffer(struct ena_com_io_sq *io_sq)
 {
 	struct ena_com_llq_pkt_ctrl *pkt_ctrl = &io_sq->llq_buf_ctrl;
 	struct ena_com_llq_info *llq_info = &io_sq->llq_info;
@@ -178,7 +189,7 @@ static inline int ena_com_close_bounce_buffer(struct ena_com_io_sq *io_sq)
 	return 0;
 }
 
-static inline void *get_sq_desc(struct ena_com_io_sq *io_sq)
+static void *get_sq_desc(struct ena_com_io_sq *io_sq)
 {
 	if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV)
 		return get_sq_desc_llq(io_sq);
@@ -186,7 +197,7 @@ static inline void *get_sq_desc(struct ena_com_io_sq *io_sq)
 	return get_sq_desc_regular_queue(io_sq);
 }
 
-static inline int ena_com_sq_update_llq_tail(struct ena_com_io_sq *io_sq)
+static int ena_com_sq_update_llq_tail(struct ena_com_io_sq *io_sq)
 {
 	struct ena_com_llq_pkt_ctrl *pkt_ctrl = &io_sq->llq_buf_ctrl;
 	struct ena_com_llq_info *llq_info = &io_sq->llq_info;
@@ -214,7 +225,7 @@ static inline int ena_com_sq_update_llq_tail(struct ena_com_io_sq *io_sq)
 	return 0;
 }
 
-static inline int ena_com_sq_update_tail(struct ena_com_io_sq *io_sq)
+static int ena_com_sq_update_tail(struct ena_com_io_sq *io_sq)
 {
 	if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV)
 		return ena_com_sq_update_llq_tail(io_sq);
@@ -228,7 +239,7 @@ static inline int ena_com_sq_update_tail(struct ena_com_io_sq *io_sq)
 	return 0;
 }
 
-static inline struct ena_eth_io_rx_cdesc_base *
+static struct ena_eth_io_rx_cdesc_base *
 	ena_com_rx_cdesc_idx_to_ptr(struct ena_com_io_cq *io_cq, u16 idx)
 {
 	idx &= (io_cq->q_depth - 1);
@@ -237,7 +248,7 @@ static inline struct ena_eth_io_rx_cdesc_base *
 		idx * io_cq->cdesc_entry_size_in_bytes);
 }
 
-static inline u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
+static u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
 					   u16 *first_cdesc_idx)
 {
 	struct ena_eth_io_rx_cdesc_base *cdesc;
@@ -274,24 +285,7 @@ static inline u16 ena_com_cdesc_rx_pkt_get(struct ena_com_io_cq *io_cq,
 	return count;
 }
 
-static inline bool ena_com_meta_desc_changed(struct ena_com_io_sq *io_sq,
-					     struct ena_com_tx_ctx *ena_tx_ctx)
-{
-	int rc;
-
-	if (ena_tx_ctx->meta_valid) {
-		rc = memcmp(&io_sq->cached_tx_meta,
-			    &ena_tx_ctx->ena_meta,
-			    sizeof(struct ena_com_tx_meta));
-
-		if (unlikely(rc != 0))
-			return true;
-	}
-
-	return false;
-}
-
-static inline int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq,
+static int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq,
 							struct ena_com_tx_ctx *ena_tx_ctx)
 {
 	struct ena_eth_io_tx_meta_desc *meta_desc = NULL;
@@ -340,7 +334,7 @@ static inline int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io
 	return ena_com_sq_update_tail(io_sq);
 }
 
-static inline void ena_com_rx_set_flags(struct ena_com_rx_ctx *ena_rx_ctx,
+static void ena_com_rx_set_flags(struct ena_com_rx_ctx *ena_rx_ctx,
 					struct ena_eth_io_rx_cdesc_base *cdesc)
 {
 	ena_rx_ctx->l3_proto = cdesc->status &
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
index 340d02b64ca6..77986c0ea52c 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
@@ -125,8 +125,55 @@ static inline bool ena_com_sq_have_enough_space(struct ena_com_io_sq *io_sq,
 	return ena_com_free_desc(io_sq) > temp;
 }
 
+static inline bool ena_com_meta_desc_changed(struct ena_com_io_sq *io_sq,
+					     struct ena_com_tx_ctx *ena_tx_ctx)
+{
+	if (!ena_tx_ctx->meta_valid)
+		return false;
+
+	return !!memcmp(&io_sq->cached_tx_meta,
+			&ena_tx_ctx->ena_meta,
+			sizeof(struct ena_com_tx_meta));
+}
+
+static inline bool is_llq_max_tx_burst_exists(struct ena_com_io_sq *io_sq)
+{
+	return (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) &&
+	       io_sq->llq_info.max_entries_in_tx_burst > 0;
+}
+
+static inline bool ena_com_is_doorbell_needed(struct ena_com_io_sq *io_sq,
+					      struct ena_com_tx_ctx *ena_tx_ctx)
+{
+	struct ena_com_llq_info *llq_info;
+	int descs_after_first_entry;
+	int num_entries_needed = 1;
+	u16 num_descs;
+
+	if (!is_llq_max_tx_burst_exists(io_sq))
+		return false;
+
+	llq_info = &io_sq->llq_info;
+	num_descs = ena_tx_ctx->num_bufs;
+
+	if (unlikely(ena_com_meta_desc_changed(io_sq, ena_tx_ctx)))
+		++num_descs;
+
+	if (num_descs > llq_info->descs_num_before_header) {
+		descs_after_first_entry = num_descs - llq_info->descs_num_before_header;
+		num_entries_needed += DIV_ROUND_UP(descs_after_first_entry,
+						   llq_info->descs_per_entry);
+	}
+
+	pr_debug("queue: %d num_descs: %d num_entries_needed: %d\n", io_sq->qid,
+		 num_descs, num_entries_needed);
+
+	return num_entries_needed > io_sq->entries_in_tx_burst_left;
+}
+
 static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq)
 {
+	u16 max_entries_in_tx_burst = io_sq->llq_info.max_entries_in_tx_burst;
 	u16 tail = io_sq->tail;
 
 	pr_debug("write submission queue doorbell for queue: %d tail: %d\n",
@@ -134,6 +181,12 @@ static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq)
 
 	writel(tail, io_sq->db_addr);
 
+	if (is_llq_max_tx_burst_exists(io_sq)) {
+		pr_debug("reset available entries in tx burst for queue %d to %d\n",
+			 io_sq->qid, max_entries_in_tx_burst);
+		io_sq->entries_in_tx_burst_left = max_entries_in_tx_burst;
+	}
+
 	return 0;
 }
 
@@ -142,15 +195,17 @@ static inline int ena_com_update_dev_comp_head(struct ena_com_io_cq *io_cq)
 	u16 unreported_comp, head;
 	bool need_update;
 
-	head = io_cq->head;
-	unreported_comp = head - io_cq->last_head_update;
-	need_update = unreported_comp > (io_cq->q_depth / ENA_COMP_HEAD_THRESH);
-
-	if (io_cq->cq_head_db_reg && need_update) {
-		pr_debug("Write completion queue doorbell for queue %d: head: %d\n",
-			 io_cq->qid, head);
-		writel(head, io_cq->cq_head_db_reg);
-		io_cq->last_head_update = head;
+	if (unlikely(io_cq->cq_head_db_reg)) {
+		head = io_cq->head;
+		unreported_comp = head - io_cq->last_head_update;
+		need_update = unreported_comp > (io_cq->q_depth / ENA_COMP_HEAD_THRESH);
+
+		if (unlikely(need_update)) {
+			pr_debug("Write completion queue doorbell for queue %d: head: %d\n",
+				 io_cq->qid, head);
+			writel(head, io_cq->cq_head_db_reg);
+			io_cq->last_head_update = head;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index f3a5a384e6e8..b997c3ce9e2b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -88,13 +88,14 @@ static const struct ena_stats ena_stats_tx_strings[] = {
 static const struct ena_stats ena_stats_rx_strings[] = {
 	ENA_STAT_RX_ENTRY(cnt),
 	ENA_STAT_RX_ENTRY(bytes),
+	ENA_STAT_RX_ENTRY(rx_copybreak_pkt),
+	ENA_STAT_RX_ENTRY(csum_good),
 	ENA_STAT_RX_ENTRY(refil_partial),
 	ENA_STAT_RX_ENTRY(bad_csum),
 	ENA_STAT_RX_ENTRY(page_alloc_fail),
 	ENA_STAT_RX_ENTRY(skb_alloc_fail),
 	ENA_STAT_RX_ENTRY(dma_mapping_err),
 	ENA_STAT_RX_ENTRY(bad_desc_num),
-	ENA_STAT_RX_ENTRY(rx_copybreak_pkt),
 	ENA_STAT_RX_ENTRY(bad_req_id),
 	ENA_STAT_RX_ENTRY(empty_rx_ring),
 	ENA_STAT_RX_ENTRY(csum_unchecked),
@@ -447,13 +448,32 @@ static void ena_get_ringparam(struct net_device *netdev,
 			      struct ethtool_ringparam *ring)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
-	struct ena_ring *tx_ring = &adapter->tx_ring[0];
-	struct ena_ring *rx_ring = &adapter->rx_ring[0];
 
-	ring->rx_max_pending = rx_ring->ring_size;
-	ring->tx_max_pending = tx_ring->ring_size;
-	ring->rx_pending = rx_ring->ring_size;
-	ring->tx_pending = tx_ring->ring_size;
+	ring->tx_max_pending = adapter->max_tx_ring_size;
+	ring->rx_max_pending = adapter->max_rx_ring_size;
+	ring->tx_pending = adapter->tx_ring[0].ring_size;
+	ring->rx_pending = adapter->rx_ring[0].ring_size;
+}
+
+static int ena_set_ringparam(struct net_device *netdev,
+			     struct ethtool_ringparam *ring)
+{
+	struct ena_adapter *adapter = netdev_priv(netdev);
+	u32 new_tx_size, new_rx_size;
+
+	new_tx_size = ring->tx_pending < ENA_MIN_RING_SIZE ?
+			ENA_MIN_RING_SIZE : ring->tx_pending;
+	new_tx_size = rounddown_pow_of_two(new_tx_size);
+
+	new_rx_size = ring->rx_pending < ENA_MIN_RING_SIZE ?
+			ENA_MIN_RING_SIZE : ring->rx_pending;
+	new_rx_size = rounddown_pow_of_two(new_rx_size);
+
+	if (new_tx_size == adapter->requested_tx_ring_size &&
+	    new_rx_size == adapter->requested_rx_ring_size)
+		return 0;
+
+	return ena_update_queue_sizes(adapter, new_tx_size, new_rx_size);
 }
 
 static u32 ena_flow_hash_to_flow_type(u16 hash_fields)
@@ -697,8 +717,8 @@ static int ena_set_rxfh(struct net_device *netdev, const u32 *indir,
 	if (indir) {
 		for (i = 0; i < ENA_RX_RSS_TABLE_SIZE; i++) {
 			rc = ena_com_indirect_table_fill_entry(ena_dev,
-							       ENA_IO_RXQ_IDX(indir[i]),
-							       i);
+							       i,
+							       ENA_IO_RXQ_IDX(indir[i]));
 			if (unlikely(rc)) {
 				netif_err(adapter, drv, netdev,
 					  "Cannot fill indirect table (index is too large)\n");
@@ -807,6 +827,7 @@ static const struct ethtool_ops ena_ethtool_ops = {
 	.get_coalesce		= ena_get_coalesce,
 	.set_coalesce		= ena_set_coalesce,
 	.get_ringparam		= ena_get_ringparam,
+	.set_ringparam		= ena_set_ringparam,
 	.get_sset_count         = ena_get_sset_count,
 	.get_strings		= ena_get_strings,
 	.get_ethtool_stats      = ena_get_ethtool_stats,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index a70bb1bb90e7..664e3ed97ea9 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -182,7 +182,7 @@ static void ena_init_io_rings(struct ena_adapter *adapter)
 		ena_init_io_rings_common(adapter, rxr, i);
 
 		/* TX specific ring state */
-		txr->ring_size = adapter->tx_ring_size;
+		txr->ring_size = adapter->requested_tx_ring_size;
 		txr->tx_max_header_size = ena_dev->tx_max_header_size;
 		txr->tx_mem_queue_type = ena_dev->tx_mem_queue_type;
 		txr->sgl_size = adapter->max_tx_sgl_size;
@@ -190,7 +190,7 @@ static void ena_init_io_rings(struct ena_adapter *adapter)
 			ena_com_get_nonadaptive_moderation_interval_tx(ena_dev);
 
 		/* RX specific ring state */
-		rxr->ring_size = adapter->rx_ring_size;
+		rxr->ring_size = adapter->requested_rx_ring_size;
 		rxr->rx_copybreak = adapter->rx_copybreak;
 		rxr->sgl_size = adapter->max_rx_sgl_size;
 		rxr->smoothed_interval =
@@ -224,33 +224,28 @@ static int ena_setup_tx_resources(struct ena_adapter *adapter, int qid)
 	if (!tx_ring->tx_buffer_info) {
 		tx_ring->tx_buffer_info = vzalloc(size);
 		if (!tx_ring->tx_buffer_info)
-			return -ENOMEM;
+			goto err_tx_buffer_info;
 	}
 
 	size = sizeof(u16) * tx_ring->ring_size;
-	tx_ring->free_tx_ids = vzalloc_node(size, node);
-	if (!tx_ring->free_tx_ids) {
-		tx_ring->free_tx_ids = vzalloc(size);
-		if (!tx_ring->free_tx_ids) {
-			vfree(tx_ring->tx_buffer_info);
-			return -ENOMEM;
-		}
+	tx_ring->free_ids = vzalloc_node(size, node);
+	if (!tx_ring->free_ids) {
+		tx_ring->free_ids = vzalloc(size);
+		if (!tx_ring->free_ids)
+			goto err_tx_free_ids;
 	}
 
 	size = tx_ring->tx_max_header_size;
 	tx_ring->push_buf_intermediate_buf = vzalloc_node(size, node);
 	if (!tx_ring->push_buf_intermediate_buf) {
 		tx_ring->push_buf_intermediate_buf = vzalloc(size);
-		if (!tx_ring->push_buf_intermediate_buf) {
-			vfree(tx_ring->tx_buffer_info);
-			vfree(tx_ring->free_tx_ids);
-			return -ENOMEM;
-		}
+		if (!tx_ring->push_buf_intermediate_buf)
+			goto err_push_buf_intermediate_buf;
 	}
 
 	/* Req id ring for TX out of order completions */
 	for (i = 0; i < tx_ring->ring_size; i++)
-		tx_ring->free_tx_ids[i] = i;
+		tx_ring->free_ids[i] = i;
 
 	/* Reset tx statistics */
 	memset(&tx_ring->tx_stats, 0x0, sizeof(tx_ring->tx_stats));
@@ -259,6 +254,15 @@ static int ena_setup_tx_resources(struct ena_adapter *adapter, int qid)
 	tx_ring->next_to_clean = 0;
 	tx_ring->cpu = ena_irq->cpu;
 	return 0;
+
+err_push_buf_intermediate_buf:
+	vfree(tx_ring->free_ids);
+	tx_ring->free_ids = NULL;
+err_tx_free_ids:
+	vfree(tx_ring->tx_buffer_info);
+	tx_ring->tx_buffer_info = NULL;
+err_tx_buffer_info:
+	return -ENOMEM;
 }
 
 /* ena_free_tx_resources - Free I/O Tx Resources per Queue
@@ -274,8 +278,8 @@ static void ena_free_tx_resources(struct ena_adapter *adapter, int qid)
 	vfree(tx_ring->tx_buffer_info);
 	tx_ring->tx_buffer_info = NULL;
 
-	vfree(tx_ring->free_tx_ids);
-	tx_ring->free_tx_ids = NULL;
+	vfree(tx_ring->free_ids);
+	tx_ring->free_ids = NULL;
 
 	vfree(tx_ring->push_buf_intermediate_buf);
 	tx_ring->push_buf_intermediate_buf = NULL;
@@ -322,7 +326,7 @@ static void ena_free_all_io_tx_resources(struct ena_adapter *adapter)
 		ena_free_tx_resources(adapter, i);
 }
 
-static inline int validate_rx_req_id(struct ena_ring *rx_ring, u16 req_id)
+static int validate_rx_req_id(struct ena_ring *rx_ring, u16 req_id)
 {
 	if (likely(req_id < rx_ring->ring_size))
 		return 0;
@@ -373,18 +377,19 @@ static int ena_setup_rx_resources(struct ena_adapter *adapter,
 	}
 
 	size = sizeof(u16) * rx_ring->ring_size;
-	rx_ring->free_rx_ids = vzalloc_node(size, node);
-	if (!rx_ring->free_rx_ids) {
-		rx_ring->free_rx_ids = vzalloc(size);
-		if (!rx_ring->free_rx_ids) {
+	rx_ring->free_ids = vzalloc_node(size, node);
+	if (!rx_ring->free_ids) {
+		rx_ring->free_ids = vzalloc(size);
+		if (!rx_ring->free_ids) {
 			vfree(rx_ring->rx_buffer_info);
+			rx_ring->rx_buffer_info = NULL;
 			return -ENOMEM;
 		}
 	}
 
 	/* Req id ring for receiving RX pkts out of order */
 	for (i = 0; i < rx_ring->ring_size; i++)
-		rx_ring->free_rx_ids[i] = i;
+		rx_ring->free_ids[i] = i;
 
 	/* Reset rx statistics */
 	memset(&rx_ring->rx_stats, 0x0, sizeof(rx_ring->rx_stats));
@@ -410,8 +415,8 @@ static void ena_free_rx_resources(struct ena_adapter *adapter,
 	vfree(rx_ring->rx_buffer_info);
 	rx_ring->rx_buffer_info = NULL;
 
-	vfree(rx_ring->free_rx_ids);
-	rx_ring->free_rx_ids = NULL;
+	vfree(rx_ring->free_ids);
+	rx_ring->free_ids = NULL;
 }
 
 /* ena_setup_all_rx_resources - allocate I/O Rx queues resources for all queues
@@ -455,7 +460,7 @@ static void ena_free_all_io_rx_resources(struct ena_adapter *adapter)
 		ena_free_rx_resources(adapter, i);
 }
 
-static inline int ena_alloc_rx_page(struct ena_ring *rx_ring,
+static int ena_alloc_rx_page(struct ena_ring *rx_ring,
 				    struct ena_rx_buffer *rx_info, gfp_t gfp)
 {
 	struct ena_com_buf *ena_buf;
@@ -526,7 +531,7 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num)
 	for (i = 0; i < num; i++) {
 		struct ena_rx_buffer *rx_info;
 
-		req_id = rx_ring->free_rx_ids[next_to_use];
+		req_id = rx_ring->free_ids[next_to_use];
 		rc = validate_rx_req_id(rx_ring, req_id);
 		if (unlikely(rc < 0))
 			break;
@@ -589,7 +594,6 @@ static void ena_free_rx_bufs(struct ena_adapter *adapter,
 
 /* ena_refill_all_rx_bufs - allocate all queues Rx buffers
  * @adapter: board private structure
- *
  */
 static void ena_refill_all_rx_bufs(struct ena_adapter *adapter)
 {
@@ -616,7 +620,7 @@ static void ena_free_all_rx_bufs(struct ena_adapter *adapter)
 		ena_free_rx_bufs(adapter, i);
 }
 
-static inline void ena_unmap_tx_skb(struct ena_ring *tx_ring,
+static void ena_unmap_tx_skb(struct ena_ring *tx_ring,
 				    struct ena_tx_buffer *tx_info)
 {
 	struct ena_com_buf *ena_buf;
@@ -792,7 +796,7 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget)
 		tx_pkts++;
 		total_done += tx_info->tx_descs;
 
-		tx_ring->free_tx_ids[next_to_clean] = req_id;
+		tx_ring->free_ids[next_to_clean] = req_id;
 		next_to_clean = ENA_TX_RING_IDX_NEXT(next_to_clean,
 						     tx_ring->ring_size);
 	}
@@ -906,7 +910,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 
 		skb_put(skb, len);
 		skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-		rx_ring->free_rx_ids[*next_to_clean] = req_id;
+		rx_ring->free_ids[*next_to_clean] = req_id;
 		*next_to_clean = ENA_RX_RING_IDX_ADD(*next_to_clean, descs,
 						     rx_ring->ring_size);
 		return skb;
@@ -930,7 +934,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 
 		rx_info->page = NULL;
 
-		rx_ring->free_rx_ids[*next_to_clean] = req_id;
+		rx_ring->free_ids[*next_to_clean] = req_id;
 		*next_to_clean =
 			ENA_RX_RING_IDX_NEXT(*next_to_clean,
 					     rx_ring->ring_size);
@@ -951,7 +955,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
  * @ena_rx_ctx: received packet context/metadata
  * @skb: skb currently being received and modified
  */
-static inline void ena_rx_checksum(struct ena_ring *rx_ring,
+static void ena_rx_checksum(struct ena_ring *rx_ring,
 				   struct ena_com_rx_ctx *ena_rx_ctx,
 				   struct sk_buff *skb)
 {
@@ -996,6 +1000,9 @@ static inline void ena_rx_checksum(struct ena_ring *rx_ring,
 
 		if (likely(ena_rx_ctx->l4_csum_checked)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			u64_stats_update_begin(&rx_ring->syncp);
+			rx_ring->rx_stats.csum_good++;
+			u64_stats_update_end(&rx_ring->syncp);
 		} else {
 			u64_stats_update_begin(&rx_ring->syncp);
 			rx_ring->rx_stats.csum_unchecked++;
@@ -1083,7 +1090,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 		/* exit if we failed to retrieve a buffer */
 		if (unlikely(!skb)) {
 			for (i = 0; i < ena_rx_ctx.descs; i++) {
-				rx_ring->free_tx_ids[next_to_clean] =
+				rx_ring->free_ids[next_to_clean] =
 					rx_ring->ena_bufs[i].req_id;
 				next_to_clean =
 					ENA_RX_RING_IDX_NEXT(next_to_clean,
@@ -1148,7 +1155,7 @@ error:
 	return 0;
 }
 
-inline void ena_adjust_intr_moderation(struct ena_ring *rx_ring,
+void ena_adjust_intr_moderation(struct ena_ring *rx_ring,
 				       struct ena_ring *tx_ring)
 {
 	/* We apply adaptive moderation on Rx path only.
@@ -1167,7 +1174,7 @@ inline void ena_adjust_intr_moderation(struct ena_ring *rx_ring,
 	rx_ring->per_napi_bytes = 0;
 }
 
-static inline void ena_unmask_interrupt(struct ena_ring *tx_ring,
+static void ena_unmask_interrupt(struct ena_ring *tx_ring,
 					struct ena_ring *rx_ring)
 {
 	struct ena_eth_io_intr_reg intr_reg;
@@ -1187,7 +1194,7 @@ static inline void ena_unmask_interrupt(struct ena_ring *tx_ring,
 	ena_com_unmask_intr(rx_ring->ena_com_io_cq, &intr_reg);
 }
 
-static inline void ena_update_ring_numa_node(struct ena_ring *tx_ring,
+static void ena_update_ring_numa_node(struct ena_ring *tx_ring,
 					     struct ena_ring *rx_ring)
 {
 	int cpu = get_cpu();
@@ -1630,7 +1637,7 @@ static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid)
 	ctx.qid = ena_qid;
 	ctx.mem_queue_type = ena_dev->tx_mem_queue_type;
 	ctx.msix_vector = msix_vector;
-	ctx.queue_size = adapter->tx_ring_size;
+	ctx.queue_size = tx_ring->ring_size;
 	ctx.numa_node = cpu_to_node(tx_ring->cpu);
 
 	rc = ena_com_create_io_queue(ena_dev, &ctx);
@@ -1697,7 +1704,7 @@ static int ena_create_io_rx_queue(struct ena_adapter *adapter, int qid)
 	ctx.direction = ENA_COM_IO_QUEUE_DIRECTION_RX;
 	ctx.mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
 	ctx.msix_vector = msix_vector;
-	ctx.queue_size = adapter->rx_ring_size;
+	ctx.queue_size = rx_ring->ring_size;
 	ctx.numa_node = cpu_to_node(rx_ring->cpu);
 
 	rc = ena_com_create_io_queue(ena_dev, &ctx);
@@ -1744,6 +1751,112 @@ create_err:
 	return rc;
 }
 
+static void set_io_rings_size(struct ena_adapter *adapter,
+				     int new_tx_size, int new_rx_size)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_queues; i++) {
+		adapter->tx_ring[i].ring_size = new_tx_size;
+		adapter->rx_ring[i].ring_size = new_rx_size;
+	}
+}
+
+/* This function allows queue allocation to backoff when the system is
+ * low on memory. If there is not enough memory to allocate io queues
+ * the driver will try to allocate smaller queues.
+ *
+ * The backoff algorithm is as follows:
+ *  1. Try to allocate TX and RX and if successful.
+ *  1.1. return success
+ *
+ *  2. Divide by 2 the size of the larger of RX and TX queues (or both if their size is the same).
+ *
+ *  3. If TX or RX is smaller than 256
+ *  3.1. return failure.
+ *  4. else
+ *  4.1. go back to 1.
+ */
+static int create_queues_with_size_backoff(struct ena_adapter *adapter)
+{
+	int rc, cur_rx_ring_size, cur_tx_ring_size;
+	int new_rx_ring_size, new_tx_ring_size;
+
+	/* current queue sizes might be set to smaller than the requested
+	 * ones due to past queue allocation failures.
+	 */
+	set_io_rings_size(adapter, adapter->requested_tx_ring_size,
+			  adapter->requested_rx_ring_size);
+
+	while (1) {
+		rc = ena_setup_all_tx_resources(adapter);
+		if (rc)
+			goto err_setup_tx;
+
+		rc = ena_create_all_io_tx_queues(adapter);
+		if (rc)
+			goto err_create_tx_queues;
+
+		rc = ena_setup_all_rx_resources(adapter);
+		if (rc)
+			goto err_setup_rx;
+
+		rc = ena_create_all_io_rx_queues(adapter);
+		if (rc)
+			goto err_create_rx_queues;
+
+		return 0;
+
+err_create_rx_queues:
+		ena_free_all_io_rx_resources(adapter);
+err_setup_rx:
+		ena_destroy_all_tx_queues(adapter);
+err_create_tx_queues:
+		ena_free_all_io_tx_resources(adapter);
+err_setup_tx:
+		if (rc != -ENOMEM) {
+			netif_err(adapter, ifup, adapter->netdev,
+				  "Queue creation failed with error code %d\n",
+				  rc);
+			return rc;
+		}
+
+		cur_tx_ring_size = adapter->tx_ring[0].ring_size;
+		cur_rx_ring_size = adapter->rx_ring[0].ring_size;
+
+		netif_err(adapter, ifup, adapter->netdev,
+			  "Not enough memory to create queues with sizes TX=%d, RX=%d\n",
+			  cur_tx_ring_size, cur_rx_ring_size);
+
+		new_tx_ring_size = cur_tx_ring_size;
+		new_rx_ring_size = cur_rx_ring_size;
+
+		/* Decrease the size of the larger queue, or
+		 * decrease both if they are the same size.
+		 */
+		if (cur_rx_ring_size <= cur_tx_ring_size)
+			new_tx_ring_size = cur_tx_ring_size / 2;
+		if (cur_rx_ring_size >= cur_tx_ring_size)
+			new_rx_ring_size = cur_rx_ring_size / 2;
+
+		if (new_tx_ring_size < ENA_MIN_RING_SIZE ||
+		    new_rx_ring_size < ENA_MIN_RING_SIZE) {
+			netif_err(adapter, ifup, adapter->netdev,
+				  "Queue creation failed with the smallest possible queue size of %d for both queues. Not retrying with smaller queues\n",
+				  ENA_MIN_RING_SIZE);
+			return rc;
+		}
+
+		netif_err(adapter, ifup, adapter->netdev,
+			  "Retrying queue creation with sizes TX=%d, RX=%d\n",
+			  new_tx_ring_size,
+			  new_rx_ring_size);
+
+		set_io_rings_size(adapter, new_tx_ring_size,
+				  new_rx_ring_size);
+	}
+}
+
 static int ena_up(struct ena_adapter *adapter)
 {
 	int rc, i;
@@ -1763,25 +1876,9 @@ static int ena_up(struct ena_adapter *adapter)
 	if (rc)
 		goto err_req_irq;
 
-	/* allocate transmit descriptors */
-	rc = ena_setup_all_tx_resources(adapter);
+	rc = create_queues_with_size_backoff(adapter);
 	if (rc)
-		goto err_setup_tx;
-
-	/* allocate receive descriptors */
-	rc = ena_setup_all_rx_resources(adapter);
-	if (rc)
-		goto err_setup_rx;
-
-	/* Create TX queues */
-	rc = ena_create_all_io_tx_queues(adapter);
-	if (rc)
-		goto err_create_tx_queues;
-
-	/* Create RX queues */
-	rc = ena_create_all_io_rx_queues(adapter);
-	if (rc)
-		goto err_create_rx_queues;
+		goto err_create_queues_with_backoff;
 
 	rc = ena_up_complete(adapter);
 	if (rc)
@@ -1810,16 +1907,14 @@ static int ena_up(struct ena_adapter *adapter)
 	return rc;
 
 err_up:
-	ena_destroy_all_rx_queues(adapter);
-err_create_rx_queues:
 	ena_destroy_all_tx_queues(adapter);
-err_create_tx_queues:
-	ena_free_all_io_rx_resources(adapter);
-err_setup_rx:
 	ena_free_all_io_tx_resources(adapter);
-err_setup_tx:
+	ena_destroy_all_rx_queues(adapter);
+	ena_free_all_io_rx_resources(adapter);
+err_create_queues_with_backoff:
 	ena_free_io_irq(adapter);
 err_req_irq:
+	ena_del_napi(adapter);
 
 	return rc;
 }
@@ -1936,6 +2031,20 @@ static int ena_close(struct net_device *netdev)
 	return 0;
 }
 
+int ena_update_queue_sizes(struct ena_adapter *adapter,
+			   u32 new_tx_size,
+			   u32 new_rx_size)
+{
+	bool dev_up;
+
+	dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
+	ena_close(adapter->netdev);
+	adapter->requested_tx_ring_size = new_tx_size;
+	adapter->requested_rx_ring_size = new_rx_size;
+	ena_init_io_rings(adapter);
+	return dev_up ? ena_up(adapter) : 0;
+}
+
 static void ena_tx_csum(struct ena_com_tx_ctx *ena_tx_ctx, struct sk_buff *skb)
 {
 	u32 mss = skb_shinfo(skb)->gso_size;
@@ -2146,7 +2255,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 
 	next_to_use = tx_ring->next_to_use;
-	req_id = tx_ring->free_tx_ids[next_to_use];
+	req_id = tx_ring->free_ids[next_to_use];
 	tx_info = &tx_ring->tx_buffer_info[req_id];
 	tx_info->num_of_bufs = 0;
 
@@ -2166,6 +2275,13 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* set flags and meta data */
 	ena_tx_csum(&ena_tx_ctx, skb);
 
+	if (unlikely(ena_com_is_doorbell_needed(tx_ring->ena_com_io_sq, &ena_tx_ctx))) {
+		netif_dbg(adapter, tx_queued, dev,
+			  "llq tx max burst size of queue %d achieved, writing doorbell to send burst\n",
+			  qid);
+		ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
+	}
+
 	/* prepare the packet's descriptors to dma engine */
 	rc = ena_com_prepare_tx(tx_ring->ena_com_io_sq, &ena_tx_ctx,
 				&nb_hw_desc);
@@ -2236,7 +2352,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	if (netif_xmit_stopped(txq) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txq) || !netdev_xmit_more()) {
 		/* trigger the dma engine. ena_com_write_sq_doorbell()
 		 * has a mb
 		 */
@@ -2258,8 +2374,7 @@ error_drop_packet:
 }
 
 static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev,
-			    select_queue_fallback_t fallback)
+			    struct net_device *sb_dev)
 {
 	u16 qid;
 	/* we suspect that this is good for in--kernel network services that
@@ -2269,7 +2384,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (skb_rx_queue_recorded(skb))
 		qid = skb_get_rx_queue(skb);
 	else
-		qid = fallback(dev, skb, NULL);
+		qid = netdev_pick_tx(dev, skb, NULL);
 
 	return qid;
 }
@@ -2292,7 +2407,7 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev,
 	host_info->bdf = (pdev->bus->number << 8) | pdev->devfn;
 	host_info->os_type = ENA_ADMIN_OS_LINUX;
 	host_info->kernel_ver = LINUX_VERSION_CODE;
-	strncpy(host_info->kernel_ver_str, utsname()->version,
+	strlcpy(host_info->kernel_ver_str, utsname()->version,
 		sizeof(host_info->kernel_ver_str) - 1);
 	host_info->os_dist = 0;
 	strncpy(host_info->os_dist_str, utsname()->release,
@@ -2442,13 +2557,6 @@ static int ena_device_validate_params(struct ena_adapter *adapter,
 		return -EINVAL;
 	}
 
-	if ((get_feat_ctx->max_queues.max_cq_num < adapter->num_queues) ||
-	    (get_feat_ctx->max_queues.max_sq_num < adapter->num_queues)) {
-		netif_err(adapter, drv, netdev,
-			  "Error, device doesn't support enough queues\n");
-		return -EINVAL;
-	}
-
 	if (get_feat_ctx->dev_attr.max_mtu < netdev->mtu) {
 		netif_err(adapter, drv, netdev,
 			  "Error, device max mtu is smaller than netdev MTU\n");
@@ -2663,11 +2771,6 @@ static int ena_restore_device(struct ena_adapter *adapter)
 		goto err_device_destroy;
 	}
 
-	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
-	/* Make sure we don't have a race with AENQ Links state handler */
-	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
-		netif_carrier_on(adapter->netdev);
-
 	rc = ena_enable_msix_and_set_admin_interrupts(adapter,
 						      adapter->num_queues);
 	if (rc) {
@@ -2684,6 +2787,11 @@ static int ena_restore_device(struct ena_adapter *adapter)
 	}
 
 	set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
+
+	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
+	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
+		netif_carrier_on(adapter->netdev);
+
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 	dev_err(&pdev->dev,
 		"Device reset completed successfully, Driver info: %s\n",
@@ -3022,18 +3130,32 @@ static int ena_calc_io_queue_num(struct pci_dev *pdev,
 				 struct ena_com_dev *ena_dev,
 				 struct ena_com_dev_get_features_ctx *get_feat_ctx)
 {
-	int io_sq_num, io_queue_num;
+	int io_tx_sq_num, io_tx_cq_num, io_rx_num, io_queue_num;
 
-	/* In case of LLQ use the llq number in the get feature cmd */
+	if (ena_dev->supported_features & BIT(ENA_ADMIN_MAX_QUEUES_EXT)) {
+		struct ena_admin_queue_ext_feature_fields *max_queue_ext =
+			&get_feat_ctx->max_queue_ext.max_queue_ext;
+		io_rx_num = min_t(int, max_queue_ext->max_rx_sq_num,
+				  max_queue_ext->max_rx_cq_num);
+
+		io_tx_sq_num = max_queue_ext->max_tx_sq_num;
+		io_tx_cq_num = max_queue_ext->max_tx_cq_num;
+	} else {
+		struct ena_admin_queue_feature_desc *max_queues =
+			&get_feat_ctx->max_queues;
+		io_tx_sq_num = max_queues->max_sq_num;
+		io_tx_cq_num = max_queues->max_cq_num;
+		io_rx_num = min_t(int, io_tx_sq_num, io_tx_cq_num);
+	}
+
+	/* In case of LLQ use the llq fields for the tx SQ/CQ */
 	if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV)
-		io_sq_num = get_feat_ctx->llq.max_llq_num;
-	else
-		io_sq_num = get_feat_ctx->max_queues.max_sq_num;
+		io_tx_sq_num = get_feat_ctx->llq.max_llq_num;
 
 	io_queue_num = min_t(int, num_online_cpus(), ENA_MAX_NUM_IO_QUEUES);
-	io_queue_num = min_t(int, io_queue_num, io_sq_num);
-	io_queue_num = min_t(int, io_queue_num,
-			     get_feat_ctx->max_queues.max_cq_num);
+	io_queue_num = min_t(int, io_queue_num, io_rx_num);
+	io_queue_num = min_t(int, io_queue_num, io_tx_sq_num);
+	io_queue_num = min_t(int, io_queue_num, io_tx_cq_num);
 	/* 1 IRQ for for mgmnt and 1 IRQs for each IO direction */
 	io_queue_num = min_t(int, io_queue_num, pci_msix_vec_count(pdev) - 1);
 	if (unlikely(!io_queue_num)) {
@@ -3207,7 +3329,7 @@ static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev)
 	pci_release_selected_regions(pdev, release_bars);
 }
 
-static inline void set_default_llq_configurations(struct ena_llq_configurations *llq_config)
+static void set_default_llq_configurations(struct ena_llq_configurations *llq_config)
 {
 	llq_config->llq_header_location = ENA_ADMIN_INLINE_HEADER;
 	llq_config->llq_ring_entry_size = ENA_ADMIN_LIST_ENTRY_SIZE_128B;
@@ -3216,36 +3338,70 @@ static inline void set_default_llq_configurations(struct ena_llq_configurations
 	llq_config->llq_ring_entry_size_value = 128;
 }
 
-static int ena_calc_queue_size(struct pci_dev *pdev,
-			       struct ena_com_dev *ena_dev,
-			       u16 *max_tx_sgl_size,
-			       u16 *max_rx_sgl_size,
-			       struct ena_com_dev_get_features_ctx *get_feat_ctx)
+static int ena_calc_queue_size(struct ena_calc_queue_size_ctx *ctx)
 {
-	u32 queue_size = ENA_DEFAULT_RING_SIZE;
+	struct ena_admin_feature_llq_desc *llq = &ctx->get_feat_ctx->llq;
+	struct ena_com_dev *ena_dev = ctx->ena_dev;
+	u32 tx_queue_size = ENA_DEFAULT_RING_SIZE;
+	u32 rx_queue_size = ENA_DEFAULT_RING_SIZE;
+	u32 max_tx_queue_size;
+	u32 max_rx_queue_size;
 
-	queue_size = min_t(u32, queue_size,
-			   get_feat_ctx->max_queues.max_cq_depth);
-	queue_size = min_t(u32, queue_size,
-			   get_feat_ctx->max_queues.max_sq_depth);
+	if (ctx->ena_dev->supported_features & BIT(ENA_ADMIN_MAX_QUEUES_EXT)) {
+		struct ena_admin_queue_ext_feature_fields *max_queue_ext =
+			&ctx->get_feat_ctx->max_queue_ext.max_queue_ext;
+		max_rx_queue_size = min_t(u32, max_queue_ext->max_rx_cq_depth,
+					  max_queue_ext->max_rx_sq_depth);
+		max_tx_queue_size = max_queue_ext->max_tx_cq_depth;
 
-	if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV)
-		queue_size = min_t(u32, queue_size,
-				   get_feat_ctx->llq.max_llq_depth);
+		if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV)
+			max_tx_queue_size = min_t(u32, max_tx_queue_size,
+						  llq->max_llq_depth);
+		else
+			max_tx_queue_size = min_t(u32, max_tx_queue_size,
+						  max_queue_ext->max_tx_sq_depth);
 
-	queue_size = rounddown_pow_of_two(queue_size);
+		ctx->max_tx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS,
+					     max_queue_ext->max_per_packet_tx_descs);
+		ctx->max_rx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS,
+					     max_queue_ext->max_per_packet_rx_descs);
+	} else {
+		struct ena_admin_queue_feature_desc *max_queues =
+			&ctx->get_feat_ctx->max_queues;
+		max_rx_queue_size = min_t(u32, max_queues->max_cq_depth,
+					  max_queues->max_sq_depth);
+		max_tx_queue_size = max_queues->max_cq_depth;
+
+		if (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV)
+			max_tx_queue_size = min_t(u32, max_tx_queue_size,
+						  llq->max_llq_depth);
+		else
+			max_tx_queue_size = min_t(u32, max_tx_queue_size,
+						  max_queues->max_sq_depth);
 
-	if (unlikely(!queue_size)) {
-		dev_err(&pdev->dev, "Invalid queue size\n");
-		return -EFAULT;
+		ctx->max_tx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS,
+					     max_queues->max_packet_tx_descs);
+		ctx->max_rx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS,
+					     max_queues->max_packet_rx_descs);
 	}
 
-	*max_tx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS,
-				 get_feat_ctx->max_queues.max_packet_tx_descs);
-	*max_rx_sgl_size = min_t(u16, ENA_PKT_MAX_BUFS,
-				 get_feat_ctx->max_queues.max_packet_rx_descs);
+	max_tx_queue_size = rounddown_pow_of_two(max_tx_queue_size);
+	max_rx_queue_size = rounddown_pow_of_two(max_rx_queue_size);
+
+	tx_queue_size = clamp_val(tx_queue_size, ENA_MIN_RING_SIZE,
+				  max_tx_queue_size);
+	rx_queue_size = clamp_val(rx_queue_size, ENA_MIN_RING_SIZE,
+				  max_rx_queue_size);
+
+	tx_queue_size = rounddown_pow_of_two(tx_queue_size);
+	rx_queue_size = rounddown_pow_of_two(rx_queue_size);
+
+	ctx->max_tx_queue_size = max_tx_queue_size;
+	ctx->max_rx_queue_size = max_rx_queue_size;
+	ctx->tx_queue_size = tx_queue_size;
+	ctx->rx_queue_size = rx_queue_size;
 
-	return queue_size;
+	return 0;
 }
 
 /* ena_probe - Device Initialization Routine
@@ -3261,23 +3417,19 @@ static int ena_calc_queue_size(struct pci_dev *pdev,
 static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct ena_com_dev_get_features_ctx get_feat_ctx;
-	static int version_printed;
-	struct net_device *netdev;
-	struct ena_adapter *adapter;
+	struct ena_calc_queue_size_ctx calc_queue_ctx = { 0 };
 	struct ena_llq_configurations llq_config;
 	struct ena_com_dev *ena_dev = NULL;
-	char *queue_type_str;
-	static int adapters_found;
+	struct ena_adapter *adapter;
 	int io_queue_num, bars, rc;
-	int queue_size;
-	u16 tx_sgl_size = 0;
-	u16 rx_sgl_size = 0;
+	struct net_device *netdev;
+	static int adapters_found;
+	char *queue_type_str;
 	bool wd_state;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
-	if (version_printed++ == 0)
-		dev_info(&pdev->dev, "%s", version);
+	dev_info_once(&pdev->dev, "%s", version);
 
 	rc = pci_enable_device_mem(pdev);
 	if (rc) {
@@ -3329,20 +3481,25 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_device_destroy;
 	}
 
+	calc_queue_ctx.ena_dev = ena_dev;
+	calc_queue_ctx.get_feat_ctx = &get_feat_ctx;
+	calc_queue_ctx.pdev = pdev;
+
 	/* initial Tx interrupt delay, Assumes 1 usec granularity.
 	* Updated during device initialization with the real granularity
 	*/
 	ena_dev->intr_moder_tx_interval = ENA_INTR_INITIAL_TX_INTERVAL_USECS;
 	io_queue_num = ena_calc_io_queue_num(pdev, ena_dev, &get_feat_ctx);
-	queue_size = ena_calc_queue_size(pdev, ena_dev, &tx_sgl_size,
-					 &rx_sgl_size, &get_feat_ctx);
-	if ((queue_size <= 0) || (io_queue_num <= 0)) {
+	rc = ena_calc_queue_size(&calc_queue_ctx);
+	if (rc || io_queue_num <= 0) {
 		rc = -EFAULT;
 		goto err_device_destroy;
 	}
 
-	dev_info(&pdev->dev, "creating %d io queues. queue size: %d. LLQ is %s\n",
-		 io_queue_num, queue_size,
+	dev_info(&pdev->dev, "creating %d io queues. rx queue size: %d tx queue size. %d LLQ is %s\n",
+		 io_queue_num,
+		 calc_queue_ctx.rx_queue_size,
+		 calc_queue_ctx.tx_queue_size,
 		 (ena_dev->tx_mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV) ?
 		 "ENABLED" : "DISABLED");
 
@@ -3368,11 +3525,12 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 	adapter->reset_reason = ENA_REGS_RESET_NORMAL;
 
-	adapter->tx_ring_size = queue_size;
-	adapter->rx_ring_size = queue_size;
-
-	adapter->max_tx_sgl_size = tx_sgl_size;
-	adapter->max_rx_sgl_size = rx_sgl_size;
+	adapter->requested_tx_ring_size = calc_queue_ctx.tx_queue_size;
+	adapter->requested_rx_ring_size = calc_queue_ctx.rx_queue_size;
+	adapter->max_tx_ring_size = calc_queue_ctx.max_tx_queue_size;
+	adapter->max_rx_ring_size = calc_queue_ctx.max_rx_queue_size;
+	adapter->max_tx_sgl_size = calc_queue_ctx.max_tx_sgl_size;
+	adapter->max_rx_sgl_size = calc_queue_ctx.max_rx_sgl_size;
 
 	adapter->num_queues = io_queue_num;
 	adapter->last_monitored_tx_qid = 0;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index dc8b6173d8d8..efbcffd22215 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -44,8 +44,8 @@
 #include "ena_eth_com.h"
 
 #define DRV_MODULE_VER_MAJOR	2
-#define DRV_MODULE_VER_MINOR	0
-#define DRV_MODULE_VER_SUBMINOR 2
+#define DRV_MODULE_VER_MINOR	1
+#define DRV_MODULE_VER_SUBMINOR 0
 
 #define DRV_MODULE_NAME		"ena"
 #ifndef DRV_MODULE_VERSION
@@ -79,6 +79,7 @@
 #define ENA_BAR_MASK (BIT(ENA_REG_BAR) | BIT(ENA_MEM_BAR))
 
 #define ENA_DEFAULT_RING_SIZE	(1024)
+#define ENA_MIN_RING_SIZE	(256)
 
 #define ENA_TX_WAKEUP_THRESH		(MAX_SKB_FRAGS + 2)
 #define ENA_DEFAULT_RX_COPYBREAK	(256 - NET_IP_ALIGN)
@@ -154,6 +155,18 @@ struct ena_napi {
 	u32 qid;
 };
 
+struct ena_calc_queue_size_ctx {
+	struct ena_com_dev_get_features_ctx *get_feat_ctx;
+	struct ena_com_dev *ena_dev;
+	struct pci_dev *pdev;
+	u16 tx_queue_size;
+	u16 rx_queue_size;
+	u16 max_tx_queue_size;
+	u16 max_rx_queue_size;
+	u16 max_tx_sgl_size;
+	u16 max_rx_sgl_size;
+};
+
 struct ena_tx_buffer {
 	struct sk_buff *skb;
 	/* num of ena desc for this specific skb
@@ -208,26 +221,24 @@ struct ena_stats_tx {
 struct ena_stats_rx {
 	u64 cnt;
 	u64 bytes;
+	u64 rx_copybreak_pkt;
+	u64 csum_good;
 	u64 refil_partial;
 	u64 bad_csum;
 	u64 page_alloc_fail;
 	u64 skb_alloc_fail;
 	u64 dma_mapping_err;
 	u64 bad_desc_num;
-	u64 rx_copybreak_pkt;
 	u64 bad_req_id;
 	u64 empty_rx_ring;
 	u64 csum_unchecked;
 };
 
 struct ena_ring {
-	union {
-		/* Holds the empty requests for TX/RX
-		 * out of order completions
-		 */
-		u16 *free_tx_ids;
-		u16 *free_rx_ids;
-	};
+	/* Holds the empty requests for TX/RX
+	 * out of order completions
+	 */
+	u16 *free_ids;
 
 	union {
 		struct ena_tx_buffer *tx_buffer_info;
@@ -321,8 +332,11 @@ struct ena_adapter {
 	u32 tx_usecs, rx_usecs; /* interrupt moderation */
 	u32 tx_frames, rx_frames; /* interrupt moderation */
 
-	u32 tx_ring_size;
-	u32 rx_ring_size;
+	u32 requested_tx_ring_size;
+	u32 requested_rx_ring_size;
+
+	u32 max_tx_ring_size;
+	u32 max_rx_ring_size;
 
 	u32 msg_enable;
 
@@ -372,6 +386,10 @@ void ena_dump_stats_to_dmesg(struct ena_adapter *adapter);
 
 void ena_dump_stats_to_buf(struct ena_adapter *adapter, u8 *buf);
 
+int ena_update_queue_sizes(struct ena_adapter *adapter,
+			   u32 new_tx_size,
+			   u32 new_rx_size);
+
 int ena_get_sset_count(struct net_device *netdev, int sset);
 
 #endif /* !(ENA_H) */
diff --git a/drivers/net/ethernet/amd/7990.c b/drivers/net/ethernet/amd/7990.c
index dc57f2759f44..ab30761003da 100644
--- a/drivers/net/ethernet/amd/7990.c
+++ b/drivers/net/ethernet/amd/7990.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * 7990.c -- LANCE ethernet IC generic routines.
  * This is an attempt to separate out the bits of various ethernet
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index 9e5cf5583c87..de4950d2022e 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # AMD network device configuration
 #
diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c
index 265039c57023..0842da492a64 100644
--- a/drivers/net/ethernet/amd/am79c961a.c
+++ b/drivers/net/ethernet/amd/am79c961a.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/drivers/net/ethernet/amd/am79c961a.c
  *
  *  by Russell King <rmk@arm.linux.org.uk> 1995-2001.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Derived from various things including skeleton.c
  *
  * This is a special driver for the am79c961A Lance chip used in the
diff --git a/drivers/net/ethernet/amd/am79c961a.h b/drivers/net/ethernet/amd/am79c961a.h
index fc5088c70731..73679e053ceb 100644
--- a/drivers/net/ethernet/amd/am79c961a.h
+++ b/drivers/net/ethernet/amd/am79c961a.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * linux/drivers/net/ethernet/amd/am79c961a.h
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef _LINUX_am79c961a_H
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index e548c0ae2e00..573e88fc8ede 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1,8 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 
 /* Advanced  Micro Devices Inc. AMD8111E Linux Network Driver
  * Copyright (C) 2004 Advanced Micro Devices
  *
- *
  * Copyright 2001,2002 Jeff Garzik <jgarzik@mandrakesoft.com> [ 8139cp.c,tg3.c ]
  * Copyright (C) 2001, 2002 David S. Miller (davem@redhat.com)[ tg3.c]
  * Copyright 1996-1999 Thomas Bogendoerfer [ pcnet32.c ]
@@ -12,19 +12,6 @@
  * Carsten Langgaard, carstenl@mips.com [ pcnet32.c ]
  * Copyright (C) 2000 MIPS Technologies, Inc.  All rights reserved.
  *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 Module Name:
 
@@ -435,7 +422,7 @@ static int amd8111e_restart(struct net_device *dev)
 	int i,reg_val;
 
 	/* stop the chip */
-	 writel(RUN, mmio + CMD0);
+	writel(RUN, mmio + CMD0);
 
 	if(amd8111e_init_ring(dev))
 		return -ENOMEM;
@@ -1720,7 +1707,7 @@ static void amd8111e_config_ipg(struct timer_list *t)
 		writew((u32)tmp_ipg, mmio + IPG);
 		writew((u32)(tmp_ipg - IFS1_DELTA), mmio + IFS1);
 	}
-	 mod_timer(&lp->ipg_data.ipg_timer, jiffies + IPG_CONVERGE_JIFFIES);
+	mod_timer(&lp->ipg_data.ipg_timer, jiffies + IPG_CONVERGE_JIFFIES);
 	return;
 
 }
diff --git a/drivers/net/ethernet/amd/amd8111e.h b/drivers/net/ethernet/amd/amd8111e.h
index 2a57b46fd6a6..493f154eccf4 100644
--- a/drivers/net/ethernet/amd/amd8111e.h
+++ b/drivers/net/ethernet/amd/amd8111e.h
@@ -1,19 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Advanced  Micro Devices Inc. AMD8111E Linux Network Driver
  * Copyright (C) 2003 Advanced Micro Devices
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 Module Name:
 
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index e833d1b3fe18..650d1bae5f56 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *
  * Alchemy Au1x00 ethernet driver
@@ -14,24 +15,6 @@
  *
  * Author: MontaVista Software, Inc.
  *		ppopov@mvista.com or source@mvista.com
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * ########################################################################
- *
- *
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
@@ -1167,7 +1150,7 @@ static int au1000_probe(struct platform_device *pdev)
 	/* Allocate the data buffers
 	 * Snooping works fine with eth on all au1xxx
 	 */
-	aup->vaddr = (u32)dma_alloc_attrs(NULL, MAX_BUF_SIZE *
+	aup->vaddr = (u32)dma_alloc_attrs(&pdev->dev, MAX_BUF_SIZE *
 					  (NUM_TX_BUFFS + NUM_RX_BUFFS),
 					  &aup->dma_addr, 0,
 					  DMA_ATTR_NON_CONSISTENT);
@@ -1349,7 +1332,7 @@ err_remap3:
 err_remap2:
 	iounmap(aup->mac);
 err_remap1:
-	dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
+	dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
 			(void *)aup->vaddr, aup->dma_addr,
 			DMA_ATTR_NON_CONSISTENT);
 err_vaddr:
@@ -1383,7 +1366,7 @@ static int au1000_remove(struct platform_device *pdev)
 		if (aup->tx_db_inuse[i])
 			au1000_ReleaseDB(aup, aup->tx_db_inuse[i]);
 
-	dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
+	dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
 			(void *)aup->vaddr, aup->dma_addr,
 			DMA_ATTR_NON_CONSISTENT);
 
diff --git a/drivers/net/ethernet/amd/au1000_eth.h b/drivers/net/ethernet/amd/au1000_eth.h
index 4c47c2377d74..e3a3ed29db61 100644
--- a/drivers/net/ethernet/amd/au1000_eth.h
+++ b/drivers/net/ethernet/amd/au1000_eth.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *
  * Alchemy Au1x00 ethernet driver include file
@@ -5,24 +6,6 @@
  * Author: Pete Popov <ppopov@mvista.com>
  *
  * Copyright 2001 MontaVista Software Inc.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * ########################################################################
- *
- *
  */
 
 
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 9f23703dd509..dac4a2fcad6a 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *    Lance ethernet driver for the MIPS processor based
  *      DECstation family
diff --git a/drivers/net/ethernet/amd/hplance.c b/drivers/net/ethernet/amd/hplance.c
index c3dbf1c8a269..1381a474063f 100644
--- a/drivers/net/ethernet/amd/hplance.c
+++ b/drivers/net/ethernet/amd/hplance.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* hplance.c  : the  Linux/hp300/lance ethernet driver
  *
  * Copyright (C) 05/1998 Peter Maydell <pmaydell@chiark.greenend.org.uk>
diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c
index b56d84c7df46..f90b454b1642 100644
--- a/drivers/net/ethernet/amd/lance.c
+++ b/drivers/net/ethernet/amd/lance.c
@@ -1084,7 +1084,7 @@ static irqreturn_t lance_interrupt(int irq, void *dev_id)
 				/* We must free the original skb if it's not a data-only copy
 				   in the bounce buffer. */
 				if (lp->tx_skbuff[entry]) {
-					dev_kfree_skb_irq(lp->tx_skbuff[entry]);
+					dev_consume_skb_irq(lp->tx_skbuff[entry]);
 					lp->tx_skbuff[entry] = NULL;
 				}
 				dirty_tx++;
diff --git a/drivers/net/ethernet/amd/mvme147.c b/drivers/net/ethernet/amd/mvme147.c
index 0a920448522f..72abd3f82249 100644
--- a/drivers/net/ethernet/amd/mvme147.c
+++ b/drivers/net/ethernet/amd/mvme147.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* mvme147.c  : the  Linux/mvme147/lance ethernet driver
  *
  * Copyright (C) 05/1998 Peter Maydell <pmaydell@chiark.greenend.org.uk>
diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c
index 8931ce6bab7b..87ff5d6d1b22 100644
--- a/drivers/net/ethernet/amd/ni65.c
+++ b/drivers/net/ethernet/amd/ni65.c
@@ -1028,7 +1028,7 @@ static void ni65_xmit_intr(struct net_device *dev,int csr0)
 
 #ifdef XMT_VIA_SKB
 		if(p->tmd_skb[p->tmdlast]) {
-			 dev_kfree_skb_irq(p->tmd_skb[p->tmdlast]);
+			 dev_consume_skb_irq(p->tmd_skb[p->tmdlast]);
 			 p->tmd_skb[p->tmdlast] = NULL;
 		}
 #endif
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index bd6589de93d9..ebcbf8ca4829 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* $Id: sunlance.c,v 1.112 2002/01/15 06:48:55 davem Exp $
  * lance.c: Linux/Sparc/Lance driver
  *
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 4666084eda16..d5fd49dd25f3 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1887,7 +1887,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 	smp_wmb();
 
 	ring->cur = cur_index + 1;
-	if (!packet->skb->xmit_more ||
+	if (!netdev_xmit_more() ||
 	    netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
 						   channel->queue_index)))
 		xgbe_tx_start_xmit(channel, ring);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 0cc911f928b1..3dd0cecddba8 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1612,7 +1612,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
 	/* PTP v2, UDP, any kind of event packet */
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-	/* PTP v1, UDP, any kind of event packet */
+		/* Fall through - to PTP v1, UDP, any kind of event packet */
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
@@ -1623,7 +1623,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
 	/* PTP v2, UDP, Sync packet */
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-	/* PTP v1, UDP, Sync packet */
+		/* Fall through - to PTP v1, UDP, Sync packet */
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
@@ -1634,7 +1634,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
 	/* PTP v2, UDP, Delay_req packet */
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1);
-	/* PTP v1, UDP, Delay_req packet */
+		/* Fall through - to PTP v1, UDP, Delay_req packet */
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1);
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1);
diff --git a/drivers/net/ethernet/apm/Kconfig b/drivers/net/ethernet/apm/Kconfig
index 59efe5b145dd..a893ef0e9c49 100644
--- a/drivers/net/ethernet/apm/Kconfig
+++ b/drivers/net/ethernet/apm/Kconfig
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
 source "drivers/net/ethernet/apm/xgene/Kconfig"
 source "drivers/net/ethernet/apm/xgene-v2/Kconfig"
diff --git a/drivers/net/ethernet/apm/Makefile b/drivers/net/ethernet/apm/Makefile
index 946b2a4c882d..cc8af97241fb 100644
--- a/drivers/net/ethernet/apm/Makefile
+++ b/drivers/net/ethernet/apm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for APM X-GENE Ethernet driver.
 #
diff --git a/drivers/net/ethernet/apm/xgene-v2/Kconfig b/drivers/net/ethernet/apm/xgene-v2/Kconfig
index eedd3f3dd22e..2274af912fb3 100644
--- a/drivers/net/ethernet/apm/xgene-v2/Kconfig
+++ b/drivers/net/ethernet/apm/xgene-v2/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config NET_XGENE_V2
 	tristate "APM X-Gene SoC Ethernet-v2 Driver"
 	depends on ARCH_XGENE || COMPILE_TEST
diff --git a/drivers/net/ethernet/apm/xgene-v2/Makefile b/drivers/net/ethernet/apm/xgene-v2/Makefile
index f16a2b3dde8b..fdde3b668acd 100644
--- a/drivers/net/ethernet/apm/xgene-v2/Makefile
+++ b/drivers/net/ethernet/apm/xgene-v2/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for APM X-Gene Ethernet v2 driver
 #
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.c b/drivers/net/ethernet/apm/xgene-v2/enet.c
index 5998da014923..a8c6b379df82 100644
--- a/drivers/net/ethernet/apm/xgene-v2/enet.c
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/drivers/net/ethernet/apm/xgene-v2/enet.h b/drivers/net/ethernet/apm/xgene-v2/enet.h
index 3fd36dc66a23..15cbd0ca1e9a 100644
--- a/drivers/net/ethernet/apm/xgene-v2/enet.h
+++ b/drivers/net/ethernet/apm/xgene-v2/enet.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_V2_ENET_H__
diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.c b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
index d31ad8270d93..a58250c1b57a 100644
--- a/drivers/net/ethernet/apm/xgene-v2/ethtool.c
+++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.h b/drivers/net/ethernet/apm/xgene-v2/ethtool.h
index 54b48d5561b8..8263b4aca6fe 100644
--- a/drivers/net/ethernet/apm/xgene-v2/ethtool.h
+++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_V2_ETHTOOL_H__
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c
index ee431e397e57..2da979e4fad1 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mac.c
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.h b/drivers/net/ethernet/apm/xgene-v2/mac.h
index 3c83fa617356..7392f606687b 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mac.h
+++ b/drivers/net/ethernet/apm/xgene-v2/mac.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_V2_MAC_H__
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
index 87b142a312e0..79048cc46703 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.c
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h
index 969b258cb7de..d41439d2709d 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.h
+++ b/drivers/net/ethernet/apm/xgene-v2/main.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_V2_MAIN_H__
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
index 53529cd85162..eba06831aec2 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mdio.c
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.c b/drivers/net/ethernet/apm/xgene-v2/ring.c
index 38810828f8f0..fbea4bc438a9 100644
--- a/drivers/net/ethernet/apm/xgene-v2/ring.c
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/drivers/net/ethernet/apm/xgene-v2/ring.h b/drivers/net/ethernet/apm/xgene-v2/ring.h
index abc8c9a84954..2fd25553d5d3 100644
--- a/drivers/net/ethernet/apm/xgene-v2/ring.h
+++ b/drivers/net/ethernet/apm/xgene-v2/ring.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Applied Micro X-Gene SoC Ethernet v2 Driver
  *
  * Copyright (c) 2017, Applied Micro Circuits Corporation
  * Author(s): Iyappan Subramanian <isubramanian@apm.com>
  *	      Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_V2_RING_H__
diff --git a/drivers/net/ethernet/apm/xgene/Kconfig b/drivers/net/ethernet/apm/xgene/Kconfig
index e4e33c900b57..7bdfe78427df 100644
--- a/drivers/net/ethernet/apm/xgene/Kconfig
+++ b/drivers/net/ethernet/apm/xgene/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config NET_XGENE
 	tristate "APM X-Gene SoC Ethernet Driver"
 	depends on ARCH_XGENE || COMPILE_TEST
diff --git a/drivers/net/ethernet/apm/xgene/Makefile b/drivers/net/ethernet/apm/xgene/Makefile
index f46321f68315..6d1314757d3c 100644
--- a/drivers/net/ethernet/apm/xgene/Makefile
+++ b/drivers/net/ethernet/apm/xgene/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for APM X-Gene Ethernet Driver.
 #
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c
index e1a51d8892fc..de5464322311 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Applied Micro X-Gene SoC Ethernet Classifier structures
  *
  * Copyright (c) 2016, Applied Micro Circuits Corporation
  * Authors: Khuong Dinh <kdinh@apm.com>
  *          Tanmay Inamdar <tinamdar@apm.com>
  *          Iyappan Subramanian <isubramanian@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "xgene_enet_main.h"
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h
index 18fe8d56082c..bc05cbcf4403 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_cle.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* Applied Micro X-Gene SoC Ethernet Classifier structures
  *
  * Copyright (c) 2016, Applied Micro Circuits Corporation
  * Authors: Khuong Dinh <kdinh@apm.com>
  *          Tanmay Inamdar <tinamdar@apm.com>
  *          Iyappan Subramanian <isubramanian@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_CLE_H__
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c
index 78dd09b5beeb..246dec27140d 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/ethtool.h>
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index e3560311711a..61a465097cb8 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Ravi Patel <rapatel@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "xgene_enet_main.h"
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
index 5d3e18d3c94c..2f534f9d4416 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Ravi Patel <rapatel@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_HW_H__
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 50dd6bf176d0..10b1c053e70a 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Ravi Patel <rapatel@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/gpio.h>
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
index 985768596900..18f4923b1723 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Ravi Patel <rapatel@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_MAIN_H__
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
index 4ff40559f970..02892efdc4dc 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2015, Applied Micro Circuits Corporation
  * Author: Iyappan Subramanian <isubramanian@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "xgene_enet_main.h"
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.h b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.h
index 8b235db23c42..4e2edeea54ab 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.h
@@ -1,20 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2015, Applied Micro Circuits Corporation
  * Author: Iyappan Subramanian <isubramanian@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_RING2_H__
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c
index b1a83fdbefb8..6453fc2ebb1f 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "xgene_enet_main.h"
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h
index 3d0ba374491b..3bba0ce34bb4 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_SGMAC_H__
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index b7d75d067c7a..133eb91c542e 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/of_gpio.h>
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
index a3b45517df45..98622dcf6c53 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* Applied Micro X-Gene SoC Ethernet Driver
  *
  * Copyright (c) 2014, Applied Micro Circuits Corporation
  * Authors: Iyappan Subramanian <isubramanian@apm.com>
  *	    Keyur Chudgar <kchudgar@apm.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef __XGENE_ENET_XGMAC_H__
diff --git a/drivers/net/ethernet/apple/Kconfig b/drivers/net/ethernet/apple/Kconfig
index 31071297896c..fde7ae33e302 100644
--- a/drivers/net/ethernet/apple/Kconfig
+++ b/drivers/net/ethernet/apple/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Apple device configuration
 #
diff --git a/drivers/net/ethernet/apple/Makefile b/drivers/net/ethernet/apple/Makefile
index 86eaa17af0f4..322457027546 100644
--- a/drivers/net/ethernet/apple/Makefile
+++ b/drivers/net/ethernet/apple/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Apple network device drivers.
 #
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 4d3855ceb500..c40daad515d5 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Network device driver for the BMAC ethernet controller on
  * Apple Powermacs.  Assumes it's under a DBDMA controller.
diff --git a/drivers/net/ethernet/apple/bmac.h b/drivers/net/ethernet/apple/bmac.h
index a1d19d867ba5..f8826c4ce792 100644
--- a/drivers/net/ethernet/apple/bmac.h
+++ b/drivers/net/ethernet/apple/bmac.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * mace.h - definitions for the registers in the "Big Mac"
  *  Ethernet controller found in PowerMac G3 models.
  *
  * Copyright (C) 1998 Randy Gobbel.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 /* The "Big MAC" appears to have some parts in common with the Sun "Happy Meal"
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index 68b9ee489489..b8ba2abf5b3a 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Network device driver for the MACE ethernet controller on
  * Apple Powermacs.  Assumes it's under a DBDMA controller.
@@ -764,7 +765,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 	    dev->stats.tx_bytes += mp->tx_bufs[i]->len;
 	    ++dev->stats.tx_packets;
 	}
-	dev_kfree_skb_irq(mp->tx_bufs[i]);
+	dev_consume_skb_irq(mp->tx_bufs[i]);
 	--mp->tx_active;
 	if (++i >= N_TX_RING)
 	    i = 0;
diff --git a/drivers/net/ethernet/apple/mace.h b/drivers/net/ethernet/apple/mace.h
index 30b7ec0cedb5..697f71cf1937 100644
--- a/drivers/net/ethernet/apple/mace.h
+++ b/drivers/net/ethernet/apple/mace.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * mace.h - definitions for the registers in the Am79C940 MACE
  * (Medium Access Control for Ethernet) controller.
  *
  * Copyright (C) 1996 Paul Mackerras.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
  */
 
 #define REG(x)	volatile unsigned char x; char x ## _pad[15]
diff --git a/drivers/net/ethernet/apple/macmace.c b/drivers/net/ethernet/apple/macmace.c
index 376f2c2613e7..8d03578d5e8c 100644
--- a/drivers/net/ethernet/apple/macmace.c
+++ b/drivers/net/ethernet/apple/macmace.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	Driver for the Macintosh 68K onboard MACE controller with PSC
  *	driven DMA. The MACE driver code is derived from mace.c. The
  *	Mac68k theory of operation is courtesy of the MacBSD wizards.
  *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
  *	Copyright (C) 1996 Paul Mackerras.
  *	Copyright (C) 1998 Alan Cox <alan@lxorguk.ukuu.org.uk>
  *
diff --git a/drivers/net/ethernet/aquantia/Kconfig b/drivers/net/ethernet/aquantia/Kconfig
index 7d623e90dc19..350a48e4f124 100644
--- a/drivers/net/ethernet/aquantia/Kconfig
+++ b/drivers/net/ethernet/aquantia/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # aQuantia device configuration
 #
@@ -17,7 +18,8 @@ if NET_VENDOR_AQUANTIA
 
 config AQTION
 	tristate "aQuantia AQtion(tm) Support"
-	depends on PCI && X86_64
+	depends on PCI
+	depends on X86_64 || ARM64 || COMPILE_TEST
 	---help---
 	  This enables the support for the aQuantia AQtion(tm) Ethernet card.
 
diff --git a/drivers/net/ethernet/aquantia/Makefile b/drivers/net/ethernet/aquantia/Makefile
index 4f4897b689b2..c4e7d01ea650 100644
--- a/drivers/net/ethernet/aquantia/Makefile
+++ b/drivers/net/ethernet/aquantia/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the aQuantia device drivers.
 #
diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile
index 4556630ee286..131cab855be7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/Makefile
+++ b/drivers/net/ethernet/aquantia/atlantic/Makefile
@@ -1,23 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
 ################################################################################
 #
 # aQuantia Ethernet Controller AQtion Linux Driver
 # Copyright(c) 2014-2017 aQuantia Corporation.
 #
-# This program is free software; you can redistribute it and/or modify it
-# under the terms and conditions of the GNU General Public License,
-# version 2, as published by the Free Software Foundation.
-#
-# This program is distributed in the hope it will be useful, but WITHOUT
-# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-# more details.
-#
-# You should have received a copy of the GNU General Public License along
-# with this program. If not, see <http://www.gnu.org/licenses/>.
-#
-# The full GNU General Public License is included in this distribution in
-# the file called "COPYING".
-#
 # Contact Information: <rdc-drv@aquantia.com>
 # aQuantia Corporation, 105 E. Tasman Dr. San Jose, CA 95134, USA
 #
@@ -36,6 +22,7 @@ atlantic-objs := aq_main.o \
 	aq_ring.o \
 	aq_hw_utils.o \
 	aq_ethtool.o \
+	aq_drvinfo.o \
 	aq_filters.o \
 	hw_atl/hw_atl_a0.o \
 	hw_atl/hw_atl_b0.o \
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index 3944ce7f0870..02f1b70c4e25 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_cfg.h: Definition of configuration parameters and constants. */
@@ -12,11 +9,13 @@
 #ifndef AQ_CFG_H
 #define AQ_CFG_H
 
+#include <generated/utsrelease.h>
+
 #define AQ_CFG_VECS_DEF   8U
 #define AQ_CFG_TCS_DEF    1U
 
 #define AQ_CFG_TXDS_DEF    4096U
-#define AQ_CFG_RXDS_DEF    1024U
+#define AQ_CFG_RXDS_DEF    2048U
 
 #define AQ_CFG_IS_POLLING_DEF 0U
 
@@ -34,10 +33,16 @@
 #define AQ_CFG_TCS_MAX    8U
 
 #define AQ_CFG_TX_FRAME_MAX  (16U * 1024U)
-#define AQ_CFG_RX_FRAME_MAX  (4U * 1024U)
+#define AQ_CFG_RX_FRAME_MAX  (2U * 1024U)
 
 #define AQ_CFG_TX_CLEAN_BUDGET 256U
 
+#define AQ_CFG_RX_REFILL_THRES 32U
+
+#define AQ_CFG_RX_HDR_SIZE 256U
+
+#define AQ_CFG_RX_PAGEORDER 0U
+
 /* LRO */
 #define AQ_CFG_IS_LRO_DEF           1U
 
@@ -83,10 +88,7 @@
 #define AQ_CFG_DRV_AUTHOR      "aQuantia"
 #define AQ_CFG_DRV_DESC        "aQuantia Corporation(R) Network Driver"
 #define AQ_CFG_DRV_NAME        "atlantic"
-#define AQ_CFG_DRV_VERSION	__stringify(NIC_MAJOR_DRIVER_VERSION)"."\
-				__stringify(NIC_MINOR_DRIVER_VERSION)"."\
-				__stringify(NIC_BUILD_DRIVER_VERSION)"."\
-				__stringify(NIC_REVISION_DRIVER_VERSION) \
+#define AQ_CFG_DRV_VERSION	UTS_RELEASE \
 				AQ_CFG_DRV_VERSION_SUFFIX
 
 #endif /* AQ_CFG_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index 6b6d1724676e..42ea8d8daa46 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_common.h: Basic includes for all files in project. */
@@ -41,9 +38,6 @@
 #define AQ_DEVICE_ID_AQC111S	0x91B1
 #define AQ_DEVICE_ID_AQC112S	0x92B1
 
-#define AQ_DEVICE_ID_AQC111E	0x51B1
-#define AQ_DEVICE_ID_AQC112E	0x52B1
-
 #define HW_ATL_NIC_NAME "aQuantia AQtion 10Gbit Network Adapter"
 
 #define AQ_HWREV_ANY	0
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
new file mode 100644
index 000000000000..6da65099047d
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2014-2019 aQuantia Corporation. */
+
+/* File aq_drvinfo.c: Definition of common code for firmware info in sys.*/
+
+#include <linux/init.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/hwmon.h>
+#include <linux/uaccess.h>
+
+#include "aq_drvinfo.h"
+
+#if IS_REACHABLE(CONFIG_HWMON)
+static int aq_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long *value)
+{
+	struct aq_nic_s *aq_nic = dev_get_drvdata(dev);
+	int temp;
+	int err;
+
+	if (!aq_nic)
+		return -EIO;
+
+	if (type != hwmon_temp)
+		return -EOPNOTSUPP;
+
+	if (!aq_nic->aq_fw_ops->get_phy_temp)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		err = aq_nic->aq_fw_ops->get_phy_temp(aq_nic->aq_hw, &temp);
+		*value = temp;
+		return err;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int aq_hwmon_read_string(struct device *dev,
+				enum hwmon_sensor_types type,
+				u32 attr, int channel, const char **str)
+{
+	struct aq_nic_s *aq_nic = dev_get_drvdata(dev);
+
+	if (!aq_nic)
+		return -EIO;
+
+	if (type != hwmon_temp)
+		return -EOPNOTSUPP;
+
+	if (!aq_nic->aq_fw_ops->get_phy_temp)
+		return -EOPNOTSUPP;
+
+	switch (attr) {
+	case hwmon_temp_label:
+		*str = "PHY Temperature";
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t aq_hwmon_is_visible(const void *data,
+				   enum hwmon_sensor_types type,
+				   u32 attr, int channel)
+{
+	if (type != hwmon_temp)
+		return 0;
+
+	switch (attr) {
+	case hwmon_temp_input:
+	case hwmon_temp_label:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static const struct hwmon_ops aq_hwmon_ops = {
+	.is_visible = aq_hwmon_is_visible,
+	.read = aq_hwmon_read,
+	.read_string = aq_hwmon_read_string,
+};
+
+static u32 aq_hwmon_temp_config[] = {
+	HWMON_T_INPUT | HWMON_T_LABEL,
+	0,
+};
+
+static const struct hwmon_channel_info aq_hwmon_temp = {
+	.type = hwmon_temp,
+	.config = aq_hwmon_temp_config,
+};
+
+static const struct hwmon_channel_info *aq_hwmon_info[] = {
+	&aq_hwmon_temp,
+	NULL,
+};
+
+static const struct hwmon_chip_info aq_hwmon_chip_info = {
+	.ops = &aq_hwmon_ops,
+	.info = aq_hwmon_info,
+};
+
+int aq_drvinfo_init(struct net_device *ndev)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct device *dev = &aq_nic->pdev->dev;
+	struct device *hwmon_dev;
+	int err = 0;
+
+	hwmon_dev = devm_hwmon_device_register_with_info(dev,
+							 ndev->name,
+							 aq_nic,
+							 &aq_hwmon_chip_info,
+							 NULL);
+
+	if (IS_ERR(hwmon_dev))
+		err = PTR_ERR(hwmon_dev);
+
+	return err;
+}
+
+#else
+int aq_drvinfo_init(struct net_device *ndev) { return 0; }
+#endif
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.h b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.h
new file mode 100644
index 000000000000..23a0487893a7
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2014-2017 aQuantia Corporation. */
+
+/* File aq_drvinfo.h: Declaration of common code for firmware info in sys.*/
+
+#ifndef AQ_DRVINFO_H
+#define AQ_DRVINFO_H
+
+#include "aq_nic.h"
+#include "aq_hw.h"
+#include "hw_atl/hw_atl_utils.h"
+
+int aq_drvinfo_init(struct net_device *ndev);
+
+#endif /* AQ_DRVINFO_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 38e87eed76b9..24df132384fb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_ethtool.c: Definition of ethertool related functions. */
@@ -138,7 +135,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 	u8 *p = data;
 
 	if (stringset == ETH_SS_STATS) {
-		memcpy(p, *aq_ethtool_stat_names,
+		memcpy(p, aq_ethtool_stat_names,
 		       sizeof(aq_ethtool_stat_names));
 		p = p + sizeof(aq_ethtool_stat_names);
 		for (i = 0; i < cfg->vecs; i++) {
@@ -405,8 +402,10 @@ static int aq_ethtool_get_eee(struct net_device *ndev, struct ethtool_eee *eee)
 	if (!aq_nic->aq_fw_ops->get_eee_rate)
 		return -EOPNOTSUPP;
 
+	mutex_lock(&aq_nic->fwreq_mutex);
 	err = aq_nic->aq_fw_ops->get_eee_rate(aq_nic->aq_hw, &rate,
 					      &supported_rates);
+	mutex_unlock(&aq_nic->fwreq_mutex);
 	if (err < 0)
 		return err;
 
@@ -439,8 +438,10 @@ static int aq_ethtool_set_eee(struct net_device *ndev, struct ethtool_eee *eee)
 		     !aq_nic->aq_fw_ops->set_eee_rate))
 		return -EOPNOTSUPP;
 
+	mutex_lock(&aq_nic->fwreq_mutex);
 	err = aq_nic->aq_fw_ops->get_eee_rate(aq_nic->aq_hw, &rate,
 					      &supported_rates);
+	mutex_unlock(&aq_nic->fwreq_mutex);
 	if (err < 0)
 		return err;
 
@@ -452,20 +453,28 @@ static int aq_ethtool_set_eee(struct net_device *ndev, struct ethtool_eee *eee)
 		cfg->eee_speeds = 0;
 	}
 
-	return aq_nic->aq_fw_ops->set_eee_rate(aq_nic->aq_hw, rate);
+	mutex_lock(&aq_nic->fwreq_mutex);
+	err = aq_nic->aq_fw_ops->set_eee_rate(aq_nic->aq_hw, rate);
+	mutex_unlock(&aq_nic->fwreq_mutex);
+
+	return err;
 }
 
 static int aq_ethtool_nway_reset(struct net_device *ndev)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	int err = 0;
 
 	if (unlikely(!aq_nic->aq_fw_ops->renegotiate))
 		return -EOPNOTSUPP;
 
-	if (netif_running(ndev))
-		return aq_nic->aq_fw_ops->renegotiate(aq_nic->aq_hw);
+	if (netif_running(ndev)) {
+		mutex_lock(&aq_nic->fwreq_mutex);
+		err = aq_nic->aq_fw_ops->renegotiate(aq_nic->aq_hw);
+		mutex_unlock(&aq_nic->fwreq_mutex);
+	}
 
-	return 0;
+	return err;
 }
 
 static void aq_ethtool_get_pauseparam(struct net_device *ndev,
@@ -503,7 +512,9 @@ static int aq_ethtool_set_pauseparam(struct net_device *ndev,
 	else
 		aq_nic->aq_hw->aq_nic_cfg->flow_control &= ~AQ_NIC_FC_TX;
 
+	mutex_lock(&aq_nic->fwreq_mutex);
 	err = aq_nic->aq_fw_ops->set_flow_control(aq_nic->aq_hw);
+	mutex_unlock(&aq_nic->fwreq_mutex);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.h b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.h
index 21c126eeb5eb..632b5531db4a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_ethtool.h: Declaration of ethertool related functions. */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
index 18bc035da850..440690b18734 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2014-2017 aQuantia Corporation. */
 
 /* File aq_filters.c: RX filters related functions. */
@@ -843,9 +843,14 @@ int aq_filters_vlans_update(struct aq_nic_s *aq_nic)
 		return err;
 
 	if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
-		if (hweight < AQ_VLAN_MAX_FILTERS)
-			err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, true);
+		if (hweight < AQ_VLAN_MAX_FILTERS && hweight > 0) {
+			err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw,
+				!(aq_nic->packet_filter & IFF_PROMISC));
+			aq_nic->aq_nic_cfg.is_vlan_force_promisc = false;
+		} else {
 		/* otherwise left in promiscue mode */
+			aq_nic->aq_nic_cfg.is_vlan_force_promisc = true;
+		}
 	}
 
 	return err;
@@ -866,6 +871,7 @@ int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic)
 	if (unlikely(!aq_hw_ops->hw_filter_vlan_ctrl))
 		return -EOPNOTSUPP;
 
+	aq_nic->aq_nic_cfg.is_vlan_force_promisc = true;
 	err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
index c6a08c6585d5..122e06c88a33 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (C) 2014-2017 aQuantia Corporation. */
 
 /* File aq_filters.h: RX filters related functions. */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 81aab73dc22f..53d7478689a0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_hw.h: Declaration of abstract interface for NIC hardware specific
@@ -88,6 +85,8 @@ struct aq_stats_s {
 #define AQ_HW_IRQ_MSI     2U
 #define AQ_HW_IRQ_MSIX    3U
 
+#define AQ_HW_SERVICE_IRQS   1U
+
 #define AQ_HW_POWER_STATE_D0   0U
 #define AQ_HW_POWER_STATE_D3   3U
 
@@ -259,6 +258,8 @@ struct aq_fw_ops {
 
 	int (*update_stats)(struct aq_hw_s *self);
 
+	int (*get_phy_temp)(struct aq_hw_s *self, int *temp);
+
 	u32 (*get_flow_control)(struct aq_hw_s *self, u32 *fcmode);
 
 	int (*set_flow_control)(struct aq_hw_s *self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
index d526c4f19d34..9c7a226d81b6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_hw_utils.c: Definitions of helper functions used across
@@ -53,6 +50,18 @@ void aq_hw_write_reg(struct aq_hw_s *hw, u32 reg, u32 value)
 	writel(value, hw->mmio + reg);
 }
 
+/* Most of 64-bit registers are in LSW, MSW form.
+   Counters are normally implemented by HW as latched pairs:
+   reading LSW first locks MSW, to overcome LSW overflow
+ */
+u64 aq_hw_read_reg64(struct aq_hw_s *hw, u32 reg)
+{
+	u64 value = aq_hw_read_reg(hw, reg);
+
+	value |= (u64)aq_hw_read_reg(hw, reg + 4) << 32;
+	return value;
+}
+
 int aq_hw_err_from_flags(struct aq_hw_s *hw)
 {
 	int err = 0;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
index dc88a1221f1d..9ef82d487e01 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_hw_utils.h: Declaration of helper functions used across hardware
@@ -14,6 +11,8 @@
 #ifndef AQ_HW_UTILS_H
 #define AQ_HW_UTILS_H
 
+#include <linux/iopoll.h>
+
 #include "aq_common.h"
 
 #ifndef HIDWORD
@@ -23,18 +22,6 @@
 
 #define AQ_HW_SLEEP(_US_) mdelay(_US_)
 
-#define AQ_HW_WAIT_FOR(_B_, _US_, _N_) \
-do { \
-	unsigned int AQ_HW_WAIT_FOR_i; \
-	for (AQ_HW_WAIT_FOR_i = _N_; (!(_B_)) && (AQ_HW_WAIT_FOR_i);\
-	--AQ_HW_WAIT_FOR_i) {\
-		udelay(_US_); \
-	} \
-	if (!AQ_HW_WAIT_FOR_i) {\
-		err = -ETIME; \
-	} \
-} while (0)
-
 #define aq_pr_err(...) pr_err(AQ_CFG_DRV_NAME ": " __VA_ARGS__)
 #define aq_pr_trace(...) pr_info(AQ_CFG_DRV_NAME ": " __VA_ARGS__)
 
@@ -45,6 +32,7 @@ void aq_hw_write_reg_bit(struct aq_hw_s *aq_hw, u32 addr, u32 msk,
 u32 aq_hw_read_reg_bit(struct aq_hw_s *aq_hw, u32 addr, u32 msk, u32 shift);
 u32 aq_hw_read_reg(struct aq_hw_s *hw, u32 reg);
 void aq_hw_write_reg(struct aq_hw_s *hw, u32 reg, u32 value);
+u64 aq_hw_read_reg64(struct aq_hw_s *hw, u32 reg);
 int aq_hw_err_from_flags(struct aq_hw_s *hw);
 
 #endif /* AQ_HW_UTILS_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 2a11c1eefd8f..100722ad5c2d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_main.c: Main file for aQuantia Linux driver. */
@@ -23,8 +20,17 @@ MODULE_VERSION(AQ_CFG_DRV_VERSION);
 MODULE_AUTHOR(AQ_CFG_DRV_AUTHOR);
 MODULE_DESCRIPTION(AQ_CFG_DRV_DESC);
 
+static const char aq_ndev_driver_name[] = AQ_CFG_DRV_NAME;
+
 static const struct net_device_ops aq_ndev_ops;
 
+static struct workqueue_struct *aq_ndev_wq;
+
+void aq_ndev_schedule_work(struct work_struct *work)
+{
+	queue_work(aq_ndev_wq, work);
+}
+
 struct net_device *aq_ndev_alloc(void)
 {
 	struct net_device *ndev = NULL;
@@ -102,11 +108,16 @@ err_exit:
 static int aq_ndev_set_features(struct net_device *ndev,
 				netdev_features_t features)
 {
+	bool is_vlan_rx_strip = !!(features & NETIF_F_HW_VLAN_CTAG_RX);
+	bool is_vlan_tx_insert = !!(features & NETIF_F_HW_VLAN_CTAG_TX);
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
-	struct aq_nic_cfg_s *aq_cfg = aq_nic_get_cfg(aq_nic);
+	bool need_ndev_restart = false;
+	struct aq_nic_cfg_s *aq_cfg;
 	bool is_lro = false;
 	int err = 0;
 
+	aq_cfg = aq_nic_get_cfg(aq_nic);
+
 	if (!(features & NETIF_F_NTUPLE)) {
 		if (aq_nic->ndev->features & NETIF_F_NTUPLE) {
 			err = aq_clear_rxnfc_all_rules(aq_nic);
@@ -129,17 +140,32 @@ static int aq_ndev_set_features(struct net_device *ndev,
 
 		if (aq_cfg->is_lro != is_lro) {
 			aq_cfg->is_lro = is_lro;
-
-			if (netif_running(ndev)) {
-				aq_ndev_close(ndev);
-				aq_ndev_open(ndev);
-			}
+			need_ndev_restart = true;
 		}
 	}
-	if ((aq_nic->ndev->features ^ features) & NETIF_F_RXCSUM)
+
+	if ((aq_nic->ndev->features ^ features) & NETIF_F_RXCSUM) {
 		err = aq_nic->aq_hw_ops->hw_set_offload(aq_nic->aq_hw,
 							aq_cfg);
 
+		if (unlikely(err))
+			goto err_exit;
+	}
+
+	if (aq_cfg->is_vlan_rx_strip != is_vlan_rx_strip) {
+		aq_cfg->is_vlan_rx_strip = is_vlan_rx_strip;
+		need_ndev_restart = true;
+	}
+	if (aq_cfg->is_vlan_tx_insert != is_vlan_tx_insert) {
+		aq_cfg->is_vlan_tx_insert = is_vlan_tx_insert;
+		need_ndev_restart = true;
+	}
+
+	if (need_ndev_restart && netif_running(ndev)) {
+		aq_ndev_close(ndev);
+		aq_ndev_open(ndev);
+	}
+
 err_exit:
 	return err;
 }
@@ -209,3 +235,35 @@ static const struct net_device_ops aq_ndev_ops = {
 	.ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid,
 };
+
+static int __init aq_ndev_init_module(void)
+{
+	int ret;
+
+	aq_ndev_wq = create_singlethread_workqueue(aq_ndev_driver_name);
+	if (!aq_ndev_wq) {
+		pr_err("Failed to create workqueue\n");
+		return -ENOMEM;
+	}
+
+	ret = aq_pci_func_register_driver();
+	if (ret) {
+		destroy_workqueue(aq_ndev_wq);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void __exit aq_ndev_exit_module(void)
+{
+	aq_pci_func_unregister_driver();
+
+	if (aq_ndev_wq) {
+		destroy_workqueue(aq_ndev_wq);
+		aq_ndev_wq = NULL;
+	}
+}
+
+module_init(aq_ndev_init_module);
+module_exit(aq_ndev_exit_module);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.h b/drivers/net/ethernet/aquantia/atlantic/aq_main.h
index ce92152eb43e..a5a624b9ce73 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_main.h: Main file for aQuantia Linux driver. */
@@ -13,7 +10,9 @@
 #define AQ_MAIN_H
 
 #include "aq_common.h"
+#include "aq_nic.h"
 
+void aq_ndev_schedule_work(struct work_struct *work);
 struct net_device *aq_ndev_alloc(void);
 
 #endif /* AQ_MAIN_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 0147c037ca96..e1392766e21e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_nic.c: Definition of common code for NIC. */
@@ -14,6 +11,7 @@
 #include "aq_vec.h"
 #include "aq_hw.h"
 #include "aq_pci_func.h"
+#include "aq_main.h"
 
 #include <linux/moduleparam.h>
 #include <linux/netdevice.h>
@@ -73,6 +71,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	cfg->tx_itr = aq_itr_tx;
 	cfg->rx_itr = aq_itr_rx;
 
+	cfg->rxpageorder = AQ_CFG_RX_PAGEORDER;
 	cfg->is_rss = AQ_CFG_IS_RSS_DEF;
 	cfg->num_rss_queues = AQ_CFG_NUM_RSS_QUEUES_DEF;
 	cfg->aq_rss.base_cpu_number = AQ_CFG_RSS_BASE_CPU_NUM_DEF;
@@ -91,7 +90,8 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	/*rss rings */
 	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
 	cfg->vecs = min(cfg->vecs, num_online_cpus());
-	cfg->vecs = min(cfg->vecs, self->irqvecs);
+	if (self->irqvecs > AQ_HW_SERVICE_IRQS)
+		cfg->vecs = min(cfg->vecs, self->irqvecs - AQ_HW_SERVICE_IRQS);
 	/* cfg->vecs should be power of 2 for RSS */
 	if (cfg->vecs >= 8U)
 		cfg->vecs = 8U;
@@ -115,8 +115,20 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 		cfg->vecs = 1U;
 	}
 
+	/* Check if we have enough vectors allocated for
+	 * link status IRQ. If no - we'll know link state from
+	 * slower service task.
+	 */
+	if (AQ_HW_SERVICE_IRQS > 0 && cfg->vecs + 1 <= self->irqvecs)
+		cfg->link_irq_vec = cfg->vecs;
+	else
+		cfg->link_irq_vec = 0;
+
 	cfg->link_speed_msk &= cfg->aq_hw_caps->link_speed_msk;
 	cfg->features = cfg->aq_hw_caps->hw_features;
+	cfg->is_vlan_rx_strip = !!(cfg->features & NETIF_F_HW_VLAN_CTAG_RX);
+	cfg->is_vlan_tx_insert = !!(cfg->features & NETIF_F_HW_VLAN_CTAG_TX);
+	cfg->is_vlan_force_promisc = true;
 }
 
 static int aq_nic_update_link_status(struct aq_nic_s *self)
@@ -160,30 +172,48 @@ static int aq_nic_update_link_status(struct aq_nic_s *self)
 	return 0;
 }
 
-static void aq_nic_service_timer_cb(struct timer_list *t)
+static irqreturn_t aq_linkstate_threaded_isr(int irq, void *private)
 {
-	struct aq_nic_s *self = from_timer(self, t, service_timer);
-	int ctimer = AQ_CFG_SERVICE_TIMER_INTERVAL;
-	int err = 0;
+	struct aq_nic_s *self = private;
+
+	if (!self)
+		return IRQ_NONE;
+
+	aq_nic_update_link_status(self);
+
+	self->aq_hw_ops->hw_irq_enable(self->aq_hw,
+				       BIT(self->aq_nic_cfg.link_irq_vec));
+	return IRQ_HANDLED;
+}
+
+static void aq_nic_service_task(struct work_struct *work)
+{
+	struct aq_nic_s *self = container_of(work, struct aq_nic_s,
+					     service_task);
+	int err;
 
 	if (aq_utils_obj_test(&self->flags, AQ_NIC_FLAGS_IS_NOT_READY))
-		goto err_exit;
+		return;
 
 	err = aq_nic_update_link_status(self);
 	if (err)
-		goto err_exit;
+		return;
 
+	mutex_lock(&self->fwreq_mutex);
 	if (self->aq_fw_ops->update_stats)
 		self->aq_fw_ops->update_stats(self->aq_hw);
+	mutex_unlock(&self->fwreq_mutex);
 
 	aq_nic_update_ndev_stats(self);
+}
+
+static void aq_nic_service_timer_cb(struct timer_list *t)
+{
+	struct aq_nic_s *self = from_timer(self, t, service_timer);
 
-	/* If no link - use faster timer rate to detect link up asap */
-	if (!netif_carrier_ok(self->ndev))
-		ctimer = max(ctimer / 2, 1);
+	mod_timer(&self->service_timer, jiffies + AQ_CFG_SERVICE_TIMER_INTERVAL);
 
-err_exit:
-	mod_timer(&self->service_timer, jiffies + ctimer);
+	aq_ndev_schedule_work(&self->service_task);
 }
 
 static void aq_nic_polling_timer_cb(struct timer_list *t)
@@ -213,8 +243,10 @@ int aq_nic_ndev_register(struct aq_nic_s *self)
 	if (err)
 		goto err_exit;
 
+	mutex_lock(&self->fwreq_mutex);
 	err = self->aq_fw_ops->get_mac_permanent(self->aq_hw,
 			    self->ndev->dev_addr);
+	mutex_unlock(&self->fwreq_mutex);
 	if (err)
 		goto err_exit;
 
@@ -256,7 +288,8 @@ void aq_nic_ndev_init(struct aq_nic_s *self)
 	self->ndev->hw_features |= aq_hw_caps->hw_features;
 	self->ndev->features = aq_hw_caps->hw_features;
 	self->ndev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
-				     NETIF_F_RXHASH | NETIF_F_SG | NETIF_F_LRO;
+				     NETIF_F_RXHASH | NETIF_F_SG |
+				     NETIF_F_LRO | NETIF_F_TSO;
 	self->ndev->priv_flags = aq_hw_caps->hw_priv_flags;
 	self->ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
@@ -283,7 +316,9 @@ int aq_nic_init(struct aq_nic_s *self)
 	unsigned int i = 0U;
 
 	self->power_state = AQ_HW_POWER_STATE_D0;
+	mutex_lock(&self->fwreq_mutex);
 	err = self->aq_hw_ops->hw_reset(self->aq_hw);
+	mutex_unlock(&self->fwreq_mutex);
 	if (err < 0)
 		goto err_exit;
 
@@ -333,9 +368,11 @@ int aq_nic_start(struct aq_nic_s *self)
 	err = aq_nic_update_interrupt_moderation_settings(self);
 	if (err)
 		goto err_exit;
+
+	INIT_WORK(&self->service_task, aq_nic_service_task);
+
 	timer_setup(&self->service_timer, aq_nic_service_timer_cb, 0);
-	mod_timer(&self->service_timer, jiffies +
-		  AQ_CFG_SERVICE_TIMER_INTERVAL);
+	aq_nic_service_timer_cb(&self->service_timer);
 
 	if (self->aq_nic_cfg.is_polling) {
 		timer_setup(&self->polling_timer, aq_nic_polling_timer_cb, 0);
@@ -344,13 +381,25 @@ int aq_nic_start(struct aq_nic_s *self)
 	} else {
 		for (i = 0U, aq_vec = self->aq_vec[0];
 			self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) {
-			err = aq_pci_func_alloc_irq(self, i,
-						    self->ndev->name, aq_vec,
+			err = aq_pci_func_alloc_irq(self, i, self->ndev->name,
+						    aq_vec_isr, aq_vec,
 						    aq_vec_get_affinity_mask(aq_vec));
 			if (err < 0)
 				goto err_exit;
 		}
 
+		if (self->aq_nic_cfg.link_irq_vec) {
+			int irqvec = pci_irq_vector(self->pdev,
+						   self->aq_nic_cfg.link_irq_vec);
+			err = request_threaded_irq(irqvec, NULL,
+						   aq_linkstate_threaded_isr,
+						   IRQF_SHARED,
+						   self->ndev->name, self);
+			if (err < 0)
+				goto err_exit;
+			self->msix_entry_mask |= (1 << self->aq_nic_cfg.link_irq_vec);
+		}
+
 		err = self->aq_hw_ops->hw_irq_enable(self->aq_hw,
 						     AQ_CFG_IRQ_MASK);
 		if (err < 0)
@@ -381,26 +430,37 @@ static unsigned int aq_nic_map_skb(struct aq_nic_s *self,
 	unsigned int dx = ring->sw_tail;
 	struct aq_ring_buff_s *first = NULL;
 	struct aq_ring_buff_s *dx_buff = &ring->buff_ring[dx];
+	bool need_context_tag = false;
+
+	dx_buff->flags = 0U;
 
 	if (unlikely(skb_is_gso(skb))) {
-		dx_buff->flags = 0U;
+		dx_buff->mss = skb_shinfo(skb)->gso_size;
+		dx_buff->is_gso = 1U;
 		dx_buff->len_pkt = skb->len;
 		dx_buff->len_l2 = ETH_HLEN;
 		dx_buff->len_l3 = ip_hdrlen(skb);
 		dx_buff->len_l4 = tcp_hdrlen(skb);
-		dx_buff->mss = skb_shinfo(skb)->gso_size;
-		dx_buff->is_txc = 1U;
 		dx_buff->eop_index = 0xffffU;
-
 		dx_buff->is_ipv6 =
 			(ip_hdr(skb)->version == 6) ? 1U : 0U;
+		need_context_tag = true;
+	}
+
+	if (self->aq_nic_cfg.is_vlan_tx_insert && skb_vlan_tag_present(skb)) {
+		dx_buff->vlan_tx_tag = skb_vlan_tag_get(skb);
+		dx_buff->len_pkt = skb->len;
+		dx_buff->is_vlan = 1U;
+		need_context_tag = true;
+	}
 
+	if (need_context_tag) {
 		dx = aq_ring_next_dx(ring, dx);
 		dx_buff = &ring->buff_ring[dx];
+		dx_buff->flags = 0U;
 		++ret;
 	}
 
-	dx_buff->flags = 0U;
 	dx_buff->len = skb_headlen(skb);
 	dx_buff->pa = dma_map_single(aq_nic_get_dev(self),
 				     skb->data,
@@ -489,7 +549,7 @@ mapping_error:
 	     --ret, dx = aq_ring_next_dx(ring, dx)) {
 		dx_buff = &ring->buff_ring[dx];
 
-		if (!dx_buff->is_txc && dx_buff->pa) {
+		if (!dx_buff->is_gso && !dx_buff->is_vlan && dx_buff->pa) {
 			if (unlikely(dx_buff->is_sop)) {
 				dma_unmap_single(aq_nic_get_dev(self),
 						 dx_buff->pa,
@@ -652,7 +712,14 @@ void aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 	unsigned int i = 0U;
 	unsigned int count = 0U;
 	struct aq_vec_s *aq_vec = NULL;
-	struct aq_stats_s *stats = self->aq_hw_ops->hw_get_hw_stats(self->aq_hw);
+	struct aq_stats_s *stats;
+
+	if (self->aq_fw_ops->update_stats) {
+		mutex_lock(&self->fwreq_mutex);
+		self->aq_fw_ops->update_stats(self->aq_hw);
+		mutex_unlock(&self->fwreq_mutex);
+	}
+	stats = self->aq_hw_ops->hw_get_hw_stats(self->aq_hw);
 
 	if (!stats)
 		goto err_exit;
@@ -698,11 +765,12 @@ static void aq_nic_update_ndev_stats(struct aq_nic_s *self)
 	struct net_device *ndev = self->ndev;
 	struct aq_stats_s *stats = self->aq_hw_ops->hw_get_hw_stats(self->aq_hw);
 
-	ndev->stats.rx_packets = stats->uprc + stats->mprc + stats->bprc;
-	ndev->stats.rx_bytes = stats->ubrc + stats->mbrc + stats->bbrc;
+	ndev->stats.rx_packets = stats->dma_pkt_rc;
+	ndev->stats.rx_bytes = stats->dma_oct_rc;
 	ndev->stats.rx_errors = stats->erpr;
-	ndev->stats.tx_packets = stats->uptc + stats->mptc + stats->bptc;
-	ndev->stats.tx_bytes = stats->ubtc + stats->mbtc + stats->bbtc;
+	ndev->stats.rx_dropped = stats->dpc;
+	ndev->stats.tx_packets = stats->dma_pkt_tc;
+	ndev->stats.tx_bytes = stats->dma_oct_tc;
 	ndev->stats.tx_errors = stats->erpt;
 	ndev->stats.multicast = stats->mprc;
 }
@@ -839,7 +907,9 @@ int aq_nic_set_link_ksettings(struct aq_nic_s *self,
 		self->aq_nic_cfg.is_autoneg = false;
 	}
 
+	mutex_lock(&self->fwreq_mutex);
 	err = self->aq_fw_ops->set_link_speed(self->aq_hw, rate);
+	mutex_unlock(&self->fwreq_mutex);
 	if (err < 0)
 		goto err_exit;
 
@@ -872,6 +942,7 @@ int aq_nic_stop(struct aq_nic_s *self)
 	netif_carrier_off(self->ndev);
 
 	del_timer_sync(&self->service_timer);
+	cancel_work_sync(&self->service_task);
 
 	self->aq_hw_ops->hw_irq_disable(self->aq_hw, AQ_CFG_IRQ_MASK);
 
@@ -899,14 +970,22 @@ void aq_nic_deinit(struct aq_nic_s *self)
 		self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i])
 		aq_vec_deinit(aq_vec);
 
-	self->aq_fw_ops->deinit(self->aq_hw);
+	if (likely(self->aq_fw_ops->deinit)) {
+		mutex_lock(&self->fwreq_mutex);
+		self->aq_fw_ops->deinit(self->aq_hw);
+		mutex_unlock(&self->fwreq_mutex);
+	}
 
 	if (self->power_state != AQ_HW_POWER_STATE_D0 ||
-	    self->aq_hw->aq_nic_cfg->wol) {
-		self->aq_fw_ops->set_power(self->aq_hw,
-					   self->power_state,
-					   self->ndev->dev_addr);
-	}
+	    self->aq_hw->aq_nic_cfg->wol)
+		if (likely(self->aq_fw_ops->set_power)) {
+			mutex_lock(&self->fwreq_mutex);
+			self->aq_fw_ops->set_power(self->aq_hw,
+						   self->power_state,
+						   self->ndev->dev_addr);
+			mutex_unlock(&self->fwreq_mutex);
+		}
+
 
 err_exit:;
 }
@@ -986,4 +1065,4 @@ void aq_nic_shutdown(struct aq_nic_s *self)
 
 err_exit:
 	rtnl_unlock();
-}
\ No newline at end of file
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 8e34c1e49bf2..255b54a6ae07 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_nic.h: Declaration of common code for NIC. */
@@ -26,16 +23,21 @@ struct aq_nic_cfg_s {
 	u64 features;
 	u32 rxds;		/* rx ring size, descriptors # */
 	u32 txds;		/* tx ring size, descriptors # */
-	u32 vecs;		/* vecs==allocated irqs */
+	u32 vecs;		/* allocated rx/tx vectors */
+	u32 link_irq_vec;
 	u32 irq_type;
 	u32 itr;
 	u16 rx_itr;
 	u16 tx_itr;
+	u32 rxpageorder;
 	u32 num_rss_queues;
 	u32 mtu;
 	u32 flow_control;
 	u32 link_speed_msk;
 	u32 wol;
+	u8 is_vlan_rx_strip;
+	u8 is_vlan_tx_insert;
+	bool is_vlan_force_promisc;
 	u16 is_mc_list_enabled;
 	u16 mc_list_count;
 	bool is_autoneg;
@@ -91,6 +93,7 @@ struct aq_nic_s {
 	const struct aq_fw_ops *aq_fw_ops;
 	struct aq_nic_cfg_s aq_nic_cfg;
 	struct timer_list service_timer;
+	struct work_struct service_task;
 	struct timer_list polling_timer;
 	struct aq_hw_link_status_s link_status;
 	struct {
@@ -103,6 +106,8 @@ struct aq_nic_s {
 	struct pci_dev *pdev;
 	unsigned int msix_entry_mask;
 	u32 irqvecs;
+	/* mutex to serialize FW interface access operations */
+	struct mutex fwreq_mutex;
 	struct aq_hw_rx_fltrs_s aq_hw_rx_fltrs;
 };
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index c8b44cdb91c1..74b9f3f1da81 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_pci_func.c: Definition of PCI functions. */
@@ -20,6 +17,7 @@
 #include "hw_atl/hw_atl_a0.h"
 #include "hw_atl/hw_atl_b0.h"
 #include "aq_filters.h"
+#include "aq_drvinfo.h"
 
 static const struct pci_device_id aq_pci_tbl[] = {
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_0001), },
@@ -42,9 +40,6 @@ static const struct pci_device_id aq_pci_tbl[] = {
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC111S), },
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC112S), },
 
-	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC111E), },
-	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC112E), },
-
 	{}
 };
 
@@ -74,9 +69,6 @@ static const struct aq_board_revision_s hw_atl_boards[] = {
 	{ AQ_DEVICE_ID_AQC109S,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc109s, },
 	{ AQ_DEVICE_ID_AQC111S,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc111s, },
 	{ AQ_DEVICE_ID_AQC112S,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc112s, },
-
-	{ AQ_DEVICE_ID_AQC111E,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc111e, },
-	{ AQ_DEVICE_ID_AQC112E,	AQ_HWREV_ANY,	&hw_atl_ops_b1, &hw_atl_b0_caps_aqc112e, },
 };
 
 MODULE_DEVICE_TABLE(pci, aq_pci_tbl);
@@ -139,26 +131,27 @@ err_exit:
 }
 
 int aq_pci_func_alloc_irq(struct aq_nic_s *self, unsigned int i,
-			  char *name, void *aq_vec, cpumask_t *affinity_mask)
+			  char *name, irq_handler_t irq_handler,
+			  void *irq_arg, cpumask_t *affinity_mask)
 {
 	struct pci_dev *pdev = self->pdev;
 	int err;
 
 	if (pdev->msix_enabled || pdev->msi_enabled)
-		err = request_irq(pci_irq_vector(pdev, i), aq_vec_isr, 0,
-				  name, aq_vec);
+		err = request_irq(pci_irq_vector(pdev, i), irq_handler, 0,
+				  name, irq_arg);
 	else
 		err = request_irq(pci_irq_vector(pdev, i), aq_vec_isr_legacy,
-				  IRQF_SHARED, name, aq_vec);
+				  IRQF_SHARED, name, irq_arg);
 
 	if (err >= 0) {
 		self->msix_entry_mask |= (1 << i);
-		self->aq_vec[i] = aq_vec;
 
-		if (pdev->msix_enabled)
+		if (pdev->msix_enabled && affinity_mask)
 			irq_set_affinity_hint(pci_irq_vector(pdev, i),
 					      affinity_mask);
 	}
+
 	return err;
 }
 
@@ -166,14 +159,22 @@ void aq_pci_func_free_irqs(struct aq_nic_s *self)
 {
 	struct pci_dev *pdev = self->pdev;
 	unsigned int i;
+	void *irq_data;
 
 	for (i = 32U; i--;) {
 		if (!((1U << i) & self->msix_entry_mask))
 			continue;
+		if (self->aq_nic_cfg.link_irq_vec &&
+		    i == self->aq_nic_cfg.link_irq_vec)
+			irq_data = self;
+		else if (i < AQ_CFG_VECS_MAX)
+			irq_data = self->aq_vec[i];
+		else
+			continue;
 
 		if (pdev->msix_enabled)
 			irq_set_affinity_hint(pci_irq_vector(pdev, i), NULL);
-		free_irq(pci_irq_vector(pdev, i), self->aq_vec[i]);
+		free_irq(pci_irq_vector(pdev, i), irq_data);
 		self->msix_entry_mask &= ~(1U << i);
 	}
 }
@@ -183,7 +184,7 @@ unsigned int aq_pci_func_get_irq_type(struct aq_nic_s *self)
 	if (self->pdev->msix_enabled)
 		return AQ_HW_IRQ_MSIX;
 	if (self->pdev->msi_enabled)
-		return AQ_HW_IRQ_MSIX;
+		return AQ_HW_IRQ_MSI;
 	return AQ_HW_IRQ_LEGACY;
 }
 
@@ -221,6 +222,8 @@ static int aq_pci_probe(struct pci_dev *pdev,
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 	pci_set_drvdata(pdev, self);
 
+	mutex_init(&self->fwreq_mutex);
+
 	err = aq_pci_probe_get_hw_by_id(pdev, &self->aq_hw_ops,
 					&aq_nic_get_cfg(self)->aq_hw_caps);
 	if (err)
@@ -266,6 +269,7 @@ static int aq_pci_probe(struct pci_dev *pdev,
 	numvecs = min((u8)AQ_CFG_VECS_DEF,
 		      aq_nic_get_cfg(self)->aq_hw_caps->msix_irqs);
 	numvecs = min(numvecs, num_online_cpus());
+	numvecs += AQ_HW_SERVICE_IRQS;
 	/*enable interrupts */
 #if !AQ_CFG_FORCE_LEGACY_INT
 	err = pci_alloc_irq_vectors(self->pdev, 1, numvecs,
@@ -287,6 +291,8 @@ static int aq_pci_probe(struct pci_dev *pdev,
 	if (err < 0)
 		goto err_register;
 
+	aq_drvinfo_init(ndev);
+
 	return 0;
 
 err_register:
@@ -363,4 +369,13 @@ static struct pci_driver aq_pci_ops = {
 	.shutdown = aq_pci_shutdown,
 };
 
-module_pci_driver(aq_pci_ops);
+int aq_pci_func_register_driver(void)
+{
+	return pci_register_driver(&aq_pci_ops);
+}
+
+void aq_pci_func_unregister_driver(void)
+{
+	pci_unregister_driver(&aq_pci_ops);
+}
+
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.h b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.h
index aeee67bf69fa..77be7ee0d7b3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_pci_func.h: Declaration of PCI functions. */
@@ -24,9 +21,12 @@ struct aq_board_revision_s {
 
 int aq_pci_func_init(struct pci_dev *pdev);
 int aq_pci_func_alloc_irq(struct aq_nic_s *self, unsigned int i,
-			  char *name, void *aq_vec,
-			  cpumask_t *affinity_mask);
+			  char *name, irq_handler_t irq_handler,
+			  void *irq_arg, cpumask_t *affinity_mask);
 void aq_pci_func_free_irqs(struct aq_nic_s *self);
 unsigned int aq_pci_func_get_irq_type(struct aq_nic_s *self);
 
+int aq_pci_func_register_driver(void);
+void aq_pci_func_unregister_driver(void);
+
 #endif /* AQ_PCI_FUNC_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 74550ccc7a20..3901d7994ca1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_ring.c: Definition of functions for Rx/Tx rings. */
@@ -12,10 +9,89 @@
 #include "aq_ring.h"
 #include "aq_nic.h"
 #include "aq_hw.h"
+#include "aq_hw_utils.h"
 
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 
+static inline void aq_free_rxpage(struct aq_rxpage *rxpage, struct device *dev)
+{
+	unsigned int len = PAGE_SIZE << rxpage->order;
+
+	dma_unmap_page(dev, rxpage->daddr, len, DMA_FROM_DEVICE);
+
+	/* Drop the ref for being in the ring. */
+	__free_pages(rxpage->page, rxpage->order);
+	rxpage->page = NULL;
+}
+
+static int aq_get_rxpage(struct aq_rxpage *rxpage, unsigned int order,
+			 struct device *dev)
+{
+	struct page *page;
+	dma_addr_t daddr;
+	int ret = -ENOMEM;
+
+	page = dev_alloc_pages(order);
+	if (unlikely(!page))
+		goto err_exit;
+
+	daddr = dma_map_page(dev, page, 0, PAGE_SIZE << order,
+			     DMA_FROM_DEVICE);
+
+	if (unlikely(dma_mapping_error(dev, daddr)))
+		goto free_page;
+
+	rxpage->page = page;
+	rxpage->daddr = daddr;
+	rxpage->order = order;
+	rxpage->pg_off = 0;
+
+	return 0;
+
+free_page:
+	__free_pages(page, order);
+
+err_exit:
+	return ret;
+}
+
+static int aq_get_rxpages(struct aq_ring_s *self, struct aq_ring_buff_s *rxbuf,
+			  int order)
+{
+	int ret;
+
+	if (rxbuf->rxdata.page) {
+		/* One means ring is the only user and can reuse */
+		if (page_ref_count(rxbuf->rxdata.page) > 1) {
+			/* Try reuse buffer */
+			rxbuf->rxdata.pg_off += AQ_CFG_RX_FRAME_MAX;
+			if (rxbuf->rxdata.pg_off + AQ_CFG_RX_FRAME_MAX <=
+				(PAGE_SIZE << order)) {
+				self->stats.rx.pg_flips++;
+			} else {
+				/* Buffer exhausted. We have other users and
+				 * should release this page and realloc
+				 */
+				aq_free_rxpage(&rxbuf->rxdata,
+					       aq_nic_get_dev(self->aq_nic));
+				self->stats.rx.pg_losts++;
+			}
+		} else {
+			rxbuf->rxdata.pg_off = 0;
+			self->stats.rx.pg_reuses++;
+		}
+	}
+
+	if (!rxbuf->rxdata.page) {
+		ret = aq_get_rxpage(&rxbuf->rxdata, order,
+				    aq_nic_get_dev(self->aq_nic));
+		return ret;
+	}
+
+	return 0;
+}
+
 static struct aq_ring_s *aq_ring_alloc(struct aq_ring_s *self,
 				       struct aq_nic_s *aq_nic)
 {
@@ -81,6 +157,11 @@ struct aq_ring_s *aq_ring_rx_alloc(struct aq_ring_s *self,
 	self->idx = idx;
 	self->size = aq_nic_cfg->rxds;
 	self->dx_size = aq_nic_cfg->aq_hw_caps->rxd_size;
+	self->page_order = fls(AQ_CFG_RX_FRAME_MAX / PAGE_SIZE +
+			       (AQ_CFG_RX_FRAME_MAX % PAGE_SIZE ? 1 : 0)) - 1;
+
+	if (aq_nic_cfg->rxpageorder > self->page_order)
+		self->page_order = aq_nic_cfg->rxpageorder;
 
 	self = aq_ring_alloc(self, aq_nic);
 	if (!self) {
@@ -139,10 +220,10 @@ void aq_ring_queue_stop(struct aq_ring_s *ring)
 bool aq_ring_tx_clean(struct aq_ring_s *self)
 {
 	struct device *dev = aq_nic_get_dev(self->aq_nic);
-	unsigned int budget = AQ_CFG_TX_CLEAN_BUDGET;
+	unsigned int budget;
 
-	for (; self->sw_head != self->hw_head && budget--;
-		self->sw_head = aq_ring_next_dx(self, self->sw_head)) {
+	for (budget = AQ_CFG_TX_CLEAN_BUDGET;
+	     budget && self->sw_head != self->hw_head; budget--) {
 		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
 
 		if (likely(buff->is_mapped)) {
@@ -167,6 +248,7 @@ bool aq_ring_tx_clean(struct aq_ring_s *self)
 
 		buff->pa = 0U;
 		buff->eop_index = 0xffffU;
+		self->sw_head = aq_ring_next_dx(self, self->sw_head);
 	}
 
 	return !!budget;
@@ -186,11 +268,12 @@ static void aq_rx_checksum(struct aq_ring_s *self,
 	}
 	if (buff->is_ip_cso) {
 		__skb_incr_checksum_unnecessary(skb);
-		if (buff->is_udp_cso || buff->is_tcp_cso)
-			__skb_incr_checksum_unnecessary(skb);
 	} else {
 		skb->ip_summed = CHECKSUM_NONE;
 	}
+
+	if (buff->is_udp_cso || buff->is_tcp_cso)
+		__skb_incr_checksum_unnecessary(skb);
 }
 
 #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
@@ -200,93 +283,136 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 		     int budget)
 {
 	struct net_device *ndev = aq_nic_get_ndev(self->aq_nic);
-	int err = 0;
 	bool is_rsc_completed = true;
+	int err = 0;
 
 	for (; (self->sw_head != self->hw_head) && budget;
 		self->sw_head = aq_ring_next_dx(self, self->sw_head),
 		--budget, ++(*work_done)) {
 		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
+		struct aq_ring_buff_s *buff_ = NULL;
 		struct sk_buff *skb = NULL;
 		unsigned int next_ = 0U;
 		unsigned int i = 0U;
-		struct aq_ring_buff_s *buff_ = NULL;
-
-		if (buff->is_error) {
-			__free_pages(buff->page, 0);
-			continue;
-		}
+		u16 hdr_len;
 
 		if (buff->is_cleaned)
 			continue;
 
 		if (!buff->is_eop) {
-			for (next_ = buff->next,
-			     buff_ = &self->buff_ring[next_]; true;
-			     next_ = buff_->next,
-			     buff_ = &self->buff_ring[next_]) {
+			buff_ = buff;
+			do {
+				next_ = buff_->next,
+				buff_ = &self->buff_ring[next_];
 				is_rsc_completed =
 					aq_ring_dx_in_range(self->sw_head,
 							    next_,
 							    self->hw_head);
 
-				if (unlikely(!is_rsc_completed)) {
-					is_rsc_completed = false;
+				if (unlikely(!is_rsc_completed))
 					break;
-				}
 
-				if (buff_->is_eop)
-					break;
-			}
+				buff->is_error |= buff_->is_error;
+
+			} while (!buff_->is_eop);
 
 			if (!is_rsc_completed) {
 				err = 0;
 				goto err_exit;
 			}
+			if (buff->is_error) {
+				buff_ = buff;
+				do {
+					next_ = buff_->next,
+					buff_ = &self->buff_ring[next_];
+
+					buff_->is_cleaned = true;
+				} while (!buff_->is_eop);
+
+				++self->stats.rx.errors;
+				continue;
+			}
+		}
+
+		if (buff->is_error) {
+			++self->stats.rx.errors;
+			continue;
 		}
 
+		dma_sync_single_range_for_cpu(aq_nic_get_dev(self->aq_nic),
+					      buff->rxdata.daddr,
+					      buff->rxdata.pg_off,
+					      buff->len, DMA_FROM_DEVICE);
+
 		/* for single fragment packets use build_skb() */
 		if (buff->is_eop &&
 		    buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) {
-			skb = build_skb(page_address(buff->page),
+			skb = build_skb(aq_buf_vaddr(&buff->rxdata),
 					AQ_CFG_RX_FRAME_MAX);
 			if (unlikely(!skb)) {
 				err = -ENOMEM;
 				goto err_exit;
 			}
-
 			skb_put(skb, buff->len);
+			page_ref_inc(buff->rxdata.page);
 		} else {
-			skb = netdev_alloc_skb(ndev, ETH_HLEN);
+			skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE);
 			if (unlikely(!skb)) {
 				err = -ENOMEM;
 				goto err_exit;
 			}
-			skb_put(skb, ETH_HLEN);
-			memcpy(skb->data, page_address(buff->page), ETH_HLEN);
 
-			skb_add_rx_frag(skb, 0, buff->page, ETH_HLEN,
-					buff->len - ETH_HLEN,
-					SKB_TRUESIZE(buff->len - ETH_HLEN));
+			hdr_len = buff->len;
+			if (hdr_len > AQ_CFG_RX_HDR_SIZE)
+				hdr_len = eth_get_headlen(skb->dev,
+							  aq_buf_vaddr(&buff->rxdata),
+							  AQ_CFG_RX_HDR_SIZE);
+
+			memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata),
+			       ALIGN(hdr_len, sizeof(long)));
+
+			if (buff->len - hdr_len > 0) {
+				skb_add_rx_frag(skb, 0, buff->rxdata.page,
+						buff->rxdata.pg_off + hdr_len,
+						buff->len - hdr_len,
+						AQ_CFG_RX_FRAME_MAX);
+				page_ref_inc(buff->rxdata.page);
+			}
 
 			if (!buff->is_eop) {
-				for (i = 1U, next_ = buff->next,
-				     buff_ = &self->buff_ring[next_];
-				     true; next_ = buff_->next,
-				     buff_ = &self->buff_ring[next_], ++i) {
-					skb_add_rx_frag(skb, i,
-							buff_->page, 0,
+				buff_ = buff;
+				i = 1U;
+				do {
+					next_ = buff_->next,
+					buff_ = &self->buff_ring[next_];
+
+					dma_sync_single_range_for_cpu(
+							aq_nic_get_dev(self->aq_nic),
+							buff_->rxdata.daddr,
+							buff_->rxdata.pg_off,
+							buff_->len,
+							DMA_FROM_DEVICE);
+					skb_add_rx_frag(skb, i++,
+							buff_->rxdata.page,
+							buff_->rxdata.pg_off,
 							buff_->len,
-							SKB_TRUESIZE(buff->len -
-							ETH_HLEN));
+							AQ_CFG_RX_FRAME_MAX);
+					page_ref_inc(buff_->rxdata.page);
 					buff_->is_cleaned = 1;
 
-					if (buff_->is_eop)
-						break;
-				}
+					buff->is_ip_cso &= buff_->is_ip_cso;
+					buff->is_udp_cso &= buff_->is_udp_cso;
+					buff->is_tcp_cso &= buff_->is_tcp_cso;
+					buff->is_cso_err |= buff_->is_cso_err;
+
+				} while (!buff_->is_eop);
 			}
 		}
 
+		if (buff->is_vlan)
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       buff->vlan_rx_tag);
+
 		skb->protocol = eth_type_trans(skb, ndev);
 
 		aq_rx_checksum(self, buff, skb);
@@ -309,12 +435,15 @@ err_exit:
 
 int aq_ring_rx_fill(struct aq_ring_s *self)
 {
-	unsigned int pages_order = fls(AQ_CFG_RX_FRAME_MAX / PAGE_SIZE +
-		(AQ_CFG_RX_FRAME_MAX % PAGE_SIZE ? 1 : 0)) - 1;
+	unsigned int page_order = self->page_order;
 	struct aq_ring_buff_s *buff = NULL;
 	int err = 0;
 	int i = 0;
 
+	if (aq_ring_avail_dx(self) < min_t(unsigned int, AQ_CFG_RX_REFILL_THRES,
+					   self->size / 2))
+		return err;
+
 	for (i = aq_ring_avail_dx(self); i--;
 		self->sw_tail = aq_ring_next_dx(self, self->sw_tail)) {
 		buff = &self->buff_ring[self->sw_tail];
@@ -322,30 +451,15 @@ int aq_ring_rx_fill(struct aq_ring_s *self)
 		buff->flags = 0U;
 		buff->len = AQ_CFG_RX_FRAME_MAX;
 
-		buff->page = alloc_pages(GFP_ATOMIC | __GFP_COMP, pages_order);
-		if (!buff->page) {
-			err = -ENOMEM;
+		err = aq_get_rxpages(self, buff, page_order);
+		if (err)
 			goto err_exit;
-		}
-
-		buff->pa = dma_map_page(aq_nic_get_dev(self->aq_nic),
-					buff->page, 0,
-					AQ_CFG_RX_FRAME_MAX, DMA_FROM_DEVICE);
-
-		if (dma_mapping_error(aq_nic_get_dev(self->aq_nic), buff->pa)) {
-			err = -ENOMEM;
-			goto err_exit;
-		}
 
+		buff->pa = aq_buf_daddr(&buff->rxdata);
 		buff = NULL;
 	}
 
 err_exit:
-	if (err < 0) {
-		if (buff && buff->page)
-			__free_pages(buff->page, 0);
-	}
-
 	return err;
 }
 
@@ -358,10 +472,7 @@ void aq_ring_rx_deinit(struct aq_ring_s *self)
 		self->sw_head = aq_ring_next_dx(self, self->sw_head)) {
 		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
 
-		dma_unmap_page(aq_nic_get_dev(self->aq_nic), buff->pa,
-			       AQ_CFG_RX_FRAME_MAX, DMA_FROM_DEVICE);
-
-		__free_pages(buff->page, 0);
+		aq_free_rxpage(&buff->rxdata, aq_nic_get_dev(self->aq_nic));
 	}
 
 err_exit:;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
index ac1329f4051d..47abd09d06c2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_ring.h: Declaration of functions for Rx/Tx rings. */
@@ -17,13 +14,20 @@
 struct page;
 struct aq_nic_cfg_s;
 
+struct aq_rxpage {
+	struct page *page;
+	dma_addr_t daddr;
+	unsigned int order;
+	unsigned int pg_off;
+};
+
 /*           TxC       SOP        DX         EOP
  *         +----------+----------+----------+-----------
  *   8bytes|len l3,l4 | pa       | pa       | pa
  *         +----------+----------+----------+-----------
  * 4/8bytes|len pkt   |len pkt   |          | skb
  *         +----------+----------+----------+-----------
- * 4/8bytes|is_txc    |len,flags |len       |len,is_eop
+ * 4/8bytes|is_gso    |len,flags |len       |len,is_eop
  *         +----------+----------+----------+-----------
  *
  *  This aq_ring_buff_s doesn't have endianness dependency.
@@ -31,28 +35,22 @@ struct aq_nic_cfg_s;
  */
 struct __packed aq_ring_buff_s {
 	union {
+		/* RX/TX */
+		dma_addr_t pa;
 		/* RX */
 		struct {
 			u32 rss_hash;
 			u16 next;
 			u8 is_hash_l4;
 			u8 rsvd1;
-			struct page *page;
+			struct aq_rxpage rxdata;
+			u16 vlan_rx_tag;
 		};
 		/* EOP */
 		struct {
 			dma_addr_t pa_eop;
 			struct sk_buff *skb;
 		};
-		/* DX */
-		struct {
-			dma_addr_t pa;
-		};
-		/* SOP */
-		struct {
-			dma_addr_t pa_sop;
-			u32 len_pkt_sop;
-		};
 		/* TxC */
 		struct {
 			u32 mss;
@@ -62,6 +60,7 @@ struct __packed aq_ring_buff_s {
 			u8 is_ipv6:1;
 			u8 rsvd2:7;
 			u32 len_pkt;
+			u16 vlan_tx_tag;
 		};
 	};
 	union {
@@ -73,11 +72,12 @@ struct __packed aq_ring_buff_s {
 			u32 is_cso_err:1;
 			u32 is_sop:1;
 			u32 is_eop:1;
-			u32 is_txc:1;
+			u32 is_gso:1;
 			u32 is_mapped:1;
 			u32 is_cleaned:1;
 			u32 is_error:1;
-			u32 rsvd3:6;
+			u32 is_vlan:1;
+			u32 rsvd3:5;
 			u16 eop_index;
 			u16 rsvd4;
 		};
@@ -91,6 +91,9 @@ struct aq_ring_stats_rx_s {
 	u64 bytes;
 	u64 lro_packets;
 	u64 jumbo_packets;
+	u64 pg_losts;
+	u64 pg_flips;
+	u64 pg_reuses;
 };
 
 struct aq_ring_stats_tx_s {
@@ -116,6 +119,7 @@ struct aq_ring_s {
 	unsigned int size;	/* descriptors number */
 	unsigned int dx_size;	/* TX or RX descriptor size,  */
 				/* stored here for fater math */
+	unsigned int page_order;
 	union aq_ring_stats_s stats;
 	dma_addr_t dx_ring_pa;
 };
@@ -126,6 +130,16 @@ struct aq_ring_param_s {
 	cpumask_t affinity_mask;
 };
 
+static inline void *aq_buf_vaddr(struct aq_rxpage *rxpage)
+{
+	return page_to_virt(rxpage->page) + rxpage->pg_off;
+}
+
+static inline dma_addr_t aq_buf_daddr(struct aq_rxpage *rxpage)
+{
+	return rxpage->daddr + rxpage->pg_off;
+}
+
 static inline unsigned int aq_ring_next_dx(struct aq_ring_s *self,
 					   unsigned int dx)
 {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_rss.h b/drivers/net/ethernet/aquantia/atlantic/aq_rss.h
index 1db6eb20a8f2..39b1f43c8ad7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_rss.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_rss.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_rss.h: Receive Side Scaling definitions. */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_utils.h b/drivers/net/ethernet/aquantia/atlantic/aq_utils.h
index 786ea8187c69..d3a0b2ec0279 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_utils.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_utils.h: Useful macro and structures used in all layers of driver. */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index d335c334fa56..715685aa48c3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_vec.c: Definition of common structure for vector of Rx and Tx rings.
@@ -353,6 +350,9 @@ void aq_vec_add_stats(struct aq_vec_s *self,
 		stats_rx->errors += rx->errors;
 		stats_rx->jumbo_packets += rx->jumbo_packets;
 		stats_rx->lro_packets += rx->lro_packets;
+		stats_rx->pg_losts += rx->pg_losts;
+		stats_rx->pg_flips += rx->pg_flips;
+		stats_rx->pg_reuses += rx->pg_reuses;
 
 		stats_tx->packets += tx->packets;
 		stats_tx->bytes += tx->bytes;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.h b/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
index 8bdf60bb3f63..0fe8e0904c7f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File aq_vec.h: Definition of common structures for vector of Rx and Tx rings.
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 2469ed4d86b9..359a4d387185 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_a0.c: Definition of Atlantic hardware specific functions. */
@@ -85,6 +82,7 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc109 = {
 static int hw_atl_a0_hw_reset(struct aq_hw_s *self)
 {
 	int err = 0;
+	u32 val;
 
 	hw_atl_glb_glb_reg_res_dis_set(self, 1U);
 	hw_atl_pci_pci_reg_res_dis_set(self, 0U);
@@ -95,7 +93,9 @@ static int hw_atl_a0_hw_reset(struct aq_hw_s *self)
 	hw_atl_glb_soft_res_set(self, 1);
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(hw_atl_glb_soft_res_get(self) == 0, 1000U, 10U);
+	err = readx_poll_timeout_atomic(hw_atl_glb_soft_res_get,
+					self, val, val == 0,
+					1000U, 10000U);
 	if (err < 0)
 		goto err_exit;
 
@@ -103,7 +103,9 @@ static int hw_atl_a0_hw_reset(struct aq_hw_s *self)
 	hw_atl_itr_res_irq_set(self, 1U);
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(hw_atl_itr_res_irq_get(self) == 0, 1000U, 10U);
+	err = readx_poll_timeout_atomic(hw_atl_itr_res_irq_get,
+					self, val, val == 0,
+					1000U, 10000U);
 	if (err < 0)
 		goto err_exit;
 
@@ -181,6 +183,7 @@ static int hw_atl_a0_hw_rss_hash_set(struct aq_hw_s *self,
 	int err = 0;
 	unsigned int i = 0U;
 	unsigned int addr = 0U;
+	u32 val;
 
 	for (i = 10, addr = 0U; i--; ++addr) {
 		u32 key_data = cfg->is_rss ?
@@ -188,8 +191,9 @@ static int hw_atl_a0_hw_rss_hash_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_key_wr_data_set(self, key_data);
 		hw_atl_rpf_rss_key_addr_set(self, addr);
 		hw_atl_rpf_rss_key_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_key_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_key_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -207,8 +211,9 @@ static int hw_atl_a0_hw_rss_set(struct aq_hw_s *self,
 	u32 i = 0U;
 	u32 num_rss_queues = max(1U, self->aq_nic_cfg->num_rss_queues);
 	int err = 0;
-	u16 bitary[(HW_ATL_A0_RSS_REDIRECTION_MAX *
-					HW_ATL_A0_RSS_REDIRECTION_BITS / 16U)];
+	u16 bitary[1 + (HW_ATL_A0_RSS_REDIRECTION_MAX *
+		   HW_ATL_A0_RSS_REDIRECTION_BITS / 16U)];
+	u32 val;
 
 	memset(bitary, 0, sizeof(bitary));
 
@@ -222,8 +227,9 @@ static int hw_atl_a0_hw_rss_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_redir_tbl_wr_data_set(self, bitary[i]);
 		hw_atl_rpf_rss_redir_tbl_addr_set(self, i);
 		hw_atl_rpf_rss_redir_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_redir_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_redir_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -341,10 +347,10 @@ err_exit:
 static int hw_atl_a0_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 {
 	static u32 aq_hw_atl_igcr_table_[4][2] = {
-		{ 0x20000000U, 0x20000000U }, /* AQ_IRQ_INVALID */
-		{ 0x20000080U, 0x20000080U }, /* AQ_IRQ_LEGACY */
-		{ 0x20000021U, 0x20000025U }, /* AQ_IRQ_MSI */
-		{ 0x20000022U, 0x20000026U }  /* AQ_IRQ_MSIX */
+		[AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U },
+		[AQ_HW_IRQ_LEGACY]  = { 0x20000080U, 0x20000080U },
+		[AQ_HW_IRQ_MSI]     = { 0x20000021U, 0x20000025U },
+		[AQ_HW_IRQ_MSIX]    = { 0x20000022U, 0x20000026U },
 	};
 
 	int err = 0;
@@ -445,7 +451,7 @@ static int hw_atl_a0_hw_ring_tx_xmit(struct aq_hw_s *self,
 
 		buff = &ring->buff_ring[ring->sw_tail];
 
-		if (buff->is_txc) {
+		if (buff->is_gso) {
 			txd->ctl |= (buff->len_l3 << 31) |
 				(buff->len_l2 << 24) |
 				HW_ATL_A0_TXD_CTL_CMD_TCP |
@@ -610,8 +616,6 @@ err_exit:
 static int hw_atl_a0_hw_ring_rx_receive(struct aq_hw_s *self,
 					struct aq_ring_s *ring)
 {
-	struct device *ndev = aq_nic_get_dev(ring->aq_nic);
-
 	for (; ring->hw_head != ring->sw_tail;
 		ring->hw_head = aq_ring_next_dx(ring, ring->hw_head)) {
 		struct aq_ring_buff_s *buff = NULL;
@@ -678,8 +682,6 @@ static int hw_atl_a0_hw_ring_rx_receive(struct aq_hw_s *self,
 		is_err &= ~0x18U;
 		is_err &= ~0x04U;
 
-		dma_unmap_page(ndev, buff->pa, buff->len, DMA_FROM_DEVICE);
-
 		if (is_err || rxd_wb->type & 0x1000U) {
 			/* status error or DMA error */
 			buff->is_error = 1U;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.h
index 25fe954def03..1a294ad4d17d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_a0.h: Declaration of abstract interface for Atlantic hardware
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
index a021dc431ef7..1b9b2e5601ed 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_a0_internal.h: Definition of Atlantic A0 chip specific
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index b58ca7cb8e9d..30f7fc4c97ff 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_b0.c: Definition of Atlantic hardware specific functions. */
@@ -43,7 +40,9 @@
 			NETIF_F_TSO |     \
 			NETIF_F_LRO |     \
 			NETIF_F_NTUPLE |  \
-			NETIF_F_HW_VLAN_CTAG_FILTER, \
+			NETIF_F_HW_VLAN_CTAG_FILTER | \
+			NETIF_F_HW_VLAN_CTAG_RX |     \
+			NETIF_F_HW_VLAN_CTAG_TX,      \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
@@ -173,6 +172,7 @@ static int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
 	int err = 0;
 	unsigned int i = 0U;
 	unsigned int addr = 0U;
+	u32 val;
 
 	for (i = 10, addr = 0U; i--; ++addr) {
 		u32 key_data = cfg->is_rss ?
@@ -180,8 +180,9 @@ static int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_key_wr_data_set(self, key_data);
 		hw_atl_rpf_rss_key_addr_set(self, addr);
 		hw_atl_rpf_rss_key_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_key_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_key_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -199,8 +200,9 @@ static int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
 	u32 i = 0U;
 	u32 num_rss_queues = max(1U, self->aq_nic_cfg->num_rss_queues);
 	int err = 0;
-	u16 bitary[(HW_ATL_B0_RSS_REDIRECTION_MAX *
-					HW_ATL_B0_RSS_REDIRECTION_BITS / 16U)];
+	u16 bitary[1 + (HW_ATL_B0_RSS_REDIRECTION_MAX *
+		   HW_ATL_B0_RSS_REDIRECTION_BITS / 16U)];
+	u32 val;
 
 	memset(bitary, 0, sizeof(bitary));
 
@@ -214,8 +216,9 @@ static int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_redir_tbl_wr_data_set(self, bitary[i]);
 		hw_atl_rpf_rss_redir_tbl_addr_set(self, i);
 		hw_atl_rpf_rss_redir_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_redir_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_redir_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -244,6 +247,9 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 	/* LSO offloads*/
 	hw_atl_tdm_large_send_offload_en_set(self, 0xFFFFFFFFU);
 
+	/* Outer VLAN tag offload */
+	hw_atl_rpo_outer_vlan_tag_mode_set(self, 1U);
+
 /* LRO offloads */
 	{
 		unsigned int val = (8U < HW_ATL_B0_LRO_RXD_MAX) ? 0x3U :
@@ -255,13 +261,18 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 
 		hw_atl_rpo_lro_time_base_divider_set(self, 0x61AU);
 		hw_atl_rpo_lro_inactive_interval_set(self, 0);
-		hw_atl_rpo_lro_max_coalescing_interval_set(self, 2);
+		/* the LRO timebase divider is 5 uS (0x61a),
+		 * which is multiplied by 50(0x32)
+		 * to get a maximum coalescing interval of 250 uS,
+		 * which is the default value
+		 */
+		hw_atl_rpo_lro_max_coalescing_interval_set(self, 50);
 
 		hw_atl_rpo_lro_qsessions_lim_set(self, 1U);
 
 		hw_atl_rpo_lro_total_desc_lim_set(self, 2U);
 
-		hw_atl_rpo_lro_patch_optimization_en_set(self, 0U);
+		hw_atl_rpo_lro_patch_optimization_en_set(self, 1U);
 
 		hw_atl_rpo_lro_min_pay_of_first_pkt_set(self, 10U);
 
@@ -269,12 +280,19 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 
 		hw_atl_rpo_lro_en_set(self,
 				      aq_nic_cfg->is_lro ? 0xFFFFFFFFU : 0U);
+		hw_atl_itr_rsc_en_set(self,
+				      aq_nic_cfg->is_lro ? 0xFFFFFFFFU : 0U);
+
+		hw_atl_itr_rsc_delay_set(self, 1U);
 	}
 	return aq_hw_err_from_flags(self);
 }
 
 static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 {
+	/* Tx TC/Queue number config */
+	hw_atl_rpb_tps_tx_tc_mode_set(self, 1U);
+
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_last_pkt_set(self, 0x0F7FU);
@@ -371,10 +389,10 @@ err_exit:
 static int hw_atl_b0_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 {
 	static u32 aq_hw_atl_igcr_table_[4][2] = {
-		{ 0x20000000U, 0x20000000U }, /* AQ_IRQ_INVALID */
-		{ 0x20000080U, 0x20000080U }, /* AQ_IRQ_LEGACY */
-		{ 0x20000021U, 0x20000025U }, /* AQ_IRQ_MSI */
-		{ 0x20000022U, 0x20000026U }  /* AQ_IRQ_MSIX */
+		[AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U },
+		[AQ_HW_IRQ_LEGACY]  = { 0x20000080U, 0x20000080U },
+		[AQ_HW_IRQ_MSI]     = { 0x20000021U, 0x20000025U },
+		[AQ_HW_IRQ_MSIX]    = { 0x20000022U, 0x20000026U },
 	};
 
 	int err = 0;
@@ -426,6 +444,11 @@ static int hw_atl_b0_hw_init(struct aq_hw_s *self, u8 *mac_addr)
 				   ((HW_ATL_B0_ERR_INT << 0x18) | (1U << 0x1F)) |
 			    ((HW_ATL_B0_ERR_INT << 0x10) | (1U << 0x17)), 0U);
 
+	/* Enable link interrupt */
+	if (aq_nic_cfg->link_irq_vec)
+		hw_atl_reg_gen_irq_map_set(self, BIT(7) |
+					   aq_nic_cfg->link_irq_vec, 3U);
+
 	hw_atl_b0_hw_offload_set(self, aq_nic_cfg);
 
 err_exit:
@@ -469,6 +492,7 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
 	unsigned int buff_pa_len = 0U;
 	unsigned int pkt_len = 0U;
 	unsigned int frag_count = 0U;
+	bool is_vlan = false;
 	bool is_gso = false;
 
 	buff = &ring->buff_ring[ring->sw_tail];
@@ -483,36 +507,44 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
 
 		buff = &ring->buff_ring[ring->sw_tail];
 
-		if (buff->is_txc) {
+		if (buff->is_gso) {
+			txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_TCP;
+			txd->ctl |= HW_ATL_B0_TXD_CTL_DESC_TYPE_TXC;
 			txd->ctl |= (buff->len_l3 << 31) |
-				(buff->len_l2 << 24) |
-				HW_ATL_B0_TXD_CTL_CMD_TCP |
-				HW_ATL_B0_TXD_CTL_DESC_TYPE_TXC;
-			txd->ctl2 |= (buff->mss << 16) |
-				(buff->len_l4 << 8) |
-				(buff->len_l3 >> 1);
+				    (buff->len_l2 << 24);
+			txd->ctl2 |= (buff->mss << 16);
+			is_gso = true;
 
 			pkt_len -= (buff->len_l4 +
 				    buff->len_l3 +
 				    buff->len_l2);
-			is_gso = true;
-
 			if (buff->is_ipv6)
 				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_IPV6;
-		} else {
+			txd->ctl2 |= (buff->len_l4 << 8) |
+				     (buff->len_l3 >> 1);
+		}
+		if (buff->is_vlan) {
+			txd->ctl |= HW_ATL_B0_TXD_CTL_DESC_TYPE_TXC;
+			txd->ctl |= buff->vlan_tx_tag << 4;
+			is_vlan = true;
+		}
+		if (!buff->is_gso && !buff->is_vlan) {
 			buff_pa_len = buff->len;
 
 			txd->buf_addr = buff->pa;
 			txd->ctl |= (HW_ATL_B0_TXD_CTL_BLEN &
 						((u32)buff_pa_len << 4));
 			txd->ctl |= HW_ATL_B0_TXD_CTL_DESC_TYPE_TXD;
+
 			/* PAY_LEN */
 			txd->ctl2 |= HW_ATL_B0_TXD_CTL2_LEN & (pkt_len << 14);
 
-			if (is_gso) {
-				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_LSO;
+			if (is_gso || is_vlan) {
+				/* enable tx context */
 				txd->ctl2 |= HW_ATL_B0_TXD_CTL2_CTX_EN;
 			}
+			if (is_gso)
+				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_LSO;
 
 			/* Tx checksum offloads */
 			if (buff->is_ip_cso)
@@ -521,13 +553,16 @@ static int hw_atl_b0_hw_ring_tx_xmit(struct aq_hw_s *self,
 			if (buff->is_udp_cso || buff->is_tcp_cso)
 				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_TUCSO;
 
+			if (is_vlan)
+				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_VLAN;
+
 			if (unlikely(buff->is_eop)) {
 				txd->ctl |= HW_ATL_B0_TXD_CTL_EOP;
 				txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_WB;
 				is_gso = false;
+				is_vlan = false;
 			}
 		}
-
 		ring->sw_tail = aq_ring_next_dx(ring, ring->sw_tail);
 	}
 
@@ -541,6 +576,7 @@ static int hw_atl_b0_hw_ring_rx_init(struct aq_hw_s *self,
 {
 	u32 dma_desc_addr_lsw = (u32)aq_ring->dx_ring_pa;
 	u32 dma_desc_addr_msw = (u32)(((u64)aq_ring->dx_ring_pa) >> 32);
+	u32 vlan_rx_stripping = self->aq_nic_cfg->is_vlan_rx_strip;
 
 	hw_atl_rdm_rx_desc_en_set(self, false, aq_ring->idx);
 
@@ -560,7 +596,8 @@ static int hw_atl_b0_hw_ring_rx_init(struct aq_hw_s *self,
 
 	hw_atl_rdm_rx_desc_head_buff_size_set(self, 0U, aq_ring->idx);
 	hw_atl_rdm_rx_desc_head_splitting_set(self, 0U, aq_ring->idx);
-	hw_atl_rpo_rx_desc_vlan_stripping_set(self, 0U, aq_ring->idx);
+	hw_atl_rpo_rx_desc_vlan_stripping_set(self, !!vlan_rx_stripping,
+					      aq_ring->idx);
 
 	/* Rx ring set mode */
 
@@ -647,8 +684,6 @@ err_exit:
 static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
 					struct aq_ring_s *ring)
 {
-	struct device *ndev = aq_nic_get_dev(ring->aq_nic);
-
 	for (; ring->hw_head != ring->sw_tail;
 		ring->hw_head = aq_ring_next_dx(ring, ring->hw_head)) {
 		struct aq_ring_buff_s *buff = NULL;
@@ -665,11 +700,15 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
 
 		buff = &ring->buff_ring[ring->hw_head];
 
+		buff->flags = 0U;
+		buff->is_hash_l4 = 0U;
+
 		rx_stat = (0x0000003CU & rxd_wb->status) >> 2;
 
 		is_rx_check_sum_enabled = (rxd_wb->type >> 19) & 0x3U;
 
-		pkt_type = 0xFFU & (rxd_wb->type >> 4);
+		pkt_type = (rxd_wb->type & HW_ATL_B0_RXD_WB_STAT_PKTTYPE) >>
+			   HW_ATL_B0_RXD_WB_STAT_PKTTYPE_SHIFT;
 
 		if (is_rx_check_sum_enabled & BIT(0) &&
 		    (0x0U == (pkt_type & 0x3U)))
@@ -690,43 +729,51 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
 			buff->is_cso_err = 0U;
 		}
 
-		dma_unmap_page(ndev, buff->pa, buff->len, DMA_FROM_DEVICE);
+		if (self->aq_nic_cfg->is_vlan_rx_strip &&
+		    ((pkt_type & HW_ATL_B0_RXD_WB_PKTTYPE_VLAN) ||
+		     (pkt_type & HW_ATL_B0_RXD_WB_PKTTYPE_VLAN_DOUBLE))) {
+			buff->is_vlan = 1;
+			buff->vlan_rx_tag = le16_to_cpu(rxd_wb->vlan);
+		}
 
 		if ((rx_stat & BIT(0)) || rxd_wb->type & 0x1000U) {
 			/* MAC error or DMA error */
 			buff->is_error = 1U;
-		} else {
-			if (self->aq_nic_cfg->is_rss) {
-				/* last 4 byte */
-				u16 rss_type = rxd_wb->type & 0xFU;
-
-				if (rss_type && rss_type < 0x8U) {
-					buff->is_hash_l4 = (rss_type == 0x4 ||
-					rss_type == 0x5);
-					buff->rss_hash = rxd_wb->rss_hash;
-				}
+		}
+		if (self->aq_nic_cfg->is_rss) {
+			/* last 4 byte */
+			u16 rss_type = rxd_wb->type & 0xFU;
+
+			if (rss_type && rss_type < 0x8U) {
+				buff->is_hash_l4 = (rss_type == 0x4 ||
+				rss_type == 0x5);
+				buff->rss_hash = rxd_wb->rss_hash;
 			}
+		}
 
-			if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
-				buff->len = rxd_wb->pkt_len %
-					AQ_CFG_RX_FRAME_MAX;
-				buff->len = buff->len ?
-					buff->len : AQ_CFG_RX_FRAME_MAX;
-				buff->next = 0U;
-				buff->is_eop = 1U;
+		if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
+			buff->len = rxd_wb->pkt_len %
+				AQ_CFG_RX_FRAME_MAX;
+			buff->len = buff->len ?
+				buff->len : AQ_CFG_RX_FRAME_MAX;
+			buff->next = 0U;
+			buff->is_eop = 1U;
+		} else {
+			buff->len =
+				rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ?
+				AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len;
+
+			if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
+				rxd_wb->status) {
+				/* LRO */
+				buff->next = rxd_wb->next_desc_ptr;
+				++ring->stats.rx.lro_packets;
 			} else {
-				if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
-					rxd_wb->status) {
-					/* LRO */
-					buff->next = rxd_wb->next_desc_ptr;
-					++ring->stats.rx.lro_packets;
-				} else {
-					/* jumbo */
-					buff->next =
-						aq_ring_next_dx(ring,
-								ring->hw_head);
-					++ring->stats.rx.jumbo_packets;
-				}
+				/* jumbo */
+				buff->next =
+					aq_ring_next_dx(ring,
+							ring->hw_head);
+				++ring->stats.rx.jumbo_packets;
 			}
 		}
 	}
@@ -761,8 +808,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 					  unsigned int packet_filter)
 {
 	unsigned int i = 0U;
+	struct aq_nic_cfg_s *cfg = self->aq_nic_cfg;
+
+	hw_atl_rpfl2promiscuous_mode_en_set(self,
+					    IS_FILTER_ENABLED(IFF_PROMISC));
+
+	hw_atl_rpf_vlan_prom_mode_en_set(self,
+				     IS_FILTER_ENABLED(IFF_PROMISC) ||
+				     cfg->is_vlan_force_promisc);
 
-	hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC));
 	hw_atl_rpfl2multicast_flr_en_set(self,
 					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
 
@@ -771,13 +825,13 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 	hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST));
 
-	self->aq_nic_cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST);
+	cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST);
 
 	for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i)
 		hw_atl_rpfl2_uc_flr_en_set(self,
-					   (self->aq_nic_cfg->is_mc_list_enabled &&
-				    (i <= self->aq_nic_cfg->mc_list_count)) ?
-				    1U : 0U, i);
+					   (cfg->is_mc_list_enabled &&
+					    (i <= cfg->mc_list_count)) ?
+					   1U : 0U, i);
 
 	return aq_hw_err_from_flags(self);
 }
@@ -1069,7 +1123,7 @@ static int hw_atl_b0_hw_vlan_set(struct aq_hw_s *self,
 static int hw_atl_b0_hw_vlan_ctrl(struct aq_hw_s *self, bool enable)
 {
 	/* set promisc in case of disabing the vland filter */
-	hw_atl_rpf_vlan_prom_mode_en_set(self, !!!enable);
+	hw_atl_rpf_vlan_prom_mode_en_set(self, !enable);
 
 	return aq_hw_err_from_flags(self);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
index 2cc8dacfdc27..09af1683034b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_b0.h: Declaration of abstract interface for Atlantic hardware
@@ -32,9 +29,6 @@ extern const struct aq_hw_caps_s hw_atl_b0_caps_aqc109;
 #define hw_atl_b0_caps_aqc111s hw_atl_b0_caps_aqc108
 #define hw_atl_b0_caps_aqc112s hw_atl_b0_caps_aqc109
 
-#define hw_atl_b0_caps_aqc111e hw_atl_b0_caps_aqc108
-#define hw_atl_b0_caps_aqc112e hw_atl_b0_caps_aqc109
-
 extern const struct aq_hw_ops hw_atl_ops_b0;
 
 #define hw_atl_ops_b1 hw_atl_ops_b0
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index b318eefd36ae..808d8cd4252a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_b0_internal.h: Definition of Atlantic B0 chip specific
@@ -78,7 +75,7 @@
 #define HW_ATL_B0_TC_MAX 1U
 #define HW_ATL_B0_RSS_MAX 8U
 
-#define HW_ATL_B0_LRO_RXD_MAX 2U
+#define HW_ATL_B0_LRO_RXD_MAX 16U
 #define HW_ATL_B0_RS_SLIP_ENABLED  0U
 
 /* (256k -1(max pay_len) - 54(header)) */
@@ -110,10 +107,17 @@
 #define HW_ATL_B0_RXD_NCEA0 (0x1)
 
 #define HW_ATL_B0_RXD_WB_STAT_RSSTYPE (0x0000000F)
+#define HW_ATL_B0_RXD_WB_STAT_RSSTYPE_SHIFT (0x0)
 #define HW_ATL_B0_RXD_WB_STAT_PKTTYPE (0x00000FF0)
+#define HW_ATL_B0_RXD_WB_STAT_PKTTYPE_SHIFT (0x4)
 #define HW_ATL_B0_RXD_WB_STAT_RXCTRL  (0x00180000)
+#define HW_ATL_B0_RXD_WB_STAT_RXCTRL_SHIFT (0x13)
 #define HW_ATL_B0_RXD_WB_STAT_SPLHDR  (0x00200000)
 #define HW_ATL_B0_RXD_WB_STAT_HDRLEN  (0xFFC00000)
+#define HW_ATL_B0_RXD_WB_STAT_HDRLEN_SHIFT (0x16)
+
+#define HW_ATL_B0_RXD_WB_PKTTYPE_VLAN          BIT(5)
+#define HW_ATL_B0_RXD_WB_PKTTYPE_VLAN_DOUBLE   BIT(6)
 
 #define HW_ATL_B0_RXD_WB_STAT2_DD      (0x0001)
 #define HW_ATL_B0_RXD_WB_STAT2_EOP     (0x0002)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 939f77e2e117..1149812ae463 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_llh.c: Definitions of bitfield and register access functions for
@@ -49,11 +46,6 @@ u32 hw_atl_glb_soft_res_get(struct aq_hw_s *aq_hw)
 				  HW_ATL_GLB_SOFT_RES_SHIFT);
 }
 
-u32 hw_atl_reg_rx_dma_stat_counter7get(struct aq_hw_s *aq_hw)
-{
-	return aq_hw_read_reg(aq_hw, HW_ATL_RX_DMA_STAT_COUNTER7_ADR);
-}
-
 u32 hw_atl_reg_glb_mif_id_get(struct aq_hw_s *aq_hw)
 {
 	return aq_hw_read_reg(aq_hw, HW_ATL_GLB_MIF_ID_ADR);
@@ -65,44 +57,24 @@ u32 hw_atl_rpb_rx_dma_drop_pkt_cnt_get(struct aq_hw_s *aq_hw)
 	return aq_hw_read_reg(aq_hw, HW_ATL_RPB_RX_DMA_DROP_PKT_CNT_ADR);
 }
 
-u32 hw_atl_stats_rx_dma_good_octet_counterlsw_get(struct aq_hw_s *aq_hw)
-{
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_RX_DMA_GOOD_OCTET_COUNTERLSW);
-}
-
-u32 hw_atl_stats_rx_dma_good_pkt_counterlsw_get(struct aq_hw_s *aq_hw)
+u64 hw_atl_stats_rx_dma_good_octet_counter_get(struct aq_hw_s *aq_hw)
 {
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_RX_DMA_GOOD_PKT_COUNTERLSW);
+	return aq_hw_read_reg64(aq_hw, HW_ATL_STATS_RX_DMA_GOOD_OCTET_COUNTERLSW);
 }
 
-u32 hw_atl_stats_tx_dma_good_octet_counterlsw_get(struct aq_hw_s *aq_hw)
+u64 hw_atl_stats_rx_dma_good_pkt_counter_get(struct aq_hw_s *aq_hw)
 {
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_TX_DMA_GOOD_OCTET_COUNTERLSW);
+	return aq_hw_read_reg64(aq_hw, HW_ATL_STATS_RX_DMA_GOOD_PKT_COUNTERLSW);
 }
 
-u32 hw_atl_stats_tx_dma_good_pkt_counterlsw_get(struct aq_hw_s *aq_hw)
+u64 hw_atl_stats_tx_dma_good_octet_counter_get(struct aq_hw_s *aq_hw)
 {
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_TX_DMA_GOOD_PKT_COUNTERLSW);
+	return aq_hw_read_reg64(aq_hw, HW_ATL_STATS_TX_DMA_GOOD_OCTET_COUNTERLSW);
 }
 
-u32 hw_atl_stats_rx_dma_good_octet_countermsw_get(struct aq_hw_s *aq_hw)
+u64 hw_atl_stats_tx_dma_good_pkt_counter_get(struct aq_hw_s *aq_hw)
 {
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_RX_DMA_GOOD_OCTET_COUNTERMSW);
-}
-
-u32 hw_atl_stats_rx_dma_good_pkt_countermsw_get(struct aq_hw_s *aq_hw)
-{
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_RX_DMA_GOOD_PKT_COUNTERMSW);
-}
-
-u32 hw_atl_stats_tx_dma_good_octet_countermsw_get(struct aq_hw_s *aq_hw)
-{
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_TX_DMA_GOOD_OCTET_COUNTERMSW);
-}
-
-u32 hw_atl_stats_tx_dma_good_pkt_countermsw_get(struct aq_hw_s *aq_hw)
-{
-	return aq_hw_read_reg(aq_hw, HW_ATL_STATS_TX_DMA_GOOD_PKT_COUNTERMSW);
+	return aq_hw_read_reg64(aq_hw, HW_ATL_STATS_TX_DMA_GOOD_PKT_COUNTERLSW);
 }
 
 /* interrupt */
@@ -315,6 +287,21 @@ void hw_atl_itr_res_irq_set(struct aq_hw_s *aq_hw, u32 res_irq)
 			    HW_ATL_ITR_RES_SHIFT, res_irq);
 }
 
+/* set RSC interrupt */
+void hw_atl_itr_rsc_en_set(struct aq_hw_s *aq_hw, u32 enable)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_ITR_RSC_EN_ADR, enable);
+}
+
+/* set RSC delay */
+void hw_atl_itr_rsc_delay_set(struct aq_hw_s *aq_hw, u32 delay)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_ITR_RSC_DELAY_ADR,
+			    HW_ATL_ITR_RSC_DELAY_MSK,
+			    HW_ATL_ITR_RSC_DELAY_SHIFT,
+			    delay);
+}
+
 /* rdm */
 void hw_atl_rdm_cpu_id_set(struct aq_hw_s *aq_hw, u32 cpuid, u32 dca)
 {
@@ -1017,6 +1004,22 @@ void hw_atl_rpo_rx_desc_vlan_stripping_set(struct aq_hw_s *aq_hw,
 			    rx_desc_vlan_stripping);
 }
 
+void hw_atl_rpo_outer_vlan_tag_mode_set(void *context,
+					u32 outervlantagmode)
+{
+	aq_hw_write_reg_bit(context, HW_ATL_RPO_OUTER_VL_INS_MODE_ADR,
+			    HW_ATL_RPO_OUTER_VL_INS_MODE_MSK,
+			    HW_ATL_RPO_OUTER_VL_INS_MODE_SHIFT,
+			    outervlantagmode);
+}
+
+u32 hw_atl_rpo_outer_vlan_tag_mode_get(void *context)
+{
+	return aq_hw_read_reg_bit(context, HW_ATL_RPO_OUTER_VL_INS_MODE_ADR,
+				  HW_ATL_RPO_OUTER_VL_INS_MODE_MSK,
+				  HW_ATL_RPO_OUTER_VL_INS_MODE_SHIFT);
+}
+
 void hw_atl_rpo_tcp_udp_crc_offload_en_set(struct aq_hw_s *aq_hw,
 					   u32 tcp_udp_crc_offload_en)
 {
@@ -1274,6 +1277,15 @@ void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en)
 			    HW_ATL_TPB_TX_BUF_EN_SHIFT, tx_buff_en);
 }
 
+void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
+				   u32 tx_traf_class_mode)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPB_TX_TC_MODE_ADDR,
+			HW_ATL_TPB_TX_TC_MODE_MSK,
+			HW_ATL_TPB_TX_TC_MODE_SHIFT,
+			tx_traf_class_mode);
+}
+
 void hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(struct aq_hw_s *aq_hw,
 						u32 tx_buff_hi_threshold_per_tc,
 					 u32 buffer)
@@ -1585,3 +1597,24 @@ void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
 				HW_ATL_RPF_L3_DSTA_ADR(location + i),
 				ipv6_dest[i]);
 }
+
+u32 hw_atl_sem_ram_get(struct aq_hw_s *self)
+{
+	return hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM);
+}
+
+u32 hw_atl_scrpad_get(struct aq_hw_s *aq_hw, u32 scratch_scp)
+{
+	return aq_hw_read_reg(aq_hw,
+			      HW_ATL_GLB_CPU_SCRATCH_SCP_ADR(scratch_scp));
+}
+
+u32 hw_atl_scrpad12_get(struct aq_hw_s *self)
+{
+	return  hw_atl_scrpad_get(self, 0xB);
+}
+
+u32 hw_atl_scrpad25_get(struct aq_hw_s *self)
+{
+	return hw_atl_scrpad_get(self, 0x18);
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index 03c570d115fe..0c37abbabca5 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_llh.h: Declarations of bitfield and register access functions for
@@ -40,29 +37,17 @@ u32 hw_atl_glb_soft_res_get(struct aq_hw_s *aq_hw);
 
 u32 hw_atl_rpb_rx_dma_drop_pkt_cnt_get(struct aq_hw_s *aq_hw);
 
-/* get rx dma good octet counter lsw */
-u32 hw_atl_stats_rx_dma_good_octet_counterlsw_get(struct aq_hw_s *aq_hw);
+/* get rx dma good octet counter */
+u64 hw_atl_stats_rx_dma_good_octet_counter_get(struct aq_hw_s *aq_hw);
 
-/* get rx dma good packet counter lsw */
-u32 hw_atl_stats_rx_dma_good_pkt_counterlsw_get(struct aq_hw_s *aq_hw);
+/* get rx dma good packet counter */
+u64 hw_atl_stats_rx_dma_good_pkt_counter_get(struct aq_hw_s *aq_hw);
 
-/* get tx dma good octet counter lsw */
-u32 hw_atl_stats_tx_dma_good_octet_counterlsw_get(struct aq_hw_s *aq_hw);
+/* get tx dma good octet counter */
+u64 hw_atl_stats_tx_dma_good_octet_counter_get(struct aq_hw_s *aq_hw);
 
-/* get tx dma good packet counter lsw */
-u32 hw_atl_stats_tx_dma_good_pkt_counterlsw_get(struct aq_hw_s *aq_hw);
-
-/* get rx dma good octet counter msw */
-u32 hw_atl_stats_rx_dma_good_octet_countermsw_get(struct aq_hw_s *aq_hw);
-
-/* get rx dma good packet counter msw */
-u32 hw_atl_stats_rx_dma_good_pkt_countermsw_get(struct aq_hw_s *aq_hw);
-
-/* get tx dma good octet counter msw */
-u32 hw_atl_stats_tx_dma_good_octet_countermsw_get(struct aq_hw_s *aq_hw);
-
-/* get tx dma good packet counter msw */
-u32 hw_atl_stats_tx_dma_good_pkt_countermsw_get(struct aq_hw_s *aq_hw);
+/* get tx dma good packet counter */
+u64 hw_atl_stats_tx_dma_good_pkt_counter_get(struct aq_hw_s *aq_hw);
 
 /* get msm rx errors counter register */
 u32 hw_atl_reg_mac_msm_rx_errs_cnt_get(struct aq_hw_s *aq_hw);
@@ -82,9 +67,6 @@ u32 hw_atl_reg_mac_msm_rx_bcst_octets_counter1get(struct aq_hw_s *aq_hw);
 /* get msm rx unicast octets counter register 0 */
 u32 hw_atl_reg_mac_msm_rx_ucst_octets_counter0get(struct aq_hw_s *aq_hw);
 
-/* get rx dma statistics counter 7 */
-u32 hw_atl_reg_rx_dma_stat_counter7get(struct aq_hw_s *aq_hw);
-
 /* get msm tx errors counter register */
 u32 hw_atl_reg_mac_msm_tx_errs_cnt_get(struct aq_hw_s *aq_hw);
 
@@ -152,6 +134,12 @@ u32 hw_atl_itr_res_irq_get(struct aq_hw_s *aq_hw);
 /* set reset interrupt */
 void hw_atl_itr_res_irq_set(struct aq_hw_s *aq_hw, u32 res_irq);
 
+/* set RSC interrupt */
+void hw_atl_itr_rsc_en_set(struct aq_hw_s *aq_hw, u32 enable);
+
+/* set RSC delay */
+void hw_atl_itr_rsc_delay_set(struct aq_hw_s *aq_hw, u32 delay);
+
 /* rdm */
 
 /* set cpu id */
@@ -500,6 +488,11 @@ void hw_atl_rpo_rx_desc_vlan_stripping_set(struct aq_hw_s *aq_hw,
 					   u32 rx_desc_vlan_stripping,
 					   u32 descriptor);
 
+void hw_atl_rpo_outer_vlan_tag_mode_set(void *context,
+					u32 outervlantagmode);
+
+u32 hw_atl_rpo_outer_vlan_tag_mode_get(void *context);
+
 /* set tcp/udp checksum offload enable */
 void hw_atl_rpo_tcp_udp_crc_offload_en_set(struct aq_hw_s *aq_hw,
 					   u32 tcp_udp_crc_offload_en);
@@ -605,6 +598,10 @@ void hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(struct aq_hw_s *aq_hw,
 
 /* tpb */
 
+/* set TX Traffic Class Mode */
+void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
+				   u32 tx_traf_class_mode);
+
 /* set tx buffer enable */
 void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en);
 
@@ -752,4 +749,16 @@ void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
 void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
 				       u32 *ipv6_dest);
 
+/* get global microprocessor ram semaphore */
+u32 hw_atl_sem_ram_get(struct aq_hw_s *self);
+
+/* get global microprocessor scratch pad register */
+u32 hw_atl_scrpad_get(struct aq_hw_s *aq_hw, u32 scratch_scp);
+
+/* get global microprocessor scratch pad 12 register */
+u32 hw_atl_scrpad12_get(struct aq_hw_s *self);
+
+/* get global microprocessor scratch pad 25 register */
+u32 hw_atl_scrpad25_get(struct aq_hw_s *self);
+
 #endif /* HW_ATL_LLH_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index 8470d92db812..c3febcdfa92e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_llh_internal.h: Preprocessor definitions
@@ -58,9 +55,6 @@
 /* preprocessor definitions for msm rx unicast octets counter register 0 */
 #define HW_ATL_MAC_MSM_RX_UCST_OCTETS_COUNTER0_ADR 0x000001b8u
 
-/* preprocessor definitions for rx dma statistics counter 7 */
-#define HW_ATL_RX_DMA_STAT_COUNTER7_ADR 0x00006818u
-
 /* preprocessor definitions for msm tx unicast frames counter register */
 #define HW_ATL_MAC_MSM_TX_UCST_FRM_CNT_ADR 0x00000108u
 
@@ -95,6 +89,19 @@
 #define HW_ATL_ITR_RES_MSK 0x80000000
 /* lower bit position of bitfield itr_reset */
 #define HW_ATL_ITR_RES_SHIFT 31
+
+/* register address for bitfield  rsc_en */
+#define HW_ATL_ITR_RSC_EN_ADR 0x00002200
+
+/* register address for bitfield  rsc_delay */
+#define HW_ATL_ITR_RSC_DELAY_ADR 0x00002204
+/* bitmask for bitfield  rsc_delay */
+#define HW_ATL_ITR_RSC_DELAY_MSK 0x0000000f
+/* width of bitfield  rsc_delay */
+#define HW_ATL_ITR_RSC_DELAY_WIDTH 4
+/* lower bit position of bitfield  rsc_delay */
+#define HW_ATL_ITR_RSC_DELAY_SHIFT 0
+
 /* register address for bitfield dca{d}_cpuid[7:0] */
 #define HW_ATL_RDM_DCADCPUID_ADR(dca) (0x00006100 + (dca) * 0x4)
 /* bitmask for bitfield dca{d}_cpuid[7:0] */
@@ -1376,6 +1383,24 @@
 /* default value of bitfield l4_chk_en */
 #define HW_ATL_RPOL4CHK_EN_DEFAULT 0x0
 
+/* RX outer_vl_ins_mode Bitfield Definitions
+ * Preprocessor definitions for the bitfield "outer_vl_ins_mode".
+ * PORT="pif_rpo_outer_vl_mode_i"
+ */
+
+/* Register address for bitfield outer_vl_ins_mode */
+#define HW_ATL_RPO_OUTER_VL_INS_MODE_ADR 0x00005580
+/* Bitmask for bitfield outer_vl_ins_mode */
+#define HW_ATL_RPO_OUTER_VL_INS_MODE_MSK 0x00000004
+/* Inverted bitmask for bitfield outer_vl_ins_mode */
+#define HW_ATL_RPO_OUTER_VL_INS_MODE_MSKN 0xFFFFFFFB
+/* Lower bit position of bitfield outer_vl_ins_mode */
+#define HW_ATL_RPO_OUTER_VL_INS_MODE_SHIFT 2
+/* Width of bitfield outer_vl_ins_mode */
+#define HW_ATL_RPO_OUTER_VL_INS_MODE_WIDTH 1
+/* Default value of bitfield outer_vl_ins_mode */
+#define HW_ATL_RPO_OUTER_VL_INS_MODE_DEFAULT 0x0
+
 /* rx reg_res_dsbl bitfield definitions
  * preprocessor definitions for the bitfield "reg_res_dsbl".
  * port="pif_rx_reg_res_dsbl_i"
@@ -1948,6 +1973,19 @@
 /* default value of bitfield tx_buf_en */
 #define HW_ATL_TPB_TX_BUF_EN_DEFAULT 0x0
 
+/* register address for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_ADDR 0x00007900
+/* bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSK 0x00000100
+/* inverted bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSKN 0xFFFFFEFF
+/* lower bit position of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_SHIFT 8
+/* width of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_WIDTH 1
+/* default value of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0
+
 /* tx tx{b}_hi_thresh[c:0] bitfield definitions
  * preprocessor definitions for the bitfield "tx{b}_hi_thresh[c:0]".
  * parameter: buffer {b} | stride size 0x10 | range [0, 7]
@@ -2519,4 +2557,6 @@
 /* Default value of bitfield l3_da0[1F:0] */
 #define HW_ATL_RPF_L3_DSTA_DEFAULT 0x0
 
+#define HW_ATL_FW_SM_RAM        0x2U
+
 #endif /* HW_ATL_LLH_INTERNAL_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 9b74a3197d7f..52646855495e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_utils.c: Definition of common functions for Atlantic hardware
@@ -25,7 +22,9 @@
 #define HW_ATL_MIF_ADDR         0x0208U
 #define HW_ATL_MIF_VAL          0x020CU
 
-#define HW_ATL_FW_SM_RAM        0x2U
+#define HW_ATL_RPC_CONTROL_ADR  0x0338U
+#define HW_ATL_RPC_STATE_ADR    0x033CU
+
 #define HW_ATL_MPI_FW_VERSION	0x18
 #define HW_ATL_MPI_CONTROL_ADR  0x0368U
 #define HW_ATL_MPI_STATE_ADR    0x036CU
@@ -53,6 +52,12 @@ static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
 static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 				      enum hal_atl_utils_fw_state_e state);
 
+static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self);
+static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self);
+static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self);
+static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self);
+static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self);
+
 int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 {
 	int err = 0;
@@ -234,6 +239,7 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self)
 {
 	int k;
 	u32 boot_exit_code = 0;
+	u32 val;
 
 	for (k = 0; k < 1000; ++k) {
 		u32 flb_status = aq_hw_read_reg(self,
@@ -260,9 +266,11 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self)
 		int err = 0;
 
 		hw_atl_utils_mpi_set_state(self, MPI_DEINIT);
-		AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR) &
-				HW_ATL_MPI_STATE_MSK) == MPI_DEINIT,
-			       10, 1000U);
+		err = readx_poll_timeout_atomic(hw_atl_utils_mpi_get_state,
+						self, val,
+						(val & HW_ATL_MPI_STATE_MSK) ==
+						 MPI_DEINIT,
+						10, 10000U);
 		if (err)
 			return err;
 	}
@@ -277,16 +285,17 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a,
 				  u32 *p, u32 cnt)
 {
 	int err = 0;
+	u32 val;
 
-	AQ_HW_WAIT_FOR(hw_atl_reg_glb_cpu_sem_get(self,
-						  HW_ATL_FW_SM_RAM) == 1U,
-		       1U, 10000U);
+	err = readx_poll_timeout_atomic(hw_atl_sem_ram_get,
+					self, val, val == 1U,
+					1U, 10000U);
 
 	if (err < 0) {
 		bool is_locked;
 
 		hw_atl_reg_glb_cpu_sem_set(self, 1U, HW_ATL_FW_SM_RAM);
-		is_locked = hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM);
+		is_locked = hw_atl_sem_ram_get(self);
 		if (!is_locked) {
 			err = -ETIME;
 			goto err_exit;
@@ -299,13 +308,14 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a,
 		aq_hw_write_reg(self, HW_ATL_MIF_CMD, 0x00008000U);
 
 		if (IS_CHIP_FEATURE(REVISION_B1))
-			AQ_HW_WAIT_FOR(a != aq_hw_read_reg(self,
-							   HW_ATL_MIF_ADDR),
-				       1, 1000U);
+			err = readx_poll_timeout_atomic(hw_atl_utils_mif_addr_get,
+							self, val, val != a,
+							1U, 1000U);
 		else
-			AQ_HW_WAIT_FOR(!(0x100 & aq_hw_read_reg(self,
-							   HW_ATL_MIF_CMD)),
-				       1, 1000U);
+			err = readx_poll_timeout_atomic(hw_atl_utils_mif_cmd_get,
+							self, val,
+							!(val & 0x100),
+							1U, 1000U);
 
 		*(p++) = aq_hw_read_reg(self, HW_ATL_MIF_VAL);
 		a += 4;
@@ -320,14 +330,15 @@ err_exit:
 static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 					 u32 cnt)
 {
+	u32 val;
 	int err = 0;
-	bool is_locked;
 
-	is_locked = hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM);
-	if (!is_locked) {
-		err = -ETIME;
+	err = readx_poll_timeout_atomic(hw_atl_sem_ram_get, self,
+					val, val == 1U,
+					10U, 100000U);
+	if (err < 0)
 		goto err_exit;
-	}
+
 	if (IS_CHIP_FEATURE(REVISION_B1)) {
 		u32 offset = 0;
 
@@ -337,10 +348,11 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 					(0x80000000 | (0xFFFF & (offset * 4))));
 			hw_atl_mcp_up_force_intr_set(self, 1);
 			/* 1000 times by 10us = 10ms */
-			AQ_HW_WAIT_FOR((aq_hw_read_reg(self,
-						       0x32C) & 0xF0000000) !=
-				       0x80000000,
-				       10, 1000);
+			err = readx_poll_timeout_atomic(hw_atl_scrpad12_get,
+							self, val,
+							(val & 0xF0000000) !=
+							0x80000000,
+							10U, 10000U);
 		}
 	} else {
 		u32 offset = 0;
@@ -351,8 +363,10 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 			aq_hw_write_reg(self, 0x20C, p[offset]);
 			aq_hw_write_reg(self, 0x200, 0xC000);
 
-			AQ_HW_WAIT_FOR((aq_hw_read_reg(self, 0x200U) &
-					0x100) == 0, 10, 1000);
+			err = readx_poll_timeout_atomic(hw_atl_utils_mif_cmd_get,
+							self, val,
+							(val & 0x100) == 0,
+							1000U, 10000U);
 		}
 	}
 
@@ -395,15 +409,14 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self,
 	hw_atl_reg_glb_cpu_scratch_scp_set(self, 0x00000000U, 25U);
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(0U != (self->mbox_addr =
-			      aq_hw_read_reg(self, 0x360U)), 1000U, 10U);
+	err = readx_poll_timeout_atomic(hw_atl_scrpad25_get,
+					self, self->mbox_addr,
+					self->mbox_addr != 0U,
+					1000U, 10000U);
 
 	return err;
 }
 
-#define HW_ATL_RPC_CONTROL_ADR 0x0338U
-#define HW_ATL_RPC_STATE_ADR   0x033CU
-
 struct aq_hw_atl_utils_fw_rpc_tid_s {
 	union {
 		u32 val;
@@ -452,10 +465,10 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 
 		self->rpc_tid = sw.tid;
 
-		AQ_HW_WAIT_FOR(sw.tid ==
-			       (fw.val =
-				aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR),
-				fw.tid), 1000U, 100U);
+		err = readx_poll_timeout_atomic(hw_atl_utils_rpc_state_get,
+						self, fw.val,
+						sw.tid == fw.tid,
+						1000U, 100000U);
 
 		if (fw.len == 0xFFFFU) {
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
@@ -529,7 +542,7 @@ void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 		pmbox->stats.ubtc = pmbox->stats.uptc * mtu;
 		pmbox->stats.dpc = atomic_read(&self->dpc);
 	} else {
-		pmbox->stats.dpc = hw_atl_reg_rx_dma_stat_counter7get(self);
+		pmbox->stats.dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self);
 	}
 
 err_exit:;
@@ -559,10 +572,11 @@ static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 
 		transaction_id = mbox.transaction_id;
 
-		AQ_HW_WAIT_FOR(transaction_id !=
-			       (hw_atl_utils_mpi_read_mbox(self, &mbox),
-				mbox.transaction_id),
-			       1000U, 100U);
+		err = readx_poll_timeout_atomic(hw_atl_utils_get_mpi_mbox_tid,
+						self, mbox.transaction_id,
+						transaction_id !=
+						mbox.transaction_id,
+						1000U, 100000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -585,7 +599,7 @@ err_exit:
 
 int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
 {
-	u32 cp0x036C = aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR);
+	u32 cp0x036C = hw_atl_utils_mpi_get_state(self);
 	u32 link_speed_mask = cp0x036C >> HW_ATL_MPI_SPEED_SHIFT;
 	struct aq_hw_link_status_s *link_status = &self->aq_link_status;
 
@@ -746,6 +760,7 @@ static int hw_atl_fw1x_deinit(struct aq_hw_s *self)
 int hw_atl_utils_update_stats(struct aq_hw_s *self)
 {
 	struct hw_atl_utils_mbox mbox;
+	struct aq_stats_s *cs = &self->curr_stats;
 
 	hw_atl_utils_mpi_read_stats(self, &mbox);
 
@@ -772,10 +787,11 @@ int hw_atl_utils_update_stats(struct aq_hw_s *self)
 		AQ_SDELTA(dpc);
 	}
 #undef AQ_SDELTA
-	self->curr_stats.dma_pkt_rc = hw_atl_stats_rx_dma_good_pkt_counterlsw_get(self);
-	self->curr_stats.dma_pkt_tc = hw_atl_stats_tx_dma_good_pkt_counterlsw_get(self);
-	self->curr_stats.dma_oct_rc = hw_atl_stats_rx_dma_good_octet_counterlsw_get(self);
-	self->curr_stats.dma_oct_tc = hw_atl_stats_tx_dma_good_octet_counterlsw_get(self);
+
+	cs->dma_pkt_rc = hw_atl_stats_rx_dma_good_pkt_counter_get(self);
+	cs->dma_pkt_tc = hw_atl_stats_tx_dma_good_pkt_counter_get(self);
+	cs->dma_oct_rc = hw_atl_stats_rx_dma_good_octet_counter_get(self);
+	cs->dma_oct_tc = hw_atl_stats_tx_dma_good_octet_counter_get(self);
 
 	memcpy(&self->last_stats, &mbox.stats, sizeof(mbox.stats));
 
@@ -905,6 +921,35 @@ err_exit:
 	return err;
 }
 
+static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self)
+{
+	struct hw_atl_utils_mbox_header mbox;
+
+	hw_atl_utils_mpi_read_mbox(self, &mbox);
+
+	return mbox.transaction_id;
+}
+
+static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR);
+}
+
+static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MIF_CMD);
+}
+
+static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MIF_ADDR);
+}
+
+static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR);
+}
+
 const struct aq_fw_ops aq_fw_1x_ops = {
 	.init = hw_atl_utils_mpi_create,
 	.deinit = hw_atl_fw1x_deinit,
@@ -914,6 +959,7 @@ const struct aq_fw_ops aq_fw_1x_ops = {
 	.set_state = hw_atl_utils_mpi_set_state,
 	.update_link_status = hw_atl_utils_mpi_get_link_status,
 	.update_stats = hw_atl_utils_update_stats,
+	.get_phy_temp = NULL,
 	.set_power = aq_fw1x_set_power,
 	.set_eee_rate = NULL,
 	.get_eee_rate = NULL,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 48278e333462..692bed70e104 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_utils.h: Declaration of common functions for Atlantic hardware
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index 7de3220d9cab..da726489e3c8 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 /* File hw_atl_utils_fw2x.c: Definition of firmware 2.x functions for
@@ -20,15 +17,14 @@
 #include "hw_atl_utils.h"
 #include "hw_atl_llh.h"
 
-#define HW_ATL_FW2X_MPI_EFUSE_ADDR	0x364
-#define HW_ATL_FW2X_MPI_MBOX_ADDR	0x360
 #define HW_ATL_FW2X_MPI_RPC_ADDR        0x334
 
+#define HW_ATL_FW2X_MPI_MBOX_ADDR       0x360
+#define HW_ATL_FW2X_MPI_EFUSE_ADDR	0x364
 #define HW_ATL_FW2X_MPI_CONTROL_ADDR	0x368
 #define HW_ATL_FW2X_MPI_CONTROL2_ADDR	0x36C
-
 #define HW_ATL_FW2X_MPI_STATE_ADDR	0x370
-#define HW_ATL_FW2X_MPI_STATE2_ADDR	0x374
+#define HW_ATL_FW2X_MPI_STATE2_ADDR     0x374
 
 #define HW_ATL_FW2X_CAP_PAUSE            BIT(CAPS_HI_PAUSE)
 #define HW_ATL_FW2X_CAP_ASYM_PAUSE       BIT(CAPS_HI_ASYMMETRIC_PAUSE)
@@ -39,6 +35,7 @@
 #define HW_ATL_FW2X_CTRL_WOL              BIT(CTRL_WOL)
 #define HW_ATL_FW2X_CTRL_LINK_DROP        BIT(CTRL_LINK_DROP)
 #define HW_ATL_FW2X_CTRL_PAUSE            BIT(CTRL_PAUSE)
+#define HW_ATL_FW2X_CTRL_TEMPERATURE      BIT(CTRL_TEMPERATURE)
 #define HW_ATL_FW2X_CTRL_ASYMMETRIC_PAUSE BIT(CTRL_ASYMMETRIC_PAUSE)
 #define HW_ATL_FW2X_CTRL_FORCE_RECONNECT  BIT(CTRL_FORCE_RECONNECT)
 
@@ -72,17 +69,24 @@ static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed);
 static int aq_fw2x_set_state(struct aq_hw_s *self,
 			     enum hal_atl_utils_fw_state_e state);
 
+static u32 aq_fw2x_mbox_get(struct aq_hw_s *self);
+static u32 aq_fw2x_rpc_get(struct aq_hw_s *self);
+static u32 aq_fw2x_state2_get(struct aq_hw_s *self);
+
 static int aq_fw2x_init(struct aq_hw_s *self)
 {
 	int err = 0;
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(0U != (self->mbox_addr =
-		       aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR)),
-		       1000U, 10U);
-	AQ_HW_WAIT_FOR(0U != (self->rpc_addr =
-		       aq_hw_read_reg(self, HW_ATL_FW2X_MPI_RPC_ADDR)),
-		       1000U, 100U);
+	err = readx_poll_timeout_atomic(aq_fw2x_mbox_get,
+					self, self->mbox_addr,
+					self->mbox_addr != 0U,
+					1000U, 10000U);
+
+	err = readx_poll_timeout_atomic(aq_fw2x_rpc_get,
+					self, self->rpc_addr,
+					self->rpc_addr != 0U,
+					1000U, 100000U);
 
 	return err;
 }
@@ -286,22 +290,58 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self)
 	int err = 0;
 	u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
 	u32 orig_stats_val = mpi_opts & BIT(CAPS_HI_STATISTICS);
+	u32 stats_val;
 
 	/* Toggle statistics bit for FW to update */
 	mpi_opts = mpi_opts ^ BIT(CAPS_HI_STATISTICS);
 	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
 
 	/* Wait FW to report back */
-	AQ_HW_WAIT_FOR(orig_stats_val !=
-		       (aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) &
-			BIT(CAPS_HI_STATISTICS)),
-		       1U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw2x_state2_get,
+					self, stats_val,
+					orig_stats_val != (stats_val &
+					BIT(CAPS_HI_STATISTICS)),
+					1U, 10000U);
 	if (err)
 		return err;
 
 	return hw_atl_utils_update_stats(self);
 }
 
+static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp)
+{
+	u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+	u32 temp_val = mpi_opts & HW_ATL_FW2X_CTRL_TEMPERATURE;
+	u32 phy_temp_offset;
+	u32 temp_res;
+	int err = 0;
+	u32 val;
+
+	phy_temp_offset = self->mbox_addr +
+			  offsetof(struct hw_atl_utils_mbox, info) +
+			  offsetof(struct hw_aq_info, phy_temperature);
+	/* Toggle statistics bit for FW to 0x36C.18 (CTRL_TEMPERATURE) */
+	mpi_opts = mpi_opts ^ HW_ATL_FW2X_CTRL_TEMPERATURE;
+	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
+	/* Wait FW to report back */
+	err = readx_poll_timeout_atomic(aq_fw2x_state2_get, self, val,
+					temp_val !=
+					(val & HW_ATL_FW2X_CTRL_TEMPERATURE),
+					1U, 10000U);
+	err = hw_atl_utils_fw_downld_dwords(self, phy_temp_offset,
+					    &temp_res, 1);
+
+	if (err)
+		return err;
+
+	/* Convert PHY temperature from 1/256 degree Celsius
+	 * to 1/1000 degree Celsius.
+	 */
+	*temp = temp_res  * 1000 / 256;
+
+	return 0;
+}
+
 static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac)
 {
 	struct hw_atl_utils_fw_rpc *rpc = NULL;
@@ -309,6 +349,7 @@ static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac)
 	unsigned int rpc_size = 0U;
 	u32 mpi_opts;
 	int err = 0;
+	u32 val;
 
 	rpc_size = sizeof(rpc->msg_id) + sizeof(*cfg);
 
@@ -337,8 +378,10 @@ static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac)
 	mpi_opts |= HW_ATL_FW2X_CTRL_SLEEP_PROXY;
 	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
 
-	AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) &
-			HW_ATL_FW2X_CTRL_SLEEP_PROXY), 1U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw2x_state2_get,
+					self, val,
+					val & HW_ATL_FW2X_CTRL_SLEEP_PROXY,
+					1U, 100000U);
 
 err_exit:
 	return err;
@@ -350,6 +393,7 @@ static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac)
 	struct fw2x_msg_wol *msg = NULL;
 	u32 mpi_opts;
 	int err = 0;
+	u32 val;
 
 	err = hw_atl_utils_fw_rpc_wait(self, &rpc);
 	if (err < 0)
@@ -357,6 +401,8 @@ static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac)
 
 	msg = (struct fw2x_msg_wol *)rpc;
 
+	memset(msg, 0, sizeof(*msg));
+
 	msg->msg_id = HAL_ATLANTIC_UTILS_FW2X_MSG_WOL;
 	msg->magic_packet_enabled = true;
 	memcpy(msg->hw_addr, mac, ETH_ALEN);
@@ -374,8 +420,9 @@ static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac)
 	mpi_opts |= HW_ATL_FW2X_CTRL_WOL;
 	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
 
-	AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) &
-			HW_ATL_FW2X_CTRL_WOL), 1U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw2x_state2_get,
+					self, val, val & HW_ATL_FW2X_CTRL_WOL,
+					1U, 10000U);
 
 err_exit:
 	return err;
@@ -425,7 +472,7 @@ static int aq_fw2x_get_eee_rate(struct aq_hw_s *self, u32 *rate,
 
 	*supported_rates = fw2x_to_eee_mask(caps_hi);
 
-	mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR);
+	mpi_state = aq_fw2x_state2_get(self);
 	*rate = fw2x_to_eee_mask(mpi_state);
 
 	return err;
@@ -455,7 +502,7 @@ static int aq_fw2x_set_flow_control(struct aq_hw_s *self)
 
 static u32 aq_fw2x_get_flow_control(struct aq_hw_s *self, u32 *fcmode)
 {
-	u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR);
+	u32 mpi_state = aq_fw2x_state2_get(self);
 
 	if (mpi_state & HW_ATL_FW2X_CAP_PAUSE)
 		if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE)
@@ -471,6 +518,21 @@ static u32 aq_fw2x_get_flow_control(struct aq_hw_s *self, u32 *fcmode)
 	return 0;
 }
 
+static u32 aq_fw2x_mbox_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR);
+}
+
+static u32 aq_fw2x_rpc_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_FW2X_MPI_RPC_ADDR);
+}
+
+static u32 aq_fw2x_state2_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR);
+}
+
 const struct aq_fw_ops aq_fw_2x_ops = {
 	.init = aq_fw2x_init,
 	.deinit = aq_fw2x_deinit,
@@ -481,6 +543,7 @@ const struct aq_fw_ops aq_fw_2x_ops = {
 	.set_state = aq_fw2x_set_state,
 	.update_link_status = aq_fw2x_update_link_status,
 	.update_stats = aq_fw2x_update_stats,
+	.get_phy_temp = aq_fw2x_get_phy_temp,
 	.set_power = aq_fw2x_set_power,
 	.set_eee_rate = aq_fw2x_set_eee_rate,
 	.get_eee_rate = aq_fw2x_get_eee_rate,
diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h
index b48260114da3..597654b51e01 100644
--- a/drivers/net/ethernet/aquantia/atlantic/ver.h
+++ b/drivers/net/ethernet/aquantia/atlantic/ver.h
@@ -1,20 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * aQuantia Corporation Network Driver
  * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
  */
 
 #ifndef VER_H
 #define VER_H
 
-#define NIC_MAJOR_DRIVER_VERSION           2
-#define NIC_MINOR_DRIVER_VERSION           0
-#define NIC_BUILD_DRIVER_VERSION           4
-#define NIC_REVISION_DRIVER_VERSION        0
-
 #define AQ_CFG_DRV_VERSION_SUFFIX "-kern"
 
 #endif /* VER_H */
diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig
index 5d0ab8e74b68..45c663d8b9aa 100644
--- a/drivers/net/ethernet/arc/Kconfig
+++ b/drivers/net/ethernet/arc/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # ARC EMAC network device configuration
 #
diff --git a/drivers/net/ethernet/arc/Makefile b/drivers/net/ethernet/arc/Makefile
index 79108af553fb..d63ada577c8e 100644
--- a/drivers/net/ethernet/arc/Makefile
+++ b/drivers/net/ethernet/arc/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the ARC network device drivers.
 #
diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c
index ffd180570920..78e52d217e56 100644
--- a/drivers/net/ethernet/arc/emac_arc.c
+++ b/drivers/net/ethernet/arc/emac_arc.c
@@ -1,19 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**
  * emac_arc.c - ARC EMAC specific glue layer
  *
  * Copyright (C) 2014 Romain Perier
  *
  * Romain Perier  <romain.perier@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 4406325fdd9f..6f2c867785fe 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2004-2013 Synopsys, Inc. (www.synopsys.com)
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Driver for the ARC EMAC 10100 (hardware revision 5)
  *
  * Contributors:
@@ -148,7 +145,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 				 dma_unmap_len(tx_buff, len), DMA_TO_DEVICE);
 
 		/* return the sk_buff to system */
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 
 		txbd->data = 0;
 		txbd->info = 0;
@@ -960,8 +957,8 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 	/* Get MAC address from device tree */
 	mac_addr = of_get_mac_address(dev->of_node);
 
-	if (mac_addr)
-		memcpy(ndev->dev_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(ndev->dev_addr, mac_addr);
 	else
 		eth_hw_addr_random(ndev);
 
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c
index 0f6576802607..42d2e1b02c44 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
+++ b/drivers/net/ethernet/arc/emac_rockchip.c
@@ -1,17 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**
  * emac-rockchip.c - Rockchip EMAC specific glue layer
  *
  * Copyright (C) 2014 Romain Perier <romain.perier@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/atheros/Kconfig b/drivers/net/ethernet/atheros/Kconfig
index e05b25675333..0058051ba925 100644
--- a/drivers/net/ethernet/atheros/Kconfig
+++ b/drivers/net/ethernet/atheros/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Atheros device configuration
 #
@@ -5,7 +6,7 @@
 config NET_VENDOR_ATHEROS
 	bool "Atheros devices"
 	default y
-	depends on PCI
+	depends on (PCI || ATH79)
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -16,6 +17,14 @@ config NET_VENDOR_ATHEROS
 
 if NET_VENDOR_ATHEROS
 
+config AG71XX
+	tristate "Atheros AR7XXX/AR9XXX built-in ethernet mac support"
+	depends on ATH79
+	select PHYLIB
+	help
+	  If you wish to compile a kernel for AR7XXX/91XXX and enable
+	  ethernet support, then you should always answer Y to this.
+
 config ATL2
 	tristate "Atheros L2 Fast Ethernet support"
 	depends on PCI
diff --git a/drivers/net/ethernet/atheros/Makefile b/drivers/net/ethernet/atheros/Makefile
index aa3d394b87e6..aca696cb6425 100644
--- a/drivers/net/ethernet/atheros/Makefile
+++ b/drivers/net/ethernet/atheros/Makefile
@@ -3,6 +3,7 @@
 # Makefile for the Atheros network device drivers.
 #
 
+obj-$(CONFIG_AG71XX) += ag71xx.o
 obj-$(CONFIG_ATL1) += atlx/
 obj-$(CONFIG_ATL2) += atlx/
 obj-$(CONFIG_ATL1E) += atl1e/
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
new file mode 100644
index 000000000000..72a57c6cd254
--- /dev/null
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -0,0 +1,1898 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  Atheros AR71xx built-in ethernet mac driver
+ *
+ *  Copyright (C) 2019 Oleksij Rempel <o.rempel@pengutronix.de>
+ *
+ *  List of authors contributed to this driver before mainlining:
+ *  Alexander Couzens <lynxis@fe80.eu>
+ *  Christian Lamparter <chunkeey@gmail.com>
+ *  Chuanhong Guo <gch981213@gmail.com>
+ *  Daniel F. Dickinson <cshored@thecshore.com>
+ *  David Bauer <mail@david-bauer.net>
+ *  Felix Fietkau <nbd@nbd.name>
+ *  Gabor Juhos <juhosg@freemail.hu>
+ *  Hauke Mehrtens <hauke@hauke-m.de>
+ *  Johann Neuhauser <johann@it-neuhauser.de>
+ *  John Crispin <john@phrozen.org>
+ *  Jo-Philipp Wich <jo@mein.io>
+ *  Koen Vandeputte <koen.vandeputte@ncentric.com>
+ *  Lucian Cristian <lucian.cristian@gmail.com>
+ *  Matt Merhar <mattmerhar@protonmail.com>
+ *  Milan Krstic <milan.krstic@gmail.com>
+ *  Petr Štetiar <ynezz@true.cz>
+ *  Rosen Penev <rosenp@gmail.com>
+ *  Stephen Walker <stephendwalker+github@gmail.com>
+ *  Vittorio Gambaletta <openwrt@vittgam.net>
+ *  Weijie Gao <hackpascal@gmail.com>
+ *  Imre Kaloz <kaloz@openwrt.org>
+ */
+
+#include <linux/if_vlan.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <linux/clk.h>
+
+/* For our NAPI weight bigger does *NOT* mean better - it means more
+ * D-cache misses and lots more wasted cycles than we'll ever
+ * possibly gain from saving instructions.
+ */
+#define AG71XX_NAPI_WEIGHT	32
+#define AG71XX_OOM_REFILL	(1 + HZ / 10)
+
+#define AG71XX_INT_ERR	(AG71XX_INT_RX_BE | AG71XX_INT_TX_BE)
+#define AG71XX_INT_TX	(AG71XX_INT_TX_PS)
+#define AG71XX_INT_RX	(AG71XX_INT_RX_PR | AG71XX_INT_RX_OF)
+
+#define AG71XX_INT_POLL	(AG71XX_INT_RX | AG71XX_INT_TX)
+#define AG71XX_INT_INIT	(AG71XX_INT_ERR | AG71XX_INT_POLL)
+
+#define AG71XX_TX_MTU_LEN	1540
+
+#define AG71XX_TX_RING_SPLIT		512
+#define AG71XX_TX_RING_DS_PER_PKT	DIV_ROUND_UP(AG71XX_TX_MTU_LEN, \
+						     AG71XX_TX_RING_SPLIT)
+#define AG71XX_TX_RING_SIZE_DEFAULT	128
+#define AG71XX_RX_RING_SIZE_DEFAULT	256
+
+#define AG71XX_MDIO_RETRY	1000
+#define AG71XX_MDIO_DELAY	5
+#define AG71XX_MDIO_MAX_CLK	5000000
+
+/* Register offsets */
+#define AG71XX_REG_MAC_CFG1	0x0000
+#define MAC_CFG1_TXE		BIT(0)	/* Tx Enable */
+#define MAC_CFG1_STX		BIT(1)	/* Synchronize Tx Enable */
+#define MAC_CFG1_RXE		BIT(2)	/* Rx Enable */
+#define MAC_CFG1_SRX		BIT(3)	/* Synchronize Rx Enable */
+#define MAC_CFG1_TFC		BIT(4)	/* Tx Flow Control Enable */
+#define MAC_CFG1_RFC		BIT(5)	/* Rx Flow Control Enable */
+#define MAC_CFG1_SR		BIT(31)	/* Soft Reset */
+#define MAC_CFG1_INIT	(MAC_CFG1_RXE | MAC_CFG1_TXE | \
+			 MAC_CFG1_SRX | MAC_CFG1_STX)
+
+#define AG71XX_REG_MAC_CFG2	0x0004
+#define MAC_CFG2_FDX		BIT(0)
+#define MAC_CFG2_PAD_CRC_EN	BIT(2)
+#define MAC_CFG2_LEN_CHECK	BIT(4)
+#define MAC_CFG2_IF_1000	BIT(9)
+#define MAC_CFG2_IF_10_100	BIT(8)
+
+#define AG71XX_REG_MAC_MFL	0x0010
+
+#define AG71XX_REG_MII_CFG	0x0020
+#define MII_CFG_CLK_DIV_4	0
+#define MII_CFG_CLK_DIV_6	2
+#define MII_CFG_CLK_DIV_8	3
+#define MII_CFG_CLK_DIV_10	4
+#define MII_CFG_CLK_DIV_14	5
+#define MII_CFG_CLK_DIV_20	6
+#define MII_CFG_CLK_DIV_28	7
+#define MII_CFG_CLK_DIV_34	8
+#define MII_CFG_CLK_DIV_42	9
+#define MII_CFG_CLK_DIV_50	10
+#define MII_CFG_CLK_DIV_58	11
+#define MII_CFG_CLK_DIV_66	12
+#define MII_CFG_CLK_DIV_74	13
+#define MII_CFG_CLK_DIV_82	14
+#define MII_CFG_CLK_DIV_98	15
+#define MII_CFG_RESET		BIT(31)
+
+#define AG71XX_REG_MII_CMD	0x0024
+#define MII_CMD_READ		BIT(0)
+
+#define AG71XX_REG_MII_ADDR	0x0028
+#define MII_ADDR_SHIFT		8
+
+#define AG71XX_REG_MII_CTRL	0x002c
+#define AG71XX_REG_MII_STATUS	0x0030
+#define AG71XX_REG_MII_IND	0x0034
+#define MII_IND_BUSY		BIT(0)
+#define MII_IND_INVALID		BIT(2)
+
+#define AG71XX_REG_MAC_IFCTL	0x0038
+#define MAC_IFCTL_SPEED		BIT(16)
+
+#define AG71XX_REG_MAC_ADDR1	0x0040
+#define AG71XX_REG_MAC_ADDR2	0x0044
+#define AG71XX_REG_FIFO_CFG0	0x0048
+#define FIFO_CFG0_WTM		BIT(0)	/* Watermark Module */
+#define FIFO_CFG0_RXS		BIT(1)	/* Rx System Module */
+#define FIFO_CFG0_RXF		BIT(2)	/* Rx Fabric Module */
+#define FIFO_CFG0_TXS		BIT(3)	/* Tx System Module */
+#define FIFO_CFG0_TXF		BIT(4)	/* Tx Fabric Module */
+#define FIFO_CFG0_ALL	(FIFO_CFG0_WTM | FIFO_CFG0_RXS | FIFO_CFG0_RXF \
+			| FIFO_CFG0_TXS | FIFO_CFG0_TXF)
+#define FIFO_CFG0_INIT	(FIFO_CFG0_ALL << FIFO_CFG0_ENABLE_SHIFT)
+
+#define FIFO_CFG0_ENABLE_SHIFT	8
+
+#define AG71XX_REG_FIFO_CFG1	0x004c
+#define AG71XX_REG_FIFO_CFG2	0x0050
+#define AG71XX_REG_FIFO_CFG3	0x0054
+#define AG71XX_REG_FIFO_CFG4	0x0058
+#define FIFO_CFG4_DE		BIT(0)	/* Drop Event */
+#define FIFO_CFG4_DV		BIT(1)	/* RX_DV Event */
+#define FIFO_CFG4_FC		BIT(2)	/* False Carrier */
+#define FIFO_CFG4_CE		BIT(3)	/* Code Error */
+#define FIFO_CFG4_CR		BIT(4)	/* CRC error */
+#define FIFO_CFG4_LM		BIT(5)	/* Length Mismatch */
+#define FIFO_CFG4_LO		BIT(6)	/* Length out of range */
+#define FIFO_CFG4_OK		BIT(7)	/* Packet is OK */
+#define FIFO_CFG4_MC		BIT(8)	/* Multicast Packet */
+#define FIFO_CFG4_BC		BIT(9)	/* Broadcast Packet */
+#define FIFO_CFG4_DR		BIT(10)	/* Dribble */
+#define FIFO_CFG4_LE		BIT(11)	/* Long Event */
+#define FIFO_CFG4_CF		BIT(12)	/* Control Frame */
+#define FIFO_CFG4_PF		BIT(13)	/* Pause Frame */
+#define FIFO_CFG4_UO		BIT(14)	/* Unsupported Opcode */
+#define FIFO_CFG4_VT		BIT(15)	/* VLAN tag detected */
+#define FIFO_CFG4_FT		BIT(16)	/* Frame Truncated */
+#define FIFO_CFG4_UC		BIT(17)	/* Unicast Packet */
+#define FIFO_CFG4_INIT	(FIFO_CFG4_DE | FIFO_CFG4_DV | FIFO_CFG4_FC | \
+			 FIFO_CFG4_CE | FIFO_CFG4_CR | FIFO_CFG4_LM | \
+			 FIFO_CFG4_LO | FIFO_CFG4_OK | FIFO_CFG4_MC | \
+			 FIFO_CFG4_BC | FIFO_CFG4_DR | FIFO_CFG4_LE | \
+			 FIFO_CFG4_CF | FIFO_CFG4_PF | FIFO_CFG4_UO | \
+			 FIFO_CFG4_VT)
+
+#define AG71XX_REG_FIFO_CFG5	0x005c
+#define FIFO_CFG5_DE		BIT(0)	/* Drop Event */
+#define FIFO_CFG5_DV		BIT(1)	/* RX_DV Event */
+#define FIFO_CFG5_FC		BIT(2)	/* False Carrier */
+#define FIFO_CFG5_CE		BIT(3)	/* Code Error */
+#define FIFO_CFG5_LM		BIT(4)	/* Length Mismatch */
+#define FIFO_CFG5_LO		BIT(5)	/* Length Out of Range */
+#define FIFO_CFG5_OK		BIT(6)	/* Packet is OK */
+#define FIFO_CFG5_MC		BIT(7)	/* Multicast Packet */
+#define FIFO_CFG5_BC		BIT(8)	/* Broadcast Packet */
+#define FIFO_CFG5_DR		BIT(9)	/* Dribble */
+#define FIFO_CFG5_CF		BIT(10)	/* Control Frame */
+#define FIFO_CFG5_PF		BIT(11)	/* Pause Frame */
+#define FIFO_CFG5_UO		BIT(12)	/* Unsupported Opcode */
+#define FIFO_CFG5_VT		BIT(13)	/* VLAN tag detected */
+#define FIFO_CFG5_LE		BIT(14)	/* Long Event */
+#define FIFO_CFG5_FT		BIT(15)	/* Frame Truncated */
+#define FIFO_CFG5_16		BIT(16)	/* unknown */
+#define FIFO_CFG5_17		BIT(17)	/* unknown */
+#define FIFO_CFG5_SF		BIT(18)	/* Short Frame */
+#define FIFO_CFG5_BM		BIT(19)	/* Byte Mode */
+#define FIFO_CFG5_INIT	(FIFO_CFG5_DE | FIFO_CFG5_DV | FIFO_CFG5_FC | \
+			 FIFO_CFG5_CE | FIFO_CFG5_LO | FIFO_CFG5_OK | \
+			 FIFO_CFG5_MC | FIFO_CFG5_BC | FIFO_CFG5_DR | \
+			 FIFO_CFG5_CF | FIFO_CFG5_PF | FIFO_CFG5_VT | \
+			 FIFO_CFG5_LE | FIFO_CFG5_FT | FIFO_CFG5_16 | \
+			 FIFO_CFG5_17 | FIFO_CFG5_SF)
+
+#define AG71XX_REG_TX_CTRL	0x0180
+#define TX_CTRL_TXE		BIT(0)	/* Tx Enable */
+
+#define AG71XX_REG_TX_DESC	0x0184
+#define AG71XX_REG_TX_STATUS	0x0188
+#define TX_STATUS_PS		BIT(0)	/* Packet Sent */
+#define TX_STATUS_UR		BIT(1)	/* Tx Underrun */
+#define TX_STATUS_BE		BIT(3)	/* Bus Error */
+
+#define AG71XX_REG_RX_CTRL	0x018c
+#define RX_CTRL_RXE		BIT(0)	/* Rx Enable */
+
+#define AG71XX_DMA_RETRY	10
+#define AG71XX_DMA_DELAY	1
+
+#define AG71XX_REG_RX_DESC	0x0190
+#define AG71XX_REG_RX_STATUS	0x0194
+#define RX_STATUS_PR		BIT(0)	/* Packet Received */
+#define RX_STATUS_OF		BIT(2)	/* Rx Overflow */
+#define RX_STATUS_BE		BIT(3)	/* Bus Error */
+
+#define AG71XX_REG_INT_ENABLE	0x0198
+#define AG71XX_REG_INT_STATUS	0x019c
+#define AG71XX_INT_TX_PS	BIT(0)
+#define AG71XX_INT_TX_UR	BIT(1)
+#define AG71XX_INT_TX_BE	BIT(3)
+#define AG71XX_INT_RX_PR	BIT(4)
+#define AG71XX_INT_RX_OF	BIT(6)
+#define AG71XX_INT_RX_BE	BIT(7)
+
+#define AG71XX_REG_FIFO_DEPTH	0x01a8
+#define AG71XX_REG_RX_SM	0x01b0
+#define AG71XX_REG_TX_SM	0x01b4
+
+#define ETH_SWITCH_HEADER_LEN	2
+
+#define AG71XX_DEFAULT_MSG_ENABLE	\
+	(NETIF_MSG_DRV			\
+	| NETIF_MSG_PROBE		\
+	| NETIF_MSG_LINK		\
+	| NETIF_MSG_TIMER		\
+	| NETIF_MSG_IFDOWN		\
+	| NETIF_MSG_IFUP		\
+	| NETIF_MSG_RX_ERR		\
+	| NETIF_MSG_TX_ERR)
+
+#define DESC_EMPTY		BIT(31)
+#define DESC_MORE		BIT(24)
+#define DESC_PKTLEN_M		0xfff
+struct ag71xx_desc {
+	u32 data;
+	u32 ctrl;
+	u32 next;
+	u32 pad;
+} __aligned(4);
+
+#define AG71XX_DESC_SIZE	roundup(sizeof(struct ag71xx_desc), \
+					L1_CACHE_BYTES)
+
+struct ag71xx_buf {
+	union {
+		struct {
+			struct sk_buff *skb;
+			unsigned int len;
+		} tx;
+		struct {
+			dma_addr_t dma_addr;
+			void *rx_buf;
+		} rx;
+	};
+};
+
+struct ag71xx_ring {
+	/* "Hot" fields in the data path. */
+	unsigned int curr;
+	unsigned int dirty;
+
+	/* "Cold" fields - not used in the data path. */
+	struct ag71xx_buf *buf;
+	u16 order;
+	u16 desc_split;
+	dma_addr_t descs_dma;
+	u8 *descs_cpu;
+};
+
+enum ag71xx_type {
+	AR7100,
+	AR7240,
+	AR9130,
+	AR9330,
+	AR9340,
+	QCA9530,
+	QCA9550,
+};
+
+struct ag71xx_dcfg {
+	u32 max_frame_len;
+	const u32 *fifodata;
+	u16 desc_pktlen_mask;
+	bool tx_hang_workaround;
+	enum ag71xx_type type;
+};
+
+struct ag71xx {
+	/* Critical data related to the per-packet data path are clustered
+	 * early in this structure to help improve the D-cache footprint.
+	 */
+	struct ag71xx_ring rx_ring ____cacheline_aligned;
+	struct ag71xx_ring tx_ring ____cacheline_aligned;
+
+	u16 rx_buf_size;
+	u8 rx_buf_offset;
+
+	struct net_device *ndev;
+	struct platform_device *pdev;
+	struct napi_struct napi;
+	u32 msg_enable;
+	const struct ag71xx_dcfg *dcfg;
+
+	/* From this point onwards we're not looking at per-packet fields. */
+	void __iomem *mac_base;
+
+	struct ag71xx_desc *stop_desc;
+	dma_addr_t stop_desc_dma;
+
+	int phy_if_mode;
+
+	struct delayed_work restart_work;
+	struct timer_list oom_timer;
+
+	struct reset_control *mac_reset;
+
+	u32 fifodata[3];
+	int mac_idx;
+
+	struct reset_control *mdio_reset;
+	struct mii_bus *mii_bus;
+	struct clk *clk_mdio;
+	struct clk *clk_eth;
+};
+
+static int ag71xx_desc_empty(struct ag71xx_desc *desc)
+{
+	return (desc->ctrl & DESC_EMPTY) != 0;
+}
+
+static struct ag71xx_desc *ag71xx_ring_desc(struct ag71xx_ring *ring, int idx)
+{
+	return (struct ag71xx_desc *)&ring->descs_cpu[idx * AG71XX_DESC_SIZE];
+}
+
+static int ag71xx_ring_size_order(int size)
+{
+	return fls(size - 1);
+}
+
+static bool ag71xx_is(struct ag71xx *ag, enum ag71xx_type type)
+{
+	return ag->dcfg->type == type;
+}
+
+static void ag71xx_wr(struct ag71xx *ag, unsigned int reg, u32 value)
+{
+	iowrite32(value, ag->mac_base + reg);
+	/* flush write */
+	(void)ioread32(ag->mac_base + reg);
+}
+
+static u32 ag71xx_rr(struct ag71xx *ag, unsigned int reg)
+{
+	return ioread32(ag->mac_base + reg);
+}
+
+static void ag71xx_sb(struct ag71xx *ag, unsigned int reg, u32 mask)
+{
+	void __iomem *r;
+
+	r = ag->mac_base + reg;
+	iowrite32(ioread32(r) | mask, r);
+	/* flush write */
+	(void)ioread32(r);
+}
+
+static void ag71xx_cb(struct ag71xx *ag, unsigned int reg, u32 mask)
+{
+	void __iomem *r;
+
+	r = ag->mac_base + reg;
+	iowrite32(ioread32(r) & ~mask, r);
+	/* flush write */
+	(void)ioread32(r);
+}
+
+static void ag71xx_int_enable(struct ag71xx *ag, u32 ints)
+{
+	ag71xx_sb(ag, AG71XX_REG_INT_ENABLE, ints);
+}
+
+static void ag71xx_int_disable(struct ag71xx *ag, u32 ints)
+{
+	ag71xx_cb(ag, AG71XX_REG_INT_ENABLE, ints);
+}
+
+static int ag71xx_mdio_wait_busy(struct ag71xx *ag)
+{
+	struct net_device *ndev = ag->ndev;
+	int i;
+
+	for (i = 0; i < AG71XX_MDIO_RETRY; i++) {
+		u32 busy;
+
+		udelay(AG71XX_MDIO_DELAY);
+
+		busy = ag71xx_rr(ag, AG71XX_REG_MII_IND);
+		if (!busy)
+			return 0;
+
+		udelay(AG71XX_MDIO_DELAY);
+	}
+
+	netif_err(ag, link, ndev, "MDIO operation timed out\n");
+
+	return -ETIMEDOUT;
+}
+
+static int ag71xx_mdio_mii_read(struct mii_bus *bus, int addr, int reg)
+{
+	struct ag71xx *ag = bus->priv;
+	int err, val;
+
+	err = ag71xx_mdio_wait_busy(ag);
+	if (err)
+		return err;
+
+	ag71xx_wr(ag, AG71XX_REG_MII_ADDR,
+		  ((addr & 0x1f) << MII_ADDR_SHIFT) | (reg & 0xff));
+	/* enable read mode */
+	ag71xx_wr(ag, AG71XX_REG_MII_CMD, MII_CMD_READ);
+
+	err = ag71xx_mdio_wait_busy(ag);
+	if (err)
+		return err;
+
+	val = ag71xx_rr(ag, AG71XX_REG_MII_STATUS);
+	/* disable read mode */
+	ag71xx_wr(ag, AG71XX_REG_MII_CMD, 0);
+
+	netif_dbg(ag, link, ag->ndev, "mii_read: addr=%04x, reg=%04x, value=%04x\n",
+		  addr, reg, val);
+
+	return val;
+}
+
+static int ag71xx_mdio_mii_write(struct mii_bus *bus, int addr, int reg,
+				 u16 val)
+{
+	struct ag71xx *ag = bus->priv;
+
+	netif_dbg(ag, link, ag->ndev, "mii_write: addr=%04x, reg=%04x, value=%04x\n",
+		  addr, reg, val);
+
+	ag71xx_wr(ag, AG71XX_REG_MII_ADDR,
+		  ((addr & 0x1f) << MII_ADDR_SHIFT) | (reg & 0xff));
+	ag71xx_wr(ag, AG71XX_REG_MII_CTRL, val);
+
+	return ag71xx_mdio_wait_busy(ag);
+}
+
+static const u32 ar71xx_mdio_div_table[] = {
+	4, 4, 6, 8, 10, 14, 20, 28,
+};
+
+static const u32 ar7240_mdio_div_table[] = {
+	2, 2, 4, 6, 8, 12, 18, 26, 32, 40, 48, 56, 62, 70, 78, 96,
+};
+
+static const u32 ar933x_mdio_div_table[] = {
+	4, 4, 6, 8, 10, 14, 20, 28, 34, 42, 50, 58, 66, 74, 82, 98,
+};
+
+static int ag71xx_mdio_get_divider(struct ag71xx *ag, u32 *div)
+{
+	unsigned long ref_clock;
+	const u32 *table;
+	int ndivs, i;
+
+	ref_clock = clk_get_rate(ag->clk_mdio);
+	if (!ref_clock)
+		return -EINVAL;
+
+	if (ag71xx_is(ag, AR9330) || ag71xx_is(ag, AR9340)) {
+		table = ar933x_mdio_div_table;
+		ndivs = ARRAY_SIZE(ar933x_mdio_div_table);
+	} else if (ag71xx_is(ag, AR7240)) {
+		table = ar7240_mdio_div_table;
+		ndivs = ARRAY_SIZE(ar7240_mdio_div_table);
+	} else {
+		table = ar71xx_mdio_div_table;
+		ndivs = ARRAY_SIZE(ar71xx_mdio_div_table);
+	}
+
+	for (i = 0; i < ndivs; i++) {
+		unsigned long t;
+
+		t = ref_clock / table[i];
+		if (t <= AG71XX_MDIO_MAX_CLK) {
+			*div = i;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+static int ag71xx_mdio_reset(struct mii_bus *bus)
+{
+	struct ag71xx *ag = bus->priv;
+	int err;
+	u32 t;
+
+	err = ag71xx_mdio_get_divider(ag, &t);
+	if (err)
+		return err;
+
+	ag71xx_wr(ag, AG71XX_REG_MII_CFG, t | MII_CFG_RESET);
+	usleep_range(100, 200);
+
+	ag71xx_wr(ag, AG71XX_REG_MII_CFG, t);
+	usleep_range(100, 200);
+
+	return 0;
+}
+
+static int ag71xx_mdio_probe(struct ag71xx *ag)
+{
+	struct device *dev = &ag->pdev->dev;
+	struct net_device *ndev = ag->ndev;
+	static struct mii_bus *mii_bus;
+	struct device_node *np;
+	int err;
+
+	np = dev->of_node;
+	ag->mii_bus = NULL;
+
+	ag->clk_mdio = devm_clk_get(dev, "mdio");
+	if (IS_ERR(ag->clk_mdio)) {
+		netif_err(ag, probe, ndev, "Failed to get mdio clk.\n");
+		return PTR_ERR(ag->clk_mdio);
+	}
+
+	err = clk_prepare_enable(ag->clk_mdio);
+	if (err) {
+		netif_err(ag, probe, ndev, "Failed to enable mdio clk.\n");
+		return err;
+	}
+
+	mii_bus = devm_mdiobus_alloc(dev);
+	if (!mii_bus) {
+		err = -ENOMEM;
+		goto mdio_err_put_clk;
+	}
+
+	ag->mdio_reset = of_reset_control_get_exclusive(np, "mdio");
+	if (IS_ERR(ag->mdio_reset)) {
+		netif_err(ag, probe, ndev, "Failed to get reset mdio.\n");
+		return PTR_ERR(ag->mdio_reset);
+	}
+
+	mii_bus->name = "ag71xx_mdio";
+	mii_bus->read = ag71xx_mdio_mii_read;
+	mii_bus->write = ag71xx_mdio_mii_write;
+	mii_bus->reset = ag71xx_mdio_reset;
+	mii_bus->priv = ag;
+	mii_bus->parent = dev;
+	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "%s.%d", np->name, ag->mac_idx);
+
+	if (!IS_ERR(ag->mdio_reset)) {
+		reset_control_assert(ag->mdio_reset);
+		msleep(100);
+		reset_control_deassert(ag->mdio_reset);
+		msleep(200);
+	}
+
+	err = of_mdiobus_register(mii_bus, np);
+	if (err)
+		goto mdio_err_put_clk;
+
+	ag->mii_bus = mii_bus;
+
+	return 0;
+
+mdio_err_put_clk:
+	clk_disable_unprepare(ag->clk_mdio);
+	return err;
+}
+
+static void ag71xx_mdio_remove(struct ag71xx *ag)
+{
+	if (ag->mii_bus)
+		mdiobus_unregister(ag->mii_bus);
+	clk_disable_unprepare(ag->clk_mdio);
+}
+
+static void ag71xx_hw_stop(struct ag71xx *ag)
+{
+	/* disable all interrupts and stop the rx/tx engine */
+	ag71xx_wr(ag, AG71XX_REG_INT_ENABLE, 0);
+	ag71xx_wr(ag, AG71XX_REG_RX_CTRL, 0);
+	ag71xx_wr(ag, AG71XX_REG_TX_CTRL, 0);
+}
+
+static bool ag71xx_check_dma_stuck(struct ag71xx *ag)
+{
+	unsigned long timestamp;
+	u32 rx_sm, tx_sm, rx_fd;
+
+	timestamp = netdev_get_tx_queue(ag->ndev, 0)->trans_start;
+	if (likely(time_before(jiffies, timestamp + HZ / 10)))
+		return false;
+
+	if (!netif_carrier_ok(ag->ndev))
+		return false;
+
+	rx_sm = ag71xx_rr(ag, AG71XX_REG_RX_SM);
+	if ((rx_sm & 0x7) == 0x3 && ((rx_sm >> 4) & 0x7) == 0x6)
+		return true;
+
+	tx_sm = ag71xx_rr(ag, AG71XX_REG_TX_SM);
+	rx_fd = ag71xx_rr(ag, AG71XX_REG_FIFO_DEPTH);
+	if (((tx_sm >> 4) & 0x7) == 0 && ((rx_sm & 0x7) == 0) &&
+	    ((rx_sm >> 4) & 0x7) == 0 && rx_fd == 0)
+		return true;
+
+	return false;
+}
+
+static int ag71xx_tx_packets(struct ag71xx *ag, bool flush)
+{
+	struct ag71xx_ring *ring = &ag->tx_ring;
+	int sent = 0, bytes_compl = 0, n = 0;
+	struct net_device *ndev = ag->ndev;
+	int ring_mask, ring_size;
+	bool dma_stuck = false;
+
+	ring_mask = BIT(ring->order) - 1;
+	ring_size = BIT(ring->order);
+
+	netif_dbg(ag, tx_queued, ndev, "processing TX ring\n");
+
+	while (ring->dirty + n != ring->curr) {
+		struct ag71xx_desc *desc;
+		struct sk_buff *skb;
+		unsigned int i;
+
+		i = (ring->dirty + n) & ring_mask;
+		desc = ag71xx_ring_desc(ring, i);
+		skb = ring->buf[i].tx.skb;
+
+		if (!flush && !ag71xx_desc_empty(desc)) {
+			if (ag->dcfg->tx_hang_workaround &&
+			    ag71xx_check_dma_stuck(ag)) {
+				schedule_delayed_work(&ag->restart_work,
+						      HZ / 2);
+				dma_stuck = true;
+			}
+			break;
+		}
+
+		if (flush)
+			desc->ctrl |= DESC_EMPTY;
+
+		n++;
+		if (!skb)
+			continue;
+
+		dev_kfree_skb_any(skb);
+		ring->buf[i].tx.skb = NULL;
+
+		bytes_compl += ring->buf[i].tx.len;
+
+		sent++;
+		ring->dirty += n;
+
+		while (n > 0) {
+			ag71xx_wr(ag, AG71XX_REG_TX_STATUS, TX_STATUS_PS);
+			n--;
+		}
+	}
+
+	netif_dbg(ag, tx_done, ndev, "%d packets sent out\n", sent);
+
+	if (!sent)
+		return 0;
+
+	ag->ndev->stats.tx_bytes += bytes_compl;
+	ag->ndev->stats.tx_packets += sent;
+
+	netdev_completed_queue(ag->ndev, sent, bytes_compl);
+	if ((ring->curr - ring->dirty) < (ring_size * 3) / 4)
+		netif_wake_queue(ag->ndev);
+
+	if (!dma_stuck)
+		cancel_delayed_work(&ag->restart_work);
+
+	return sent;
+}
+
+static void ag71xx_dma_wait_stop(struct ag71xx *ag)
+{
+	struct net_device *ndev = ag->ndev;
+	int i;
+
+	for (i = 0; i < AG71XX_DMA_RETRY; i++) {
+		u32 rx, tx;
+
+		mdelay(AG71XX_DMA_DELAY);
+
+		rx = ag71xx_rr(ag, AG71XX_REG_RX_CTRL) & RX_CTRL_RXE;
+		tx = ag71xx_rr(ag, AG71XX_REG_TX_CTRL) & TX_CTRL_TXE;
+		if (!rx && !tx)
+			return;
+	}
+
+	netif_err(ag, hw, ndev, "DMA stop operation timed out\n");
+}
+
+static void ag71xx_dma_reset(struct ag71xx *ag)
+{
+	struct net_device *ndev = ag->ndev;
+	u32 val;
+	int i;
+
+	/* stop RX and TX */
+	ag71xx_wr(ag, AG71XX_REG_RX_CTRL, 0);
+	ag71xx_wr(ag, AG71XX_REG_TX_CTRL, 0);
+
+	/* give the hardware some time to really stop all rx/tx activity
+	 * clearing the descriptors too early causes random memory corruption
+	 */
+	ag71xx_dma_wait_stop(ag);
+
+	/* clear descriptor addresses */
+	ag71xx_wr(ag, AG71XX_REG_TX_DESC, ag->stop_desc_dma);
+	ag71xx_wr(ag, AG71XX_REG_RX_DESC, ag->stop_desc_dma);
+
+	/* clear pending RX/TX interrupts */
+	for (i = 0; i < 256; i++) {
+		ag71xx_wr(ag, AG71XX_REG_RX_STATUS, RX_STATUS_PR);
+		ag71xx_wr(ag, AG71XX_REG_TX_STATUS, TX_STATUS_PS);
+	}
+
+	/* clear pending errors */
+	ag71xx_wr(ag, AG71XX_REG_RX_STATUS, RX_STATUS_BE | RX_STATUS_OF);
+	ag71xx_wr(ag, AG71XX_REG_TX_STATUS, TX_STATUS_BE | TX_STATUS_UR);
+
+	val = ag71xx_rr(ag, AG71XX_REG_RX_STATUS);
+	if (val)
+		netif_err(ag, hw, ndev, "unable to clear DMA Rx status: %08x\n",
+			  val);
+
+	val = ag71xx_rr(ag, AG71XX_REG_TX_STATUS);
+
+	/* mask out reserved bits */
+	val &= ~0xff000000;
+
+	if (val)
+		netif_err(ag, hw, ndev, "unable to clear DMA Tx status: %08x\n",
+			  val);
+}
+
+static void ag71xx_hw_setup(struct ag71xx *ag)
+{
+	u32 init = MAC_CFG1_INIT;
+
+	/* setup MAC configuration registers */
+	ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, init);
+
+	ag71xx_sb(ag, AG71XX_REG_MAC_CFG2,
+		  MAC_CFG2_PAD_CRC_EN | MAC_CFG2_LEN_CHECK);
+
+	/* setup max frame length to zero */
+	ag71xx_wr(ag, AG71XX_REG_MAC_MFL, 0);
+
+	/* setup FIFO configuration registers */
+	ag71xx_wr(ag, AG71XX_REG_FIFO_CFG0, FIFO_CFG0_INIT);
+	ag71xx_wr(ag, AG71XX_REG_FIFO_CFG1, ag->fifodata[0]);
+	ag71xx_wr(ag, AG71XX_REG_FIFO_CFG2, ag->fifodata[1]);
+	ag71xx_wr(ag, AG71XX_REG_FIFO_CFG4, FIFO_CFG4_INIT);
+	ag71xx_wr(ag, AG71XX_REG_FIFO_CFG5, FIFO_CFG5_INIT);
+}
+
+static unsigned int ag71xx_max_frame_len(unsigned int mtu)
+{
+	return ETH_SWITCH_HEADER_LEN + ETH_HLEN + VLAN_HLEN + mtu + ETH_FCS_LEN;
+}
+
+static void ag71xx_hw_set_macaddr(struct ag71xx *ag, unsigned char *mac)
+{
+	u32 t;
+
+	t = (((u32)mac[5]) << 24) | (((u32)mac[4]) << 16)
+	  | (((u32)mac[3]) << 8) | ((u32)mac[2]);
+
+	ag71xx_wr(ag, AG71XX_REG_MAC_ADDR1, t);
+
+	t = (((u32)mac[1]) << 24) | (((u32)mac[0]) << 16);
+	ag71xx_wr(ag, AG71XX_REG_MAC_ADDR2, t);
+}
+
+static void ag71xx_fast_reset(struct ag71xx *ag)
+{
+	struct net_device *dev = ag->ndev;
+	u32 rx_ds;
+	u32 mii_reg;
+
+	ag71xx_hw_stop(ag);
+
+	mii_reg = ag71xx_rr(ag, AG71XX_REG_MII_CFG);
+	rx_ds = ag71xx_rr(ag, AG71XX_REG_RX_DESC);
+
+	ag71xx_tx_packets(ag, true);
+
+	reset_control_assert(ag->mac_reset);
+	usleep_range(10, 20);
+	reset_control_deassert(ag->mac_reset);
+	usleep_range(10, 20);
+
+	ag71xx_dma_reset(ag);
+	ag71xx_hw_setup(ag);
+	ag->tx_ring.curr = 0;
+	ag->tx_ring.dirty = 0;
+	netdev_reset_queue(ag->ndev);
+
+	/* setup max frame length */
+	ag71xx_wr(ag, AG71XX_REG_MAC_MFL,
+		  ag71xx_max_frame_len(ag->ndev->mtu));
+
+	ag71xx_wr(ag, AG71XX_REG_RX_DESC, rx_ds);
+	ag71xx_wr(ag, AG71XX_REG_TX_DESC, ag->tx_ring.descs_dma);
+	ag71xx_wr(ag, AG71XX_REG_MII_CFG, mii_reg);
+
+	ag71xx_hw_set_macaddr(ag, dev->dev_addr);
+}
+
+static void ag71xx_hw_start(struct ag71xx *ag)
+{
+	/* start RX engine */
+	ag71xx_wr(ag, AG71XX_REG_RX_CTRL, RX_CTRL_RXE);
+
+	/* enable interrupts */
+	ag71xx_wr(ag, AG71XX_REG_INT_ENABLE, AG71XX_INT_INIT);
+
+	netif_wake_queue(ag->ndev);
+}
+
+static void ag71xx_link_adjust(struct ag71xx *ag, bool update)
+{
+	struct phy_device *phydev = ag->ndev->phydev;
+	u32 cfg2;
+	u32 ifctl;
+	u32 fifo5;
+
+	if (!phydev->link && update) {
+		ag71xx_hw_stop(ag);
+		return;
+	}
+
+	if (!ag71xx_is(ag, AR7100) && !ag71xx_is(ag, AR9130))
+		ag71xx_fast_reset(ag);
+
+	cfg2 = ag71xx_rr(ag, AG71XX_REG_MAC_CFG2);
+	cfg2 &= ~(MAC_CFG2_IF_1000 | MAC_CFG2_IF_10_100 | MAC_CFG2_FDX);
+	cfg2 |= (phydev->duplex) ? MAC_CFG2_FDX : 0;
+
+	ifctl = ag71xx_rr(ag, AG71XX_REG_MAC_IFCTL);
+	ifctl &= ~(MAC_IFCTL_SPEED);
+
+	fifo5 = ag71xx_rr(ag, AG71XX_REG_FIFO_CFG5);
+	fifo5 &= ~FIFO_CFG5_BM;
+
+	switch (phydev->speed) {
+	case SPEED_1000:
+		cfg2 |= MAC_CFG2_IF_1000;
+		fifo5 |= FIFO_CFG5_BM;
+		break;
+	case SPEED_100:
+		cfg2 |= MAC_CFG2_IF_10_100;
+		ifctl |= MAC_IFCTL_SPEED;
+		break;
+	case SPEED_10:
+		cfg2 |= MAC_CFG2_IF_10_100;
+		break;
+	default:
+		WARN(1, "not supported speed %i\n", phydev->speed);
+		return;
+	}
+
+	if (ag->tx_ring.desc_split) {
+		ag->fifodata[2] &= 0xffff;
+		ag->fifodata[2] |= ((2048 - ag->tx_ring.desc_split) / 4) << 16;
+	}
+
+	ag71xx_wr(ag, AG71XX_REG_FIFO_CFG3, ag->fifodata[2]);
+
+	ag71xx_wr(ag, AG71XX_REG_MAC_CFG2, cfg2);
+	ag71xx_wr(ag, AG71XX_REG_FIFO_CFG5, fifo5);
+	ag71xx_wr(ag, AG71XX_REG_MAC_IFCTL, ifctl);
+
+	ag71xx_hw_start(ag);
+
+	if (update)
+		phy_print_status(phydev);
+}
+
+static void ag71xx_phy_link_adjust(struct net_device *ndev)
+{
+	struct ag71xx *ag = netdev_priv(ndev);
+
+	ag71xx_link_adjust(ag, true);
+}
+
+static int ag71xx_phy_connect(struct ag71xx *ag)
+{
+	struct device_node *np = ag->pdev->dev.of_node;
+	struct net_device *ndev = ag->ndev;
+	struct device_node *phy_node;
+	struct phy_device *phydev;
+	int ret;
+
+	if (of_phy_is_fixed_link(np)) {
+		ret = of_phy_register_fixed_link(np);
+		if (ret < 0) {
+			netif_err(ag, probe, ndev, "Failed to register fixed PHY link: %d\n",
+				  ret);
+			return ret;
+		}
+
+		phy_node = of_node_get(np);
+	} else {
+		phy_node = of_parse_phandle(np, "phy-handle", 0);
+	}
+
+	if (!phy_node) {
+		netif_err(ag, probe, ndev, "Could not find valid phy node\n");
+		return -ENODEV;
+	}
+
+	phydev = of_phy_connect(ag->ndev, phy_node, ag71xx_phy_link_adjust,
+				0, ag->phy_if_mode);
+
+	of_node_put(phy_node);
+
+	if (!phydev) {
+		netif_err(ag, probe, ndev, "Could not connect to PHY device\n");
+		return -ENODEV;
+	}
+
+	phy_attached_info(phydev);
+
+	return 0;
+}
+
+static void ag71xx_ring_tx_clean(struct ag71xx *ag)
+{
+	struct ag71xx_ring *ring = &ag->tx_ring;
+	int ring_mask = BIT(ring->order) - 1;
+	u32 bytes_compl = 0, pkts_compl = 0;
+	struct net_device *ndev = ag->ndev;
+
+	while (ring->curr != ring->dirty) {
+		struct ag71xx_desc *desc;
+		u32 i = ring->dirty & ring_mask;
+
+		desc = ag71xx_ring_desc(ring, i);
+		if (!ag71xx_desc_empty(desc)) {
+			desc->ctrl = 0;
+			ndev->stats.tx_errors++;
+		}
+
+		if (ring->buf[i].tx.skb) {
+			bytes_compl += ring->buf[i].tx.len;
+			pkts_compl++;
+			dev_kfree_skb_any(ring->buf[i].tx.skb);
+		}
+		ring->buf[i].tx.skb = NULL;
+		ring->dirty++;
+	}
+
+	/* flush descriptors */
+	wmb();
+
+	netdev_completed_queue(ndev, pkts_compl, bytes_compl);
+}
+
+static void ag71xx_ring_tx_init(struct ag71xx *ag)
+{
+	struct ag71xx_ring *ring = &ag->tx_ring;
+	int ring_size = BIT(ring->order);
+	int ring_mask = ring_size - 1;
+	int i;
+
+	for (i = 0; i < ring_size; i++) {
+		struct ag71xx_desc *desc = ag71xx_ring_desc(ring, i);
+
+		desc->next = (u32)(ring->descs_dma +
+			AG71XX_DESC_SIZE * ((i + 1) & ring_mask));
+
+		desc->ctrl = DESC_EMPTY;
+		ring->buf[i].tx.skb = NULL;
+	}
+
+	/* flush descriptors */
+	wmb();
+
+	ring->curr = 0;
+	ring->dirty = 0;
+	netdev_reset_queue(ag->ndev);
+}
+
+static void ag71xx_ring_rx_clean(struct ag71xx *ag)
+{
+	struct ag71xx_ring *ring = &ag->rx_ring;
+	int ring_size = BIT(ring->order);
+	int i;
+
+	if (!ring->buf)
+		return;
+
+	for (i = 0; i < ring_size; i++)
+		if (ring->buf[i].rx.rx_buf) {
+			dma_unmap_single(&ag->pdev->dev,
+					 ring->buf[i].rx.dma_addr,
+					 ag->rx_buf_size, DMA_FROM_DEVICE);
+			skb_free_frag(ring->buf[i].rx.rx_buf);
+		}
+}
+
+static int ag71xx_buffer_size(struct ag71xx *ag)
+{
+	return ag->rx_buf_size +
+	       SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+}
+
+static bool ag71xx_fill_rx_buf(struct ag71xx *ag, struct ag71xx_buf *buf,
+			       int offset,
+			       void *(*alloc)(unsigned int size))
+{
+	struct ag71xx_ring *ring = &ag->rx_ring;
+	struct ag71xx_desc *desc;
+	void *data;
+
+	desc = ag71xx_ring_desc(ring, buf - &ring->buf[0]);
+
+	data = alloc(ag71xx_buffer_size(ag));
+	if (!data)
+		return false;
+
+	buf->rx.rx_buf = data;
+	buf->rx.dma_addr = dma_map_single(&ag->pdev->dev, data, ag->rx_buf_size,
+					  DMA_FROM_DEVICE);
+	desc->data = (u32)buf->rx.dma_addr + offset;
+	return true;
+}
+
+static int ag71xx_ring_rx_init(struct ag71xx *ag)
+{
+	struct ag71xx_ring *ring = &ag->rx_ring;
+	struct net_device *ndev = ag->ndev;
+	int ring_mask = BIT(ring->order) - 1;
+	int ring_size = BIT(ring->order);
+	unsigned int i;
+	int ret;
+
+	ret = 0;
+	for (i = 0; i < ring_size; i++) {
+		struct ag71xx_desc *desc = ag71xx_ring_desc(ring, i);
+
+		desc->next = (u32)(ring->descs_dma +
+			AG71XX_DESC_SIZE * ((i + 1) & ring_mask));
+
+		netif_dbg(ag, rx_status, ndev, "RX desc at %p, next is %08x\n",
+			  desc, desc->next);
+	}
+
+	for (i = 0; i < ring_size; i++) {
+		struct ag71xx_desc *desc = ag71xx_ring_desc(ring, i);
+
+		if (!ag71xx_fill_rx_buf(ag, &ring->buf[i], ag->rx_buf_offset,
+					netdev_alloc_frag)) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		desc->ctrl = DESC_EMPTY;
+	}
+
+	/* flush descriptors */
+	wmb();
+
+	ring->curr = 0;
+	ring->dirty = 0;
+
+	return ret;
+}
+
+static int ag71xx_ring_rx_refill(struct ag71xx *ag)
+{
+	struct ag71xx_ring *ring = &ag->rx_ring;
+	int ring_mask = BIT(ring->order) - 1;
+	int offset = ag->rx_buf_offset;
+	unsigned int count;
+
+	count = 0;
+	for (; ring->curr - ring->dirty > 0; ring->dirty++) {
+		struct ag71xx_desc *desc;
+		unsigned int i;
+
+		i = ring->dirty & ring_mask;
+		desc = ag71xx_ring_desc(ring, i);
+
+		if (!ring->buf[i].rx.rx_buf &&
+		    !ag71xx_fill_rx_buf(ag, &ring->buf[i], offset,
+					napi_alloc_frag))
+			break;
+
+		desc->ctrl = DESC_EMPTY;
+		count++;
+	}
+
+	/* flush descriptors */
+	wmb();
+
+	netif_dbg(ag, rx_status, ag->ndev, "%u rx descriptors refilled\n",
+		  count);
+
+	return count;
+}
+
+static int ag71xx_rings_init(struct ag71xx *ag)
+{
+	struct ag71xx_ring *tx = &ag->tx_ring;
+	struct ag71xx_ring *rx = &ag->rx_ring;
+	int ring_size, tx_size;
+
+	ring_size = BIT(tx->order) + BIT(rx->order);
+	tx_size = BIT(tx->order);
+
+	tx->buf = kcalloc(ring_size, sizeof(*tx->buf), GFP_KERNEL);
+	if (!tx->buf)
+		return -ENOMEM;
+
+	tx->descs_cpu = dma_alloc_coherent(&ag->pdev->dev,
+					   ring_size * AG71XX_DESC_SIZE,
+					   &tx->descs_dma, GFP_ATOMIC);
+	if (!tx->descs_cpu) {
+		kfree(tx->buf);
+		tx->buf = NULL;
+		return -ENOMEM;
+	}
+
+	rx->buf = &tx->buf[BIT(tx->order)];
+	rx->descs_cpu = ((void *)tx->descs_cpu) + tx_size * AG71XX_DESC_SIZE;
+	rx->descs_dma = tx->descs_dma + tx_size * AG71XX_DESC_SIZE;
+
+	ag71xx_ring_tx_init(ag);
+	return ag71xx_ring_rx_init(ag);
+}
+
+static void ag71xx_rings_free(struct ag71xx *ag)
+{
+	struct ag71xx_ring *tx = &ag->tx_ring;
+	struct ag71xx_ring *rx = &ag->rx_ring;
+	int ring_size;
+
+	ring_size = BIT(tx->order) + BIT(rx->order);
+
+	if (tx->descs_cpu)
+		dma_free_coherent(&ag->pdev->dev, ring_size * AG71XX_DESC_SIZE,
+				  tx->descs_cpu, tx->descs_dma);
+
+	kfree(tx->buf);
+
+	tx->descs_cpu = NULL;
+	rx->descs_cpu = NULL;
+	tx->buf = NULL;
+	rx->buf = NULL;
+}
+
+static void ag71xx_rings_cleanup(struct ag71xx *ag)
+{
+	ag71xx_ring_rx_clean(ag);
+	ag71xx_ring_tx_clean(ag);
+	ag71xx_rings_free(ag);
+
+	netdev_reset_queue(ag->ndev);
+}
+
+static void ag71xx_hw_init(struct ag71xx *ag)
+{
+	ag71xx_hw_stop(ag);
+
+	ag71xx_sb(ag, AG71XX_REG_MAC_CFG1, MAC_CFG1_SR);
+	usleep_range(20, 30);
+
+	reset_control_assert(ag->mac_reset);
+	msleep(100);
+	reset_control_deassert(ag->mac_reset);
+	msleep(200);
+
+	ag71xx_hw_setup(ag);
+
+	ag71xx_dma_reset(ag);
+}
+
+static int ag71xx_hw_enable(struct ag71xx *ag)
+{
+	int ret;
+
+	ret = ag71xx_rings_init(ag);
+	if (ret)
+		return ret;
+
+	napi_enable(&ag->napi);
+	ag71xx_wr(ag, AG71XX_REG_TX_DESC, ag->tx_ring.descs_dma);
+	ag71xx_wr(ag, AG71XX_REG_RX_DESC, ag->rx_ring.descs_dma);
+	netif_start_queue(ag->ndev);
+
+	return 0;
+}
+
+static void ag71xx_hw_disable(struct ag71xx *ag)
+{
+	netif_stop_queue(ag->ndev);
+
+	ag71xx_hw_stop(ag);
+	ag71xx_dma_reset(ag);
+
+	napi_disable(&ag->napi);
+	del_timer_sync(&ag->oom_timer);
+
+	ag71xx_rings_cleanup(ag);
+}
+
+static int ag71xx_open(struct net_device *ndev)
+{
+	struct ag71xx *ag = netdev_priv(ndev);
+	unsigned int max_frame_len;
+	int ret;
+
+	max_frame_len = ag71xx_max_frame_len(ndev->mtu);
+	ag->rx_buf_size =
+		SKB_DATA_ALIGN(max_frame_len + NET_SKB_PAD + NET_IP_ALIGN);
+
+	/* setup max frame length */
+	ag71xx_wr(ag, AG71XX_REG_MAC_MFL, max_frame_len);
+	ag71xx_hw_set_macaddr(ag, ndev->dev_addr);
+
+	ret = ag71xx_hw_enable(ag);
+	if (ret)
+		goto err;
+
+	ret = ag71xx_phy_connect(ag);
+	if (ret)
+		goto err;
+
+	phy_start(ndev->phydev);
+
+	return 0;
+
+err:
+	ag71xx_rings_cleanup(ag);
+	return ret;
+}
+
+static int ag71xx_stop(struct net_device *ndev)
+{
+	struct ag71xx *ag = netdev_priv(ndev);
+
+	phy_stop(ndev->phydev);
+	phy_disconnect(ndev->phydev);
+	ag71xx_hw_disable(ag);
+
+	return 0;
+}
+
+static int ag71xx_fill_dma_desc(struct ag71xx_ring *ring, u32 addr, int len)
+{
+	int i, ring_mask, ndesc, split;
+	struct ag71xx_desc *desc;
+
+	ring_mask = BIT(ring->order) - 1;
+	ndesc = 0;
+	split = ring->desc_split;
+
+	if (!split)
+		split = len;
+
+	while (len > 0) {
+		unsigned int cur_len = len;
+
+		i = (ring->curr + ndesc) & ring_mask;
+		desc = ag71xx_ring_desc(ring, i);
+
+		if (!ag71xx_desc_empty(desc))
+			return -1;
+
+		if (cur_len > split) {
+			cur_len = split;
+
+			/*  TX will hang if DMA transfers <= 4 bytes,
+			 * make sure next segment is more than 4 bytes long.
+			 */
+			if (len <= split + 4)
+				cur_len -= 4;
+		}
+
+		desc->data = addr;
+		addr += cur_len;
+		len -= cur_len;
+
+		if (len > 0)
+			cur_len |= DESC_MORE;
+
+		/* prevent early tx attempt of this descriptor */
+		if (!ndesc)
+			cur_len |= DESC_EMPTY;
+
+		desc->ctrl = cur_len;
+		ndesc++;
+	}
+
+	return ndesc;
+}
+
+static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb,
+					  struct net_device *ndev)
+{
+	int i, n, ring_min, ring_mask, ring_size;
+	struct ag71xx *ag = netdev_priv(ndev);
+	struct ag71xx_ring *ring;
+	struct ag71xx_desc *desc;
+	dma_addr_t dma_addr;
+
+	ring = &ag->tx_ring;
+	ring_mask = BIT(ring->order) - 1;
+	ring_size = BIT(ring->order);
+
+	if (skb->len <= 4) {
+		netif_dbg(ag, tx_err, ndev, "packet len is too small\n");
+		goto err_drop;
+	}
+
+	dma_addr = dma_map_single(&ag->pdev->dev, skb->data, skb->len,
+				  DMA_TO_DEVICE);
+
+	i = ring->curr & ring_mask;
+	desc = ag71xx_ring_desc(ring, i);
+
+	/* setup descriptor fields */
+	n = ag71xx_fill_dma_desc(ring, (u32)dma_addr,
+				 skb->len & ag->dcfg->desc_pktlen_mask);
+	if (n < 0)
+		goto err_drop_unmap;
+
+	i = (ring->curr + n - 1) & ring_mask;
+	ring->buf[i].tx.len = skb->len;
+	ring->buf[i].tx.skb = skb;
+
+	netdev_sent_queue(ndev, skb->len);
+
+	skb_tx_timestamp(skb);
+
+	desc->ctrl &= ~DESC_EMPTY;
+	ring->curr += n;
+
+	/* flush descriptor */
+	wmb();
+
+	ring_min = 2;
+	if (ring->desc_split)
+		ring_min *= AG71XX_TX_RING_DS_PER_PKT;
+
+	if (ring->curr - ring->dirty >= ring_size - ring_min) {
+		netif_dbg(ag, tx_err, ndev, "tx queue full\n");
+		netif_stop_queue(ndev);
+	}
+
+	netif_dbg(ag, tx_queued, ndev, "packet injected into TX queue\n");
+
+	/* enable TX engine */
+	ag71xx_wr(ag, AG71XX_REG_TX_CTRL, TX_CTRL_TXE);
+
+	return NETDEV_TX_OK;
+
+err_drop_unmap:
+	dma_unmap_single(&ag->pdev->dev, dma_addr, skb->len, DMA_TO_DEVICE);
+
+err_drop:
+	ndev->stats.tx_dropped++;
+
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static int ag71xx_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+	if (!ndev->phydev)
+		return -EINVAL;
+
+	return phy_mii_ioctl(ndev->phydev, ifr, cmd);
+}
+
+static void ag71xx_oom_timer_handler(struct timer_list *t)
+{
+	struct ag71xx *ag = from_timer(ag, t, oom_timer);
+
+	napi_schedule(&ag->napi);
+}
+
+static void ag71xx_tx_timeout(struct net_device *ndev)
+{
+	struct ag71xx *ag = netdev_priv(ndev);
+
+	netif_err(ag, tx_err, ndev, "tx timeout\n");
+
+	schedule_delayed_work(&ag->restart_work, 1);
+}
+
+static void ag71xx_restart_work_func(struct work_struct *work)
+{
+	struct ag71xx *ag = container_of(work, struct ag71xx,
+					 restart_work.work);
+	struct net_device *ndev = ag->ndev;
+
+	rtnl_lock();
+	ag71xx_hw_disable(ag);
+	ag71xx_hw_enable(ag);
+	if (ndev->phydev->link)
+		ag71xx_link_adjust(ag, false);
+	rtnl_unlock();
+}
+
+static int ag71xx_rx_packets(struct ag71xx *ag, int limit)
+{
+	struct net_device *ndev = ag->ndev;
+	int ring_mask, ring_size, done = 0;
+	unsigned int pktlen_mask, offset;
+	struct sk_buff *next, *skb;
+	struct ag71xx_ring *ring;
+	struct list_head rx_list;
+
+	ring = &ag->rx_ring;
+	pktlen_mask = ag->dcfg->desc_pktlen_mask;
+	offset = ag->rx_buf_offset;
+	ring_mask = BIT(ring->order) - 1;
+	ring_size = BIT(ring->order);
+
+	netif_dbg(ag, rx_status, ndev, "rx packets, limit=%d, curr=%u, dirty=%u\n",
+		  limit, ring->curr, ring->dirty);
+
+	INIT_LIST_HEAD(&rx_list);
+
+	while (done < limit) {
+		unsigned int i = ring->curr & ring_mask;
+		struct ag71xx_desc *desc = ag71xx_ring_desc(ring, i);
+		int pktlen;
+		int err = 0;
+
+		if (ag71xx_desc_empty(desc))
+			break;
+
+		if ((ring->dirty + ring_size) == ring->curr) {
+			WARN_ONCE(1, "RX out of ring");
+			break;
+		}
+
+		ag71xx_wr(ag, AG71XX_REG_RX_STATUS, RX_STATUS_PR);
+
+		pktlen = desc->ctrl & pktlen_mask;
+		pktlen -= ETH_FCS_LEN;
+
+		dma_unmap_single(&ag->pdev->dev, ring->buf[i].rx.dma_addr,
+				 ag->rx_buf_size, DMA_FROM_DEVICE);
+
+		ndev->stats.rx_packets++;
+		ndev->stats.rx_bytes += pktlen;
+
+		skb = build_skb(ring->buf[i].rx.rx_buf, ag71xx_buffer_size(ag));
+		if (!skb) {
+			skb_free_frag(ring->buf[i].rx.rx_buf);
+			goto next;
+		}
+
+		skb_reserve(skb, offset);
+		skb_put(skb, pktlen);
+
+		if (err) {
+			ndev->stats.rx_dropped++;
+			kfree_skb(skb);
+		} else {
+			skb->dev = ndev;
+			skb->ip_summed = CHECKSUM_NONE;
+			list_add_tail(&skb->list, &rx_list);
+		}
+
+next:
+		ring->buf[i].rx.rx_buf = NULL;
+		done++;
+
+		ring->curr++;
+	}
+
+	ag71xx_ring_rx_refill(ag);
+
+	list_for_each_entry_safe(skb, next, &rx_list, list)
+		skb->protocol = eth_type_trans(skb, ndev);
+	netif_receive_skb_list(&rx_list);
+
+	netif_dbg(ag, rx_status, ndev, "rx finish, curr=%u, dirty=%u, done=%d\n",
+		  ring->curr, ring->dirty, done);
+
+	return done;
+}
+
+static int ag71xx_poll(struct napi_struct *napi, int limit)
+{
+	struct ag71xx *ag = container_of(napi, struct ag71xx, napi);
+	struct ag71xx_ring *rx_ring = &ag->rx_ring;
+	int rx_ring_size = BIT(rx_ring->order);
+	struct net_device *ndev = ag->ndev;
+	int tx_done, rx_done;
+	u32 status;
+
+	tx_done = ag71xx_tx_packets(ag, false);
+
+	netif_dbg(ag, rx_status, ndev, "processing RX ring\n");
+	rx_done = ag71xx_rx_packets(ag, limit);
+
+	if (!rx_ring->buf[rx_ring->dirty % rx_ring_size].rx.rx_buf)
+		goto oom;
+
+	status = ag71xx_rr(ag, AG71XX_REG_RX_STATUS);
+	if (unlikely(status & RX_STATUS_OF)) {
+		ag71xx_wr(ag, AG71XX_REG_RX_STATUS, RX_STATUS_OF);
+		ndev->stats.rx_fifo_errors++;
+
+		/* restart RX */
+		ag71xx_wr(ag, AG71XX_REG_RX_CTRL, RX_CTRL_RXE);
+	}
+
+	if (rx_done < limit) {
+		if (status & RX_STATUS_PR)
+			goto more;
+
+		status = ag71xx_rr(ag, AG71XX_REG_TX_STATUS);
+		if (status & TX_STATUS_PS)
+			goto more;
+
+		netif_dbg(ag, rx_status, ndev, "disable polling mode, rx=%d, tx=%d,limit=%d\n",
+			  rx_done, tx_done, limit);
+
+		napi_complete(napi);
+
+		/* enable interrupts */
+		ag71xx_int_enable(ag, AG71XX_INT_POLL);
+		return rx_done;
+	}
+
+more:
+	netif_dbg(ag, rx_status, ndev, "stay in polling mode, rx=%d, tx=%d, limit=%d\n",
+		  rx_done, tx_done, limit);
+	return limit;
+
+oom:
+	netif_err(ag, rx_err, ndev, "out of memory\n");
+
+	mod_timer(&ag->oom_timer, jiffies + AG71XX_OOM_REFILL);
+	napi_complete(napi);
+	return 0;
+}
+
+static irqreturn_t ag71xx_interrupt(int irq, void *dev_id)
+{
+	struct net_device *ndev = dev_id;
+	struct ag71xx *ag;
+	u32 status;
+
+	ag = netdev_priv(ndev);
+	status = ag71xx_rr(ag, AG71XX_REG_INT_STATUS);
+
+	if (unlikely(!status))
+		return IRQ_NONE;
+
+	if (unlikely(status & AG71XX_INT_ERR)) {
+		if (status & AG71XX_INT_TX_BE) {
+			ag71xx_wr(ag, AG71XX_REG_TX_STATUS, TX_STATUS_BE);
+			netif_err(ag, intr, ndev, "TX BUS error\n");
+		}
+		if (status & AG71XX_INT_RX_BE) {
+			ag71xx_wr(ag, AG71XX_REG_RX_STATUS, RX_STATUS_BE);
+			netif_err(ag, intr, ndev, "RX BUS error\n");
+		}
+	}
+
+	if (likely(status & AG71XX_INT_POLL)) {
+		ag71xx_int_disable(ag, AG71XX_INT_POLL);
+		netif_dbg(ag, intr, ndev, "enable polling mode\n");
+		napi_schedule(&ag->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int ag71xx_change_mtu(struct net_device *ndev, int new_mtu)
+{
+	struct ag71xx *ag = netdev_priv(ndev);
+
+	ndev->mtu = new_mtu;
+	ag71xx_wr(ag, AG71XX_REG_MAC_MFL,
+		  ag71xx_max_frame_len(ndev->mtu));
+
+	return 0;
+}
+
+static const struct net_device_ops ag71xx_netdev_ops = {
+	.ndo_open		= ag71xx_open,
+	.ndo_stop		= ag71xx_stop,
+	.ndo_start_xmit		= ag71xx_hard_start_xmit,
+	.ndo_do_ioctl		= ag71xx_do_ioctl,
+	.ndo_tx_timeout		= ag71xx_tx_timeout,
+	.ndo_change_mtu		= ag71xx_change_mtu,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+};
+
+static const u32 ar71xx_addr_ar7100[] = {
+	0x19000000, 0x1a000000,
+};
+
+static int ag71xx_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const struct ag71xx_dcfg *dcfg;
+	struct net_device *ndev;
+	struct resource *res;
+	const void *mac_addr;
+	int tx_size, err, i;
+	struct ag71xx *ag;
+
+	if (!np)
+		return -ENODEV;
+
+	ndev = devm_alloc_etherdev(&pdev->dev, sizeof(*ag));
+	if (!ndev)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+
+	dcfg = of_device_get_match_data(&pdev->dev);
+	if (!dcfg)
+		return -EINVAL;
+
+	ag = netdev_priv(ndev);
+	ag->mac_idx = -1;
+	for (i = 0; i < ARRAY_SIZE(ar71xx_addr_ar7100); i++) {
+		if (ar71xx_addr_ar7100[i] == res->start)
+			ag->mac_idx = i;
+	}
+
+	if (ag->mac_idx < 0) {
+		netif_err(ag, probe, ndev, "unknown mac idx\n");
+		return -EINVAL;
+	}
+
+	ag->clk_eth = devm_clk_get(&pdev->dev, "eth");
+	if (IS_ERR(ag->clk_eth)) {
+		netif_err(ag, probe, ndev, "Failed to get eth clk.\n");
+		return PTR_ERR(ag->clk_eth);
+	}
+
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+
+	ag->pdev = pdev;
+	ag->ndev = ndev;
+	ag->dcfg = dcfg;
+	ag->msg_enable = netif_msg_init(-1, AG71XX_DEFAULT_MSG_ENABLE);
+	memcpy(ag->fifodata, dcfg->fifodata, sizeof(ag->fifodata));
+
+	ag->mac_reset = devm_reset_control_get(&pdev->dev, "mac");
+	if (IS_ERR(ag->mac_reset)) {
+		netif_err(ag, probe, ndev, "missing mac reset\n");
+		err = PTR_ERR(ag->mac_reset);
+		goto err_free;
+	}
+
+	ag->mac_base = devm_ioremap_nocache(&pdev->dev, res->start,
+					    res->end - res->start + 1);
+	if (!ag->mac_base) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	ndev->irq = platform_get_irq(pdev, 0);
+	err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt,
+			       0x0, dev_name(&pdev->dev), ndev);
+	if (err) {
+		netif_err(ag, probe, ndev, "unable to request IRQ %d\n",
+			  ndev->irq);
+		goto err_free;
+	}
+
+	ndev->netdev_ops = &ag71xx_netdev_ops;
+
+	INIT_DELAYED_WORK(&ag->restart_work, ag71xx_restart_work_func);
+	timer_setup(&ag->oom_timer, ag71xx_oom_timer_handler, 0);
+
+	tx_size = AG71XX_TX_RING_SIZE_DEFAULT;
+	ag->rx_ring.order = ag71xx_ring_size_order(AG71XX_RX_RING_SIZE_DEFAULT);
+
+	ndev->min_mtu = 68;
+	ndev->max_mtu = dcfg->max_frame_len - ag71xx_max_frame_len(0);
+
+	ag->rx_buf_offset = NET_SKB_PAD;
+	if (!ag71xx_is(ag, AR7100) && !ag71xx_is(ag, AR9130))
+		ag->rx_buf_offset += NET_IP_ALIGN;
+
+	if (ag71xx_is(ag, AR7100)) {
+		ag->tx_ring.desc_split = AG71XX_TX_RING_SPLIT;
+		tx_size *= AG71XX_TX_RING_DS_PER_PKT;
+	}
+	ag->tx_ring.order = ag71xx_ring_size_order(tx_size);
+
+	ag->stop_desc = dmam_alloc_coherent(&pdev->dev,
+					    sizeof(struct ag71xx_desc),
+					    &ag->stop_desc_dma, GFP_KERNEL);
+	if (!ag->stop_desc)
+		goto err_free;
+
+	ag->stop_desc->data = 0;
+	ag->stop_desc->ctrl = 0;
+	ag->stop_desc->next = (u32)ag->stop_desc_dma;
+
+	mac_addr = of_get_mac_address(np);
+	if (mac_addr)
+		memcpy(ndev->dev_addr, mac_addr, ETH_ALEN);
+	if (!mac_addr || !is_valid_ether_addr(ndev->dev_addr)) {
+		netif_err(ag, probe, ndev, "invalid MAC address, using random address\n");
+		eth_random_addr(ndev->dev_addr);
+	}
+
+	ag->phy_if_mode = of_get_phy_mode(np);
+	if (ag->phy_if_mode < 0) {
+		netif_err(ag, probe, ndev, "missing phy-mode property in DT\n");
+		err = ag->phy_if_mode;
+		goto err_free;
+	}
+
+	netif_napi_add(ndev, &ag->napi, ag71xx_poll, AG71XX_NAPI_WEIGHT);
+
+	err = clk_prepare_enable(ag->clk_eth);
+	if (err) {
+		netif_err(ag, probe, ndev, "Failed to enable eth clk.\n");
+		goto err_free;
+	}
+
+	ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0);
+
+	ag71xx_hw_init(ag);
+
+	err = ag71xx_mdio_probe(ag);
+	if (err)
+		goto err_put_clk;
+
+	platform_set_drvdata(pdev, ndev);
+
+	err = register_netdev(ndev);
+	if (err) {
+		netif_err(ag, probe, ndev, "unable to register net device\n");
+		platform_set_drvdata(pdev, NULL);
+		goto err_mdio_remove;
+	}
+
+	netif_info(ag, probe, ndev, "Atheros AG71xx at 0x%08lx, irq %d, mode:%s\n",
+		   (unsigned long)ag->mac_base, ndev->irq,
+		   phy_modes(ag->phy_if_mode));
+
+	return 0;
+
+err_mdio_remove:
+	ag71xx_mdio_remove(ag);
+err_put_clk:
+	clk_disable_unprepare(ag->clk_eth);
+err_free:
+	free_netdev(ndev);
+	return err;
+}
+
+static int ag71xx_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct ag71xx *ag;
+
+	if (!ndev)
+		return 0;
+
+	ag = netdev_priv(ndev);
+	unregister_netdev(ndev);
+	ag71xx_mdio_remove(ag);
+	clk_disable_unprepare(ag->clk_eth);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static const u32 ar71xx_fifo_ar7100[] = {
+	0x0fff0000, 0x00001fff, 0x00780fff,
+};
+
+static const u32 ar71xx_fifo_ar9130[] = {
+	0x0fff0000, 0x00001fff, 0x008001ff,
+};
+
+static const u32 ar71xx_fifo_ar9330[] = {
+	0x0010ffff, 0x015500aa, 0x01f00140,
+};
+
+static const struct ag71xx_dcfg ag71xx_dcfg_ar7100 = {
+	.type = AR7100,
+	.fifodata = ar71xx_fifo_ar7100,
+	.max_frame_len = 1540,
+	.desc_pktlen_mask = SZ_4K - 1,
+	.tx_hang_workaround = false,
+};
+
+static const struct ag71xx_dcfg ag71xx_dcfg_ar7240 = {
+	.type = AR7240,
+	.fifodata = ar71xx_fifo_ar7100,
+	.max_frame_len = 1540,
+	.desc_pktlen_mask = SZ_4K - 1,
+	.tx_hang_workaround = true,
+};
+
+static const struct ag71xx_dcfg ag71xx_dcfg_ar9130 = {
+	.type = AR9130,
+	.fifodata = ar71xx_fifo_ar9130,
+	.max_frame_len = 1540,
+	.desc_pktlen_mask = SZ_4K - 1,
+	.tx_hang_workaround = false,
+};
+
+static const struct ag71xx_dcfg ag71xx_dcfg_ar9330 = {
+	.type = AR9330,
+	.fifodata = ar71xx_fifo_ar9330,
+	.max_frame_len = 1540,
+	.desc_pktlen_mask = SZ_4K - 1,
+	.tx_hang_workaround = true,
+};
+
+static const struct ag71xx_dcfg ag71xx_dcfg_ar9340 = {
+	.type = AR9340,
+	.fifodata = ar71xx_fifo_ar9330,
+	.max_frame_len = SZ_16K - 1,
+	.desc_pktlen_mask = SZ_16K - 1,
+	.tx_hang_workaround = true,
+};
+
+static const struct ag71xx_dcfg ag71xx_dcfg_qca9530 = {
+	.type = QCA9530,
+	.fifodata = ar71xx_fifo_ar9330,
+	.max_frame_len = SZ_16K - 1,
+	.desc_pktlen_mask = SZ_16K - 1,
+	.tx_hang_workaround = true,
+};
+
+static const struct ag71xx_dcfg ag71xx_dcfg_qca9550 = {
+	.type = QCA9550,
+	.fifodata = ar71xx_fifo_ar9330,
+	.max_frame_len = 1540,
+	.desc_pktlen_mask = SZ_16K - 1,
+	.tx_hang_workaround = true,
+};
+
+static const struct of_device_id ag71xx_match[] = {
+	{ .compatible = "qca,ar7100-eth", .data = &ag71xx_dcfg_ar7100 },
+	{ .compatible = "qca,ar7240-eth", .data = &ag71xx_dcfg_ar7240 },
+	{ .compatible = "qca,ar7241-eth", .data = &ag71xx_dcfg_ar7240 },
+	{ .compatible = "qca,ar7242-eth", .data = &ag71xx_dcfg_ar7240 },
+	{ .compatible = "qca,ar9130-eth", .data = &ag71xx_dcfg_ar9130 },
+	{ .compatible = "qca,ar9330-eth", .data = &ag71xx_dcfg_ar9330 },
+	{ .compatible = "qca,ar9340-eth", .data = &ag71xx_dcfg_ar9340 },
+	{ .compatible = "qca,qca9530-eth", .data = &ag71xx_dcfg_qca9530 },
+	{ .compatible = "qca,qca9550-eth", .data = &ag71xx_dcfg_qca9550 },
+	{ .compatible = "qca,qca9560-eth", .data = &ag71xx_dcfg_qca9550 },
+	{}
+};
+
+static struct platform_driver ag71xx_driver = {
+	.probe		= ag71xx_probe,
+	.remove		= ag71xx_remove,
+	.driver = {
+		.name	= "ag71xx",
+		.of_match_table = ag71xx_match,
+	}
+};
+
+module_platform_driver(ag71xx_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/atheros/alx/Makefile b/drivers/net/ethernet/atheros/alx/Makefile
index ed4a605874a3..fec7885a599b 100644
--- a/drivers/net/ethernet/atheros/alx/Makefile
+++ b/drivers/net/ethernet/atheros/alx/Makefile
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_ALX) += alx.o
 alx-objs := main.o ethtool.o hw.o
diff --git a/drivers/net/ethernet/atheros/atl1c/Makefile b/drivers/net/ethernet/atheros/atl1c/Makefile
index c37d966952ee..02d025029554 100644
--- a/drivers/net/ethernet/atheros/atl1c/Makefile
+++ b/drivers/net/ethernet/atheros/atl1c/Makefile
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_ATL1C) += atl1c.o
 atl1c-objs := atl1c_main.o atl1c_hw.o atl1c_ethtool.o
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h
index c46b489ce9b4..60b2febd7315 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright(c) 2008 - 2009 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #ifndef _ATL1C_H_
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
index 28e9ae1a193b..b5a70a36fa04 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
@@ -1,23 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2009 - 2009 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c
index 73efdb05a490..140358dcf61e 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 #include <linux/pci.h>
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
index 21d8c4dbdbe1..ce1a123dce2c 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright(c) 2008 - 2009 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #ifndef _ATL1C_HW_H_
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 3a3b35b5df67..be7f9cebb675 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2008 - 2009 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #include "atl1c.h"
@@ -1833,10 +1820,10 @@ rrs_checked:
 		atl1c_clean_rrd(rrd_ring, rrs, rfd_num);
 		if (rrs->word3 & (RRS_RX_ERR_SUM | RRS_802_3_LEN_ERR)) {
 			atl1c_clean_rfd(rfd_ring, rrs, rfd_num);
-				if (netif_msg_rx_err(adapter))
-					dev_warn(&pdev->dev,
-						"wrong packet! rrs word3 is %x\n",
-						rrs->word3);
+			if (netif_msg_rx_err(adapter))
+				dev_warn(&pdev->dev,
+					 "wrong packet! rrs word3 is %x\n",
+					 rrs->word3);
 			continue;
 		}
 
@@ -2214,7 +2201,7 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
 					  struct net_device *netdev)
 {
 	struct atl1c_adapter *adapter = netdev_priv(netdev);
-	u16 tpd_req = 1;
+	u16 tpd_req;
 	struct atl1c_tpd_desc *tpd;
 	enum atl1c_trans_queue type = atl1c_trans_normal;
 
diff --git a/drivers/net/ethernet/atheros/atl1e/Makefile b/drivers/net/ethernet/atheros/atl1e/Makefile
index bc11be824e76..8506694054a7 100644
--- a/drivers/net/ethernet/atheros/atl1e/Makefile
+++ b/drivers/net/ethernet/atheros/atl1e/Makefile
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_ATL1E)	+= atl1e.o
 atl1e-objs		+= atl1e_main.o atl1e_hw.o atl1e_ethtool.o atl1e_param.o
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e.h b/drivers/net/ethernet/atheros/atl1e/atl1e.h
index 632bb843aed6..e9893da50995 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e.h
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  * Copyright(c) 2007 xiong huang <xiong.huang@atheros.com>
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #ifndef _ATL1E_H_
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
index 282ebdde4769..c6b9e7ea8e38 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
@@ -1,23 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_hw.c b/drivers/net/ethernet/atheros/atl1e/atl1e_hw.c
index 113565da155f..fa89bc27f62d 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_hw.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_hw.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 #include <linux/pci.h>
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h b/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h
index 88a6271de5bc..3193f7d26945 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_hw.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #ifndef _ATHL1E_HW_H_
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 3164aad29bcf..7f14e010bfeb 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #include "atl1e.h"
@@ -1259,7 +1246,7 @@ static bool atl1e_clean_tx_irq(struct atl1e_adapter *adapter)
 		}
 
 		if (tx_buffer->skb) {
-			dev_kfree_skb_irq(tx_buffer->skb);
+			dev_consume_skb_irq(tx_buffer->skb);
 			tx_buffer->skb = NULL;
 		}
 
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_param.c b/drivers/net/ethernet/atheros/atl1e/atl1e_param.c
index fa314282c9ad..6b1d6df8da97 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_param.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_param.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/atheros/atlx/Makefile b/drivers/net/ethernet/atheros/atlx/Makefile
index e4f6022ca552..df030e421ff3 100644
--- a/drivers/net/ethernet/atheros/atlx/Makefile
+++ b/drivers/net/ethernet/atheros/atlx/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_ATL1)	+= atl1.o
 obj-$(CONFIG_ATL2)	+= atl2.o
 
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 63edc5706c09..7c767ce9aafa 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
  * Copyright(c) 2006 - 2007 Chris Snook <csnook@redhat.com>
@@ -6,23 +7,6 @@
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called COPYING.
- *
  * Contact Information:
  * Xiong Huang <xiong.huang@atheros.com>
  * Jie Yang <jie.yang@atheros.com>
@@ -1721,7 +1705,7 @@ static void atl1_inc_smb(struct atl1_adapter *adapter)
 	adapter->soft_stats.scc += smb->tx_1_col;
 	adapter->soft_stats.mcc += smb->tx_2_col;
 	adapter->soft_stats.latecol += smb->tx_late_col;
-	adapter->soft_stats.tx_underun += smb->tx_underrun;
+	adapter->soft_stats.tx_underrun += smb->tx_underrun;
 	adapter->soft_stats.tx_trunc += smb->tx_trunc;
 	adapter->soft_stats.tx_pause += smb->tx_pause;
 
@@ -2088,7 +2072,7 @@ static int atl1_intr_tx(struct atl1_adapter *adapter)
 		}
 
 		if (buffer_info->skb) {
-			dev_kfree_skb_irq(buffer_info->skb);
+			dev_consume_skb_irq(buffer_info->skb);
 			buffer_info->skb = NULL;
 		}
 
@@ -2439,7 +2423,6 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	atl1_tx_map(adapter, skb, ptpd);
 	atl1_tx_queue(adapter, count, ptpd);
 	atl1_update_mailbox(adapter);
-	mmiowb();
 	return NETDEV_TX_OK;
 }
 
@@ -3179,7 +3162,7 @@ static struct atl1_stats atl1_gstrings_stats[] = {
 	{"tx_deferred_ok", ATL1_STAT(soft_stats.deffer)},
 	{"tx_single_coll_ok", ATL1_STAT(soft_stats.scc)},
 	{"tx_multi_coll_ok", ATL1_STAT(soft_stats.mcc)},
-	{"tx_underun", ATL1_STAT(soft_stats.tx_underun)},
+	{"tx_underrun", ATL1_STAT(soft_stats.tx_underrun)},
 	{"tx_trunc", ATL1_STAT(soft_stats.tx_trunc)},
 	{"tx_pause", ATL1_STAT(soft_stats.tx_pause)},
 	{"rx_pause", ATL1_STAT(soft_stats.rx_pause)},
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.h b/drivers/net/ethernet/atheros/atlx/atl1.h
index 34a58cd846a0..6b264c5127a5 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.h
+++ b/drivers/net/ethernet/atheros/atlx/atl1.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
  * Copyright(c) 2006 - 2007 Chris Snook <csnook@redhat.com>
@@ -5,20 +6,6 @@
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #ifndef ATL1_H
@@ -681,7 +668,7 @@ struct atl1_sft_stats {
 	u64 scc;		/* packets TX after a single collision */
 	u64 mcc;		/* packets TX after multiple collisions */
 	u64 latecol;		/* TX packets w/ late collisions */
-	u64 tx_underun;		/* TX packets aborted due to TX FIFO underrun
+	u64 tx_underrun;	/* TX packets aborted due to TX FIFO underrun
 				 * or TRD FIFO underrun */
 	u64 tx_trunc;		/* TX packets truncated due to size > MTU */
 	u64 rx_pause;		/* num Pause packets received. */
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index bb41becb6609..3a3fb5ce0fee 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright(c) 2006 - 2007 Atheros Corporation. All rights reserved.
  * Copyright(c) 2007 - 2008 Chris Snook <csnook@redhat.com>
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #include <linux/atomic.h>
@@ -553,7 +540,7 @@ static void atl2_intr_tx(struct atl2_adapter *adapter)
 			netdev->stats.tx_aborted_errors++;
 		if (txs->late_col)
 			netdev->stats.tx_window_errors++;
-		if (txs->underun)
+		if (txs->underrun)
 			netdev->stats.tx_fifo_errors++;
 	} while (1);
 
@@ -908,8 +895,7 @@ static netdev_tx_t atl2_xmit_frame(struct sk_buff *skb,
 	ATL2_WRITE_REGW(&adapter->hw, REG_MB_TXD_WR_IDX,
 		(adapter->txd_write_ptr >> 2));
 
-	mmiowb();
-	dev_kfree_skb_any(skb);
+	dev_consume_skb_any(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -1335,13 +1321,11 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
 	struct atl2_adapter *adapter;
-	static int cards_found;
+	static int cards_found = 0;
 	unsigned long mmio_start;
 	int mmio_len;
 	int err;
 
-	cards_found = 0;
-
 	err = pci_enable_device(pdev);
 	if (err)
 		return err;
@@ -2946,7 +2930,7 @@ static int atl2_validate_option(int *value, struct atl2_option *opt)
 			if (*value == ent->i) {
 				if (ent->str[0] != '\0')
 					printk(KERN_INFO "%s\n", ent->str);
-			return 0;
+				return 0;
 			}
 		}
 		break;
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.h b/drivers/net/ethernet/atheros/atlx/atl2.h
index c64a6bdfa7ae..d97613bd15d5 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.h
+++ b/drivers/net/ethernet/atheros/atlx/atl2.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* atl2.h -- atl2 driver definitions
  *
  * Copyright(c) 2007 Atheros Corporation. All rights reserved.
@@ -6,20 +7,6 @@
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #ifndef _ATL2_H_
@@ -260,7 +247,7 @@ struct tx_pkt_status {
 	unsigned multi_col:1;
 	unsigned late_col:1;
 	unsigned abort_col:1;
-	unsigned underun:1;	/* current packet is aborted
+	unsigned underrun:1;	/* current packet is aborted
 				 * due to txram underrun */
 	unsigned:3;		/* reserved */
 	unsigned update:1;	/* always 1'b1 in tx_status_buf */
diff --git a/drivers/net/ethernet/atheros/atlx/atlx.c b/drivers/net/ethernet/atheros/atlx/atlx.c
index 46a622cceee4..505a22c703f7 100644
--- a/drivers/net/ethernet/atheros/atlx/atlx.c
+++ b/drivers/net/ethernet/atheros/atlx/atlx.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* atlx.c -- common functions for Attansic network drivers
  *
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
@@ -7,20 +8,6 @@
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 /* Including this file like a header is a temporary hack, I promise. -- CHS */
diff --git a/drivers/net/ethernet/atheros/atlx/atlx.h b/drivers/net/ethernet/atheros/atlx/atlx.h
index 448f5dcc02e6..7f5d4e24eb9f 100644
--- a/drivers/net/ethernet/atheros/atlx/atlx.h
+++ b/drivers/net/ethernet/atheros/atlx/atlx.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /* atlx_hw.h -- common hardware definitions for Attansic network drivers
  *
  * Copyright(c) 2005 - 2006 Attansic Corporation. All rights reserved.
@@ -7,20 +8,6 @@
  *
  * Derived from Intel e1000 driver
  * Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #ifndef ATLX_H
diff --git a/drivers/net/ethernet/aurora/Kconfig b/drivers/net/ethernet/aurora/Kconfig
index 392f564d8fd4..9ee30ea90bfa 100644
--- a/drivers/net/ethernet/aurora/Kconfig
+++ b/drivers/net/ethernet/aurora/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config NET_VENDOR_AURORA
 	bool "Aurora VLSI devices"
 	default y
diff --git a/drivers/net/ethernet/aurora/Makefile b/drivers/net/ethernet/aurora/Makefile
index 6cb528a2fc26..f3d599867619 100644
--- a/drivers/net/ethernet/aurora/Makefile
+++ b/drivers/net/ethernet/aurora/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_AURORA_NB8800) += nb8800.o
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 6f56276015a4..3b3370a94a9c 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -1,23 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2015 Mans Rullgard <mans@mansr.com>
  *
  * Mostly rewritten, based on driver from Sigma Designs.  Original
  * copyright notice below.
  *
- *
  * Driver for tangox SMP864x/SMP865x/SMP867x/SMP868x builtin Ethernet Mac.
  *
  * Copyright (C) 2005 Maxime Bizon <mbizon@freebox.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/module.h>
@@ -404,6 +394,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int dma_len;
 	unsigned int align;
 	unsigned int next;
+	bool xmit_more;
 
 	if (atomic_read(&priv->tx_free) <= NB8800_DESC_LOW) {
 		netif_stop_queue(dev);
@@ -423,9 +414,10 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	xmit_more = netdev_xmit_more();
 	if (atomic_dec_return(&priv->tx_free) <= NB8800_DESC_LOW) {
 		netif_stop_queue(dev);
-		skb->xmit_more = 0;
+		xmit_more = false;
 	}
 
 	next = priv->tx_next;
@@ -450,7 +442,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 	desc->n_addr = priv->tx_bufs[next].dma_desc;
 	desc->config = DESC_BTS(2) | DESC_DS | DESC_EOF | dma_len;
 
-	if (!skb->xmit_more)
+	if (!xmit_more)
 		desc->config |= DESC_EOC;
 
 	txb->skb = skb;
@@ -468,7 +460,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	priv->tx_next = next;
 
-	if (!skb->xmit_more) {
+	if (!xmit_more) {
 		smp_wmb();
 		priv->tx_chain->ready = true;
 		priv->tx_chain = NULL;
@@ -1461,7 +1453,7 @@ static int nb8800_probe(struct platform_device *pdev)
 	dev->irq = irq;
 
 	mac = of_get_mac_address(pdev->dev.of_node);
-	if (mac)
+	if (!IS_ERR(mac))
 		ether_addr_copy(dev->dev_addr, mac);
 
 	if (!is_valid_ether_addr(dev->dev_addr))
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index c1d3ee9baf7e..e9017caf024d 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Broadcom device configuration
 #
@@ -7,6 +8,7 @@ config NET_VENDOR_BROADCOM
 	default y
 	depends on (SSB_POSSIBLE && HAS_DMA) || PCI || BCM63XX || \
 		   SIBYTE_SB1xxx_SOC
+	select DIMLIB
 	---help---
 	  If you have a network (Ethernet) chipset belonging to this class,
 	  say Y.
@@ -194,9 +196,10 @@ config SYSTEMPORT
 config BNXT
 	tristate "Broadcom NetXtreme-C/E support"
 	depends on PCI
-	depends on MAY_USE_DEVLINK
 	select FW_LOADER
 	select LIBCRC32C
+	select NET_DEVLINK
+	select PAGE_POOL
 	---help---
 	  This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit
 	  Ethernet cards.  To compile this driver as a module, choose M here:
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 09cd188826b1..291e4afd4a1a 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Driver for BCM963xx builtin Ethernet mac
  *
  * Copyright (C) 2008 Maxime Bizon <mbizon@freebox.fr>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -2672,7 +2659,6 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	if (!dev)
 		return -ENOMEM;
 	priv = netdev_priv(dev);
-	memset(priv, 0, sizeof(*priv));
 
 	/* initialize default and fetch platform data */
 	priv->enet_is_sw = true;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 28c9b0bdf2f6..b9c5cea8db16 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Broadcom BCM7xxx System Port Ethernet MAC driver
  *
  * Copyright (C) 2014 Broadcom Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
@@ -116,15 +113,6 @@ static inline void dma_desc_set_addr(struct bcm_sysport_priv *priv,
 	writel_relaxed(lower_32_bits(addr), d + DESC_ADDR_LO);
 }
 
-static inline void tdma_port_write_desc_addr(struct bcm_sysport_priv *priv,
-					     struct dma_desc *desc,
-					     unsigned int port)
-{
-	/* Ports are latched, so write upper address first */
-	tdma_writel(priv, desc->addr_status_len, TDMA_WRITE_PORT_HI(port));
-	tdma_writel(priv, desc->addr_lo, TDMA_WRITE_PORT_LO(port));
-}
-
 /* Ethtool operations */
 static void bcm_sysport_set_rx_csum(struct net_device *dev,
 				    netdev_features_t wanted)
@@ -134,6 +122,10 @@ static void bcm_sysport_set_rx_csum(struct net_device *dev,
 
 	priv->rx_chk_en = !!(wanted & NETIF_F_RXCSUM);
 	reg = rxchk_readl(priv, RXCHK_CONTROL);
+	/* Clear L2 header checks, which would prevent BPDUs
+	 * from being received.
+	 */
+	reg &= ~RXCHK_L2_HDR_DIS;
 	if (priv->rx_chk_en)
 		reg |= RXCHK_EN;
 	else
@@ -617,7 +609,7 @@ static int bcm_sysport_set_coalesce(struct net_device *dev,
 				    struct ethtool_coalesce *ec)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 	u32 usecs, pkts;
 	unsigned int i;
 
@@ -1000,7 +992,7 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget)
 {
 	struct bcm_sysport_priv *priv =
 		container_of(napi, struct bcm_sysport_priv, napi);
-	struct net_dim_sample dim_sample;
+	struct dim_sample dim_sample;
 	unsigned int work_done = 0;
 
 	work_done = bcm_sysport_desc_rx(priv, budget);
@@ -1024,8 +1016,8 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget)
 	}
 
 	if (priv->dim.use_dim) {
-		net_dim_sample(priv->dim.event_ctr, priv->dim.packets,
-			       priv->dim.bytes, &dim_sample);
+		dim_update_sample(priv->dim.event_ctr, priv->dim.packets,
+				  priv->dim.bytes, &dim_sample);
 		net_dim(&priv->dim.dim, dim_sample);
 	}
 
@@ -1095,16 +1087,16 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 
 static void bcm_sysport_dim_work(struct work_struct *work)
 {
-	struct net_dim *dim = container_of(work, struct net_dim, work);
+	struct dim *dim = container_of(work, struct dim, work);
 	struct bcm_sysport_net_dim *ndim =
 			container_of(dim, struct bcm_sysport_net_dim, dim);
 	struct bcm_sysport_priv *priv =
 			container_of(ndim, struct bcm_sysport_priv, dim);
-	struct net_dim_cq_moder cur_profile =
-			net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+	struct dim_cq_moder cur_profile = net_dim_get_rx_moderation(dim->mode,
+								    dim->profile_ix);
 
 	bcm_sysport_set_rx_coalesce(priv, cur_profile.usec, cur_profile.pkts);
-	dim->state = NET_DIM_START_MEASURE;
+	dim->state = DIM_START_MEASURE;
 }
 
 /* RX and misc interrupt routine */
@@ -1287,11 +1279,10 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
 	struct bcm_sysport_tx_ring *ring;
 	struct bcm_sysport_cb *cb;
 	struct netdev_queue *txq;
-	struct dma_desc *desc;
+	u32 len_status, addr_lo;
 	unsigned int skb_len;
 	unsigned long flags;
 	dma_addr_t mapping;
-	u32 len_status;
 	u16 queue;
 	int ret;
 
@@ -1334,10 +1325,7 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
 	dma_unmap_addr_set(cb, dma_addr, mapping);
 	dma_unmap_len_set(cb, dma_len, skb_len);
 
-	/* Fetch a descriptor entry from our pool */
-	desc = ring->desc_cpu;
-
-	desc->addr_lo = lower_32_bits(mapping);
+	addr_lo = lower_32_bits(mapping);
 	len_status = upper_32_bits(mapping) & DESC_ADDR_HI_MASK;
 	len_status |= (skb_len << DESC_LEN_SHIFT);
 	len_status |= (DESC_SOP | DESC_EOP | TX_STATUS_APP_CRC) <<
@@ -1350,16 +1338,9 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
 		ring->curr_desc = 0;
 	ring->desc_count--;
 
-	/* Ensure write completion of the descriptor status/length
-	 * in DRAM before the System Port WRITE_PORT register latches
-	 * the value
-	 */
-	wmb();
-	desc->addr_status_len = len_status;
-	wmb();
-
-	/* Write this descriptor address to the RING write port */
-	tdma_port_write_desc_addr(priv, desc, ring->index);
+	/* Ports are latched, so write upper address first */
+	tdma_writel(priv, len_status, TDMA_WRITE_PORT_HI(ring->index));
+	tdma_writel(priv, addr_lo, TDMA_WRITE_PORT_LO(ring->index));
 
 	/* Check ring space and update SW control flow */
 	if (ring->desc_count == 0)
@@ -1456,7 +1437,7 @@ static void bcm_sysport_init_dim(struct bcm_sysport_priv *priv,
 	struct bcm_sysport_net_dim *dim = &priv->dim;
 
 	INIT_WORK(&dim->dim.work, cb);
-	dim->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	dim->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	dim->event_ctr = 0;
 	dim->packets = 0;
 	dim->bytes = 0;
@@ -1465,7 +1446,7 @@ static void bcm_sysport_init_dim(struct bcm_sysport_priv *priv,
 static void bcm_sysport_init_rx_coalesce(struct bcm_sysport_priv *priv)
 {
 	struct bcm_sysport_net_dim *dim = &priv->dim;
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 	u32 usecs, pkts;
 
 	usecs = priv->rx_coalesce_usecs;
@@ -1485,28 +1466,14 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 				    unsigned int index)
 {
 	struct bcm_sysport_tx_ring *ring = &priv->tx_rings[index];
-	struct device *kdev = &priv->pdev->dev;
 	size_t size;
-	void *p;
 	u32 reg;
 
 	/* Simple descriptors partitioning for now */
 	size = 256;
 
-	/* We just need one DMA descriptor which is DMA-able, since writing to
-	 * the port will allocate a new descriptor in its internal linked-list
-	 */
-	p = dma_alloc_coherent(kdev, sizeof(struct dma_desc), &ring->desc_dma,
-			       GFP_KERNEL);
-	if (!p) {
-		netif_err(priv, hw, priv->netdev, "DMA alloc failed\n");
-		return -ENOMEM;
-	}
-
 	ring->cbs = kcalloc(size, sizeof(struct bcm_sysport_cb), GFP_KERNEL);
 	if (!ring->cbs) {
-		dma_free_coherent(kdev, sizeof(struct dma_desc),
-				  ring->desc_cpu, ring->desc_dma);
 		netif_err(priv, hw, priv->netdev, "CB allocation failed\n");
 		return -ENOMEM;
 	}
@@ -1519,7 +1486,6 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	ring->size = size;
 	ring->clean_index = 0;
 	ring->alloc_size = ring->size;
-	ring->desc_cpu = p;
 	ring->desc_count = ring->size;
 	ring->curr_desc = 0;
 
@@ -1574,8 +1540,8 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	napi_enable(&ring->napi);
 
 	netif_dbg(priv, hw, priv->netdev,
-		  "TDMA cfg, size=%d, desc_cpu=%p switch q=%d,port=%d\n",
-		  ring->size, ring->desc_cpu, ring->switch_queue,
+		  "TDMA cfg, size=%d, switch q=%d,port=%d\n",
+		  ring->size, ring->switch_queue,
 		  ring->switch_port);
 
 	return 0;
@@ -1585,7 +1551,6 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv,
 				     unsigned int index)
 {
 	struct bcm_sysport_tx_ring *ring = &priv->tx_rings[index];
-	struct device *kdev = &priv->pdev->dev;
 	u32 reg;
 
 	/* Caller should stop the TDMA engine */
@@ -1607,12 +1572,6 @@ static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv,
 
 	kfree(ring->cbs);
 	ring->cbs = NULL;
-
-	if (ring->desc_dma) {
-		dma_free_coherent(kdev, sizeof(struct dma_desc),
-				  ring->desc_cpu, ring->desc_dma);
-		ring->desc_dma = 0;
-	}
 	ring->size = 0;
 	ring->alloc_size = 0;
 
@@ -2270,8 +2229,7 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 };
 
 static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
-				    struct net_device *sb_dev,
-				    select_queue_fallback_t fallback)
+				    struct net_device *sb_dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	u16 queue = skb_get_queue_mapping(skb);
@@ -2279,7 +2237,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	unsigned int q, port;
 
 	if (!netdev_uses_dsa(dev))
-		return fallback(dev, skb, NULL);
+		return netdev_pick_tx(dev, skb, NULL);
 
 	/* DSA tagging layer will have configured the correct queue */
 	q = BRCM_TAG_GET_QUEUE(queue);
@@ -2287,7 +2245,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
 
 	if (unlikely(!tx_ring))
-		return fallback(dev, skb, NULL);
+		return netdev_pick_tx(dev, skb, NULL);
 
 	return tx_ring->index;
 }
@@ -2544,7 +2502,7 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	/* Initialize netdevice members */
 	macaddr = of_get_mac_address(dn);
-	if (!macaddr || !is_valid_ether_addr(macaddr)) {
+	if (IS_ERR(macaddr)) {
 		dev_warn(&pdev->dev, "using random Ethernet MAC\n");
 		eth_hw_addr_random(dev);
 	} else {
@@ -2595,11 +2553,11 @@ static int bcm_sysport_probe(struct platform_device *pdev)
 
 	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
 	dev_info(&pdev->dev,
-		 "Broadcom SYSTEMPORT%s" REV_FMT
-		 " at 0x%p (irqs: %d, %d, TXQs: %d, RXQs: %d)\n",
+		 "Broadcom SYSTEMPORT%s " REV_FMT
+		 " (irqs: %d, %d, TXQs: %d, RXQs: %d)\n",
 		 priv->is_lite ? " Lite" : "",
 		 (priv->rev >> 8) & 0xff, priv->rev & 0xff,
-		 priv->base, priv->irq0, priv->irq1, txq, rxq);
+		 priv->irq0, priv->irq1, txq, rxq);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 0b192fea9c5d..6d80735fbc7f 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Broadcom BCM7xxx System Port Ethernet MAC driver
  *
  * Copyright (C) 2014 Broadcom Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __BCM_SYSPORT_H
@@ -14,7 +11,7 @@
 #include <linux/bitmap.h>
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 
 /* Receive/transmit descriptor format */
 #define DESC_ADDR_HI_STATUS_LEN	0x00
@@ -516,12 +513,6 @@ struct bcm_rsb {
 
 #define TDMA_DEBUG			0x64c
 
-/* Transmit/Receive descriptor */
-struct dma_desc {
-	u32	addr_status_len;
-	u32	addr_lo;
-};
-
 /* Number of Receive hardware descriptor words */
 #define SP_NUM_HW_RX_DESC_WORDS		1024
 #define SP_LT_NUM_HW_RX_DESC_WORDS	256
@@ -530,7 +521,7 @@ struct dma_desc {
 #define SP_NUM_TX_DESC			1536
 #define SP_LT_NUM_TX_DESC		256
 
-#define WORDS_PER_DESC			(sizeof(struct dma_desc) / sizeof(u32))
+#define WORDS_PER_DESC			2
 
 /* Rx/Tx common counter group.*/
 struct bcm_sysport_pkt_counters {
@@ -711,14 +702,13 @@ struct bcm_sysport_net_dim {
 	u16			event_ctr;
 	unsigned long		packets;
 	unsigned long		bytes;
-	struct net_dim		dim;
+	struct dim		dim;
 };
 
 /* Software view of the TX ring */
 struct bcm_sysport_tx_ring {
 	spinlock_t	lock;		/* Ring lock for tx reclaim/xmit */
 	struct napi_struct napi;	/* NAPI per tx queue */
-	dma_addr_t	desc_dma;	/* DMA cookie */
 	unsigned int	index;		/* Ring index */
 	unsigned int	size;		/* Ring current size */
 	unsigned int	alloc_size;	/* Ring one-time allocated size */
@@ -727,7 +717,6 @@ struct bcm_sysport_tx_ring {
 	unsigned int	c_index;	/* Last consumer index */
 	unsigned int	clean_index;	/* Current clean index */
 	struct bcm_sysport_cb *cbs;	/* Transmit control blocks */
-	struct dma_desc	*desc_cpu;	/* CPU view of the descriptor */
 	struct bcm_sysport_priv *priv;	/* private context backpointer */
 	unsigned long	packets;	/* packets statistics */
 	unsigned long	bytes;		/* bytes statistics */
diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c
index 6fe074c1588b..34d18302b1a3 100644
--- a/drivers/net/ethernet/broadcom/bgmac-bcma.c
+++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c
@@ -132,7 +132,7 @@ static int bgmac_probe(struct bcma_device *core)
 		mac = of_get_mac_address(bgmac->dev->of_node);
 
 	/* If no MAC address assigned via device tree, check SPROM */
-	if (!mac) {
+	if (IS_ERR_OR_NULL(mac)) {
 		switch (core->core_unit) {
 		case 0:
 			mac = sprom->et0mac;
diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c
index 894eda5b13cf..6dc0dd91ad11 100644
--- a/drivers/net/ethernet/broadcom/bgmac-platform.c
+++ b/drivers/net/ethernet/broadcom/bgmac-platform.c
@@ -193,7 +193,7 @@ static int bgmac_probe(struct platform_device *pdev)
 	bgmac->dma_dev = &pdev->dev;
 
 	mac_addr = of_get_mac_address(np);
-	if (mac_addr)
+	if (!IS_ERR(mac_addr))
 		ether_addr_copy(bgmac->net_dev->dev_addr, mac_addr);
 	else
 		dev_warn(&pdev->dev, "MAC address not present in device tree\n");
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 2d3a44c40221..4632dd5dbad1 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1446,7 +1446,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac)
 	struct phy_device *phy_dev;
 	int err;
 
-	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL);
+	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
 	if (!phy_dev || IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
 		return -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index d63371d70bce..dfdd14eadd57 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -3305,8 +3305,6 @@ next_rx:
 
 	BNX2_WR(bp, rxr->rx_bseq_addr, rxr->rx_prod_bseq);
 
-	mmiowb();
-
 	return rx_pkt;
 
 }
@@ -6723,8 +6721,6 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	BNX2_WR16(bp, txr->tx_bidx_addr, prod);
 	BNX2_WR(bp, txr->tx_bseq_addr, txr->tx_prod_bseq);
 
-	mmiowb();
-
 	txr->tx_prod = prod;
 
 	if (unlikely(bnx2_tx_avail(bp, txr) <= MAX_SKB_FRAGS)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/Makefile b/drivers/net/ethernet/broadcom/bnx2x/Makefile
index 116762daae09..9fdfaa269af9 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/Makefile
+++ b/drivers/net/ethernet/broadcom/bnx2x/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for Broadcom 10-Gigabit ethernet driver
 #
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 03d131f777bc..6026b53137aa 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -32,7 +32,7 @@
  * (you will need to reboot afterwards) */
 /* #define BNX2X_STOP_ON_ERROR */
 
-#define DRV_MODULE_VERSION      "1.712.30-0"
+#define DRV_MODULE_VERSION      "1.713.36-0"
 #define DRV_MODULE_RELDATE      "2014/02/10"
 #define BNX2X_BC_VER            0x040200
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ecb1bd7eb508..656ed80647f0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -684,7 +684,7 @@ static void *bnx2x_frag_alloc(const struct bnx2x_fastpath *fp, gfp_t gfp_mask)
 		if (unlikely(gfpflags_allow_blocking(gfp_mask)))
 			return (void *)__get_free_page(gfp_mask);
 
-		return netdev_alloc_frag(fp->rx_frag_size);
+		return napi_alloc_frag(fp->rx_frag_size);
 	}
 
 	return kmalloc(fp->rx_buf_size + NET_SKB_PAD, gfp_mask);
@@ -1909,8 +1909,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback)
+		       struct net_device *sb_dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -1932,7 +1931,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb, NULL) %
+	return netdev_pick_tx(dev, skb, NULL) %
 	       (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
@@ -3858,9 +3857,12 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		if (!(bp->flags & TX_TIMESTAMPING_EN)) {
+			bp->eth_stats.ptp_skip_tx_ts++;
 			BNX2X_ERR("Tx timestamping was not enabled, this packet will not be timestamped\n");
 		} else if (bp->ptp_tx_skb) {
-			BNX2X_ERR("The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n");
+			bp->eth_stats.ptp_skip_tx_ts++;
+			netdev_err_once(bp->dev,
+					"Device supports only a single outstanding packet to timestamp, this packet won't be timestamped\n");
 		} else {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			/* schedule check for Tx timestamp */
@@ -4166,8 +4168,6 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
-	mmiowb();
-
 	txdata->tx_bd_prod += nbd;
 
 	if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_DESC_PER_TX_PKT)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 2462e7aa0c5d..c2f6e44e9a3f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -498,8 +498,7 @@ int bnx2x_set_vf_spoofchk(struct net_device *dev, int idx, bool val);
 
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback);
+		       struct net_device *sb_dev);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
@@ -527,8 +526,6 @@ static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 		REG_WR_RELAXED(bp, fp->ustorm_rx_prods_offset + i * 4,
 			       ((u32 *)&rx_prods)[i]);
 
-	mmiowb(); /* keep prod updates ordered */
-
 	DP(NETIF_MSG_RX_STATUS,
 	   "queue[%d]:  wrote  bd_prod %u  cqe_prod %u  sge_prod %u\n",
 	   fp->index, bd_prod, rx_comp_prod, rx_sge_prod);
@@ -653,7 +650,6 @@ static inline void bnx2x_igu_ack_sb_gen(struct bnx2x *bp, u8 igu_sb_id,
 	REG_WR(bp, igu_addr, cmd_data.sb_id_and_flags);
 
 	/* Make sure that ACK is written */
-	mmiowb();
 	barrier();
 }
 
@@ -674,7 +670,6 @@ static inline void bnx2x_hc_ack_sb(struct bnx2x *bp, u8 sb_id,
 	REG_WR(bp, hc_addr, (*(u32 *)&igu_ack));
 
 	/* Make sure that ACK is written */
-	mmiowb();
 	barrier();
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 749d0ef44371..4a0ba6801c9e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -182,7 +182,9 @@ static const struct {
 	{ STATS_OFFSET32(driver_filtered_tx_pkt),
 				4, false, "driver_filtered_tx_pkt" },
 	{ STATS_OFFSET32(eee_tx_lpi),
-				4, true, "Tx LPI entry count"}
+				4, true, "Tx LPI entry count"},
+	{ STATS_OFFSET32(ptp_skip_tx_ts),
+				4, false, "ptp_skipped_tx_tstamp" },
 };
 
 #define BNX2X_NUM_STATS		ARRAY_SIZE(bnx2x_stats_arr)
@@ -1609,7 +1611,8 @@ static int bnx2x_get_module_info(struct net_device *dev,
 	}
 
 	if (!sff8472_comp ||
-	    (diag_type & SFP_EEPROM_DIAG_ADDR_CHANGE_REQ)) {
+	    (diag_type & SFP_EEPROM_DIAG_ADDR_CHANGE_REQ) ||
+	    !(diag_type & SFP_EEPROM_DDM_IMPLEMENTED)) {
 		modinfo->type = ETH_MODULE_SFF_8079;
 		modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
 	} else {
@@ -2623,7 +2626,6 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	wmb();
 	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
-	mmiowb();
 	barrier();
 
 	num_pkts++;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index d9057c8bbeef..78326a6c0aba 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -3024,7 +3024,7 @@ struct afex_stats {
 
 #define BCM_5710_FW_MAJOR_VERSION			7
 #define BCM_5710_FW_MINOR_VERSION			13
-#define BCM_5710_FW_REVISION_VERSION		1
+#define BCM_5710_FW_REVISION_VERSION		11
 #define BCM_5710_FW_ENGINEERING_VERSION		0
 #define BCM_5710_FW_COMPILE_FLAGS			1
 
@@ -3639,8 +3639,10 @@ struct client_init_rx_data {
 #define CLIENT_INIT_RX_DATA_TPA_EN_IPV6_SHIFT 1
 #define CLIENT_INIT_RX_DATA_TPA_MODE (0x1<<2)
 #define CLIENT_INIT_RX_DATA_TPA_MODE_SHIFT 2
-#define CLIENT_INIT_RX_DATA_RESERVED5 (0x1F<<3)
-#define CLIENT_INIT_RX_DATA_RESERVED5_SHIFT 3
+#define CLIENT_INIT_RX_DATA_TPA_OVER_VLAN_DISABLE (0x1<<3)
+#define CLIENT_INIT_RX_DATA_TPA_OVER_VLAN_DISABLE_SHIFT 3
+#define CLIENT_INIT_RX_DATA_RESERVED5 (0xF<<4)
+#define CLIENT_INIT_RX_DATA_RESERVED5_SHIFT 4
 	u8 vmqueue_mode_en_flg;
 	u8 extra_data_over_sgl_en_flg;
 	u8 cache_line_alignment_log_size;
@@ -3831,7 +3833,7 @@ struct eth_classify_cmd_header {
  */
 struct eth_classify_header {
 	u8 rule_cnt;
-	u8 reserved0;
+	u8 warning_on_error;
 	__le16 reserved1;
 	__le32 echo;
 };
@@ -4752,6 +4754,8 @@ struct tpa_update_ramrod_data {
 	__le32 sge_page_base_hi;
 	__le16 sge_pause_thr_low;
 	__le16 sge_pause_thr_high;
+	u8 tpa_over_vlan_disable;
+	u8 reserved[7];
 };
 
 
@@ -4946,7 +4950,7 @@ struct fairness_vars_per_port {
 	u32 upper_bound;
 	u32 fair_threshold;
 	u32 fairness_timeout;
-	u32 reserved0;
+	u32 size_thr;
 };
 
 /*
@@ -5415,7 +5419,9 @@ struct function_start_data {
 	u8 sd_vlan_force_pri_val;
 	u8 c2s_pri_tt_valid;
 	u8 c2s_pri_default;
-	u8 reserved2[6];
+	u8 tx_vlan_filtering_enable;
+	u8 tx_vlan_filtering_use_pvid;
+	u8 reserved2[4];
 	struct c2s_pri_trans_table_entry c2s_pri_trans_table;
 };
 
@@ -5448,7 +5454,8 @@ struct function_update_data {
 	u8 reserved1;
 	__le16 sd_vlan_tag;
 	__le16 sd_vlan_eth_type;
-	__le16 reserved0;
+	u8 tx_vlan_filtering_pvid_change_flg;
+	u8 reserved0;
 	__le32 reserved2;
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
index 46ee2c01f4c5..066765fbef06 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
@@ -449,7 +449,7 @@ static inline void bnx2x_init_fw_wrr(const struct cmng_init_input *input_data,
 				ccd[cos] =
 				    (u32)input_data->cos_min_rate[cos] * 100 *
 				    (T_FAIR_COEF / (8 * 100 * cosWeightSum));
-				 if (ccd[cos] < pdata->fair_vars.fair_threshold
+				if (ccd[cos] < pdata->fair_vars.fair_threshold
 						+ MIN_ABOVE_THRESH) {
 					ccd[cos] =
 					    pdata->fair_vars.fair_threshold +
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 98d4c5a3ff21..d581d0ae6584 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -837,49 +837,45 @@ static int bnx2x_ets_e3b0_set_cos_bw(struct bnx2x *bp,
 
 	switch (cos_entry) {
 	case 0:
-	    nig_reg_adress_crd_weight =
-		 (port) ? NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_0 :
-		     NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_0;
-	     pbf_reg_adress_crd_weight = (port) ?
-		 PBF_REG_COS0_WEIGHT_P1 : PBF_REG_COS0_WEIGHT_P0;
-	     break;
+		nig_reg_adress_crd_weight =
+			(port) ? NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_0 :
+			NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_0;
+		pbf_reg_adress_crd_weight = (port) ?
+		    PBF_REG_COS0_WEIGHT_P1 : PBF_REG_COS0_WEIGHT_P0;
+		break;
 	case 1:
-	     nig_reg_adress_crd_weight = (port) ?
-		 NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_1 :
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_1;
-	     pbf_reg_adress_crd_weight = (port) ?
-		 PBF_REG_COS1_WEIGHT_P1 : PBF_REG_COS1_WEIGHT_P0;
-	     break;
+		nig_reg_adress_crd_weight = (port) ?
+			NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_1 :
+			NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_1;
+		pbf_reg_adress_crd_weight = (port) ?
+			PBF_REG_COS1_WEIGHT_P1 : PBF_REG_COS1_WEIGHT_P0;
+		break;
 	case 2:
-	     nig_reg_adress_crd_weight = (port) ?
-		 NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_2 :
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_2;
+		nig_reg_adress_crd_weight = (port) ?
+			NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_2 :
+			NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_2;
 
-		 pbf_reg_adress_crd_weight = (port) ?
-		     PBF_REG_COS2_WEIGHT_P1 : PBF_REG_COS2_WEIGHT_P0;
-	     break;
+		pbf_reg_adress_crd_weight = (port) ?
+			PBF_REG_COS2_WEIGHT_P1 : PBF_REG_COS2_WEIGHT_P0;
+		break;
 	case 3:
-	    if (port)
+		if (port)
 			return -EINVAL;
-	     nig_reg_adress_crd_weight =
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_3;
-	     pbf_reg_adress_crd_weight =
-		 PBF_REG_COS3_WEIGHT_P0;
-	     break;
+		nig_reg_adress_crd_weight = NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_3;
+		pbf_reg_adress_crd_weight = PBF_REG_COS3_WEIGHT_P0;
+		break;
 	case 4:
-	    if (port)
-		return -EINVAL;
-	     nig_reg_adress_crd_weight =
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_4;
-	     pbf_reg_adress_crd_weight = PBF_REG_COS4_WEIGHT_P0;
-	     break;
+		if (port)
+			return -EINVAL;
+		nig_reg_adress_crd_weight = NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_4;
+		pbf_reg_adress_crd_weight = PBF_REG_COS4_WEIGHT_P0;
+		break;
 	case 5:
-	    if (port)
-		return -EINVAL;
-	     nig_reg_adress_crd_weight =
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_5;
-	     pbf_reg_adress_crd_weight = PBF_REG_COS5_WEIGHT_P0;
-	     break;
+		if (port)
+			return -EINVAL;
+		nig_reg_adress_crd_weight = NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_5;
+		pbf_reg_adress_crd_weight = PBF_REG_COS5_WEIGHT_P0;
+		break;
 	}
 
 	REG_WR(bp, nig_reg_adress_crd_weight, cos_bw_nig);
@@ -966,7 +962,7 @@ static int bnx2x_ets_e3b0_sp_pri_to_cos_set(const struct link_params *params,
 	if (pri >= max_num_of_cos) {
 		DP(NETIF_MSG_LINK, "bnx2x_ets_e3b0_sp_pri_to_cos_set invalid "
 		   "parameter Illegal strict priority\n");
-	    return -EINVAL;
+		return -EINVAL;
 	}
 
 	if (sp_pri_to_cos[pri] != DCBX_INVALID_COS) {
@@ -1845,28 +1841,28 @@ static int bnx2x_emac_enable(struct link_params *params,
 	bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_TX_MODE,
 		      EMAC_TX_MODE_RESET);
 
-		/* pause enable/disable */
-		bnx2x_bits_dis(bp, emac_base + EMAC_REG_EMAC_RX_MODE,
-			       EMAC_RX_MODE_FLOW_EN);
+	/* pause enable/disable */
+	bnx2x_bits_dis(bp, emac_base + EMAC_REG_EMAC_RX_MODE,
+		       EMAC_RX_MODE_FLOW_EN);
 
-		bnx2x_bits_dis(bp,  emac_base + EMAC_REG_EMAC_TX_MODE,
-			       (EMAC_TX_MODE_EXT_PAUSE_EN |
-				EMAC_TX_MODE_FLOW_EN));
-		if (!(params->feature_config_flags &
-		      FEATURE_CONFIG_PFC_ENABLED)) {
-			if (vars->flow_ctrl & BNX2X_FLOW_CTRL_RX)
-				bnx2x_bits_en(bp, emac_base +
-					      EMAC_REG_EMAC_RX_MODE,
-					      EMAC_RX_MODE_FLOW_EN);
-
-			if (vars->flow_ctrl & BNX2X_FLOW_CTRL_TX)
-				bnx2x_bits_en(bp, emac_base +
-					      EMAC_REG_EMAC_TX_MODE,
-					      (EMAC_TX_MODE_EXT_PAUSE_EN |
-					       EMAC_TX_MODE_FLOW_EN));
-		} else
-			bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_TX_MODE,
-				      EMAC_TX_MODE_FLOW_EN);
+	bnx2x_bits_dis(bp,  emac_base + EMAC_REG_EMAC_TX_MODE,
+		       (EMAC_TX_MODE_EXT_PAUSE_EN |
+			EMAC_TX_MODE_FLOW_EN));
+	if (!(params->feature_config_flags &
+	      FEATURE_CONFIG_PFC_ENABLED)) {
+		if (vars->flow_ctrl & BNX2X_FLOW_CTRL_RX)
+			bnx2x_bits_en(bp, emac_base +
+				      EMAC_REG_EMAC_RX_MODE,
+				      EMAC_RX_MODE_FLOW_EN);
+
+		if (vars->flow_ctrl & BNX2X_FLOW_CTRL_TX)
+			bnx2x_bits_en(bp, emac_base +
+				      EMAC_REG_EMAC_TX_MODE,
+				      (EMAC_TX_MODE_EXT_PAUSE_EN |
+				       EMAC_TX_MODE_FLOW_EN));
+	} else
+		bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_TX_MODE,
+			      EMAC_TX_MODE_FLOW_EN);
 
 	/* KEEP_VLAN_TAG, promiscuous */
 	val = REG_RD(bp, emac_base + EMAC_REG_EMAC_RX_MODE);
@@ -6339,7 +6335,7 @@ int bnx2x_set_led(struct link_params *params,
 		 */
 		if (!vars->link_up)
 			break;
-		/* else: fall through */
+		/* fall through */
 	case LED_MODE_ON:
 		if (((params->phy[EXT_PHY1].type ==
 			  PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) ||
@@ -6478,9 +6474,9 @@ int bnx2x_test_link(struct link_params *params, struct link_vars *vars,
 			  MDIO_REG_BANK_GP_STATUS,
 			  MDIO_GP_STATUS_TOP_AN_STATUS1,
 			  &gp_status);
-	/* Link is up only if both local phy and external phy are up */
-	if (!(gp_status & MDIO_GP_STATUS_TOP_AN_STATUS1_LINK_STATUS))
-		return -ESRCH;
+		/* Link is up only if both local phy and external phy are up */
+		if (!(gp_status & MDIO_GP_STATUS_TOP_AN_STATUS1_LINK_STATUS))
+			return -ESRCH;
 	}
 	/* In XGXS loopback mode, do not check external PHY */
 	if (params->loopback_mode == LOOPBACK_XGXS)
@@ -7293,8 +7289,8 @@ static int bnx2x_8073_xaui_wa(struct bnx2x *bp, struct bnx2x_phy *phy)
 					DP(NETIF_MSG_LINK,
 					  "XAUI workaround has completed\n");
 					return 0;
-				 }
-				 usleep_range(3000, 6000);
+				}
+				usleep_range(3000, 6000);
 			}
 			break;
 		}
@@ -12675,39 +12671,39 @@ static void bnx2x_init_bmac_loopback(struct link_params *params,
 				     struct link_vars *vars)
 {
 	struct bnx2x *bp = params->bp;
-		vars->link_up = 1;
-		vars->line_speed = SPEED_10000;
-		vars->duplex = DUPLEX_FULL;
-		vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
-		vars->mac_type = MAC_TYPE_BMAC;
+	vars->link_up = 1;
+	vars->line_speed = SPEED_10000;
+	vars->duplex = DUPLEX_FULL;
+	vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
+	vars->mac_type = MAC_TYPE_BMAC;
 
-		vars->phy_flags = PHY_XGXS_FLAG;
+	vars->phy_flags = PHY_XGXS_FLAG;
 
-		bnx2x_xgxs_deassert(params);
+	bnx2x_xgxs_deassert(params);
 
-		/* Set bmac loopback */
-		bnx2x_bmac_enable(params, vars, 1, 1);
+	/* Set bmac loopback */
+	bnx2x_bmac_enable(params, vars, 1, 1);
 
-		REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0);
+	REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port * 4, 0);
 }
 
 static void bnx2x_init_emac_loopback(struct link_params *params,
 				     struct link_vars *vars)
 {
 	struct bnx2x *bp = params->bp;
-		vars->link_up = 1;
-		vars->line_speed = SPEED_1000;
-		vars->duplex = DUPLEX_FULL;
-		vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
-		vars->mac_type = MAC_TYPE_EMAC;
+	vars->link_up = 1;
+	vars->line_speed = SPEED_1000;
+	vars->duplex = DUPLEX_FULL;
+	vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
+	vars->mac_type = MAC_TYPE_EMAC;
 
-		vars->phy_flags = PHY_XGXS_FLAG;
+	vars->phy_flags = PHY_XGXS_FLAG;
 
-		bnx2x_xgxs_deassert(params);
-		/* Set bmac loopback */
-		bnx2x_emac_enable(params, vars, 1);
-		bnx2x_emac_program(params, vars);
-		REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0);
+	bnx2x_xgxs_deassert(params);
+	/* Set bmac loopback */
+	bnx2x_emac_enable(params, vars, 1);
+	bnx2x_emac_program(params, vars);
+	REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port * 4, 0);
 }
 
 static void bnx2x_init_xmac_loopback(struct link_params *params,
@@ -13073,12 +13069,12 @@ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars,
 		REG_WR(bp, NIG_REG_EGRESS_EMAC0_OUT_EN + port*4, 0);
 	}
 
-		if (!CHIP_IS_E3(bp)) {
-			bnx2x_set_bmac_rx(bp, params->chip_id, port, 0);
-		} else {
-			bnx2x_set_xmac_rxtx(params, 0);
-			bnx2x_set_umac_rxtx(params, 0);
-		}
+	if (!CHIP_IS_E3(bp)) {
+		bnx2x_set_bmac_rx(bp, params->chip_id, port, 0);
+	} else {
+		bnx2x_set_xmac_rxtx(params, 0);
+		bnx2x_set_umac_rxtx(params, 0);
+	}
 	/* Disable emac */
 	if (!CHIP_IS_E3(bp))
 		REG_WR(bp, NIG_REG_NIG_EMAC0_EN + port*4, 0);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
index b7d251108c19..7115f5025664 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
@@ -62,6 +62,7 @@
 #define SFP_EEPROM_DIAG_TYPE_ADDR		0x5c
 #define SFP_EEPROM_DIAG_TYPE_SIZE		1
 #define SFP_EEPROM_DIAG_ADDR_CHANGE_REQ		(1<<2)
+#define SFP_EEPROM_DDM_IMPLEMENTED		(1<<6)
 #define SFP_EEPROM_SFF_8472_COMP_ADDR		0x5e
 #define SFP_EEPROM_SFF_8472_COMP_SIZE		1
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 3b5b47e98c73..2cc14db8f0ec 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -869,9 +869,6 @@ static void bnx2x_hc_int_disable(struct bnx2x *bp)
 	   "write %x to HC %d (addr 0x%x)\n",
 	   val, port, addr);
 
-	/* flush all outstanding writes */
-	mmiowb();
-
 	REG_WR(bp, addr, val);
 	if (REG_RD(bp, addr) != val)
 		BNX2X_ERR("BUG! Proper val not read from IGU!\n");
@@ -887,9 +884,6 @@ static void bnx2x_igu_int_disable(struct bnx2x *bp)
 
 	DP(NETIF_MSG_IFDOWN, "write %x to IGU\n", val);
 
-	/* flush all outstanding writes */
-	mmiowb();
-
 	REG_WR(bp, IGU_REG_PF_CONFIGURATION, val);
 	if (REG_RD(bp, IGU_REG_PF_CONFIGURATION) != val)
 		BNX2X_ERR("BUG! Proper val not read from IGU!\n");
@@ -1595,7 +1589,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp)
 	/*
 	 * Ensure that HC_CONFIG is written before leading/trailing edge config
 	 */
-	mmiowb();
 	barrier();
 
 	if (!CHIP_IS_E1(bp)) {
@@ -1611,9 +1604,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp)
 		REG_WR(bp, HC_REG_TRAILING_EDGE_0 + port*8, val);
 		REG_WR(bp, HC_REG_LEADING_EDGE_0 + port*8, val);
 	}
-
-	/* Make sure that interrupts are indeed enabled from here on */
-	mmiowb();
 }
 
 static void bnx2x_igu_int_enable(struct bnx2x *bp)
@@ -1674,9 +1664,6 @@ static void bnx2x_igu_int_enable(struct bnx2x *bp)
 
 	REG_WR(bp, IGU_REG_TRAILING_EDGE_LATCH, val);
 	REG_WR(bp, IGU_REG_LEADING_EDGE_LATCH, val);
-
-	/* Make sure that interrupts are indeed enabled from here on */
-	mmiowb();
 }
 
 void bnx2x_int_enable(struct bnx2x *bp)
@@ -3833,7 +3820,6 @@ static void bnx2x_sp_prod_update(struct bnx2x *bp)
 
 	REG_WR16_RELAXED(bp, BAR_XSTRORM_INTMEM + XSTORM_SPQ_PROD_OFFSET(func),
 			 bp->spq_prod_idx);
-	mmiowb();
 }
 
 /**
@@ -5244,7 +5230,6 @@ static void bnx2x_update_eq_prod(struct bnx2x *bp, u16 prod)
 {
 	/* No memory barriers */
 	storm_memset_eq_prod(bp, prod, BP_FUNC(bp));
-	mmiowb(); /* keep prod updates ordered */
 }
 
 static int  bnx2x_cnic_handle_cfc_del(struct bnx2x *bp, u32 cid,
@@ -6513,7 +6498,6 @@ void bnx2x_nic_init_cnic(struct bnx2x *bp)
 
 	/* flush all */
 	mb();
-	mmiowb();
 }
 
 void bnx2x_pre_irq_nic_init(struct bnx2x *bp)
@@ -6553,7 +6537,6 @@ void bnx2x_post_irq_nic_init(struct bnx2x *bp, u32 load_code)
 
 	/* flush all before enabling interrupts */
 	mb();
-	mmiowb();
 
 	bnx2x_int_enable(bp);
 
@@ -7775,12 +7758,10 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, bool is_pf)
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 			 data, igu_addr_data);
 	REG_WR(bp, igu_addr_data, data);
-	mmiowb();
 	barrier();
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 			  ctl, igu_addr_ctl);
 	REG_WR(bp, igu_addr_ctl, ctl);
-	mmiowb();
 	barrier();
 
 	/* wait for clean up to finish */
@@ -9550,7 +9531,6 @@ static void bnx2x_set_234_gates(struct bnx2x *bp, bool close)
 
 	DP(NETIF_MSG_HW | NETIF_MSG_IFUP, "%s gates #2, #3 and #4\n",
 		close ? "closing" : "opening");
-	mmiowb();
 }
 
 #define SHARED_MF_CLP_MAGIC  0x80000000 /* `magic' bit */
@@ -9674,7 +9654,6 @@ static void bnx2x_pxp_prep(struct bnx2x *bp)
 	if (!CHIP_IS_E1(bp)) {
 		REG_WR(bp, PXP2_REG_RD_START_INIT, 0);
 		REG_WR(bp, PXP2_REG_RQ_RBC_DONE, 0);
-		mmiowb();
 	}
 }
 
@@ -9774,16 +9753,13 @@ static void bnx2x_process_kill_chip_reset(struct bnx2x *bp, bool global)
 	       reset_mask1 & (~not_reset_mask1));
 
 	barrier();
-	mmiowb();
 
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET,
 	       reset_mask2 & (~stay_reset2));
 
 	barrier();
-	mmiowb();
 
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_1_SET, reset_mask1);
-	mmiowb();
 }
 
 /**
@@ -9867,9 +9843,6 @@ static int bnx2x_process_kill(struct bnx2x *bp, bool global)
 	REG_WR(bp, MISC_REG_UNPREPARED, 0);
 	barrier();
 
-	/* Make sure all is written to the chip before the reset */
-	mmiowb();
-
 	/* Wait for 1ms to empty GLUE and PCI-E core queues,
 	 * PSWHST, GRC and PSWRD Tetris buffer.
 	 */
@@ -11298,7 +11271,7 @@ static void bnx2x_link_settings_supported(struct bnx2x *bp, u32 switch_cfg)
 			   dev_info.port_hw_config[port].external_phy_config),
 			   SHMEM_RD(bp,
 			   dev_info.port_hw_config[port].external_phy_config2));
-			return;
+		return;
 	}
 
 	if (CHIP_IS_E3(bp))
@@ -11998,7 +11971,7 @@ static void validate_set_si_mode(struct bnx2x *bp)
 static int bnx2x_get_hwinfo(struct bnx2x *bp)
 {
 	int /*abs*/func = BP_ABS_FUNC(bp);
-	int vn, mfw_vn;
+	int vn;
 	u32 val = 0, val2 = 0;
 	int rc = 0;
 
@@ -12083,12 +12056,10 @@ static int bnx2x_get_hwinfo(struct bnx2x *bp)
 	/*
 	 * Initialize MF configuration
 	 */
-
 	bp->mf_ov = 0;
 	bp->mf_mode = 0;
 	bp->mf_sub_mode = 0;
 	vn = BP_VN(bp);
-	mfw_vn = BP_FW_MB_IDX(bp);
 
 	if (!CHIP_IS_E1(bp) && !BP_NOMCP(bp)) {
 		BNX2X_DEV_INFO("shmem2base 0x%x, size %d, mfcfg offset %d\n",
@@ -14830,7 +14801,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 		if (rc)
 			break;
 
-		mmiowb();
 		barrier();
 
 		/* Start accepting on iSCSI L2 ring */
@@ -14865,7 +14835,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 		if (!bnx2x_wait_sp_comp(bp, sp_bits))
 			BNX2X_ERR("rx_mode completion timed out!\n");
 
-		mmiowb();
 		barrier();
 
 		/* Unset iSCSI L2 MAC */
@@ -15245,11 +15214,24 @@ static void bnx2x_ptp_task(struct work_struct *work)
 	u32 val_seq;
 	u64 timestamp, ns;
 	struct skb_shared_hwtstamps shhwtstamps;
+	bool bail = true;
+	int i;
 
-	/* Read Tx timestamp registers */
-	val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
-			 NIG_REG_P0_TLLH_PTP_BUF_SEQID);
-	if (val_seq & 0x10000) {
+	/* FW may take a while to complete timestamping; try a bit and if it's
+	 * still not complete, may indicate an error state - bail out then.
+	 */
+	for (i = 0; i < 10; i++) {
+		/* Read Tx timestamp registers */
+		val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
+				 NIG_REG_P0_TLLH_PTP_BUF_SEQID);
+		if (val_seq & 0x10000) {
+			bail = false;
+			break;
+		}
+		msleep(1 << i);
+	}
+
+	if (!bail) {
 		/* There is a valid timestamp value */
 		timestamp = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_TS_MSB :
 				   NIG_REG_P0_TLLH_PTP_BUF_TS_MSB);
@@ -15264,16 +15246,18 @@ static void bnx2x_ptp_task(struct work_struct *work)
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 		shhwtstamps.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(bp->ptp_tx_skb, &shhwtstamps);
-		dev_kfree_skb_any(bp->ptp_tx_skb);
-		bp->ptp_tx_skb = NULL;
 
 		DP(BNX2X_MSG_PTP, "Tx timestamp, timestamp cycles = %llu, ns = %llu\n",
 		   timestamp, ns);
 	} else {
-		DP(BNX2X_MSG_PTP, "There is no valid Tx timestamp yet\n");
-		/* Reschedule to keep checking for a valid timestamp value */
-		schedule_work(&bp->ptp_task);
+		DP(BNX2X_MSG_PTP,
+		   "Tx timestamp is not recorded (register read=%u)\n",
+		   val_seq);
+		bp->eth_stats.ptp_skip_tx_ts++;
 	}
+
+	dev_kfree_skb_any(bp->ptp_tx_skb);
+	bp->ptp_tx_skb = NULL;
 }
 
 void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb)
@@ -15378,27 +15362,47 @@ static int bnx2x_enable_ptp_packets(struct bnx2x *bp)
 	return 0;
 }
 
+#define BNX2X_P2P_DETECT_PARAM_MASK 0x5F5
+#define BNX2X_P2P_DETECT_RULE_MASK 0x3DBB
+#define BNX2X_PTP_TX_ON_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x6AA)
+#define BNX2X_PTP_TX_ON_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3EEE)
+#define BNX2X_PTP_V1_L4_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x7EE)
+#define BNX2X_PTP_V1_L4_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3FFE)
+#define BNX2X_PTP_V2_L4_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x7EA)
+#define BNX2X_PTP_V2_L4_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3FEE)
+#define BNX2X_PTP_V2_L2_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x6BF)
+#define BNX2X_PTP_V2_L2_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3EFF)
+#define BNX2X_PTP_V2_PARAM_MASK (BNX2X_P2P_DETECT_PARAM_MASK & 0x6AA)
+#define BNX2X_PTP_V2_RULE_MASK (BNX2X_P2P_DETECT_RULE_MASK & 0x3EEE)
+
 int bnx2x_configure_ptp_filters(struct bnx2x *bp)
 {
 	int port = BP_PORT(bp);
+	u32 param, rule;
 	int rc;
 
 	if (!bp->hwtstamp_ioctl_called)
 		return 0;
 
+	param = port ? NIG_REG_P1_TLLH_PTP_PARAM_MASK :
+		NIG_REG_P0_TLLH_PTP_PARAM_MASK;
+	rule = port ? NIG_REG_P1_TLLH_PTP_RULE_MASK :
+		NIG_REG_P0_TLLH_PTP_RULE_MASK;
 	switch (bp->tx_type) {
 	case HWTSTAMP_TX_ON:
 		bp->flags |= TX_TIMESTAMPING_EN;
-		REG_WR(bp, port ? NIG_REG_P1_TLLH_PTP_PARAM_MASK :
-		       NIG_REG_P0_TLLH_PTP_PARAM_MASK, 0x6AA);
-		REG_WR(bp, port ? NIG_REG_P1_TLLH_PTP_RULE_MASK :
-		       NIG_REG_P0_TLLH_PTP_RULE_MASK, 0x3EEE);
+		REG_WR(bp, param, BNX2X_PTP_TX_ON_PARAM_MASK);
+		REG_WR(bp, rule, BNX2X_PTP_TX_ON_RULE_MASK);
 		break;
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		BNX2X_ERR("One-step timestamping is not supported\n");
 		return -ERANGE;
 	}
 
+	param = port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
+		NIG_REG_P0_LLH_PTP_PARAM_MASK;
+	rule = port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
+		NIG_REG_P0_LLH_PTP_RULE_MASK;
 	switch (bp->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
@@ -15412,30 +15416,24 @@ int bnx2x_configure_ptp_filters(struct bnx2x *bp)
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
 		bp->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		/* Initialize PTP detection for UDP/IPv4 events */
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
-		       NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x7EE);
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
-		       NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3FFE);
+		REG_WR(bp, param, BNX2X_PTP_V1_L4_PARAM_MASK);
+		REG_WR(bp, rule, BNX2X_PTP_V1_L4_RULE_MASK);
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 		bp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 		/* Initialize PTP detection for UDP/IPv4 or UDP/IPv6 events */
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
-		       NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x7EA);
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
-		       NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3FEE);
+		REG_WR(bp, param, BNX2X_PTP_V2_L4_PARAM_MASK);
+		REG_WR(bp, rule, BNX2X_PTP_V2_L4_RULE_MASK);
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
 		bp->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		/* Initialize PTP detection L2 events */
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
-		       NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x6BF);
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
-		       NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3EFF);
+		REG_WR(bp, param, BNX2X_PTP_V2_L2_PARAM_MASK);
+		REG_WR(bp, rule, BNX2X_PTP_V2_L2_RULE_MASK);
 
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
@@ -15443,10 +15441,8 @@ int bnx2x_configure_ptp_filters(struct bnx2x *bp)
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
 		bp->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		/* Initialize PTP detection L2, UDP/IPv4 or UDP/IPv6 events */
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_PARAM_MASK :
-		       NIG_REG_P0_LLH_PTP_PARAM_MASK, 0x6AA);
-		REG_WR(bp, port ? NIG_REG_P1_LLH_PTP_RULE_MASK :
-		       NIG_REG_P0_LLH_PTP_RULE_MASK, 0x3EEE);
+		REG_WR(bp, param, BNX2X_PTP_V2_PARAM_MASK);
+		REG_WR(bp, rule, BNX2X_PTP_V2_RULE_MASK);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index a9eaaf3e73a4..80d250a6d048 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -2977,8 +2977,8 @@ static inline void bnx2x_mcast_hdl_pending_del_e2(struct bnx2x *bp,
 
 		cmd_pos->data.macs_num--;
 
-		  DP(BNX2X_MSG_SP, "Deleting MAC. %d left,cnt is %d\n",
-				   cmd_pos->data.macs_num, cnt);
+		DP(BNX2X_MSG_SP, "Deleting MAC. %d left,cnt is %d\n",
+		   cmd_pos->data.macs_num, cnt);
 
 		/* Break if we reached the maximum
 		 * number of rules.
@@ -3597,8 +3597,8 @@ static int bnx2x_mcast_validate_e1(struct bnx2x *bp,
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
 		p->mcast_list_len = reg_sz;
-		  DP(BNX2X_MSG_SP, "Command %d, p->mcast_list_len=%d\n",
-				   cmd, p->mcast_list_len);
+		DP(BNX2X_MSG_SP, "Command %d, p->mcast_list_len=%d\n",
+		   cmd, p->mcast_list_len);
 		break;
 
 	case BNX2X_MCAST_CMD_ADD:
@@ -3735,8 +3735,8 @@ static inline int bnx2x_mcast_handle_restore_cmd_e1(
 
 		i++;
 
-		  DP(BNX2X_MSG_SP, "About to configure %pM mcast MAC\n",
-		     cfg_data.mac);
+		DP(BNX2X_MSG_SP, "About to configure %pM mcast MAC\n",
+		   cfg_data.mac);
 	}
 
 	*rdata_idx = i;
@@ -5039,7 +5039,6 @@ static inline int bnx2x_q_init(struct bnx2x *bp,
 	/* As no ramrod is sent, complete the command immediately  */
 	o->complete_cmd(bp, o, BNX2X_Q_CMD_INIT);
 
-	mmiowb();
 	smp_mb();
 
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index c835f6c7ecd0..0edbb0a76847 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -100,13 +100,11 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 	   cmd_data.sb_id_and_flags, igu_addr_data);
 	REG_WR(bp, igu_addr_data, cmd_data.sb_id_and_flags);
-	mmiowb();
 	barrier();
 
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 	   ctl, igu_addr_ctl);
 	REG_WR(bp, igu_addr_ctl, ctl);
-	mmiowb();
 	barrier();
 }
 
@@ -2230,7 +2228,7 @@ int bnx2x_vf_free(struct bnx2x *bp, struct bnx2x_virtf *vf)
 		rc = bnx2x_vf_close(bp, vf);
 		if (rc)
 			goto op_err;
-		/* Fallthrough to release resources */
+		/* Fall through - to release resources */
 	case VF_ACQUIRED:
 		DP(BNX2X_MSG_IOV, "about to free resources\n");
 		bnx2x_vf_free_resc(bp, vf);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
index b2644ed13d06..d55e63692cf3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
@@ -207,6 +207,9 @@ struct bnx2x_eth_stats {
 	u32 driver_filtered_tx_pkt;
 	/* src: Clear-on-Read register; Will not survive PMF Migration */
 	u32 eee_tx_lpi;
+
+	/* PTP */
+	u32 ptp_skip_tx_ts;
 };
 
 struct bnx2x_eth_q_stats {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 8e0a317b31f7..0752b7fa4d9c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -172,8 +172,6 @@ static int bnx2x_send_msg2pf(struct bnx2x *bp, u8 *done, dma_addr_t msg_mapping)
 	/* Trigger the PF FW */
 	writeb_relaxed(1, &zone_data->trigger.vf_pf_channel.addr_valid);
 
-	mmiowb();
-
 	/* Wait for PF to complete */
 	while ((tout >= 0) && (!*done)) {
 		msleep(interval);
@@ -957,7 +955,7 @@ int bnx2x_vfpf_update_vlan(struct bnx2x *bp, u16 vid, u8 vf_qid, bool add)
 	bnx2x_sample_bulletin(bp);
 
 	if (bp->shadow_bulletin.content.valid_bitmap & 1 << VLAN_VALID) {
-		BNX2X_ERR("Hypervisor will dicline the request, avoiding\n");
+		BNX2X_ERR("Hypervisor will decline the request, avoiding\n");
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1179,7 +1177,6 @@ static void bnx2x_vf_mbx_resp_send_msg(struct bnx2x *bp,
 
 	/* ack the FW */
 	storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
-	mmiowb();
 
 	/* copy the response header including status-done field,
 	 * must be last dmae, must be after FW is acked
@@ -1654,13 +1651,9 @@ static int bnx2x_vf_mbx_macvlan_list(struct bnx2x *bp,
 {
 	int i, j;
 	struct bnx2x_vf_mac_vlan_filters *fl = NULL;
-	size_t fsz;
-
-	fsz = tlv->n_mac_vlan_filters *
-	      sizeof(struct bnx2x_vf_mac_vlan_filter) +
-	      sizeof(struct bnx2x_vf_mac_vlan_filters);
 
-	fl = kzalloc(fsz, GFP_KERNEL);
+	fl = kzalloc(struct_size(fl, filters, tlv->n_mac_vlan_filters),
+		     GFP_KERNEL);
 	if (!fl)
 		return -ENOMEM;
 
@@ -2178,7 +2171,6 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		 */
 		storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
 		/* Firmware ack should be written before unlocking channel */
-		mmiowb();
 		bnx2x_unlock_vf_pf_channel(bp, vf, mbx->first_tlv.tl.type);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile
index 5a779b19d149..cb97ec56fdec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/Makefile
+++ b/drivers/net/ethernet/broadcom/bnxt/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_BNXT) += bnxt_en.o
 
 bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8bc7e495b027..3f632028eff0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1,7 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
- * Copyright (c) 2016-2018 Broadcom Limited
+ * Copyright (c) 2016-2019 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -31,6 +31,7 @@
 #include <asm/page.h>
 #include <linux/time.h>
 #include <linux/mii.h>
+#include <linux/mdio.h>
 #include <linux/if.h>
 #include <linux/if_vlan.h>
 #include <linux/if_bridge.h>
@@ -53,6 +54,7 @@
 #include <net/pkt_cls.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <net/page_pool.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -112,6 +114,8 @@ enum board_idx {
 	BCM57454,
 	BCM5745x_NPAR,
 	BCM57508,
+	BCM57504,
+	BCM57502,
 	BCM58802,
 	BCM58804,
 	BCM58808,
@@ -155,6 +159,8 @@ static const struct {
 	[BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[BCM5745x_NPAR] = { "Broadcom BCM5745x NetXtreme-E Ethernet Partition" },
 	[BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
+	[BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
+	[BCM57502] = { "Broadcom BCM57502 NetXtreme-E 10Gb/25Gb/50Gb Ethernet" },
 	[BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
 	[BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
@@ -201,6 +207,8 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 },
 	{ PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 },
 	{ PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 },
+	{ PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 },
+	{ PCI_VDEVICE(BROADCOM, 0x1752), .driver_data = BCM57502 },
 	{ PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 },
 	{ PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 },
 #ifdef CONFIG_BNXT_SRIOV
@@ -212,6 +220,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = NETXTREME_C_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e5), .driver_data = NETXTREME_C_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x1806), .driver_data = NETXTREME_E_P5_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x1807), .driver_data = NETXTREME_E_P5_VF },
 	{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
 #endif
@@ -500,6 +509,12 @@ normal_tx:
 	}
 
 	length >>= 9;
+	if (unlikely(length >= ARRAY_SIZE(bnxt_lhint_arr))) {
+		dev_warn_ratelimited(&pdev->dev, "Dropped oversize %d bytes TX packet.\n",
+				     skb->len);
+		i = 0;
+		goto tx_dma_error;
+	}
 	flags |= bnxt_lhint_arr[length];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 
@@ -541,15 +556,13 @@ normal_tx:
 	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
 
-	if (!skb->xmit_more || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
 		bnxt_db_write(bp, &txr->tx_db, prod);
 
 tx_done:
 
-	mmiowb();
-
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
-		if (skb->xmit_more && !tx_buf->is_push)
+		if (netdev_xmit_more() && !tx_buf->is_push)
 			bnxt_db_write(bp, &txr->tx_db, prod);
 
 		netif_tx_stop_queue(txq);
@@ -656,19 +669,20 @@ next_tx_int:
 }
 
 static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
+					 struct bnxt_rx_ring_info *rxr,
 					 gfp_t gfp)
 {
 	struct device *dev = &bp->pdev->dev;
 	struct page *page;
 
-	page = alloc_page(gfp);
+	page = page_pool_dev_alloc_pages(rxr->page_pool);
 	if (!page)
 		return NULL;
 
 	*mapping = dma_map_page_attrs(dev, page, 0, PAGE_SIZE, bp->rx_dir,
 				      DMA_ATTR_WEAK_ORDERING);
 	if (dma_mapping_error(dev, *mapping)) {
-		__free_page(page);
+		page_pool_recycle_direct(rxr->page_pool, page);
 		return NULL;
 	}
 	*mapping += bp->rx_dma_offset;
@@ -704,7 +718,8 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	dma_addr_t mapping;
 
 	if (BNXT_RX_PAGE_MODE(bp)) {
-		struct page *page = __bnxt_alloc_rx_page(bp, &mapping, gfp);
+		struct page *page =
+			__bnxt_alloc_rx_page(bp, &mapping, rxr, gfp);
 
 		if (!page)
 			return -ENOMEM;
@@ -889,7 +904,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 			     DMA_ATTR_WEAK_ORDERING);
 
 	if (unlikely(!payload))
-		payload = eth_get_headlen(data_ptr, len);
+		payload = eth_get_headlen(bp->dev, data_ptr, len);
 
 	skb = napi_alloc_skb(&rxr->bnapi->napi, payload);
 	if (!skb) {
@@ -1123,6 +1138,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons)) {
+		netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return;
 	}
@@ -1575,15 +1592,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	cons = rxcmp->rx_cmp_opaque;
-	rx_buf = &rxr->rx_buf_ring[cons];
-	data = rx_buf->data;
-	data_ptr = rx_buf->data_ptr;
 	if (unlikely(cons != rxr->rx_next_cons)) {
 		int rc1 = bnxt_discard_rx(bp, cpr, raw_cons, rxcmp);
 
+		netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return rc1;
 	}
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data;
+	data_ptr = rx_buf->data_ptr;
 	prefetch(data_ptr);
 
 	misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
@@ -1600,12 +1619,18 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	rx_buf->data = NULL;
 	if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+		u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (agg_bufs)
 			bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);
 
 		rc = -EIO;
-		goto next_rx;
+		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+			bnxt_sched_reset(bp, rxr);
+		}
+		goto next_rx_no_len;
 	}
 
 	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
@@ -1620,6 +1645,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr);
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (!skb) {
+			if (agg_bufs)
+				bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);
 			rc = -ENOMEM;
 			goto next_rx;
 		}
@@ -1686,12 +1713,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	rc = 1;
 
 next_rx:
-	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
-
 	cpr->rx_packets += 1;
 	cpr->rx_bytes += len;
 
+next_rx_no_len:
+	rxr->rx_prod = NEXT_RX(prod);
+	rxr->rx_next_cons = NEXT_RX(cons);
+
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
 
@@ -1964,6 +1992,9 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
+	if (event & BNXT_REDIRECT_EVENT)
+		xdp_do_flush_map();
+
 	if (event & BNXT_TX_EVENT) {
 		struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
 		u16 prod = txr->tx_prod;
@@ -2105,15 +2136,14 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 		}
 	}
 	if (bp->flags & BNXT_FLAG_DIM) {
-		struct net_dim_sample dim_sample;
+		struct dim_sample dim_sample;
 
-		net_dim_sample(cpr->event_ctr,
-			       cpr->rx_packets,
-			       cpr->rx_bytes,
-			       &dim_sample);
+		dim_update_sample(cpr->event_ctr,
+				  cpr->rx_packets,
+				  cpr->rx_bytes,
+				  &dim_sample);
 		net_dim(&cpr->dim, dim_sample);
 	}
-	mmiowb();
 	return work_done;
 }
 
@@ -2230,9 +2260,23 @@ static void bnxt_free_tx_skbs(struct bnxt *bp)
 
 		for (j = 0; j < max_idx;) {
 			struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j];
-			struct sk_buff *skb = tx_buf->skb;
+			struct sk_buff *skb;
 			int k, last;
 
+			if (i < bp->tx_nr_rings_xdp &&
+			    tx_buf->action == XDP_REDIRECT) {
+				dma_unmap_single(&pdev->dev,
+					dma_unmap_addr(tx_buf, mapping),
+					dma_unmap_len(tx_buf, len),
+					PCI_DMA_TODEVICE);
+				xdp_return_frame(tx_buf->xdpf);
+				tx_buf->action = 0;
+				tx_buf->xdpf = NULL;
+				j++;
+				continue;
+			}
+
+			skb = tx_buf->skb;
 			if (!skb) {
 				j++;
 				continue;
@@ -2319,7 +2363,7 @@ static void bnxt_free_rx_skbs(struct bnxt *bp)
 				dma_unmap_page_attrs(&pdev->dev, mapping,
 						     PAGE_SIZE, bp->rx_dir,
 						     DMA_ATTR_WEAK_ORDERING);
-				__free_page(data);
+				page_pool_recycle_direct(rxr->page_pool, data);
 			} else {
 				dma_unmap_single_attrs(&pdev->dev, mapping,
 						       bp->rx_buf_use_size,
@@ -2456,6 +2500,9 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 		if (xdp_rxq_info_is_reg(&rxr->xdp_rxq))
 			xdp_rxq_info_unreg(&rxr->xdp_rxq);
 
+		page_pool_destroy(rxr->page_pool);
+		rxr->page_pool = NULL;
+
 		kfree(rxr->rx_tpa);
 		rxr->rx_tpa = NULL;
 
@@ -2470,6 +2517,26 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
 	}
 }
 
+static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
+				   struct bnxt_rx_ring_info *rxr)
+{
+	struct page_pool_params pp = { 0 };
+
+	pp.pool_size = bp->rx_ring_size;
+	pp.nid = dev_to_node(&bp->pdev->dev);
+	pp.dev = &bp->pdev->dev;
+	pp.dma_dir = DMA_BIDIRECTIONAL;
+
+	rxr->page_pool = page_pool_create(&pp);
+	if (IS_ERR(rxr->page_pool)) {
+		int err = PTR_ERR(rxr->page_pool);
+
+		rxr->page_pool = NULL;
+		return err;
+	}
+	return 0;
+}
+
 static int bnxt_alloc_rx_rings(struct bnxt *bp)
 {
 	int i, rc, agg_rings = 0, tpa_rings = 0;
@@ -2489,10 +2556,22 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 
 		ring = &rxr->rx_ring_struct;
 
+		rc = bnxt_alloc_rx_page_pool(bp, rxr);
+		if (rc)
+			return rc;
+
 		rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i);
 		if (rc < 0)
 			return rc;
 
+		rc = xdp_rxq_info_reg_mem_model(&rxr->xdp_rxq,
+						MEM_TYPE_PAGE_POOL,
+						rxr->page_pool);
+		if (rc) {
+			xdp_rxq_info_unreg(&rxr->xdp_rxq);
+			return rc;
+		}
+
 		rc = bnxt_alloc_ring(bp, &ring->ring_mem);
 		if (rc)
 			return rc;
@@ -3375,6 +3454,12 @@ static void bnxt_free_port_stats(struct bnxt *bp)
 				  bp->hw_rx_port_stats_ext_map);
 		bp->hw_rx_port_stats_ext = NULL;
 	}
+
+	if (bp->hw_pcie_stats) {
+		dma_free_coherent(&pdev->dev, sizeof(struct pcie_ctx_hw_stats),
+				  bp->hw_pcie_stats, bp->hw_pcie_stats_map);
+		bp->hw_pcie_stats = NULL;
+	}
 }
 
 static void bnxt_free_ring_stats(struct bnxt *bp)
@@ -3419,56 +3504,68 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 		cpr->hw_stats_ctx_id = INVALID_STATS_CTX_ID;
 	}
 
-	if (BNXT_PF(bp) && bp->chip_num != CHIP_NUM_58700) {
-		if (bp->hw_rx_port_stats)
-			goto alloc_ext_stats;
+	if (BNXT_VF(bp) || bp->chip_num == CHIP_NUM_58700)
+		return 0;
 
-		bp->hw_port_stats_size = sizeof(struct rx_port_stats) +
-					 sizeof(struct tx_port_stats) + 1024;
+	if (bp->hw_rx_port_stats)
+		goto alloc_ext_stats;
 
-		bp->hw_rx_port_stats =
-			dma_alloc_coherent(&pdev->dev, bp->hw_port_stats_size,
-					   &bp->hw_rx_port_stats_map,
-					   GFP_KERNEL);
-		if (!bp->hw_rx_port_stats)
-			return -ENOMEM;
+	bp->hw_port_stats_size = sizeof(struct rx_port_stats) +
+				 sizeof(struct tx_port_stats) + 1024;
 
-		bp->hw_tx_port_stats = (void *)(bp->hw_rx_port_stats + 1) +
-				       512;
-		bp->hw_tx_port_stats_map = bp->hw_rx_port_stats_map +
-					   sizeof(struct rx_port_stats) + 512;
-		bp->flags |= BNXT_FLAG_PORT_STATS;
+	bp->hw_rx_port_stats =
+		dma_alloc_coherent(&pdev->dev, bp->hw_port_stats_size,
+				   &bp->hw_rx_port_stats_map,
+				   GFP_KERNEL);
+	if (!bp->hw_rx_port_stats)
+		return -ENOMEM;
+
+	bp->hw_tx_port_stats = (void *)(bp->hw_rx_port_stats + 1) + 512;
+	bp->hw_tx_port_stats_map = bp->hw_rx_port_stats_map +
+				   sizeof(struct rx_port_stats) + 512;
+	bp->flags |= BNXT_FLAG_PORT_STATS;
 
 alloc_ext_stats:
-		/* Display extended statistics only if FW supports it */
-		if (bp->hwrm_spec_code < 0x10804 ||
-		    bp->hwrm_spec_code == 0x10900)
+	/* Display extended statistics only if FW supports it */
+	if (bp->hwrm_spec_code < 0x10804 || bp->hwrm_spec_code == 0x10900)
+		if (!(bp->fw_cap & BNXT_FW_CAP_EXT_STATS_SUPPORTED))
 			return 0;
 
-		if (bp->hw_rx_port_stats_ext)
-			goto alloc_tx_ext_stats;
+	if (bp->hw_rx_port_stats_ext)
+		goto alloc_tx_ext_stats;
 
-		bp->hw_rx_port_stats_ext =
-			dma_alloc_coherent(&pdev->dev,
-					   sizeof(struct rx_port_stats_ext),
-					   &bp->hw_rx_port_stats_ext_map,
-					   GFP_KERNEL);
-		if (!bp->hw_rx_port_stats_ext)
-			return 0;
+	bp->hw_rx_port_stats_ext =
+		dma_alloc_coherent(&pdev->dev, sizeof(struct rx_port_stats_ext),
+				   &bp->hw_rx_port_stats_ext_map, GFP_KERNEL);
+	if (!bp->hw_rx_port_stats_ext)
+		return 0;
 
 alloc_tx_ext_stats:
-		if (bp->hw_tx_port_stats_ext)
-			return 0;
+	if (bp->hw_tx_port_stats_ext)
+		goto alloc_pcie_stats;
 
-		if (bp->hwrm_spec_code >= 0x10902) {
-			bp->hw_tx_port_stats_ext =
-				dma_alloc_coherent(&pdev->dev,
-						   sizeof(struct tx_port_stats_ext),
-						   &bp->hw_tx_port_stats_ext_map,
-						   GFP_KERNEL);
-		}
-		bp->flags |= BNXT_FLAG_PORT_STATS_EXT;
+	if (bp->hwrm_spec_code >= 0x10902 ||
+	    (bp->fw_cap & BNXT_FW_CAP_EXT_STATS_SUPPORTED)) {
+		bp->hw_tx_port_stats_ext =
+			dma_alloc_coherent(&pdev->dev,
+					   sizeof(struct tx_port_stats_ext),
+					   &bp->hw_tx_port_stats_ext_map,
+					   GFP_KERNEL);
 	}
+	bp->flags |= BNXT_FLAG_PORT_STATS_EXT;
+
+alloc_pcie_stats:
+	if (bp->hw_pcie_stats ||
+	    !(bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED))
+		return 0;
+
+	bp->hw_pcie_stats =
+		dma_alloc_coherent(&pdev->dev, sizeof(struct pcie_ctx_hw_stats),
+				   &bp->hw_pcie_stats_map, GFP_KERNEL);
+	if (!bp->hw_pcie_stats)
+		return 0;
+
+	bp->flags |= BNXT_FLAG_PCIE_STATS;
 	return 0;
 }
 
@@ -3903,7 +4000,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			if (len)
 				break;
 			/* on first few passes, just barely sleep */
-			if (i < DFLT_HWRM_CMD_TIMEOUT)
+			if (i < HWRM_SHORT_TIMEOUT_COUNTER)
 				usleep_range(HWRM_SHORT_MIN_TIMEOUT,
 					     HWRM_SHORT_MAX_TIMEOUT);
 			else
@@ -3926,7 +4023,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			dma_rmb();
 			if (*valid)
 				break;
-			udelay(1);
+			usleep_range(1, 5);
 		}
 
 		if (j >= HWRM_VALID_BIT_DELAY_USEC) {
@@ -4187,16 +4284,25 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 					     struct bnxt_ntuple_filter *fltr)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[fltr->rxq + 1];
 	struct hwrm_cfa_ntuple_filter_alloc_input req = {0};
 	struct hwrm_cfa_ntuple_filter_alloc_output *resp;
 	struct flow_keys *keys = &fltr->fkeys;
+	struct bnxt_vnic_info *vnic;
+	u32 dst_ena = 0;
 	int rc = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_NTUPLE_FILTER_ALLOC, -1, -1);
 	req.l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
 
-	req.enables = cpu_to_le32(BNXT_NTP_FLTR_FLAGS);
+	if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX) {
+		dst_ena = CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_RFS_RING_TBL_IDX;
+		req.rfs_ring_tbl_idx = cpu_to_le16(fltr->rxq);
+		vnic = &bp->vnic_info[0];
+	} else {
+		vnic = &bp->vnic_info[fltr->rxq + 1];
+	}
+	req.dst_id = cpu_to_le16(vnic->fw_vnic_id);
+	req.enables = cpu_to_le32(BNXT_NTP_FLTR_FLAGS | dst_ena);
 
 	req.ethertype = htons(ETH_P_IP);
 	memcpy(req.src_macaddr, fltr->src_mac_addr, ETH_ALEN);
@@ -4234,7 +4340,6 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 	req.dst_port = keys->ports.dst;
 	req.dst_port_mask = cpu_to_be16(0xffff);
 
-	req.dst_id = cpu_to_le16(vnic->fw_vnic_id);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
@@ -5115,10 +5220,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_TX,
 						close_path ? cmpl_ring_id :
@@ -5131,10 +5236,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_RX,
 						close_path ? cmpl_ring_id :
@@ -5153,10 +5258,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring, type,
 						close_path ? cmpl_ring_id :
 						INVALID_HW_RING_ID);
@@ -5295,17 +5400,16 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
+		enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
 			enables |= tx_rings + ring_grps ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= rx_rings ?
 				FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
 		} else {
 			enables |= cp_rings ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= ring_grps ?
 				   FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS |
 				   FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
@@ -5345,14 +5449,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 	enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
+	enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		enables |= tx_rings + ring_grps ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 	} else {
 		enables |= cp_rings ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 		enables |= ring_grps ?
 			   FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0;
 	}
@@ -5460,7 +5563,16 @@ static int bnxt_cp_rings_in_use(struct bnxt *bp)
 
 static int bnxt_get_func_stat_ctxs(struct bnxt *bp)
 {
-	return bp->cp_nr_rings + bnxt_get_ulp_stat_ctxs(bp);
+	int ulp_stat = bnxt_get_ulp_stat_ctxs(bp);
+	int cp = bp->cp_nr_rings;
+
+	if (!ulp_stat)
+		return cp;
+
+	if (bnxt_nq_rings_in_use(bp) > cp + bnxt_get_ulp_msix_num(bp))
+		return bnxt_get_ulp_msix_base(bp) + ulp_stat;
+
+	return cp + ulp_stat;
 }
 
 static bool bnxt_need_reserve_rings(struct bnxt *bp)
@@ -5484,11 +5596,13 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 	stat = bnxt_get_func_stat_ctxs(bp);
 	if (BNXT_NEW_RM(bp) &&
 	    (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
-	     hw_resc->resv_irqs < nq || hw_resc->resv_vnics != vnic ||
-	     hw_resc->resv_stat_ctxs != stat ||
+	     hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat ||
 	     (hw_resc->resv_hw_ring_grps != grp &&
 	      !(bp->flags & BNXT_FLAG_CHIP_P5))))
 		return true;
+	if ((bp->flags & BNXT_FLAG_CHIP_P5) && BNXT_PF(bp) &&
+	    hw_resc->resv_irqs != nq)
+		return true;
 	return false;
 }
 
@@ -6037,6 +6151,8 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp)
 			ctx->tqm_entries_multiple = 1;
 		ctx->mrav_max_entries = le32_to_cpu(resp->mrav_max_entries);
 		ctx->mrav_entry_size = le16_to_cpu(resp->mrav_entry_size);
+		ctx->mrav_num_entries_units =
+			le16_to_cpu(resp->mrav_num_entries_units);
 		ctx->tim_entry_size = le16_to_cpu(resp->tim_entry_size);
 		ctx->tim_max_entries = le32_to_cpu(resp->tim_max_entries);
 	} else {
@@ -6083,6 +6199,7 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 	struct bnxt_ctx_pg_info *ctx_pg;
 	__le32 *num_entries;
 	__le64 *pg_dir;
+	u32 flags = 0;
 	u8 *pg_attr;
 	int i, rc;
 	u32 ena;
@@ -6142,6 +6259,9 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV) {
 		ctx_pg = &ctx->mrav_mem;
 		req.mrav_num_entries = cpu_to_le32(ctx_pg->entries);
+		if (ctx->mrav_num_entries_units)
+			flags |=
+			FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT;
 		req.mrav_entry_size = cpu_to_le16(ctx->mrav_entry_size);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
 				      &req.mrav_pg_size_mrav_lvl,
@@ -6168,6 +6288,7 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 		*num_entries = cpu_to_le32(ctx_pg->entries);
 		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem, pg_attr, pg_dir);
 	}
+	req.flags = cpu_to_le32(flags);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
 		rc = -EIO;
@@ -6306,6 +6427,7 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	struct bnxt_ctx_pg_info *ctx_pg;
 	struct bnxt_ctx_mem_info *ctx;
 	u32 mem_size, ena, entries;
+	u32 num_mr, num_ah;
 	u32 extra_srqs = 0;
 	u32 extra_qps = 0;
 	u8 pg_lvl = 1;
@@ -6321,7 +6443,7 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	if (!ctx || (ctx->flags & BNXT_CTX_FLAG_INITED))
 		return 0;
 
-	if (bp->flags & BNXT_FLAG_ROCE_CAP) {
+	if ((bp->flags & BNXT_FLAG_ROCE_CAP) && !is_kdump_kernel()) {
 		pg_lvl = 2;
 		extra_qps = 65536;
 		extra_srqs = 8192;
@@ -6369,12 +6491,21 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 		goto skip_rdma;
 
 	ctx_pg = &ctx->mrav_mem;
-	ctx_pg->entries = extra_qps * 4;
+	/* 128K extra is needed to accommodate static AH context
+	 * allocation by f/w.
+	 */
+	num_mr = 1024 * 256;
+	num_ah = 1024 * 128;
+	ctx_pg->entries = num_mr + num_ah;
 	mem_size = ctx->mrav_entry_size * ctx_pg->entries;
 	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 2);
 	if (rc)
 		return rc;
 	ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
+	if (ctx->mrav_num_entries_units)
+		ctx_pg->entries =
+			((num_mr / ctx->mrav_num_entries_units) << 16) |
+			 (num_ah / ctx->mrav_num_entries_units);
 
 	ctx_pg = &ctx->tim_mem;
 	ctx_pg->entries = ctx->qp_mem.entries;
@@ -6489,6 +6620,10 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->flags |= BNXT_FLAG_ROCEV1_CAP;
 	if (flags & FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED)
 		bp->flags |= BNXT_FLAG_ROCEV2_CAP;
+	if (flags & FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_PCIE_STATS_SUPPORTED;
+	if (flags & FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_EXT_STATS_SUPPORTED;
 
 	bp->tx_push_thresh = 0;
 	if (flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED)
@@ -6561,6 +6696,34 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	return 0;
 }
 
+static int bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(struct bnxt *bp)
+{
+	struct hwrm_cfa_adv_flow_mgnt_qcaps_input req = {0};
+	struct hwrm_cfa_adv_flow_mgnt_qcaps_output *resp;
+	int rc = 0;
+	u32 flags;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_CFA_ADV_FLOW))
+		return 0;
+
+	resp = bp->hwrm_cmd_resp_addr;
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_ADV_FLOW_MGNT_QCAPS, -1, -1);
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		goto hwrm_cfa_adv_qcaps_exit;
+
+	flags = le32_to_cpu(resp->flags);
+	if (flags &
+	    CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX;
+
+hwrm_cfa_adv_qcaps_exit:
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 static int bnxt_hwrm_func_reset(struct bnxt *bp)
 {
 	struct hwrm_func_reset_input req = {0};
@@ -6652,6 +6815,15 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 		 resp->hwrm_fw_maj_8b, resp->hwrm_fw_min_8b,
 		 resp->hwrm_fw_bld_8b, resp->hwrm_fw_rsvd_8b);
 
+	if (strlen(resp->active_pkg_name)) {
+		int fw_ver_len = strlen(bp->fw_ver_str);
+
+		snprintf(bp->fw_ver_str + fw_ver_len,
+			 FW_VER_STR_LEN - fw_ver_len - 1, "/pkg %s",
+			 resp->active_pkg_name);
+		bp->fw_cap |= BNXT_FW_CAP_PKG_VER;
+	}
+
 	bp->hwrm_cmd_timeout = le16_to_cpu(resp->def_req_timeout);
 	if (!bp->hwrm_cmd_timeout)
 		bp->hwrm_cmd_timeout = DFLT_HWRM_CMD_TIMEOUT;
@@ -6680,6 +6852,14 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	    VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_OVS_64BIT_HANDLE;
 
+	if (dev_caps_cfg &
+	    VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_TRUSTED_VF;
+
+	if (dev_caps_cfg &
+	    VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_CFA_ADV_FLOW;
+
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -6729,6 +6909,7 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
 	struct hwrm_port_qstats_ext_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
+	u32 tx_stat_size;
 	int rc;
 
 	if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
@@ -6738,13 +6919,16 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	req.port_id = cpu_to_le16(pf->port_id);
 	req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
 	req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map);
-	req.tx_stat_size = cpu_to_le16(sizeof(struct tx_port_stats_ext));
+	tx_stat_size = bp->hw_tx_port_stats_ext ?
+		       sizeof(*bp->hw_tx_port_stats_ext) : 0;
+	req.tx_stat_size = cpu_to_le16(tx_stat_size);
 	req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8;
-		bp->fw_tx_stats_ext_size = le16_to_cpu(resp->tx_stat_size) / 8;
+		bp->fw_tx_stats_ext_size = tx_stat_size ?
+			le16_to_cpu(resp->tx_stat_size) / 8 : 0;
 	} else {
 		bp->fw_rx_stats_ext_size = 0;
 		bp->fw_tx_stats_ext_size = 0;
@@ -6781,6 +6965,19 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	return rc;
 }
 
+static int bnxt_hwrm_pcie_qstats(struct bnxt *bp)
+{
+	struct hwrm_pcie_qstats_input req = {0};
+
+	if (!(bp->flags & BNXT_FLAG_PCIE_STATS))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PCIE_QSTATS, -1, -1);
+	req.pcie_stat_size = cpu_to_le16(sizeof(struct pcie_ctx_hw_stats));
+	req.pcie_stat_host_addr = cpu_to_le64(bp->hw_pcie_stats_map);
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
 static void bnxt_hwrm_free_tunnel_ports(struct bnxt *bp)
 {
 	if (bp->vxlan_port_cnt) {
@@ -7344,11 +7541,7 @@ unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp)
 
 unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp)
 {
-	unsigned int stat;
-
-	stat = bnxt_get_max_func_stat_ctxs(bp) - bnxt_get_ulp_stat_ctxs(bp);
-	stat -= bp->cp_nr_rings;
-	return stat;
+	return bnxt_get_max_func_stat_ctxs(bp) - bnxt_get_func_stat_ctxs(bp);
 }
 
 int bnxt_get_avail_msix(struct bnxt *bp, int num)
@@ -7485,22 +7678,23 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 	bp->flags &= ~BNXT_FLAG_USING_MSIX;
 }
 
-int bnxt_reserve_rings(struct bnxt *bp)
+int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 {
 	int tcs = netdev_get_num_tc(bp->dev);
-	bool reinit_irq = false;
+	bool irq_cleared = false;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
-	if (BNXT_NEW_RM(bp) && (bnxt_get_num_msix(bp) != bp->total_irqs)) {
+	if (irq_re_init && BNXT_NEW_RM(bp) &&
+	    bnxt_get_num_msix(bp) != bp->total_irqs) {
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
-		reinit_irq = true;
+		irq_cleared = true;
 	}
 	rc = __bnxt_reserve_rings(bp);
-	if (reinit_irq) {
+	if (irq_cleared) {
 		if (!rc)
 			rc = bnxt_init_int_mode(bp);
 		bnxt_ulp_irq_restart(bp, rc);
@@ -7679,7 +7873,7 @@ static void bnxt_enable_napi(struct bnxt *bp)
 
 		if (bp->bnapi[i]->rx_ring) {
 			INIT_WORK(&cpr->dim.work, bnxt_dim_work);
-			cpr->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+			cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 		}
 		napi_enable(&bp->bnapi[i]->napi);
 	}
@@ -8399,7 +8593,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 			return rc;
 		}
 	}
-	rc = bnxt_reserve_rings(bp);
+	rc = bnxt_reserve_rings(bp, irq_re_init);
 	if (rc)
 		return rc;
 	if ((bp->flags & BNXT_FLAG_RFS) &&
@@ -8614,24 +8808,88 @@ static int bnxt_close(struct net_device *dev)
 	return 0;
 }
 
+static int bnxt_hwrm_port_phy_read(struct bnxt *bp, u16 phy_addr, u16 reg,
+				   u16 *val)
+{
+	struct hwrm_port_phy_mdio_read_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_port_phy_mdio_read_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10a00)
+		return -EOPNOTSUPP;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_READ, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.phy_addr = phy_addr;
+	req.reg_addr = cpu_to_le16(reg & 0x1f);
+	if (mdio_phy_id_is_c45(phy_addr)) {
+		req.cl45_mdio = 1;
+		req.phy_addr = mdio_phy_id_prtad(phy_addr);
+		req.dev_addr = mdio_phy_id_devad(phy_addr);
+		req.reg_addr = cpu_to_le16(reg);
+	}
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*val = le16_to_cpu(resp->reg_data);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+static int bnxt_hwrm_port_phy_write(struct bnxt *bp, u16 phy_addr, u16 reg,
+				    u16 val)
+{
+	struct hwrm_port_phy_mdio_write_input req = {0};
+
+	if (bp->hwrm_spec_code < 0x10a00)
+		return -EOPNOTSUPP;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_WRITE, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.phy_addr = phy_addr;
+	req.reg_addr = cpu_to_le16(reg & 0x1f);
+	if (mdio_phy_id_is_c45(phy_addr)) {
+		req.cl45_mdio = 1;
+		req.phy_addr = mdio_phy_id_prtad(phy_addr);
+		req.dev_addr = mdio_phy_id_devad(phy_addr);
+		req.reg_addr = cpu_to_le16(reg);
+	}
+	req.reg_data = cpu_to_le16(val);
+
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
 /* rtnl_lock held */
 static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
+	struct mii_ioctl_data *mdio = if_mii(ifr);
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
 	switch (cmd) {
 	case SIOCGMIIPHY:
+		mdio->phy_id = bp->link_info.phy_addr;
+
 		/* fallthru */
 	case SIOCGMIIREG: {
+		u16 mii_regval = 0;
+
 		if (!netif_running(dev))
 			return -EAGAIN;
 
-		return 0;
+		rc = bnxt_hwrm_port_phy_read(bp, mdio->phy_id, mdio->reg_num,
+					     &mii_regval);
+		mdio->val_out = mii_regval;
+		return rc;
 	}
 
 	case SIOCSMIIREG:
 		if (!netif_running(dev))
 			return -EAGAIN;
 
-		return 0;
+		return bnxt_hwrm_port_phy_write(bp, mdio->phy_id, mdio->reg_num,
+						mdio->val_in);
 
 	default:
 		/* do nothing */
@@ -8873,8 +9131,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 
 skip_uc:
 	rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	if (rc && vnic->mc_list_count) {
+		netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+			    rc);
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+		rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	}
 	if (rc)
-		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
+		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n",
 			   rc);
 
 	return rc;
@@ -8902,8 +9167,11 @@ static bool bnxt_can_reserve_rings(struct bnxt *bp)
 /* If the chip and firmware supports RFS */
 static bool bnxt_rfs_supported(struct bnxt *bp)
 {
-	if (bp->flags & BNXT_FLAG_CHIP_P5)
+	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX)
+			return true;
 		return false;
+	}
 	if (BNXT_PF(bp) && !BNXT_CHIP_TYPE_NITRO_A0(bp))
 		return true;
 	if (bp->flags & BNXT_FLAG_NEW_RSS_CAP)
@@ -8918,7 +9186,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	int vnics, max_vnics, max_rss_ctxs;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5)
-		return false;
+		return bnxt_rfs_supported(bp);
 	if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp))
 		return false;
 
@@ -9300,6 +9568,7 @@ static void bnxt_sp_task(struct work_struct *work)
 	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) {
 		bnxt_hwrm_port_qstats(bp);
 		bnxt_hwrm_port_qstats_ext(bp);
+		bnxt_hwrm_pcie_qstats(bp);
 	}
 
 	if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
@@ -9638,32 +9907,19 @@ static int bnxt_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int bnxt_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct bnxt *bp = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
-					     bp, bp, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(bnxt_block_cb_list);
 
 static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			 void *type_data)
 {
+	struct bnxt *bp = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return bnxt_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &bnxt_block_cb_list,
+						  bnxt_setup_tc_block_cb,
+						  bp, bp, true);
 	case TC_SETUP_QDISC_MQPRIO: {
 		struct tc_mqprio_qopt *mqprio = type_data;
 
@@ -9970,25 +10226,11 @@ static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 	return rc;
 }
 
-static int bnxt_get_phys_port_name(struct net_device *dev, char *buf,
-				   size_t len)
+int bnxt_get_port_parent_id(struct net_device *dev,
+			    struct netdev_phys_item_id *ppid)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	int rc;
 
-	/* The PF and it's VF-reps only support the switchdev framework */
-	if (!BNXT_PF(bp))
-		return -EOPNOTSUPP;
-
-	rc = snprintf(buf, len, "p%d", bp->pf.port_id);
-
-	if (rc >= len)
-		return -EOPNOTSUPP;
-	return 0;
-}
-
-int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr)
-{
 	if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
 		return -EOPNOTSUPP;
 
@@ -9996,26 +10238,18 @@ int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr)
 	if (!BNXT_PF(bp))
 		return -EOPNOTSUPP;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(bp->switch_id);
-		memcpy(attr->u.ppid.id, bp->switch_id, attr->u.ppid.id_len);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
+	ppid->id_len = sizeof(bp->switch_id);
+	memcpy(ppid->id, bp->switch_id, ppid->id_len);
+
 	return 0;
 }
 
-static int bnxt_swdev_port_attr_get(struct net_device *dev,
-				    struct switchdev_attr *attr)
+static struct devlink_port *bnxt_get_devlink_port(struct net_device *dev)
 {
-	return bnxt_port_attr_get(netdev_priv(dev), attr);
-}
+	struct bnxt *bp = netdev_priv(dev);
 
-static const struct switchdev_ops bnxt_switchdev_ops = {
-	.switchdev_port_attr_get	= bnxt_swdev_port_attr_get
-};
+	return &bp->dl_port;
+}
 
 static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_open		= bnxt_open,
@@ -10046,9 +10280,10 @@ static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_udp_tunnel_add	= bnxt_udp_tunnel_add,
 	.ndo_udp_tunnel_del	= bnxt_udp_tunnel_del,
 	.ndo_bpf		= bnxt_xdp,
+	.ndo_xdp_xmit		= bnxt_xdp_xmit,
 	.ndo_bridge_getlink	= bnxt_bridge_getlink,
 	.ndo_bridge_setlink	= bnxt_bridge_setlink,
-	.ndo_get_phys_port_name = bnxt_get_phys_port_name
+	.ndo_get_devlink_port	= bnxt_get_devlink_port,
 };
 
 static void bnxt_remove_one(struct pci_dev *pdev)
@@ -10075,10 +10310,10 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
+	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;
-	bnxt_cleanup_pci(bp);
 	bnxt_free_port_stats(bp);
 	free_netdev(dev);
 }
@@ -10250,7 +10485,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 
 	if (sh)
 		bp->flags |= BNXT_FLAG_SHARED_RINGS;
-	dflt_rings = netif_get_num_default_rss_queues();
+	dflt_rings = is_kdump_kernel() ? 1 : netif_get_num_default_rss_queues();
 	/* Reduce default rings on multi-port cards so that total default
 	 * rings do not exceed CPU count.
 	 */
@@ -10372,6 +10607,26 @@ static int bnxt_init_mac_addr(struct bnxt *bp)
 	return rc;
 }
 
+static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
+{
+	struct pci_dev *pdev = bp->pdev;
+	int pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
+	u32 dw;
+
+	if (!pos) {
+		netdev_info(bp->dev, "Unable do read adapter's DSN");
+		return -EOPNOTSUPP;
+	}
+
+	/* DSN (two dw) is at an offset of 4 from the cap pos */
+	pos += 4;
+	pci_read_config_dword(pdev, pos, &dw);
+	put_unaligned_le32(dw, &dsn[0]);
+	pci_read_config_dword(pdev, pos + 4, &dw);
+	put_unaligned_le32(dw, &dsn[4]);
+	return 0;
+}
+
 static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	static int version_printed;
@@ -10406,7 +10661,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->netdev_ops = &bnxt_netdev_ops;
 	dev->watchdog_timeo = BNXT_TX_TIMEOUT;
 	dev->ethtool_ops = &bnxt_ethtool_ops;
-	SWITCHDEV_SET_OPS(dev, &bnxt_switchdev_ops);
 	pci_set_drvdata(pdev, dev);
 
 	rc = bnxt_alloc_hwrm_resources(bp);
@@ -10506,6 +10760,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		rc = -1;
 		goto init_err_pci_clean;
 	}
+
+	rc = bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(bp);
+	if (rc)
+		netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n",
+			    rc);
+
 	rc = bnxt_init_mac_addr(bp);
 	if (rc) {
 		dev_err(&pdev->dev, "Unable to initialize mac address.\n");
@@ -10513,6 +10773,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto init_err_pci_clean;
 	}
 
+	if (BNXT_PF(bp)) {
+		/* Read the adapter's DSN to use as the eswitch switch_id */
+		rc = bnxt_pcie_dsn_get(bp, bp->switch_id);
+		if (rc)
+			goto init_err_pci_clean;
+	}
 	bnxt_hwrm_func_qcfg(bp);
 	bnxt_hwrm_vnic_qcaps(bp);
 	bnxt_hwrm_port_led_qcaps(bp);
@@ -10609,6 +10875,7 @@ init_err_cleanup_tc:
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
@@ -10640,6 +10907,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 
 	if (system_state == SYSTEM_POWER_OFF) {
 		bnxt_clear_int_mode(bp);
+		pci_disable_device(pdev);
 		pci_wake_from_d3(pdev, bp->wol);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a451796deefe..16694b704d15 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -20,11 +20,13 @@
 
 #include <linux/interrupt.h>
 #include <linux/rhashtable.h>
+#include <linux/crash_dump.h>
 #include <net/devlink.h>
 #include <net/dst_metadata.h>
-#include <net/switchdev.h>
 #include <net/xdp.h>
-#include <linux/net_dim.h>
+#include <linux/dim.h>
+
+struct page_pool;
 
 struct tx_bd {
 	__le32 tx_bd_len_flags_type;
@@ -582,20 +584,26 @@ struct nqe_cn {
 	(HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT +		\
 	 ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT))
 
-#define HWRM_VALID_BIT_DELAY_USEC	20
+#define HWRM_VALID_BIT_DELAY_USEC	150
 
 #define BNXT_HWRM_CHNL_CHIMP	0
 #define BNXT_HWRM_CHNL_KONG	1
 
-#define BNXT_RX_EVENT	1
-#define BNXT_AGG_EVENT	2
-#define BNXT_TX_EVENT	4
+#define BNXT_RX_EVENT		1
+#define BNXT_AGG_EVENT		2
+#define BNXT_TX_EVENT		4
+#define BNXT_REDIRECT_EVENT	8
 
 struct bnxt_sw_tx_bd {
-	struct sk_buff		*skb;
+	union {
+		struct sk_buff		*skb;
+		struct xdp_frame	*xdpf;
+	};
 	DEFINE_DMA_UNMAP_ADDR(mapping);
+	DEFINE_DMA_UNMAP_LEN(len);
 	u8			is_gso;
 	u8			is_push;
+	u8			action;
 	union {
 		unsigned short		nr_frags;
 		u16			rx_prod;
@@ -793,6 +801,7 @@ struct bnxt_rx_ring_info {
 	struct bnxt_ring_struct	rx_ring_struct;
 	struct bnxt_ring_struct	rx_agg_ring_struct;
 	struct xdp_rxq_info	xdp_rxq;
+	struct page_pool	*page_pool;
 };
 
 struct bnxt_cp_ring_info {
@@ -810,7 +819,7 @@ struct bnxt_cp_ring_info {
 	u64			rx_bytes;
 	u64			event_ctr;
 
-	struct net_dim		dim;
+	struct dim		dim;
 
 	union {
 		struct tx_cmp	*cp_desc_ring[MAX_CP_PAGES];
@@ -946,6 +955,7 @@ struct bnxt_vf_info {
 					 * stored by PF.
 					 */
 	u16	vlan;
+	u16	func_qcfg_flags;
 	u32	flags;
 #define BNXT_VF_QOS		0x1
 #define BNXT_VF_SPOOFCHK	0x2
@@ -1227,6 +1237,7 @@ struct bnxt_ctx_mem_info {
 	u16	mrav_entry_size;
 	u16	tim_entry_size;
 	u32	tim_max_entries;
+	u16	mrav_num_entries_units;
 	u8	tqm_entries_multiple;
 
 	u32	flags;
@@ -1354,6 +1365,7 @@ struct bnxt {
 	#define BNXT_FLAG_DIM		0x2000000
 	#define BNXT_FLAG_ROCE_MIRROR_CAP	0x4000000
 	#define BNXT_FLAG_PORT_STATS_EXT	0x10000000
+	#define BNXT_FLAG_PCIE_STATS	0x40000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
 					    BNXT_FLAG_RFS |		\
@@ -1367,7 +1379,8 @@ struct bnxt {
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 #define BNXT_RX_PAGE_MODE(bp)	((bp)->flags & BNXT_FLAG_RX_PAGE_MODE)
 #define BNXT_SUPPORTS_TPA(bp)	(!BNXT_CHIP_TYPE_NITRO_A0(bp) &&	\
-				 !(bp->flags & BNXT_FLAG_CHIP_P5))
+				 !(bp->flags & BNXT_FLAG_CHIP_P5) &&	\
+				 !is_kdump_kernel())
 
 /* Chip class phase 5 */
 #define BNXT_CHIP_P5(bp)			\
@@ -1479,6 +1492,12 @@ struct bnxt {
 	#define BNXT_FW_CAP_IF_CHANGE			0x00000010
 	#define BNXT_FW_CAP_KONG_MB_CHNL		0x00000080
 	#define BNXT_FW_CAP_OVS_64BIT_HANDLE		0x00000400
+	#define BNXT_FW_CAP_TRUSTED_VF			0x00000800
+	#define BNXT_FW_CAP_PKG_VER			0x00004000
+	#define BNXT_FW_CAP_CFA_ADV_FLOW		0x00008000
+	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX	0x00010000
+	#define BNXT_FW_CAP_PCIE_STATS_SUPPORTED	0x00020000
+	#define BNXT_FW_CAP_EXT_STATS_SUPPORTED		0x00040000
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
@@ -1497,10 +1516,12 @@ struct bnxt {
 	struct tx_port_stats	*hw_tx_port_stats;
 	struct rx_port_stats_ext	*hw_rx_port_stats_ext;
 	struct tx_port_stats_ext	*hw_tx_port_stats_ext;
+	struct pcie_ctx_hw_stats	*hw_pcie_stats;
 	dma_addr_t		hw_rx_port_stats_map;
 	dma_addr_t		hw_tx_port_stats_map;
 	dma_addr_t		hw_rx_port_stats_ext_map;
 	dma_addr_t		hw_tx_port_stats_ext_map;
+	dma_addr_t		hw_pcie_stats_map;
 	int			hw_port_stats_size;
 	u16			fw_rx_stats_ext_size;
 	u16			fw_tx_stats_ext_size;
@@ -1609,6 +1630,7 @@ struct bnxt {
 
 	/* devlink interface and vf-rep structs */
 	struct devlink		*dl;
+	struct devlink_port	dl_port;
 	enum devlink_eswitch_mode eswitch_mode;
 	struct bnxt_vf_rep	**vf_reps; /* array of vf-rep ptrs */
 	u16			*cfa_code_map; /* cfa_code -> vf_idx map */
@@ -1632,6 +1654,9 @@ struct bnxt {
 #define BNXT_TX_STATS_EXT_OFFSET(counter)		\
 	(offsetof(struct tx_port_stats_ext, counter) / 8)
 
+#define BNXT_PCIE_STATS_OFFSET(counter)			\
+	(offsetof(struct pcie_ctx_hw_stats, counter) / 8)
+
 #define I2C_DEV_ADDR_A0				0xa0
 #define I2C_DEV_ADDR_A2				0xa2
 #define SFF_DIAG_SUPPORT_OFFSET			0x5c
@@ -1776,7 +1801,7 @@ unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
-int bnxt_reserve_rings(struct bnxt *bp);
+int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init);
 void bnxt_tx_disable(struct bnxt *bp);
 void bnxt_tx_enable(struct bnxt *bp);
 int bnxt_hwrm_set_pause(struct bnxt *);
@@ -1794,7 +1819,8 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
 int bnxt_restore_pf_fw_resources(struct bnxt *bp);
-int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr);
+int bnxt_get_port_parent_id(struct net_device *dev,
+			    struct netdev_phys_item_id *ppid);
 void bnxt_dim_work(struct work_struct *work);
 int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 70775158c8c4..07301cb87c03 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -396,7 +396,7 @@ static int bnxt_hwrm_queue_dscp_qcaps(struct bnxt *bp)
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP_QCAPS, -1, -1);
 	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		bp->max_dscp_value = (1 << resp->num_dscp_bits) - 1;
 		if (bp->max_dscp_value < 0x3f)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
index 94e208e9789f..61393f351a77 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include "bnxt_hsi.h"
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 #include "bnxt.h"
 #include "bnxt_debugfs.h"
 
@@ -21,7 +21,7 @@ static ssize_t debugfs_dim_read(struct file *filep,
 				char __user *buffer,
 				size_t count, loff_t *ppos)
 {
-	struct net_dim *dim = filep->private_data;
+	struct dim *dim = filep->private_data;
 	int len;
 	char *buf;
 
@@ -61,7 +61,7 @@ static const struct file_operations debugfs_dim_fops = {
 	.read = debugfs_dim_read,
 };
 
-static struct dentry *debugfs_dim_ring_init(struct net_dim *dim, int ring_idx,
+static struct dentry *debugfs_dim_ring_init(struct dim *dim, int ring_idx,
 					    struct dentry *dd)
 {
 	static char qname[16];
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 7f56032e44ac..549c90d3e465 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -9,6 +9,7 @@
 
 #include <linux/pci.h>
 #include <linux/netdevice.h>
+#include <net/devlink.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_vfr.h"
@@ -188,6 +189,9 @@ static const struct devlink_param bnxt_dl_params[] = {
 			     NULL),
 };
 
+static const struct devlink_param bnxt_dl_port_params[] = {
+};
+
 int bnxt_dl_register(struct bnxt *bp)
 {
 	struct devlink *dl;
@@ -225,8 +229,32 @@ int bnxt_dl_register(struct bnxt *bp)
 		goto err_dl_unreg;
 	}
 
+	devlink_port_attrs_set(&bp->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
+			       bp->pf.port_id, false, 0,
+			       bp->switch_id, sizeof(bp->switch_id));
+	rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id);
+	if (rc) {
+		netdev_err(bp->dev, "devlink_port_register failed");
+		goto err_dl_param_unreg;
+	}
+	devlink_port_type_eth_set(&bp->dl_port, bp->dev);
+
+	rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params,
+					  ARRAY_SIZE(bnxt_dl_port_params));
+	if (rc) {
+		netdev_err(bp->dev, "devlink_port_params_register failed");
+		goto err_dl_port_unreg;
+	}
+
+	devlink_params_publish(dl);
+
 	return 0;
 
+err_dl_port_unreg:
+	devlink_port_unregister(&bp->dl_port);
+err_dl_param_unreg:
+	devlink_params_unregister(dl, bnxt_dl_params,
+				  ARRAY_SIZE(bnxt_dl_params));
 err_dl_unreg:
 	devlink_unregister(dl);
 err_dl_free:
@@ -242,6 +270,9 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
+	devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params,
+				       ARRAY_SIZE(bnxt_dl_port_params));
+	devlink_port_unregister(&bp->dl_port);
 	devlink_params_unregister(dl, bnxt_dl_params,
 				  ARRAY_SIZE(bnxt_dl_params));
 	devlink_unregister(dl);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
index afa97c8bb081..6f6576dc417a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
@@ -7,26 +7,25 @@
  * the Free Software Foundation.
  */
 
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 
 void bnxt_dim_work(struct work_struct *work)
 {
-	struct net_dim *dim = container_of(work, struct net_dim,
-					   work);
+	struct dim *dim = container_of(work, struct dim, work);
 	struct bnxt_cp_ring_info *cpr = container_of(dim,
 						     struct bnxt_cp_ring_info,
 						     dim);
 	struct bnxt_napi *bnapi = container_of(cpr,
 					       struct bnxt_napi,
 					       cp_ring);
-	struct net_dim_cq_moder cur_moder =
+	struct dim_cq_moder cur_moder =
 		net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
 
 	cpr->rx_ring_coal.coal_ticks = cur_moder.usec;
 	cpr->rx_ring_coal.coal_bufs = cur_moder.pkts;
 
 	bnxt_hwrm_set_ring_coal(bnapi->bp, bnapi);
-	dim->state = NET_DIM_START_MEASURE;
+	dim->state = DIM_START_MEASURE;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index adabbe94a259..c7ee63d69679 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -235,6 +235,9 @@ reset_coalesce:
 	BNXT_TX_STATS_PRI_ENTRY(counter, 6),		\
 	BNXT_TX_STATS_PRI_ENTRY(counter, 7)
 
+#define BNXT_PCIE_STATS_ENTRY(counter)	\
+	{ BNXT_PCIE_STATS_OFFSET(counter), __stringify(counter) }
+
 enum {
 	RX_TOTAL_DISCARDS,
 	TX_TOTAL_DISCARDS,
@@ -345,6 +348,10 @@ static const struct {
 	BNXT_RX_STATS_EXT_ENTRY(resume_roce_pause_events),
 	BNXT_RX_STATS_EXT_COS_ENTRIES,
 	BNXT_RX_STATS_EXT_PFC_ENTRIES,
+	BNXT_RX_STATS_EXT_ENTRY(rx_bits),
+	BNXT_RX_STATS_EXT_ENTRY(rx_buffer_passed_threshold),
+	BNXT_RX_STATS_EXT_ENTRY(rx_pcs_symbol_err),
+	BNXT_RX_STATS_EXT_ENTRY(rx_corrected_bits),
 };
 
 static const struct {
@@ -383,6 +390,24 @@ static const struct {
 	BNXT_TX_STATS_PRI_ENTRIES(tx_packets),
 };
 
+static const struct {
+	long offset;
+	char string[ETH_GSTRING_LEN];
+} bnxt_pcie_stats_arr[] = {
+	BNXT_PCIE_STATS_ENTRY(pcie_pl_signal_integrity),
+	BNXT_PCIE_STATS_ENTRY(pcie_dl_signal_integrity),
+	BNXT_PCIE_STATS_ENTRY(pcie_tl_signal_integrity),
+	BNXT_PCIE_STATS_ENTRY(pcie_link_integrity),
+	BNXT_PCIE_STATS_ENTRY(pcie_tx_traffic_rate),
+	BNXT_PCIE_STATS_ENTRY(pcie_rx_traffic_rate),
+	BNXT_PCIE_STATS_ENTRY(pcie_tx_dllp_statistics),
+	BNXT_PCIE_STATS_ENTRY(pcie_rx_dllp_statistics),
+	BNXT_PCIE_STATS_ENTRY(pcie_equalization_time),
+	BNXT_PCIE_STATS_ENTRY(pcie_ltssm_histogram[0]),
+	BNXT_PCIE_STATS_ENTRY(pcie_ltssm_histogram[2]),
+	BNXT_PCIE_STATS_ENTRY(pcie_recovery_histogram),
+};
+
 #define BNXT_NUM_SW_FUNC_STATS	ARRAY_SIZE(bnxt_sw_func_stats)
 #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)
 #define BNXT_NUM_STATS_PRI			\
@@ -390,6 +415,7 @@ static const struct {
 	 ARRAY_SIZE(bnxt_rx_pkts_pri_arr) +	\
 	 ARRAY_SIZE(bnxt_tx_bytes_pri_arr) +	\
 	 ARRAY_SIZE(bnxt_tx_pkts_pri_arr))
+#define BNXT_NUM_PCIE_STATS ARRAY_SIZE(bnxt_pcie_stats_arr)
 
 static int bnxt_get_num_stats(struct bnxt *bp)
 {
@@ -407,6 +433,9 @@ static int bnxt_get_num_stats(struct bnxt *bp)
 			num_stats += BNXT_NUM_STATS_PRI;
 	}
 
+	if (bp->flags & BNXT_FLAG_PCIE_STATS)
+		num_stats += BNXT_NUM_PCIE_STATS;
+
 	return num_stats;
 }
 
@@ -509,6 +538,14 @@ skip_ring_stats:
 			}
 		}
 	}
+	if (bp->flags & BNXT_FLAG_PCIE_STATS) {
+		__le64 *pcie_stats = (__le64 *)bp->hw_pcie_stats;
+
+		for (i = 0; i < BNXT_NUM_PCIE_STATS; i++, j++) {
+			buf[j] = le64_to_cpu(*(pcie_stats +
+					       bnxt_pcie_stats_arr[i].offset));
+		}
+	}
 }
 
 static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
@@ -609,6 +646,12 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 				}
 			}
 		}
+		if (bp->flags & BNXT_FLAG_PCIE_STATS) {
+			for (i = 0; i < BNXT_NUM_PCIE_STATS; i++) {
+				strcpy(buf, bnxt_pcie_stats_arr[i].string);
+				buf += ETH_GSTRING_LEN;
+			}
+		}
 		break;
 	case ETH_SS_TEST:
 		if (bp->num_tests)
@@ -788,7 +831,7 @@ static int bnxt_set_channels(struct net_device *dev,
 			 */
 		}
 	} else {
-		rc = bnxt_reserve_rings(bp);
+		rc = bnxt_reserve_rings(bp, true);
 	}
 
 	return rc;
@@ -2756,7 +2799,7 @@ static int bnxt_run_loopback(struct bnxt *bp)
 		dev_kfree_skb(skb);
 		return -EIO;
 	}
-	bnxt_xmit_xdp(bp, txr, map, pkt_size, 0);
+	bnxt_xmit_bd(bp, txr, map, pkt_size);
 
 	/* Sync BD data before updating doorbell */
 	wmb();
@@ -2799,7 +2842,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 	bool offline = false;
 	u8 test_results = 0;
 	u8 test_mask = 0;
-	int rc, i;
+	int rc = 0, i;
 
 	if (!bp->num_tests || !BNXT_SINGLE_PF(bp))
 		return;
@@ -2870,9 +2913,9 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		}
 		bnxt_hwrm_phy_loopback(bp, false, false);
 		bnxt_half_close_nic(bp);
-		bnxt_open_nic(bp, false, true);
+		rc = bnxt_open_nic(bp, false, true);
 	}
-	if (bnxt_test_irq(bp)) {
+	if (rc || bnxt_test_irq(bp)) {
 		buf[BNXT_IRQ_TEST_IDX] = 1;
 		etest->flags |= ETH_TEST_FL_FAILED;
 	}
@@ -3262,7 +3305,8 @@ void bnxt_ethtool_init(struct bnxt *bp)
 	struct net_device *dev = bp->dev;
 	int i, rc;
 
-	bnxt_get_pkgver(dev);
+	if (!(bp->fw_cap & BNXT_FW_CAP_PKG_VER))
+		bnxt_get_pkgver(dev);
 
 	if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp))
 		return;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 0a0995894ddb..12bbb2a207d0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -1,7 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
- * Copyright (c) 2016-2018 Broadcom Limited
+ * Copyright (c) 2016-2019 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -89,7 +89,10 @@ struct hwrm_short_input {
 	__le16	signature;
 	#define SHORT_REQ_SIGNATURE_SHORT_CMD 0x4321UL
 	#define SHORT_REQ_SIGNATURE_LAST     SHORT_REQ_SIGNATURE_SHORT_CMD
-	__le16	unused_0;
+	__le16	target_id;
+	#define SHORT_REQ_TARGET_ID_DEFAULT 0x0UL
+	#define SHORT_REQ_TARGET_ID_TOOLS   0xfffdUL
+	#define SHORT_REQ_TARGET_ID_LAST   SHORT_REQ_TARGET_ID_TOOLS
 	__le16	size;
 	__le64	req_addr;
 };
@@ -98,6 +101,7 @@ struct hwrm_short_input {
 struct cmd_nums {
 	__le16	req_type;
 	#define HWRM_VER_GET                              0x0UL
+	#define HWRM_ERROR_RECOVERY_QCFG                  0xcUL
 	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
 	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
 	#define HWRM_FUNC_VF_CFG                          0xfUL
@@ -210,6 +214,7 @@ struct cmd_nums {
 	#define HWRM_FWD_RESP                             0xd2UL
 	#define HWRM_FWD_ASYNC_EVENT_CMPL                 0xd3UL
 	#define HWRM_OEM_CMD                              0xd4UL
+	#define HWRM_PORT_PRBS_TEST                       0xd5UL
 	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
 	#define HWRM_WOL_FILTER_ALLOC                     0xf0UL
 	#define HWRM_WOL_FILTER_FREE                      0xf1UL
@@ -221,6 +226,7 @@ struct cmd_nums {
 	#define HWRM_CFA_METER_PROFILE_CFG                0xf7UL
 	#define HWRM_CFA_METER_INSTANCE_ALLOC             0xf8UL
 	#define HWRM_CFA_METER_INSTANCE_FREE              0xf9UL
+	#define HWRM_CFA_METER_INSTANCE_CFG               0xfaUL
 	#define HWRM_CFA_VFR_ALLOC                        0xfdUL
 	#define HWRM_CFA_VFR_FREE                         0xfeUL
 	#define HWRM_CFA_VF_PAIR_ALLOC                    0x100UL
@@ -260,6 +266,7 @@ struct cmd_nums {
 	#define HWRM_CFA_EEM_QCFG                         0x122UL
 	#define HWRM_CFA_EEM_OP                           0x123UL
 	#define HWRM_CFA_ADV_FLOW_MGNT_QCAPS              0x124UL
+	#define HWRM_CFA_TFLIB                            0x125UL
 	#define HWRM_ENGINE_CKV_HELLO                     0x12dUL
 	#define HWRM_ENGINE_CKV_STATUS                    0x12eUL
 	#define HWRM_ENGINE_CKV_CKEK_ADD                  0x12fUL
@@ -269,6 +276,8 @@ struct cmd_nums {
 	#define HWRM_ENGINE_CKV_FLUSH                     0x133UL
 	#define HWRM_ENGINE_CKV_RNG_GET                   0x134UL
 	#define HWRM_ENGINE_CKV_KEY_GEN                   0x135UL
+	#define HWRM_ENGINE_CKV_KEY_LABEL_CFG             0x136UL
+	#define HWRM_ENGINE_CKV_KEY_LABEL_QCFG            0x137UL
 	#define HWRM_ENGINE_QG_CONFIG_QUERY               0x13cUL
 	#define HWRM_ENGINE_QG_QUERY                      0x13dUL
 	#define HWRM_ENGINE_QG_METER_PROFILE_CONFIG_QUERY 0x13eUL
@@ -296,6 +305,7 @@ struct cmd_nums {
 	#define HWRM_ENGINE_NQ_ALLOC                      0x162UL
 	#define HWRM_ENGINE_NQ_FREE                       0x163UL
 	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
+	#define HWRM_ENGINE_FUNC_QCFG                     0x165UL
 	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
 	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
 	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
@@ -308,6 +318,11 @@ struct cmd_nums {
 	#define HWRM_SELFTEST_IRQ                         0x202UL
 	#define HWRM_SELFTEST_RETRIEVE_SERDES_DATA        0x203UL
 	#define HWRM_PCIE_QSTATS                          0x204UL
+	#define HWRM_MFG_FRU_WRITE_CONTROL                0x205UL
+	#define HWRM_MFG_TIMERS_QUERY                     0x206UL
+	#define HWRM_MFG_OTP_CFG                          0x207UL
+	#define HWRM_MFG_OTP_QCFG                         0x208UL
+	#define HWRM_MFG_HDMA_TEST                        0x209UL
 	#define HWRM_DBG_READ_DIRECT                      0xff10UL
 	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
 	#define HWRM_DBG_WRITE_DIRECT                     0xff12UL
@@ -321,6 +336,8 @@ struct cmd_nums {
 	#define HWRM_DBG_FW_CLI                           0xff1aUL
 	#define HWRM_DBG_I2C_CMD                          0xff1bUL
 	#define HWRM_DBG_RING_INFO_GET                    0xff1cUL
+	#define HWRM_DBG_CRASHDUMP_HEADER                 0xff1dUL
+	#define HWRM_DBG_CRASHDUMP_ERASE                  0xff1eUL
 	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
 	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
 	#define HWRM_NVM_FLUSH                            0xfff0UL
@@ -346,23 +363,26 @@ struct cmd_nums {
 /* ret_codes (size:64b/8B) */
 struct ret_codes {
 	__le16	error_code;
-	#define HWRM_ERR_CODE_SUCCESS                   0x0UL
-	#define HWRM_ERR_CODE_FAIL                      0x1UL
-	#define HWRM_ERR_CODE_INVALID_PARAMS            0x2UL
-	#define HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED    0x3UL
-	#define HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR      0x4UL
-	#define HWRM_ERR_CODE_INVALID_FLAGS             0x5UL
-	#define HWRM_ERR_CODE_INVALID_ENABLES           0x6UL
-	#define HWRM_ERR_CODE_UNSUPPORTED_TLV           0x7UL
-	#define HWRM_ERR_CODE_NO_BUFFER                 0x8UL
-	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR    0x9UL
-	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS        0xaUL
-	#define HWRM_ERR_CODE_HOT_RESET_FAIL            0xbUL
-	#define HWRM_ERR_CODE_HWRM_ERROR                0xfUL
-	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE 0x8000UL
-	#define HWRM_ERR_CODE_UNKNOWN_ERR               0xfffeUL
-	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED         0xffffUL
-	#define HWRM_ERR_CODE_LAST                     HWRM_ERR_CODE_CMD_NOT_SUPPORTED
+	#define HWRM_ERR_CODE_SUCCESS                      0x0UL
+	#define HWRM_ERR_CODE_FAIL                         0x1UL
+	#define HWRM_ERR_CODE_INVALID_PARAMS               0x2UL
+	#define HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED       0x3UL
+	#define HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR         0x4UL
+	#define HWRM_ERR_CODE_INVALID_FLAGS                0x5UL
+	#define HWRM_ERR_CODE_INVALID_ENABLES              0x6UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_TLV              0x7UL
+	#define HWRM_ERR_CODE_NO_BUFFER                    0x8UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR       0x9UL
+	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS           0xaUL
+	#define HWRM_ERR_CODE_HOT_RESET_FAIL               0xbUL
+	#define HWRM_ERR_CODE_NO_FLOW_COUNTER_DURING_ALLOC 0xcUL
+	#define HWRM_ERR_CODE_KEY_HASH_COLLISION           0xdUL
+	#define HWRM_ERR_CODE_KEY_ALREADY_EXISTS           0xeUL
+	#define HWRM_ERR_CODE_HWRM_ERROR                   0xfUL
+	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE    0x8000UL
+	#define HWRM_ERR_CODE_UNKNOWN_ERR                  0xfffeUL
+	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED            0xffffUL
+	#define HWRM_ERR_CODE_LAST                        HWRM_ERR_CODE_CMD_NOT_SUPPORTED
 	__le16	unused_0[3];
 };
 
@@ -379,15 +399,19 @@ struct hwrm_err_output {
 };
 #define HWRM_NA_SIGNATURE ((__le32)(-1))
 #define HWRM_MAX_REQ_LEN 128
-#define HWRM_MAX_RESP_LEN 280
+#define HWRM_MAX_RESP_LEN 704
 #define HW_HASH_INDEX_SIZE 0x80
 #define HW_HASH_KEY_SIZE 40
 #define HWRM_RESP_VALID_KEY 1
+#define HWRM_TARGET_ID_BONO 0xFFF8
+#define HWRM_TARGET_ID_KONG 0xFFF9
+#define HWRM_TARGET_ID_APE 0xFFFA
+#define HWRM_TARGET_ID_TOOLS 0xFFFD
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 0
-#define HWRM_VERSION_RSVD 35
-#define HWRM_VERSION_STR "1.10.0.35"
+#define HWRM_VERSION_RSVD 69
+#define HWRM_VERSION_STR "1.10.0.69"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -438,6 +462,7 @@ struct hwrm_ver_get_output {
 	#define VER_GET_RESP_DEV_CAPS_CFG_ADV_FLOW_COUNTERS_SUPPORTED              0x400UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED                      0x2000UL
 	u8	roce_fw_maj_8b;
 	u8	roce_fw_min_8b;
 	u8	roce_fw_bld_8b;
@@ -445,7 +470,7 @@ struct hwrm_ver_get_output {
 	char	hwrm_fw_name[16];
 	char	mgmt_fw_name[16];
 	char	netctrl_fw_name[16];
-	u8	reserved2[16];
+	char	active_pkg_name[16];
 	char	roce_fw_name[16];
 	__le16	chip_num;
 	u8	chip_rev;
@@ -580,6 +605,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE      0x6UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE        0x7UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY               0x8UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY             0x9UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD           0x10UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD             0x11UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT        0x12UL
@@ -595,6 +621,9 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION         0x37UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ        0x38UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE       0x39UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE     0x3aUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE            0x3bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE             0x3cUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG               0xfeUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                 0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                      ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
@@ -724,6 +753,30 @@ struct hwrm_async_event_cmpl_reset_notify {
 	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT            16
 };
 
+/* hwrm_async_event_cmpl_error_recovery (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_recovery {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY 0x9UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_LAST          ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASK                 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_SFT                  0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC           0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED      0x2UL
+};
+
 /* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
 struct hwrm_async_event_cmpl_vf_cfg_change {
 	__le16	type;
@@ -1014,6 +1067,8 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE                   0x100000UL
 	#define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC           0x200000UL
 	#define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE               0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE          0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED             0x1000000UL
 	u8	mac_address[6];
 	__le16	max_rsscos_ctx;
 	__le16	max_cmpl_rings;
@@ -1185,6 +1240,7 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE              0x200000UL
 	#define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC          0x400000UL
 	#define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST                 0x800000UL
+	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE             0x1000000UL
 	__le32	enables;
 	#define FUNC_CFG_REQ_ENABLES_MTU                     0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU                     0x2UL
@@ -1390,6 +1446,7 @@ struct hwrm_func_drv_rgtr_input {
 	#define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE             0x4UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE     0x8UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT          0x10UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT     0x20UL
 	__le32	enables;
 	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
 	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
@@ -1680,7 +1737,7 @@ struct hwrm_func_backing_store_qcaps_output {
 	__le16	mrav_entry_size;
 	__le16	tim_entry_size;
 	__le32	tim_max_entries;
-	u8	unused_0[2];
+	__le16	mrav_num_entries_units;
 	u8	tqm_entries_multiple;
 	u8	valid;
 };
@@ -1693,7 +1750,8 @@ struct hwrm_func_backing_store_cfg_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le32	flags;
-	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE     0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE               0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT     0x2UL
 	__le32	enables;
 	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP            0x1UL
 	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ           0x2UL
@@ -2024,6 +2082,89 @@ struct hwrm_func_backing_store_cfg_output {
 	u8	valid;
 };
 
+/* hwrm_error_recovery_qcfg_input (size:192b/24B) */
+struct hwrm_error_recovery_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_error_recovery_qcfg_output (size:1664b/208B) */
+struct hwrm_error_recovery_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU     0x2UL
+	__le32	driver_polling_freq;
+	__le32	master_func_wait_period;
+	__le32	normal_func_wait_period;
+	__le32	master_func_wait_period_after_reset;
+	__le32	max_bailout_time_after_reset;
+	__le32	fw_health_status_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SFT           2
+	__le32	fw_heartbeat_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SFT           2
+	__le32	fw_reset_cnt_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg_mask;
+	u8	unused_0[3];
+	u8	reg_array_cnt;
+	__le32	reset_reg[16];
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT           2
+	__le32	reset_reg_val[16];
+	u8	delay_after_reset[16];
+	u8	unused_1[7];
+	u8	valid;
+};
+
 /* hwrm_func_drv_if_change_input (size:192b/24B) */
 struct hwrm_func_drv_if_change_input {
 	__le16	req_type;
@@ -2462,7 +2603,7 @@ struct hwrm_port_phy_qcfg_output {
 	u8	valid;
 };
 
-/* hwrm_port_mac_cfg_input (size:320b/40B) */
+/* hwrm_port_mac_cfg_input (size:384b/48B) */
 struct hwrm_port_mac_cfg_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -2483,6 +2624,7 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_DISABLE          0x400UL
 	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_DISABLE        0x800UL
 	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_DISABLE           0x1000UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_ONE_STEP_TX_TS            0x2000UL
 	__le32	enables;
 	#define PORT_MAC_CFG_REQ_ENABLES_IPG                            0x1UL
 	#define PORT_MAC_CFG_REQ_ENABLES_LPBK                           0x2UL
@@ -2492,6 +2634,7 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE     0x40UL
 	#define PORT_MAC_CFG_REQ_ENABLES_TX_TS_CAPTURE_PTP_MSG_TYPE     0x80UL
 	#define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG                  0x100UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB               0x200UL
 	__le16	port_id;
 	u8	ipg;
 	u8	lpbk;
@@ -2524,6 +2667,8 @@ struct hwrm_port_mac_cfg_input {
 	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_MASK          0xe0UL
 	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT           5
 	u8	unused_0[3];
+	__s32	ptp_freq_adj_ppb;
+	u8	unused_1[4];
 };
 
 /* hwrm_port_mac_cfg_output (size:128b/16B) */
@@ -2562,8 +2707,9 @@ struct hwrm_port_mac_ptp_qcfg_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	u8	flags;
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS     0x1UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS       0x2UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS      0x1UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS        0x2UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS     0x4UL
 	u8	unused_0[3];
 	__le32	rx_ts_reg_off_lower;
 	__le32	rx_ts_reg_off_upper;
@@ -2770,7 +2916,7 @@ struct tx_port_stats_ext {
 	__le64	pfc_pri7_tx_transitions;
 };
 
-/* rx_port_stats_ext (size:2368b/296B) */
+/* rx_port_stats_ext (size:2624b/328B) */
 struct rx_port_stats_ext {
 	__le64	link_down_events;
 	__le64	continuous_pause_events;
@@ -2809,6 +2955,10 @@ struct rx_port_stats_ext {
 	__le64	pfc_pri6_rx_transitions;
 	__le64	pfc_pri7_rx_duration_us;
 	__le64	pfc_pri7_rx_transitions;
+	__le64	rx_bits;
+	__le64	rx_buffer_passed_threshold;
+	__le64	rx_pcs_symbol_err;
+	__le64	rx_corrected_bits;
 };
 
 /* hwrm_port_qstats_ext_input (size:320b/40B) */
@@ -2911,6 +3061,35 @@ struct hwrm_port_lpbk_clr_stats_output {
 	u8	valid;
 };
 
+/* hwrm_port_ts_query_input (size:192b/24B) */
+struct hwrm_port_ts_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH             0x1UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_TX            0x0UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_RX            0x1UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_LAST         PORT_TS_QUERY_REQ_FLAGS_PATH_RX
+	#define PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME     0x2UL
+	__le16	port_id;
+	u8	unused_0[2];
+};
+
+/* hwrm_port_ts_query_output (size:192b/24B) */
+struct hwrm_port_ts_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	ptp_msg_ts;
+	__le16	ptp_msg_seqid;
+	u8	unused_0[5];
+	u8	valid;
+};
+
 /* hwrm_port_phy_qcaps_input (size:192b/24B) */
 struct hwrm_port_phy_qcaps_input {
 	__le16	req_type;
@@ -2955,6 +3134,7 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB       0x800UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD      0x1000UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB        0x2000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_200GB       0x4000UL
 	__le16	supported_speeds_auto_mode;
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD     0x1UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB       0x2UL
@@ -2970,6 +3150,7 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB       0x800UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD      0x1000UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB        0x2000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_200GB       0x4000UL
 	__le16	supported_speeds_eee_mode;
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1     0x1UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB     0x2UL
@@ -4583,7 +4764,8 @@ struct hwrm_vnic_qcaps_output {
 	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP                     0x20UL
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP     0x40UL
 	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP                   0x80UL
-	u8	unused_1[7];
+	__le16	max_aggs_supported;
+	u8	unused_1[5];
 	u8	valid;
 };
 
@@ -4603,6 +4785,7 @@ struct hwrm_vnic_tpa_cfg_input {
 	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
 	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_IPID_CHECK            0x40UL
 	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_TTL_CHECK             0x80UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_PACK_AS_GRO           0x100UL
 	__le32	enables;
 	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS      0x1UL
 	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS          0x2UL
@@ -4919,6 +5102,35 @@ struct hwrm_ring_free_output {
 	u8	valid;
 };
 
+/* hwrm_ring_reset_input (size:192b/24B) */
+struct hwrm_ring_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define RING_RESET_REQ_RING_TYPE_L2_CMPL   0x0UL
+	#define RING_RESET_REQ_RING_TYPE_TX        0x1UL
+	#define RING_RESET_REQ_RING_TYPE_RX        0x2UL
+	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL 0x3UL
+	#define RING_RESET_REQ_RING_TYPE_LAST     RING_RESET_REQ_RING_TYPE_ROCE_CMPL
+	u8	unused_0;
+	__le16	ring_id;
+	u8	unused_1[4];
+};
+
+/* hwrm_ring_reset_output (size:128b/16B) */
+struct hwrm_ring_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[4];
+	u8	consumer_idx[3];
+	u8	valid;
+};
+
 /* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
 struct hwrm_ring_aggint_qcaps_input {
 	__le16	req_type;
@@ -5105,6 +5317,8 @@ struct hwrm_cfa_l2_filter_alloc_input {
 	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_L2          (0x1UL << 4)
 	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE        (0x2UL << 4)
 	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_LAST       CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_XDP_DISABLE       0x40UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_SOURCE_VALID      0x80UL
 	__le32	enables;
 	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR             0x1UL
 	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK        0x2UL
@@ -5123,8 +5337,11 @@ struct hwrm_cfa_l2_filter_alloc_input {
 	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE         0x4000UL
 	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID              0x8000UL
 	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID      0x10000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS           0x20000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_NUM_VLANS         0x40000UL
 	u8	l2_addr[6];
-	u8	unused_0[2];
+	u8	num_vlans;
+	u8	t_num_vlans;
 	u8	l2_addr_mask[6];
 	__le16	l2_ovlan;
 	__le16	l2_ovlan_mask;
@@ -5189,6 +5406,16 @@ struct hwrm_cfa_l2_filter_alloc_output {
 	__le16	resp_len;
 	__le64	l2_filter_id;
 	__le32	flow_id;
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -5355,6 +5582,16 @@ struct hwrm_cfa_tunnel_filter_alloc_output {
 	__le16	resp_len;
 	__le64	tunnel_filter_id;
 	__le32	flow_id;
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -5446,19 +5683,21 @@ struct hwrm_cfa_encap_record_alloc_input {
 	__le64	resp_addr;
 	__le32	flags;
 	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_EXTERNAL     0x2UL
 	u8	encap_type;
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN    0x1UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE    0x2UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE    0x3UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP     0x4UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE   0x5UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS     0x6UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN     0x7UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE    0x8UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4 0x9UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1 0xaUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE 0xbUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST    CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN        0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE        0x2UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE        0x3UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP         0x4UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE       0x5UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS         0x6UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN         0x7UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE        0x8UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4     0x9UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1     0xaUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE     0xbUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST        CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6
 	u8	unused_0[3];
 	__le32	encap_data[20];
 };
@@ -5495,7 +5734,7 @@ struct hwrm_cfa_encap_record_free_output {
 	u8	valid;
 };
 
-/* hwrm_cfa_ntuple_filter_alloc_input (size:1024b/128B) */
+/* hwrm_cfa_ntuple_filter_alloc_input (size:1088b/136B) */
 struct hwrm_cfa_ntuple_filter_alloc_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -5506,6 +5745,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP         0x2UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_METER        0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID     0x8UL
 	__le32	enables;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID         0x1UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE            0x2UL
@@ -5526,6 +5766,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_ID               0x10000UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID       0x20000UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR          0x40000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_RFS_RING_TBL_IDX     0x80000UL
 	__le64	l2_filter_id;
 	u8	src_macaddr[6];
 	__be16	ethertype;
@@ -5573,6 +5814,8 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	__be16	dst_port;
 	__be16	dst_port_mask;
 	__le64	ntuple_filter_id_hint;
+	__le16	rfs_ring_tbl_idx;
+	u8	unused_0[6];
 };
 
 /* hwrm_cfa_ntuple_filter_alloc_output (size:192b/24B) */
@@ -5583,6 +5826,16 @@ struct hwrm_cfa_ntuple_filter_alloc_output {
 	__le16	resp_len;
 	__le64	ntuple_filter_id;
 	__le32	flow_id;
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -5627,7 +5880,8 @@ struct hwrm_cfa_ntuple_filter_cfg_input {
 	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID                0x1UL
 	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID        0x2UL
 	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_METER_INSTANCE_ID     0x4UL
-	u8	unused_0[4];
+	__le32	flags;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID     0x1UL
 	__le64	ntuple_filter_id;
 	__le32	new_dst_id;
 	__le32	new_mirror_vnic_id;
@@ -5781,19 +6035,20 @@ struct hwrm_cfa_flow_alloc_input {
 	__le16	src_fid;
 	__le32	tunnel_handle;
 	__le16	action_flags;
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                    0x1UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                0x2UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                   0x4UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                  0x8UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                 0x10UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                0x20UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST               0x40UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS       0x80UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE      0x100UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT          0x200UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP              0x400UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED     0x800UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT               0x1000UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                       0x1UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                   0x2UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                      0x4UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                     0x8UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                    0x10UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                   0x20UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST                  0x40UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS          0x80UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE         0x100UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT             0x200UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP                 0x400UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED        0x800UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT                  0x1000UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NO_FLOW_COUNTER_ALLOC     0x2000UL
 	__le16	dst_fid;
 	__be16	l2_rewrite_vlan_tpid;
 	__be16	l2_rewrite_vlan_tci;
@@ -5844,6 +6099,16 @@ struct hwrm_cfa_flow_alloc_output {
 	__le16	flow_handle;
 	u8	unused_0[2];
 	__le32	flow_id;
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX
 	__le64	ext_flow_handle;
 	__le32	flow_counter_id;
 	u8	unused_1[3];
@@ -5858,7 +6123,8 @@ struct hwrm_cfa_flow_free_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	flow_handle;
-	u8	unused_0[6];
+	__le16	unused_0;
+	__le32	flow_counter_id;
 	__le64	ext_flow_handle;
 };
 
@@ -5892,13 +6158,15 @@ struct hwrm_cfa_flow_info_input {
 	__le64	ext_flow_handle;
 };
 
-/* hwrm_cfa_flow_info_output (size:448b/56B) */
+/* hwrm_cfa_flow_info_output (size:5632b/704B) */
 struct hwrm_cfa_flow_info_output {
 	__le16	error_code;
 	__le16	req_type;
 	__le16	seq_id;
 	__le16	resp_len;
 	u8	flags;
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_TX     0x1UL
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_RX     0x2UL
 	u8	profile;
 	__le16	src_fid;
 	__le16	dst_fid;
@@ -5910,7 +6178,10 @@ struct hwrm_cfa_flow_info_output {
 	__le16	flow_handle;
 	__le32	tunnel_handle;
 	__le16	flow_timer;
-	u8	unused_0[5];
+	u8	unused_0[6];
+	__le32	flow_key_data[130];
+	__le32	flow_action_info[30];
+	u8	unused_1[7];
 	u8	valid;
 };
 
@@ -6041,8 +6312,10 @@ struct hwrm_cfa_eem_qcaps_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	__le32	flags;
-	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX     0x1UL
-	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX     0x2UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX                                         0x1UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX                                         0x2UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_CENTRALIZED_MEMORY_MODEL_SUPPORTED              0x4UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_DETACHED_CENTRALIZED_MEMORY_MODEL_SUPPORTED     0x8UL
 	__le32	unused_0;
 	__le32	supported;
 	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY0_TABLE                       0x1UL
@@ -6068,7 +6341,9 @@ struct hwrm_cfa_eem_cfg_input {
 	#define CFA_EEM_CFG_REQ_FLAGS_PATH_TX               0x1UL
 	#define CFA_EEM_CFG_REQ_FLAGS_PATH_RX               0x2UL
 	#define CFA_EEM_CFG_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
-	__le32	unused_0;
+	#define CFA_EEM_CFG_REQ_FLAGS_SECONDARY_PF          0x8UL
+	__le16	group_id;
+	__le16	unused_0;
 	__le32	num_entries;
 	__le32	unused_1;
 	__le16	key0_ctx_id;
@@ -6100,7 +6375,7 @@ struct hwrm_cfa_eem_qcfg_input {
 	__le32	unused_0;
 };
 
-/* hwrm_cfa_eem_qcfg_output (size:128b/16B) */
+/* hwrm_cfa_eem_qcfg_output (size:192b/24B) */
 struct hwrm_cfa_eem_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -6111,6 +6386,8 @@ struct hwrm_cfa_eem_qcfg_output {
 	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX               0x2UL
 	#define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD     0x4UL
 	__le32	num_entries;
+	u8	unused_0[7];
+	u8	valid;
 };
 
 /* hwrm_cfa_eem_op_input (size:192b/24B) */
@@ -6142,6 +6419,39 @@ struct hwrm_cfa_eem_op_output {
 	u8	valid;
 };
 
+/* hwrm_cfa_adv_flow_mgnt_qcaps_input (size:256b/32B) */
+struct hwrm_cfa_adv_flow_mgnt_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[4];
+};
+
+/* hwrm_cfa_adv_flow_mgnt_qcaps_output (size:128b/16B) */
+struct hwrm_cfa_adv_flow_mgnt_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_16BIT_SUPPORTED              0x1UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_64BIT_SUPPORTED              0x2UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_BATCH_DELETE_SUPPORTED           0x4UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_RESET_ALL_SUPPORTED              0x8UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_DEST_FUNC_SUPPORTED       0x10UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TX_EEM_FLOW_SUPPORTED                 0x20UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RX_EEM_FLOW_SUPPORTED                 0x40UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_COUNTER_ALLOC_SUPPORTED          0x80UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_SUPPORTED            0x100UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_UNTAGGED_VLAN_SUPPORTED               0x200UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_XDP_SUPPORTED                         0x400UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_HEADER_SOURCE_FIELDS_SUPPORTED     0x800UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
 /* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
 struct hwrm_tunnel_dst_port_query_input {
 	__le16	req_type;
@@ -6478,7 +6788,8 @@ struct hwrm_fw_qstatus_output {
 	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTNONE    0x0UL
 	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTASAP    0x1UL
 	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPCIERST 0x2UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_LAST          FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPCIERST
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER   0x3UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_LAST          FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER
 	u8	unused_0[6];
 	u8	valid;
 };
@@ -6501,8 +6812,8 @@ struct hwrm_fw_set_time_input {
 	u8	unused_0;
 	__le16	millisecond;
 	__le16	zone;
-	#define FW_SET_TIME_REQ_ZONE_UTC     0x0UL
-	#define FW_SET_TIME_REQ_ZONE_UNKNOWN 0xffffUL
+	#define FW_SET_TIME_REQ_ZONE_UTC     0
+	#define FW_SET_TIME_REQ_ZONE_UNKNOWN 65535
 	#define FW_SET_TIME_REQ_ZONE_LAST   FW_SET_TIME_REQ_ZONE_UNKNOWN
 	u8	unused_1[4];
 };
@@ -6906,7 +7217,9 @@ struct hwrm_dbg_coredump_list_input {
 	__le64	host_dest_addr;
 	__le32	host_buf_len;
 	__le16	seq_no;
-	u8	unused_0[2];
+	u8	flags;
+	#define DBG_COREDUMP_LIST_REQ_FLAGS_CRASHDUMP     0x1UL
+	u8	unused_0[1];
 };
 
 /* hwrm_dbg_coredump_list_output (size:128b/16B) */
@@ -7234,7 +7547,9 @@ struct hwrm_nvm_get_dev_info_output {
 	__le32	nvram_size;
 	__le32	reserved_size;
 	__le32	available_size;
-	u8	unused_0[3];
+	u8	nvm_cfg_ver_maj;
+	u8	nvm_cfg_ver_min;
+	u8	nvm_cfg_ver_upd;
 	u8	valid;
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index d80f5c981d90..2b90a2bb1a1d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -121,6 +121,54 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	return rc;
 }
 
+static int bnxt_hwrm_func_qcfg_flags(struct bnxt *bp, struct bnxt_vf_info *vf)
+{
+	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_qcfg_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
+	req.fid = cpu_to_le16(vf->fw_fid);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
+		return -EIO;
+	}
+	vf->func_qcfg_flags = le16_to_cpu(resp->flags);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return 0;
+}
+
+static bool bnxt_is_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
+{
+	if (!(bp->fw_cap & BNXT_FW_CAP_TRUSTED_VF))
+		return !!(vf->flags & BNXT_VF_TRUST);
+
+	bnxt_hwrm_func_qcfg_flags(bp, vf);
+	return !!(vf->func_qcfg_flags & FUNC_QCFG_RESP_FLAGS_TRUSTED_VF);
+}
+
+static int bnxt_hwrm_set_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
+{
+	struct hwrm_func_cfg_input req = {0};
+	int rc;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_TRUSTED_VF))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+	req.fid = cpu_to_le16(vf->fw_fid);
+	if (vf->flags & BNXT_VF_TRUST)
+		req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE);
+	else
+		req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		return -EIO;
+	return 0;
+}
+
 int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -135,6 +183,7 @@ int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted)
 	else
 		vf->flags &= ~BNXT_VF_TRUST;
 
+	bnxt_hwrm_set_trusted_vf(bp, vf);
 	return 0;
 }
 
@@ -164,7 +213,7 @@ int bnxt_get_vf_config(struct net_device *dev, int vf_id,
 	else
 		ivi->qos = 0;
 	ivi->spoofchk = !!(vf->flags & BNXT_VF_SPOOFCHK);
-	ivi->trusted = !!(vf->flags & BNXT_VF_TRUST);
+	ivi->trusted = bnxt_is_trusted_vf(bp, vf);
 	if (!(vf->flags & BNXT_VF_LINK_FORCED))
 		ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
 	else if (vf->flags & BNXT_VF_LINK_UP)
@@ -935,9 +984,10 @@ static int bnxt_vf_configure_mac(struct bnxt *bp, struct bnxt_vf_info *vf)
 	 * if the PF assigned MAC address is zero
 	 */
 	if (req->enables & cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR)) {
+		bool trust = bnxt_is_trusted_vf(bp, vf);
+
 		if (is_valid_ether_addr(req->dflt_mac_addr) &&
-		    ((vf->flags & BNXT_VF_TRUST) ||
-		     !is_valid_ether_addr(vf->mac_addr) ||
+		    (trust || !is_valid_ether_addr(vf->mac_addr) ||
 		     ether_addr_equal(req->dflt_mac_addr, vf->mac_addr))) {
 			ether_addr_copy(vf->vf_mac_addr, req->dflt_mac_addr);
 			return bnxt_hwrm_exec_fwd_resp(bp, vf, msg_size);
@@ -962,7 +1012,7 @@ static int bnxt_vf_validate_set_mac(struct bnxt *bp, struct bnxt_vf_info *vf)
 	 * Otherwise, it must match the VF MAC address if firmware spec >=
 	 * 1.2.2
 	 */
-	if (vf->flags & BNXT_VF_TRUST) {
+	if (bnxt_is_trusted_vf(bp, vf)) {
 		mac_ok = true;
 	} else if (is_valid_ether_addr(vf->mac_addr)) {
 		if (ether_addr_equal((const u8 *)req->l2_addr, vf->mac_addr))
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index c683b5e96b1d..6fe4a7174271 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -45,7 +45,7 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev)
 	struct bnxt *bp;
 
 	/* check if dev belongs to the same switch */
-	if (!switchdev_port_same_parent_id(pf_bp->dev, dev)) {
+	if (!netdev_port_same_parent_id(pf_bp->dev, dev)) {
 		netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch",
 			    dev->ifindex);
 		return BNXT_FID_INVALID;
@@ -61,9 +61,9 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev)
 
 static int bnxt_tc_parse_redir(struct bnxt *bp,
 			       struct bnxt_tc_actions *actions,
-			       const struct tc_action *tc_act)
+			       const struct flow_action_entry *act)
 {
-	struct net_device *dev = tcf_mirred_dev(tc_act);
+	struct net_device *dev = act->dev;
 
 	if (!dev) {
 		netdev_info(bp->dev, "no dev in mirred action");
@@ -77,16 +77,16 @@ static int bnxt_tc_parse_redir(struct bnxt *bp,
 
 static int bnxt_tc_parse_vlan(struct bnxt *bp,
 			      struct bnxt_tc_actions *actions,
-			      const struct tc_action *tc_act)
+			      const struct flow_action_entry *act)
 {
-	switch (tcf_vlan_action(tc_act)) {
-	case TCA_VLAN_ACT_POP:
+	switch (act->id) {
+	case FLOW_ACTION_VLAN_POP:
 		actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN;
 		break;
-	case TCA_VLAN_ACT_PUSH:
+	case FLOW_ACTION_VLAN_PUSH:
 		actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN;
-		actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act));
-		actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act);
+		actions->push_vlan_tci = htons(act->vlan.vid);
+		actions->push_vlan_tpid = act->vlan.proto;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -96,10 +96,10 @@ static int bnxt_tc_parse_vlan(struct bnxt *bp,
 
 static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
 				    struct bnxt_tc_actions *actions,
-				    const struct tc_action *tc_act)
+				    const struct flow_action_entry *act)
 {
-	struct ip_tunnel_info *tun_info = tcf_tunnel_info(tc_act);
-	struct ip_tunnel_key *tun_key = &tun_info->key;
+	const struct ip_tunnel_info *tun_info = act->tunnel;
+	const struct ip_tunnel_key *tun_key = &tun_info->key;
 
 	if (ip_tunnel_info_af(tun_info) != AF_INET) {
 		netdev_info(bp->dev, "only IPv4 tunnel-encap is supported");
@@ -113,51 +113,43 @@ static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
 
 static int bnxt_tc_parse_actions(struct bnxt *bp,
 				 struct bnxt_tc_actions *actions,
-				 struct tcf_exts *tc_exts)
+				 struct flow_action *flow_action)
 {
-	const struct tc_action *tc_act;
+	struct flow_action_entry *act;
 	int i, rc;
 
-	if (!tcf_exts_has_actions(tc_exts)) {
+	if (!flow_action_has_entries(flow_action)) {
 		netdev_info(bp->dev, "no actions");
 		return -EINVAL;
 	}
 
-	tcf_exts_for_each_action(i, tc_act, tc_exts) {
-		/* Drop action */
-		if (is_tcf_gact_shot(tc_act)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
 			actions->flags |= BNXT_TC_ACTION_FLAG_DROP;
 			return 0; /* don't bother with other actions */
-		}
-
-		/* Redirect action */
-		if (is_tcf_mirred_egress_redirect(tc_act)) {
-			rc = bnxt_tc_parse_redir(bp, actions, tc_act);
+		case FLOW_ACTION_REDIRECT:
+			rc = bnxt_tc_parse_redir(bp, actions, act);
 			if (rc)
 				return rc;
-			continue;
-		}
-
-		/* Push/pop VLAN */
-		if (is_tcf_vlan(tc_act)) {
-			rc = bnxt_tc_parse_vlan(bp, actions, tc_act);
+			break;
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_MANGLE:
+			rc = bnxt_tc_parse_vlan(bp, actions, act);
 			if (rc)
 				return rc;
-			continue;
-		}
-
-		/* Tunnel encap */
-		if (is_tcf_tunnel_set(tc_act)) {
-			rc = bnxt_tc_parse_tunnel_set(bp, actions, tc_act);
+			break;
+		case FLOW_ACTION_TUNNEL_ENCAP:
+			rc = bnxt_tc_parse_tunnel_set(bp, actions, act);
 			if (rc)
 				return rc;
-			continue;
-		}
-
-		/* Tunnel decap */
-		if (is_tcf_tunnel_release(tc_act)) {
+			break;
+		case FLOW_ACTION_TUNNEL_DECAP:
 			actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_DECAP;
-			continue;
+			break;
+		default:
+			break;
 		}
 	}
 
@@ -177,18 +169,12 @@ static int bnxt_tc_parse_actions(struct bnxt *bp,
 	return 0;
 }
 
-#define GET_KEY(flow_cmd, key_type)					\
-		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
-					  (flow_cmd)->key)
-#define GET_MASK(flow_cmd, key_type)					\
-		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
-					  (flow_cmd)->mask)
-
 static int bnxt_tc_parse_flow(struct bnxt *bp,
-			      struct tc_cls_flower_offload *tc_flow_cmd,
+			      struct flow_cls_offload *tc_flow_cmd,
 			      struct bnxt_tc_flow *flow)
 {
-	struct flow_dissector *dissector = tc_flow_cmd->dissector;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(tc_flow_cmd);
+	struct flow_dissector *dissector = rule->match.dissector;
 
 	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
 	if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
@@ -198,143 +184,123 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
-		struct flow_dissector_key_basic *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		flow->l2_key.ether_type = key->n_proto;
-		flow->l2_mask.ether_type = mask->n_proto;
+		flow_rule_match_basic(rule, &match);
+		flow->l2_key.ether_type = match.key->n_proto;
+		flow->l2_mask.ether_type = match.mask->n_proto;
 
-		if (key->n_proto == htons(ETH_P_IP) ||
-		    key->n_proto == htons(ETH_P_IPV6)) {
-			flow->l4_key.ip_proto = key->ip_proto;
-			flow->l4_mask.ip_proto = mask->ip_proto;
+		if (match.key->n_proto == htons(ETH_P_IP) ||
+		    match.key->n_proto == htons(ETH_P_IPV6)) {
+			flow->l4_key.ip_proto = match.key->ip_proto;
+			flow->l4_mask.ip_proto = match.mask->ip_proto;
 		}
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
-		struct flow_dissector_key_eth_addrs *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
+		flow_rule_match_eth_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS;
-		ether_addr_copy(flow->l2_key.dmac, key->dst);
-		ether_addr_copy(flow->l2_mask.dmac, mask->dst);
-		ether_addr_copy(flow->l2_key.smac, key->src);
-		ether_addr_copy(flow->l2_mask.smac, mask->src);
+		ether_addr_copy(flow->l2_key.dmac, match.key->dst);
+		ether_addr_copy(flow->l2_mask.dmac, match.mask->dst);
+		ether_addr_copy(flow->l2_key.smac, match.key->src);
+		ether_addr_copy(flow->l2_mask.smac, match.mask->src);
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
-		struct flow_dissector_key_vlan *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
+		flow_rule_match_vlan(rule, &match);
 		flow->l2_key.inner_vlan_tci =
-		   cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority));
+			cpu_to_be16(VLAN_TCI(match.key->vlan_id,
+					     match.key->vlan_priority));
 		flow->l2_mask.inner_vlan_tci =
-		   cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority)));
+			cpu_to_be16((VLAN_TCI(match.mask->vlan_id,
+					      match.mask->vlan_priority)));
 		flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q);
 		flow->l2_mask.inner_vlan_tpid = htons(0xffff);
 		flow->l2_key.num_vlans = 1;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
 
+		flow_rule_match_ipv4_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS;
-		flow->l3_key.ipv4.daddr.s_addr = key->dst;
-		flow->l3_mask.ipv4.daddr.s_addr = mask->dst;
-		flow->l3_key.ipv4.saddr.s_addr = key->src;
-		flow->l3_mask.ipv4.saddr.s_addr = mask->src;
-	} else if (dissector_uses_key(dissector,
-				      FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
-
+		flow->l3_key.ipv4.daddr.s_addr = match.key->dst;
+		flow->l3_mask.ipv4.daddr.s_addr = match.mask->dst;
+		flow->l3_key.ipv4.saddr.s_addr = match.key->src;
+		flow->l3_mask.ipv4.saddr.s_addr = match.mask->src;
+	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS;
-		flow->l3_key.ipv6.daddr = key->dst;
-		flow->l3_mask.ipv6.daddr = mask->dst;
-		flow->l3_key.ipv6.saddr = key->src;
-		flow->l3_mask.ipv6.saddr = mask->src;
+		flow->l3_key.ipv6.daddr = match.key->dst;
+		flow->l3_mask.ipv6.daddr = match.mask->dst;
+		flow->l3_key.ipv6.saddr = match.key->src;
+		flow->l3_mask.ipv6.saddr = match.mask->src;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
-		struct flow_dissector_key_ports *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
+		flow_rule_match_ports(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS;
-		flow->l4_key.ports.dport = key->dst;
-		flow->l4_mask.ports.dport = mask->dst;
-		flow->l4_key.ports.sport = key->src;
-		flow->l4_mask.ports.sport = mask->src;
+		flow->l4_key.ports.dport = match.key->dst;
+		flow->l4_mask.ports.dport = match.mask->dst;
+		flow->l4_key.ports.sport = match.key->src;
+		flow->l4_mask.ports.sport = match.mask->src;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) {
-		struct flow_dissector_key_icmp *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
-		struct flow_dissector_key_icmp *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP)) {
+		struct flow_match_icmp match;
 
+		flow_rule_match_icmp(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP;
-		flow->l4_key.icmp.type = key->type;
-		flow->l4_key.icmp.code = key->code;
-		flow->l4_mask.icmp.type = mask->type;
-		flow->l4_mask.icmp.code = mask->code;
+		flow->l4_key.icmp.type = match.key->type;
+		flow->l4_key.icmp.code = match.key->code;
+		flow->l4_mask.icmp.type = match.mask->type;
+		flow->l4_mask.icmp.code = match.mask->code;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
-		struct flow_dissector_key_ipv4_addrs *mask =
-				GET_MASK(tc_flow_cmd,
-					 FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
 
+		flow_rule_match_enc_ipv4_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS;
-		flow->tun_key.u.ipv4.dst = key->dst;
-		flow->tun_mask.u.ipv4.dst = mask->dst;
-		flow->tun_key.u.ipv4.src = key->src;
-		flow->tun_mask.u.ipv4.src = mask->src;
-	} else if (dissector_uses_key(dissector,
+		flow->tun_key.u.ipv4.dst = match.key->dst;
+		flow->tun_mask.u.ipv4.dst = match.mask->dst;
+		flow->tun_key.u.ipv4.src = match.key->src;
+		flow->tun_mask.u.ipv4.src = match.mask->src;
+	} else if (flow_rule_match_key(rule,
 				      FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
-		struct flow_dissector_key_keyid *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
 
+		flow_rule_match_enc_keyid(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ID;
-		flow->tun_key.tun_id = key32_to_tunnel_id(key->keyid);
-		flow->tun_mask.tun_id = key32_to_tunnel_id(mask->keyid);
+		flow->tun_key.tun_id = key32_to_tunnel_id(match.key->keyid);
+		flow->tun_mask.tun_id = key32_to_tunnel_id(match.mask->keyid);
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
-		struct flow_dissector_key_ports *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+		struct flow_match_ports match;
 
+		flow_rule_match_enc_ports(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_PORTS;
-		flow->tun_key.tp_dst = key->dst;
-		flow->tun_mask.tp_dst = mask->dst;
-		flow->tun_key.tp_src = key->src;
-		flow->tun_mask.tp_src = mask->src;
+		flow->tun_key.tp_dst = match.key->dst;
+		flow->tun_mask.tp_dst = match.mask->dst;
+		flow->tun_key.tp_src = match.key->src;
+		flow->tun_mask.tp_src = match.mask->src;
 	}
 
-	return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts);
+	return bnxt_tc_parse_actions(bp, &flow->actions, &rule->action);
 }
 
 static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp,
@@ -1296,7 +1262,7 @@ static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow,
  * The hash-tables are already protected by the rhashtable API.
  */
 static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
-			    struct tc_cls_flower_offload *tc_flow_cmd)
+			    struct flow_cls_offload *tc_flow_cmd)
 {
 	struct bnxt_tc_flow_node *new_node, *old_node;
 	struct bnxt_tc_info *tc_info = bp->tc_info;
@@ -1324,7 +1290,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 		bnxt_tc_set_flow_dir(bp, flow, src_fid);
 
 	if (!bnxt_tc_can_offload(bp, flow)) {
-		rc = -ENOSPC;
+		rc = -EOPNOTSUPP;
 		goto free_node;
 	}
 
@@ -1382,7 +1348,7 @@ done:
 }
 
 static int bnxt_tc_del_flow(struct bnxt *bp,
-			    struct tc_cls_flower_offload *tc_flow_cmd)
+			    struct flow_cls_offload *tc_flow_cmd)
 {
 	struct bnxt_tc_info *tc_info = bp->tc_info;
 	struct bnxt_tc_flow_node *flow_node;
@@ -1397,7 +1363,7 @@ static int bnxt_tc_del_flow(struct bnxt *bp,
 }
 
 static int bnxt_tc_get_flow_stats(struct bnxt *bp,
-				  struct tc_cls_flower_offload *tc_flow_cmd)
+				  struct flow_cls_offload *tc_flow_cmd)
 {
 	struct bnxt_tc_flow_stats stats, *curr_stats, *prev_stats;
 	struct bnxt_tc_info *tc_info = bp->tc_info;
@@ -1422,8 +1388,8 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp,
 	lastused = flow->lastused;
 	spin_unlock(&flow->stats_lock);
 
-	tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets,
-			      lastused);
+	flow_stats_update(&tc_flow_cmd->stats, stats.bytes, stats.packets,
+			  lastused);
 	return 0;
 }
 
@@ -1619,14 +1585,14 @@ void bnxt_tc_flow_stats_work(struct bnxt *bp)
 }
 
 int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
-			 struct tc_cls_flower_offload *cls_flower)
+			 struct flow_cls_offload *cls_flower)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return bnxt_tc_add_flow(bp, src_fid, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return bnxt_tc_del_flow(bp, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return bnxt_tc_get_flow_stats(bp, cls_flower);
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
index 8a0968967bc5..ffec57d1a5ec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -196,7 +196,7 @@ struct bnxt_tc_flow_node {
 };
 
 int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
-			 struct tc_cls_flower_offload *cls_flower);
+			 struct flow_cls_offload *cls_flower);
 int bnxt_init_tc(struct bnxt *bp);
 void bnxt_shutdown_tc(struct bnxt *bp);
 void bnxt_tc_flow_stats_work(struct bnxt *bp);
@@ -209,7 +209,7 @@ static inline bool bnxt_tc_flower_enabled(struct bnxt *bp)
 #else /* CONFIG_BNXT_FLOWER_OFFLOAD */
 
 static inline int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
-				       struct tc_cls_flower_offload *cls_flower)
+				       struct flow_cls_offload *cls_flower)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index ea45a9b8179e..fc77caf0a076 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -43,9 +43,6 @@ static int bnxt_register_dev(struct bnxt_en_dev *edev, int ulp_id,
 	if (ulp_id == BNXT_ROCE_ULP) {
 		unsigned int max_stat_ctxs;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			return -EOPNOTSUPP;
-
 		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
 		if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS ||
 		    bp->cp_nr_rings == max_stat_ctxs)
@@ -150,7 +147,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 			bnxt_close_nic(bp, true, false);
 			rc = bnxt_open_nic(bp, true, false);
 		} else {
-			rc = bnxt_reserve_rings(bp);
+			rc = bnxt_reserve_rings(bp, true);
 		}
 	}
 	if (rc) {
@@ -160,8 +157,10 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 
 	if (BNXT_NEW_RM(bp)) {
 		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+		int resv_msix;
 
-		avail_msix = hw_resc->resv_irqs - bp->cp_nr_rings;
+		resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings;
+		avail_msix = min_t(int, resv_msix, avail_msix);
 		edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
 	}
 	bnxt_fill_msix_vecs(bp, ent);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 9a25c05aa571..f9bf7d7250ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -161,34 +161,19 @@ static int bnxt_vf_rep_setup_tc_block_cb(enum tc_setup_type type,
 	}
 }
 
-static int bnxt_vf_rep_setup_tc_block(struct net_device *dev,
-				      struct tc_block_offload *f)
-{
-	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     bnxt_vf_rep_setup_tc_block_cb,
-					     vf_rep, vf_rep, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block,
-					bnxt_vf_rep_setup_tc_block_cb, vf_rep);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(bnxt_vf_block_cb_list);
 
 static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 				void *type_data)
 {
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return bnxt_vf_rep_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &bnxt_vf_block_cb_list,
+						  bnxt_vf_rep_setup_tc_block_cb,
+						  vf_rep, vf_rep, true);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -237,21 +222,17 @@ static void bnxt_vf_rep_get_drvinfo(struct net_device *dev,
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 }
 
-static int bnxt_vf_rep_port_attr_get(struct net_device *dev,
-				     struct switchdev_attr *attr)
+static int bnxt_vf_rep_get_port_parent_id(struct net_device *dev,
+					  struct netdev_phys_item_id *ppid)
 {
 	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
 
 	/* as only PORT_PARENT_ID is supported currently use common code
 	 * between PF and VF-rep for now.
 	 */
-	return bnxt_port_attr_get(vf_rep->bp, attr);
+	return bnxt_get_port_parent_id(vf_rep->bp->dev, ppid);
 }
 
-static const struct switchdev_ops bnxt_vf_rep_switchdev_ops = {
-	.switchdev_port_attr_get	= bnxt_vf_rep_port_attr_get
-};
-
 static const struct ethtool_ops bnxt_vf_rep_ethtool_ops = {
 	.get_drvinfo		= bnxt_vf_rep_get_drvinfo
 };
@@ -262,6 +243,7 @@ static const struct net_device_ops bnxt_vf_rep_netdev_ops = {
 	.ndo_start_xmit		= bnxt_vf_rep_xmit,
 	.ndo_get_stats64	= bnxt_vf_rep_get_stats64,
 	.ndo_setup_tc		= bnxt_vf_rep_setup_tc,
+	.ndo_get_port_parent_id	= bnxt_vf_rep_get_port_parent_id,
 	.ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name
 };
 
@@ -392,7 +374,6 @@ static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 
 	dev->netdev_ops = &bnxt_vf_rep_netdev_ops;
 	dev->ethtool_ops = &bnxt_vf_rep_ethtool_ops;
-	SWITCHDEV_SET_OPS(dev, &bnxt_vf_rep_switchdev_ops);
 	/* Just inherit all the featues of the parent PF as the VF-R
 	 * uses the RX/TX rings of the parent PF
 	 */
@@ -410,26 +391,6 @@ static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 	dev->min_mtu = ETH_ZLEN;
 }
 
-static int bnxt_pcie_dsn_get(struct bnxt *bp, u8 dsn[])
-{
-	struct pci_dev *pdev = bp->pdev;
-	int pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
-	u32 dw;
-
-	if (!pos) {
-		netdev_info(bp->dev, "Unable do read adapter's DSN");
-		return -EOPNOTSUPP;
-	}
-
-	/* DSN (two dw) is at an offset of 4 from the cap pos */
-	pos += 4;
-	pci_read_config_dword(pdev, pos, &dw);
-	put_unaligned_le32(dw, &dsn[0]);
-	pci_read_config_dword(pdev, pos + 4, &dw);
-	put_unaligned_le32(dw, &dsn[4]);
-	return 0;
-}
-
 static int bnxt_vf_reps_create(struct bnxt *bp)
 {
 	u16 *cfa_code_map = NULL, num_vfs = pci_num_vf(bp->pdev);
@@ -494,11 +455,6 @@ static int bnxt_vf_reps_create(struct bnxt *bp)
 		}
 	}
 
-	/* Read the adapter's DSN to use as the eswitch switch_id */
-	rc = bnxt_pcie_dsn_get(bp, bp->switch_id);
-	if (rc)
-		goto err;
-
 	/* publish cfa_code_map only after all VF-reps have been initialized */
 	bp->cfa_code_map = cfa_code_map;
 	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 0184ef6f05a7..c6f6f2033880 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -15,12 +15,14 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
+#include <net/page_pool.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 
-void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-		   dma_addr_t mapping, u32 len, u16 rx_prod)
+struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr,
+				   dma_addr_t mapping, u32 len)
 {
 	struct bnxt_sw_tx_bd *tx_buf;
 	struct tx_bd *txbd;
@@ -29,7 +31,6 @@ void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 
 	prod = txr->tx_prod;
 	tx_buf = &txr->tx_buf_ring[prod];
-	tx_buf->rx_prod = rx_prod;
 
 	txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)];
 	flags = (len << TX_BD_LEN_SHIFT) | (1 << TX_BD_FLAGS_BD_CNT_SHIFT) |
@@ -40,30 +41,67 @@ void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
 
 	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
+	return tx_buf;
+}
+
+static void __bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
+			    dma_addr_t mapping, u32 len, u16 rx_prod)
+{
+	struct bnxt_sw_tx_bd *tx_buf;
+
+	tx_buf = bnxt_xmit_bd(bp, txr, mapping, len);
+	tx_buf->rx_prod = rx_prod;
+	tx_buf->action = XDP_TX;
+}
+
+static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
+				     struct bnxt_tx_ring_info *txr,
+				     dma_addr_t mapping, u32 len,
+				     struct xdp_frame *xdpf)
+{
+	struct bnxt_sw_tx_bd *tx_buf;
+
+	tx_buf = bnxt_xmit_bd(bp, txr, mapping, len);
+	tx_buf->action = XDP_REDIRECT;
+	tx_buf->xdpf = xdpf;
+	dma_unmap_addr_set(tx_buf, mapping, mapping);
+	dma_unmap_len_set(tx_buf, len, 0);
 }
 
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 {
 	struct bnxt_tx_ring_info *txr = bnapi->tx_ring;
 	struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
+	bool rx_doorbell_needed = false;
 	struct bnxt_sw_tx_bd *tx_buf;
 	u16 tx_cons = txr->tx_cons;
 	u16 last_tx_cons = tx_cons;
-	u16 rx_prod;
 	int i;
 
 	for (i = 0; i < nr_pkts; i++) {
-		last_tx_cons = tx_cons;
+		tx_buf = &txr->tx_buf_ring[tx_cons];
+
+		if (tx_buf->action == XDP_REDIRECT) {
+			struct pci_dev *pdev = bp->pdev;
+
+			dma_unmap_single(&pdev->dev,
+					 dma_unmap_addr(tx_buf, mapping),
+					 dma_unmap_len(tx_buf, len),
+					 PCI_DMA_TODEVICE);
+			xdp_return_frame(tx_buf->xdpf);
+			tx_buf->action = 0;
+			tx_buf->xdpf = NULL;
+		} else if (tx_buf->action == XDP_TX) {
+			rx_doorbell_needed = true;
+			last_tx_cons = tx_cons;
+		}
 		tx_cons = NEXT_TX(tx_cons);
 	}
 	txr->tx_cons = tx_cons;
-	if (bnxt_tx_avail(bp, txr) == bp->tx_ring_size) {
-		rx_prod = rxr->rx_prod;
-	} else {
+	if (rx_doorbell_needed) {
 		tx_buf = &txr->tx_buf_ring[last_tx_cons];
-		rx_prod = tx_buf->rx_prod;
+		bnxt_db_write(bp, &rxr->rx_db, tx_buf->rx_prod);
 	}
-	bnxt_db_write(bp, &rxr->rx_db, rx_prod);
 }
 
 /* returns the following:
@@ -88,19 +126,19 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		return false;
 
 	pdev = bp->pdev;
-	txr = rxr->bnapi->tx_ring;
 	rx_buf = &rxr->rx_buf_ring[cons];
 	offset = bp->rx_offset;
 
+	mapping = rx_buf->mapping - bp->rx_dma_offset;
+	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
+
+	txr = rxr->bnapi->tx_ring;
 	xdp.data_hard_start = *data_ptr - offset;
 	xdp.data = *data_ptr;
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = *data_ptr + *len;
 	xdp.rxq = &rxr->xdp_rxq;
 	orig_data = xdp.data;
-	mapping = rx_buf->mapping - bp->rx_dma_offset;
-
-	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
 
 	rcu_read_lock();
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
@@ -132,10 +170,34 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		*event = BNXT_TX_EVENT;
 		dma_sync_single_for_device(&pdev->dev, mapping + offset, *len,
 					   bp->rx_dir);
-		bnxt_xmit_xdp(bp, txr, mapping + offset, *len,
-			      NEXT_RX(rxr->rx_prod));
+		__bnxt_xmit_xdp(bp, txr, mapping + offset, *len,
+				NEXT_RX(rxr->rx_prod));
 		bnxt_reuse_rx_data(rxr, cons, page);
 		return true;
+	case XDP_REDIRECT:
+		/* if we are calling this here then we know that the
+		 * redirect is coming from a frame received by the
+		 * bnxt_en driver.
+		 */
+		dma_unmap_page_attrs(&pdev->dev, mapping,
+				     PAGE_SIZE, bp->rx_dir,
+				     DMA_ATTR_WEAK_ORDERING);
+
+		/* if we are unable to allocate a new buffer, abort and reuse */
+		if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) {
+			trace_xdp_exception(bp->dev, xdp_prog, act);
+			bnxt_reuse_rx_data(rxr, cons, page);
+			return true;
+		}
+
+		if (xdp_do_redirect(bp->dev, &xdp, xdp_prog)) {
+			trace_xdp_exception(bp->dev, xdp_prog, act);
+			page_pool_recycle_direct(rxr->page_pool, page);
+			return true;
+		}
+
+		*event |= BNXT_REDIRECT_EVENT;
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		/* Fall thru */
@@ -149,6 +211,56 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	return true;
 }
 
+int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
+		  struct xdp_frame **frames, u32 flags)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	struct bpf_prog *xdp_prog = READ_ONCE(bp->xdp_prog);
+	struct pci_dev *pdev = bp->pdev;
+	struct bnxt_tx_ring_info *txr;
+	dma_addr_t mapping;
+	int drops = 0;
+	int ring;
+	int i;
+
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state) ||
+	    !bp->tx_nr_rings_xdp ||
+	    !xdp_prog)
+		return -EINVAL;
+
+	ring = smp_processor_id() % bp->tx_nr_rings_xdp;
+	txr = &bp->tx_ring[ring];
+
+	for (i = 0; i < num_frames; i++) {
+		struct xdp_frame *xdp = frames[i];
+
+		if (!txr || !bnxt_tx_avail(bp, txr) ||
+		    !(bp->bnapi[ring]->flags & BNXT_NAPI_FLAG_XDP)) {
+			xdp_return_frame_rx_napi(xdp);
+			drops++;
+			continue;
+		}
+
+		mapping = dma_map_single(&pdev->dev, xdp->data, xdp->len,
+					 DMA_TO_DEVICE);
+
+		if (dma_mapping_error(&pdev->dev, mapping)) {
+			xdp_return_frame_rx_napi(xdp);
+			drops++;
+			continue;
+		}
+		__bnxt_xmit_xdp_redirect(bp, txr, mapping, xdp->len, xdp);
+	}
+
+	if (flags & XDP_XMIT_FLUSH) {
+		/* Sync BD data before updating doorbell */
+		wmb();
+		bnxt_db_write(bp, &txr->tx_db, txr->tx_prod);
+	}
+
+	return num_frames - drops;
+}
+
 /* Under rtnl_lock */
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 414b748038ca..0df40c3beb05 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -10,12 +10,15 @@
 #ifndef BNXT_XDP_H
 #define BNXT_XDP_H
 
-void bnxt_xmit_xdp(struct bnxt *bp, struct bnxt_tx_ring_info *txr,
-		   dma_addr_t mapping, u32 len, u16 rx_prod);
+struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr,
+				   dma_addr_t mapping, u32 len);
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		 struct page *page, u8 **data_ptr, unsigned int *len,
 		 u8 *event);
 int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
+int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
+		  struct xdp_frame **frames, u32 flags);
 
 #endif
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 510dfc1c236b..57dc3cbff36e 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -4038,15 +4038,14 @@ static void cnic_cm_process_kcqe(struct cnic_dev *dev, struct kcqe *kcqe)
 	case L5CM_RAMROD_CMD_ID_CLOSE: {
 		struct iscsi_kcqe *l5kcqe = (struct iscsi_kcqe *) kcqe;
 
-		if (l4kcqe->status != 0 || l5kcqe->completion_status != 0) {
-			netdev_warn(dev->netdev, "RAMROD CLOSE compl with status 0x%x completion status 0x%x\n",
-				    l4kcqe->status, l5kcqe->completion_status);
-			opcode = L4_KCQE_OPCODE_VALUE_CLOSE_COMP;
-			/* Fall through */
-		} else {
+		if (l4kcqe->status == 0 && l5kcqe->completion_status == 0)
 			break;
-		}
+
+		netdev_warn(dev->netdev, "RAMROD CLOSE compl with status 0x%x completion status 0x%x\n",
+			    l4kcqe->status, l5kcqe->completion_status);
+		opcode = L4_KCQE_OPCODE_VALUE_CLOSE_COMP;
 	}
+		/* Fall through */
 	case L4_KCQE_OPCODE_VALUE_RESET_RECEIVED:
 	case L4_KCQE_OPCODE_VALUE_CLOSE_COMP:
 	case L4_KCQE_OPCODE_VALUE_RESET_COMP:
diff --git a/drivers/net/ethernet/broadcom/genet/Makefile b/drivers/net/ethernet/broadcom/genet/Makefile
index 9b6885efa9e7..edfc26a46948 100644
--- a/drivers/net/ethernet/broadcom/genet/Makefile
+++ b/drivers/net/ethernet/broadcom/genet/Makefile
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_BCMGENET) += genet.o
 genet-objs := bcmgenet.o bcmmii.o bcmgenet_wol.o
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 983245c0867c..34466b827dde 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Broadcom GENET (Gigabit Ethernet) controller driver
  *
  * Copyright (c) 2014-2017 Broadcom
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt)				"bcmgenet: " fmt
@@ -643,7 +640,7 @@ static void bcmgenet_set_rx_coalesce(struct bcmgenet_rx_ring *ring,
 static void bcmgenet_set_ring_rx_coalesce(struct bcmgenet_rx_ring *ring,
 					  struct ethtool_coalesce *ec)
 {
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 	u32 usecs, pkts;
 
 	ring->rx_coalesce_usecs = ec->rx_coalesce_usecs;
@@ -1665,7 +1662,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (ring->free_bds <= (MAX_SKB_FRAGS + 1))
 		netif_tx_stop_queue(txq);
 
-	if (!skb->xmit_more || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
 		/* Packets are ready, update producer index */
 		bcmgenet_tdma_ring_writel(priv, ring->index,
 					  ring->prod_index, TDMA_PROD_INDEX);
@@ -1898,7 +1895,7 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
 {
 	struct bcmgenet_rx_ring *ring = container_of(napi,
 			struct bcmgenet_rx_ring, napi);
-	struct net_dim_sample dim_sample;
+	struct dim_sample dim_sample;
 	unsigned int work_done;
 
 	work_done = bcmgenet_desc_rx(ring, budget);
@@ -1909,8 +1906,8 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
 	}
 
 	if (ring->dim.use_dim) {
-		net_dim_sample(ring->dim.event_ctr, ring->dim.packets,
-			       ring->dim.bytes, &dim_sample);
+		dim_update_sample(ring->dim.event_ctr, ring->dim.packets,
+				  ring->dim.bytes, &dim_sample);
 		net_dim(&ring->dim.dim, dim_sample);
 	}
 
@@ -1919,16 +1916,16 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
 
 static void bcmgenet_dim_work(struct work_struct *work)
 {
-	struct net_dim *dim = container_of(work, struct net_dim, work);
+	struct dim *dim = container_of(work, struct dim, work);
 	struct bcmgenet_net_dim *ndim =
 			container_of(dim, struct bcmgenet_net_dim, dim);
 	struct bcmgenet_rx_ring *ring =
 			container_of(ndim, struct bcmgenet_rx_ring, dim);
-	struct net_dim_cq_moder cur_profile =
+	struct dim_cq_moder cur_profile =
 			net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
 
 	bcmgenet_set_rx_coalesce(ring, cur_profile.usec, cur_profile.pkts);
-	dim->state = NET_DIM_START_MEASURE;
+	dim->state = DIM_START_MEASURE;
 }
 
 /* Assign skb to RX DMA descriptor. */
@@ -2085,7 +2082,7 @@ static void bcmgenet_init_dim(struct bcmgenet_rx_ring *ring,
 	struct bcmgenet_net_dim *dim = &ring->dim;
 
 	INIT_WORK(&dim->dim.work, cb);
-	dim->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	dim->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	dim->event_ctr = 0;
 	dim->packets = 0;
 	dim->bytes = 0;
@@ -2094,7 +2091,7 @@ static void bcmgenet_init_dim(struct bcmgenet_rx_ring *ring,
 static void bcmgenet_init_rx_coalesce(struct bcmgenet_rx_ring *ring)
 {
 	struct bcmgenet_net_dim *dim = &ring->dim;
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 	u32 usecs, pkts;
 
 	usecs = ring->rx_coalesce_usecs;
@@ -3476,7 +3473,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 
 	if (dn) {
 		macaddr = of_get_mac_address(dn);
-		if (!macaddr) {
+		if (IS_ERR(macaddr)) {
 			dev_err(&pdev->dev, "can't find MAC address\n");
 			err = -EINVAL;
 			goto err;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 14b49612aa86..4a8fc03d82fd 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (c) 2014-2017 Broadcom
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __BCMGENET_H__
@@ -16,7 +13,7 @@
 #include <linux/mii.h>
 #include <linux/if_vlan.h>
 #include <linux/phy.h>
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 
 /* total number of Buffer Descriptors, same for Rx/Tx */
 #define TOTAL_DESC				256
@@ -581,7 +578,7 @@ struct bcmgenet_net_dim {
 	u16		event_ctr;
 	unsigned long	packets;
 	unsigned long	bytes;
-	struct net_dim	dim;
+	struct dim	dim;
 };
 
 struct bcmgenet_rx_ring {
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 57582efa362d..ea20d94bd050 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
  *
  * Copyright (c) 2014-2017 Broadcom
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt)				"bcmgenet_wol: " fmt
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index aceb9b7b55bd..970e478a9017 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Broadcom GENET MDIO routines
  *
  * Copyright (c) 2014-2017 Broadcom
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 
@@ -525,7 +522,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 			.asym_pause = 0,
 		};
 
-		phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL);
+		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
 		if (!phydev || IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register fixed PHY device\n");
 			return -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 134ae2862efa..1604ad32e920 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -1,21 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2001,2002,2003,2004 Broadcom Corporation
  * Copyright (c) 2006, 2007  Maciej W. Rozycki
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- *
  * This driver is designed for the Broadcom SiByte SOC built-in
  * Ethernet controllers. Written by Mitch Lichtenberg at Broadcom Corp.
  *
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index b1627dd5f2fd..4c404d2213f9 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -721,7 +721,7 @@ static int tg3_ape_lock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return 0;
-		/* else: fall through */
+		/* fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -782,7 +782,7 @@ static void tg3_ape_unlock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return;
-		/* else: fall through */
+		/* fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -1073,7 +1073,6 @@ static void tg3_int_reenable(struct tg3_napi *tnapi)
 	struct tg3 *tp = tnapi->tp;
 
 	tw32_mailbox(tnapi->int_mbox, tnapi->last_tag << 24);
-	mmiowb();
 
 	/* When doing tagged status, this work check is unnecessary.
 	 * The last_tag we write above tells the chip which piece of
@@ -4283,7 +4282,7 @@ static void tg3_power_down(struct tg3 *tp)
 	pci_set_power_state(tp->pdev, PCI_D3hot);
 }
 
-static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u16 *speed, u8 *duplex)
+static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u32 *speed, u8 *duplex)
 {
 	switch (val & MII_TG3_AUX_STAT_SPDMASK) {
 	case MII_TG3_AUX_STAT_10HALF:
@@ -4787,7 +4786,7 @@ static int tg3_setup_copper_phy(struct tg3 *tp, bool force_reset)
 	bool current_link_up;
 	u32 bmsr, val;
 	u32 lcl_adv, rmt_adv;
-	u16 current_speed;
+	u32 current_speed;
 	u8 current_duplex;
 	int i, err;
 
@@ -5719,7 +5718,7 @@ out:
 static int tg3_setup_fiber_phy(struct tg3 *tp, bool force_reset)
 {
 	u32 orig_pause_cfg;
-	u16 orig_active_speed;
+	u32 orig_active_speed;
 	u8 orig_active_duplex;
 	u32 mac_status;
 	bool current_link_up;
@@ -5823,7 +5822,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 {
 	int err = 0;
 	u32 bmsr, bmcr;
-	u16 current_speed = SPEED_UNKNOWN;
+	u32 current_speed = SPEED_UNKNOWN;
 	u8 current_duplex = DUPLEX_UNKNOWN;
 	bool current_link_up = false;
 	u32 local_adv, remote_adv, sgsr;
@@ -6711,7 +6710,7 @@ static int tg3_alloc_rx_data(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
 	skb_size = SKB_DATA_ALIGN(data_size + TG3_RX_OFFSET(tp)) +
 		   SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	if (skb_size <= PAGE_SIZE) {
-		data = netdev_alloc_frag(skb_size);
+		data = napi_alloc_frag(skb_size);
 		*frag_size = skb_size;
 	} else {
 		data = kmalloc(skb_size, GFP_ATOMIC);
@@ -6999,7 +6998,6 @@ next_pkt_nopost:
 			tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG,
 				     tpr->rx_jmb_prod_idx);
 		}
-		mmiowb();
 	} else if (work_mask) {
 		/* rx_std_buffers[] and rx_jmb_buffers[] entries must be
 		 * updated before the producer indices can be updated.
@@ -7210,8 +7208,6 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
 			tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG,
 				     dpr->rx_jmb_prod_idx);
 
-		mmiowb();
-
 		if (err)
 			tw32_f(HOSTCC_MODE, tp->coal_now);
 	}
@@ -7278,7 +7274,6 @@ static int tg3_poll_msix(struct napi_struct *napi, int budget)
 						  HOSTCC_MODE_ENABLE |
 						  tnapi->coal_now);
 			}
-			mmiowb();
 			break;
 		}
 	}
@@ -8156,10 +8151,9 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			netif_tx_wake_queue(txq);
 	}
 
-	if (!skb->xmit_more || netif_xmit_stopped(txq)) {
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
 		/* Packets are ready, update Tx producer idx on card. */
 		tw32_tx_mbox(tnapi->prodmbox, entry);
-		mmiowb();
 	}
 
 	return NETDEV_TX_OK;
@@ -12763,9 +12757,6 @@ static int tg3_set_phys_id(struct net_device *dev,
 {
 	struct tg3 *tp = netdev_priv(dev);
 
-	if (!netif_running(tp->dev))
-		return -EAGAIN;
-
 	switch (state) {
 	case ETHTOOL_ID_ACTIVE:
 		return 1;	/* cycle on/off once per second */
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index a772a33b685c..6953d0546acb 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2873,7 +2873,7 @@ struct tg3_tx_ring_info {
 struct tg3_link_config {
 	/* Describes what we're trying to get. */
 	u32				advertising;
-	u16				speed;
+	u32				speed;
 	u8				duplex;
 	u8				autoneg;
 	u8				flowctrl;
@@ -2882,7 +2882,7 @@ struct tg3_link_config {
 	u8				active_flowctrl;
 
 	u8				active_duplex;
-	u16				active_speed;
+	u32				active_speed;
 	u32				rmt_adv;
 };
 
diff --git a/drivers/net/ethernet/brocade/Kconfig b/drivers/net/ethernet/brocade/Kconfig
index c4bbe54e2cad..d4564c7a279c 100644
--- a/drivers/net/ethernet/brocade/Kconfig
+++ b/drivers/net/ethernet/brocade/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # QLogic BR-series device configuration
 #
diff --git a/drivers/net/ethernet/brocade/Makefile b/drivers/net/ethernet/brocade/Makefile
index fec10f9b4558..88b2f402675f 100644
--- a/drivers/net/ethernet/brocade/Makefile
+++ b/drivers/net/ethernet/brocade/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the QLogic BR-series device drivers.
 #
diff --git a/drivers/net/ethernet/brocade/bna/Kconfig b/drivers/net/ethernet/brocade/bna/Kconfig
index fe01279a8843..b124a628f86a 100644
--- a/drivers/net/ethernet/brocade/bna/Kconfig
+++ b/drivers/net/ethernet/brocade/bna/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # QLogic BR-series network device configuration
 #
diff --git a/drivers/net/ethernet/brocade/bna/Makefile b/drivers/net/ethernet/brocade/bna/Makefile
index 8584abcf5366..d804b30c33eb 100644
--- a/drivers/net/ethernet/brocade/bna/Makefile
+++ b/drivers/net/ethernet/brocade/bna/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
 # Copyright (c) 2014-2015 QLogic Corporation.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.c b/drivers/net/ethernet/brocade/bna/bfa_cee.c
index 95bc8b644a5d..09fb9315d1ae 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cee.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_cee.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.h b/drivers/net/ethernet/brocade/bna/bfa_cee.h
index d04eef5d5a77..8e628bb54ba0 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cee.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_cee.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cs.h b/drivers/net/ethernet/brocade/bna/bfa_cs.h
index 1d11d666d408..8f0ac7b99973 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cs.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_cs.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs.h b/drivers/net/ethernet/brocade/bna/bfa_defs.h
index d152b3fa6c54..b08b16864bb0 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h b/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h
index f048887cbb81..50d3562f7d32 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h b/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h
index 7e17451c94d1..0478f35ae685 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs_status.h b/drivers/net/ethernet/brocade/bna/bfa_defs_status.h
index a43b56002752..0ed9ec2e68a6 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs_status.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs_status.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index a36e38676640..4042c2185e98 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
@@ -743,7 +735,7 @@ bfa_iocpf_sm_hwinit(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_TIMEOUT:
 		bfa_nw_ioc_hw_sem_release(ioc);
-			bfa_ioc_pf_failed(ioc);
+		bfa_ioc_pf_failed(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_initfail_sync);
 		break;
 
@@ -788,9 +780,8 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_INITFAIL:
 		del_timer(&ioc->iocpf_timer);
-		/*
-		 * !!! fall through !!!
-		 */
+		/* fall through */
+
 	case IOCPF_E_TIMEOUT:
 		bfa_nw_ioc_hw_sem_release(ioc);
 		if (event == IOCPF_E_TIMEOUT)
@@ -858,9 +849,7 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_FAIL:
 		del_timer(&ioc->iocpf_timer);
-		/*
-		 * !!! fall through !!!
-		 */
+		/* fall through*/
 
 	case IOCPF_E_TIMEOUT:
 		bfa_ioc_set_cur_ioc_fwstate(ioc, BFI_IOC_FAIL);
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.h b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
index 2c0b4c076355..edd0ed5b5332 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c b/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c
index 74e5ed55ac01..bd643d841180 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_msgq.c b/drivers/net/ethernet/brocade/bna/bfa_msgq.c
index 9c5bb24e8abb..47125f419530 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_msgq.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_msgq.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfa_msgq.h b/drivers/net/ethernet/brocade/bna/bfa_msgq.h
index 66bc8b5acd57..75343b535798 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_msgq.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_msgq.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfi.h b/drivers/net/ethernet/brocade/bna/bfi.h
index 81e59ea8b4f2..09c912e984fe 100644
--- a/drivers/net/ethernet/brocade/bna/bfi.h
+++ b/drivers/net/ethernet/brocade/bna/bfi.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfi_cna.h b/drivers/net/ethernet/brocade/bna/bfi_cna.h
index fad651101c48..fb78bfd0bcf2 100644
--- a/drivers/net/ethernet/brocade/bna/bfi_cna.h
+++ b/drivers/net/ethernet/brocade/bna/bfi_cna.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfi_enet.h b/drivers/net/ethernet/brocade/bna/bfi_enet.h
index d7be7ea8c7f5..112aadf493b1 100644
--- a/drivers/net/ethernet/brocade/bna/bfi_enet.h
+++ b/drivers/net/ethernet/brocade/bna/bfi_enet.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bfi_reg.h b/drivers/net/ethernet/brocade/bna/bfi_reg.h
index 2835b51eabec..b15ae9e341af 100644
--- a/drivers/net/ethernet/brocade/bna/bfi_reg.h
+++ b/drivers/net/ethernet/brocade/bna/bfi_reg.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bna.h b/drivers/net/ethernet/brocade/bna/bna.h
index 006dcad9a260..50de1532a807 100644
--- a/drivers/net/ethernet/brocade/bna/bna.h
+++ b/drivers/net/ethernet/brocade/bna/bna.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c
index 6d2d4527357c..40107a9bd120 100644
--- a/drivers/net/ethernet/brocade/bna/bna_enet.c
+++ b/drivers/net/ethernet/brocade/bna/bna_enet.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bna_hw_defs.h b/drivers/net/ethernet/brocade/bna/bna_hw_defs.h
index 52b45c9935aa..f335b7115c1b 100644
--- a/drivers/net/ethernet/brocade/bna/bna_hw_defs.h
+++ b/drivers/net/ethernet/brocade/bna/bna_hw_defs.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
index 95bc470ae441..b5ecbfe13ab0 100644
--- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
+++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
   */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h
index c438d032e8bf..666b6922e24d 100644
--- a/drivers/net/ethernet/brocade/bna/bna_types.h
+++ b/drivers/net/ethernet/brocade/bna/bna_types.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index ea5f32ea308a..7767ae6fa1fd 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h
index 46f7b842b39c..492a02d54f14 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.h
+++ b/drivers/net/ethernet/brocade/bna/bnad.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
index 933799be0471..04ad0f2b9677 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index 31032de5843b..b764c9ff9ad1 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/cna.h b/drivers/net/ethernet/brocade/bna/cna.h
index 75f8f1ac9fb7..28d89d0c2297 100644
--- a/drivers/net/ethernet/brocade/bna/cna.h
+++ b/drivers/net/ethernet/brocade/bna/cna.h
@@ -1,14 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2006-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/brocade/bna/cna_fwimg.c b/drivers/net/ethernet/brocade/bna/cna_fwimg.c
index 2e7fb97883dc..824eaef30704 100644
--- a/drivers/net/ethernet/brocade/bna/cna_fwimg.c
+++ b/drivers/net/ethernet/brocade/bna/cna_fwimg.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Linux network driver for QLogic BR-series Converged Network Adapter.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License (GPL) Version 2 as
- * published by the Free Software Foundation
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 /*
  * Copyright (c) 2005-2014 Brocade Communications Systems, Inc.
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index b9984015ca8c..f4b3bd85dfe3 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -1,5 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
-# Atmel device configuration
+# Cadence device configuration
 #
 
 config NET_VENDOR_CADENCE
@@ -12,15 +13,15 @@ config NET_VENDOR_CADENCE
 	  If unsure, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
-	  kernel: saying N will just cause the configurator to skip all
-	  the remaining Atmel network card questions. If you say Y, you will be
+	  kernel: saying N will just cause the configurator to skip all the
+	  remaining Cadence network card questions. If you say Y, you will be
 	  asked for your specific card in the following questions.
 
 if NET_VENDOR_CADENCE
 
 config MACB
 	tristate "Cadence MACB/GEM support"
-	depends on HAS_DMA
+	depends on HAS_DMA && COMMON_CLK
 	select PHYLIB
 	---help---
 	  The Cadence MACB ethernet interface is found on many Atmel AT32 and
@@ -41,7 +42,7 @@ config MACB_USE_HWSTAMP
 
 config MACB_PCI
 	tristate "Cadence PCI MACB/GEM support"
-	depends on MACB && PCI && COMMON_CLK
+	depends on MACB && PCI
 	---help---
 	  This is PCI wrapper for MACB driver.
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 9bbaad9f3d63..03983bd46eef 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Atmel MACB Ethernet Controller driver
  *
  * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef _MACB_H
 #define _MACB_H
@@ -499,7 +496,11 @@
 
 /* Bitfields in TISUBN */
 #define GEM_SUBNSINCR_OFFSET			0
-#define GEM_SUBNSINCR_SIZE			16
+#define GEM_SUBNSINCRL_OFFSET			24
+#define GEM_SUBNSINCRL_SIZE			8
+#define GEM_SUBNSINCRH_OFFSET			0
+#define GEM_SUBNSINCRH_SIZE			16
+#define GEM_SUBNSINCR_SIZE			24
 
 /* Bitfields in TI */
 #define GEM_NSINCR_OFFSET			0
@@ -715,6 +716,8 @@
 		__v; \
 	})
 
+#define MACB_READ_NSR(bp)	macb_readl(bp, NSR)
+
 /* struct macb_dma_desc - Hardware DMA descriptor
  * @addr: DMA address of data buffer
  * @ctrl: Control and status bits
@@ -835,6 +838,9 @@ struct gem_tx_ts {
 /* limit RX checksum offload to TCP and UDP packets */
 #define GEM_RX_CSUM_CHECKED_MASK		2
 
+/* Scaled PPM fraction */
+#define PPM_FRACTION	16
+
 /* struct macb_tx_skb - data about an skb which is being transmitted
  * @skb: skb currently being transmitted, only set for the last buffer
  *       of the frame
@@ -1061,7 +1067,8 @@ struct macb_or_gem_ops {
 	int	(*mog_alloc_rx_buffers)(struct macb *bp);
 	void	(*mog_free_rx_buffers)(struct macb *bp);
 	void	(*mog_init_rings)(struct macb *bp);
-	int	(*mog_rx)(struct macb_queue *queue, int budget);
+	int	(*mog_rx)(struct macb_queue *queue, struct napi_struct *napi,
+			  int budget);
 };
 
 /* MACB-PTP interface: adapt to platform needs. */
@@ -1078,12 +1085,17 @@ struct macb_ptp_info {
 			 struct ifreq *ifr, int cmd);
 };
 
+struct macb_pm_data {
+	u32 scrt2;
+	u32 usrio;
+};
+
 struct macb_config {
 	u32			caps;
 	unsigned int		dma_burst_length;
 	int	(*clk_init)(struct platform_device *pdev, struct clk **pclk,
 			    struct clk **hclk, struct clk **tx_clk,
-			    struct clk **rx_clk);
+			    struct clk **rx_clk, struct clk **tsu_clk);
 	int	(*init)(struct platform_device *pdev);
 	int	jumbo_max_len;
 };
@@ -1163,6 +1175,7 @@ struct macb {
 	struct clk		*hclk;
 	struct clk		*tx_clk;
 	struct clk		*rx_clk;
+	struct clk		*tsu_clk;
 	struct net_device	*dev;
 	union {
 		struct macb_stats	macb;
@@ -1217,6 +1230,8 @@ struct macb {
 	int	tx_bd_rd_prefetch;
 
 	u32	rx_intr_mask;
+
+	struct macb_pm_data pm_data;
 };
 
 #ifdef CONFIG_MACB_USE_HWSTAMP
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 2b2882615e8b..5ca17e62dc3e 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1,15 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Cadence MACB/GEM Ethernet Controller driver
  *
  * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/crc32.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -36,8 +34,17 @@
 #include <linux/ip.h>
 #include <linux/udp.h>
 #include <linux/tcp.h>
+#include <linux/iopoll.h>
+#include <linux/pm_runtime.h>
 #include "macb.h"
 
+/* This structure is only used for MACB on SiFive FU540 devices */
+struct sifive_fu540_macb_mgmt {
+	void __iomem *reg;
+	unsigned long rate;
+	struct clk_hw hw;
+};
+
 #define MACB_RX_BUFFER_SIZE	128
 #define RX_BUFFER_MULTIPLE	64  /* bytes */
 
@@ -79,6 +86,10 @@
  */
 #define MACB_HALT_TIMEOUT	1230
 
+#define MACB_PM_TIMEOUT  100 /* ms */
+
+#define MACB_MDIO_TIMEOUT	1000000 /* in usecs */
+
 /* DMA buffer descriptor might be different size
  * depends on hardware configuration:
  *
@@ -279,34 +290,22 @@ static void macb_set_hwaddr(struct macb *bp)
 
 static void macb_get_hwaddr(struct macb *bp)
 {
-	struct macb_platform_data *pdata;
 	u32 bottom;
 	u16 top;
 	u8 addr[6];
 	int i;
 
-	pdata = dev_get_platdata(&bp->pdev->dev);
-
 	/* Check all 4 address register for valid address */
 	for (i = 0; i < 4; i++) {
 		bottom = macb_or_gem_readl(bp, SA1B + i * 8);
 		top = macb_or_gem_readl(bp, SA1T + i * 8);
 
-		if (pdata && pdata->rev_eth_addr) {
-			addr[5] = bottom & 0xff;
-			addr[4] = (bottom >> 8) & 0xff;
-			addr[3] = (bottom >> 16) & 0xff;
-			addr[2] = (bottom >> 24) & 0xff;
-			addr[1] = top & 0xff;
-			addr[0] = (top & 0xff00) >> 8;
-		} else {
-			addr[0] = bottom & 0xff;
-			addr[1] = (bottom >> 8) & 0xff;
-			addr[2] = (bottom >> 16) & 0xff;
-			addr[3] = (bottom >> 24) & 0xff;
-			addr[4] = top & 0xff;
-			addr[5] = (top >> 8) & 0xff;
-		}
+		addr[0] = bottom & 0xff;
+		addr[1] = (bottom >> 8) & 0xff;
+		addr[2] = (bottom >> 16) & 0xff;
+		addr[3] = (bottom >> 24) & 0xff;
+		addr[4] = top & 0xff;
+		addr[5] = (top >> 8) & 0xff;
 
 		if (is_valid_ether_addr(addr)) {
 			memcpy(bp->dev->dev_addr, addr, sizeof(addr));
@@ -318,10 +317,26 @@ static void macb_get_hwaddr(struct macb *bp)
 	eth_hw_addr_random(bp->dev);
 }
 
+static int macb_mdio_wait_for_idle(struct macb *bp)
+{
+	u32 val;
+
+	return readx_poll_timeout(MACB_READ_NSR, bp, val, val & MACB_BIT(IDLE),
+				  1, MACB_MDIO_TIMEOUT);
+}
+
 static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct macb *bp = bus->priv;
-	int value;
+	int status;
+
+	status = pm_runtime_get_sync(&bp->pdev->dev);
+	if (status < 0)
+		goto mdio_pm_exit;
+
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_read_exit;
 
 	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_SOF)
 			      | MACB_BF(RW, MACB_MAN_READ)
@@ -329,19 +344,32 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 			      | MACB_BF(REGA, regnum)
 			      | MACB_BF(CODE, MACB_MAN_CODE)));
 
-	/* wait for end of transfer */
-	while (!MACB_BFEXT(IDLE, macb_readl(bp, NSR)))
-		cpu_relax();
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_read_exit;
 
-	value = MACB_BFEXT(DATA, macb_readl(bp, MAN));
+	status = MACB_BFEXT(DATA, macb_readl(bp, MAN));
 
-	return value;
+mdio_read_exit:
+	pm_runtime_mark_last_busy(&bp->pdev->dev);
+	pm_runtime_put_autosuspend(&bp->pdev->dev);
+mdio_pm_exit:
+	return status;
 }
 
 static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			   u16 value)
 {
 	struct macb *bp = bus->priv;
+	int status;
+
+	status = pm_runtime_get_sync(&bp->pdev->dev);
+	if (status < 0)
+		goto mdio_pm_exit;
+
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_write_exit;
 
 	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_SOF)
 			      | MACB_BF(RW, MACB_MAN_WRITE)
@@ -350,11 +378,15 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			      | MACB_BF(CODE, MACB_MAN_CODE)
 			      | MACB_BF(DATA, value)));
 
-	/* wait for end of transfer */
-	while (!MACB_BFEXT(IDLE, macb_readl(bp, NSR)))
-		cpu_relax();
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_write_exit;
 
-	return 0;
+mdio_write_exit:
+	pm_runtime_mark_last_busy(&bp->pdev->dev);
+	pm_runtime_put_autosuspend(&bp->pdev->dev);
+mdio_pm_exit:
+	return status;
 }
 
 /**
@@ -471,12 +503,10 @@ static void macb_handle_link_change(struct net_device *dev)
 static int macb_mii_probe(struct net_device *dev)
 {
 	struct macb *bp = netdev_priv(dev);
-	struct macb_platform_data *pdata;
 	struct phy_device *phydev;
 	struct device_node *np;
-	int phy_irq, ret, i;
+	int ret, i;
 
-	pdata = dev_get_platdata(&bp->pdev->dev);
 	np = bp->pdev->dev.of_node;
 	ret = 0;
 
@@ -491,8 +521,6 @@ static int macb_mii_probe(struct net_device *dev)
 			 */
 			if (!bp->phy_node && !phy_find_first(bp->mii_bus)) {
 				for (i = 0; i < PHY_MAX_ADDR; i++) {
-					struct phy_device *phydev;
-
 					phydev = mdiobus_scan(bp->mii_bus, i);
 					if (IS_ERR(phydev) &&
 					    PTR_ERR(phydev) != -ENODEV) {
@@ -520,19 +548,6 @@ static int macb_mii_probe(struct net_device *dev)
 			return -ENXIO;
 		}
 
-		if (pdata) {
-			if (gpio_is_valid(pdata->phy_irq_pin)) {
-				ret = devm_gpio_request(&bp->pdev->dev,
-							pdata->phy_irq_pin, "phy int");
-				if (!ret) {
-					phy_irq = gpio_to_irq(pdata->phy_irq_pin);
-					phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
-				}
-			} else {
-				phydev->irq = PHY_POLL;
-			}
-		}
-
 		/* attach the mac to the phy */
 		ret = phy_connect_direct(dev, phydev, &macb_handle_link_change,
 					 bp->phy_interface);
@@ -561,7 +576,6 @@ static int macb_mii_probe(struct net_device *dev)
 
 static int macb_mii_init(struct macb *bp)
 {
-	struct macb_platform_data *pdata;
 	struct device_node *np;
 	int err = -ENXIO;
 
@@ -581,7 +595,6 @@ static int macb_mii_init(struct macb *bp)
 		 bp->pdev->name, bp->pdev->id);
 	bp->mii_bus->priv = bp;
 	bp->mii_bus->parent = &bp->pdev->dev;
-	pdata = dev_get_platdata(&bp->pdev->dev);
 
 	dev_set_drvdata(&bp->dev->dev, bp->mii_bus);
 
@@ -595,9 +608,6 @@ static int macb_mii_init(struct macb *bp)
 
 		err = mdiobus_register(bp->mii_bus);
 	} else {
-		if (pdata)
-			bp->mii_bus->phy_mask = pdata->phy_mask;
-
 		err = of_mdiobus_register(bp->mii_bus, np);
 	}
 
@@ -859,7 +869,9 @@ static void macb_tx_interrupt(struct macb_queue *queue)
 
 			/* First, update TX stats if needed */
 			if (skb) {
-				if (gem_ptp_do_txstamp(queue, skb, desc) == 0) {
+				if (unlikely(skb_shinfo(skb)->tx_flags &
+					     SKBTX_HW_TSTAMP) &&
+				    gem_ptp_do_txstamp(queue, skb, desc) == 0) {
 					/* skb now belongs to timestamp buffer
 					 * and will be removed later
 					 */
@@ -977,7 +989,8 @@ static void discard_partial_frame(struct macb_queue *queue, unsigned int begin,
 	 */
 }
 
-static int gem_rx(struct macb_queue *queue, int budget)
+static int gem_rx(struct macb_queue *queue, struct napi_struct *napi,
+		  int budget)
 {
 	struct macb *bp = queue->bp;
 	unsigned int		len;
@@ -1059,7 +1072,7 @@ static int gem_rx(struct macb_queue *queue, int budget)
 			       skb->data, 32, true);
 #endif
 
-		netif_receive_skb(skb);
+		napi_gro_receive(napi, skb);
 	}
 
 	gem_rx_refill(queue);
@@ -1067,8 +1080,8 @@ static int gem_rx(struct macb_queue *queue, int budget)
 	return count;
 }
 
-static int macb_rx_frame(struct macb_queue *queue, unsigned int first_frag,
-			 unsigned int last_frag)
+static int macb_rx_frame(struct macb_queue *queue, struct napi_struct *napi,
+			 unsigned int first_frag, unsigned int last_frag)
 {
 	unsigned int len;
 	unsigned int frag;
@@ -1144,7 +1157,7 @@ static int macb_rx_frame(struct macb_queue *queue, unsigned int first_frag,
 	bp->dev->stats.rx_bytes += skb->len;
 	netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n",
 		    skb->len, skb->csum);
-	netif_receive_skb(skb);
+	napi_gro_receive(napi, skb);
 
 	return 0;
 }
@@ -1167,7 +1180,8 @@ static inline void macb_init_rx_ring(struct macb_queue *queue)
 	queue->rx_tail = 0;
 }
 
-static int macb_rx(struct macb_queue *queue, int budget)
+static int macb_rx(struct macb_queue *queue, struct napi_struct *napi,
+		   int budget)
 {
 	struct macb *bp = queue->bp;
 	bool reset_rx_queue = false;
@@ -1204,7 +1218,7 @@ static int macb_rx(struct macb_queue *queue, int budget)
 				continue;
 			}
 
-			dropped = macb_rx_frame(queue, first_frag, tail);
+			dropped = macb_rx_frame(queue, napi, first_frag, tail);
 			first_frag = -1;
 			if (unlikely(dropped < 0)) {
 				reset_rx_queue = true;
@@ -1258,7 +1272,7 @@ static int macb_poll(struct napi_struct *napi, int budget)
 	netdev_vdbg(bp->dev, "poll: status = %08lx, budget = %d\n",
 		    (unsigned long)status, budget);
 
-	work_done = bp->macbgem_ops.mog_rx(queue, budget);
+	work_done = bp->macbgem_ops.mog_rx(queue, napi, budget);
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
 
@@ -1734,7 +1748,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
 		if (!nskb)
 			return -ENOMEM;
 
-		dev_kfree_skb_any(*skb);
+		dev_consume_skb_any(*skb);
 		*skb = nskb;
 	}
 
@@ -2397,12 +2411,18 @@ static int macb_open(struct net_device *dev)
 
 	netdev_dbg(bp->dev, "open\n");
 
+	err = pm_runtime_get_sync(&bp->pdev->dev);
+	if (err < 0)
+		goto pm_exit;
+
 	/* carrier starts down */
 	netif_carrier_off(dev);
 
 	/* if the phy is not yet register, retry later*/
-	if (!dev->phydev)
-		return -EAGAIN;
+	if (!dev->phydev) {
+		err = -EAGAIN;
+		goto pm_exit;
+	}
 
 	/* RX buffers initialization */
 	macb_init_rx_buffer_size(bp, bufsz);
@@ -2411,15 +2431,15 @@ static int macb_open(struct net_device *dev)
 	if (err) {
 		netdev_err(dev, "Unable to allocate DMA memory (error %d)\n",
 			   err);
-		return err;
+		goto pm_exit;
 	}
 
-	bp->macbgem_ops.mog_init_rings(bp);
-	macb_init_hw(bp);
-
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
 		napi_enable(&queue->napi);
 
+	bp->macbgem_ops.mog_init_rings(bp);
+	macb_init_hw(bp);
+
 	/* schedule a link state check */
 	phy_start(dev->phydev);
 
@@ -2428,6 +2448,11 @@ static int macb_open(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+pm_exit:
+	if (err) {
+		pm_runtime_put_sync(&bp->pdev->dev);
+		return err;
+	}
 	return 0;
 }
 
@@ -2456,6 +2481,8 @@ static int macb_close(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_remove(dev);
 
+	pm_runtime_put(&bp->pdev->dev);
+
 	return 0;
 }
 
@@ -2829,10 +2856,14 @@ static int macb_get_ts_info(struct net_device *netdev,
 
 static void gem_enable_flow_filters(struct macb *bp, bool enable)
 {
+	struct net_device *netdev = bp->dev;
 	struct ethtool_rx_fs_item *item;
 	u32 t2_scr;
 	int num_t2_scr;
 
+	if (!(netdev->features & NETIF_F_NTUPLE))
+		return;
+
 	num_t2_scr = GEM_BFEXT(T2SCR, gem_readl(bp, DCFG8));
 
 	list_for_each_entry(item, &bp->rx_fs_list.list, list) {
@@ -2992,8 +3023,7 @@ static int gem_add_flow_filter(struct net_device *netdev,
 	gem_prog_cmp_regs(bp, fs);
 	bp->rx_fs_list.count++;
 	/* enable filtering if NTUPLE on */
-	if (netdev->features & NETIF_F_NTUPLE)
-		gem_enable_flow_filters(bp, 1);
+	gem_enable_flow_filters(bp, 1);
 
 	spin_unlock_irqrestore(&bp->rx_fs_lock, flags);
 	return 0;
@@ -3181,6 +3211,50 @@ static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	}
 }
 
+static inline void macb_set_txcsum_feature(struct macb *bp,
+					   netdev_features_t features)
+{
+	u32 val;
+
+	if (!macb_is_gem(bp))
+		return;
+
+	val = gem_readl(bp, DMACFG);
+	if (features & NETIF_F_HW_CSUM)
+		val |= GEM_BIT(TXCOEN);
+	else
+		val &= ~GEM_BIT(TXCOEN);
+
+	gem_writel(bp, DMACFG, val);
+}
+
+static inline void macb_set_rxcsum_feature(struct macb *bp,
+					   netdev_features_t features)
+{
+	struct net_device *netdev = bp->dev;
+	u32 val;
+
+	if (!macb_is_gem(bp))
+		return;
+
+	val = gem_readl(bp, NCFGR);
+	if ((features & NETIF_F_RXCSUM) && !(netdev->flags & IFF_PROMISC))
+		val |= GEM_BIT(RXCOEN);
+	else
+		val &= ~GEM_BIT(RXCOEN);
+
+	gem_writel(bp, NCFGR, val);
+}
+
+static inline void macb_set_rxflow_feature(struct macb *bp,
+					   netdev_features_t features)
+{
+	if (!macb_is_gem(bp))
+		return;
+
+	gem_enable_flow_filters(bp, !!(features & NETIF_F_NTUPLE));
+}
+
 static int macb_set_features(struct net_device *netdev,
 			     netdev_features_t features)
 {
@@ -3188,39 +3262,35 @@ static int macb_set_features(struct net_device *netdev,
 	netdev_features_t changed = features ^ netdev->features;
 
 	/* TX checksum offload */
-	if ((changed & NETIF_F_HW_CSUM) && macb_is_gem(bp)) {
-		u32 dmacfg;
-
-		dmacfg = gem_readl(bp, DMACFG);
-		if (features & NETIF_F_HW_CSUM)
-			dmacfg |= GEM_BIT(TXCOEN);
-		else
-			dmacfg &= ~GEM_BIT(TXCOEN);
-		gem_writel(bp, DMACFG, dmacfg);
-	}
+	if (changed & NETIF_F_HW_CSUM)
+		macb_set_txcsum_feature(bp, features);
 
 	/* RX checksum offload */
-	if ((changed & NETIF_F_RXCSUM) && macb_is_gem(bp)) {
-		u32 netcfg;
-
-		netcfg = gem_readl(bp, NCFGR);
-		if (features & NETIF_F_RXCSUM &&
-		    !(netdev->flags & IFF_PROMISC))
-			netcfg |= GEM_BIT(RXCOEN);
-		else
-			netcfg &= ~GEM_BIT(RXCOEN);
-		gem_writel(bp, NCFGR, netcfg);
-	}
+	if (changed & NETIF_F_RXCSUM)
+		macb_set_rxcsum_feature(bp, features);
 
 	/* RX Flow Filters */
-	if ((changed & NETIF_F_NTUPLE) && macb_is_gem(bp)) {
-		bool turn_on = features & NETIF_F_NTUPLE;
+	if (changed & NETIF_F_NTUPLE)
+		macb_set_rxflow_feature(bp, features);
 
-		gem_enable_flow_filters(bp, turn_on);
-	}
 	return 0;
 }
 
+static void macb_restore_features(struct macb *bp)
+{
+	struct net_device *netdev = bp->dev;
+	netdev_features_t features = netdev->features;
+
+	/* TX checksum offload */
+	macb_set_txcsum_feature(bp, features);
+
+	/* RX checksum offload */
+	macb_set_rxcsum_feature(bp, features);
+
+	/* RX Flow Filters */
+	macb_set_rxflow_feature(bp, features);
+}
+
 static const struct net_device_ops macb_netdev_ops = {
 	.ndo_open		= macb_open,
 	.ndo_stop		= macb_close,
@@ -3304,7 +3374,7 @@ static void macb_probe_queues(void __iomem *mem,
 
 static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 			 struct clk **hclk, struct clk **tx_clk,
-			 struct clk **rx_clk)
+			 struct clk **rx_clk, struct clk **tsu_clk)
 {
 	struct macb_platform_data *pdata;
 	int err;
@@ -3318,15 +3388,21 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 		*hclk = devm_clk_get(&pdev->dev, "hclk");
 	}
 
-	if (IS_ERR(*pclk)) {
+	if (IS_ERR_OR_NULL(*pclk)) {
 		err = PTR_ERR(*pclk);
-		dev_err(&pdev->dev, "failed to get macb_clk (%u)\n", err);
+		if (!err)
+			err = -ENODEV;
+
+		dev_err(&pdev->dev, "failed to get macb_clk (%d)\n", err);
 		return err;
 	}
 
-	if (IS_ERR(*hclk)) {
+	if (IS_ERR_OR_NULL(*hclk)) {
 		err = PTR_ERR(*hclk);
-		dev_err(&pdev->dev, "failed to get hclk (%u)\n", err);
+		if (!err)
+			err = -ENODEV;
+
+		dev_err(&pdev->dev, "failed to get hclk (%d)\n", err);
 		return err;
 	}
 
@@ -3338,32 +3414,45 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 	if (IS_ERR(*rx_clk))
 		*rx_clk = NULL;
 
+	*tsu_clk = devm_clk_get(&pdev->dev, "tsu_clk");
+	if (IS_ERR(*tsu_clk))
+		*tsu_clk = NULL;
+
 	err = clk_prepare_enable(*pclk);
 	if (err) {
-		dev_err(&pdev->dev, "failed to enable pclk (%u)\n", err);
+		dev_err(&pdev->dev, "failed to enable pclk (%d)\n", err);
 		return err;
 	}
 
 	err = clk_prepare_enable(*hclk);
 	if (err) {
-		dev_err(&pdev->dev, "failed to enable hclk (%u)\n", err);
+		dev_err(&pdev->dev, "failed to enable hclk (%d)\n", err);
 		goto err_disable_pclk;
 	}
 
 	err = clk_prepare_enable(*tx_clk);
 	if (err) {
-		dev_err(&pdev->dev, "failed to enable tx_clk (%u)\n", err);
+		dev_err(&pdev->dev, "failed to enable tx_clk (%d)\n", err);
 		goto err_disable_hclk;
 	}
 
 	err = clk_prepare_enable(*rx_clk);
 	if (err) {
-		dev_err(&pdev->dev, "failed to enable rx_clk (%u)\n", err);
+		dev_err(&pdev->dev, "failed to enable rx_clk (%d)\n", err);
 		goto err_disable_txclk;
 	}
 
+	err = clk_prepare_enable(*tsu_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable tsu_clk (%d)\n", err);
+		goto err_disable_rxclk;
+	}
+
 	return 0;
 
+err_disable_rxclk:
+	clk_disable_unprepare(*rx_clk);
+
 err_disable_txclk:
 	clk_disable_unprepare(*tx_clk);
 
@@ -3398,7 +3487,7 @@ static int macb_init(struct platform_device *pdev)
 
 		queue = &bp->queues[q];
 		queue->bp = bp;
-		netif_napi_add(dev, &queue->napi, macb_poll, 64);
+		netif_napi_add(dev, &queue->napi, macb_poll, NAPI_POLL_WEIGHT);
 		if (hw_q) {
 			queue->ISR  = GEM_ISR(hw_q - 1);
 			queue->IER  = GEM_IER(hw_q - 1);
@@ -3537,6 +3626,8 @@ static int macb_init(struct platform_device *pdev)
 /* max number of receive buffers */
 #define AT91ETHER_MAX_RX_DESCR	9
 
+static struct sifive_fu540_macb_mgmt *mgmt;
+
 /* Initialize and start the Receiver and Transmit subsystems */
 static int at91ether_start(struct net_device *dev)
 {
@@ -3673,9 +3764,9 @@ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb,
 		/* Store packet information (to free when Tx completed) */
 		lp->skb = skb;
 		lp->skb_length = skb->len;
-		lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len,
-							DMA_TO_DEVICE);
-		if (dma_mapping_error(NULL, lp->skb_physaddr)) {
+		lp->skb_physaddr = dma_map_single(&lp->pdev->dev, skb->data,
+						  skb->len, DMA_TO_DEVICE);
+		if (dma_mapping_error(&lp->pdev->dev, lp->skb_physaddr)) {
 			dev_kfree_skb_any(skb);
 			dev->stats.tx_dropped++;
 			netdev_err(dev, "%s: DMA mapping error\n", __func__);
@@ -3763,9 +3854,9 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id)
 			dev->stats.tx_errors++;
 
 		if (lp->skb) {
-			dev_kfree_skb_irq(lp->skb);
+			dev_consume_skb_irq(lp->skb);
 			lp->skb = NULL;
-			dma_unmap_single(NULL, lp->skb_physaddr,
+			dma_unmap_single(&lp->pdev->dev, lp->skb_physaddr,
 					 lp->skb_length, DMA_TO_DEVICE);
 			dev->stats.tx_packets++;
 			dev->stats.tx_bytes += lp->skb_length;
@@ -3814,13 +3905,14 @@ static const struct net_device_ops at91ether_netdev_ops = {
 
 static int at91ether_clk_init(struct platform_device *pdev, struct clk **pclk,
 			      struct clk **hclk, struct clk **tx_clk,
-			      struct clk **rx_clk)
+			      struct clk **rx_clk, struct clk **tsu_clk)
 {
 	int err;
 
 	*hclk = NULL;
 	*tx_clk = NULL;
 	*rx_clk = NULL;
+	*tsu_clk = NULL;
 
 	*pclk = devm_clk_get(&pdev->dev, "ether_clk");
 	if (IS_ERR(*pclk))
@@ -3828,7 +3920,7 @@ static int at91ether_clk_init(struct platform_device *pdev, struct clk **pclk,
 
 	err = clk_prepare_enable(*pclk);
 	if (err) {
-		dev_err(&pdev->dev, "failed to enable pclk (%u)\n", err);
+		dev_err(&pdev->dev, "failed to enable pclk (%d)\n", err);
 		return err;
 	}
 
@@ -3863,6 +3955,116 @@ static int at91ether_init(struct platform_device *pdev)
 	return 0;
 }
 
+static unsigned long fu540_macb_tx_recalc_rate(struct clk_hw *hw,
+					       unsigned long parent_rate)
+{
+	return mgmt->rate;
+}
+
+static long fu540_macb_tx_round_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long *parent_rate)
+{
+	if (WARN_ON(rate < 2500000))
+		return 2500000;
+	else if (rate == 2500000)
+		return 2500000;
+	else if (WARN_ON(rate < 13750000))
+		return 2500000;
+	else if (WARN_ON(rate < 25000000))
+		return 25000000;
+	else if (rate == 25000000)
+		return 25000000;
+	else if (WARN_ON(rate < 75000000))
+		return 25000000;
+	else if (WARN_ON(rate < 125000000))
+		return 125000000;
+	else if (rate == 125000000)
+		return 125000000;
+
+	WARN_ON(rate > 125000000);
+
+	return 125000000;
+}
+
+static int fu540_macb_tx_set_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long parent_rate)
+{
+	rate = fu540_macb_tx_round_rate(hw, rate, &parent_rate);
+	if (rate != 125000000)
+		iowrite32(1, mgmt->reg);
+	else
+		iowrite32(0, mgmt->reg);
+	mgmt->rate = rate;
+
+	return 0;
+}
+
+static const struct clk_ops fu540_c000_ops = {
+	.recalc_rate = fu540_macb_tx_recalc_rate,
+	.round_rate = fu540_macb_tx_round_rate,
+	.set_rate = fu540_macb_tx_set_rate,
+};
+
+static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk,
+			       struct clk **hclk, struct clk **tx_clk,
+			       struct clk **rx_clk, struct clk **tsu_clk)
+{
+	struct clk_init_data init;
+	int err = 0;
+
+	err = macb_clk_init(pdev, pclk, hclk, tx_clk, rx_clk, tsu_clk);
+	if (err)
+		return err;
+
+	mgmt = devm_kzalloc(&pdev->dev, sizeof(*mgmt), GFP_KERNEL);
+	if (!mgmt)
+		return -ENOMEM;
+
+	init.name = "sifive-gemgxl-mgmt";
+	init.ops = &fu540_c000_ops;
+	init.flags = 0;
+	init.num_parents = 0;
+
+	mgmt->rate = 0;
+	mgmt->hw.init = &init;
+
+	*tx_clk = clk_register(NULL, &mgmt->hw);
+	if (IS_ERR(*tx_clk))
+		return PTR_ERR(*tx_clk);
+
+	err = clk_prepare_enable(*tx_clk);
+	if (err)
+		dev_err(&pdev->dev, "failed to enable tx_clk (%u)\n", err);
+	else
+		dev_info(&pdev->dev, "Registered clk switch '%s'\n", init.name);
+
+	return 0;
+}
+
+static int fu540_c000_init(struct platform_device *pdev)
+{
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res)
+		return -ENODEV;
+
+	mgmt->reg = ioremap(res->start, resource_size(res));
+	if (!mgmt->reg)
+		return -ENOMEM;
+
+	return macb_init(pdev);
+}
+
+static const struct macb_config fu540_c000_config = {
+	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO |
+		MACB_CAPS_GEM_HAS_PTP,
+	.dma_burst_length = 16,
+	.clk_init = fu540_c000_clk_init,
+	.init = fu540_c000_init,
+	.jumbo_max_len = 10240,
+};
+
 static const struct macb_config at91sam9260_config = {
 	.caps = MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII,
 	.clk_init = macb_clk_init,
@@ -3943,6 +4145,7 @@ static const struct of_device_id macb_dt_ids[] = {
 	{ .compatible = "cdns,np4-macb", .data = &np4_config },
 	{ .compatible = "cdns,pc302-gem", .data = &pc302gem_config },
 	{ .compatible = "cdns,gem", .data = &pc302gem_config },
+	{ .compatible = "cdns,sam9x60-macb", .data = &at91sam9260_config },
 	{ .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config },
 	{ .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config },
 	{ .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config },
@@ -3951,6 +4154,7 @@ static const struct of_device_id macb_dt_ids[] = {
 	{ .compatible = "cdns,emac", .data = &emac_config },
 	{ .compatible = "cdns,zynqmp-gem", .data = &zynqmp_config},
 	{ .compatible = "cdns,zynq-gem", .data = &zynq_config },
+	{ .compatible = "sifive,fu540-macb", .data = &fu540_c000_config },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, macb_dt_ids);
@@ -3970,13 +4174,13 @@ static int macb_probe(struct platform_device *pdev)
 {
 	const struct macb_config *macb_config = &default_gem_config;
 	int (*clk_init)(struct platform_device *, struct clk **,
-			struct clk **, struct clk **,  struct clk **)
-					      = macb_config->clk_init;
+			struct clk **, struct clk **,  struct clk **,
+			struct clk **) = macb_config->clk_init;
 	int (*init)(struct platform_device *) = macb_config->init;
 	struct device_node *np = pdev->dev.of_node;
 	struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL;
+	struct clk *tsu_clk = NULL;
 	unsigned int queue_mask, num_queues;
-	struct macb_platform_data *pdata;
 	bool native_io;
 	struct phy_device *phydev;
 	struct net_device *dev;
@@ -4002,10 +4206,15 @@ static int macb_probe(struct platform_device *pdev)
 		}
 	}
 
-	err = clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk);
+	err = clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk, &tsu_clk);
 	if (err)
 		return err;
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, MACB_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 	native_io = hw_is_native_io(mem);
 
 	macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
@@ -4039,6 +4248,7 @@ static int macb_probe(struct platform_device *pdev)
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
 	bp->rx_clk = rx_clk;
+	bp->tsu_clk = tsu_clk;
 	if (macb_config)
 		bp->jumbo_max_len = macb_config->jumbo_max_len;
 
@@ -4090,27 +4300,21 @@ static int macb_probe(struct platform_device *pdev)
 		bp->rx_intr_mask |= MACB_BIT(RXUBR);
 
 	mac = of_get_mac_address(np);
-	if (mac) {
+	if (PTR_ERR(mac) == -EPROBE_DEFER) {
+		err = -EPROBE_DEFER;
+		goto err_out_free_netdev;
+	} else if (!IS_ERR_OR_NULL(mac)) {
 		ether_addr_copy(bp->dev->dev_addr, mac);
 	} else {
-		err = nvmem_get_mac_address(&pdev->dev, bp->dev->dev_addr);
-		if (err) {
-			if (err == -EPROBE_DEFER)
-				goto err_out_free_netdev;
-			macb_get_hwaddr(bp);
-		}
+		macb_get_hwaddr(bp);
 	}
 
 	err = of_get_phy_mode(np);
-	if (err < 0) {
-		pdata = dev_get_platdata(&pdev->dev);
-		if (pdata && pdata->is_rmii)
-			bp->phy_interface = PHY_INTERFACE_MODE_RMII;
-		else
-			bp->phy_interface = PHY_INTERFACE_MODE_MII;
-	} else {
+	if (err < 0)
+		/* not found in DT, MII by default */
+		bp->phy_interface = PHY_INTERFACE_MODE_MII;
+	else
 		bp->phy_interface = err;
-	}
 
 	/* IP specific init */
 	err = init(pdev);
@@ -4140,6 +4344,9 @@ static int macb_probe(struct platform_device *pdev)
 		    macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID),
 		    dev->base_addr, dev->irq, dev->dev_addr);
 
+	pm_runtime_mark_last_busy(&bp->pdev->dev);
+	pm_runtime_put_autosuspend(&bp->pdev->dev);
+
 	return 0;
 
 err_out_unregister_mdio:
@@ -4155,9 +4362,14 @@ err_out_free_netdev:
 
 err_disable_clocks:
 	clk_disable_unprepare(tx_clk);
+	clk_unregister(tx_clk);
 	clk_disable_unprepare(hclk);
 	clk_disable_unprepare(pclk);
 	clk_disable_unprepare(rx_clk);
+	clk_disable_unprepare(tsu_clk);
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
 
 	return err;
 }
@@ -4181,10 +4393,17 @@ static int macb_remove(struct platform_device *pdev)
 		mdiobus_free(bp->mii_bus);
 
 		unregister_netdev(dev);
-		clk_disable_unprepare(bp->tx_clk);
-		clk_disable_unprepare(bp->hclk);
-		clk_disable_unprepare(bp->pclk);
-		clk_disable_unprepare(bp->rx_clk);
+		pm_runtime_disable(&pdev->dev);
+		pm_runtime_dont_use_autosuspend(&pdev->dev);
+		if (!pm_runtime_suspended(&pdev->dev)) {
+			clk_disable_unprepare(bp->tx_clk);
+			clk_unregister(bp->tx_clk);
+			clk_disable_unprepare(bp->hclk);
+			clk_disable_unprepare(bp->pclk);
+			clk_disable_unprepare(bp->rx_clk);
+			clk_disable_unprepare(bp->tsu_clk);
+			pm_runtime_set_suspended(&pdev->dev);
+		}
 		of_node_put(bp->phy_node);
 		free_netdev(dev);
 	}
@@ -4196,21 +4415,42 @@ static int __maybe_unused macb_suspend(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct macb *bp = netdev_priv(netdev);
+	struct macb_queue *queue = bp->queues;
+	unsigned long flags;
+	unsigned int q;
+
+	if (!netif_running(netdev))
+		return 0;
 
-	netif_carrier_off(netdev);
-	netif_device_detach(netdev);
 
 	if (bp->wol & MACB_WOL_ENABLED) {
 		macb_writel(bp, IER, MACB_BIT(WOL));
 		macb_writel(bp, WOL, MACB_BIT(MAG));
 		enable_irq_wake(bp->queues[0].irq);
+		netif_device_detach(netdev);
 	} else {
-		clk_disable_unprepare(bp->tx_clk);
-		clk_disable_unprepare(bp->hclk);
-		clk_disable_unprepare(bp->pclk);
-		clk_disable_unprepare(bp->rx_clk);
+		netif_device_detach(netdev);
+		for (q = 0, queue = bp->queues; q < bp->num_queues;
+		     ++q, ++queue)
+			napi_disable(&queue->napi);
+		phy_stop(netdev->phydev);
+		phy_suspend(netdev->phydev);
+		spin_lock_irqsave(&bp->lock, flags);
+		macb_reset_hw(bp);
+		spin_unlock_irqrestore(&bp->lock, flags);
+
+		if (!(bp->caps & MACB_CAPS_USRIO_DISABLED))
+			bp->pm_data.usrio = macb_or_gem_readl(bp, USRIO);
+
+		if (netdev->hw_features & NETIF_F_NTUPLE)
+			bp->pm_data.scrt2 = gem_readl_n(bp, ETHT, SCRT2_ETHT);
 	}
 
+	netif_carrier_off(netdev);
+	if (bp->ptp_info)
+		bp->ptp_info->ptp_remove(netdev);
+	pm_runtime_force_suspend(dev);
+
 	return 0;
 }
 
@@ -4218,24 +4458,82 @@ static int __maybe_unused macb_resume(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct macb *bp = netdev_priv(netdev);
+	struct macb_queue *queue = bp->queues;
+	unsigned int q;
+
+	if (!netif_running(netdev))
+		return 0;
+
+	pm_runtime_force_resume(dev);
 
 	if (bp->wol & MACB_WOL_ENABLED) {
 		macb_writel(bp, IDR, MACB_BIT(WOL));
 		macb_writel(bp, WOL, 0);
 		disable_irq_wake(bp->queues[0].irq);
 	} else {
+		macb_writel(bp, NCR, MACB_BIT(MPE));
+
+		if (netdev->hw_features & NETIF_F_NTUPLE)
+			gem_writel_n(bp, ETHT, SCRT2_ETHT, bp->pm_data.scrt2);
+
+		if (!(bp->caps & MACB_CAPS_USRIO_DISABLED))
+			macb_or_gem_writel(bp, USRIO, bp->pm_data.usrio);
+
+		for (q = 0, queue = bp->queues; q < bp->num_queues;
+		     ++q, ++queue)
+			napi_enable(&queue->napi);
+		phy_resume(netdev->phydev);
+		phy_init_hw(netdev->phydev);
+		phy_start(netdev->phydev);
+	}
+
+	bp->macbgem_ops.mog_init_rings(bp);
+	macb_init_hw(bp);
+	macb_set_rx_mode(netdev);
+	macb_restore_features(bp);
+	netif_device_attach(netdev);
+	if (bp->ptp_info)
+		bp->ptp_info->ptp_init(netdev);
+
+	return 0;
+}
+
+static int __maybe_unused macb_runtime_suspend(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+	struct macb *bp = netdev_priv(netdev);
+
+	if (!(device_may_wakeup(&bp->dev->dev))) {
+		clk_disable_unprepare(bp->tx_clk);
+		clk_disable_unprepare(bp->hclk);
+		clk_disable_unprepare(bp->pclk);
+		clk_disable_unprepare(bp->rx_clk);
+	}
+	clk_disable_unprepare(bp->tsu_clk);
+
+	return 0;
+}
+
+static int __maybe_unused macb_runtime_resume(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+	struct macb *bp = netdev_priv(netdev);
+
+	if (!(device_may_wakeup(&bp->dev->dev))) {
 		clk_prepare_enable(bp->pclk);
 		clk_prepare_enable(bp->hclk);
 		clk_prepare_enable(bp->tx_clk);
 		clk_prepare_enable(bp->rx_clk);
 	}
-
-	netif_device_attach(netdev);
+	clk_prepare_enable(bp->tsu_clk);
 
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(macb_pm_ops, macb_suspend, macb_resume);
+static const struct dev_pm_ops macb_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(macb_suspend, macb_resume)
+	SET_RUNTIME_PM_OPS(macb_runtime_suspend, macb_runtime_resume, NULL)
+};
 
 static struct platform_driver macb_driver = {
 	.probe		= macb_probe,
diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index 248a8fc45069..617b3b728dd0 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /**
  * Cadence GEM PCI wrapper.
  *
@@ -5,18 +6,6 @@
  *
  * Authors: Rafal Ozieblo <rafalo@cadence.com>
  *	    Bartosz Folta <bfolta@cadence.com>
- *
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2  of
- * the License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/clk.h>
diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index a6dc47edc4cf..43a3f0dbf857 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /**
  * 1588 PTP support for Cadence GEM device.
  *
@@ -5,18 +6,6 @@
  *
  * Authors: Rafal Ozieblo <rafalo@cadence.com>
  *          Bartosz Folta <bfolta@cadence.com>
- *
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2  of
- * the License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -115,7 +104,10 @@ static int gem_tsu_incr_set(struct macb *bp, struct tsu_incr *incr_spec)
 	 * to take effect.
 	 */
 	spin_lock_irqsave(&bp->tsu_clk_lock, flags);
-	gem_writel(bp, TISUBN, GEM_BF(SUBNSINCR, incr_spec->sub_ns));
+	/* RegBit[15:0] = Subns[23:8]; RegBit[31:24] = Subns[7:0] */
+	gem_writel(bp, TISUBN, GEM_BF(SUBNSINCRL, incr_spec->sub_ns) |
+		   GEM_BF(SUBNSINCRH, (incr_spec->sub_ns >>
+			  GEM_SUBNSINCRL_SIZE)));
 	gem_writel(bp, TI, GEM_BF(NSINCR, incr_spec->ns));
 	spin_unlock_irqrestore(&bp->tsu_clk_lock, flags);
 
@@ -146,7 +138,7 @@ static int gem_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	 * (temp / USEC_PER_SEC) + 0.5
 	 */
 	adj += (USEC_PER_SEC >> 1);
-	adj >>= GEM_SUBNSINCR_SIZE; /* remove fractions */
+	adj >>= PPM_FRACTION; /* remove fractions */
 	adj = div_u64(adj, USEC_PER_SEC);
 	adj = neg_adj ? (word - adj) : (word + adj);
 
diff --git a/drivers/net/ethernet/calxeda/Kconfig b/drivers/net/ethernet/calxeda/Kconfig
index 9fdd496b90ff..ce42157f13f6 100644
--- a/drivers/net/ethernet/calxeda/Kconfig
+++ b/drivers/net/ethernet/calxeda/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config NET_CALXEDA_XGMAC
 	tristate "Calxeda 1G/10G XGMAC Ethernet driver"
 	depends on HAS_IOMEM
diff --git a/drivers/net/ethernet/calxeda/Makefile b/drivers/net/ethernet/calxeda/Makefile
index f0ef08067f97..641e5b6b5ac7 100644
--- a/drivers/net/ethernet/calxeda/Makefile
+++ b/drivers/net/ethernet/calxeda/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_NET_CALXEDA_XGMAC) += xgmac.o
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index 13741ee49b9b..99f49d059414 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright 2010-2011 Calxeda, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -1866,7 +1855,7 @@ static void xgmac_pmt(void __iomem *ioaddr, unsigned long mode)
 
 static int xgmac_suspend(struct device *dev)
 {
-	struct net_device *ndev = platform_get_drvdata(to_platform_device(dev));
+	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xgmac_priv *priv = netdev_priv(ndev);
 	u32 value;
 
@@ -1892,7 +1881,7 @@ static int xgmac_suspend(struct device *dev)
 
 static int xgmac_resume(struct device *dev)
 {
-	struct net_device *ndev = platform_get_drvdata(to_platform_device(dev));
+	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xgmac_priv *priv = netdev_priv(ndev);
 	void __iomem *ioaddr = priv->base;
 
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 05f4a3b21e29..6a700d34019e 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Cavium ethernet device configuration
 #
@@ -64,11 +65,11 @@ config CAVIUM_PTP
 config LIQUIDIO
 	tristate "Cavium LiquidIO support"
 	depends on 64BIT && PCI
-	depends on MAY_USE_DEVLINK
 	depends on PCI
 	imply PTP_1588_CLOCK
 	select FW_LOADER
 	select LIBCRC32C
+	select NET_DEVLINK
 	---help---
 	  This driver supports Cavium LiquidIO Intelligent Server Adapters
 	  based on CN66XX, CN68XX and CN23XX chips.
diff --git a/drivers/net/ethernet/cavium/Makefile b/drivers/net/ethernet/cavium/Makefile
index 946bba84e81d..5d32808210fb 100644
--- a/drivers/net/ethernet/cavium/Makefile
+++ b/drivers/net/ethernet/cavium/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Cavium ethernet device drivers.
 #
diff --git a/drivers/net/ethernet/cavium/common/Makefile b/drivers/net/ethernet/cavium/common/Makefile
index dd8561b8060b..e3f87bd65928 100644
--- a/drivers/net/ethernet/cavium/common/Makefile
+++ b/drivers/net/ethernet/cavium/common/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_CAVIUM_PTP) += cavium_ptp.o
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 9f4f3c1d5043..43d11c38b38a 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1450,7 +1450,7 @@ void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx,
 		mbox_cmd.recv_len = 0;
 		mbox_cmd.recv_status = 0;
 		mbox_cmd.fn = NULL;
-		mbox_cmd.fn_arg = 0;
+		mbox_cmd.fn_arg = NULL;
 		ether_addr_copy(mbox_cmd.msg.s.params, mac);
 		mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf;
 		octeon_mbox_write(oct, &mbox_cmd);
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
index 2df7440f58df..39643be8c30a 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -38,9 +38,6 @@ int lio_cn6xxx_soft_reset(struct octeon_device *oct)
 	lio_pci_readq(oct, CN6XXX_CIU_SOFT_RST);
 	lio_pci_writeq(oct, 1, CN6XXX_CIU_SOFT_RST);
 
-	/* make sure that the reset is written before starting timer */
-	mmiowb();
-
 	/* Wait for 10ms as Octeon resets. */
 	mdelay(100);
 
@@ -487,9 +484,6 @@ void lio_cn6xxx_disable_interrupt(struct octeon_device *oct,
 
 	/* Disable Interrupts */
 	writeq(0, cn6xxx->intr_enb_reg64);
-
-	/* make sure interrupts are really disabled */
-	mmiowb();
 }
 
 static void lio_cn6xxx_get_pcie_qlmport(struct octeon_device *oct)
@@ -555,10 +549,6 @@ static int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
 				value &= ~(1 << oq_no);
 				octeon_write_csr(oct, reg, value);
 
-				/* Ensure that the enable register is written.
-				 */
-				mmiowb();
-
 				spin_unlock(&cn6xxx->lock_for_droq_int_enb_reg);
 			}
 		}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 825a28e5b544..d7e805749a5b 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -661,7 +661,8 @@ liquidio_push_packet(u32 octeon_id __attribute__((unused)),
 		    (((rh->r_dh.encap_on) &&
 		      (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) ||
 		     (!(rh->r_dh.encap_on) &&
-		      (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED))))
+		      ((rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED) ==
+			CNNIC_CSUM_VERIFIED))))
 			/* checksum has already been verified */
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		else
@@ -963,7 +964,7 @@ static void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
 
 			if (droq->ops.poll_mode) {
 				droq->ops.napi_fn(droq);
-				oct_priv->napi_mask |= (1 << oq_no);
+				oct_priv->napi_mask |= BIT_ULL(oq_no);
 			} else {
 				tasklet_schedule(&oct_priv->droq_tasklet);
 			}
@@ -1210,6 +1211,11 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
 
 	sc = (struct octeon_soft_command *)
 		octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, 16, 0);
+	if (!sc) {
+		netif_info(lio, rx_err, lio->netdev,
+			   "Failed to allocate soft command\n");
+		return -ENOMEM;
+	}
 
 	ncmd = (union octnet_cmd *)sc->virtdptr;
 
@@ -1683,6 +1689,11 @@ int liquidio_set_fec(struct lio *lio, int on_off)
 
 	sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
 				       sizeof(struct oct_nic_seapi_resp), 0);
+	if (!sc) {
+		dev_err(&oct->pci_dev->dev,
+			"Failed to allocate soft command\n");
+		return -ENOMEM;
+	}
 
 	ncmd = sc->virtdptr;
 	resp = sc->virtrptr;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 3d24133e5e49..eab805579f96 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -21,7 +21,6 @@
 #include <linux/firmware.h>
 #include <net/vxlan.h>
 #include <linux/kthread.h>
-#include <net/switchdev.h>
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
@@ -1193,6 +1192,11 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 	sc = (struct octeon_soft_command *)
 		octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
 					  16, 0);
+	if (!sc) {
+		netif_info(lio, rx_err, lio->netdev,
+			   "Failed to allocate octeon_soft_command\n");
+		return;
+	}
 
 	ncmd = (union octnet_cmd *)sc->virtdptr;
 
@@ -2518,7 +2522,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		irh->vlan = skb_vlan_tag_get(skb) & 0xfff;
 	}
 
-	xmit_more = skb->xmit_more;
+	xmit_more = netdev_xmit_more();
 
 	if (unlikely(cmdsetup.s.timestamp))
 		status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
@@ -2908,7 +2912,7 @@ static int liquidio_set_vf_spoofchk(struct net_device *netdev, int vfidx,
 	nctrl.ncmd.s.param2 = enable;
 	nctrl.ncmd.s.more = 0;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.cb_fn = NULL;
 
 	retval = octnet_send_nic_ctrl_pkt(oct, &nctrl);
 
@@ -3184,7 +3188,8 @@ static const struct devlink_ops liquidio_devlink_ops = {
 };
 
 static int
-lio_pf_switchdev_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+liquidio_get_port_parent_id(struct net_device *dev,
+			    struct netdev_phys_item_id *ppid)
 {
 	struct lio *lio = GET_LIO(dev);
 	struct octeon_device *oct = lio->oct_dev;
@@ -3192,24 +3197,12 @@ lio_pf_switchdev_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 	if (oct->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
 		return -EOPNOTSUPP;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = ETH_ALEN;
-		ether_addr_copy(attr->u.ppid.id,
-				(void *)&lio->linfo.hw_addr + 2);
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
+	ppid->id_len = ETH_ALEN;
+	ether_addr_copy(ppid->id, (void *)&lio->linfo.hw_addr + 2);
 
 	return 0;
 }
 
-static const struct switchdev_ops lio_pf_switchdev_ops = {
-	.switchdev_port_attr_get = lio_pf_switchdev_attr_get,
-};
-
 static int liquidio_get_vf_stats(struct net_device *netdev, int vfidx,
 				 struct ifla_vf_stats *vf_stats)
 {
@@ -3259,6 +3252,7 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_set_vf_trust	= liquidio_set_vf_trust,
 	.ndo_set_vf_link_state  = liquidio_set_vf_link_state,
 	.ndo_get_vf_stats	= liquidio_get_vf_stats,
+	.ndo_get_port_parent_id	= liquidio_get_port_parent_id,
 };
 
 /** \brief Entry point for the liquidio module
@@ -3534,7 +3528,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		 * netdev tasks.
 		 */
 		netdev->netdev_ops = &lionetdevops;
-		SWITCHDEV_SET_OPS(netdev, &lio_pf_switchdev_ops);
 
 		retval = netif_set_real_num_rx_queues(netdev, num_oqueues);
 		if (retval) {
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 54b245797d2e..db0b90555acb 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -1585,7 +1585,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		irh->vlan = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
 	}
 
-	xmit_more = skb->xmit_more;
+	xmit_more = netdev_xmit_more();
 
 	if (unlikely(cmdsetup.s.timestamp))
 		status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
index de61060721c4..f3f2e71431ac 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
@@ -25,7 +25,6 @@
 #include "octeon_nic.h"
 #include "octeon_main.h"
 #include "octeon_network.h"
-#include <net/switchdev.h>
 #include "lio_vf_rep.h"
 
 static int lio_vf_rep_open(struct net_device *ndev);
@@ -38,6 +37,8 @@ static int lio_vf_rep_phys_port_name(struct net_device *dev,
 static void lio_vf_rep_get_stats64(struct net_device *dev,
 				   struct rtnl_link_stats64 *stats64);
 static int lio_vf_rep_change_mtu(struct net_device *ndev, int new_mtu);
+static int lio_vf_get_port_parent_id(struct net_device *dev,
+				     struct netdev_phys_item_id *ppid);
 
 static const struct net_device_ops lio_vf_rep_ndev_ops = {
 	.ndo_open = lio_vf_rep_open,
@@ -47,6 +48,7 @@ static const struct net_device_ops lio_vf_rep_ndev_ops = {
 	.ndo_get_phys_port_name = lio_vf_rep_phys_port_name,
 	.ndo_get_stats64 = lio_vf_rep_get_stats64,
 	.ndo_change_mtu = lio_vf_rep_change_mtu,
+	.ndo_get_port_parent_id = lio_vf_get_port_parent_id,
 };
 
 static int
@@ -443,31 +445,19 @@ xmit_failed:
 	return NETDEV_TX_OK;
 }
 
-static int
-lio_vf_rep_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static int lio_vf_get_port_parent_id(struct net_device *dev,
+				     struct netdev_phys_item_id *ppid)
 {
 	struct lio_vf_rep_desc *vf_rep = netdev_priv(dev);
 	struct net_device *parent_ndev = vf_rep->parent_ndev;
 	struct lio *lio = GET_LIO(parent_ndev);
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = ETH_ALEN;
-		ether_addr_copy(attr->u.ppid.id,
-				(void *)&lio->linfo.hw_addr + 2);
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
+	ppid->id_len = ETH_ALEN;
+	ether_addr_copy(ppid->id, (void *)&lio->linfo.hw_addr + 2);
 
 	return 0;
 }
 
-static const struct switchdev_ops lio_vf_rep_switchdev_ops = {
-	.switchdev_port_attr_get        = lio_vf_rep_attr_get,
-};
-
 static void
 lio_vf_rep_fetch_stats(struct work_struct *work)
 {
@@ -524,7 +514,6 @@ lio_vf_rep_create(struct octeon_device *oct)
 		ndev->min_mtu = LIO_MIN_MTU_SIZE;
 		ndev->max_mtu = LIO_MAX_MTU_SIZE;
 		ndev->netdev_ops = &lio_vf_rep_ndev_ops;
-		SWITCHDEV_SET_OPS(ndev, &lio_vf_rep_switchdev_ops);
 
 		vf_rep = netdev_priv(ndev);
 		memset(vf_rep, 0, sizeof(*vf_rep));
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index ce8c3f818666..934115d18488 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1449,7 +1449,6 @@ void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq)
 		iq->pkt_in_done -= iq->pkts_processed;
 		iq->pkts_processed = 0;
 		/* this write needs to be flushed before we release the lock */
-		mmiowb();
 		spin_unlock_bh(&iq->lock);
 		oct = iq->oct_dev;
 	}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index a0c099f71524..017169023cca 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -513,8 +513,6 @@ int octeon_retry_droq_refill(struct octeon_droq *droq)
 		 */
 		wmb();
 		writel(desc_refilled, droq->pkts_credit_reg);
-		/* make sure mmio write completes */
-		mmiowb();
 
 		if (pkts_credit + desc_refilled >= CN23XX_SLI_DEF_BP)
 			reschedule = 0;
@@ -712,8 +710,6 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 				 */
 				wmb();
 				writel(desc_refilled, droq->pkts_credit_reg);
-				/* make sure mmio write completes */
-				mmiowb();
 			}
 		}
 	}                       /* for (each packet)... */
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index c6f4cbda040f..fcf20a8f92d9 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -278,7 +278,6 @@ ring_doorbell(struct octeon_device *oct, struct octeon_instr_queue *iq)
 	if (atomic_read(&oct->status) == OCT_DEV_RUNNING) {
 		writel(iq->fill_cnt, iq->doorbell_reg);
 		/* make sure doorbell write goes through */
-		mmiowb();
 		iq->fill_cnt = 0;
 		iq->last_db_time = jiffies;
 		return;
diff --git a/drivers/net/ethernet/cavium/octeon/Makefile b/drivers/net/ethernet/cavium/octeon/Makefile
index efa41c1d91c5..4f5098f6bc14 100644
--- a/drivers/net/ethernet/cavium/octeon/Makefile
+++ b/drivers/net/ethernet/cavium/octeon/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Cavium network device drivers.
 #
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 5359c1021f42..0e5de88fd6e8 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1503,8 +1503,8 @@ static int octeon_mgmt_probe(struct platform_device *pdev)
 
 	mac = of_get_mac_address(pdev->dev.of_node);
 
-	if (mac)
-		memcpy(netdev->dev_addr, mac, ETH_ALEN);
+	if (!IS_ERR(mac))
+		ether_addr_copy(netdev->dev_addr, mac);
 	else
 		eth_hw_addr_random(netdev);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index f4d81765221e..090d6b83982a 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #ifndef NIC_H
@@ -271,7 +268,7 @@ struct xcast_addr_list {
 };
 
 struct nicvf_work {
-	struct delayed_work    work;
+	struct work_struct     work;
 	u8                     mode;
 	struct xcast_addr_list *mc;
 };
@@ -327,7 +324,11 @@ struct nicvf {
 	struct nicvf_work       rx_mode_work;
 	/* spinlock to protect workqueue arguments from concurrent access */
 	spinlock_t              rx_mode_wq_lock;
-
+	/* workqueue for handling kernel ndo_set_rx_mode() calls */
+	struct workqueue_struct *nicvf_rx_mode_wq;
+	/* mutex to protect VF's mailbox contents from concurrent access */
+	struct mutex            rx_mode_mtx;
+	struct delayed_work	link_change_work;
 	/* PTP timestamp */
 	struct cavium_ptp	*ptp_clock;
 	/* Inbound timestamping is on */
@@ -575,10 +576,8 @@ struct set_ptp {
 
 struct xcast {
 	u8    msg;
-	union {
-		u8    mode;
-		u64   mac;
-	} data;
+	u8    mode;
+	u64   mac:48;
 };
 
 /* 128 bit shared memory between PF and each VF */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 6c8dcb65ff03..9361f964bb9b 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -57,14 +54,8 @@ struct nicpf {
 #define	NIC_GET_BGX_FROM_VF_LMAC_MAP(map)	((map >> 4) & 0xF)
 #define	NIC_GET_LMAC_FROM_VF_LMAC_MAP(map)	(map & 0xF)
 	u8			*vf_lmac_map;
-	struct delayed_work     dwork;
-	struct workqueue_struct *check_link;
-	u8			*link;
-	u8			*duplex;
-	u32			*speed;
 	u16			cpi_base[MAX_NUM_VFS_SUPPORTED];
 	u16			rssi_base[MAX_NUM_VFS_SUPPORTED];
-	bool			mbx_lock[MAX_NUM_VFS_SUPPORTED];
 
 	/* MSI-X */
 	u8			num_vec;
@@ -929,6 +920,35 @@ static void nic_config_timestamp(struct nicpf *nic, int vf, struct set_ptp *ptp)
 	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3), pkind_val);
 }
 
+/* Get BGX LMAC link status and update corresponding VF
+ * if there is a change, valid only if internal L2 switch
+ * is not present otherwise VF link is always treated as up
+ */
+static void nic_link_status_get(struct nicpf *nic, u8 vf)
+{
+	union nic_mbx mbx = {};
+	struct bgx_link_status link;
+	u8 bgx, lmac;
+
+	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+
+	/* Get BGX, LMAC indices for the VF */
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+	/* Get interface link status */
+	bgx_get_lmac_link_state(nic->node, bgx, lmac, &link);
+
+	/* Send a mbox message to VF with current link status */
+	mbx.link_status.link_up = link.link_up;
+	mbx.link_status.duplex = link.duplex;
+	mbx.link_status.speed = link.speed;
+	mbx.link_status.mac_type = link.mac_type;
+
+	/* reply with link status */
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
 /* Interrupt handler to handle mailbox messages from VFs */
 static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 {
@@ -941,8 +961,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	int i;
 	int ret = 0;
 
-	nic->mbx_lock[vf] = true;
-
 	mbx_addr = nic_get_mbx_addr(vf);
 	mbx_data = (u64 *)&mbx;
 
@@ -957,12 +975,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	switch (mbx.msg.msg) {
 	case NIC_MBOX_MSG_READY:
 		nic_mbx_send_ready(nic, vf);
-		if (vf < nic->num_vf_en) {
-			nic->link[vf] = 0;
-			nic->duplex[vf] = 0;
-			nic->speed[vf] = 0;
-		}
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_QS_CFG:
 		reg_addr = NIC_PF_QSET_0_127_CFG |
 			   (mbx.qs.num << NIC_QS_ID_SHIFT);
@@ -1031,7 +1044,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_RSS_SIZE:
 		nic_send_rss_size(nic, vf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_RSS_CFG:
 	case NIC_MBOX_MSG_RSS_CFG_CONT:
 		nic_config_rss(nic, &mbx.rss_cfg);
@@ -1039,7 +1052,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	case NIC_MBOX_MSG_CFG_DONE:
 		/* Last message of VF config msg sequence */
 		nic_enable_vf(nic, vf, true);
-		goto unlock;
+		break;
 	case NIC_MBOX_MSG_SHUTDOWN:
 		/* First msg in VF teardown sequence */
 		if (vf >= nic->num_vf_en)
@@ -1049,19 +1062,19 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
 		nic_alloc_sqs(nic, &mbx.sqs_alloc);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_NICVF_PTR:
 		nic->nicvf[vf] = mbx.nicvf.nicvf;
 		break;
 	case NIC_MBOX_MSG_PNICVF_PTR:
 		nic_send_pnicvf(nic, vf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_SNICVF_PTR:
 		nic_send_snicvf(nic, &mbx.nicvf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_BGX_STATS:
 		nic_get_bgx_stats(nic, &mbx.bgx_stats);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_LOOPBACK:
 		ret = nic_config_loopback(nic, &mbx.lbk);
 		break;
@@ -1070,7 +1083,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_PFC:
 		nic_pause_frame(nic, vf, &mbx.pfc);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_PTP_CFG:
 		nic_config_timestamp(nic, vf, &mbx.ptp);
 		break;
@@ -1094,7 +1107,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		bgx_set_dmac_cam_filter(nic->node, bgx, lmac,
-					mbx.xcast.data.mac,
+					mbx.xcast.mac,
 					vf < NIC_VF_PER_MBX_REG ? vf :
 					vf - NIC_VF_PER_MBX_REG);
 		break;
@@ -1106,8 +1119,15 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		}
 		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode);
+		bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.mode);
 		break;
+	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
+		if (vf >= nic->num_vf_en) {
+			ret = -1; /* NACK */
+			break;
+		}
+		nic_link_status_get(nic, vf);
+		return;
 	default:
 		dev_err(&nic->pdev->dev,
 			"Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg);
@@ -1121,8 +1141,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 			mbx.msg.msg, vf);
 		nic_mbx_send_nack(nic, vf);
 	}
-unlock:
-	nic->mbx_lock[vf] = false;
 }
 
 static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq)
@@ -1270,52 +1288,6 @@ static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic)
 	return 0;
 }
 
-/* Poll for BGX LMAC link status and update corresponding VF
- * if there is a change, valid only if internal L2 switch
- * is not present otherwise VF link is always treated as up
- */
-static void nic_poll_for_link(struct work_struct *work)
-{
-	union nic_mbx mbx = {};
-	struct nicpf *nic;
-	struct bgx_link_status link;
-	u8 vf, bgx, lmac;
-
-	nic = container_of(work, struct nicpf, dwork.work);
-
-	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
-
-	for (vf = 0; vf < nic->num_vf_en; vf++) {
-		/* Poll only if VF is UP */
-		if (!nic->vf_enabled[vf])
-			continue;
-
-		/* Get BGX, LMAC indices for the VF */
-		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		/* Get interface link status */
-		bgx_get_lmac_link_state(nic->node, bgx, lmac, &link);
-
-		/* Inform VF only if link status changed */
-		if (nic->link[vf] == link.link_up)
-			continue;
-
-		if (!nic->mbx_lock[vf]) {
-			nic->link[vf] = link.link_up;
-			nic->duplex[vf] = link.duplex;
-			nic->speed[vf] = link.speed;
-
-			/* Send a mbox message to VF with current link status */
-			mbx.link_status.link_up = link.link_up;
-			mbx.link_status.duplex = link.duplex;
-			mbx.link_status.speed = link.speed;
-			mbx.link_status.mac_type = link.mac_type;
-			nic_send_msg_to_vf(nic, vf, &mbx);
-		}
-	}
-	queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2);
-}
-
 static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct device *dev = &pdev->dev;
@@ -1384,18 +1356,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!nic->vf_lmac_map)
 		goto err_release_regions;
 
-	nic->link = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL);
-	if (!nic->link)
-		goto err_release_regions;
-
-	nic->duplex = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL);
-	if (!nic->duplex)
-		goto err_release_regions;
-
-	nic->speed = devm_kmalloc_array(dev, max_lmac, sizeof(u32), GFP_KERNEL);
-	if (!nic->speed)
-		goto err_release_regions;
-
 	/* Initialize hardware */
 	nic_init_hw(nic);
 
@@ -1411,22 +1371,8 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_unregister_interrupts;
 
-	/* Register a physical link status poll fn() */
-	nic->check_link = alloc_workqueue("check_link_status",
-					  WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
-	if (!nic->check_link) {
-		err = -ENOMEM;
-		goto err_disable_sriov;
-	}
-
-	INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link);
-	queue_delayed_work(nic->check_link, &nic->dwork, 0);
-
 	return 0;
 
-err_disable_sriov:
-	if (nic->flags & NIC_SRIOV_ENABLED)
-		pci_disable_sriov(pdev);
 err_unregister_interrupts:
 	nic_unregister_interrupts(nic);
 err_release_regions:
@@ -1447,12 +1393,6 @@ static void nic_remove(struct pci_dev *pdev)
 	if (nic->flags & NIC_SRIOV_ENABLED)
 		pci_disable_sriov(pdev);
 
-	if (nic->check_link) {
-		/* Destroy work Queue */
-		cancel_delayed_work_sync(&nic->dwork);
-		destroy_workqueue(nic->check_link);
-	}
-
 	nic_unregister_interrupts(nic);
 	pci_release_regions(pdev);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index a16c48a1ebb2..b3bd24febe75 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #ifndef NIC_REG_H
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 92ba958e204e..5e0b16bb95a0 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 /* ETHTOOL Support for VNIC_VF Device*/
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 88f8a8fa93cd..40a44dcb3d9b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -32,6 +29,13 @@
 #define DRV_NAME	"nicvf"
 #define DRV_VERSION	"1.0"
 
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU	(1530 - ETH_HLEN - VLAN_HLEN * 2)
+
 /* Supported devices */
 static const struct pci_device_id nicvf_id_table[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
@@ -68,9 +72,6 @@ module_param(cpi_alg, int, 0444);
 MODULE_PARM_DESC(cpi_alg,
 		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
 
-/* workqueue for handling kernel ndo_set_rx_mode() calls */
-static struct workqueue_struct *nicvf_rx_mode_wq;
-
 static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 {
 	if (nic->sqs_mode)
@@ -127,6 +128,9 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 {
 	int timeout = NIC_MBOX_MSG_TIMEOUT;
 	int sleep = 10;
+	int ret = 0;
+
+	mutex_lock(&nic->rx_mode_mtx);
 
 	nic->pf_acked = false;
 	nic->pf_nacked = false;
@@ -139,7 +143,8 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF NACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EINVAL;
+			ret = -EINVAL;
+			break;
 		}
 		msleep(sleep);
 		if (nic->pf_acked)
@@ -149,10 +154,12 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF didn't ACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EBUSY;
+			ret = -EBUSY;
+			break;
 		}
 	}
-	return 0;
+	mutex_unlock(&nic->rx_mode_mtx);
+	return ret;
 }
 
 /* Checks if VF is able to comminicate with PF
@@ -172,6 +179,17 @@ static int nicvf_check_pf_ready(struct nicvf *nic)
 	return 1;
 }
 
+static void nicvf_send_cfg_done(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
+	if (nicvf_send_msg_to_pf(nic, &mbx)) {
+		netdev_err(nic->netdev,
+			   "PF didn't respond to CFG DONE msg\n");
+	}
+}
+
 static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx)
 {
 	if (bgx->rx)
@@ -228,21 +246,24 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
 		break;
 	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
 		nic->pf_acked = true;
-		nic->link_up = mbx.link_status.link_up;
-		nic->duplex = mbx.link_status.duplex;
-		nic->speed = mbx.link_status.speed;
-		nic->mac_type = mbx.link_status.mac_type;
-		if (nic->link_up) {
-			netdev_info(nic->netdev, "Link is Up %d Mbps %s duplex\n",
-				    nic->speed,
-				    nic->duplex == DUPLEX_FULL ?
-				    "Full" : "Half");
-			netif_carrier_on(nic->netdev);
-			netif_tx_start_all_queues(nic->netdev);
-		} else {
-			netdev_info(nic->netdev, "Link is Down\n");
-			netif_carrier_off(nic->netdev);
-			netif_tx_stop_all_queues(nic->netdev);
+		if (nic->link_up != mbx.link_status.link_up) {
+			nic->link_up = mbx.link_status.link_up;
+			nic->duplex = mbx.link_status.duplex;
+			nic->speed = mbx.link_status.speed;
+			nic->mac_type = mbx.link_status.mac_type;
+			if (nic->link_up) {
+				netdev_info(nic->netdev,
+					    "Link is Up %d Mbps %s duplex\n",
+					    nic->speed,
+					    nic->duplex == DUPLEX_FULL ?
+					    "Full" : "Half");
+				netif_carrier_on(nic->netdev);
+				netif_tx_start_all_queues(nic->netdev);
+			} else {
+				netdev_info(nic->netdev, "Link is Down\n");
+				netif_carrier_off(nic->netdev);
+				netif_tx_stop_all_queues(nic->netdev);
+			}
 		}
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
@@ -1311,6 +1332,12 @@ int nicvf_stop(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 	union nic_mbx mbx = {};
 
+	/* wait till all queued set_rx_mode tasks completes */
+	if (nic->nicvf_rx_mode_wq) {
+		cancel_delayed_work_sync(&nic->link_change_work);
+		drain_workqueue(nic->nicvf_rx_mode_wq);
+	}
+
 	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
 	nicvf_send_msg_to_pf(nic, &mbx);
 
@@ -1410,13 +1437,28 @@ static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
 	return nicvf_send_msg_to_pf(nic, &mbx);
 }
 
+static void nicvf_link_status_check_task(struct work_struct *work_arg)
+{
+	struct nicvf *nic = container_of(work_arg,
+					 struct nicvf,
+					 link_change_work.work);
+	union nic_mbx mbx = {};
+	mbx.msg.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+	nicvf_send_msg_to_pf(nic, &mbx);
+	queue_delayed_work(nic->nicvf_rx_mode_wq,
+			   &nic->link_change_work, 2 * HZ);
+}
+
 int nicvf_open(struct net_device *netdev)
 {
 	int cpu, err, qidx;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct nicvf_cq_poll *cq_poll = NULL;
-	union nic_mbx mbx = {};
+
+	/* wait till all queued set_rx_mode tasks completes if any */
+	if (nic->nicvf_rx_mode_wq)
+		drain_workqueue(nic->nicvf_rx_mode_wq);
 
 	netif_carrier_off(netdev);
 
@@ -1512,8 +1554,14 @@ int nicvf_open(struct net_device *netdev)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
 	/* Send VF config done msg to PF */
-	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
-	nicvf_write_to_mbx(nic, &mbx);
+	nicvf_send_cfg_done(nic);
+
+	if (nic->nicvf_rx_mode_wq) {
+		INIT_DELAYED_WORK(&nic->link_change_work,
+				  nicvf_link_status_check_task);
+		queue_delayed_work(nic->nicvf_rx_mode_wq,
+				   &nic->link_change_work, 0);
+	}
 
 	return 0;
 cleanup:
@@ -1538,6 +1586,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct nicvf *nic = netdev_priv(netdev);
 	int orig_mtu = netdev->mtu;
 
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+		netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    netdev->mtu);
+		return -EINVAL;
+	}
+
 	netdev->mtu = new_mtu;
 
 	if (!netif_running(netdev))
@@ -1786,8 +1843,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool bpf_attached = false;
 	int ret = 0;
 
-	/* For now just support only the usual MTU sized frames */
-	if (prog && (dev->mtu > 1500)) {
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (prog && dev->mtu > MAX_XDP_MTU) {
 		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
@@ -1941,15 +2000,17 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 
 	/* flush DMAC filters and reset RX mode */
 	mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST;
-	nicvf_send_msg_to_pf(nic, &mbx);
+	if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+		goto free_mc;
 
 	if (mode & BGX_XCAST_MCAST_FILTER) {
 		/* once enabling filtering, we need to signal to PF to add
 		 * its' own LMAC to the filter to accept packets for it.
 		 */
 		mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-		mbx.xcast.data.mac = 0;
-		nicvf_send_msg_to_pf(nic, &mbx);
+		mbx.xcast.mac = 0;
+		if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+			goto free_mc;
 	}
 
 	/* check if we have any specific MACs to be added to PF DMAC filter */
@@ -1957,23 +2018,25 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 		/* now go through kernel list of MACs and add them one by one */
 		for (idx = 0; idx < mc_addrs->count; idx++) {
 			mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-			mbx.xcast.data.mac = mc_addrs->mc[idx];
-			nicvf_send_msg_to_pf(nic, &mbx);
+			mbx.xcast.mac = mc_addrs->mc[idx];
+			if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+				goto free_mc;
 		}
-		kfree(mc_addrs);
 	}
 
 	/* and finally set rx mode for PF accordingly */
 	mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST;
-	mbx.xcast.data.mode = mode;
+	mbx.xcast.mode = mode;
 
 	nicvf_send_msg_to_pf(nic, &mbx);
+free_mc:
+	kfree(mc_addrs);
 }
 
 static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
 {
 	struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work,
-						  work.work);
+						  work);
 	struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
 	u8 mode;
 	struct xcast_addr_list *mc;
@@ -2030,7 +2093,7 @@ static void nicvf_set_rx_mode(struct net_device *netdev)
 	kfree(nic->rx_mode_work.mc);
 	nic->rx_mode_work.mc = mc_list;
 	nic->rx_mode_work.mode = mode;
-	queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0);
+	queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work);
 	spin_unlock(&nic->rx_mode_wq_lock);
 }
 
@@ -2187,8 +2250,18 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
-	INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
+	nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d",
+							WQ_MEM_RECLAIM,
+							nic->vf_id);
+	if (!nic->nicvf_rx_mode_wq) {
+		err = -ENOMEM;
+		dev_err(dev, "Failed to allocate work queue\n");
+		goto err_unregister_interrupts;
+	}
+
+	INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
 	spin_lock_init(&nic->rx_mode_wq_lock);
+	mutex_init(&nic->rx_mode_mtx);
 
 	err = register_netdev(netdev);
 	if (err) {
@@ -2228,13 +2301,15 @@ static void nicvf_remove(struct pci_dev *pdev)
 	nic = netdev_priv(netdev);
 	pnetdev = nic->pnicvf->netdev;
 
-	cancel_delayed_work_sync(&nic->rx_mode_work.work);
-
 	/* Check if this Qset is assigned to different VF.
 	 * If yes, clean primary and all secondary Qsets.
 	 */
 	if (pnetdev && (pnetdev->reg_state == NETREG_REGISTERED))
 		unregister_netdev(pnetdev);
+	if (nic->nicvf_rx_mode_wq) {
+		destroy_workqueue(nic->nicvf_rx_mode_wq);
+		nic->nicvf_rx_mode_wq = NULL;
+	}
 	nicvf_unregister_interrupts(nic);
 	pci_set_drvdata(pdev, NULL);
 	if (nic->drv_stats)
@@ -2261,17 +2336,11 @@ static struct pci_driver nicvf_driver = {
 static int __init nicvf_init_module(void)
 {
 	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
-	nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic",
-						   WQ_MEM_RECLAIM);
 	return pci_register_driver(&nicvf_driver);
 }
 
 static void __exit nicvf_cleanup_module(void)
 {
-	if (nicvf_rx_mode_wq) {
-		destroy_workqueue(nicvf_rx_mode_wq);
-		nicvf_rx_mode_wq = NULL;
-	}
 	pci_unregister_driver(&nicvf_driver);
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 5b4d3badcb73..192bc92da881 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #include <linux/pci.h>
@@ -105,20 +102,19 @@ static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic,
 	/* Check if page can be recycled */
 	if (page) {
 		ref_count = page_ref_count(page);
-		/* Check if this page has been used once i.e 'put_page'
-		 * called after packet transmission i.e internal ref_count
-		 * and page's ref_count are equal i.e page can be recycled.
-		 */
-		if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
-			pgcache->ref_count--;
-		else
-			page = NULL;
-
-		/* In non-XDP mode, page's ref_count needs to be '1' for it
-		 * to be recycled.
+		/* This page can be recycled if internal ref_count and page's
+		 * ref_count are equal, indicating that the page has been used
+		 * once for packet transmission. For non-XDP mode, internal
+		 * ref_count is always '1'.
 		 */
-		if (!rbdr->is_xdp && (ref_count != 1))
+		if (rbdr->is_xdp) {
+			if (ref_count == pgcache->ref_count)
+				pgcache->ref_count--;
+			else
+				page = NULL;
+		} else if (ref_count != 1) {
 			page = NULL;
+		}
 	}
 
 	if (!page) {
@@ -365,11 +361,10 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	while (head < rbdr->pgcnt) {
 		pgcache = &rbdr->pgcache[head];
 		if (pgcache->page && page_ref_count(pgcache->page) != 0) {
-			if (!rbdr->is_xdp) {
-				put_page(pgcache->page);
-				continue;
+			if (rbdr->is_xdp) {
+				page_ref_sub(pgcache->page,
+					     pgcache->ref_count - 1);
 			}
-			page_ref_sub(pgcache->page, pgcache->ref_count - 1);
 			put_page(pgcache->page);
 		}
 		head++;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 5e9a03cf1b4d..bc2427c49b89 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #ifndef NICVF_QUEUES_H
diff --git a/drivers/net/ethernet/cavium/thunder/q_struct.h b/drivers/net/ethernet/cavium/thunder/q_struct.h
index e47205aa87ea..0df115d42612 100644
--- a/drivers/net/ethernet/cavium/thunder/q_struct.h
+++ b/drivers/net/ethernet/cavium/thunder/q_struct.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * This file contains HW queue descriptor formats, config register
  * structures etc
  *
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #ifndef Q_STRUCT_H
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index e337da6ba2a4..ad22554857bf 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
@@ -962,13 +959,13 @@ static void bgx_poll_for_sgmii_link(struct lmac *lmac)
 	lmac->last_duplex = (an_result >> 1) & 0x1;
 	switch (speed) {
 	case 0:
-		lmac->last_speed = 10;
+		lmac->last_speed = SPEED_10;
 		break;
 	case 1:
-		lmac->last_speed = 100;
+		lmac->last_speed = SPEED_100;
 		break;
 	case 2:
-		lmac->last_speed = 1000;
+		lmac->last_speed = SPEED_1000;
 		break;
 	default:
 		lmac->link_up = false;
@@ -1012,10 +1009,10 @@ static void bgx_poll_for_link(struct work_struct *work)
 	    !(smu_link & SMU_RX_CTL_STATUS)) {
 		lmac->link_up = 1;
 		if (lmac->lmac_type == BGX_MODE_XLAUI)
-			lmac->last_speed = 40000;
+			lmac->last_speed = SPEED_40000;
 		else
-			lmac->last_speed = 10000;
-		lmac->last_duplex = 1;
+			lmac->last_speed = SPEED_10000;
+		lmac->last_duplex = DUPLEX_FULL;
 	} else {
 		lmac->link_up = 0;
 		lmac->last_speed = SPEED_UNKNOWN;
@@ -1105,8 +1102,8 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 			} else {
 				/* Default to below link speed and duplex */
 				lmac->link_up = true;
-				lmac->last_speed = 1000;
-				lmac->last_duplex = 1;
+				lmac->last_speed = SPEED_1000;
+				lmac->last_duplex = DUPLEX_FULL;
 				bgx_sgmii_change_link_state(lmac);
 				return 0;
 			}
@@ -1217,7 +1214,7 @@ static void bgx_init_hw(struct bgx *bgx)
 
 	/* Disable MAC steering (NCSI traffic) */
 	for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++)
-		bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00);
+		bgx_reg_write(bgx, 0, BGX_CMR_RX_STEERING + (i * 8), 0x00);
 }
 
 static u8 bgx_get_lane2sds_cfg(struct bgx *bgx, struct lmac *lmac)
@@ -1484,7 +1481,7 @@ static int bgx_init_of_phy(struct bgx *bgx)
 			break;
 
 		mac = of_get_mac_address(node);
-		if (mac)
+		if (!IS_ERR(mac))
 			ether_addr_copy(bgx->lmac[lmac].mac, mac);
 
 		SET_NETDEV_DEV(&bgx->lmac[lmac].netdev, &bgx->pdev->dev);
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index cbdd20b9ee6f..25888706bdcd 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2015 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #ifndef THUNDER_BGX_H
@@ -60,7 +57,7 @@
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(((u64)x) << 49)
 #define  RX_DMAC_COUNT				32
-#define BGX_CMR_RX_STREERING		0x300
+#define BGX_CMR_RX_STEERING		0x300
 #define  RX_TRAFFIC_STEER_RULE_COUNT		8
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
index 2d5e8dab1f70..3ebb93792831 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2016 Cavium, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig
index e8001e974411..9909bfda167e 100644
--- a/drivers/net/ethernet/chelsio/Kconfig
+++ b/drivers/net/ethernet/chelsio/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Chelsio device configuration
 #
diff --git a/drivers/net/ethernet/chelsio/cxgb/Makefile b/drivers/net/ethernet/chelsio/cxgb/Makefile
index 57a4b262fd3f..8008282a276f 100644
--- a/drivers/net/ethernet/chelsio/cxgb/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Chelsio T1 driver
 #
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 30de26ef3da4..47b5c8e2104b 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -585,8 +585,7 @@ static int alloc_rx_resources(struct sge *sge, struct sge_params *p)
 		sizeof(struct cpl_rx_data) +
 		sge->freelQ[!sge->jumbo_fl].dma_offset;
 
-		size = (16 * 1024) -
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	size = (16 * 1024) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	sge->freelQ[sge->jumbo_fl].rx_buffer_size = size;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/Makefile b/drivers/net/ethernet/chelsio/cxgb3/Makefile
index 29aff78c7820..f65f0d93be42 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb3/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Chelsio T3 driver
 #
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
index 0e9182d3f02c..b3e4118a15e7 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
@@ -443,9 +443,9 @@ found:
 struct l2t_data *t3_init_l2t(unsigned int l2t_capacity)
 {
 	struct l2t_data *d;
-	int i, size = sizeof(*d) + l2t_capacity * sizeof(struct l2t_entry);
+	int i;
 
-	d = kvzalloc(size, GFP_KERNEL);
+	d = kvzalloc(struct_size(d, l2tab, l2t_capacity), GFP_KERNEL);
 	if (!d)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.h b/drivers/net/ethernet/chelsio/cxgb3/l2t.h
index c2fd323c4078..ea75f275023f 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.h
@@ -75,8 +75,8 @@ struct l2t_data {
 	struct l2t_entry *rover;	/* starting point for next allocation */
 	atomic_t nfree;		/* number of free entries */
 	rwlock_t lock;
-	struct l2t_entry l2tab[0];
 	struct rcu_head rcu_head;	/* to handle rcu cleanup */
+	struct l2t_entry l2tab[];
 };
 
 typedef void (*arp_failure_handler_func)(struct t3cdev * dev,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile
index 91d8a885deba..20390f6afbb4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o
 
 cxgb4-objs := cxgb4_main.o l2t.o smt.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \
 	      cxgb4_uld.o srq.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \
-	      cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o \
+	      cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o cxgb4_mps.o \
 	      cudbg_common.o cudbg_lib.o cudbg_zlib.o
 cxgb4-$(CONFIG_CHELSIO_T4_DCB) +=  cxgb4_dcb.o
 cxgb4-$(CONFIG_CHELSIO_T4_FCOE) +=  cxgb4_fcoe.o
diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
index 5701272aa7f7..ce28820c57c9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
@@ -289,8 +289,7 @@ struct clip_tbl *t4_init_clip_tbl(unsigned int clipt_start,
 	if (clipt_size < CLIPT_MIN_HASH_BUCKETS)
 		return NULL;
 
-	ctbl = kvzalloc(sizeof(*ctbl) +
-			    clipt_size*sizeof(struct list_head), GFP_KERNEL);
+	ctbl = kvzalloc(struct_size(ctbl, hash_list, clipt_size), GFP_KERNEL);
 	if (!ctbl)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c
index 8edc49827af0..175e1a675de5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_common.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #include "cxgb4.h"
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
index b2d617abcf49..69746696a929 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -1,18 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #ifndef __CUDBG_ENTITY_H__
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
index dec63c15c0ba..fc3813050f0d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h
@@ -1,18 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #ifndef __CUDBG_IF_H__
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 127b1f624413..c2e92786608b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #include <linux/sort.h>
@@ -81,7 +69,7 @@ static int is_fw_attached(struct cudbg_init *pdbg_init)
 {
 	struct adapter *padap = pdbg_init->adap;
 
-	if (!(padap->flags & FW_OK) || padap->use_bd)
+	if (!(padap->flags & CXGB4_FW_OK) || padap->use_bd)
 		return 0;
 
 	return 1;
@@ -1066,14 +1054,12 @@ static void cudbg_t4_fwcache(struct cudbg_init *pdbg_init,
 	}
 }
 
-static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
-				    struct cudbg_buffer *dbg_buff,
-				    struct cudbg_error *cudbg_err,
-				    u8 mem_type)
+static unsigned long cudbg_mem_region_size(struct cudbg_init *pdbg_init,
+					   struct cudbg_error *cudbg_err,
+					   u8 mem_type)
 {
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_meminfo mem_info;
-	unsigned long size;
 	u8 mc_idx;
 	int rc;
 
@@ -1087,7 +1073,16 @@ static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
 	if (rc)
 		return rc;
 
-	size = mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base;
+	return mem_info.avail[mc_idx].limit - mem_info.avail[mc_idx].base;
+}
+
+static int cudbg_collect_mem_region(struct cudbg_init *pdbg_init,
+				    struct cudbg_buffer *dbg_buff,
+				    struct cudbg_error *cudbg_err,
+				    u8 mem_type)
+{
+	unsigned long size = cudbg_mem_region_size(pdbg_init, cudbg_err, mem_type);
+
 	return cudbg_read_fw_mem(pdbg_init, dbg_buff, mem_type, size,
 				 cudbg_err);
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h
index f047a01a3e5b..10ee6ed1d932 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h
@@ -1,18 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #ifndef __CUDBG_LIB_H__
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h
index 8150ea85d6a5..9fac777b0b24 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib_common.h
@@ -1,18 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #ifndef __CUDBG_LIB_COMMON_H__
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c
index 25cc06d75cff..aad55fb3585f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2018 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #include <linux/zlib.h>
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h
index 60d23805dfc3..f6d83289ff1e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h
@@ -1,18 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2018 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #ifndef __CUDBG_ZLIB_H__
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 2d1ca920601e..1fbb640e896a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -280,6 +280,7 @@ struct tp_params {
 	unsigned short tx_modq[NCHAN];	/* channel to modulation queue map */
 
 	u32 vlan_pri_map;               /* cached TP_VLAN_PRI_MAP */
+	u32 filter_mask;
 	u32 ingress_config;             /* cached TP_INGRESS_CONFIG */
 
 	/* cached TP_OUT_CONFIG compressed error vector
@@ -568,7 +569,7 @@ struct sge_rspq;
 struct port_info {
 	struct adapter *adapter;
 	u16    viid;
-	s16    xact_addr_filt;        /* index of exact MAC address filter */
+	int    xact_addr_filt;        /* index of exact MAC address filter */
 	u16    rss_size;              /* size of VI's RSS table slice */
 	s8     mdio_addr;
 	enum fw_port_type port_type;
@@ -600,23 +601,25 @@ struct port_info {
 	u8 vin;
 	u8 vivld;
 	u8 smt_idx;
+	u8 rx_cchan;
 };
 
 struct dentry;
 struct work_struct;
 
 enum {                                 /* adapter flags */
-	FULL_INIT_DONE     = (1 << 0),
-	DEV_ENABLED        = (1 << 1),
-	USING_MSI          = (1 << 2),
-	USING_MSIX         = (1 << 3),
-	FW_OK              = (1 << 4),
-	RSS_TNLALLLOOKUP   = (1 << 5),
-	USING_SOFT_PARAMS  = (1 << 6),
-	MASTER_PF          = (1 << 7),
-	FW_OFLD_CONN       = (1 << 9),
-	ROOT_NO_RELAXED_ORDERING = (1 << 10),
-	SHUTTING_DOWN	   = (1 << 11),
+	CXGB4_FULL_INIT_DONE		= (1 << 0),
+	CXGB4_DEV_ENABLED		= (1 << 1),
+	CXGB4_USING_MSI			= (1 << 2),
+	CXGB4_USING_MSIX		= (1 << 3),
+	CXGB4_FW_OK			= (1 << 4),
+	CXGB4_RSS_TNLALLLOOKUP		= (1 << 5),
+	CXGB4_USING_SOFT_PARAMS		= (1 << 6),
+	CXGB4_MASTER_PF			= (1 << 7),
+	CXGB4_FW_OFLD_CONN		= (1 << 9),
+	CXGB4_ROOT_NO_RELAXED_ORDERING	= (1 << 10),
+	CXGB4_SHUTTING_DOWN		= (1 << 11),
+	CXGB4_SGE_DBQ_TIMER		= (1 << 12),
 };
 
 enum {
@@ -756,6 +759,8 @@ struct sge_eth_txq {                /* state for an SGE Ethernet Tx queue */
 #ifdef CONFIG_CHELSIO_T4_DCB
 	u8 dcb_prio;		    /* DCB Priority bound to queue */
 #endif
+	u8 dbqt;                    /* SGE Doorbell Queue Timer in use */
+	unsigned int dbqtimerix;    /* SGE Doorbell Queue Timer Index */
 	unsigned long tso;          /* # of TSO requests */
 	unsigned long tx_cso;       /* # of Tx checksum offloads */
 	unsigned long vlan_ins;     /* # of Tx VLAN insertions */
@@ -816,6 +821,8 @@ struct sge {
 	u16 nqs_per_uld;	    /* # of Rx queues per ULD */
 	u16 timer_val[SGE_NTIMERS];
 	u8 counter_val[SGE_NCOUNTERS];
+	u16 dbqtimer_tick;
+	u16 dbqtimer_val[SGE_NDBQTIMERS];
 	u32 fl_pg_order;            /* large page allocation size */
 	u32 stat_len;               /* length of status page at ring end */
 	u32 pktshift;               /* padding between CPL & packet data */
@@ -860,6 +867,7 @@ struct doorbell_stats {
 struct hash_mac_addr {
 	struct list_head list;
 	u8 addr[ETH_ALEN];
+	unsigned int iface_mac;
 };
 
 struct uld_msix_bmap {
@@ -872,6 +880,7 @@ struct uld_msix_info {
 	unsigned short vec;
 	char desc[IFNAMSIZ + 10];
 	unsigned int idx;
+	cpumask_var_t aff_mask;
 };
 
 struct vf_info {
@@ -879,6 +888,7 @@ struct vf_info {
 	unsigned int tx_rate;
 	bool pf_set_mac;
 	u16 vlan;
+	int link_state;
 };
 
 enum {
@@ -895,10 +905,6 @@ struct mbox_list {
 	struct list_head list;
 };
 
-struct mps_encap_entry {
-	atomic_t refcnt;
-};
-
 #if IS_ENABLED(CONFIG_THERMAL)
 struct ch_thermal {
 	struct thermal_zone_device *tzdev;
@@ -907,6 +913,14 @@ struct ch_thermal {
 };
 #endif
 
+struct mps_entries_ref {
+	struct list_head list;
+	u8 addr[ETH_ALEN];
+	u8 mask[ETH_ALEN];
+	u16 idx;
+	refcount_t refcnt;
+};
+
 struct adapter {
 	void __iomem *regs;
 	void __iomem *bar2;
@@ -931,9 +945,10 @@ struct adapter {
 	struct cxgb4_virt_res vres;
 	unsigned int swintr;
 
-	struct {
+	struct msix_info {
 		unsigned short vec;
 		char desc[IFNAMSIZ + 10];
+		cpumask_var_t aff_mask;
 	} msix_info[MAX_INGQ + 1];
 	struct uld_msix_info *msix_info_ulds; /* msix info for uld's */
 	struct uld_msix_bmap msix_bmap_ulds; /* msix bitmap for all uld */
@@ -958,7 +973,6 @@ struct adapter {
 	unsigned int rawf_start;
 	unsigned int rawf_cnt;
 	struct smt_data *smt;
-	struct mps_encap_entry *mps_encap;
 	struct cxgb4_uld_info *uld;
 	void *uld_handle[CXGB4_ULD_MAX];
 	unsigned int num_uld;
@@ -966,6 +980,8 @@ struct adapter {
 	struct list_head list_node;
 	struct list_head rcu_node;
 	struct list_head mac_hlist; /* list of MAC addresses in MPS Hash */
+	struct list_head mps_ref;
+	spinlock_t mps_ref_lock; /* lock for syncing mps ref/def activities */
 
 	void *iscsi_ppm;
 
@@ -1401,7 +1417,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		     rspq_flush_handler_t flush_handler, int cong);
 int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			 struct net_device *dev, struct netdev_queue *netdevq,
-			 unsigned int iqid);
+			 unsigned int iqid, u8 dbqt);
 int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 			  struct net_device *dev, unsigned int iqid,
 			  unsigned int cmplqid);
@@ -1414,6 +1430,8 @@ irqreturn_t t4_sge_intr_msix(int irq, void *cookie);
 int t4_sge_init(struct adapter *adap);
 void t4_sge_start(struct adapter *adap);
 void t4_sge_stop(struct adapter *adap);
+int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *q,
+				 int maxreclaim);
 void cxgb4_set_ethtool_ops(struct net_device *netdev);
 int cxgb4_write_rss(const struct port_info *pi, const u16 *queues);
 enum cpl_tx_tnl_lso_type cxgb_encap_offload_supported(struct sk_buff *skb);
@@ -1566,9 +1584,11 @@ int t4_slow_intr_handler(struct adapter *adapter);
 
 int t4_wait_dev_ready(void __iomem *regs);
 
+fw_port_cap32_t t4_link_acaps(struct adapter *adapter, unsigned int port,
+			      struct link_config *lc);
 int t4_link_l1cfg_core(struct adapter *adap, unsigned int mbox,
 		       unsigned int port, struct link_config *lc,
-		       bool sleep_ok, int timeout);
+		       u8 sleep_ok, int timeout);
 
 static inline int t4_link_l1cfg(struct adapter *adapter, unsigned int mbox,
 				unsigned int port, struct link_config *lc)
@@ -1820,6 +1840,8 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int eqid);
 int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type);
+int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers,
+			  u16 *dbqtimers);
 void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl);
 int t4_update_port_info(struct port_info *pi);
 int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,
@@ -1885,5 +1907,46 @@ int cxgb4_dcb_enabled(const struct net_device *dev);
 
 int cxgb4_thermal_init(struct adapter *adap);
 int cxgb4_thermal_remove(struct adapter *adap);
+int cxgb4_set_msix_aff(struct adapter *adap, unsigned short vec,
+		       cpumask_var_t *aff_mask, int idx);
+void cxgb4_clear_msix_aff(unsigned short vec, cpumask_var_t aff_mask);
+
+int cxgb4_change_mac(struct port_info *pi, unsigned int viid,
+		     int *tcam_idx, const u8 *addr,
+		     bool persistent, u8 *smt_idx);
+
+int cxgb4_alloc_mac_filt(struct adapter *adap, unsigned int viid,
+			 bool free, unsigned int naddr,
+			 const u8 **addr, u16 *idx,
+			 u64 *hash, bool sleep_ok);
+int cxgb4_free_mac_filt(struct adapter *adap, unsigned int viid,
+			unsigned int naddr, const u8 **addr, bool sleep_ok);
+int cxgb4_init_mps_ref_entries(struct adapter *adap);
+void cxgb4_free_mps_ref_entries(struct adapter *adap);
+int cxgb4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid,
+			       const u8 *addr, const u8 *mask,
+			       unsigned int vni, unsigned int vni_mask,
+			       u8 dip_hit, u8 lookup_type, bool sleep_ok);
+int cxgb4_free_encap_mac_filt(struct adapter *adap, unsigned int viid,
+			      int idx, bool sleep_ok);
+int cxgb4_free_raw_mac_filt(struct adapter *adap,
+			    unsigned int viid,
+			    const u8 *addr,
+			    const u8 *mask,
+			    unsigned int idx,
+			    u8 lookup_type,
+			    u8 port_id,
+			    bool sleep_ok);
+int cxgb4_alloc_raw_mac_filt(struct adapter *adap,
+			     unsigned int viid,
+			     const u8 *addr,
+			     const u8 *mask,
+			     unsigned int idx,
+			     u8 lookup_type,
+			     u8 port_id,
+			     bool sleep_ok);
+int cxgb4_update_mac_filt(struct port_info *pi, unsigned int viid,
+			  int *tcam_idx, const u8 *addr,
+			  bool persistent, u8 *smt_idx);
 
 #endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
index 972f0a124714..e374b413d9ac 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #include "t4_regs.h"
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
index ef59ba1ed968..66b805c7a92c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.h
@@ -1,18 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #ifndef __CXGB4_CUDBG_H__
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
index 9bd5f755a0e0..4a872f328fea 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2013-2014 Chelsio Communications.  All rights reserved.
  *
  *  Written by Anish Bhatt (anish@chelsio.com)
  *	       Casey Leedom (leedom@chelsio.com)
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #include "cxgb4.h"
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
index 484ee8290090..d3c654b9989b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
@@ -1,20 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2013-2014 Chelsio Communications.  All rights reserved.
  *
  *  Written by Anish Bhatt (anish@chelsio.com)
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #ifndef __CXGB4_DCB_H
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index b0ff9fa183f4..02959035ed3f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2620,7 +2620,7 @@ static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset)
 	}
 
 	/* should never happen! */
-	BUG_ON(1);
+	BUG();
 	return NULL;
 }
 
@@ -3143,7 +3143,7 @@ static int tid_info_show(struct seq_file *seq, void *v)
 			seq_printf(seq, ", in use: %u/%u\n",
 				   atomic_read(&t->tids_in_use),
 				   atomic_read(&t->hash_tids_in_use));
-		} else if (adap->flags & FW_OFLD_CONN) {
+		} else if (adap->flags & CXGB4_FW_OFLD_CONN) {
 			seq_printf(seq, "TID range: %u..%u/%u..%u",
 				   t->aftid_base,
 				   t->aftid_end,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index d07230c892a5..76538f4cd595 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1,18 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2013-2015 Chelsio Communications.  All rights reserved.
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  */
 
 #include <linux/firmware.h>
@@ -442,12 +430,14 @@ static unsigned int speed_to_fw_caps(int speed)
  *	Link Mode Mask.
  */
 static void fw_caps_to_lmm(enum fw_port_type port_type,
-			   unsigned int fw_caps,
+			   fw_port_cap32_t fw_caps,
 			   unsigned long *link_mode_mask)
 {
 	#define SET_LMM(__lmm_name) \
-		__set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \
-			  link_mode_mask)
+		do { \
+			__set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \
+				  link_mode_mask); \
+		} while (0)
 
 	#define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \
 		do { \
@@ -541,7 +531,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 	case FW_PORT_TYPE_CR4_QSFP:
 		SET_LMM(FIBRE);
 		FW_CAPS_TO_LMM(SPEED_1G,  1000baseT_Full);
-		FW_CAPS_TO_LMM(SPEED_10G, 10000baseSR_Full);
+		FW_CAPS_TO_LMM(SPEED_10G, 10000baseKR_Full);
 		FW_CAPS_TO_LMM(SPEED_40G, 40000baseSR4_Full);
 		FW_CAPS_TO_LMM(SPEED_25G, 25000baseCR_Full);
 		FW_CAPS_TO_LMM(SPEED_50G, 50000baseCR2_Full);
@@ -552,6 +542,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 		break;
 	}
 
+	if (fw_caps & FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M)) {
+		FW_CAPS_TO_LMM(FEC_RS, FEC_RS);
+		FW_CAPS_TO_LMM(FEC_BASER_RS, FEC_BASER);
+	} else {
+		SET_LMM(FEC_NONE);
+	}
+
 	FW_CAPS_TO_LMM(ANEG, Autoneg);
 	FW_CAPS_TO_LMM(802_3_PAUSE, Pause);
 	FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause);
@@ -623,7 +620,10 @@ static int get_link_ksettings(struct net_device *dev,
 
 	fw_caps_to_lmm(pi->port_type, pi->link_cfg.pcaps,
 		       link_ksettings->link_modes.supported);
-	fw_caps_to_lmm(pi->port_type, pi->link_cfg.acaps,
+	fw_caps_to_lmm(pi->port_type,
+		       t4_link_acaps(pi->adapter,
+				     pi->lport,
+				     &pi->link_cfg),
 		       link_ksettings->link_modes.advertising);
 	fw_caps_to_lmm(pi->port_type, pi->link_cfg.lpacaps,
 		       link_ksettings->link_modes.lp_advertising);
@@ -633,22 +633,6 @@ static int get_link_ksettings(struct net_device *dev,
 		       : SPEED_UNKNOWN);
 	base->duplex = DUPLEX_FULL;
 
-	if (pi->link_cfg.fc & PAUSE_RX) {
-		if (pi->link_cfg.fc & PAUSE_TX) {
-			ethtool_link_ksettings_add_link_mode(link_ksettings,
-							     advertising,
-							     Pause);
-		} else {
-			ethtool_link_ksettings_add_link_mode(link_ksettings,
-							     advertising,
-							     Asym_Pause);
-		}
-	} else if (pi->link_cfg.fc & PAUSE_TX) {
-		ethtool_link_ksettings_add_link_mode(link_ksettings,
-						     advertising,
-						     Asym_Pause);
-	}
-
 	base->autoneg = pi->link_cfg.autoneg;
 	if (pi->link_cfg.pcaps & FW_PORT_CAP32_ANEG)
 		ethtool_link_ksettings_add_link_mode(link_ksettings,
@@ -679,18 +663,15 @@ static int set_link_ksettings(struct net_device *dev,
 	    base->autoneg == AUTONEG_DISABLE) {
 		fw_caps = speed_to_fw_caps(base->speed);
 
-		/* Must only specify a single speed which must be supported
-		 * as part of the Physical Port Capabilities.
-		 */
-		if ((fw_caps & (fw_caps - 1)) != 0 ||
-		    !(lc->pcaps & fw_caps))
+		/* Speed must be supported by Physical Port Capabilities. */
+		if (!(lc->pcaps & fw_caps))
 			return -EINVAL;
 
 		lc->speed_caps = fw_caps;
 		lc->acaps = fw_caps;
 	} else {
 		fw_caps =
-			 lmm_to_fw_caps(link_ksettings->link_modes.advertising);
+			lmm_to_fw_caps(link_ksettings->link_modes.advertising);
 		if (!(lc->pcaps & fw_caps))
 			return -EINVAL;
 		lc->speed_caps = 0;
@@ -869,7 +850,7 @@ static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 	    e->rx_pending < MIN_FL_ENTRIES || e->tx_pending < MIN_TXQ_ENTRIES)
 		return -EINVAL;
 
-	if (adapter->flags & FULL_INIT_DONE)
+	if (adapter->flags & CXGB4_FULL_INIT_DONE)
 		return -EBUSY;
 
 	for (i = 0; i < pi->nqsets; ++i) {
@@ -926,11 +907,190 @@ static int get_adaptive_rx_setting(struct net_device *dev)
 	return q->rspq.adaptive_rx;
 }
 
-static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+/* Return the current global Adapter SGE Doorbell Queue Timer Tick for all
+ * Ethernet TX Queues.
+ */
+static int get_dbqtimer_tick(struct net_device *dev)
 {
-	set_adaptive_rx_setting(dev, c->use_adaptive_rx_coalesce);
-	return set_rx_intr_params(dev, c->rx_coalesce_usecs,
-				  c->rx_max_coalesced_frames);
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	return adap->sge.dbqtimer_tick;
+}
+
+/* Return the SGE Doorbell Queue Timer Value for the Ethernet TX Queues
+ * associated with a Network Device.
+ */
+static int get_dbqtimer(struct net_device *dev)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	struct sge_eth_txq *txq;
+
+	txq = &adap->sge.ethtxq[pi->first_qset];
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	/* all of the TX Queues use the same Timer Index */
+	return adap->sge.dbqtimer_val[txq->dbqtimerix];
+}
+
+/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX
+ * Queues.  This is the fundamental "Tick" that sets the scale of values which
+ * can be used.  Individual Ethernet TX Queues index into a relatively small
+ * array of Tick Multipliers.  Changing the base Tick will thus change all of
+ * the resulting Timer Values associated with those multipliers for all
+ * Ethernet TX Queues.
+ */
+static int set_dbqtimer_tick(struct net_device *dev, int usecs)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	struct sge *s = &adap->sge;
+	u32 param, val;
+	int ret;
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	/* return early if it's the same Timer Tick we're already using */
+	if (s->dbqtimer_tick == usecs)
+		return 0;
+
+	/* attempt to set the new Timer Tick value */
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK));
+	val = usecs;
+	ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, &param, &val);
+	if (ret)
+		return ret;
+	s->dbqtimer_tick = usecs;
+
+	/* if successful, reread resulting dependent Timer values */
+	ret = t4_read_sge_dbqtimers(adap, ARRAY_SIZE(s->dbqtimer_val),
+				    s->dbqtimer_val);
+	return ret;
+}
+
+/* Set the SGE Doorbell Queue Timer Value for the Ethernet TX Queues
+ * associated with a Network Device.  There is a relatively small array of
+ * possible Timer Values so we need to pick the closest value available.
+ */
+static int set_dbqtimer(struct net_device *dev, int usecs)
+{
+	int qix, timerix, min_timerix, delta, min_delta;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	struct sge *s = &adap->sge;
+	struct sge_eth_txq *txq;
+	u32 param, val;
+	int ret;
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	/* Find the SGE Doorbell Timer Value that's closest to the requested
+	 * value.
+	 */
+	min_delta = INT_MAX;
+	min_timerix = 0;
+	for (timerix = 0; timerix < ARRAY_SIZE(s->dbqtimer_val); timerix++) {
+		delta = s->dbqtimer_val[timerix] - usecs;
+		if (delta < 0)
+			delta = -delta;
+		if (delta < min_delta) {
+			min_delta = delta;
+			min_timerix = timerix;
+		}
+	}
+
+	/* Return early if it's the same Timer Index we're already using.
+	 * We use the same Timer Index for all of the TX Queues for an
+	 * interface so it's only necessary to check the first one.
+	 */
+	txq = &s->ethtxq[pi->first_qset];
+	if (txq->dbqtimerix == min_timerix)
+		return 0;
+
+	for (qix = 0; qix < pi->nqsets; qix++, txq++) {
+		if (adap->flags & CXGB4_FULL_INIT_DONE) {
+			param =
+			 (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
+			  FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX) |
+			  FW_PARAMS_PARAM_YZ_V(txq->q.cntxt_id));
+			val = min_timerix;
+			ret = t4_set_params(adap, adap->mbox, adap->pf, 0,
+					    1, &param, &val);
+			if (ret)
+				return ret;
+		}
+		txq->dbqtimerix = min_timerix;
+	}
+	return 0;
+}
+
+/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX
+ * Queues and the Timer Value for the Ethernet TX Queues associated with a
+ * Network Device.  Since changing the global Tick changes all of the
+ * available Timer Values, we need to do this first before selecting the
+ * resulting closest Timer Value.  Moreover, since the Tick is global,
+ * changing it affects the Timer Values for all Network Devices on the
+ * adapter.  So, before changing the Tick, we grab all of the current Timer
+ * Values for other Network Devices on this Adapter and then attempt to select
+ * new Timer Values which are close to the old values ...
+ */
+static int set_dbqtimer_tickval(struct net_device *dev,
+				int tick_usecs, int timer_usecs)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	int timer[MAX_NPORTS];
+	unsigned int port;
+	int ret;
+
+	/* Grab the other adapter Network Interface current timers and fill in
+	 * the new one for this Network Interface.
+	 */
+	for_each_port(adap, port)
+		if (port == pi->port_id)
+			timer[port] = timer_usecs;
+		else
+			timer[port] = get_dbqtimer(adap->port[port]);
+
+	/* Change the global Tick first ... */
+	ret = set_dbqtimer_tick(dev, tick_usecs);
+	if (ret)
+		return ret;
+
+	/* ... and then set all of the Network Interface Timer Values ... */
+	for_each_port(adap, port) {
+		ret = set_dbqtimer(adap->port[port], timer[port]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int set_coalesce(struct net_device *dev,
+			struct ethtool_coalesce *coalesce)
+{
+	int ret;
+
+	set_adaptive_rx_setting(dev, coalesce->use_adaptive_rx_coalesce);
+
+	ret = set_rx_intr_params(dev, coalesce->rx_coalesce_usecs,
+				 coalesce->rx_max_coalesced_frames);
+	if (ret)
+		return ret;
+
+	return set_dbqtimer_tickval(dev,
+				    coalesce->tx_coalesce_usecs_irq,
+				    coalesce->tx_coalesce_usecs);
 }
 
 static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
@@ -943,6 +1103,8 @@ static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 	c->rx_max_coalesced_frames = (rq->intr_params & QINTR_CNT_EN_F) ?
 		adap->sge.counter_val[rq->pktcnt_idx] : 0;
 	c->use_adaptive_rx_coalesce = get_adaptive_rx_setting(dev);
+	c->tx_coalesce_usecs_irq = get_dbqtimer_tick(dev);
+	c->tx_coalesce_usecs = get_dbqtimer(dev);
 	return 0;
 }
 
@@ -1076,7 +1238,7 @@ static int set_flash(struct net_device *netdev, struct ethtool_flash *ef)
 	 * firmware image otherwise we'll try to do the entire job from the
 	 * host ... and we always "force" the operation in this path.
 	 */
-	if (adap->flags & FULL_INIT_DONE)
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		mbox = adap->mbox;
 
 	ret = t4_fw_upgrade(adap, mbox, fw->data, fw->size, 1);
@@ -1155,7 +1317,7 @@ static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key,
 		return 0;
 
 	/* Interface must be brought up atleast once */
-	if (pi->adapter->flags & FULL_INIT_DONE) {
+	if (pi->adapter->flags & CXGB4_FULL_INIT_DONE) {
 		for (i = 0; i < pi->rss_size; i++)
 			pi->rss[i] = p[i];
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
index 6c8a62eefe51..33b2c0c45509 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
@@ -74,7 +74,7 @@ int cxgb_fcoe_enable(struct net_device *netdev)
 	if (is_t4(adap->params.chip))
 		return -EINVAL;
 
-	if (!(adap->flags & FULL_INIT_DONE))
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE))
 		return -EINVAL;
 
 	dev_info(adap->pdev_dev, "Enabling FCoE offload features\n");
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 7dddb9e748b8..43b0f8c57da7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -248,8 +248,9 @@ static int validate_filter(struct net_device *dev,
 	u32 fconf, iconf;
 
 	/* Check for unconfigured fields being used. */
-	fconf = adapter->params.tp.vlan_pri_map;
 	iconf = adapter->params.tp.ingress_config;
+	fconf = fs->hash ? adapter->params.tp.filter_mask :
+			   adapter->params.tp.vlan_pri_map;
 
 	if (unsupported(fconf, FCOE_F, fs->val.fcoe, fs->mask.fcoe) ||
 	    unsupported(fconf, PORT_F, fs->val.iport, fs->mask.iport) ||
@@ -524,8 +525,7 @@ static int del_filter_wr(struct adapter *adapter, int fidx)
 		return -ENOMEM;
 
 	fwr = __skb_put(skb, len);
-	t4_mk_filtdelwr(f->tid, fwr, (adapter->flags & SHUTTING_DOWN) ? -1
-			: adapter->sge.fw_evtq.abs_id);
+	t4_mk_filtdelwr(f->tid, fwr, adapter->sge.fw_evtq.abs_id);
 
 	/* Mark the filter as "pending" and ship off the Filter Work Request.
 	 * When we get the Work Request Reply we'll clear the pending status.
@@ -727,10 +727,8 @@ void clear_filter(struct adapter *adap, struct filter_entry *f)
 		cxgb4_smt_release(f->smt);
 
 	if (f->fs.val.encap_vld && f->fs.val.ovlan_vld)
-		if (atomic_dec_and_test(&adap->mps_encap[f->fs.val.ovlan &
-							 0x1ff].refcnt))
-			t4_free_encap_mac_filt(adap, pi->viid,
-					       f->fs.val.ovlan & 0x1ff, 0);
+		t4_free_encap_mac_filt(adap, pi->viid,
+				       f->fs.val.ovlan & 0x1ff, 0);
 
 	if ((f->fs.hash || is_t6(adap->params.chip)) && f->fs.type)
 		cxgb4_clip_release(f->dev, (const u32 *)&f->fs.val.lip, 1);
@@ -744,16 +742,40 @@ void clear_filter(struct adapter *adap, struct filter_entry *f)
 
 void clear_all_filters(struct adapter *adapter)
 {
+	struct net_device *dev = adapter->port[0];
 	unsigned int i;
 
 	if (adapter->tids.ftid_tab) {
 		struct filter_entry *f = &adapter->tids.ftid_tab[0];
 		unsigned int max_ftid = adapter->tids.nftids +
 					adapter->tids.nsftids;
-
+		/* Clear all TCAM filters */
 		for (i = 0; i < max_ftid; i++, f++)
 			if (f->valid || f->pending)
-				clear_filter(adapter, f);
+				cxgb4_del_filter(dev, i, &f->fs);
+	}
+
+	/* Clear all hash filters */
+	if (is_hashfilter(adapter) && adapter->tids.tid_tab) {
+		struct filter_entry *f;
+		unsigned int sb;
+
+		for (i = adapter->tids.hash_base;
+		     i <= adapter->tids.ntids; i++) {
+			f = (struct filter_entry *)
+				adapter->tids.tid_tab[i];
+
+			if (f && (f->valid || f->pending))
+				cxgb4_del_filter(dev, i, &f->fs);
+		}
+
+		sb = t4_read_reg(adapter, LE_DB_SRVR_START_INDEX_A);
+		for (i = 0; i < sb; i++) {
+			f = (struct filter_entry *)adapter->tids.tid_tab[i];
+
+			if (f && (f->valid || f->pending))
+				cxgb4_del_filter(dev, i, &f->fs);
+		}
 	}
 }
 
@@ -1018,7 +1040,7 @@ static void mk_act_open_req6(struct filter_entry *f, struct sk_buff *skb,
 			    RSS_QUEUE_V(f->fs.iq) |
 			    TX_QUEUE_V(f->fs.nat_mode) |
 			    T5_OPT_2_VALID_F |
-			    RX_CHANNEL_F |
+			    RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) |
 			    CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
 					 (f->fs.dirsteer << 1)) |
 			    PACE_V((f->fs.maskhash) |
@@ -1058,7 +1080,7 @@ static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb,
 			    RSS_QUEUE_V(f->fs.iq) |
 			    TX_QUEUE_V(f->fs.nat_mode) |
 			    T5_OPT_2_VALID_F |
-			    RX_CHANNEL_F |
+			    RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) |
 			    CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
 					 (f->fs.dirsteer << 1)) |
 			    PACE_V((f->fs.maskhash) |
@@ -1153,7 +1175,6 @@ static int cxgb4_set_hash_filter(struct net_device *dev,
 			if (ret < 0)
 				goto free_atid;
 
-			atomic_inc(&adapter->mps_encap[ret].refcnt);
 			f->fs.val.ovlan = ret;
 			f->fs.mask.ovlan = 0xffff;
 			f->fs.val.ovlan_vld = 1;
@@ -1396,7 +1417,6 @@ int __cxgb4_set_filter(struct net_device *dev, int filter_id,
 			if (ret < 0)
 				goto free_clip;
 
-			atomic_inc(&adapter->mps_encap[ret].refcnt);
 			f->fs.val.ovlan = ret;
 			f->fs.mask.ovlan = 0x1ff;
 			f->fs.val.ovlan_vld = 1;
@@ -1568,9 +1588,8 @@ int cxgb4_del_filter(struct net_device *dev, int filter_id,
 	struct filter_ctx ctx;
 	int ret;
 
-	/* If we are shutting down the adapter do not wait for completion */
-	if (netdev2adap(dev)->flags & SHUTTING_DOWN)
-		return __cxgb4_del_filter(dev, filter_id, fs, NULL);
+	if (netdev2adap(dev)->flags & CXGB4_SHUTTING_DOWN)
+		return 0;
 
 	init_completion(&ctx.completion);
 
@@ -1722,12 +1741,13 @@ void hash_filter_rpl(struct adapter *adap, const struct cpl_act_open_rpl *rpl)
 		break;
 
 	default:
-		dev_err(adap->pdev_dev, "%s: filter creation PROBLEM; status = %u\n",
-			__func__, status);
+		if (status != CPL_ERR_TCAM_FULL)
+			dev_err(adap->pdev_dev, "%s: filter creation PROBLEM; status = %u\n",
+				__func__, status);
 
 		if (ctx) {
 			if (status == CPL_ERR_TCAM_FULL)
-				ctx->result = -EAGAIN;
+				ctx->result = -ENOSPC;
 			else
 				ctx->result = -EINVAL;
 		}
@@ -1810,24 +1830,38 @@ void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
 	}
 }
 
-int init_hash_filter(struct adapter *adap)
+void init_hash_filter(struct adapter *adap)
 {
+	u32 reg;
+
 	/* On T6, verify the necessary register configs and warn the user in
 	 * case of improper config
 	 */
 	if (is_t6(adap->params.chip)) {
-		if (TCAM_ACTV_HIT_G(t4_read_reg(adap, LE_DB_RSP_CODE_0_A)) != 4)
-			goto err;
+		if (is_offload(adap)) {
+			if (!(t4_read_reg(adap, TP_GLOBAL_CONFIG_A)
+			   & ACTIVEFILTERCOUNTS_F)) {
+				dev_err(adap->pdev_dev, "Invalid hash filter + ofld config\n");
+				return;
+			}
+		} else {
+			reg = t4_read_reg(adap, LE_DB_RSP_CODE_0_A);
+			if (TCAM_ACTV_HIT_G(reg) != 4) {
+				dev_err(adap->pdev_dev, "Invalid hash filter config\n");
+				return;
+			}
+
+			reg = t4_read_reg(adap, LE_DB_RSP_CODE_1_A);
+			if (HASH_ACTV_HIT_G(reg) != 4) {
+				dev_err(adap->pdev_dev, "Invalid hash filter config\n");
+				return;
+			}
+		}
 
-		if (HASH_ACTV_HIT_G(t4_read_reg(adap, LE_DB_RSP_CODE_1_A)) != 4)
-			goto err;
 	} else {
 		dev_err(adap->pdev_dev, "Hash filter supported only on T6\n");
-		return -EINVAL;
+		return;
 	}
+
 	adap->params.hash_filter = 1;
-	return 0;
-err:
-	dev_warn(adap->pdev_dev, "Invalid hash filter config!\n");
-	return -EINVAL;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h
index 8db5fca6dcc9..b0751c0611ec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.h
@@ -50,7 +50,7 @@ int delete_filter(struct adapter *adapter, unsigned int fidx);
 
 int writable_filter(struct filter_entry *f);
 void clear_all_filters(struct adapter *adapter);
-int init_hash_filter(struct adapter *adap);
+void init_hash_filter(struct adapter *adap);
 bool is_filter_exact_match(struct adapter *adap,
 			   struct ch_filter_specification *fs);
 #endif /* __CXGB4_FILTER_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 6ba9099ca7fe..67202b6f352e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -366,13 +366,19 @@ static int cxgb4_mac_sync(struct net_device *netdev, const u8 *mac_addr)
 	int ret;
 	u64 mhash = 0;
 	u64 uhash = 0;
+	/* idx stores the index of allocated filters,
+	 * its size should be modified based on the number of
+	 * MAC addresses that we allocate filters for
+	 */
+
+	u16 idx[1] = {};
 	bool free = false;
 	bool ucast = is_unicast_ether_addr(mac_addr);
 	const u8 *maclist[1] = {mac_addr};
 	struct hash_mac_addr *new_entry;
 
-	ret = t4_alloc_mac_filt(adap, adap->mbox, pi->viid, free, 1, maclist,
-				NULL, ucast ? &uhash : &mhash, false);
+	ret = cxgb4_alloc_mac_filt(adap, pi->viid, free, 1, maclist,
+				   idx, ucast ? &uhash : &mhash, false);
 	if (ret < 0)
 		goto out;
 	/* if hash != 0, then add the addr to hash addr list
@@ -410,7 +416,7 @@ static int cxgb4_mac_unsync(struct net_device *netdev, const u8 *mac_addr)
 		}
 	}
 
-	ret = t4_free_mac_filt(adap, adap->mbox, pi->viid, 1, maclist, false);
+	ret = cxgb4_free_mac_filt(adap, pi->viid, 1, maclist, false);
 	return ret < 0 ? -EINVAL : 0;
 }
 
@@ -433,6 +439,60 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
 }
 
 /**
+ *	cxgb4_change_mac - Update match filter for a MAC address.
+ *	@pi: the port_info
+ *	@viid: the VI id
+ *	@tcam_idx: TCAM index of existing filter for old value of MAC address,
+ *		   or -1
+ *	@addr: the new MAC address value
+ *	@persist: whether a new MAC allocation should be persistent
+ *	@add_smt: if true also add the address to the HW SMT
+ *
+ *	Modifies an MPS filter and sets it to the new MAC address if
+ *	@tcam_idx >= 0, or adds the MAC address to a new filter if
+ *	@tcam_idx < 0. In the latter case the address is added persistently
+ *	if @persist is %true.
+ *	Addresses are programmed to hash region, if tcam runs out of entries.
+ *
+ */
+int cxgb4_change_mac(struct port_info *pi, unsigned int viid,
+		     int *tcam_idx, const u8 *addr, bool persist,
+		     u8 *smt_idx)
+{
+	struct adapter *adapter = pi->adapter;
+	struct hash_mac_addr *entry, *new_entry;
+	int ret;
+
+	ret = t4_change_mac(adapter, adapter->mbox, viid,
+			    *tcam_idx, addr, persist, smt_idx);
+	/* We ran out of TCAM entries. try programming hash region. */
+	if (ret == -ENOMEM) {
+		/* If the MAC address to be updated is in the hash addr
+		 * list, update it from the list
+		 */
+		list_for_each_entry(entry, &adapter->mac_hlist, list) {
+			if (entry->iface_mac) {
+				ether_addr_copy(entry->addr, addr);
+				goto set_hash;
+			}
+		}
+		new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL);
+		if (!new_entry)
+			return -ENOMEM;
+		ether_addr_copy(new_entry->addr, addr);
+		new_entry->iface_mac = true;
+		list_add_tail(&new_entry->list, &adapter->mac_hlist);
+set_hash:
+		ret = cxgb4_set_addr_hash(pi);
+	} else if (ret >= 0) {
+		*tcam_idx = ret;
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/*
  *	link_start - enable a port
  *	@dev: the port to enable
  *
@@ -450,15 +510,9 @@ static int link_start(struct net_device *dev)
 	 */
 	ret = t4_set_rxmode(pi->adapter, mb, pi->viid, dev->mtu, -1, -1, -1,
 			    !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true);
-	if (ret == 0) {
-		ret = t4_change_mac(pi->adapter, mb, pi->viid,
-				    pi->xact_addr_filt, dev->dev_addr, true,
-				    &pi->smt_idx);
-		if (ret >= 0) {
-			pi->xact_addr_filt = ret;
-			ret = 0;
-		}
-	}
+	if (ret == 0)
+		ret = cxgb4_update_mac_filt(pi, pi->viid, &pi->xact_addr_filt,
+					    dev->dev_addr, true, &pi->smt_idx);
 	if (ret == 0)
 		ret = t4_link_l1cfg(pi->adapter, mb, pi->tx_chan,
 				    &pi->link_cfg);
@@ -527,7 +581,7 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 			struct sge_eth_txq *eq;
 
 			eq = container_of(txq, struct sge_eth_txq, q);
-			netif_tx_wake_queue(eq->txq);
+			t4_sge_eth_txq_egress_update(q->adap, eq, -1);
 		} else {
 			struct sge_uld_txq *oq;
 
@@ -603,12 +657,12 @@ out:
 
 static void disable_msi(struct adapter *adapter)
 {
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4_USING_MSIX) {
 		pci_disable_msix(adapter->pdev);
-		adapter->flags &= ~USING_MSIX;
-	} else if (adapter->flags & USING_MSI) {
+		adapter->flags &= ~CXGB4_USING_MSIX;
+	} else if (adapter->flags & CXGB4_USING_MSI) {
 		pci_disable_msi(adapter->pdev);
-		adapter->flags &= ~USING_MSI;
+		adapter->flags &= ~CXGB4_USING_MSI;
 	}
 }
 
@@ -624,7 +678,7 @@ static irqreturn_t t4_nondata_intr(int irq, void *cookie)
 		adap->swintr = 1;
 		t4_write_reg(adap, MYPF_REG(PL_PF_INT_CAUSE_A), v);
 	}
-	if (adap->flags & MASTER_PF)
+	if (adap->flags & CXGB4_MASTER_PF)
 		t4_slow_intr_handler(adap);
 	return IRQ_HANDLED;
 }
@@ -654,9 +708,38 @@ static void name_msix_vecs(struct adapter *adap)
 	}
 }
 
+int cxgb4_set_msix_aff(struct adapter *adap, unsigned short vec,
+		       cpumask_var_t *aff_mask, int idx)
+{
+	int rv;
+
+	if (!zalloc_cpumask_var(aff_mask, GFP_KERNEL)) {
+		dev_err(adap->pdev_dev, "alloc_cpumask_var failed\n");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(idx, dev_to_node(adap->pdev_dev)),
+			*aff_mask);
+
+	rv = irq_set_affinity_hint(vec, *aff_mask);
+	if (rv)
+		dev_warn(adap->pdev_dev,
+			 "irq_set_affinity_hint %u failed %d\n",
+			 vec, rv);
+
+	return 0;
+}
+
+void cxgb4_clear_msix_aff(unsigned short vec, cpumask_var_t aff_mask)
+{
+	irq_set_affinity_hint(vec, NULL);
+	free_cpumask_var(aff_mask);
+}
+
 static int request_msix_queue_irqs(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
+	struct msix_info *minfo;
 	int err, ethqidx;
 	int msi_index = 2;
 
@@ -666,32 +749,77 @@ static int request_msix_queue_irqs(struct adapter *adap)
 		return err;
 
 	for_each_ethrxq(s, ethqidx) {
-		err = request_irq(adap->msix_info[msi_index].vec,
+		minfo = &adap->msix_info[msi_index];
+		err = request_irq(minfo->vec,
 				  t4_sge_intr_msix, 0,
-				  adap->msix_info[msi_index].desc,
+				  minfo->desc,
 				  &s->ethrxq[ethqidx].rspq);
 		if (err)
 			goto unwind;
+
+		cxgb4_set_msix_aff(adap, minfo->vec,
+				   &minfo->aff_mask, ethqidx);
 		msi_index++;
 	}
 	return 0;
 
 unwind:
-	while (--ethqidx >= 0)
-		free_irq(adap->msix_info[--msi_index].vec,
-			 &s->ethrxq[ethqidx].rspq);
+	while (--ethqidx >= 0) {
+		msi_index--;
+		minfo = &adap->msix_info[msi_index];
+		cxgb4_clear_msix_aff(minfo->vec, minfo->aff_mask);
+		free_irq(minfo->vec, &s->ethrxq[ethqidx].rspq);
+	}
 	free_irq(adap->msix_info[1].vec, &s->fw_evtq);
 	return err;
 }
 
 static void free_msix_queue_irqs(struct adapter *adap)
 {
-	int i, msi_index = 2;
 	struct sge *s = &adap->sge;
+	struct msix_info *minfo;
+	int i, msi_index = 2;
 
 	free_irq(adap->msix_info[1].vec, &s->fw_evtq);
-	for_each_ethrxq(s, i)
-		free_irq(adap->msix_info[msi_index++].vec, &s->ethrxq[i].rspq);
+	for_each_ethrxq(s, i) {
+		minfo = &adap->msix_info[msi_index++];
+		cxgb4_clear_msix_aff(minfo->vec, minfo->aff_mask);
+		free_irq(minfo->vec, &s->ethrxq[i].rspq);
+	}
+}
+
+static int setup_ppod_edram(struct adapter *adap)
+{
+	unsigned int param, val;
+	int ret;
+
+	/* Driver sends FW_PARAMS_PARAM_DEV_PPOD_EDRAM read command to check
+	 * if firmware supports ppod edram feature or not. If firmware
+	 * returns 1, then driver can enable this feature by sending
+	 * FW_PARAMS_PARAM_DEV_PPOD_EDRAM write command with value 1 to
+	 * enable ppod edram feature.
+	 */
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PPOD_EDRAM));
+
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &param, &val);
+	if (ret < 0) {
+		dev_warn(adap->pdev_dev,
+			 "querying PPOD_EDRAM support failed: %d\n",
+			 ret);
+		return -1;
+	}
+
+	if (val != 1)
+		return -1;
+
+	ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, &param, &val);
+	if (ret < 0) {
+		dev_err(adap->pdev_dev,
+			"setting PPOD_EDRAM failed: %d\n", ret);
+		return -1;
+	}
+	return 0;
 }
 
 /**
@@ -789,9 +917,9 @@ static void quiesce_rx(struct adapter *adap)
 /* Disable interrupt and napi handler */
 static void disable_interrupts(struct adapter *adap)
 {
-	if (adap->flags & FULL_INIT_DONE) {
+	if (adap->flags & CXGB4_FULL_INIT_DONE) {
 		t4_intr_disable(adap);
-		if (adap->flags & USING_MSIX) {
+		if (adap->flags & CXGB4_USING_MSIX) {
 			free_msix_queue_irqs(adap);
 			free_irq(adap->msix_info[0].vec, adap);
 		} else {
@@ -832,7 +960,7 @@ static int setup_fw_sge_queues(struct adapter *adap)
 	bitmap_zero(s->starving_fl, s->egr_sz);
 	bitmap_zero(s->txq_maperr, s->egr_sz);
 
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		adap->msi_idx = 1;         /* vector 0 is for non-queue interrupts */
 	else {
 		err = t4_sge_alloc_rxq(adap, &s->intrq, false, adap->port[0], 0,
@@ -885,10 +1013,13 @@ static int setup_sge_queues(struct adapter *adap)
 			q->rspq.idx = j;
 			memset(&q->stats, 0, sizeof(q->stats));
 		}
-		for (j = 0; j < pi->nqsets; j++, t++) {
+
+		q = &s->ethrxq[pi->first_qset];
+		for (j = 0; j < pi->nqsets; j++, t++, q++) {
 			err = t4_sge_alloc_eth_txq(adap, t, dev,
 					netdev_get_tx_queue(dev, j),
-					s->fw_evtq.cntxt_id);
+					q->rspq.cntxt_id,
+					!!(adap->flags & CXGB4_SGE_DBQ_TIMER));
 			if (err)
 				goto freeout;
 		}
@@ -910,7 +1041,7 @@ static int setup_sge_queues(struct adapter *adap)
 	if (!is_t4(adap->params.chip)) {
 		err = t4_sge_alloc_eth_txq(adap, &s->ptptxq, adap->port[0],
 					   netdev_get_tx_queue(adap->port[0], 0)
-					   , s->fw_evtq.cntxt_id);
+					   , s->fw_evtq.cntxt_id, false);
 		if (err)
 			goto freeout;
 	}
@@ -928,8 +1059,7 @@ freeout:
 }
 
 static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	int txq;
 
@@ -971,7 +1101,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return txq;
 	}
 
-	return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
+	return netdev_pick_tx(dev, skb, NULL) % dev->real_num_tx_queues;
 }
 
 static int closest_timer(const struct sge *s, int time)
@@ -1596,6 +1726,18 @@ unsigned int cxgb4_port_chan(const struct net_device *dev)
 }
 EXPORT_SYMBOL(cxgb4_port_chan);
 
+/**
+ *      cxgb4_port_e2cchan - get the HW c-channel of a port
+ *      @dev: the net device for the port
+ *
+ *      Return the HW RX c-channel of the given port.
+ */
+unsigned int cxgb4_port_e2cchan(const struct net_device *dev)
+{
+	return netdev2pinfo(dev)->rx_cchan;
+}
+EXPORT_SYMBOL(cxgb4_port_e2cchan);
+
 unsigned int cxgb4_dbfifo_count(const struct net_device *dev, int lpfifo)
 {
 	struct adapter *adap = netdev2adap(dev);
@@ -2229,7 +2371,7 @@ static int cxgb_up(struct adapter *adap)
 	if (err)
 		goto freeq;
 
-	if (adap->flags & USING_MSIX) {
+	if (adap->flags & CXGB4_USING_MSIX) {
 		name_msix_vecs(adap);
 		err = request_irq(adap->msix_info[0].vec, t4_nondata_intr, 0,
 				  adap->msix_info[0].desc, adap);
@@ -2242,7 +2384,8 @@ static int cxgb_up(struct adapter *adap)
 		}
 	} else {
 		err = request_irq(adap->pdev->irq, t4_intr_handler(adap),
-				  (adap->flags & USING_MSI) ? 0 : IRQF_SHARED,
+				  (adap->flags & CXGB4_USING_MSI) ? 0
+								  : IRQF_SHARED,
 				  adap->port[0]->name, adap);
 		if (err)
 			goto irq_err;
@@ -2251,7 +2394,7 @@ static int cxgb_up(struct adapter *adap)
 	enable_rx(adap);
 	t4_sge_start(adap);
 	t4_intr_enable(adap);
-	adap->flags |= FULL_INIT_DONE;
+	adap->flags |= CXGB4_FULL_INIT_DONE;
 	mutex_unlock(&uld_mutex);
 
 	notify_ulds(adap, CXGB4_STATE_UP);
@@ -2280,7 +2423,7 @@ static void cxgb_down(struct adapter *adapter)
 	t4_sge_stop(adapter);
 	t4_free_sge_resources(adapter);
 
-	adapter->flags &= ~FULL_INIT_DONE;
+	adapter->flags &= ~CXGB4_FULL_INIT_DONE;
 }
 
 /*
@@ -2294,7 +2437,7 @@ static int cxgb_open(struct net_device *dev)
 
 	netif_carrier_off(dev);
 
-	if (!(adapter->flags & FULL_INIT_DONE)) {
+	if (!(adapter->flags & CXGB4_FULL_INIT_DONE)) {
 		err = cxgb_up(adapter);
 		if (err < 0)
 			return err;
@@ -2689,6 +2832,7 @@ static int cxgb4_mgmt_get_vf_config(struct net_device *dev,
 	ivi->min_tx_rate = 0;
 	ether_addr_copy(ivi->mac, vfinfo->vf_mac_addr);
 	ivi->vlan = vfinfo->vlan;
+	ivi->linkstate = vfinfo->link_state;
 	return 0;
 }
 
@@ -2828,6 +2972,49 @@ static int cxgb4_mgmt_set_vf_vlan(struct net_device *dev, int vf,
 		ret, (vlan ? "setting" : "clearing"), adap->pf, vf);
 	return ret;
 }
+
+static int cxgb4_mgmt_set_vf_link_state(struct net_device *dev, int vf,
+					int link)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	u32 param, val;
+	int ret = 0;
+
+	if (vf >= adap->num_vfs)
+		return -EINVAL;
+
+	switch (link) {
+	case IFLA_VF_LINK_STATE_AUTO:
+		val = FW_VF_LINK_STATE_AUTO;
+		break;
+
+	case IFLA_VF_LINK_STATE_ENABLE:
+		val = FW_VF_LINK_STATE_ENABLE;
+		break;
+
+	case IFLA_VF_LINK_STATE_DISABLE:
+		val = FW_VF_LINK_STATE_DISABLE;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_LINK_STATE));
+	ret = t4_set_params(adap, adap->mbox, adap->pf, vf + 1, 1,
+			    &param, &val);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Error %d in setting PF %d VF %d link state\n",
+			ret, adap->pf, vf);
+		return -EINVAL;
+	}
+
+	adap->vfinfo[vf].link_state = link;
+	return ret;
+}
 #endif /* CONFIG_PCI_IOV */
 
 static int cxgb_set_mac_addr(struct net_device *dev, void *p)
@@ -2839,9 +3026,8 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	ret = t4_change_mac(pi->adapter, pi->adapter->pf, pi->viid,
-			    pi->xact_addr_filt, addr->sa_data, true,
-			    &pi->smt_idx);
+	ret = cxgb4_update_mac_filt(pi, pi->viid, &pi->xact_addr_filt,
+				    addr->sa_data, true, &pi->smt_idx);
 	if (ret < 0)
 		return ret;
 
@@ -2856,7 +3042,7 @@ static void cxgb_netpoll(struct net_device *dev)
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adap = pi->adapter;
 
-	if (adap->flags & USING_MSIX) {
+	if (adap->flags & CXGB4_USING_MSIX) {
 		int i;
 		struct sge_eth_rxq *rx = &adap->sge.ethrxq[pi->first_qset];
 
@@ -2883,7 +3069,7 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	if (index < 0 || index > pi->nqsets - 1)
 		return -EINVAL;
 
-	if (!(adap->flags & FULL_INIT_DONE)) {
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE)) {
 		dev_err(adap->pdev_dev,
 			"Failed to rate limit on queue %d. Link Down?\n",
 			index);
@@ -2949,14 +3135,14 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 }
 
 static int cxgb_setup_tc_flower(struct net_device *dev,
-				struct tc_cls_flower_offload *cls_flower)
+				struct flow_cls_offload *cls_flower)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return cxgb4_tc_flower_replace(dev, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return cxgb4_tc_flower_destroy(dev, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return cxgb4_tc_flower_stats(dev, cls_flower);
 	default:
 		return -EOPNOTSUPP;
@@ -2984,7 +3170,7 @@ static int cxgb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	struct port_info *pi = netdev2pinfo(dev);
 	struct adapter *adap = netdev2adap(dev);
 
-	if (!(adap->flags & FULL_INIT_DONE)) {
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE)) {
 		dev_err(adap->pdev_dev,
 			"Failed to setup tc on port %d. Link Down?\n",
 			pi->port_id);
@@ -3004,32 +3190,19 @@ static int cxgb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int cxgb_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct port_info *pi = netdev2pinfo(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb,
-					     pi, dev, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(cxgb_block_cb_list);
 
 static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			 void *type_data)
 {
+	struct port_info *pi = netdev2pinfo(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return cxgb_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &cxgb_block_cb_list,
+						  cxgb_setup_tc_block_cb,
+						  pi, dev, true);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3093,8 +3266,6 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev,
 				    i);
 			return;
 		}
-		atomic_dec(&adapter->mps_encap[adapter->rawf_start +
-			   pi->port_id].refcnt);
 	}
 }
 
@@ -3183,7 +3354,6 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev,
 			cxgb_del_udp_tunnel(netdev, ti);
 			return;
 		}
-		atomic_inc(&adapter->mps_encap[ret].refcnt);
 	}
 }
 
@@ -3244,12 +3414,13 @@ static const struct net_device_ops cxgb4_netdev_ops = {
 
 #ifdef CONFIG_PCI_IOV
 static const struct net_device_ops cxgb4_mgmt_netdev_ops = {
-	.ndo_open             = cxgb4_mgmt_open,
-	.ndo_set_vf_mac       = cxgb4_mgmt_set_vf_mac,
-	.ndo_get_vf_config    = cxgb4_mgmt_get_vf_config,
-	.ndo_set_vf_rate      = cxgb4_mgmt_set_vf_rate,
-	.ndo_get_phys_port_id = cxgb4_mgmt_get_phys_port_id,
-	.ndo_set_vf_vlan      = cxgb4_mgmt_set_vf_vlan,
+	.ndo_open               = cxgb4_mgmt_open,
+	.ndo_set_vf_mac         = cxgb4_mgmt_set_vf_mac,
+	.ndo_get_vf_config      = cxgb4_mgmt_get_vf_config,
+	.ndo_set_vf_rate        = cxgb4_mgmt_set_vf_rate,
+	.ndo_get_phys_port_id   = cxgb4_mgmt_get_phys_port_id,
+	.ndo_set_vf_vlan        = cxgb4_mgmt_set_vf_vlan,
+	.ndo_set_vf_link_state	= cxgb4_mgmt_set_vf_link_state,
 };
 #endif
 
@@ -3810,14 +3981,14 @@ static int adap_init0_phy(struct adapter *adap)
  */
 static int adap_init0_config(struct adapter *adapter, int reset)
 {
+	char *fw_config_file, fw_config_file_path[256];
+	u32 finiver, finicsum, cfcsum, param, val;
 	struct fw_caps_config_cmd caps_cmd;
-	const struct firmware *cf;
 	unsigned long mtype = 0, maddr = 0;
-	u32 finiver, finicsum, cfcsum;
-	int ret;
-	int config_issued = 0;
-	char *fw_config_file, fw_config_file_path[256];
+	const struct firmware *cf;
 	char *config_name = NULL;
+	int config_issued = 0;
+	int ret;
 
 	/*
 	 * Reset device if necessary.
@@ -3925,6 +4096,24 @@ static int adap_init0_config(struct adapter *adapter, int reset)
 			goto bye;
 	}
 
+	val = 0;
+
+	/* Ofld + Hash filter is supported. Older fw will fail this request and
+	 * it is fine.
+	 */
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_HASHFILTER_WITH_OFLD));
+	ret = t4_set_params(adapter, adapter->mbox, adapter->pf, 0,
+			    1, &param, &val);
+
+	/* FW doesn't know about Hash filter + ofld support,
+	 * it's not a problem, don't return an error.
+	 */
+	if (ret < 0) {
+		dev_warn(adapter->pdev_dev,
+			 "Hash filter with ofld is not supported by FW\n");
+	}
+
 	/*
 	 * Issue a Capability Configuration command to the firmware to get it
 	 * to parse the Configuration File.  We don't use t4_fw_config_file()
@@ -4001,6 +4190,13 @@ static int adap_init0_config(struct adapter *adapter, int reset)
 		dev_err(adapter->pdev_dev,
 			"HMA configuration failed with error %d\n", ret);
 
+	if (is_t6(adapter->params.chip)) {
+		ret = setup_ppod_edram(adapter);
+		if (!ret)
+			dev_info(adapter->pdev_dev, "Successfully enabled "
+				 "ppod edram feature\n");
+	}
+
 	/*
 	 * And finally tell the firmware to initialize itself using the
 	 * parameters from the Configuration File.
@@ -4115,7 +4311,7 @@ static int adap_init0(struct adapter *adap)
 		return ret;
 	}
 	if (ret == adap->mbox)
-		adap->flags |= MASTER_PF;
+		adap->flags |= CXGB4_MASTER_PF;
 
 	/*
 	 * If we're the Master PF Driver and the device is uninitialized,
@@ -4130,7 +4326,7 @@ static int adap_init0(struct adapter *adap)
 	/* If firmware is too old (not supported by driver) force an update. */
 	if (ret)
 		state = DEV_STATE_UNINIT;
-	if ((adap->flags & MASTER_PF) && state != DEV_STATE_INIT) {
+	if ((adap->flags & CXGB4_MASTER_PF) && state != DEV_STATE_INIT) {
 		struct fw_info *fw_info;
 		struct fw_hdr *card_fw;
 		const struct firmware *fw;
@@ -4192,7 +4388,7 @@ static int adap_init0(struct adapter *adap)
 				ret);
 		dev_info(adap->pdev_dev, "Coming up as %s: "\
 			 "Adapter already initialized\n",
-			 adap->flags & MASTER_PF ? "MASTER" : "SLAVE");
+			 adap->flags & CXGB4_MASTER_PF ? "MASTER" : "SLAVE");
 	} else {
 		dev_info(adap->pdev_dev, "Coming up as MASTER: "\
 			 "Initializing adapter\n");
@@ -4278,6 +4474,24 @@ static int adap_init0(struct adapter *adap)
 	if (ret < 0)
 		goto bye;
 
+	/* Grab the SGE Doorbell Queue Timer values.  If successful, that
+	 * indicates that the Firmware and Hardware support this.
+	 */
+	params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK));
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
+			      1, params, val);
+
+	if (!ret) {
+		adap->sge.dbqtimer_tick = val[0];
+		ret = t4_read_sge_dbqtimers(adap,
+					    ARRAY_SIZE(adap->sge.dbqtimer_val),
+					    adap->sge.dbqtimer_val);
+	}
+
+	if (!ret)
+		adap->flags |= CXGB4_SGE_DBQ_TIMER;
+
 	if (is_bypass_device(adap->pdev->device))
 		adap->params.bypass = 1;
 
@@ -4400,7 +4614,7 @@ static int adap_init0(struct adapter *adap)
 	 * offload connection through firmware work request
 	 */
 	if ((val[0] != val[1]) && (ret >= 0)) {
-		adap->flags |= FW_OFLD_CONN;
+		adap->flags |= CXGB4_FW_OFLD_CONN;
 		adap->tids.aftid_base = val[0];
 		adap->tids.aftid_end = val[1];
 	}
@@ -4467,6 +4681,13 @@ static int adap_init0(struct adapter *adap)
 	if (ret < 0)
 		goto bye;
 
+	/* hash filter has some mandatory register settings to be tested and for
+	 * that it needs to test whether offload is enabled or not, hence
+	 * checking and setting it here.
+	 */
+	if (caps_cmd.ofldcaps)
+		adap->params.offload = 1;
+
 	if (caps_cmd.ofldcaps ||
 	    (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_HASHFILTER))) {
 		/* query offload-related parameters */
@@ -4493,7 +4714,7 @@ static int adap_init0(struct adapter *adap)
 		 * 2. Server filter: This are special filters which are used
 		 * to redirect SYN packets to offload queue.
 		 */
-		if (adap->flags & FW_OFLD_CONN && !is_bypass(adap)) {
+		if (adap->flags & CXGB4_FW_OFLD_CONN && !is_bypass(adap)) {
 			adap->tids.sftid_base = adap->tids.ftid_base +
 					DIV_ROUND_UP(adap->tids.nftids, 3);
 			adap->tids.nsftids = adap->tids.nftids -
@@ -4506,11 +4727,8 @@ static int adap_init0(struct adapter *adap)
 		adap->params.ofldq_wr_cred = val[5];
 
 		if (caps_cmd.niccaps & htons(FW_CAPS_CONFIG_NIC_HASHFILTER)) {
-			ret = init_hash_filter(adap);
-			if (ret < 0)
-				goto bye;
+			init_hash_filter(adap);
 		} else {
-			adap->params.offload = 1;
 			adap->num_ofld_uld += 1;
 		}
 	}
@@ -4602,6 +4820,22 @@ static int adap_init0(struct adapter *adap)
 			goto bye;
 		adap->vres.iscsi.start = val[0];
 		adap->vres.iscsi.size = val[1] - val[0] + 1;
+		if (is_t6(adap->params.chip)) {
+			params[0] = FW_PARAM_PFVF(PPOD_EDRAM_START);
+			params[1] = FW_PARAM_PFVF(PPOD_EDRAM_END);
+			ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
+					      params, val);
+			if (!ret) {
+				adap->vres.ppod_edram.start = val[0];
+				adap->vres.ppod_edram.size =
+					val[1] - val[0] + 1;
+
+				dev_info(adap->pdev_dev,
+					 "ppod edram start 0x%x end 0x%x size 0x%x\n",
+					 val[0], val[1],
+					 adap->vres.ppod_edram.size);
+			}
+		}
 		/* LIO target and cxgb4i initiaitor */
 		adap->num_ofld_uld += 2;
 	}
@@ -4672,7 +4906,7 @@ static int adap_init0(struct adapter *adap)
 			     adap->params.b_wnd);
 	}
 	t4_init_sge_params(adap);
-	adap->flags |= FW_OK;
+	adap->flags |= CXGB4_FW_OK;
 	t4_init_tp_params(adap, true);
 	return 0;
 
@@ -4707,7 +4941,7 @@ static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev,
 		goto out;
 
 	rtnl_lock();
-	adap->flags &= ~FW_OK;
+	adap->flags &= ~CXGB4_FW_OK;
 	notify_ulds(adap, CXGB4_STATE_START_RECOVERY);
 	spin_lock(&adap->stats_lock);
 	for_each_port(adap, i) {
@@ -4719,12 +4953,12 @@ static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev,
 	}
 	spin_unlock(&adap->stats_lock);
 	disable_interrupts(adap);
-	if (adap->flags & FULL_INIT_DONE)
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		cxgb_down(adap);
 	rtnl_unlock();
-	if ((adap->flags & DEV_ENABLED)) {
+	if ((adap->flags & CXGB4_DEV_ENABLED)) {
 		pci_disable_device(pdev);
-		adap->flags &= ~DEV_ENABLED;
+		adap->flags &= ~CXGB4_DEV_ENABLED;
 	}
 out:	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -4742,13 +4976,13 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_RECOVERED;
 	}
 
-	if (!(adap->flags & DEV_ENABLED)) {
+	if (!(adap->flags & CXGB4_DEV_ENABLED)) {
 		if (pci_enable_device(pdev)) {
 			dev_err(&pdev->dev, "Cannot reenable PCI "
 					    "device after reset\n");
 			return PCI_ERS_RESULT_DISCONNECT;
 		}
-		adap->flags |= DEV_ENABLED;
+		adap->flags |= CXGB4_DEV_ENABLED;
 	}
 
 	pci_set_master(pdev);
@@ -4759,7 +4993,7 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_DISCONNECT;
 	if (t4_fw_hello(adap, adap->mbox, adap->pf, MASTER_MUST, NULL) < 0)
 		return PCI_ERS_RESULT_DISCONNECT;
-	adap->flags |= FW_OK;
+	adap->flags |= CXGB4_FW_OK;
 	if (adap_init1(adap, &c))
 		return PCI_ERS_RESULT_DISCONNECT;
 
@@ -4871,7 +5105,7 @@ static int cfg_queues(struct adapter *adap)
 	 * at all is problematic ...
 	 */
 	niqflint = adap->params.pfres.niqflint - 1;
-	if (!(adap->flags & USING_MSIX))
+	if (!(adap->flags & CXGB4_USING_MSIX))
 		niqflint--;
 	neq = adap->params.pfres.neq / 2;
 	avail_eth_qsets = min(niqflint, neq);
@@ -5153,8 +5387,8 @@ static void print_adapter_info(struct adapter *adapter)
 	/* Software/Hardware configuration */
 	dev_info(adapter->pdev_dev, "Configuration: %sNIC %s, %s capable\n",
 		 is_offload(adapter) ? "R" : "",
-		 ((adapter->flags & USING_MSIX) ? "MSI-X" :
-		  (adapter->flags & USING_MSI) ? "MSI" : ""),
+		 ((adapter->flags & CXGB4_USING_MSIX) ? "MSI-X" :
+		  (adapter->flags & CXGB4_USING_MSI) ? "MSI" : ""),
 		 is_offload(adapter) ? "Offload" : "non-Offload");
 }
 
@@ -5202,7 +5436,6 @@ static void free_some_resources(struct adapter *adapter)
 {
 	unsigned int i;
 
-	kvfree(adapter->mps_encap);
 	kvfree(adapter->smt);
 	kvfree(adapter->l2t);
 	kvfree(adapter->srq);
@@ -5229,13 +5462,13 @@ static void free_some_resources(struct adapter *adapter)
 			kfree(adap2pinfo(adapter, i)->rss);
 			free_netdev(adapter->port[i]);
 		}
-	if (adapter->flags & FW_OK)
+	if (adapter->flags & CXGB4_FW_OK)
 		t4_fw_bye(adapter, adapter->pf);
 }
 
 #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
 #define VLAN_FEAT (NETIF_F_SG | NETIF_F_IP_CSUM | TSO_FLAGS | \
-		   NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
+		   NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
 #define SEGMENT_SIZE 128
 
 static int t4_get_chip_type(struct adapter *adap, int ver)
@@ -5533,7 +5766,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* PCI device has been enabled */
-	adapter->flags |= DEV_ENABLED;
+	adapter->flags |= CXGB4_DEV_ENABLED;
 	memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
 
 	/* If possible, we use PCIe Relaxed Ordering Attribute to deliver
@@ -5551,7 +5784,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * using Relaxed Ordering.
 	 */
 	if (!pcie_relaxed_ordering_enabled(pdev))
-		adapter->flags |= ROOT_NO_RELAXED_ORDERING;
+		adapter->flags |= CXGB4_ROOT_NO_RELAXED_ORDERING;
 
 	spin_lock_init(&adapter->stats_lock);
 	spin_lock_init(&adapter->tid_release_lock);
@@ -5642,7 +5875,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 		netdev->hw_features = NETIF_F_SG | TSO_FLAGS |
 			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			NETIF_F_RXCSUM | NETIF_F_RXHASH |
+			NETIF_F_RXCSUM | NETIF_F_RXHASH | NETIF_F_GRO |
 			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 			NETIF_F_HW_TC;
 
@@ -5651,9 +5884,12 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 						   NETIF_F_IPV6_CSUM |
 						   NETIF_F_RXCSUM |
 						   NETIF_F_GSO_UDP_TUNNEL |
+						   NETIF_F_GSO_UDP_TUNNEL_CSUM |
 						   NETIF_F_TSO | NETIF_F_TSO6;
 
-			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL |
+					       NETIF_F_GSO_UDP_TUNNEL_CSUM |
+					       NETIF_F_HW_TLS_RECORD;
 		}
 
 		if (highdma)
@@ -5680,7 +5916,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, adapter);
 
-	if (adapter->flags & FW_OK) {
+	if (adapter->flags & CXGB4_FW_OK) {
 		err = t4_port_init(adapter, func, func, 0);
 		if (err)
 			goto out_free_dev;
@@ -5702,7 +5938,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
-	if (!(adapter->flags & FW_OK))
+	if (!(adapter->flags & CXGB4_FW_OK))
 		goto fw_attach_fail;
 
 	/* Configure queues and allocate tables now, they can be needed as
@@ -5725,12 +5961,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		adapter->params.offload = 0;
 	}
 
-	adapter->mps_encap = kvcalloc(adapter->params.arch.mps_tcam_size,
-				      sizeof(struct mps_encap_entry),
-				      GFP_KERNEL);
-	if (!adapter->mps_encap)
-		dev_warn(&pdev->dev, "could not allocate MPS Encap entries, continuing\n");
-
 #if IS_ENABLED(CONFIG_IPV6)
 	if (chip_ver <= CHELSIO_T5 &&
 	    (!(t4_read_reg(adapter, LE_DB_CONFIG_A) & ASLIPCOMPEN_F))) {
@@ -5796,9 +6026,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* See what interrupts we'll be using */
 	if (msi > 1 && enable_msix(adapter) == 0)
-		adapter->flags |= USING_MSIX;
+		adapter->flags |= CXGB4_USING_MSIX;
 	else if (msi > 0 && pci_enable_msi(pdev) == 0) {
-		adapter->flags |= USING_MSI;
+		adapter->flags |= CXGB4_USING_MSI;
 		if (msi > 1)
 			free_msix_info(adapter);
 	}
@@ -5806,6 +6036,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* check for PCI Express bandwidth capabiltites */
 	pcie_print_link_status(pdev);
 
+	cxgb4_init_mps_ref_entries(adapter);
+
 	err = init_rss(adapter);
 	if (err)
 		goto out_free_dev;
@@ -5866,7 +6098,7 @@ fw_attach_fail:
 		cxgb4_ptp_init(adapter);
 
 	if (IS_REACHABLE(CONFIG_THERMAL) &&
-	    !is_t4(adapter->params.chip) && (adapter->flags & FW_OK))
+	    !is_t4(adapter->params.chip) && (adapter->flags & CXGB4_FW_OK))
 		cxgb4_thermal_init(adapter);
 
 	print_adapter_info(adapter);
@@ -5875,7 +6107,7 @@ fw_attach_fail:
  out_free_dev:
 	t4_free_sge_resources(adapter);
 	free_some_resources(adapter);
-	if (adapter->flags & USING_MSIX)
+	if (adapter->flags & CXGB4_USING_MSIX)
 		free_msix_info(adapter);
 	if (adapter->num_uld || adapter->num_ofld_uld)
 		t4_uld_mem_free(adapter);
@@ -5908,7 +6140,12 @@ static void remove_one(struct pci_dev *pdev)
 		return;
 	}
 
-	adapter->flags |= SHUTTING_DOWN;
+	/* If we allocated filters, free up state associated with any
+	 * valid filters ...
+	 */
+	clear_all_filters(adapter);
+
+	adapter->flags |= CXGB4_SHUTTING_DOWN;
 
 	if (adapter->pf == 4) {
 		int i;
@@ -5927,6 +6164,8 @@ static void remove_one(struct pci_dev *pdev)
 
 		disable_interrupts(adapter);
 
+		cxgb4_free_mps_ref_entries(adapter);
+
 		for_each_port(adapter, i)
 			if (adapter->port[i]->reg_state == NETREG_REGISTERED)
 				unregister_netdev(adapter->port[i]);
@@ -5938,15 +6177,10 @@ static void remove_one(struct pci_dev *pdev)
 		if (IS_REACHABLE(CONFIG_THERMAL))
 			cxgb4_thermal_remove(adapter);
 
-		/* If we allocated filters, free up state associated with any
-		 * valid filters ...
-		 */
-		clear_all_filters(adapter);
-
-		if (adapter->flags & FULL_INIT_DONE)
+		if (adapter->flags & CXGB4_FULL_INIT_DONE)
 			cxgb_down(adapter);
 
-		if (adapter->flags & USING_MSIX)
+		if (adapter->flags & CXGB4_USING_MSIX)
 			free_msix_info(adapter);
 		if (adapter->num_uld || adapter->num_ofld_uld)
 			t4_uld_mem_free(adapter);
@@ -5970,9 +6204,9 @@ static void remove_one(struct pci_dev *pdev)
 #endif
 	iounmap(adapter->regs);
 	pci_disable_pcie_error_reporting(pdev);
-	if ((adapter->flags & DEV_ENABLED)) {
+	if ((adapter->flags & CXGB4_DEV_ENABLED)) {
 		pci_disable_device(pdev);
-		adapter->flags &= ~DEV_ENABLED;
+		adapter->flags &= ~CXGB4_DEV_ENABLED;
 	}
 	pci_release_regions(pdev);
 	kfree(adapter->mbox_log);
@@ -5998,7 +6232,7 @@ static void shutdown_one(struct pci_dev *pdev)
 		return;
 	}
 
-	adapter->flags |= SHUTTING_DOWN;
+	adapter->flags |= CXGB4_SHUTTING_DOWN;
 
 	if (adapter->pf == 4) {
 		int i;
@@ -6016,7 +6250,7 @@ static void shutdown_one(struct pci_dev *pdev)
 		disable_msi(adapter);
 
 		t4_sge_stop(adapter);
-		if (adapter->flags & FW_OK)
+		if (adapter->flags & CXGB4_FW_OK)
 			t4_fw_bye(adapter, adapter->mbox);
 	}
 }
@@ -6044,15 +6278,24 @@ static int __init cxgb4_init_module(void)
 
 	ret = pci_register_driver(&cxgb4_driver);
 	if (ret < 0)
-		debugfs_remove(cxgb4_debugfs_root);
+		goto err_pci;
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (!inet6addr_registered) {
-		register_inet6addr_notifier(&cxgb4_inet6addr_notifier);
-		inet6addr_registered = true;
+		ret = register_inet6addr_notifier(&cxgb4_inet6addr_notifier);
+		if (ret)
+			pci_unregister_driver(&cxgb4_driver);
+		else
+			inet6addr_registered = true;
 	}
 #endif
 
+	if (ret == 0)
+		return ret;
+
+err_pci:
+	debugfs_remove(cxgb4_debugfs_root);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
new file mode 100644
index 000000000000..b1a073eea60b
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c
@@ -0,0 +1,241 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Chelsio Communications, Inc. All rights reserved. */
+
+#include "cxgb4.h"
+
+static int cxgb4_mps_ref_dec_by_mac(struct adapter *adap,
+				    const u8 *addr, const u8 *mask)
+{
+	u8 bitmask[] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+	struct mps_entries_ref *mps_entry, *tmp;
+	int ret = -EINVAL;
+
+	spin_lock_bh(&adap->mps_ref_lock);
+	list_for_each_entry_safe(mps_entry, tmp, &adap->mps_ref, list) {
+		if (ether_addr_equal(mps_entry->addr, addr) &&
+		    ether_addr_equal(mps_entry->mask, mask ? mask : bitmask)) {
+			if (!refcount_dec_and_test(&mps_entry->refcnt)) {
+				spin_unlock_bh(&adap->mps_ref_lock);
+				return -EBUSY;
+			}
+			list_del(&mps_entry->list);
+			kfree(mps_entry);
+			ret = 0;
+			break;
+		}
+	}
+	spin_unlock_bh(&adap->mps_ref_lock);
+	return ret;
+}
+
+static int cxgb4_mps_ref_dec(struct adapter *adap, u16 idx)
+{
+	struct mps_entries_ref *mps_entry, *tmp;
+	int ret = -EINVAL;
+
+	spin_lock(&adap->mps_ref_lock);
+	list_for_each_entry_safe(mps_entry, tmp, &adap->mps_ref, list) {
+		if (mps_entry->idx == idx) {
+			if (!refcount_dec_and_test(&mps_entry->refcnt)) {
+				spin_unlock(&adap->mps_ref_lock);
+				return -EBUSY;
+			}
+			list_del(&mps_entry->list);
+			kfree(mps_entry);
+			ret = 0;
+			break;
+		}
+	}
+	spin_unlock(&adap->mps_ref_lock);
+	return ret;
+}
+
+static int cxgb4_mps_ref_inc(struct adapter *adap, const u8 *mac_addr,
+			     u16 idx, const u8 *mask)
+{
+	u8 bitmask[] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+	struct mps_entries_ref *mps_entry;
+	int ret = 0;
+
+	spin_lock_bh(&adap->mps_ref_lock);
+	list_for_each_entry(mps_entry, &adap->mps_ref, list) {
+		if (mps_entry->idx == idx) {
+			refcount_inc(&mps_entry->refcnt);
+			goto unlock;
+		}
+	}
+	mps_entry = kzalloc(sizeof(*mps_entry), GFP_ATOMIC);
+	if (!mps_entry) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+	ether_addr_copy(mps_entry->mask, mask ? mask : bitmask);
+	ether_addr_copy(mps_entry->addr, mac_addr);
+	mps_entry->idx = idx;
+	refcount_set(&mps_entry->refcnt, 1);
+	list_add_tail(&mps_entry->list, &adap->mps_ref);
+unlock:
+	spin_unlock_bh(&adap->mps_ref_lock);
+	return ret;
+}
+
+int cxgb4_free_mac_filt(struct adapter *adap, unsigned int viid,
+			unsigned int naddr, const u8 **addr, bool sleep_ok)
+{
+	int ret, i;
+
+	for (i = 0; i < naddr; i++) {
+		if (!cxgb4_mps_ref_dec_by_mac(adap, addr[i], NULL)) {
+			ret = t4_free_mac_filt(adap, adap->mbox, viid,
+					       1, &addr[i], sleep_ok);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	/* return number of filters freed */
+	return naddr;
+}
+
+int cxgb4_alloc_mac_filt(struct adapter *adap, unsigned int viid,
+			 bool free, unsigned int naddr, const u8 **addr,
+			 u16 *idx, u64 *hash, bool sleep_ok)
+{
+	int ret, i;
+
+	ret = t4_alloc_mac_filt(adap, adap->mbox, viid, free,
+				naddr, addr, idx, hash, sleep_ok);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < naddr; i++) {
+		if (idx[i] != 0xffff) {
+			if (cxgb4_mps_ref_inc(adap, addr[i], idx[i], NULL)) {
+				ret = -ENOMEM;
+				goto error;
+			}
+		}
+	}
+
+	goto out;
+error:
+	cxgb4_free_mac_filt(adap, viid, naddr, addr, sleep_ok);
+
+out:
+	/* Returns a negative error number or the number of filters allocated */
+	return ret;
+}
+
+int cxgb4_update_mac_filt(struct port_info *pi, unsigned int viid,
+			  int *tcam_idx, const u8 *addr,
+			  bool persistent, u8 *smt_idx)
+{
+	int ret;
+
+	ret = cxgb4_change_mac(pi, viid, tcam_idx,
+			       addr, persistent, smt_idx);
+	if (ret < 0)
+		return ret;
+
+	cxgb4_mps_ref_inc(pi->adapter, addr, *tcam_idx, NULL);
+	return ret;
+}
+
+int cxgb4_free_raw_mac_filt(struct adapter *adap,
+			    unsigned int viid,
+			    const u8 *addr,
+			    const u8 *mask,
+			    unsigned int idx,
+			    u8 lookup_type,
+			    u8 port_id,
+			    bool sleep_ok)
+{
+	int ret = 0;
+
+	if (!cxgb4_mps_ref_dec(adap, idx))
+		ret = t4_free_raw_mac_filt(adap, viid, addr,
+					   mask, idx, lookup_type,
+					   port_id, sleep_ok);
+
+	return ret;
+}
+
+int cxgb4_alloc_raw_mac_filt(struct adapter *adap,
+			     unsigned int viid,
+			     const u8 *addr,
+			     const u8 *mask,
+			     unsigned int idx,
+			     u8 lookup_type,
+			     u8 port_id,
+			     bool sleep_ok)
+{
+	int ret;
+
+	ret = t4_alloc_raw_mac_filt(adap, viid, addr,
+				    mask, idx, lookup_type,
+				    port_id, sleep_ok);
+	if (ret < 0)
+		return ret;
+
+	if (cxgb4_mps_ref_inc(adap, addr, ret, mask)) {
+		ret = -ENOMEM;
+		t4_free_raw_mac_filt(adap, viid, addr,
+				     mask, idx, lookup_type,
+				     port_id, sleep_ok);
+	}
+
+	return ret;
+}
+
+int cxgb4_free_encap_mac_filt(struct adapter *adap, unsigned int viid,
+			      int idx, bool sleep_ok)
+{
+	int ret = 0;
+
+	if (!cxgb4_mps_ref_dec(adap, idx))
+		ret = t4_free_encap_mac_filt(adap, viid, idx, sleep_ok);
+
+	return ret;
+}
+
+int cxgb4_alloc_encap_mac_filt(struct adapter *adap, unsigned int viid,
+			       const u8 *addr, const u8 *mask,
+			       unsigned int vni, unsigned int vni_mask,
+			       u8 dip_hit, u8 lookup_type, bool sleep_ok)
+{
+	int ret;
+
+	ret = t4_alloc_encap_mac_filt(adap, viid, addr, mask, vni, vni_mask,
+				      dip_hit, lookup_type, sleep_ok);
+	if (ret < 0)
+		return ret;
+
+	if (cxgb4_mps_ref_inc(adap, addr, ret, mask)) {
+		ret = -ENOMEM;
+		t4_free_encap_mac_filt(adap, viid, ret, sleep_ok);
+	}
+	return ret;
+}
+
+int cxgb4_init_mps_ref_entries(struct adapter *adap)
+{
+	spin_lock_init(&adap->mps_ref_lock);
+	INIT_LIST_HEAD(&adap->mps_ref);
+
+	return 0;
+}
+
+void cxgb4_free_mps_ref_entries(struct adapter *adap)
+{
+	struct mps_entries_ref *mps_entry, *tmp;
+
+	if (!list_empty(&adap->mps_ref))
+		return;
+
+	spin_lock(&adap->mps_ref_lock);
+	list_for_each_entry_safe(mps_entry, tmp, &adap->mps_ref, list) {
+		list_del(&mps_entry->list);
+		kfree(mps_entry);
+	}
+	spin_unlock(&adap->mps_ref_lock);
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index c116f96956fe..312599c6b35a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -80,31 +80,26 @@ static struct ch_tc_flower_entry *ch_flower_lookup(struct adapter *adap,
 }
 
 static void cxgb4_process_flow_match(struct net_device *dev,
-				     struct tc_cls_flower_offload *cls,
+				     struct flow_cls_offload *cls,
 				     struct ch_filter_specification *fs)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	u16 addr_type = 0;
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  cls->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->mask);
-		u16 ethtype_key = ntohs(key->n_proto);
-		u16 ethtype_mask = ntohs(mask->n_proto);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+		u16 ethtype_key, ethtype_mask;
+
+		flow_rule_match_basic(rule, &match);
+		ethtype_key = ntohs(match.key->n_proto);
+		ethtype_mask = ntohs(match.mask->n_proto);
 
 		if (ethtype_key == ETH_P_ALL) {
 			ethtype_key = 0;
@@ -116,118 +111,95 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 
 		fs->val.ethtype = ethtype_key;
 		fs->mask.ethtype = ethtype_mask;
-		fs->val.proto = key->ip_proto;
-		fs->mask.proto = mask->ip_proto;
+		fs->val.proto = match.key->ip_proto;
+		fs->mask.proto = match.mask->ip_proto;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  cls->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  cls->mask);
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_ipv4_addrs(rule, &match);
 		fs->type = 0;
-		memcpy(&fs->val.lip[0], &key->dst, sizeof(key->dst));
-		memcpy(&fs->val.fip[0], &key->src, sizeof(key->src));
-		memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst));
-		memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src));
+		memcpy(&fs->val.lip[0], &match.key->dst, sizeof(match.key->dst));
+		memcpy(&fs->val.fip[0], &match.key->src, sizeof(match.key->src));
+		memcpy(&fs->mask.lip[0], &match.mask->dst, sizeof(match.mask->dst));
+		memcpy(&fs->mask.fip[0], &match.mask->src, sizeof(match.mask->src));
 
 		/* also initialize nat_lip/fip to same values */
-		memcpy(&fs->nat_lip[0], &key->dst, sizeof(key->dst));
-		memcpy(&fs->nat_fip[0], &key->src, sizeof(key->src));
-
+		memcpy(&fs->nat_lip[0], &match.key->dst, sizeof(match.key->dst));
+		memcpy(&fs->nat_fip[0], &match.key->src, sizeof(match.key->src));
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  cls->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  cls->mask);
+		struct flow_match_ipv6_addrs match;
 
+		flow_rule_match_ipv6_addrs(rule, &match);
 		fs->type = 1;
-		memcpy(&fs->val.lip[0], key->dst.s6_addr, sizeof(key->dst));
-		memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src));
-		memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst));
-		memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src));
+		memcpy(&fs->val.lip[0], match.key->dst.s6_addr,
+		       sizeof(match.key->dst));
+		memcpy(&fs->val.fip[0], match.key->src.s6_addr,
+		       sizeof(match.key->src));
+		memcpy(&fs->mask.lip[0], match.mask->dst.s6_addr,
+		       sizeof(match.mask->dst));
+		memcpy(&fs->mask.fip[0], match.mask->src.s6_addr,
+		       sizeof(match.mask->src));
 
 		/* also initialize nat_lip/fip to same values */
-		memcpy(&fs->nat_lip[0], key->dst.s6_addr, sizeof(key->dst));
-		memcpy(&fs->nat_fip[0], key->src.s6_addr, sizeof(key->src));
+		memcpy(&fs->nat_lip[0], match.key->dst.s6_addr,
+		       sizeof(match.key->dst));
+		memcpy(&fs->nat_fip[0], match.key->src.s6_addr,
+		       sizeof(match.key->src));
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key, *mask;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_PORTS,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_PORTS,
-						 cls->mask);
-		fs->val.lport = cpu_to_be16(key->dst);
-		fs->mask.lport = cpu_to_be16(mask->dst);
-		fs->val.fport = cpu_to_be16(key->src);
-		fs->mask.fport = cpu_to_be16(mask->src);
+		flow_rule_match_ports(rule, &match);
+		fs->val.lport = cpu_to_be16(match.key->dst);
+		fs->mask.lport = cpu_to_be16(match.mask->dst);
+		fs->val.fport = cpu_to_be16(match.key->src);
+		fs->mask.fport = cpu_to_be16(match.mask->src);
 
 		/* also initialize nat_lport/fport to same values */
-		fs->nat_lport = cpu_to_be16(key->dst);
-		fs->nat_fport = cpu_to_be16(key->src);
+		fs->nat_lport = cpu_to_be16(match.key->dst);
+		fs->nat_fport = cpu_to_be16(match.key->src);
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
-		struct flow_dissector_key_ip *key, *mask;
-
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_IP,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_IP,
-						 cls->mask);
-		fs->val.tos = key->tos;
-		fs->mask.tos = mask->tos;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_match_ip match;
+
+		flow_rule_match_ip(rule, &match);
+		fs->val.tos = match.key->tos;
+		fs->mask.tos = match.mask->tos;
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key, *mask;
-
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_ENC_KEYID,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_ENC_KEYID,
-						 cls->mask);
-		fs->val.vni = be32_to_cpu(key->keyid);
-		fs->mask.vni = be32_to_cpu(mask->keyid);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
+
+		flow_rule_match_enc_keyid(rule, &match);
+		fs->val.vni = be32_to_cpu(match.key->keyid);
+		fs->mask.vni = be32_to_cpu(match.mask->keyid);
 		if (fs->mask.vni) {
 			fs->val.encap_vld = 1;
 			fs->mask.encap_vld = 1;
 		}
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key, *mask;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 		u16 vlan_tci, vlan_tci_mask;
 
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_VLAN,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_VLAN,
-						 cls->mask);
-		vlan_tci = key->vlan_id | (key->vlan_priority <<
-					   VLAN_PRIO_SHIFT);
-		vlan_tci_mask = mask->vlan_id | (mask->vlan_priority <<
-						 VLAN_PRIO_SHIFT);
+		flow_rule_match_vlan(rule, &match);
+		vlan_tci = match.key->vlan_id | (match.key->vlan_priority <<
+					       VLAN_PRIO_SHIFT);
+		vlan_tci_mask = match.mask->vlan_id | (match.mask->vlan_priority <<
+						     VLAN_PRIO_SHIFT);
 		fs->val.ivlan = vlan_tci;
 		fs->mask.ivlan = vlan_tci_mask;
 
+		fs->val.ivlan_vld = 1;
+		fs->mask.ivlan_vld = 1;
+
 		/* Chelsio adapters use ivlan_vld bit to match vlan packets
 		 * as 802.1Q. Also, when vlan tag is present in packets,
 		 * ethtype match is used then to match on ethtype of inner
@@ -238,8 +210,6 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 		 * ethtype value with ethtype of inner header.
 		 */
 		if (fs->val.ethtype == ETH_P_8021Q) {
-			fs->val.ivlan_vld = 1;
-			fs->mask.ivlan_vld = 1;
 			fs->val.ethtype = 0;
 			fs->mask.ethtype = 0;
 		}
@@ -253,12 +223,14 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 }
 
 static int cxgb4_validate_flow_match(struct net_device *dev,
-				     struct tc_cls_flower_offload *cls)
+				     struct flow_cls_offload *cls)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 ethtype_mask = 0;
 	u16 ethtype_key = 0;
 
-	if (cls->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
@@ -268,36 +240,29 @@ static int cxgb4_validate_flow_match(struct net_device *dev,
 	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
 	      BIT(FLOW_DISSECTOR_KEY_IP))) {
 		netdev_warn(dev, "Unsupported key used: 0x%x\n",
-			    cls->dissector->used_keys);
+			    dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->mask);
-		ethtype_key = ntohs(key->n_proto);
-		ethtype_mask = ntohs(mask->n_proto);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		ethtype_key = ntohs(match.key->n_proto);
+		ethtype_mask = ntohs(match.mask->n_proto);
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
 		u16 eth_ip_type = ethtype_key & ethtype_mask;
-		struct flow_dissector_key_ip *mask;
+		struct flow_match_ip match;
 
 		if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) {
 			netdev_err(dev, "IP Key supported only with IPv4/v6");
 			return -EINVAL;
 		}
 
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_IP,
-						 cls->mask);
-		if (mask->ttl) {
+		flow_rule_match_ip(rule, &match);
+		if (match.mask->ttl) {
 			netdev_warn(dev, "ttl match unsupported for offload");
 			return -EOPNOTSUPP;
 		}
@@ -328,7 +293,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 				u32 mask, u32 offset, u8 htype)
 {
 	switch (htype) {
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+	case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
 		switch (offset) {
 		case PEDIT_ETH_DMAC_31_0:
 			fs->newdmac = 1;
@@ -346,7 +311,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 			offload_pedit(fs, val, mask, ETH_SMAC_47_16);
 		}
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
 		switch (offset) {
 		case PEDIT_IP4_SRC:
 			offload_pedit(fs, val, mask, IP4_SRC);
@@ -356,7 +321,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
 		switch (offset) {
 		case PEDIT_IP6_SRC_31_0:
 			offload_pedit(fs, val, mask, IP6_SRC_31_0);
@@ -384,7 +349,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
 		switch (offset) {
 		case PEDIT_TCP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
@@ -397,7 +362,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
 		switch (offset) {
 		case PEDIT_UDP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
@@ -413,59 +378,66 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 }
 
 static void cxgb4_process_flow_actions(struct net_device *in,
-				       struct tc_cls_flower_offload *cls,
+				       struct flow_cls_offload *cls,
 				       struct ch_filter_specification *fs)
 {
-	const struct tc_action *a;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_action_entry *act;
 	int i;
 
-	tcf_exts_for_each_action(i, a, cls->exts) {
-		if (is_tcf_gact_ok(a)) {
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
 			fs->action = FILTER_PASS;
-		} else if (is_tcf_gact_shot(a)) {
+			break;
+		case FLOW_ACTION_DROP:
 			fs->action = FILTER_DROP;
-		} else if (is_tcf_mirred_egress_redirect(a)) {
-			struct net_device *out = tcf_mirred_dev(a);
+			break;
+		case FLOW_ACTION_REDIRECT: {
+			struct net_device *out = act->dev;
 			struct port_info *pi = netdev_priv(out);
 
 			fs->action = FILTER_SWITCH;
 			fs->eport = pi->port_id;
-		} else if (is_tcf_vlan(a)) {
-			u32 vlan_action = tcf_vlan_action(a);
-			u8 prio = tcf_vlan_push_prio(a);
-			u16 vid = tcf_vlan_push_vid(a);
+			}
+			break;
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_MANGLE: {
+			u8 prio = act->vlan.prio;
+			u16 vid = act->vlan.vid;
 			u16 vlan_tci = (prio << VLAN_PRIO_SHIFT) | vid;
-
-			switch (vlan_action) {
-			case TCA_VLAN_ACT_POP:
+			switch (act->id) {
+			case FLOW_ACTION_VLAN_POP:
 				fs->newvlan |= VLAN_REMOVE;
 				break;
-			case TCA_VLAN_ACT_PUSH:
+			case FLOW_ACTION_VLAN_PUSH:
 				fs->newvlan |= VLAN_INSERT;
 				fs->vlan = vlan_tci;
 				break;
-			case TCA_VLAN_ACT_MODIFY:
+			case FLOW_ACTION_VLAN_MANGLE:
 				fs->newvlan |= VLAN_REWRITE;
 				fs->vlan = vlan_tci;
 				break;
 			default:
 				break;
 			}
-		} else if (is_tcf_pedit(a)) {
+			}
+			break;
+		case FLOW_ACTION_MANGLE: {
 			u32 mask, val, offset;
-			int nkeys, i;
 			u8 htype;
 
-			nkeys = tcf_pedit_nkeys(a);
-			for (i = 0; i < nkeys; i++) {
-				htype = tcf_pedit_htype(a, i);
-				mask = tcf_pedit_mask(a, i);
-				val = tcf_pedit_val(a, i);
-				offset = tcf_pedit_offset(a, i);
+			htype = act->mangle.htype;
+			mask = act->mangle.mask;
+			val = act->mangle.val;
+			offset = act->mangle.offset;
 
-				process_pedit_field(fs, val, mask, offset,
-						    htype);
+			process_pedit_field(fs, val, mask, offset, htype);
 			}
+			break;
+		default:
+			break;
 		}
 	}
 }
@@ -484,126 +456,116 @@ static bool valid_l4_mask(u32 mask)
 }
 
 static bool valid_pedit_action(struct net_device *dev,
-			       const struct tc_action *a)
+			       const struct flow_action_entry *act)
 {
 	u32 mask, offset;
-	u8 cmd, htype;
-	int nkeys, i;
-
-	nkeys = tcf_pedit_nkeys(a);
-	for (i = 0; i < nkeys; i++) {
-		htype = tcf_pedit_htype(a, i);
-		cmd = tcf_pedit_cmd(a, i);
-		mask = tcf_pedit_mask(a, i);
-		offset = tcf_pedit_offset(a, i);
-
-		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) {
-			netdev_err(dev, "%s: Unsupported pedit cmd\n",
+	u8 htype;
+
+	htype = act->mangle.htype;
+	mask = act->mangle.mask;
+	offset = act->mangle.offset;
+
+	switch (htype) {
+	case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+		switch (offset) {
+		case PEDIT_ETH_DMAC_31_0:
+		case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
+		case PEDIT_ETH_SMAC_47_16:
+			break;
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
 				   __func__);
 			return false;
 		}
-
-		switch (htype) {
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
-			switch (offset) {
-			case PEDIT_ETH_DMAC_31_0:
-			case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
-			case PEDIT_ETH_SMAC_47_16:
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
-					   __func__);
-				return false;
-			}
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
-			switch (offset) {
-			case PEDIT_IP4_SRC:
-			case PEDIT_IP4_DST:
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
-					   __func__);
-				return false;
-			}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+		switch (offset) {
+		case PEDIT_IP4_SRC:
+		case PEDIT_IP4_DST:
 			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
-			switch (offset) {
-			case PEDIT_IP6_SRC_31_0:
-			case PEDIT_IP6_SRC_63_32:
-			case PEDIT_IP6_SRC_95_64:
-			case PEDIT_IP6_SRC_127_96:
-			case PEDIT_IP6_DST_31_0:
-			case PEDIT_IP6_DST_63_32:
-			case PEDIT_IP6_DST_95_64:
-			case PEDIT_IP6_DST_127_96:
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
-					   __func__);
-				return false;
-			}
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
+				   __func__);
+			return false;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
+		switch (offset) {
+		case PEDIT_IP6_SRC_31_0:
+		case PEDIT_IP6_SRC_63_32:
+		case PEDIT_IP6_SRC_95_64:
+		case PEDIT_IP6_SRC_127_96:
+		case PEDIT_IP6_DST_31_0:
+		case PEDIT_IP6_DST_63_32:
+		case PEDIT_IP6_DST_95_64:
+		case PEDIT_IP6_DST_127_96:
 			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
-			switch (offset) {
-			case PEDIT_TCP_SPORT_DPORT:
-				if (!valid_l4_mask(~mask)) {
-					netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n",
-						   __func__);
-					return false;
-				}
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
+				   __func__);
+			return false;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+		switch (offset) {
+		case PEDIT_TCP_SPORT_DPORT:
+			if (!valid_l4_mask(~mask)) {
+				netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n",
 					   __func__);
 				return false;
 			}
 			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
-			switch (offset) {
-			case PEDIT_UDP_SPORT_DPORT:
-				if (!valid_l4_mask(~mask)) {
-					netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n",
-						   __func__);
-					return false;
-				}
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
+				   __func__);
+			return false;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+		switch (offset) {
+		case PEDIT_UDP_SPORT_DPORT:
+			if (!valid_l4_mask(~mask)) {
+				netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n",
 					   __func__);
 				return false;
 			}
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported pedit type\n",
+			netdev_err(dev, "%s: Unsupported pedit field\n",
 				   __func__);
 			return false;
 		}
+		break;
+	default:
+		netdev_err(dev, "%s: Unsupported pedit type\n", __func__);
+		return false;
 	}
 	return true;
 }
 
 static int cxgb4_validate_flow_actions(struct net_device *dev,
-				       struct tc_cls_flower_offload *cls)
+				       struct flow_cls_offload *cls)
 {
-	const struct tc_action *a;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
+	struct flow_action_entry *act;
 	bool act_redir = false;
 	bool act_pedit = false;
 	bool act_vlan = false;
 	int i;
 
-	tcf_exts_for_each_action(i, a, cls->exts) {
-		if (is_tcf_gact_ok(a)) {
-			/* Do nothing */
-		} else if (is_tcf_gact_shot(a)) {
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
+		case FLOW_ACTION_DROP:
 			/* Do nothing */
-		} else if (is_tcf_mirred_egress_redirect(a)) {
+			break;
+		case FLOW_ACTION_REDIRECT: {
 			struct adapter *adap = netdev2adap(dev);
 			struct net_device *n_dev, *target_dev;
 			unsigned int i;
 			bool found = false;
 
-			target_dev = tcf_mirred_dev(a);
+			target_dev = act->dev;
 			for_each_port(adap, i) {
 				n_dev = adap->port[i];
 				if (target_dev == n_dev) {
@@ -621,15 +583,18 @@ static int cxgb4_validate_flow_actions(struct net_device *dev,
 				return -EINVAL;
 			}
 			act_redir = true;
-		} else if (is_tcf_vlan(a)) {
-			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
-			u32 vlan_action = tcf_vlan_action(a);
+			}
+			break;
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_MANGLE: {
+			u16 proto = be16_to_cpu(act->vlan.proto);
 
-			switch (vlan_action) {
-			case TCA_VLAN_ACT_POP:
+			switch (act->id) {
+			case FLOW_ACTION_VLAN_POP:
 				break;
-			case TCA_VLAN_ACT_PUSH:
-			case TCA_VLAN_ACT_MODIFY:
+			case FLOW_ACTION_VLAN_PUSH:
+			case FLOW_ACTION_VLAN_MANGLE:
 				if (proto != ETH_P_8021Q) {
 					netdev_err(dev, "%s: Unsupported vlan proto\n",
 						   __func__);
@@ -642,13 +607,17 @@ static int cxgb4_validate_flow_actions(struct net_device *dev,
 				return -EOPNOTSUPP;
 			}
 			act_vlan = true;
-		} else if (is_tcf_pedit(a)) {
-			bool pedit_valid = valid_pedit_action(dev, a);
+			}
+			break;
+		case FLOW_ACTION_MANGLE: {
+			bool pedit_valid = valid_pedit_action(dev, act);
 
 			if (!pedit_valid)
 				return -EOPNOTSUPP;
 			act_pedit = true;
-		} else {
+			}
+			break;
+		default:
 			netdev_err(dev, "%s: Unsupported action\n", __func__);
 			return -EOPNOTSUPP;
 		}
@@ -664,7 +633,7 @@ static int cxgb4_validate_flow_actions(struct net_device *dev,
 }
 
 int cxgb4_tc_flower_replace(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls)
+			    struct flow_cls_offload *cls)
 {
 	struct adapter *adap = netdev2adap(dev);
 	struct ch_tc_flower_entry *ch_flower;
@@ -719,11 +688,8 @@ int cxgb4_tc_flower_replace(struct net_device *dev,
 
 	ret = ctx.result;
 	/* Check if hw returned error for filter creation */
-	if (ret) {
-		netdev_err(dev, "%s: filter creation err %d\n",
-			   __func__, ret);
+	if (ret)
 		goto free_entry;
-	}
 
 	ch_flower->tc_flower_cookie = cls->cookie;
 	ch_flower->filter_id = ctx.tid;
@@ -743,7 +709,7 @@ free_entry:
 }
 
 int cxgb4_tc_flower_destroy(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls)
+			    struct flow_cls_offload *cls)
 {
 	struct adapter *adap = netdev2adap(dev);
 	struct ch_tc_flower_entry *ch_flower;
@@ -817,7 +783,7 @@ static void ch_flower_stats_cb(struct timer_list *t)
 }
 
 int cxgb4_tc_flower_stats(struct net_device *dev,
-			  struct tc_cls_flower_offload *cls)
+			  struct flow_cls_offload *cls)
 {
 	struct adapter *adap = netdev2adap(dev);
 	struct ch_tc_flower_stats *ofld_stats;
@@ -843,9 +809,9 @@ int cxgb4_tc_flower_stats(struct net_device *dev,
 	if (ofld_stats->packet_count != packets) {
 		if (ofld_stats->prev_packet_count != packets)
 			ofld_stats->last_used = jiffies;
-		tcf_exts_stats_update(cls->exts, bytes - ofld_stats->byte_count,
-				      packets - ofld_stats->packet_count,
-				      ofld_stats->last_used);
+		flow_stats_update(&cls->stats, bytes - ofld_stats->byte_count,
+				  packets - ofld_stats->packet_count,
+				  ofld_stats->last_used);
 
 		ofld_stats->packet_count = packets;
 		ofld_stats->byte_count = bytes;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
index 050c8a50ae41..eb4c95248baf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
@@ -109,11 +109,11 @@ struct ch_tc_pedit_fields {
 #define PEDIT_UDP_SPORT_DPORT		0x0
 
 int cxgb4_tc_flower_replace(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls);
+			    struct flow_cls_offload *cls);
 int cxgb4_tc_flower_destroy(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls);
+			    struct flow_cls_offload *cls);
 int cxgb4_tc_flower_stats(struct net_device *dev,
-			  struct tc_cls_flower_offload *cls);
+			  struct flow_cls_offload *cls);
 
 int cxgb4_init_tc_flower(struct adapter *adap);
 void cxgb4_cleanup_tc_flower(struct adapter *adap);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
index c7d2b4dc7568..02fc63fa7f25 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
@@ -444,8 +444,7 @@ struct cxgb4_tc_u32_table *cxgb4_init_tc_u32(struct adapter *adap)
 	if (!max_tids)
 		return NULL;
 
-	t = kvzalloc(sizeof(*t) +
-			 (max_tids * sizeof(struct cxgb4_link)), GFP_KERNEL);
+	t = kvzalloc(struct_size(t, table, max_tids), GFP_KERNEL);
 	if (!t)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
index 28052e7504e5..3de8a5e83b6c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_thermal.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Copyright (C) 2017 Chelsio Communications.  All rights reserved.
  *
- *  This program is free software; you can redistribute it and/or modify it
- *  under the terms and conditions of the GNU General Public License,
- *  version 2, as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- *  more details.
- *
- *  The full GNU General Public License is included in this distribution in
- *  the file called "COPYING".
- *
  *  Written by: Ganesh Goudar (ganeshgr@chelsio.com)
  */
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index c041f44324db..5b602243d573 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -147,7 +147,7 @@ static int alloc_uld_rxqs(struct adapter *adap,
 
 	per_chan = rxq_info->nrxq / adap->params.nports;
 
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		msi_idx = 1;
 	else
 		msi_idx = -((int)s->intrq.abs_id + 1);
@@ -195,7 +195,7 @@ setup_sge_queues_uld(struct adapter *adap, unsigned int uld_type, bool lro)
 	struct sge_uld_rxq_info *rxq_info = adap->sge.uld_rxq_info[uld_type];
 	int i, ret = 0;
 
-	if (adap->flags & USING_MSIX) {
+	if (adap->flags & CXGB4_USING_MSIX) {
 		rxq_info->msix_tbl = kcalloc((rxq_info->nrxq + rxq_info->nciq),
 					     sizeof(unsigned short),
 					     GFP_KERNEL);
@@ -206,7 +206,7 @@ setup_sge_queues_uld(struct adapter *adap, unsigned int uld_type, bool lro)
 	ret = !(!alloc_uld_rxqs(adap, rxq_info, lro));
 
 	/* Tell uP to route control queue completions to rdma rspq */
-	if (adap->flags & FULL_INIT_DONE &&
+	if (adap->flags & CXGB4_FULL_INIT_DONE &&
 	    !ret && uld_type == CXGB4_ULD_RDMA) {
 		struct sge *s = &adap->sge;
 		unsigned int cmplqid;
@@ -239,7 +239,7 @@ static void free_sge_queues_uld(struct adapter *adap, unsigned int uld_type)
 {
 	struct sge_uld_rxq_info *rxq_info = adap->sge.uld_rxq_info[uld_type];
 
-	if (adap->flags & FULL_INIT_DONE && uld_type == CXGB4_ULD_RDMA) {
+	if (adap->flags & CXGB4_FULL_INIT_DONE && uld_type == CXGB4_ULD_RDMA) {
 		struct sge *s = &adap->sge;
 		u32 param, cmdop, cmplqid = 0;
 		int i;
@@ -258,7 +258,7 @@ static void free_sge_queues_uld(struct adapter *adap, unsigned int uld_type)
 		t4_free_uld_rxqs(adap, rxq_info->nciq,
 				 rxq_info->uldrxq + rxq_info->nrxq);
 	t4_free_uld_rxqs(adap, rxq_info->nrxq, rxq_info->uldrxq);
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		kfree(rxq_info->msix_tbl);
 }
 
@@ -273,7 +273,7 @@ static int cfg_queues_uld(struct adapter *adap, unsigned int uld_type,
 	if (!rxq_info)
 		return -ENOMEM;
 
-	if (adap->flags & USING_MSIX && uld_info->nrxq > s->nqs_per_uld) {
+	if (adap->flags & CXGB4_USING_MSIX && uld_info->nrxq > s->nqs_per_uld) {
 		i = s->nqs_per_uld;
 		rxq_info->nrxq = roundup(i, adap->params.nports);
 	} else {
@@ -284,7 +284,7 @@ static int cfg_queues_uld(struct adapter *adap, unsigned int uld_type,
 	if (!uld_info->ciq) {
 		rxq_info->nciq = 0;
 	} else  {
-		if (adap->flags & USING_MSIX)
+		if (adap->flags & CXGB4_USING_MSIX)
 			rxq_info->nciq = min_t(int, s->nqs_per_uld,
 					       num_online_cpus());
 		else
@@ -352,25 +352,32 @@ static int
 request_msix_queue_irqs_uld(struct adapter *adap, unsigned int uld_type)
 {
 	struct sge_uld_rxq_info *rxq_info = adap->sge.uld_rxq_info[uld_type];
+	struct uld_msix_info *minfo;
 	int err = 0;
 	unsigned int idx, bmap_idx;
 
 	for_each_uldrxq(rxq_info, idx) {
 		bmap_idx = rxq_info->msix_tbl[idx];
-		err = request_irq(adap->msix_info_ulds[bmap_idx].vec,
+		minfo = &adap->msix_info_ulds[bmap_idx];
+		err = request_irq(minfo->vec,
 				  t4_sge_intr_msix, 0,
-				  adap->msix_info_ulds[bmap_idx].desc,
+				  minfo->desc,
 				  &rxq_info->uldrxq[idx].rspq);
 		if (err)
 			goto unwind;
+
+		cxgb4_set_msix_aff(adap, minfo->vec,
+				   &minfo->aff_mask, idx);
 	}
 	return 0;
+
 unwind:
 	while (idx-- > 0) {
 		bmap_idx = rxq_info->msix_tbl[idx];
+		minfo = &adap->msix_info_ulds[bmap_idx];
+		cxgb4_clear_msix_aff(minfo->vec, minfo->aff_mask);
 		free_msix_idx_in_bmap(adap, bmap_idx);
-		free_irq(adap->msix_info_ulds[bmap_idx].vec,
-			 &rxq_info->uldrxq[idx].rspq);
+		free_irq(minfo->vec, &rxq_info->uldrxq[idx].rspq);
 	}
 	return err;
 }
@@ -379,14 +386,16 @@ static void
 free_msix_queue_irqs_uld(struct adapter *adap, unsigned int uld_type)
 {
 	struct sge_uld_rxq_info *rxq_info = adap->sge.uld_rxq_info[uld_type];
+	struct uld_msix_info *minfo;
 	unsigned int idx, bmap_idx;
 
 	for_each_uldrxq(rxq_info, idx) {
 		bmap_idx = rxq_info->msix_tbl[idx];
+		minfo = &adap->msix_info_ulds[bmap_idx];
 
+		cxgb4_clear_msix_aff(minfo->vec, minfo->aff_mask);
 		free_msix_idx_in_bmap(adap, bmap_idx);
-		free_irq(adap->msix_info_ulds[bmap_idx].vec,
-			 &rxq_info->uldrxq[idx].rspq);
+		free_irq(minfo->vec, &rxq_info->uldrxq[idx].rspq);
 	}
 }
 
@@ -611,10 +620,10 @@ static void cxgb4_shutdown_uld_adapter(struct adapter *adap, enum cxgb4_uld type
 		adap->uld[type].add = NULL;
 		release_sge_txq_uld(adap, type);
 
-		if (adap->flags & FULL_INIT_DONE)
+		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			quiesce_rx_uld(adap, type);
 
-		if (adap->flags & USING_MSIX)
+		if (adap->flags & CXGB4_USING_MSIX)
 			free_msix_queue_irqs_uld(adap, type);
 
 		free_sge_queues_uld(adap, type);
@@ -660,6 +669,7 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->cclk_ps = 1000000000 / adap->params.vpd.cclk;
 	lld->udb_density = 1 << adap->params.sge.eq_qpp;
 	lld->ucq_density = 1 << adap->params.sge.iq_qpp;
+	lld->sge_host_page_size = 1 << (adap->params.sge.hps + 10);
 	lld->filt_mode = adap->params.tp.vlan_pri_map;
 	/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
 	for (i = 0; i < NCHAN; i++)
@@ -672,7 +682,7 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->sge_egrstatuspagesize = adap->sge.stat_len;
 	lld->sge_pktshift = adap->sge.pktshift;
 	lld->ulp_crypto = adap->params.crypto;
-	lld->enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN;
+	lld->enable_fw_ofld_conn = adap->flags & CXGB4_FW_OFLD_CONN;
 	lld->max_ordird_qp = adap->params.max_ordird_qp;
 	lld->max_ird_adapter = adap->params.max_ird_adapter;
 	lld->ulptx_memwrite_dsgl = adap->params.ulptx_memwrite_dsgl;
@@ -701,7 +711,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	adap->uld[uld].handle = handle;
 	t4_register_netevent_notifier();
 
-	if (adap->flags & FULL_INIT_DONE)
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		adap->uld[uld].state_change(handle, CXGB4_STATE_UP);
 }
 
@@ -736,13 +746,13 @@ void cxgb4_register_uld(enum cxgb4_uld type,
 		ret = setup_sge_queues_uld(adap, type, p->lro);
 		if (ret)
 			goto free_queues;
-		if (adap->flags & USING_MSIX) {
+		if (adap->flags & CXGB4_USING_MSIX) {
 			name_msix_vecs_uld(adap, type);
 			ret = request_msix_queue_irqs_uld(adap, type);
 			if (ret)
 				goto free_rxq;
 		}
-		if (adap->flags & FULL_INIT_DONE)
+		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			enable_rx_uld(adap, type);
 		if (adap->uld[type].add)
 			goto free_irq;
@@ -753,9 +763,9 @@ void cxgb4_register_uld(enum cxgb4_uld type,
 		uld_attach(adap, type);
 		continue;
 free_irq:
-		if (adap->flags & FULL_INIT_DONE)
+		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			quiesce_rx_uld(adap, type);
-		if (adap->flags & USING_MSIX)
+		if (adap->flags & CXGB4_USING_MSIX)
 			free_msix_queue_irqs_uld(adap, type);
 free_rxq:
 		free_sge_queues_uld(adap, type);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 5fa9a2d5fc4b..cee582e36134 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -292,6 +292,7 @@ struct cxgb4_virt_res {                      /* virtualized HW resources */
 	struct cxgb4_range ocq;
 	struct cxgb4_range key;
 	unsigned int ncrypto_fc;
+	struct cxgb4_range ppod_edram;
 };
 
 struct chcr_stats_debug {
@@ -336,6 +337,7 @@ struct cxgb4_lld_info {
 	unsigned int cclk_ps;                /* Core clock period in psec */
 	unsigned short udb_density;          /* # of user DB/page */
 	unsigned short ucq_density;          /* # of user CQs/page */
+	unsigned int sge_host_page_size;     /* SGE host page size */
 	unsigned short filt_mode;            /* filter optional components */
 	unsigned short tx_modq[NCHAN];       /* maps each tx channel to a */
 					     /* scheduler queue */
@@ -392,6 +394,7 @@ int cxgb4_immdata_send(struct net_device *dev, unsigned int idx,
 int cxgb4_crypto_send(struct net_device *dev, struct sk_buff *skb);
 unsigned int cxgb4_dbfifo_count(const struct net_device *dev, int lpfifo);
 unsigned int cxgb4_port_chan(const struct net_device *dev);
+unsigned int cxgb4_port_e2cchan(const struct net_device *dev);
 unsigned int cxgb4_port_viid(const struct net_device *dev);
 unsigned int cxgb4_tp_smt_idx(enum chip_type chip, unsigned int viid);
 unsigned int cxgb4_port_idx(const struct net_device *dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 4852febbfec3..1a407d3c1d67 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -646,7 +646,7 @@ struct l2t_data *t4_init_l2t(unsigned int l2t_start, unsigned int l2t_end)
 	if (l2t_size < L2T_MIN_HASH_BUCKETS)
 		return NULL;
 
-	d = kvzalloc(sizeof(*d) + l2t_size * sizeof(struct l2t_entry), GFP_KERNEL);
+	d = kvzalloc(struct_size(d, l2tab, l2t_size), GFP_KERNEL);
 	if (!d)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index 52edb688942b..ba6c153ee45c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -478,7 +478,7 @@ struct sched_table *t4_init_sched(unsigned int sched_size)
 	struct sched_table *s;
 	unsigned int i;
 
-	s = kvzalloc(sizeof(*s) + sched_size * sizeof(struct sched_class), GFP_KERNEL);
+	s = kvzalloc(struct_size(s, tab, sched_size), GFP_KERNEL);
 	if (!s)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index fc0bc6458e84..b3da81e90132 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -80,9 +80,10 @@
  * Max number of Tx descriptors we clean up at a time.  Should be modest as
  * freeing skbs isn't cheap and it happens while holding locks.  We just need
  * to free packets faster than they arrive, we eventually catch up and keep
- * the amortized cost reasonable.  Must be >= 2 * TXQ_STOP_THRES.
+ * the amortized cost reasonable.  Must be >= 2 * TXQ_STOP_THRES.  It should
+ * also match the CIDX Flush Threshold.
  */
-#define MAX_TX_RECLAIM 16
+#define MAX_TX_RECLAIM 32
 
 /*
  * Max number of Rx buffers we replenish at a time.  Again keep this modest,
@@ -401,31 +402,52 @@ static inline int reclaimable(const struct sge_txq *q)
 }
 
 /**
- *	cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors
+ *	reclaim_completed_tx - reclaims completed TX Descriptors
  *	@adap: the adapter
  *	@q: the Tx queue to reclaim completed descriptors from
+ *	@maxreclaim: the maximum number of TX Descriptors to reclaim or -1
  *	@unmap: whether the buffers should be unmapped for DMA
  *
- *	Reclaims Tx descriptors that the SGE has indicated it has processed,
- *	and frees the associated buffers if possible.  Called with the Tx
- *	queue locked.
+ *	Reclaims Tx Descriptors that the SGE has indicated it has processed,
+ *	and frees the associated buffers if possible.  If @max == -1, then
+ *	we'll use a defaiult maximum.  Called with the TX Queue locked.
  */
-inline void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q,
-					bool unmap)
+static inline int reclaim_completed_tx(struct adapter *adap, struct sge_txq *q,
+				       int maxreclaim, bool unmap)
 {
-	int avail = reclaimable(q);
+	int reclaim = reclaimable(q);
 
-	if (avail) {
+	if (reclaim) {
 		/*
 		 * Limit the amount of clean up work we do at a time to keep
 		 * the Tx lock hold time O(1).
 		 */
-		if (avail > MAX_TX_RECLAIM)
-			avail = MAX_TX_RECLAIM;
+		if (maxreclaim < 0)
+			maxreclaim = MAX_TX_RECLAIM;
+		if (reclaim > maxreclaim)
+			reclaim = maxreclaim;
 
-		free_tx_desc(adap, q, avail, unmap);
-		q->in_use -= avail;
+		free_tx_desc(adap, q, reclaim, unmap);
+		q->in_use -= reclaim;
 	}
+
+	return reclaim;
+}
+
+/**
+ *	cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors
+ *	@adap: the adapter
+ *	@q: the Tx queue to reclaim completed descriptors from
+ *	@unmap: whether the buffers should be unmapped for DMA
+ *
+ *	Reclaims Tx descriptors that the SGE has indicated it has processed,
+ *	and frees the associated buffers if possible.  Called with the Tx
+ *	queue locked.
+ */
+void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q,
+				bool unmap)
+{
+	(void)reclaim_completed_tx(adap, q, -1, unmap);
 }
 EXPORT_SYMBOL(cxgb4_reclaim_completed_tx);
 
@@ -454,7 +476,7 @@ static inline int get_buf_size(struct adapter *adapter,
 		break;
 
 	default:
-		BUG_ON(1);
+		BUG();
 	}
 
 	return buf_size;
@@ -1288,6 +1310,44 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb,
 }
 
 /**
+ *	t4_sge_eth_txq_egress_update - handle Ethernet TX Queue update
+ *	@adap: the adapter
+ *	@eq: the Ethernet TX Queue
+ *	@maxreclaim: the maximum number of TX Descriptors to reclaim or -1
+ *
+ *	We're typically called here to update the state of an Ethernet TX
+ *	Queue with respect to the hardware's progress in consuming the TX
+ *	Work Requests that we've put on that Egress Queue.  This happens
+ *	when we get Egress Queue Update messages and also prophylactically
+ *	in regular timer-based Ethernet TX Queue maintenance.
+ */
+int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
+				 int maxreclaim)
+{
+	struct sge_txq *q = &eq->q;
+	unsigned int reclaimed;
+
+	if (!q->in_use || !__netif_tx_trylock(eq->txq))
+		return 0;
+
+	/* Reclaim pending completed TX Descriptors. */
+	reclaimed = reclaim_completed_tx(adap, &eq->q, maxreclaim, true);
+
+	/* If the TX Queue is currently stopped and there's now more than half
+	 * the queue available, restart it.  Otherwise bail out since the rest
+	 * of what we want do here is with the possibility of shipping any
+	 * currently buffered Coalesced TX Work Request.
+	 */
+	if (netif_tx_queue_stopped(eq->txq) && txq_avail(q) > (q->size / 2)) {
+		netif_tx_wake_queue(eq->txq);
+		eq->q.restarts++;
+	}
+
+	__netif_tx_unlock(eq->txq);
+	return reclaimed;
+}
+
+/**
  *	cxgb4_eth_xmit - add a packet to an Ethernet Tx queue
  *	@skb: the packet
  *	@dev: the egress net device
@@ -1357,7 +1417,7 @@ out_free:	dev_kfree_skb_any(skb);
 	}
 	skb_tx_timestamp(skb);
 
-	cxgb4_reclaim_completed_tx(adap, &q->q, true);
+	reclaim_completed_tx(adap, &q->q, -1, true);
 	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
 
 #ifdef CONFIG_CHELSIO_T4_FCOE
@@ -1400,8 +1460,25 @@ out_free:	dev_kfree_skb_any(skb);
 
 	wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2));
 	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		/* After we're done injecting the Work Request for this
+		 * packet, we'll be below our "stop threshold" so stop the TX
+		 * Queue now and schedule a request for an SGE Egress Queue
+		 * Update message. The queue will get started later on when
+		 * the firmware processes this Work Request and sends us an
+		 * Egress Queue Status Update message indicating that space
+		 * has opened up.
+		 */
 		eth_txq_stop(q);
-		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+
+		/* If we're using the SGE Doorbell Queue Timer facility, we
+		 * don't need to ask the Firmware to send us Egress Queue CIDX
+		 * Updates: the Hardware will do this automatically.  And
+		 * since we send the Ingress Queue CIDX Updates to the
+		 * corresponding Ethernet Response Queue, we'll get them very
+		 * quickly.
+		 */
+		if (!q->dbqt)
+			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	wr = (void *)&q->q.desc[q->q.pidx];
@@ -1671,7 +1748,7 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
 	/* Take this opportunity to reclaim any TX Descriptors whose DMA
 	 * transfers have completed.
 	 */
-	cxgb4_reclaim_completed_tx(adapter, &txq->q, true);
+	reclaim_completed_tx(adapter, &txq->q, -1, true);
 
 	/* Calculate the number of flits and TX Descriptors we're going to
 	 * need along with how many TX Descriptors will be left over after
@@ -1715,7 +1792,16 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
 		 * has opened up.
 		 */
 		eth_txq_stop(txq);
-		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+
+		/* If we're using the SGE Doorbell Queue Timer facility, we
+		 * don't need to ask the Firmware to send us Egress Queue CIDX
+		 * Updates: the Hardware will do this automatically.  And
+		 * since we send the Ingress Queue CIDX Updates to the
+		 * corresponding Ethernet Response Queue, we'll get them very
+		 * quickly.
+		 */
+		if (!txq->dbqt)
+			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	/* Start filling in our Work Request.  Note that we do _not_ handle
@@ -2794,6 +2880,74 @@ static int t4_tx_hststamp(struct adapter *adapter, struct sk_buff *skb,
 }
 
 /**
+ *	t4_tx_completion_handler - handle CPL_SGE_EGR_UPDATE messages
+ *	@rspq: Ethernet RX Response Queue associated with Ethernet TX Queue
+ *	@rsp: Response Entry pointer into Response Queue
+ *	@gl: Gather List pointer
+ *
+ *	For adapters which support the SGE Doorbell Queue Timer facility,
+ *	we configure the Ethernet TX Queues to send CIDX Updates to the
+ *	Associated Ethernet RX Response Queue with CPL_SGE_EGR_UPDATE
+ *	messages.  This adds a small load to PCIe Link RX bandwidth and,
+ *	potentially, higher CPU Interrupt load, but allows us to respond
+ *	much more quickly to the CIDX Updates.  This is important for
+ *	Upper Layer Software which isn't willing to have a large amount
+ *	of TX Data outstanding before receiving DMA Completions.
+ */
+static void t4_tx_completion_handler(struct sge_rspq *rspq,
+				     const __be64 *rsp,
+				     const struct pkt_gl *gl)
+{
+	u8 opcode = ((const struct rss_header *)rsp)->opcode;
+	struct port_info *pi = netdev_priv(rspq->netdev);
+	struct adapter *adapter = rspq->adap;
+	struct sge *s = &adapter->sge;
+	struct sge_eth_txq *txq;
+
+	/* skip RSS header */
+	rsp++;
+
+	/* FW can send EGR_UPDATEs encapsulated in a CPL_FW4_MSG.
+	 */
+	if (unlikely(opcode == CPL_FW4_MSG &&
+		     ((const struct cpl_fw4_msg *)rsp)->type ==
+							FW_TYPE_RSSCPL)) {
+		rsp++;
+		opcode = ((const struct rss_header *)rsp)->opcode;
+		rsp++;
+	}
+
+	if (unlikely(opcode != CPL_SGE_EGR_UPDATE)) {
+		pr_info("%s: unexpected FW4/CPL %#x on Rx queue\n",
+			__func__, opcode);
+		return;
+	}
+
+	txq = &s->ethtxq[pi->first_qset + rspq->idx];
+
+	/* We've got the Hardware Consumer Index Update in the Egress Update
+	 * message.  If we're using the SGE Doorbell Queue Timer mechanism,
+	 * these Egress Update messages will be our sole CIDX Updates we get
+	 * since we don't want to chew up PCIe bandwidth for both Ingress
+	 * Messages and Status Page writes.  However, The code which manages
+	 * reclaiming successfully DMA'ed TX Work Requests uses the CIDX value
+	 * stored in the Status Page at the end of the TX Queue.  It's easiest
+	 * to simply copy the CIDX Update value from the Egress Update message
+	 * to the Status Page.  Also note that no Endian issues need to be
+	 * considered here since both are Big Endian and we're just copying
+	 * bytes consistently ...
+	 */
+	if (txq->dbqt) {
+		struct cpl_sge_egr_update *egr;
+
+		egr = (struct cpl_sge_egr_update *)rsp;
+		WRITE_ONCE(txq->q.stat->cidx, egr->cidx);
+	}
+
+	t4_sge_eth_txq_egress_update(adapter, txq, -1);
+}
+
+/**
  *	t4_ethrx_handler - process an ingress ethernet packet
  *	@q: the response queue that received the packet
  *	@rsp: the response queue descriptor holding the RX_PKT message
@@ -2816,6 +2970,15 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 	struct port_info *pi;
 	int ret = 0;
 
+	/* If we're looking at TX Queue CIDX Update, handle that separately
+	 * and return.
+	 */
+	if (unlikely((*(u8 *)rsp == CPL_FW4_MSG) ||
+		     (*(u8 *)rsp == CPL_SGE_EGR_UPDATE))) {
+		t4_tx_completion_handler(q, rsp, si);
+		return 0;
+	}
+
 	if (unlikely(*(u8 *)rsp == cpl_trace_pkt))
 		return handle_trace_pkt(q->adap, si);
 
@@ -3212,7 +3375,7 @@ static irqreturn_t t4_intr_msi(int irq, void *cookie)
 {
 	struct adapter *adap = cookie;
 
-	if (adap->flags & MASTER_PF)
+	if (adap->flags & CXGB4_MASTER_PF)
 		t4_slow_intr_handler(adap);
 	process_intrq(adap);
 	return IRQ_HANDLED;
@@ -3228,7 +3391,7 @@ static irqreturn_t t4_intr_intx(int irq, void *cookie)
 	struct adapter *adap = cookie;
 
 	t4_write_reg(adap, MYPF_REG(PCIE_PF_CLI_A), 0);
-	if (((adap->flags & MASTER_PF) && t4_slow_intr_handler(adap)) |
+	if (((adap->flags & CXGB4_MASTER_PF) && t4_slow_intr_handler(adap)) |
 	    process_intrq(adap))
 		return IRQ_HANDLED;
 	return IRQ_NONE;             /* probably shared interrupt */
@@ -3243,9 +3406,9 @@ static irqreturn_t t4_intr_intx(int irq, void *cookie)
  */
 irq_handler_t t4_intr_handler(struct adapter *adap)
 {
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		return t4_sge_intr_msix;
-	if (adap->flags & USING_MSI)
+	if (adap->flags & CXGB4_USING_MSI)
 		return t4_intr_msi;
 	return t4_intr_intx;
 }
@@ -3278,7 +3441,7 @@ static void sge_rx_timer_cb(struct timer_list *t)
 	 * global Master PF activities like checking for chip ingress stalls,
 	 * etc.
 	 */
-	if (!(adap->flags & MASTER_PF))
+	if (!(adap->flags & CXGB4_MASTER_PF))
 		goto done;
 
 	t4_idma_monitor(adap, &s->idma_monitor, HZ, RX_QCHECK_PERIOD);
@@ -3289,10 +3452,10 @@ done:
 
 static void sge_tx_timer_cb(struct timer_list *t)
 {
-	unsigned long m;
-	unsigned int i, budget;
 	struct adapter *adap = from_timer(adap, t, sge.tx_timer);
 	struct sge *s = &adap->sge;
+	unsigned long m, period;
+	unsigned int i, budget;
 
 	for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++)
 		for (m = s->txq_maperr[i]; m; m &= m - 1) {
@@ -3320,29 +3483,29 @@ static void sge_tx_timer_cb(struct timer_list *t)
 	budget = MAX_TIMER_TX_RECLAIM;
 	i = s->ethtxq_rover;
 	do {
-		struct sge_eth_txq *q = &s->ethtxq[i];
-
-		if (q->q.in_use &&
-		    time_after_eq(jiffies, q->txq->trans_start + HZ / 100) &&
-		    __netif_tx_trylock(q->txq)) {
-			int avail = reclaimable(&q->q);
-
-			if (avail) {
-				if (avail > budget)
-					avail = budget;
-
-				free_tx_desc(adap, &q->q, avail, true);
-				q->q.in_use -= avail;
-				budget -= avail;
-			}
-			__netif_tx_unlock(q->txq);
-		}
+		budget -= t4_sge_eth_txq_egress_update(adap, &s->ethtxq[i],
+						       budget);
+		if (!budget)
+			break;
 
 		if (++i >= s->ethqsets)
 			i = 0;
-	} while (budget && i != s->ethtxq_rover);
+	} while (i != s->ethtxq_rover);
 	s->ethtxq_rover = i;
-	mod_timer(&s->tx_timer, jiffies + (budget ? TX_QCHECK_PERIOD : 2));
+
+	if (budget == 0) {
+		/* If we found too many reclaimable packets schedule a timer
+		 * in the near future to continue where we left off.
+		 */
+		period = 2;
+	} else {
+		/* We reclaimed all reclaimable TX Descriptors, so reschedule
+		 * at the normal period.
+		 */
+		period = TX_QCHECK_PERIOD;
+	}
+
+	mod_timer(&s->tx_timer, jiffies + period);
 }
 
 /**
@@ -3386,7 +3549,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	struct fw_iq_cmd c;
 	struct sge *s = &adap->sge;
 	struct port_info *pi = netdev_priv(dev);
-	int relaxed = !(adap->flags & ROOT_NO_RELAXED_ORDERING);
+	int relaxed = !(adap->flags & CXGB4_ROOT_NO_RELAXED_ORDERING);
 
 	/* Size needs to be multiple of 16, including status entry. */
 	iq->size = roundup(iq->size, 16);
@@ -3421,7 +3584,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 							:  FW_IQ_IQTYPE_OFLD));
 
 	if (fl) {
-		enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
+		unsigned int chip_ver =
+			CHELSIO_CHIP_VERSION(adap->params.chip);
 
 		/* Allocate the ring for the hardware free list (with space
 		 * for its status page) along with the associated software
@@ -3459,10 +3623,10 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		 * the smaller 64-byte value there).
 		 */
 		c.fl0dcaen_to_fl0cidxfthresh =
-			htons(FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ?
+			htons(FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5 ?
 						   FETCHBURSTMIN_128B_X :
-						   FETCHBURSTMIN_64B_X) |
-			      FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ?
+						   FETCHBURSTMIN_64B_T6_X) |
+			      FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ?
 						   FETCHBURSTMAX_512B_X :
 						   FETCHBURSTMAX_256B_X));
 		c.fl0size = htons(flsz);
@@ -3584,14 +3748,24 @@ static void init_txq(struct adapter *adap, struct sge_txq *q, unsigned int id)
 	adap->sge.egr_map[id - adap->sge.egr_start] = q;
 }
 
+/**
+ *	t4_sge_alloc_eth_txq - allocate an Ethernet TX Queue
+ *	@adap: the adapter
+ *	@txq: the SGE Ethernet TX Queue to initialize
+ *	@dev: the Linux Network Device
+ *	@netdevq: the corresponding Linux TX Queue
+ *	@iqid: the Ingress Queue to which to deliver CIDX Update messages
+ *	@dbqt: whether this TX Queue will use the SGE Doorbell Queue Timers
+ */
 int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			 struct net_device *dev, struct netdev_queue *netdevq,
-			 unsigned int iqid)
+			 unsigned int iqid, u8 dbqt)
 {
-	int ret, nentries;
-	struct fw_eq_eth_cmd c;
-	struct sge *s = &adap->sge;
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
 	struct port_info *pi = netdev_priv(dev);
+	struct sge *s = &adap->sge;
+	struct fw_eq_eth_cmd c;
+	int ret, nentries;
 
 	/* Add status entries */
 	nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
@@ -3610,19 +3784,47 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			    FW_EQ_ETH_CMD_VFN_V(0));
 	c.alloc_to_len16 = htonl(FW_EQ_ETH_CMD_ALLOC_F |
 				 FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(c));
-	c.viid_pkd = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
-			   FW_EQ_ETH_CMD_VIID_V(pi->viid));
+
+	/* For TX Ethernet Queues using the SGE Doorbell Queue Timer
+	 * mechanism, we use Ingress Queue messages for Hardware Consumer
+	 * Index Updates on the TX Queue.  Otherwise we have the Hardware
+	 * write the CIDX Updates into the Status Page at the end of the
+	 * TX Queue.
+	 */
+	c.autoequiqe_to_viid = htonl((dbqt
+				      ? FW_EQ_ETH_CMD_AUTOEQUIQE_F
+				      : FW_EQ_ETH_CMD_AUTOEQUEQE_F) |
+				     FW_EQ_ETH_CMD_VIID_V(pi->viid));
+
 	c.fetchszm_to_iqid =
-		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) |
+		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(dbqt
+						 ? HOSTFCMODE_INGRESS_QUEUE_X
+						 : HOSTFCMODE_STATUS_PAGE_X) |
 		      FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid));
+
+	/* Note that the CIDX Flush Threshold should match MAX_TX_RECLAIM. */
 	c.dcaen_to_eqsize =
-		htonl(FW_EQ_ETH_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		htonl(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+					    ? FETCHBURSTMIN_64B_X
+					    : FETCHBURSTMIN_64B_T6_X) |
 		      FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 		      FW_EQ_ETH_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
 		      FW_EQ_ETH_CMD_EQSIZE_V(nentries));
+
 	c.eqaddr = cpu_to_be64(txq->q.phys_addr);
 
+	/* If we're using the SGE Doorbell Queue Timer mechanism, pass in the
+	 * currently configured Timer Index.  THis can be changed later via an
+	 * ethtool -C tx-usecs {Timer Val} command.  Note that the SGE
+	 * Doorbell Queue mode is currently automatically enabled in the
+	 * Firmware by setting either AUTOEQUEQE or AUTOEQUIQE ...
+	 */
+	if (dbqt)
+		c.timeren_timerix =
+			cpu_to_be32(FW_EQ_ETH_CMD_TIMEREN_F |
+				    FW_EQ_ETH_CMD_TIMERIX_V(txq->dbqtimerix));
+
 	ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
 	if (ret) {
 		kfree(txq->q.sdesc);
@@ -3639,6 +3841,8 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 	txq->txq = netdevq;
 	txq->tso = txq->tx_cso = txq->vlan_ins = 0;
 	txq->mapping_err = 0;
+	txq->dbqt = dbqt;
+
 	return 0;
 }
 
@@ -3646,10 +3850,11 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 			  struct net_device *dev, unsigned int iqid,
 			  unsigned int cmplqid)
 {
-	int ret, nentries;
-	struct fw_eq_ctrl_cmd c;
-	struct sge *s = &adap->sge;
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
 	struct port_info *pi = netdev_priv(dev);
+	struct sge *s = &adap->sge;
+	struct fw_eq_ctrl_cmd c;
+	int ret, nentries;
 
 	/* Add status entries */
 	nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
@@ -3673,7 +3878,9 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 		      FW_EQ_CTRL_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_CTRL_CMD_FETCHRO_F | FW_EQ_CTRL_CMD_IQID_V(iqid));
 	c.dcaen_to_eqsize =
-		htonl(FW_EQ_CTRL_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		htonl(FW_EQ_CTRL_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+					     ? FETCHBURSTMIN_64B_X
+					     : FETCHBURSTMIN_64B_T6_X) |
 		      FW_EQ_CTRL_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 		      FW_EQ_CTRL_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
 		      FW_EQ_CTRL_CMD_EQSIZE_V(nentries));
@@ -3713,6 +3920,7 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq,
 			 struct net_device *dev, unsigned int iqid,
 			 unsigned int uld_type)
 {
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
 	int ret, nentries;
 	struct fw_eq_ofld_cmd c;
 	struct sge *s = &adap->sge;
@@ -3743,7 +3951,9 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq,
 		      FW_EQ_OFLD_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_OFLD_CMD_FETCHRO_F | FW_EQ_OFLD_CMD_IQID_V(iqid));
 	c.dcaen_to_eqsize =
-		htonl(FW_EQ_OFLD_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		htonl(FW_EQ_OFLD_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+					     ? FETCHBURSTMIN_64B_X
+					     : FETCHBURSTMIN_64B_T6_X) |
 		      FW_EQ_OFLD_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 		      FW_EQ_OFLD_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
 		      FW_EQ_OFLD_CMD_EQSIZE_V(nentries));
diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c
index 7b2207a2a130..eaf1fb74689c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/smt.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c
@@ -47,8 +47,7 @@ struct smt_data *t4_init_smt(void)
 
 	smt_size = SMT_SIZE;
 
-	s = kvzalloc(sizeof(*s) + smt_size * sizeof(struct smt_entry),
-		     GFP_KERNEL);
+	s = kvzalloc(struct_size(s, smtab, smt_size), GFP_KERNEL);
 	if (!s)
 		return NULL;
 	s->smt_size = smt_size;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/srq.c b/drivers/net/ethernet/chelsio/cxgb4/srq.c
index 82b70a565e24..9a54302bb046 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/srq.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/srq.c
@@ -77,7 +77,7 @@ int cxgb4_get_srq_entry(struct net_device *dev,
 	adap = netdev2adap(dev);
 	s = adap->srq;
 
-	if (!(adap->flags & FULL_INIT_DONE) || !s)
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE) || !s)
 		goto out;
 
 	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 2b03f6187a24..9dd5ed9a2965 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -198,7 +198,7 @@ static void t4_report_fw_error(struct adapter *adap)
 	if (pcie_fw & PCIE_FW_ERR_F) {
 		dev_err(adap->pdev_dev, "Firmware reports adapter error: %s\n",
 			reason[PCIE_FW_EVAL_G(pcie_fw)]);
-		adap->flags &= ~FW_OK;
+		adap->flags &= ~CXGB4_FW_OK;
 	}
 }
 
@@ -3964,6 +3964,14 @@ void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf)
 	}
 }
 
+/* The ADVERT_MASK is used to mask out all of the Advertised Firmware Port
+ * Capabilities which we control with separate controls -- see, for instance,
+ * Pause Frames and Forward Error Correction.  In order to determine what the
+ * full set of Advertised Port Capabilities are, the base Advertised Port
+ * Capabilities (masked by ADVERT_MASK) must be combined with the Advertised
+ * Port Capabilities associated with those other controls.  See
+ * t4_link_acaps() for how this is done.
+ */
 #define ADVERT_MASK (FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_M) | \
 		     FW_PORT_CAP32_ANEG)
 
@@ -4061,6 +4069,9 @@ static inline enum cc_pause fwcap_to_cc_pause(fw_port_cap32_t fw_pause)
 /* Translate Common Code Pause specification into Firmware Port Capabilities */
 static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause)
 {
+	/* Translate orthogonal RX/TX Pause Controls for L1 Configure
+	 * commands, etc.
+	 */
 	fw_port_cap32_t fw_pause = 0;
 
 	if (cc_pause & PAUSE_RX)
@@ -4070,6 +4081,19 @@ static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause)
 	if (!(cc_pause & PAUSE_AUTONEG))
 		fw_pause |= FW_PORT_CAP32_FORCE_PAUSE;
 
+	/* Translate orthogonal Pause controls into IEEE 802.3 Pause,
+	 * Asymetrical Pause for use in reporting to upper layer OS code, etc.
+	 * Note that these bits are ignored in L1 Configure commands.
+	 */
+	if (cc_pause & PAUSE_RX) {
+		if (cc_pause & PAUSE_TX)
+			fw_pause |= FW_PORT_CAP32_802_3_PAUSE;
+		else
+			fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR;
+	} else if (cc_pause & PAUSE_TX) {
+		fw_pause |= FW_PORT_CAP32_802_3_ASM_DIR;
+	}
+
 	return fw_pause;
 }
 
@@ -4100,30 +4124,25 @@ static inline fw_port_cap32_t cc_to_fwcap_fec(enum cc_fec cc_fec)
 }
 
 /**
- *	t4_link_l1cfg - apply link configuration to MAC/PHY
+ *	t4_link_acaps - compute Link Advertised Port Capabilities
  *	@adapter: the adapter
- *	@mbox: the Firmware Mailbox to use
  *	@port: the Port ID
  *	@lc: the Port's Link Configuration
  *
- *	Set up a port's MAC and PHY according to a desired link configuration.
- *	- If the PHY can auto-negotiate first decide what to advertise, then
- *	  enable/disable auto-negotiation as desired, and reset.
- *	- If the PHY does not auto-negotiate just reset it.
- *	- If auto-negotiation is off set the MAC to the proper speed/duplex/FC,
- *	  otherwise do it later based on the outcome of auto-negotiation.
+ *	Synthesize the Advertised Port Capabilities we'll be using based on
+ *	the base Advertised Port Capabilities (which have been filtered by
+ *	ADVERT_MASK) plus the individual controls for things like Pause
+ *	Frames, Forward Error Correction, MDI, etc.
  */
-int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
-		       unsigned int port, struct link_config *lc,
-		       bool sleep_ok, int timeout)
+fw_port_cap32_t t4_link_acaps(struct adapter *adapter, unsigned int port,
+			      struct link_config *lc)
 {
-	unsigned int fw_caps = adapter->params.fw_caps_support;
-	fw_port_cap32_t fw_fc, cc_fec, fw_fec, rcap;
-	struct fw_port_cmd cmd;
+	fw_port_cap32_t fw_fc, fw_fec, acaps;
 	unsigned int fw_mdi;
-	int ret;
+	char cc_fec;
 
 	fw_mdi = (FW_PORT_CAP32_MDI_V(FW_PORT_CAP32_MDI_AUTO) & lc->pcaps);
+
 	/* Convert driver coding of Pause Frame Flow Control settings into the
 	 * Firmware's API.
 	 */
@@ -4143,32 +4162,73 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
 	fw_fec = cc_to_fwcap_fec(cc_fec);
 
 	/* Figure out what our Requested Port Capabilities are going to be.
+	 * Note parallel structure in t4_handle_get_port_info() and
+	 * init_link_config().
 	 */
 	if (!(lc->pcaps & FW_PORT_CAP32_ANEG)) {
-		rcap = lc->acaps | fw_fc | fw_fec;
+		acaps = lc->acaps | fw_fc | fw_fec;
 		lc->fc = lc->requested_fc & ~PAUSE_AUTONEG;
 		lc->fec = cc_fec;
 	} else if (lc->autoneg == AUTONEG_DISABLE) {
-		rcap = lc->speed_caps | fw_fc | fw_fec | fw_mdi;
+		acaps = lc->speed_caps | fw_fc | fw_fec | fw_mdi;
 		lc->fc = lc->requested_fc & ~PAUSE_AUTONEG;
 		lc->fec = cc_fec;
 	} else {
-		rcap = lc->acaps | fw_fc | fw_fec | fw_mdi;
+		acaps = lc->acaps | fw_fc | fw_fec | fw_mdi;
 	}
 
-	/* Note that older Firmware doesn't have FW_PORT_CAP32_FORCE_PAUSE, so
+	/* Some Requested Port Capabilities are trivially wrong if they exceed
+	 * the Physical Port Capabilities.  We can check that here and provide
+	 * moderately useful feedback in the system log.
+	 *
+	 * Note that older Firmware doesn't have FW_PORT_CAP32_FORCE_PAUSE, so
 	 * we need to exclude this from this check in order to maintain
 	 * compatibility ...
 	 */
-	if ((rcap & ~lc->pcaps) & ~FW_PORT_CAP32_FORCE_PAUSE) {
-		dev_err(adapter->pdev_dev,
-			"Requested Port Capabilities %#x exceed Physical Port Capabilities %#x\n",
-			rcap, lc->pcaps);
+	if ((acaps & ~lc->pcaps) & ~FW_PORT_CAP32_FORCE_PAUSE) {
+		dev_err(adapter->pdev_dev, "Requested Port Capabilities %#x exceed Physical Port Capabilities %#x\n",
+			acaps, lc->pcaps);
+		return -EINVAL;
+	}
+
+	return acaps;
+}
+
+/**
+ *	t4_link_l1cfg_core - apply link configuration to MAC/PHY
+ *	@adapter: the adapter
+ *	@mbox: the Firmware Mailbox to use
+ *	@port: the Port ID
+ *	@lc: the Port's Link Configuration
+ *	@sleep_ok: if true we may sleep while awaiting command completion
+ *	@timeout: time to wait for command to finish before timing out
+ *		(negative implies @sleep_ok=false)
+ *
+ *	Set up a port's MAC and PHY according to a desired link configuration.
+ *	- If the PHY can auto-negotiate first decide what to advertise, then
+ *	  enable/disable auto-negotiation as desired, and reset.
+ *	- If the PHY does not auto-negotiate just reset it.
+ *	- If auto-negotiation is off set the MAC to the proper speed/duplex/FC,
+ *	  otherwise do it later based on the outcome of auto-negotiation.
+ */
+int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
+		       unsigned int port, struct link_config *lc,
+		       u8 sleep_ok, int timeout)
+{
+	unsigned int fw_caps = adapter->params.fw_caps_support;
+	struct fw_port_cmd cmd;
+	fw_port_cap32_t rcap;
+	int ret;
+
+	if (!(lc->pcaps & FW_PORT_CAP32_ANEG) &&
+	    lc->autoneg == AUTONEG_ENABLE) {
 		return -EINVAL;
 	}
 
-	/* And send that on to the Firmware ...
+	/* Compute our Requested Port Capabilities and send that on to the
+	 * Firmware.
 	 */
+	rcap = t4_link_acaps(adapter, port, lc);
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) |
 				       FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
@@ -4185,13 +4245,20 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
 
 	ret = t4_wr_mbox_meat_timeout(adapter, mbox, &cmd, sizeof(cmd), NULL,
 				      sleep_ok, timeout);
+
+	/* Unfortunately, even if the Requested Port Capabilities "fit" within
+	 * the Physical Port Capabilities, some combinations of features may
+	 * still not be leagal.  For example, 40Gb/s and Reed-Solomon Forward
+	 * Error Correction.  So if the Firmware rejects the L1 Configure
+	 * request, flag that here.
+	 */
 	if (ret) {
 		dev_err(adapter->pdev_dev,
 			"Requested Port Capabilities %#x rejected, error %d\n",
 			rcap, -ret);
 		return ret;
 	}
-	return ret;
+	return 0;
 }
 
 /**
@@ -4942,7 +5009,13 @@ static void pl_intr_handler(struct adapter *adap)
  */
 int t4_slow_intr_handler(struct adapter *adapter)
 {
-	u32 cause = t4_read_reg(adapter, PL_INT_CAUSE_A);
+	/* There are rare cases where a PL_INT_CAUSE bit may end up getting
+	 * set when the corresponding PL_INT_ENABLE bit isn't set.  It's
+	 * easiest just to mask that case here.
+	 */
+	u32 raw_cause = t4_read_reg(adapter, PL_INT_CAUSE_A);
+	u32 enable = t4_read_reg(adapter, PL_INT_ENABLE_A);
+	u32 cause = raw_cause & enable;
 
 	if (!(cause & GLBL_INTR_MASK))
 		return 0;
@@ -4994,7 +5067,7 @@ int t4_slow_intr_handler(struct adapter *adapter)
 		ulptx_intr_handler(adapter);
 
 	/* Clear the interrupts just processed for which we are the master. */
-	t4_write_reg(adapter, PL_INT_CAUSE_A, cause & GLBL_INTR_MASK);
+	t4_write_reg(adapter, PL_INT_CAUSE_A, raw_cause & GLBL_INTR_MASK);
 	(void)t4_read_reg(adapter, PL_INT_CAUSE_A); /* flush */
 	return 1;
 }
@@ -5217,7 +5290,7 @@ int t4_read_rss(struct adapter *adapter, u16 *map)
 
 static unsigned int t4_use_ldst(struct adapter *adap)
 {
-	return (adap->flags & FW_OK) && !adap->use_bd;
+	return (adap->flags & CXGB4_FW_OK) && !adap->use_bd;
 }
 
 /**
@@ -6106,7 +6179,7 @@ unsigned int t4_get_mps_bg_map(struct adapter *adapter, int pidx)
 	 *        ( MPSBGMAP[Port 1] <<  8 ) |
 	 *        ( MPSBGMAP[Port 0] <<  0 ))
 	 */
-	if (adapter->flags & FW_OK) {
+	if (adapter->flags & CXGB4_FW_OK) {
 		u32 param, val;
 		int ret;
 
@@ -6136,6 +6209,37 @@ unsigned int t4_get_mps_bg_map(struct adapter *adapter, int pidx)
 }
 
 /**
+ *      t4_get_tp_e2c_map - return the E2C channel map associated with a port
+ *      @adapter: the adapter
+ *      @pidx: the port index
+ */
+static unsigned int t4_get_tp_e2c_map(struct adapter *adapter, int pidx)
+{
+	unsigned int nports;
+	u32 param, val = 0;
+	int ret;
+
+	nports = 1 << NUMPORTS_G(t4_read_reg(adapter, MPS_CMN_CTL_A));
+	if (pidx >= nports) {
+		CH_WARN(adapter, "TP E2C Channel Port Index %d >= Nports %d\n",
+			pidx, nports);
+		return 0;
+	}
+
+	/* FW version >= 1.16.44.0 can determine E2C channel map using
+	 * FW_PARAMS_PARAM_DEV_TPCHMAP API.
+	 */
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_TPCHMAP));
+	ret = t4_query_params_ns(adapter, adapter->mbox, adapter->pf,
+				 0, 1, &param, &val);
+	if (!ret)
+		return (val >> (8 * pidx)) & 0xff;
+
+	return 0;
+}
+
+/**
  *	t4_get_tp_ch_map - return TP ingress channels associated with a port
  *	@adapter: the adapter
  *	@pidx: the port index
@@ -6693,6 +6797,47 @@ int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type)
 }
 
 /**
+ *	t4_read_sge_dbqtimers - reag SGE Doorbell Queue Timer values
+ *	@adap - the adapter
+ *	@ndbqtimers: size of the provided SGE Doorbell Queue Timer table
+ *	@dbqtimers: SGE Doorbell Queue Timer table
+ *
+ *	Reads the SGE Doorbell Queue Timer values into the provided table.
+ *	Returns 0 on success (Firmware and Hardware support this feature),
+ *	an error on failure.
+ */
+int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers,
+			  u16 *dbqtimers)
+{
+	int ret, dbqtimerix;
+
+	ret = 0;
+	dbqtimerix = 0;
+	while (dbqtimerix < ndbqtimers) {
+		int nparams, param;
+		u32 params[7], vals[7];
+
+		nparams = ndbqtimers - dbqtimerix;
+		if (nparams > ARRAY_SIZE(params))
+			nparams = ARRAY_SIZE(params);
+
+		for (param = 0; param < nparams; param++)
+			params[param] =
+			  (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+			   FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMER) |
+			   FW_PARAMS_PARAM_Y_V(dbqtimerix + param));
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
+				      nparams, params, vals);
+		if (ret)
+			break;
+
+		for (param = 0; param < nparams; param++)
+			dbqtimers[dbqtimerix++] = vals[param];
+	}
+	return ret;
+}
+
+/**
  *      t4_fw_hello - establish communication with FW
  *      @adap: the adapter
  *      @mbox: mailbox to use for the FW command
@@ -7026,10 +7171,10 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
 	if (!t4_fw_matches_chip(adap, fw_hdr))
 		return -EINVAL;
 
-	/* Disable FW_OK flag so that mbox commands with FW_OK flag set
-	 * wont be sent when we are flashing FW.
+	/* Disable CXGB4_FW_OK flag so that mbox commands with CXGB4_FW_OK flag
+	 * set wont be sent when we are flashing FW.
 	 */
-	adap->flags &= ~FW_OK;
+	adap->flags &= ~CXGB4_FW_OK;
 
 	ret = t4_fw_halt(adap, mbox, force);
 	if (ret < 0 && !force)
@@ -7068,7 +7213,7 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
 	 */
 	(void)t4_init_devlog_params(adap);
 out:
-	adap->flags |= FW_OK;
+	adap->flags |= CXGB4_FW_OK;
 	return ret;
 }
 
@@ -7139,10 +7284,21 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 			 unsigned int cache_line_size)
 {
 	unsigned int page_shift = fls(page_size) - 1;
+	unsigned int sge_hps = page_shift - 10;
 	unsigned int stat_len = cache_line_size > 64 ? 128 : 64;
 	unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size;
 	unsigned int fl_align_log = fls(fl_align) - 1;
 
+	t4_write_reg(adap, SGE_HOST_PAGE_SIZE_A,
+		     HOSTPAGESIZEPF0_V(sge_hps) |
+		     HOSTPAGESIZEPF1_V(sge_hps) |
+		     HOSTPAGESIZEPF2_V(sge_hps) |
+		     HOSTPAGESIZEPF3_V(sge_hps) |
+		     HOSTPAGESIZEPF4_V(sge_hps) |
+		     HOSTPAGESIZEPF5_V(sge_hps) |
+		     HOSTPAGESIZEPF6_V(sge_hps) |
+		     HOSTPAGESIZEPF7_V(sge_hps));
+
 	if (is_t4(adap->params.chip)) {
 		t4_set_reg_field(adap, SGE_CONTROL_A,
 				 INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
@@ -8461,6 +8617,10 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 	fc = fwcap_to_cc_pause(linkattr);
 	speed = fwcap_to_speed(linkattr);
 
+	/* Reset state for communicating new Transceiver Module status and
+	 * whether the OS-dependent layer wants us to redo the current
+	 * "sticky" L1 Configure Link Parameters.
+	 */
 	lc->new_module = false;
 	lc->redo_l1cfg = false;
 
@@ -8497,9 +8657,15 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 		 */
 		pi->port_type = port_type;
 
+		/* Record new Module Type information.
+		 */
 		pi->mod_type = mod_type;
 
+		/* Let the OS-dependent layer know if we have a new
+		 * Transceiver Module inserted.
+		 */
 		lc->new_module = t4_is_inserted_mod_type(mod_type);
+
 		t4_os_portmod_changed(adapter, pi->port_id);
 	}
 
@@ -8507,8 +8673,10 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 	    fc != lc->fc || fec != lc->fec) {	/* something changed */
 		if (!link_ok && lc->link_ok) {
 			lc->link_down_rc = linkdnrc;
-			dev_warn(adapter->pdev_dev, "Port %d link down, reason: %s\n",
-				 pi->tx_chan, t4_link_down_rc_str(linkdnrc));
+			dev_warn_ratelimited(adapter->pdev_dev,
+					     "Port %d link down, reason: %s\n",
+					     pi->tx_chan,
+					     t4_link_down_rc_str(linkdnrc));
 		}
 		lc->link_ok = link_ok;
 		lc->speed = speed;
@@ -8518,6 +8686,11 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 		lc->lpacaps = lpacaps;
 		lc->acaps = acaps & ADVERT_MASK;
 
+		/* If we're not physically capable of Auto-Negotiation, note
+		 * this as Auto-Negotiation disabled.  Otherwise, we track
+		 * what Auto-Negotiation settings we have.  Note parallel
+		 * structure in t4_link_l1cfg_core() and init_link_config().
+		 */
 		if (!(lc->acaps & FW_PORT_CAP32_ANEG)) {
 			lc->autoneg = AUTONEG_DISABLE;
 		} else if (lc->acaps & FW_PORT_CAP32_ANEG) {
@@ -8535,6 +8708,10 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 		t4_os_link_changed(adapter, pi->port_id, link_ok);
 	}
 
+	/* If we have a new Transceiver Module and the OS-dependent code has
+	 * told us that it wants us to redo whatever "sticky" L1 Configuration
+	 * Link Parameters are set, do that now.
+	 */
 	if (lc->new_module && lc->redo_l1cfg) {
 		struct link_config old_lc;
 		int ret;
@@ -9222,8 +9399,9 @@ int t4_init_sge_params(struct adapter *adapter)
  */
 int t4_init_tp_params(struct adapter *adap, bool sleep_ok)
 {
-	int chan;
-	u32 v;
+	u32 param, val, v;
+	int chan, ret;
+
 
 	v = t4_read_reg(adap, TP_TIMER_RESOLUTION_A);
 	adap->params.tp.tre = TIMERRESOLUTION_G(v);
@@ -9233,11 +9411,47 @@ int t4_init_tp_params(struct adapter *adap, bool sleep_ok)
 	for (chan = 0; chan < NCHAN; chan++)
 		adap->params.tp.tx_modq[chan] = chan;
 
-	/* Cache the adapter's Compressed Filter Mode and global Incress
+	/* Cache the adapter's Compressed Filter Mode/Mask and global Ingress
 	 * Configuration.
 	 */
-	t4_tp_pio_read(adap, &adap->params.tp.vlan_pri_map, 1,
-		       TP_VLAN_PRI_MAP_A, sleep_ok);
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_FILTER) |
+		 FW_PARAMS_PARAM_Y_V(FW_PARAM_DEV_FILTER_MODE_MASK));
+
+	/* Read current value */
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
+			      &param, &val);
+	if (ret == 0) {
+		dev_info(adap->pdev_dev,
+			 "Current filter mode/mask 0x%x:0x%x\n",
+			 FW_PARAMS_PARAM_FILTER_MODE_G(val),
+			 FW_PARAMS_PARAM_FILTER_MASK_G(val));
+		adap->params.tp.vlan_pri_map =
+			FW_PARAMS_PARAM_FILTER_MODE_G(val);
+		adap->params.tp.filter_mask =
+			FW_PARAMS_PARAM_FILTER_MASK_G(val);
+	} else {
+		dev_info(adap->pdev_dev,
+			 "Failed to read filter mode/mask via fw api, using indirect-reg-read\n");
+
+		/* Incase of older-fw (which doesn't expose the api
+		 * FW_PARAM_DEV_FILTER_MODE_MASK) and newer-driver (which uses
+		 * the fw api) combination, fall-back to older method of reading
+		 * the filter mode from indirect-register
+		 */
+		t4_tp_pio_read(adap, &adap->params.tp.vlan_pri_map, 1,
+			       TP_VLAN_PRI_MAP_A, sleep_ok);
+
+		/* With the older-fw and newer-driver combination we might run
+		 * into an issue when user wants to use hash filter region but
+		 * the filter_mask is zero, in this case filter_mask validation
+		 * is tough. To avoid that we set the filter_mask same as filter
+		 * mode, which will behave exactly as the older way of ignoring
+		 * the filter mask validation.
+		 */
+		adap->params.tp.filter_mask = adap->params.tp.vlan_pri_map;
+	}
+
 	t4_tp_pio_read(adap, &adap->params.tp.ingress_config, 1,
 		       TP_INGRESS_CONFIG_A, sleep_ok);
 
@@ -9448,6 +9662,7 @@ int t4_init_portinfo(struct port_info *pi, int mbox,
 	pi->tx_chan = port;
 	pi->lport = port;
 	pi->rss_size = rss_size;
+	pi->rx_cchan = t4_get_tp_e2c_map(pi->adapter, port);
 
 	/* If fw supports returning the VIN as part of FW_VI_CMD,
 	 * save the returned values.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
index 361d5032c288..002fc62ea726 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
@@ -91,6 +91,7 @@ enum {
 	SGE_CTXT_SIZE = 24,       /* size of SGE context */
 	SGE_NTIMERS = 6,          /* # of interrupt holdoff timer values */
 	SGE_NCOUNTERS = 4,        /* # of interrupt packet counter values */
+	SGE_NDBQTIMERS = 8,       /* # of Doorbell Queue Timer values */
 	SGE_MAX_IQ_SIZE = 65520,
 
 	SGE_TIMER_RSTRT_CNTR = 6, /* restart RX packet threshold counter */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index c62a0c830705..38dd41eb959e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -56,6 +56,7 @@ enum {
 	CPL_TX_DATA_ISO	      = 0x1F,
 
 	CPL_CLOSE_LISTSRV_RPL = 0x20,
+	CPL_GET_TCB_RPL       = 0x22,
 	CPL_L2T_WRITE_RPL     = 0x23,
 	CPL_PASS_OPEN_RPL     = 0x24,
 	CPL_ACT_OPEN_RPL      = 0x25,
@@ -688,6 +689,13 @@ struct cpl_get_tcb {
 #define NO_REPLY_V(x) ((x) << NO_REPLY_S)
 #define NO_REPLY_F    NO_REPLY_V(1U)
 
+struct cpl_get_tcb_rpl {
+	union opcode_tid ot;
+	__u8 cookie;
+	__u8 status;
+	__be16 len;
+};
+
 struct cpl_set_tcb_field {
 	WR_HDR;
 	union opcode_tid ot;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index bf7325f6d553..0c5373462ced 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -218,6 +218,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x6088), /* Custom T62100-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x6089), /* Custom T62100-KR */
 	CH_PCI_ID_TABLE_FENTRY(0x608a), /* Custom T62100-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x608b), /* Custom T6225-CR */
 CH_PCI_DEVICE_ID_TABLE_DEFINE_END;
 
 #endif /* __T4_PCI_ID_TBL_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index eb222d40ddbf..a957a6e4d4c4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1334,6 +1334,10 @@
 #define TP_OUT_CONFIG_A		0x7d04
 #define TP_GLOBAL_CONFIG_A	0x7d08
 
+#define ACTIVEFILTERCOUNTS_S    22
+#define ACTIVEFILTERCOUNTS_V(x) ((x) << ACTIVEFILTERCOUNTS_S)
+#define ACTIVEFILTERCOUNTS_F    ACTIVEFILTERCOUNTS_V(1U)
+
 #define TP_CMM_TCB_BASE_A 0x7d10
 #define TP_CMM_MM_BASE_A 0x7d14
 #define TP_CMM_TIMER_BASE_A 0x7d18
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
index 3297ce025e8b..1b9afb192f7f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
@@ -41,6 +41,14 @@
 #define TCB_SMAC_SEL_V(x)	((x) << TCB_SMAC_SEL_S)
 
 #define TCB_T_FLAGS_W		1
+#define TCB_T_FLAGS_S		0
+#define TCB_T_FLAGS_M		0xffffffffffffffffULL
+#define TCB_T_FLAGS_V(x)	((__u64)(x) << TCB_T_FLAGS_S)
+
+#define TCB_RQ_START_W		30
+#define TCB_RQ_START_S		0
+#define TCB_RQ_START_M		0x3ffffffULL
+#define TCB_RQ_START_V(x)	((x) << TCB_RQ_START_S)
 
 #define TF_CCTRL_ECE_S		60
 #define TF_CCTRL_CWR_S		61
@@ -66,4 +74,8 @@
 #define TCB_RX_FRAG3_LEN_RAW_W	29
 #define TCB_RX_FRAG3_START_IDX_OFFSET_RAW_W	30
 #define TCB_PDU_HDR_LEN_W	31
+
+#define TF_RX_PDU_OUT_S		49
+#define TF_RX_PDU_OUT_V(x)	((__u64)(x) << TF_RX_PDU_OUT_S)
+
 #endif /* __T4_TCB_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
index f6558cbfc54e..eb1aa82149db 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
@@ -71,12 +71,18 @@
 #define FETCHBURSTMIN_64B_X		2
 #define FETCHBURSTMIN_128B_X		3
 
+/* T6 and later use a single-bit encoding for FetchBurstMin */
+#define FETCHBURSTMIN_64B_T6_X		0
+#define FETCHBURSTMIN_128B_T6_X		1
+
 #define FETCHBURSTMAX_256B_X		2
 #define FETCHBURSTMAX_512B_X		3
 
+#define HOSTFCMODE_INGRESS_QUEUE_X	1
 #define HOSTFCMODE_STATUS_PAGE_X	2
 
 #define CIDXFLUSHTHRESH_32_X		5
+#define CIDXFLUSHTHRESH_128_X		7
 
 #define UPDATEDELIVERY_INTERRUPT_X	1
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 1d9b3e1e5f94..65313f6b5704 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -1221,6 +1221,23 @@ enum fw_params_mnem {
 /*
  * device parameters
  */
+
+#define FW_PARAMS_PARAM_FILTER_MODE_S 16
+#define FW_PARAMS_PARAM_FILTER_MODE_M 0xffff
+#define FW_PARAMS_PARAM_FILTER_MODE_V(x)          \
+	((x) << FW_PARAMS_PARAM_FILTER_MODE_S)
+#define FW_PARAMS_PARAM_FILTER_MODE_G(x)          \
+	(((x) >> FW_PARAMS_PARAM_FILTER_MODE_S) & \
+	FW_PARAMS_PARAM_FILTER_MODE_M)
+
+#define FW_PARAMS_PARAM_FILTER_MASK_S 0
+#define FW_PARAMS_PARAM_FILTER_MASK_M 0xffff
+#define FW_PARAMS_PARAM_FILTER_MASK_V(x)          \
+	((x) << FW_PARAMS_PARAM_FILTER_MASK_S)
+#define FW_PARAMS_PARAM_FILTER_MASK_G(x)          \
+	(((x) >> FW_PARAMS_PARAM_FILTER_MASK_S) & \
+	FW_PARAMS_PARAM_FILTER_MASK_M)
+
 enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_CCLK	= 0x00, /* chip core clock in khz */
 	FW_PARAMS_PARAM_DEV_PORTVEC	= 0x01, /* the port vector */
@@ -1250,10 +1267,16 @@ enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_RI_FR_NSMR_TPTE_WR	= 0x1C,
 	FW_PARAMS_PARAM_DEV_FILTER2_WR  = 0x1D,
 	FW_PARAMS_PARAM_DEV_MPSBGMAP	= 0x1E,
+	FW_PARAMS_PARAM_DEV_TPCHMAP     = 0x1F,
 	FW_PARAMS_PARAM_DEV_HMA_SIZE	= 0x20,
 	FW_PARAMS_PARAM_DEV_RDMA_WRITE_WITH_IMM = 0x21,
+	FW_PARAMS_PARAM_DEV_PPOD_EDRAM  = 0x23,
 	FW_PARAMS_PARAM_DEV_RI_WRITE_CMPL_WR    = 0x24,
 	FW_PARAMS_PARAM_DEV_OPAQUE_VIID_SMT_EXTN = 0x27,
+	FW_PARAMS_PARAM_DEV_HASHFILTER_WITH_OFLD = 0x28,
+	FW_PARAMS_PARAM_DEV_DBQ_TIMER	= 0x29,
+	FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK = 0x2A,
+	FW_PARAMS_PARAM_DEV_FILTER = 0x2E,
 };
 
 /*
@@ -1310,6 +1333,16 @@ enum fw_params_param_pfvf {
 	FW_PARAMS_PARAM_PFVF_RAWF_END = 0x37,
 	FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x39,
 	FW_PARAMS_PARAM_PFVF_PORT_CAPS32 = 0x3A,
+	FW_PARAMS_PARAM_PFVF_PPOD_EDRAM_START = 0x3B,
+	FW_PARAMS_PARAM_PFVF_PPOD_EDRAM_END = 0x3C,
+	FW_PARAMS_PARAM_PFVF_LINK_STATE = 0x40,
+};
+
+/* Virtual link state as seen by the specified VF */
+enum vf_link_states {
+	FW_VF_LINK_STATE_AUTO		= 0x00,
+	FW_VF_LINK_STATE_ENABLE		= 0x01,
+	FW_VF_LINK_STATE_DISABLE	= 0x02,
 };
 
 /*
@@ -1322,6 +1355,7 @@ enum fw_params_param_dmaq {
 	FW_PARAMS_PARAM_DMAQ_EQ_CMPLIQID_CTRL = 0x11,
 	FW_PARAMS_PARAM_DMAQ_EQ_SCHEDCLASS_ETH = 0x12,
 	FW_PARAMS_PARAM_DMAQ_EQ_DCBPRIO_ETH = 0x13,
+	FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX	= 0x15,
 	FW_PARAMS_PARAM_DMAQ_CONM_CTXT = 0x20,
 };
 
@@ -1336,6 +1370,11 @@ enum fw_params_param_dev_diag {
 	FW_PARAM_DEV_DIAG_MAXTMPTHRESH	= 0x02,
 };
 
+enum fw_params_param_dev_filter {
+	FW_PARAM_DEV_FILTER_VNIC_MODE   = 0x00,
+	FW_PARAM_DEV_FILTER_MODE_MASK   = 0x01,
+};
+
 enum fw_params_param_dev_fwcache {
 	FW_PARAM_DEV_FWCACHE_FLUSH      = 0x00,
 	FW_PARAM_DEV_FWCACHE_FLUSHINV   = 0x01,
@@ -1751,8 +1790,8 @@ struct fw_eq_eth_cmd {
 	__be32 fetchszm_to_iqid;
 	__be32 dcaen_to_eqsize;
 	__be64 eqaddr;
-	__be32 viid_pkd;
-	__be32 r8_lo;
+	__be32 autoequiqe_to_viid;
+	__be32 timeren_timerix;
 	__be64 r9;
 };
 
@@ -1847,6 +1886,10 @@ struct fw_eq_eth_cmd {
 #define FW_EQ_ETH_CMD_EQSIZE_S		0
 #define FW_EQ_ETH_CMD_EQSIZE_V(x)	((x) << FW_EQ_ETH_CMD_EQSIZE_S)
 
+#define FW_EQ_ETH_CMD_AUTOEQUIQE_S	31
+#define FW_EQ_ETH_CMD_AUTOEQUIQE_V(x)	((x) << FW_EQ_ETH_CMD_AUTOEQUIQE_S)
+#define FW_EQ_ETH_CMD_AUTOEQUIQE_F	FW_EQ_ETH_CMD_AUTOEQUIQE_V(1U)
+
 #define FW_EQ_ETH_CMD_AUTOEQUEQE_S	30
 #define FW_EQ_ETH_CMD_AUTOEQUEQE_V(x)	((x) << FW_EQ_ETH_CMD_AUTOEQUEQE_S)
 #define FW_EQ_ETH_CMD_AUTOEQUEQE_F	FW_EQ_ETH_CMD_AUTOEQUEQE_V(1U)
@@ -1854,6 +1897,19 @@ struct fw_eq_eth_cmd {
 #define FW_EQ_ETH_CMD_VIID_S	16
 #define FW_EQ_ETH_CMD_VIID_V(x)	((x) << FW_EQ_ETH_CMD_VIID_S)
 
+#define FW_EQ_ETH_CMD_TIMEREN_S		3
+#define FW_EQ_ETH_CMD_TIMEREN_M		0x1
+#define FW_EQ_ETH_CMD_TIMEREN_V(x)	((x) << FW_EQ_ETH_CMD_TIMEREN_S)
+#define FW_EQ_ETH_CMD_TIMEREN_G(x)	\
+    (((x) >> FW_EQ_ETH_CMD_TIMEREN_S) & FW_EQ_ETH_CMD_TIMEREN_M)
+#define FW_EQ_ETH_CMD_TIMEREN_F	FW_EQ_ETH_CMD_TIMEREN_V(1U)
+
+#define FW_EQ_ETH_CMD_TIMERIX_S		0
+#define FW_EQ_ETH_CMD_TIMERIX_M		0x7
+#define FW_EQ_ETH_CMD_TIMERIX_V(x)	((x) << FW_EQ_ETH_CMD_TIMERIX_S)
+#define FW_EQ_ETH_CMD_TIMERIX_G(x)	\
+    (((x) >> FW_EQ_ETH_CMD_TIMERIX_S) & FW_EQ_ETH_CMD_TIMERIX_M)
+
 struct fw_eq_ctrl_cmd {
 	__be32 op_to_vfn;
 	__be32 alloc_to_len16;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index a844296135b4..a02b1dff403e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x14
-#define T4FW_VERSION_MICRO 0x08
+#define T4FW_VERSION_MINOR 0x17
+#define T4FW_VERSION_MICRO 0x03
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x14
-#define T5FW_VERSION_MICRO 0x08
+#define T5FW_VERSION_MINOR 0x17
+#define T5FW_VERSION_MICRO 0x03
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x14
-#define T6FW_VERSION_MICRO 0x08
+#define T6FW_VERSION_MINOR 0x17
+#define T6FW_VERSION_MICRO 0x03
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/Makefile b/drivers/net/ethernet/chelsio/cxgb4vf/Makefile
index d72ee26cb4c7..f527ab13a008 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/Makefile
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Chelsio T4 SR-IOV Virtual Function Driver
 #
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
index 5883f09e3804..3782e48dada2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
@@ -94,7 +94,7 @@ struct port_info {
 	struct adapter *adapter;	/* our adapter */
 	u32 vlan_id;			/* vlan id for VST */
 	u16 viid;			/* virtual interface ID */
-	s16 xact_addr_filt;		/* index of our MAC address filter */
+	int xact_addr_filt;		/* index of our MAC address filter */
 	u16 rss_size;			/* size of VI's RSS table slice */
 	u8 pidx;			/* index into adapter port[] */
 	s8 mdio_addr;
@@ -352,6 +352,7 @@ struct sge {
 struct hash_mac_addr {
 	struct list_head list;
 	u8 addr[ETH_ALEN];
+	unsigned int iface_mac;
 };
 
 struct mbox_list {
@@ -405,11 +406,12 @@ struct adapter {
 };
 
 enum { /* adapter flags */
-	FULL_INIT_DONE     = (1UL << 0),
-	USING_MSI          = (1UL << 1),
-	USING_MSIX         = (1UL << 2),
-	QUEUES_BOUND       = (1UL << 3),
-	ROOT_NO_RELAXED_ORDERING = (1UL << 4),
+	CXGB4VF_FULL_INIT_DONE			= (1UL << 0),
+	CXGB4VF_USING_MSI			= (1UL << 1),
+	CXGB4VF_USING_MSIX			= (1UL << 2),
+	CXGB4VF_QUEUES_BOUND			= (1UL << 3),
+	CXGB4VF_ROOT_NO_RELAXED_ORDERING	= (1UL << 4),
+	CXGB4VF_FW_OK				= (1UL << 5),
 };
 
 /*
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 2fab87e86561..6d4cf3d0b2f0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -155,6 +155,8 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok)
 		const char *fc;
 		const struct port_info *pi = netdev_priv(dev);
 
+		netif_carrier_on(dev);
+
 		switch (pi->link_cfg.speed) {
 		case 100:
 			s = "100Mbps";
@@ -200,6 +202,7 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok)
 
 		netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s, fc);
 	} else {
+		netif_carrier_off(dev);
 		netdev_info(dev, "link down\n");
 	}
 }
@@ -236,6 +239,73 @@ void t4vf_os_portmod_changed(struct adapter *adapter, int pidx)
 			 "inserted\n", dev->name, pi->mod_type);
 }
 
+static int cxgb4vf_set_addr_hash(struct port_info *pi)
+{
+	struct adapter *adapter = pi->adapter;
+	u64 vec = 0;
+	bool ucast = false;
+	struct hash_mac_addr *entry;
+
+	/* Calculate the hash vector for the updated list and program it */
+	list_for_each_entry(entry, &adapter->mac_hlist, list) {
+		ucast |= is_unicast_ether_addr(entry->addr);
+		vec |= (1ULL << hash_mac_addr(entry->addr));
+	}
+	return t4vf_set_addr_hash(adapter, pi->viid, ucast, vec, false);
+}
+
+/**
+ *	cxgb4vf_change_mac - Update match filter for a MAC address.
+ *	@pi: the port_info
+ *	@viid: the VI id
+ *	@tcam_idx: TCAM index of existing filter for old value of MAC address,
+ *		   or -1
+ *	@addr: the new MAC address value
+ *	@persist: whether a new MAC allocation should be persistent
+ *	@add_smt: if true also add the address to the HW SMT
+ *
+ *	Modifies an MPS filter and sets it to the new MAC address if
+ *	@tcam_idx >= 0, or adds the MAC address to a new filter if
+ *	@tcam_idx < 0. In the latter case the address is added persistently
+ *	if @persist is %true.
+ *	Addresses are programmed to hash region, if tcam runs out of entries.
+ *
+ */
+static int cxgb4vf_change_mac(struct port_info *pi, unsigned int viid,
+			      int *tcam_idx, const u8 *addr, bool persistent)
+{
+	struct hash_mac_addr *new_entry, *entry;
+	struct adapter *adapter = pi->adapter;
+	int ret;
+
+	ret = t4vf_change_mac(adapter, viid, *tcam_idx, addr, persistent);
+	/* We ran out of TCAM entries. try programming hash region. */
+	if (ret == -ENOMEM) {
+		/* If the MAC address to be updated is in the hash addr
+		 * list, update it from the list
+		 */
+		list_for_each_entry(entry, &adapter->mac_hlist, list) {
+			if (entry->iface_mac) {
+				ether_addr_copy(entry->addr, addr);
+				goto set_hash;
+			}
+		}
+		new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL);
+		if (!new_entry)
+			return -ENOMEM;
+		ether_addr_copy(new_entry->addr, addr);
+		new_entry->iface_mac = true;
+		list_add_tail(&new_entry->list, &adapter->mac_hlist);
+set_hash:
+		ret = cxgb4vf_set_addr_hash(pi);
+	} else if (ret >= 0) {
+		*tcam_idx = ret;
+		ret = 0;
+	}
+
+	return ret;
+}
+
 /*
  * Net device operations.
  * ======================
@@ -259,14 +329,10 @@ static int link_start(struct net_device *dev)
 	 */
 	ret = t4vf_set_rxmode(pi->adapter, pi->viid, dev->mtu, -1, -1, -1, 1,
 			      true);
-	if (ret == 0) {
-		ret = t4vf_change_mac(pi->adapter, pi->viid,
-				      pi->xact_addr_filt, dev->dev_addr, true);
-		if (ret >= 0) {
-			pi->xact_addr_filt = ret;
-			ret = 0;
-		}
-	}
+	if (ret == 0)
+		ret = cxgb4vf_change_mac(pi, pi->viid,
+					 &pi->xact_addr_filt,
+					 dev->dev_addr, true);
 
 	/*
 	 * We don't need to actually "start the link" itself since the
@@ -276,16 +342,6 @@ static int link_start(struct net_device *dev)
 	if (ret == 0)
 		ret = t4vf_enable_pi(pi->adapter, pi, true, true);
 
-	/* The Virtual Interfaces are connected to an internal switch on the
-	 * chip which allows VIs attached to the same port to talk to each
-	 * other even when the port link is down.  As a result, we generally
-	 * want to always report a VI's link as being "up", provided there are
-	 * no errors in enabling vi.
-	 */
-
-	if (ret == 0)
-		netif_carrier_on(dev);
-
 	return ret;
 }
 
@@ -406,7 +462,7 @@ static void enable_rx(struct adapter *adapter)
 	 * The interrupt queue doesn't use NAPI so we do the 0-increment of
 	 * its Going To Sleep register here to get it started.
 	 */
-	if (adapter->flags & USING_MSI)
+	if (adapter->flags & CXGB4VF_USING_MSI)
 		t4_write_reg(adapter, T4VF_SGE_BASE_ADDR + SGE_VF_GTS,
 			     CIDXINC_V(0) |
 			     SEINTARM_V(s->intrq.intr_params) |
@@ -462,8 +518,8 @@ static int fwevtq_handler(struct sge_rspq *rspq, const __be64 *rsp,
 			break;
 		}
 		cpl = (void *)p;
-		/*FALLTHROUGH*/
 	}
+		/* Fall through */
 
 	case CPL_SGE_EGR_UPDATE: {
 		/*
@@ -550,7 +606,7 @@ static int setup_sge_queues(struct adapter *adapter)
 	 * the intrq's queue ID as the interrupt forwarding queue for the
 	 * subsequent calls ...
 	 */
-	if (adapter->flags & USING_MSI) {
+	if (adapter->flags & CXGB4VF_USING_MSI) {
 		err = t4vf_sge_alloc_rxq(adapter, &s->intrq, false,
 					 adapter->port[0], 0, NULL, NULL);
 		if (err)
@@ -710,7 +766,7 @@ static int adapter_up(struct adapter *adapter)
 	 * adapter setup.  Once we've done this, many of our adapter
 	 * parameters can no longer be changed ...
 	 */
-	if ((adapter->flags & FULL_INIT_DONE) == 0) {
+	if ((adapter->flags & CXGB4VF_FULL_INIT_DONE) == 0) {
 		err = setup_sge_queues(adapter);
 		if (err)
 			return err;
@@ -720,17 +776,18 @@ static int adapter_up(struct adapter *adapter)
 			return err;
 		}
 
-		if (adapter->flags & USING_MSIX)
+		if (adapter->flags & CXGB4VF_USING_MSIX)
 			name_msix_vecs(adapter);
 
-		adapter->flags |= FULL_INIT_DONE;
+		adapter->flags |= CXGB4VF_FULL_INIT_DONE;
 	}
 
 	/*
 	 * Acquire our interrupt resources.  We only support MSI-X and MSI.
 	 */
-	BUG_ON((adapter->flags & (USING_MSIX|USING_MSI)) == 0);
-	if (adapter->flags & USING_MSIX)
+	BUG_ON((adapter->flags &
+	       (CXGB4VF_USING_MSIX | CXGB4VF_USING_MSI)) == 0);
+	if (adapter->flags & CXGB4VF_USING_MSIX)
 		err = request_msix_queue_irqs(adapter);
 	else
 		err = request_irq(adapter->pdev->irq,
@@ -761,7 +818,7 @@ static void adapter_down(struct adapter *adapter)
 	/*
 	 * Free interrupt resources.
 	 */
-	if (adapter->flags & USING_MSIX)
+	if (adapter->flags & CXGB4VF_USING_MSIX)
 		free_msix_queue_irqs(adapter);
 	else
 		free_irq(adapter->pdev->irq, adapter);
@@ -782,6 +839,13 @@ static int cxgb4vf_open(struct net_device *dev)
 	struct adapter *adapter = pi->adapter;
 
 	/*
+	 * If we don't have a connection to the firmware there's nothing we
+	 * can do.
+	 */
+	if (!(adapter->flags & CXGB4VF_FW_OK))
+		return -ENXIO;
+
+	/*
 	 * If this is the first interface that we're opening on the "adapter",
 	 * bring the "adapter" up now.
 	 */
@@ -791,6 +855,13 @@ static int cxgb4vf_open(struct net_device *dev)
 			return err;
 	}
 
+	/* It's possible that the basic port information could have
+	 * changed since we first read it.
+	 */
+	err = t4vf_update_port_info(pi);
+	if (err < 0)
+		return err;
+
 	/*
 	 * Note that this interface is up and start everything up ...
 	 */
@@ -863,21 +934,6 @@ static struct net_device_stats *cxgb4vf_get_stats(struct net_device *dev)
 	return ns;
 }
 
-static inline int cxgb4vf_set_addr_hash(struct port_info *pi)
-{
-	struct adapter *adapter = pi->adapter;
-	u64 vec = 0;
-	bool ucast = false;
-	struct hash_mac_addr *entry;
-
-	/* Calculate the hash vector for the updated list and program it */
-	list_for_each_entry(entry, &adapter->mac_hlist, list) {
-		ucast |= is_unicast_ether_addr(entry->addr);
-		vec |= (1ULL << hash_mac_addr(entry->addr));
-	}
-	return t4vf_set_addr_hash(adapter, pi->viid, ucast, vec, false);
-}
-
 static int cxgb4vf_mac_sync(struct net_device *netdev, const u8 *mac_addr)
 {
 	struct port_info *pi = netdev_priv(netdev);
@@ -1159,13 +1215,12 @@ static int cxgb4vf_set_mac_addr(struct net_device *dev, void *_addr)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	ret = t4vf_change_mac(pi->adapter, pi->viid, pi->xact_addr_filt,
-			      addr->sa_data, true);
+	ret = cxgb4vf_change_mac(pi, pi->viid, &pi->xact_addr_filt,
+				 addr->sa_data, true);
 	if (ret < 0)
 		return ret;
 
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	pi->xact_addr_filt = ret;
 	return 0;
 }
 
@@ -1179,7 +1234,7 @@ static void cxgb4vf_poll_controller(struct net_device *dev)
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
 
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4VF_USING_MSIX) {
 		struct sge_eth_rxq *rxq;
 		int nqsets;
 
@@ -1354,7 +1409,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 	case FW_PORT_TYPE_CR4_QSFP:
 		SET_LMM(FIBRE);
 		FW_CAPS_TO_LMM(SPEED_1G,  1000baseT_Full);
-		FW_CAPS_TO_LMM(SPEED_10G, 10000baseSR_Full);
+		FW_CAPS_TO_LMM(SPEED_10G, 10000baseKR_Full);
 		FW_CAPS_TO_LMM(SPEED_40G, 40000baseSR4_Full);
 		FW_CAPS_TO_LMM(SPEED_25G, 25000baseCR_Full);
 		FW_CAPS_TO_LMM(SPEED_50G, 50000baseCR2_Full);
@@ -1365,6 +1420,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 		break;
 	}
 
+	if (fw_caps & FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M)) {
+		FW_CAPS_TO_LMM(FEC_RS, FEC_RS);
+		FW_CAPS_TO_LMM(FEC_BASER_RS, FEC_BASER);
+	} else {
+		SET_LMM(FEC_NONE);
+	}
+
 	FW_CAPS_TO_LMM(ANEG, Autoneg);
 	FW_CAPS_TO_LMM(802_3_PAUSE, Pause);
 	FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause);
@@ -1417,22 +1479,6 @@ static int cxgb4vf_get_link_ksettings(struct net_device *dev,
 		base->duplex = DUPLEX_UNKNOWN;
 	}
 
-	if (pi->link_cfg.fc & PAUSE_RX) {
-		if (pi->link_cfg.fc & PAUSE_TX) {
-			ethtool_link_ksettings_add_link_mode(link_ksettings,
-							     advertising,
-							     Pause);
-		} else {
-			ethtool_link_ksettings_add_link_mode(link_ksettings,
-							     advertising,
-							     Asym_Pause);
-		}
-	} else if (pi->link_cfg.fc & PAUSE_TX) {
-		ethtool_link_ksettings_add_link_mode(link_ksettings,
-						     advertising,
-						     Asym_Pause);
-	}
-
 	base->autoneg = pi->link_cfg.autoneg;
 	if (pi->link_cfg.pcaps & FW_PORT_CAP32_ANEG)
 		ethtool_link_ksettings_add_link_mode(link_ksettings,
@@ -1587,7 +1633,7 @@ static int cxgb4vf_set_ringparam(struct net_device *dev,
 	    rp->tx_pending < MIN_TXQ_ENTRIES)
 		return -EINVAL;
 
-	if (adapter->flags & FULL_INIT_DONE)
+	if (adapter->flags & CXGB4VF_FULL_INIT_DONE)
 		return -EBUSY;
 
 	for (qs = pi->first_qset; qs < pi->first_qset + pi->nqsets; qs++) {
@@ -1871,6 +1917,8 @@ static void cxgb4vf_get_wol(struct net_device *dev,
  * TCP Segmentation Offload flags which we support.
  */
 #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+#define VLAN_FEAT (NETIF_F_SG | NETIF_F_IP_CSUM | TSO_FLAGS | \
+		   NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
 
 static const struct ethtool_ops cxgb4vf_ethtool_ops = {
 	.get_link_ksettings	= cxgb4vf_get_link_ksettings,
@@ -2102,7 +2150,7 @@ static int sge_qinfo_show(struct seq_file *seq, void *v)
 static int sge_queue_entries(const struct adapter *adapter)
 {
 	return DIV_ROUND_UP(adapter->sge.ethqsets, QPL) + 1 +
-		((adapter->flags & USING_MSI) != 0);
+		((adapter->flags & CXGB4VF_USING_MSI) != 0);
 }
 
 static void *sge_queue_start(struct seq_file *seq, loff_t *pos)
@@ -2248,7 +2296,7 @@ static int sge_qstats_show(struct seq_file *seq, void *v)
 static int sge_qstats_entries(const struct adapter *adapter)
 {
 	return DIV_ROUND_UP(adapter->sge.ethqsets, QPL) + 1 +
-		((adapter->flags & USING_MSI) != 0);
+		((adapter->flags & CXGB4VF_USING_MSI) != 0);
 }
 
 static void *sge_qstats_start(struct seq_file *seq, loff_t *pos)
@@ -2657,6 +2705,7 @@ static int adap_init0(struct adapter *adapter)
 	 */
 	size_nports_qsets(adapter);
 
+	adapter->flags |= CXGB4VF_FW_OK;
 	return 0;
 }
 
@@ -2691,7 +2740,8 @@ static void cfg_queues(struct adapter *adapter)
 	 * support.  In particular, this means that we need to know what kind
 	 * of interrupts we'll be using ...
 	 */
-	BUG_ON((adapter->flags & (USING_MSIX|USING_MSI)) == 0);
+	BUG_ON((adapter->flags &
+	       (CXGB4VF_USING_MSIX | CXGB4VF_USING_MSI)) == 0);
 
 	/*
 	 * Count the number of 10GbE Virtual Interfaces that we have.
@@ -3017,11 +3067,13 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * using Relaxed Ordering.
 	 */
 	if (!pcie_relaxed_ordering_enabled(pdev))
-		adapter->flags |= ROOT_NO_RELAXED_ORDERING;
+		adapter->flags |= CXGB4VF_ROOT_NO_RELAXED_ORDERING;
 
 	err = adap_init0(adapter);
 	if (err)
-		goto err_unmap_bar;
+		dev_err(&pdev->dev,
+			"Adapter initialization failed, error %d. Continuing in debug mode\n",
+			err);
 
 	/* Initialize hash mac addr list */
 	INIT_LIST_HEAD(&adapter->mac_hlist);
@@ -3046,13 +3098,6 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 			break;
 		port_id = ffs(pmask) - 1;
 		pmask &= ~(1 << port_id);
-		viid = t4vf_alloc_vi(adapter, port_id);
-		if (viid < 0) {
-			dev_err(&pdev->dev, "cannot allocate VI for port %d:"
-				" err=%d\n", port_id, viid);
-			err = viid;
-			goto err_free_dev;
-		}
 
 		/*
 		 * Allocate our network device and stitch things together.
@@ -3060,7 +3105,6 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 		netdev = alloc_etherdev_mq(sizeof(struct port_info),
 					   MAX_PORT_QSETS);
 		if (netdev == NULL) {
-			t4vf_free_vi(adapter, viid);
 			err = -ENOMEM;
 			goto err_free_dev;
 		}
@@ -3070,26 +3114,21 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 		pi->adapter = adapter;
 		pi->pidx = pidx;
 		pi->port_id = port_id;
-		pi->viid = viid;
 
 		/*
 		 * Initialize the starting state of our "port" and register
 		 * it.
 		 */
 		pi->xact_addr_filt = -1;
-		netif_carrier_off(netdev);
 		netdev->irq = pdev->irq;
 
-		netdev->hw_features = NETIF_F_SG | TSO_FLAGS |
-			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_RXCSUM;
-		netdev->vlan_features = NETIF_F_SG | TSO_FLAGS |
-			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			NETIF_F_HIGHDMA;
-		netdev->features = netdev->hw_features |
-				   NETIF_F_HW_VLAN_CTAG_TX;
+		netdev->hw_features = NETIF_F_SG | TSO_FLAGS | NETIF_F_GRO |
+			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
+			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+		netdev->features = netdev->hw_features;
 		if (pci_using_dac)
 			netdev->features |= NETIF_F_HIGHDMA;
+		netdev->vlan_features = netdev->features & VLAN_FEAT;
 
 		netdev->priv_flags |= IFF_UNICAST_FLT;
 		netdev->min_mtu = 81;
@@ -3100,6 +3139,23 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 		netdev->dev_port = pi->port_id;
 
 		/*
+		 * If we haven't been able to contact the firmware, there's
+		 * nothing else we can do for this "port" ...
+		 */
+		if (!(adapter->flags & CXGB4VF_FW_OK))
+			continue;
+
+		viid = t4vf_alloc_vi(adapter, port_id);
+		if (viid < 0) {
+			dev_err(&pdev->dev,
+				"cannot allocate VI for port %d: err=%d\n",
+				port_id, viid);
+			err = viid;
+			goto err_free_dev;
+		}
+		pi->viid = viid;
+
+		/*
 		 * Initialize the hardware/software state for the port.
 		 */
 		err = t4vf_port_init(adapter, pidx);
@@ -3136,7 +3192,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * get MSI interrupts we bail with the error.
 	 */
 	if (msi == MSI_MSIX && enable_msix(adapter) == 0)
-		adapter->flags |= USING_MSIX;
+		adapter->flags |= CXGB4VF_USING_MSIX;
 	else {
 		if (msi == MSI_MSIX) {
 			dev_info(adapter->pdev_dev,
@@ -3156,7 +3212,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 				" err=%d\n", err);
 			goto err_free_dev;
 		}
-		adapter->flags |= USING_MSI;
+		adapter->flags |= CXGB4VF_USING_MSI;
 	}
 
 	/* Now that we know how many "ports" we have and what interrupt
@@ -3186,6 +3242,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 			continue;
 		}
 
+		netif_carrier_off(netdev);
 		set_bit(pidx, &adapter->registered_device_map);
 	}
 	if (adapter->registered_device_map == 0) {
@@ -3214,8 +3271,8 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	for_each_port(adapter, pidx) {
 		dev_info(adapter->pdev_dev, "%s: Chelsio VF NIC PCIe %s\n",
 			 adapter->port[pidx]->name,
-			 (adapter->flags & USING_MSIX) ? "MSI-X" :
-			 (adapter->flags & USING_MSI)  ? "MSI" : "");
+			 (adapter->flags & CXGB4VF_USING_MSIX) ? "MSI-X" :
+			 (adapter->flags & CXGB4VF_USING_MSI)  ? "MSI" : "");
 	}
 
 	/*
@@ -3228,12 +3285,12 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * so far and return the error.
 	 */
 err_disable_interrupts:
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4VF_USING_MSIX) {
 		pci_disable_msix(adapter->pdev);
-		adapter->flags &= ~USING_MSIX;
-	} else if (adapter->flags & USING_MSI) {
+		adapter->flags &= ~CXGB4VF_USING_MSIX;
+	} else if (adapter->flags & CXGB4VF_USING_MSI) {
 		pci_disable_msi(adapter->pdev);
-		adapter->flags &= ~USING_MSI;
+		adapter->flags &= ~CXGB4VF_USING_MSI;
 	}
 
 err_free_dev:
@@ -3242,13 +3299,13 @@ err_free_dev:
 		if (netdev == NULL)
 			continue;
 		pi = netdev_priv(netdev);
-		t4vf_free_vi(adapter, pi->viid);
+		if (pi->viid)
+			t4vf_free_vi(adapter, pi->viid);
 		if (test_bit(pidx, &adapter->registered_device_map))
 			unregister_netdev(netdev);
 		free_netdev(netdev);
 	}
 
-err_unmap_bar:
 	if (!is_t4(adapter->params.chip))
 		iounmap(adapter->bar2);
 
@@ -3293,12 +3350,12 @@ static void cxgb4vf_pci_remove(struct pci_dev *pdev)
 			if (test_bit(pidx, &adapter->registered_device_map))
 				unregister_netdev(adapter->port[pidx]);
 		t4vf_sge_stop(adapter);
-		if (adapter->flags & USING_MSIX) {
+		if (adapter->flags & CXGB4VF_USING_MSIX) {
 			pci_disable_msix(adapter->pdev);
-			adapter->flags &= ~USING_MSIX;
-		} else if (adapter->flags & USING_MSI) {
+			adapter->flags &= ~CXGB4VF_USING_MSIX;
+		} else if (adapter->flags & CXGB4VF_USING_MSI) {
 			pci_disable_msi(adapter->pdev);
-			adapter->flags &= ~USING_MSI;
+			adapter->flags &= ~CXGB4VF_USING_MSI;
 		}
 
 		/*
@@ -3321,7 +3378,8 @@ static void cxgb4vf_pci_remove(struct pci_dev *pdev)
 				continue;
 
 			pi = netdev_priv(netdev);
-			t4vf_free_vi(adapter, pi->viid);
+			if (pi->viid)
+				t4vf_free_vi(adapter, pi->viid);
 			free_netdev(netdev);
 		}
 		iounmap(adapter->regs);
@@ -3369,12 +3427,12 @@ static void cxgb4vf_pci_shutdown(struct pci_dev *pdev)
 	 * Interrupts allowing various internal pathways to drain.
 	 */
 	t4vf_sge_stop(adapter);
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4VF_USING_MSIX) {
 		pci_disable_msix(adapter->pdev);
-		adapter->flags &= ~USING_MSIX;
-	} else if (adapter->flags & USING_MSI) {
+		adapter->flags &= ~CXGB4VF_USING_MSIX;
+	} else if (adapter->flags & CXGB4VF_USING_MSI) {
 		pci_disable_msi(adapter->pdev);
-		adapter->flags &= ~USING_MSI;
+		adapter->flags &= ~CXGB4VF_USING_MSI;
 	}
 
 	/*
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 1d534f0baa69..f71c973398ec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -2044,8 +2044,9 @@ static irqreturn_t t4vf_intr_msi(int irq, void *cookie)
  */
 irq_handler_t t4vf_intr_handler(struct adapter *adapter)
 {
-	BUG_ON((adapter->flags & (USING_MSIX|USING_MSI)) == 0);
-	if (adapter->flags & USING_MSIX)
+	BUG_ON((adapter->flags &
+	       (CXGB4VF_USING_MSIX | CXGB4VF_USING_MSI)) == 0);
+	if (adapter->flags & CXGB4VF_USING_MSIX)
 		return t4vf_sge_intr_msix;
 	else
 		return t4vf_intr_msi;
@@ -2209,7 +2210,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 	struct port_info *pi = netdev_priv(dev);
 	struct fw_iq_cmd cmd, rpl;
 	int ret, iqandst, flsz = 0;
-	int relaxed = !(adapter->flags & ROOT_NO_RELAXED_ORDERING);
+	int relaxed = !(adapter->flags & CXGB4VF_ROOT_NO_RELAXED_ORDERING);
 
 	/*
 	 * If we're using MSI interrupts and we're not initializing the
@@ -2218,7 +2219,8 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 	 * the Forwarded Interrupt Queue must be set up before any other
 	 * ingress queue ...
 	 */
-	if ((adapter->flags & USING_MSI) && rspq != &adapter->sge.intrq) {
+	if ((adapter->flags & CXGB4VF_USING_MSI) &&
+	    rspq != &adapter->sge.intrq) {
 		iqandst = SGE_INTRDST_IQ;
 		intr_dest = adapter->sge.intrq.abs_id;
 	} else
@@ -2268,7 +2270,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 	cmd.iqaddr = cpu_to_be64(rspq->phys_addr);
 
 	if (fl) {
-		enum chip_type chip =
+		unsigned int chip_ver =
 			CHELSIO_CHIP_VERSION(adapter->params.chip);
 		/*
 		 * Allocate the ring for the hardware free list (with space
@@ -2319,10 +2321,10 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 		 */
 		cmd.fl0dcaen_to_fl0cidxfthresh =
 			cpu_to_be16(
-				FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ?
-						     FETCHBURSTMIN_128B_X :
-						     FETCHBURSTMIN_64B_X) |
-				FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ?
+				FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5
+						     ? FETCHBURSTMIN_128B_X
+						     : FETCHBURSTMIN_64B_T6_X) |
+				FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ?
 						     FETCHBURSTMAX_512B_X :
 						     FETCHBURSTMAX_256B_X));
 		cmd.fl0size = cpu_to_be16(flsz);
@@ -2411,10 +2413,11 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq,
 			   struct net_device *dev, struct netdev_queue *devq,
 			   unsigned int iqid)
 {
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip);
+	struct port_info *pi = netdev_priv(dev);
+	struct fw_eq_eth_cmd cmd, rpl;
 	struct sge *s = &adapter->sge;
 	int ret, nentries;
-	struct fw_eq_eth_cmd cmd, rpl;
-	struct port_info *pi = netdev_priv(dev);
 
 	/*
 	 * Calculate the size of the hardware TX Queue (including the Status
@@ -2448,17 +2451,19 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq,
 	cmd.alloc_to_len16 = cpu_to_be32(FW_EQ_ETH_CMD_ALLOC_F |
 					 FW_EQ_ETH_CMD_EQSTART_F |
 					 FW_LEN16(cmd));
-	cmd.viid_pkd = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
-				   FW_EQ_ETH_CMD_VIID_V(pi->viid));
+	cmd.autoequiqe_to_viid = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
+					     FW_EQ_ETH_CMD_VIID_V(pi->viid));
 	cmd.fetchszm_to_iqid =
 		cpu_to_be32(FW_EQ_ETH_CMD_HOSTFCMODE_V(SGE_HOSTFCMODE_STPG) |
 			    FW_EQ_ETH_CMD_PCIECHN_V(pi->port_id) |
 			    FW_EQ_ETH_CMD_IQID_V(iqid));
 	cmd.dcaen_to_eqsize =
-		cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(SGE_FETCHBURSTMIN_64B) |
-			    FW_EQ_ETH_CMD_FBMAX_V(SGE_FETCHBURSTMAX_512B) |
+		cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+						  ? FETCHBURSTMIN_64B_X
+						  : FETCHBURSTMIN_64B_T6_X) |
+			    FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 			    FW_EQ_ETH_CMD_CIDXFTHRESH_V(
-						SGE_CIDXFLUSHTHRESH_32) |
+						CIDXFLUSHTHRESH_32_X) |
 			    FW_EQ_ETH_CMD_EQSIZE_V(nentries));
 	cmd.eqaddr = cpu_to_be64(txq->q.phys_addr);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index 5b8c08cf523f..8a389d617a23 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -313,7 +313,17 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 	return ret;
 }
 
+/* In the Physical Function Driver Common Code, the ADVERT_MASK is used to
+ * mask out bits in the Advertised Port Capabilities which are managed via
+ * separate controls, like Pause Frames and Forward Error Correction.  In the
+ * Virtual Function Common Code, since we never perform L1 Configuration on
+ * the Link, the only things we really need to filter out are things which
+ * we decode and report separately like Speed.
+ */
 #define ADVERT_MASK (FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_M) | \
+		     FW_PORT_CAP32_802_3_PAUSE | \
+		     FW_PORT_CAP32_802_3_ASM_DIR | \
+		     FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M) | \
 		     FW_PORT_CAP32_ANEG)
 
 /**
@@ -2005,8 +2015,10 @@ static void t4vf_handle_get_port_info(struct port_info *pi,
 	    fc != lc->fc || fec != lc->fec) {	/* something changed */
 		if (!link_ok && lc->link_ok) {
 			lc->link_down_rc = linkdnrc;
-			dev_warn(adapter->pdev_dev, "Port %d link down, reason: %s\n",
-				 pi->port_id, t4vf_link_down_rc_str(linkdnrc));
+			dev_warn_ratelimited(adapter->pdev_dev,
+					     "Port %d link down, reason: %s\n",
+					     pi->port_id,
+					     t4vf_link_down_rc_str(linkdnrc));
 		}
 		lc->link_ok = link_ok;
 		lc->speed = speed;
diff --git a/drivers/net/ethernet/chelsio/libcxgb/Makefile b/drivers/net/ethernet/chelsio/libcxgb/Makefile
index 2534e30a1560..aa79264e72ba 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/Makefile
+++ b/drivers/net/ethernet/chelsio/libcxgb/Makefile
@@ -1,4 +1,5 @@
-ccflags-y := -Idrivers/net/ethernet/chelsio/cxgb4
+# SPDX-License-Identifier: GPL-2.0-only
+ccflags-y := -I $(srctree)/$(src)/../cxgb4
 
 obj-$(CONFIG_CHELSIO_LIB) += libcxgb.o
 
diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
index 74849be5f004..21034536c9c5 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
@@ -123,6 +123,9 @@ static int ppm_get_cpu_entries(struct cxgbi_ppm *ppm, unsigned int count,
 	unsigned int cpu;
 	int i;
 
+	if (!ppm->pool)
+		return -EINVAL;
+
 	cpu = get_cpu();
 	pool = per_cpu_ptr(ppm->pool, cpu);
 	spin_lock_bh(&pool->lock);
@@ -169,7 +172,9 @@ static int ppm_get_entries(struct cxgbi_ppm *ppm, unsigned int count,
 	}
 
 	ppm->next = i + count;
-	if (ppm->next >= ppm->bmap_index_max)
+	if (ppm->max_index_in_edram && (ppm->next >= ppm->max_index_in_edram))
+		ppm->next = 0;
+	else if (ppm->next >= ppm->bmap_index_max)
 		ppm->next = 0;
 
 	spin_unlock_bh(&ppm->map_lock);
@@ -354,7 +359,10 @@ static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total,
 		ppmax = max;
 
 	/* pool size must be multiple of unsigned long */
-	bmap = BITS_TO_LONGS(ppmax);
+	bmap = ppmax / BITS_PER_TYPE(unsigned long);
+	if (!bmap)
+		return NULL;
+
 	ppmax = (bmap * sizeof(unsigned long)) << 3;
 
 	alloc_sz = sizeof(*pools) + sizeof(unsigned long) * bmap;
@@ -379,18 +387,36 @@ static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total,
 
 int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 		   struct pci_dev *pdev, void *lldev,
-		   struct cxgbi_tag_format *tformat,
-		   unsigned int ppmax,
-		   unsigned int llimit,
-		   unsigned int start,
-		   unsigned int reserve_factor)
+		   struct cxgbi_tag_format *tformat, unsigned int iscsi_size,
+		   unsigned int llimit, unsigned int start,
+		   unsigned int reserve_factor, unsigned int iscsi_edram_start,
+		   unsigned int iscsi_edram_size)
 {
 	struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp);
 	struct cxgbi_ppm_pool *pool = NULL;
-	unsigned int ppmax_pool = 0;
 	unsigned int pool_index_max = 0;
-	unsigned int alloc_sz;
+	unsigned int ppmax_pool = 0;
 	unsigned int ppod_bmap_size;
+	unsigned int alloc_sz;
+	unsigned int ppmax;
+
+	if (!iscsi_edram_start)
+		iscsi_edram_size = 0;
+
+	if (iscsi_edram_size &&
+	    ((iscsi_edram_start + iscsi_edram_size) != start)) {
+		pr_err("iscsi ppod region not contiguous: EDRAM start 0x%x "
+			"size 0x%x DDR start 0x%x\n",
+			iscsi_edram_start, iscsi_edram_size, start);
+		return -EINVAL;
+	}
+
+	if (iscsi_edram_size) {
+		reserve_factor = 0;
+		start = iscsi_edram_start;
+	}
+
+	ppmax = (iscsi_edram_size + iscsi_size) >> PPOD_SIZE_SHIFT;
 
 	if (ppm) {
 		pr_info("ippm: %s, ppm 0x%p,0x%p already initialized, %u/%u.\n",
@@ -402,6 +428,10 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 	if (reserve_factor) {
 		ppmax_pool = ppmax / reserve_factor;
 		pool = ppm_alloc_cpu_pool(&ppmax_pool, &pool_index_max);
+		if (!pool) {
+			ppmax_pool = 0;
+			reserve_factor = 0;
+		}
 
 		pr_debug("%s: ppmax %u, cpu total %u, per cpu %u.\n",
 			 ndev->name, ppmax, ppmax_pool, pool_index_max);
@@ -427,6 +457,14 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 			__func__, ppmax, ppmax_pool, ppod_bmap_size, start,
 			end);
 	}
+	if (iscsi_edram_size) {
+		unsigned int first_ddr_idx =
+				iscsi_edram_size >> PPOD_SIZE_SHIFT;
+
+		ppm->max_index_in_edram = first_ddr_idx - 1;
+		bitmap_set(ppm->ppod_bmap, first_ddr_idx, 1);
+		pr_debug("reserved %u ppod in bitmap\n", first_ddr_idx);
+	}
 
 	spin_lock_init(&ppm->map_lock);
 	kref_init(&ppm->refcnt);
diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h
index a91ad766cef0..7b02c200dd1e 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h
@@ -143,6 +143,7 @@ struct cxgbi_ppm {
 	spinlock_t map_lock;		/* ppm map lock */
 	unsigned int bmap_index_max;
 	unsigned int next;
+	unsigned int max_index_in_edram;
 	unsigned long *ppod_bmap;
 	struct cxgbi_ppod_data ppod_data[0];
 };
@@ -324,9 +325,9 @@ int cxgbi_ppm_ppods_reserve(struct cxgbi_ppm *, unsigned short nr_pages,
 			    unsigned long caller_data);
 int cxgbi_ppm_init(void **ppm_pp, struct net_device *, struct pci_dev *,
 		   void *lldev, struct cxgbi_tag_format *,
-		   unsigned int ppmax, unsigned int llimit,
-		   unsigned int start,
-		   unsigned int reserve_factor);
+		   unsigned int iscsi_size, unsigned int llimit,
+		   unsigned int start, unsigned int reserve_factor,
+		   unsigned int edram_start, unsigned int edram_size);
 int cxgbi_ppm_release(struct cxgbi_ppm *ppm);
 void cxgbi_tagmask_check(unsigned int tagmask, struct cxgbi_tag_format *);
 unsigned int cxgbi_tagmask_set(unsigned int ppmax);
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index e9a0213b08c4..48f3198381bc 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Cirrus network device configuration
 #
@@ -41,7 +42,7 @@ config CS89x0_PLATFORM
 
 config EP93XX_ETH
 	tristate "EP93xx Ethernet support"
-	depends on ARM && ARCH_EP93XX
+	depends on (ARM && ARCH_EP93XX) || COMPILE_TEST
 	select MII
 	help
 	  This is a driver for the ethernet hardware included in EP93xx CPUs.
diff --git a/drivers/net/ethernet/cirrus/Makefile b/drivers/net/ethernet/cirrus/Makefile
index ca245e2b5d98..84865e593788 100644
--- a/drivers/net/ethernet/cirrus/Makefile
+++ b/drivers/net/ethernet/cirrus/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Cirrus network device drivers.
 #
diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c
index 13dfdfca49fc..f1a0c4dceda0 100644
--- a/drivers/net/ethernet/cirrus/ep93xx_eth.c
+++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * EP93xx ethernet network device driver
  * Copyright (C) 2006 Lennert Buytenhek <buytenh@wantstofly.org>
  * Dedicated to Marija Kulikova.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
@@ -25,7 +21,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 
-#include <mach/hardware.h>
+#include <linux/platform_data/eth-ep93xx.h>
 
 #define DRV_MODULE_NAME		"ep93xx-eth"
 #define DRV_MODULE_VERSION	"0.1"
diff --git a/drivers/net/ethernet/cisco/Kconfig b/drivers/net/ethernet/cisco/Kconfig
index 15b713a89620..ee5b7b3868c7 100644
--- a/drivers/net/ethernet/cisco/Kconfig
+++ b/drivers/net/ethernet/cisco/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Cisco device configuration
 #
diff --git a/drivers/net/ethernet/cisco/Makefile b/drivers/net/ethernet/cisco/Makefile
index 6c7437bc4a92..074635beec82 100644
--- a/drivers/net/ethernet/cisco/Makefile
+++ b/drivers/net/ethernet/cisco/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Cisco device drivers.
 #
diff --git a/drivers/net/ethernet/cisco/enic/Kconfig b/drivers/net/ethernet/cisco/enic/Kconfig
index b63f8d8a4261..edaae706a102 100644
--- a/drivers/net/ethernet/cisco/enic/Kconfig
+++ b/drivers/net/ethernet/cisco/enic/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Cisco device configuration
 #
diff --git a/drivers/net/ethernet/cisco/enic/Makefile b/drivers/net/ethernet/cisco/enic/Makefile
index aadcaf7876ce..c3b6febfdbe4 100644
--- a/drivers/net/ethernet/cisco/enic/Makefile
+++ b/drivers/net/ethernet/cisco/enic/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_ENIC) := enic.o
 
 enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c
index 99038dfc7fbe..9900993b6aea 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.c
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c
@@ -32,7 +32,8 @@ int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq)
 		break;
 	default:
 		return -EPROTONOSUPPORT;
-	};
+	}
+
 	data.type = FILTER_IPV4_5TUPLE;
 	data.u.ipv4.src_addr = ntohl(keys->addrs.v4addrs.src);
 	data.u.ipv4.dst_addr = ntohl(keys->addrs.v4addrs.dst);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 9a7f70db20c7..acb2856936d2 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -119,7 +119,7 @@ static void enic_init_affinity_hint(struct enic *enic)
 
 	for (i = 0; i < enic->intr_count; i++) {
 		if (enic_is_err_intr(enic, i) || enic_is_notify_intr(enic, i) ||
-		    (enic->msix[i].affinity_mask &&
+		    (cpumask_available(enic->msix[i].affinity_mask) &&
 		     !cpumask_empty(enic->msix[i].affinity_mask)))
 			continue;
 		if (zalloc_cpumask_var(&enic->msix[i].affinity_mask,
@@ -148,7 +148,7 @@ static void enic_set_affinity_hint(struct enic *enic)
 	for (i = 0; i < enic->intr_count; i++) {
 		if (enic_is_err_intr(enic, i)		||
 		    enic_is_notify_intr(enic, i)	||
-		    !enic->msix[i].affinity_mask	||
+		    !cpumask_available(enic->msix[i].affinity_mask) ||
 		    cpumask_empty(enic->msix[i].affinity_mask))
 			continue;
 		err = irq_set_affinity_hint(enic->msix_entry[i].vector,
@@ -161,7 +161,7 @@ static void enic_set_affinity_hint(struct enic *enic)
 	for (i = 0; i < enic->wq_count; i++) {
 		int wq_intr = enic_msix_wq_intr(enic, i);
 
-		if (enic->msix[wq_intr].affinity_mask &&
+		if (cpumask_available(enic->msix[wq_intr].affinity_mask) &&
 		    !cpumask_empty(enic->msix[wq_intr].affinity_mask))
 			netif_set_xps_queue(enic->netdev,
 					    enic->msix[wq_intr].affinity_mask,
@@ -897,7 +897,7 @@ static netdev_tx_t enic_hard_start_xmit(struct sk_buff *skb,
 	if (vnic_wq_desc_avail(wq) < MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)
 		netif_tx_stop_queue(txq);
 	skb_tx_timestamp(skb);
-	if (!skb->xmit_more || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
 		vnic_wq_doorbell(wq);
 
 	spin_unlock(&enic->wq_lock[txq_map]);
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 949103db8a8a..9003eb6716cd 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1235,8 +1235,6 @@ static int gmac_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	int txq_num, nfrags;
 	union dma_rwptr rw;
 
-	SKB_FRAG_ASSERT(skb);
-
 	if (skb->len >= 0x10000)
 		goto out_drop_free;
 
diff --git a/drivers/net/ethernet/davicom/Kconfig b/drivers/net/ethernet/davicom/Kconfig
index 680a6d983f37..a321a7144fb0 100644
--- a/drivers/net/ethernet/davicom/Kconfig
+++ b/drivers/net/ethernet/davicom/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Davicom device configuration
 #
diff --git a/drivers/net/ethernet/davicom/Makefile b/drivers/net/ethernet/davicom/Makefile
index 74b31f0ebe18..173c87d21076 100644
--- a/drivers/net/ethernet/davicom/Makefile
+++ b/drivers/net/ethernet/davicom/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Davicom device drivers.
 #
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 0a82fcf16d35..386bdc1378d1 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1,17 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *      Davicom DM9000 Fast Ethernet driver for Linux.
  * 	Copyright (C) 1997  Sten Wang
  *
- * 	This program is free software; you can redistribute it and/or
- * 	modify it under the terms of the GNU General Public License
- * 	as published by the Free Software Foundation; either version 2
- * 	of the License, or (at your option) any later version.
- *
- * 	This program is distributed in the hope that it will be useful,
- * 	but WITHOUT ANY WARRANTY; without even the implied warranty of
- * 	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * 	GNU General Public License for more details.
- *
  * (C) Copyright 1997-1998 DAVICOM Semiconductor,Inc. All Rights Reserved.
  *
  * Additional updates, Copyright:
@@ -395,6 +386,7 @@ static void dm9000_set_io(struct board_info *db, int byte_width)
 
 	case 3:
 		dev_dbg(db->dev, ": 3 byte IO, falling back to 16bit\n");
+		/* fall through */
 	case 2:
 		db->dumpblk = dm9000_dumpblk_16bit;
 		db->outblk  = dm9000_outblk_16bit;
@@ -1411,8 +1403,8 @@ static struct dm9000_plat_data *dm9000_parse_dt(struct device *dev)
 		pdata->flags |= DM9000_PLATF_NO_EEPROM;
 
 	mac_addr = of_get_mac_address(np);
-	if (mac_addr)
-		memcpy(pdata->dev_addr, mac_addr, sizeof(pdata->dev_addr));
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(pdata->dev_addr, mac_addr);
 
 	return pdata;
 }
diff --git a/drivers/net/ethernet/dec/Kconfig b/drivers/net/ethernet/dec/Kconfig
index 740bbad5ed38..df1eeb04d5ea 100644
--- a/drivers/net/ethernet/dec/Kconfig
+++ b/drivers/net/ethernet/dec/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Digital Equipment Inc network device configuration
 #
diff --git a/drivers/net/ethernet/dec/Makefile b/drivers/net/ethernet/dec/Makefile
index 32993fccbbfd..e8aa12c8492a 100644
--- a/drivers/net/ethernet/dec/Makefile
+++ b/drivers/net/ethernet/dec/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Digital Equipment Inc. network device drivers.
 #
diff --git a/drivers/net/ethernet/dec/tulip/Kconfig b/drivers/net/ethernet/dec/tulip/Kconfig
index 264e9b413e94..8ce6888ea722 100644
--- a/drivers/net/ethernet/dec/tulip/Kconfig
+++ b/drivers/net/ethernet/dec/tulip/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Tulip family network device configuration
 #
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 66535d1653f6..f16853c3c851 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -2107,7 +2107,6 @@ static struct eisa_driver de4x5_eisa_driver = {
 		.remove  = de4x5_eisa_remove,
         }
 };
-MODULE_DEVICE_TABLE(eisa, de4x5_eisa_ids);
 #endif
 
 #ifdef CONFIG_PCI
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 17ef7a28873d..0efdbd1a4a6f 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
     A Davicom DM9102/DM9102A/DM9102A+DM9801/DM9102A+DM9802 NIC fast
     ethernet driver for Linux.
     Copyright (C) 1997  Sten Wang
 
-    This program is free software; you can redistribute it and/or
-    modify it under the terms of the GNU General Public License
-    as published by the Free Software Foundation; either version 2
-    of the License, or (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
 
     DAVICOM Web-Site: www.davicom.com.tw
 
diff --git a/drivers/net/ethernet/dec/tulip/eeprom.c b/drivers/net/ethernet/dec/tulip/eeprom.c
index 1812f4916917..ba0a69b363f8 100644
--- a/drivers/net/ethernet/dec/tulip/eeprom.c
+++ b/drivers/net/ethernet/dec/tulip/eeprom.c
@@ -224,9 +224,7 @@ subsequent_board:
 		        return;
 		}
 
-		mtable = kmalloc(sizeof(struct mediatable) +
-				 count * sizeof(struct medialeaf),
-				 GFP_KERNEL);
+		mtable = kmalloc(struct_size(mtable, mleaf, count), GFP_KERNEL);
 		if (mtable == NULL)
 			return;				/* Horrible, impossible failure. */
 		last_mediatable = tp->mtable = mtable;
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index 488a744084c9..b1f30b194300 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
-    This program is free software; you can redistribute it and/or
-    modify it under the terms of the GNU General Public License
-    as published by the Free Software Foundation; either version 2
-    of the License, or (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
 
 
 */
diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig
index ebdc83247bb6..1362658a3030 100644
--- a/drivers/net/ethernet/dlink/Kconfig
+++ b/drivers/net/ethernet/dlink/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # D-Link device configuration
 #
diff --git a/drivers/net/ethernet/dlink/Makefile b/drivers/net/ethernet/dlink/Makefile
index 40085f67157b..3ff503c747db 100644
--- a/drivers/net/ethernet/dlink/Makefile
+++ b/drivers/net/ethernet/dlink/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the D-Link network device drivers.
 #
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d8d423f22c4f..55e720d2ea0c 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*  D-Link DL2000-based Gigabit Ethernet Adapter Linux driver */
 /*
     Copyright (c) 2001, 2002 by D-Link Corporation
     Written by Edward Peng.<edward_peng@dlink.com.tw>
     Created 03-May-2001, base on Linux' sundance.c.
 
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
 */
 
 #define DRV_NAME	"DL2000/TC902x-based linux driver"
@@ -843,9 +840,9 @@ rio_free_tx (struct net_device *dev, int irq)
 				  desc_to_dma(&np->tx_ring[entry]),
 				  skb->len, PCI_DMA_TODEVICE);
 		if (irq)
-			dev_kfree_skb_irq (skb);
+			dev_consume_skb_irq(skb);
 		else
-			dev_kfree_skb (skb);
+			dev_kfree_skb(skb);
 
 		np->tx_skbuff[entry] = NULL;
 		entry = (entry + 1) % TX_RING_SIZE;
diff --git a/drivers/net/ethernet/dlink/dl2k.h b/drivers/net/ethernet/dlink/dl2k.h
index 10e98ba33ebf..195dc6cfd895 100644
--- a/drivers/net/ethernet/dlink/dl2k.h
+++ b/drivers/net/ethernet/dlink/dl2k.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*  D-Link DL2000-based Gigabit Ethernet Adapter Linux driver */
 /*
     Copyright (c) 2001, 2002 by D-Link Corporation
     Written by Edward Peng.<edward_peng@dlink.com.tw>
     Created 03-May-2001, base on Linux' sundance.c.
 
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
 */
 
 #ifndef __DL2K_H__
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index 1a27176381fb..4a37a69764ce 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -1193,7 +1193,6 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 	int handled = 0;
 	int i;
 
-
 	do {
 		int intr_status = ioread16(ioaddr + IntrStatus);
 		iowrite16(intr_status, ioaddr + IntrStatus);
@@ -1286,7 +1285,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 				dma_unmap_single(&np->pci_dev->dev,
 					le32_to_cpu(np->tx_ring[entry].frag[0].addr),
 					skb->len, DMA_TO_DEVICE);
-				dev_kfree_skb_irq (np->tx_skbuff[entry]);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
 				np->tx_skbuff[entry] = NULL;
 				np->tx_ring[entry].frag[0].addr = 0;
 				np->tx_ring[entry].frag[0].length = 0;
@@ -1305,7 +1304,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 				dma_unmap_single(&np->pci_dev->dev,
 					le32_to_cpu(np->tx_ring[entry].frag[0].addr),
 					skb->len, DMA_TO_DEVICE);
-				dev_kfree_skb_irq (np->tx_skbuff[entry]);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
 				np->tx_skbuff[entry] = NULL;
 				np->tx_ring[entry].frag[0].addr = 0;
 				np->tx_ring[entry].frag[0].length = 0;
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index 79521e27f0d1..e24979010969 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Dave DNET Ethernet Controller driver
  *
  * Copyright (C) 2008 Dave S.r.l. <www.dave.eu>
  * Copyright (C) 2009 Ilya Yanok, Emcraft Systems Ltd, <yanok@emcraft.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/io.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/dnet.h b/drivers/net/ethernet/dnet.h
index d985080bbd5d..8af6c0705ab3 100644
--- a/drivers/net/ethernet/dnet.h
+++ b/drivers/net/ethernet/dnet.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Dave DNET Ethernet Controller driver
  *
  * Copyright (C) 2008 Dave S.r.l. <www.dave.eu>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef _DNET_H
 #define _DNET_H
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index d71cba0842c5..46b0dbab8aad 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -1,17 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
  /*
  * drivers/net/ethernet/ec_bhf.c
  *
  * Copyright (C) 2014 Darek Marcinkiewicz <reksio@newterm.pl>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  */
 
 /* This is a driver for EtherCAT master module present on CCAT FPGA.
diff --git a/drivers/net/ethernet/emulex/Kconfig b/drivers/net/ethernet/emulex/Kconfig
index fdbb27ceb02f..22c143f2d787 100644
--- a/drivers/net/ethernet/emulex/Kconfig
+++ b/drivers/net/ethernet/emulex/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Emulex driver configuration
 #
diff --git a/drivers/net/ethernet/emulex/Makefile b/drivers/net/ethernet/emulex/Makefile
index ea8ec574d45a..1a7c5aed6f65 100644
--- a/drivers/net/ethernet/emulex/Makefile
+++ b/drivers/net/ethernet/emulex/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Emulex device drivers.
 #
diff --git a/drivers/net/ethernet/emulex/benet/Kconfig b/drivers/net/ethernet/emulex/benet/Kconfig
index 8cf794edd3c3..e8c7eb842dbe 100644
--- a/drivers/net/ethernet/emulex/benet/Kconfig
+++ b/drivers/net/ethernet/emulex/benet/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config BE2NET
 	tristate "ServerEngines' 10Gbps NIC - BladeEngine"
 	depends on PCI
diff --git a/drivers/net/ethernet/emulex/benet/Makefile b/drivers/net/ethernet/emulex/benet/Makefile
index 1a91b276940d..1a238ec7fe1a 100644
--- a/drivers/net/ethernet/emulex/benet/Makefile
+++ b/drivers/net/ethernet/emulex/benet/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile to build the network driver for ServerEngine's BladeEngine.
 #
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index ce041c90adb0..f287b5da5546 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.  The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 59a7f0b99069..ef5d61d57597 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.  The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index e8b43cf44b6f..c30d6d6f0f3a 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.  The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 4c218341c51b..492f8769ac12 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.  The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
@@ -895,7 +891,7 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test,
 			 u64 *data)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	int status;
+	int status, cnt;
 	u8 link_status = 0;
 
 	if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) {
@@ -906,6 +902,9 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test,
 
 	memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM);
 
+	/* check link status before offline tests */
+	link_status = netif_carrier_ok(netdev);
+
 	if (test->flags & ETH_TEST_FL_OFFLINE) {
 		if (be_loopback_test(adapter, BE_MAC_LOOPBACK, &data[0]) != 0)
 			test->flags |= ETH_TEST_FL_FAILED;
@@ -926,13 +925,26 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test,
 		test->flags |= ETH_TEST_FL_FAILED;
 	}
 
-	status = be_cmd_link_status_query(adapter, NULL, &link_status, 0);
-	if (status) {
-		test->flags |= ETH_TEST_FL_FAILED;
-		data[4] = -1;
-	} else if (!link_status) {
+	/* link status was down prior to test */
+	if (!link_status) {
 		test->flags |= ETH_TEST_FL_FAILED;
 		data[4] = 1;
+		return;
+	}
+
+	for (cnt = 10; cnt; cnt--) {
+		status = be_cmd_link_status_query(adapter, NULL, &link_status,
+						  0);
+		if (status) {
+			test->flags |= ETH_TEST_FL_FAILED;
+			data[4] = -1;
+			break;
+		}
+
+		if (link_status)
+			break;
+
+		msleep_interruptible(500);
 	}
 }
 
@@ -1105,7 +1117,7 @@ static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 		cmd->data = be_get_rss_hash_opts(adapter, cmd->flow_type);
 		break;
 	case ETHTOOL_GRXRINGS:
-		cmd->data = adapter->num_rx_qs - 1;
+		cmd->data = adapter->num_rx_qs;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h
index db5f92fb87e0..3476194f0855 100644
--- a/drivers/net/ethernet/emulex/benet/be_hw.h
+++ b/drivers/net/ethernet/emulex/benet/be_hw.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2005-2016 Broadcom.
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.  The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index d5026909dec5..82015c8a5ed7 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.  The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
@@ -1270,10 +1266,6 @@ static void be_xmit_flush(struct be_adapter *adapter, struct be_tx_obj *txo)
 #define is_arp_allowed_on_bmc(adapter, skb)	\
 	(is_arp(skb) && is_arp_filt_enabled(adapter))
 
-#define is_broadcast_packet(eh, adapter)	\
-		(is_multicast_ether_addr(eh->h_dest) && \
-		!compare_ether_addr(eh->h_dest, adapter->netdev->broadcast))
-
 #define is_arp(skb)	(skb->protocol == htons(ETH_P_ARP))
 
 #define is_arp_filt_enabled(adapter)	\
@@ -1380,7 +1372,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 	u16 q_idx = skb_get_queue_mapping(skb);
 	struct be_tx_obj *txo = &adapter->tx_obj[q_idx];
 	struct be_wrb_params wrb_params = { 0 };
-	bool flush = !skb->xmit_more;
+	bool flush = !netdev_xmit_more();
 	u16 wrb_cnt;
 
 	skb = be_xmit_workarounds(adapter, skb, &wrb_params);
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c
index 05989aafaf32..521c4c2b4887 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.c
+++ b/drivers/net/ethernet/emulex/benet/be_roce.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h
index e51719a7307f..801e10522129 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.h
+++ b/drivers/net/ethernet/emulex/benet/be_roce.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2005 - 2016 Broadcom
  * All rights reserved.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
- *
  * Contact Information:
  * linux-drivers@emulex.com
  *
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 0f3e7f21c6fa..ea4f17f5cce7 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * linux/drivers/net/ethernet/ethoc.c
  *
  * Copyright (C) 2007-2008 Avionic Design Development GmbH
  * Copyright (C) 2008-2009 Avionic Design GmbH
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Written by Thierry Reding <thierry.reding@avionic-design.de>
  */
 
@@ -1153,7 +1150,7 @@ static int ethoc_probe(struct platform_device *pdev)
 		const void *mac;
 
 		mac = of_get_mac_address(pdev->dev.of_node);
-		if (mac)
+		if (!IS_ERR(mac))
 			ether_addr_copy(netdev->dev_addr, mac);
 		priv->phy_id = -1;
 	}
diff --git a/drivers/net/ethernet/ezchip/Kconfig b/drivers/net/ethernet/ezchip/Kconfig
index b423ad380b6a..6db75fd2f9af 100644
--- a/drivers/net/ethernet/ezchip/Kconfig
+++ b/drivers/net/ethernet/ezchip/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # EZchip network device configuration
 #
diff --git a/drivers/net/ethernet/ezchip/Makefile b/drivers/net/ethernet/ezchip/Makefile
index e490176a8137..444570f35d45 100644
--- a/drivers/net/ethernet/ezchip/Makefile
+++ b/drivers/net/ethernet/ezchip/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_EZCHIP_NPS_MANAGEMENT_ENET) += nps_enet.o
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
index 659f1ad37e96..027225e1ade2 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.c
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright(c) 2015 EZchip Technologies.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
  */
 
 #include <linux/module.h>
@@ -616,7 +605,7 @@ static s32 nps_enet_probe(struct platform_device *pdev)
 
 	/* set kernel MAC address to dev */
 	mac_addr = of_get_mac_address(dev->of_node);
-	if (mac_addr)
+	if (!IS_ERR(mac_addr))
 		ether_addr_copy(ndev->dev_addr, mac_addr);
 	else
 		eth_hw_addr_random(ndev);
diff --git a/drivers/net/ethernet/ezchip/nps_enet.h b/drivers/net/ethernet/ezchip/nps_enet.h
index 3939ca20cc9f..133acca0bf31 100644
--- a/drivers/net/ethernet/ezchip/nps_enet.h
+++ b/drivers/net/ethernet/ezchip/nps_enet.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright(c) 2015 EZchip Technologies.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
  */
 
 #ifndef _NPS_ENET_H
diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig
index 0fb8df656677..a9b105803fb7 100644
--- a/drivers/net/ethernet/faraday/Kconfig
+++ b/drivers/net/ethernet/faraday/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Faraday device configuration
 #
diff --git a/drivers/net/ethernet/faraday/Makefile b/drivers/net/ethernet/faraday/Makefile
index 408b53980d53..f16f58467868 100644
--- a/drivers/net/ethernet/faraday/Makefile
+++ b/drivers/net/ethernet/faraday/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Faraday device drivers.
 #
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 3e5e97186fc4..030fed65393e 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Faraday FTGMAC100 Gigabit Ethernet
  *
  * (C) Copyright 2009-2011 Faraday Technology
  * Po-Yu Chuang <ratbert@faraday-tech.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
@@ -1075,7 +1062,7 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf)
 	}
 
 	/* Indicate that we support PAUSE frames (see comment in
-	 * Documentation/networking/phy.txt)
+	 * Documentation/networking/phy.rst)
 	 */
 	phy_support_asym_pause(phydev);
 
@@ -1637,7 +1624,7 @@ static int ftgmac100_setup_mdio(struct net_device *netdev)
 		reg = ioread32(priv->base + FTGMAC100_OFFSET_REVR);
 		reg &= ~FTGMAC100_REVR_NEW_MDIO_INTERFACE;
 		iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR);
-	};
+	}
 
 	/* Get PHY mode from device-tree */
 	if (np) {
diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h
index 0653d8176e6a..e5876a3fda91 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.h
+++ b/drivers/net/ethernet/faraday/ftgmac100.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Faraday FTGMAC100 Gigabit Ethernet
  *
  * (C) Copyright 2009-2011 Faraday Technology
  * Po-Yu Chuang <ratbert@faraday-tech.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __FTGMAC100_H
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 2a0e820526dc..6c247cbbd23e 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Faraday FTMAC100 10/100 Ethernet
  *
  * (C) Copyright 2009-2011 Faraday Technology
  * Po-Yu Chuang <ratbert@faraday-tech.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/faraday/ftmac100.h b/drivers/net/ethernet/faraday/ftmac100.h
index 46a0c47b1ee1..fe986f1673fc 100644
--- a/drivers/net/ethernet/faraday/ftmac100.h
+++ b/drivers/net/ethernet/faraday/ftmac100.h
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Faraday FTMAC100 10/100 Ethernet
  *
  * (C) Copyright 2009-2011 Faraday Technology
  * Po-Yu Chuang <ratbert@faraday-tech.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __FTMAC100_H
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index ae55da60ed0e..c24fd56a2c71 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -1531,7 +1531,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 			/* Free the original skb. */
 			pci_unmap_single(np->pci_dev, np->cur_tx->buffer,
 				np->cur_tx->skbuff->len, PCI_DMA_TODEVICE);
-			dev_kfree_skb_irq(np->cur_tx->skbuff);
+			dev_consume_skb_irq(np->cur_tx->skbuff);
 			np->cur_tx->skbuff = NULL;
 			--np->really_tx_count;
 			if (np->cur_tx->control & TXLD) {
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index d3a62bc1f1c6..6a7e8993119f 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Freescale device configuration
 #
@@ -97,5 +98,6 @@ config GIANFAR
 
 source "drivers/net/ethernet/freescale/dpaa/Kconfig"
 source "drivers/net/ethernet/freescale/dpaa2/Kconfig"
+source "drivers/net/ethernet/freescale/enetc/Kconfig"
 
 endif # NET_VENDOR_FREESCALE
diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile
index 3b4ff08e3841..6a93293d31e0 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -23,3 +23,6 @@ obj-$(CONFIG_FSL_FMAN) += fman/
 obj-$(CONFIG_FSL_DPAA_ETH) += dpaa/
 
 obj-$(CONFIG_FSL_DPAA2_ETH) += dpaa2/
+
+obj-$(CONFIG_FSL_ENETC) += enetc/
+obj-$(CONFIG_FSL_ENETC_VF) += enetc/
diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig
index a654736237a9..3b325733a4f8 100644
--- a/drivers/net/ethernet/freescale/dpaa/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 menuconfig FSL_DPAA_ETH
 	tristate "DPAA Ethernet"
 	depends on FSL_DPAA && FSL_FMAN
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index dfebc30c4841..f38c3fa7d705 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -780,7 +780,7 @@ static void dpaa_eth_add_channel(u16 channel)
 	struct qman_portal *portal;
 	int cpu;
 
-	for_each_cpu(cpu, cpus) {
+	for_each_cpu_and(cpu, cpus, cpu_online_mask) {
 		portal = qman_get_affine_portal(cpu);
 		qman_p_static_dequeue_add(portal, pool);
 	}
@@ -896,7 +896,7 @@ static void dpaa_fq_setup(struct dpaa_priv *priv,
 	u16 channels[NR_CPUS];
 	struct dpaa_fq *fq;
 
-	for_each_cpu(cpu, affine_cpus)
+	for_each_cpu_and(cpu, affine_cpus, cpu_online_mask)
 		channels[num_portals++] = qman_affine_channel(cpu);
 
 	if (num_portals == 0)
@@ -1648,7 +1648,7 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 				 qm_sg_entry_get_len(&sgt[0]), dma_dir);
 
 		/* remaining pages were mapped with skb_frag_dma_map() */
-		for (i = 1; i < nr_frags; i++) {
+		for (i = 1; i <= nr_frags; i++) {
 			WARN_ON(qm_sg_entry_is_ext(&sgt[i]));
 
 			dma_unmap_page(dev, qm_sg_addr(&sgt[i]),
@@ -2174,7 +2174,6 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget)
 	if (cleaned < budget) {
 		napi_complete_done(napi, cleaned);
 		qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
-
 	} else if (np->down) {
 		qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
 	}
@@ -2448,7 +2447,7 @@ static void dpaa_eth_napi_enable(struct dpaa_priv *priv)
 	struct dpaa_percpu_priv *percpu_priv;
 	int i;
 
-	for_each_possible_cpu(i) {
+	for_each_online_cpu(i) {
 		percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
 
 		percpu_priv->np.down = 0;
@@ -2461,7 +2460,7 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv)
 	struct dpaa_percpu_priv *percpu_priv;
 	int i;
 
-	for_each_possible_cpu(i) {
+	for_each_online_cpu(i) {
 		percpu_priv = per_cpu_ptr(priv->percpu_priv, i);
 
 		percpu_priv->np.down = 1;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 62497119c85f..7ce2e99b594d 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -501,7 +501,7 @@ static int dpaa_get_ts_info(struct net_device *net_dev,
 	struct device_node *mac_node = dev->of_node;
 	struct device_node *fman_node = NULL, *ptp_node = NULL;
 	struct platform_device *ptp_dev = NULL;
-	struct qoriq_ptp *ptp = NULL;
+	struct ptp_qoriq *ptp = NULL;
 
 	info->phc_index = -1;
 
@@ -569,7 +569,7 @@ static int dpaa_set_coalesce(struct net_device *dev,
 	qman_dqrr_get_ithresh(portal, &prev_thresh);
 
 	/* set new values */
-	for_each_cpu(cpu, cpus) {
+	for_each_cpu_and(cpu, cpus, cpu_online_mask) {
 		portal = qman_get_affine_portal(cpu);
 		res = qman_portal_set_iperiod(portal, period);
 		if (res)
@@ -586,7 +586,7 @@ static int dpaa_set_coalesce(struct net_device *dev,
 
 revert_values:
 	/* restore previous values */
-	for_each_cpu(cpu, cpus) {
+	for_each_cpu_and(cpu, cpus, cpu_online_mask) {
 		if (!needs_revert[cpu])
 			continue;
 		portal = qman_get_affine_portal(cpu);
diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig
index f6d244c663fd..fbef2829f3de 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config FSL_DPAA2_ETH
 	tristate "Freescale DPAA2 Ethernet"
 	depends on FSL_MC_BUS && FSL_MC_DPIO
@@ -9,8 +10,7 @@ config FSL_DPAA2_ETH
 
 config FSL_DPAA2_PTP_CLOCK
 	tristate "Freescale DPAA2 PTP Clock"
-	depends on FSL_DPAA2_ETH
-	imply PTP_1588_CLOCK
+	depends on FSL_DPAA2_ETH && PTP_1588_CLOCK_QORIQ
 	default y
 	help
 	  This driver adds support for using the DPAA2 1588 timer module
diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile
index 2f424e0a8225..d1e78cdd512f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa2/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_FSL_DPAA2_ETH)		+= fsl-dpaa2-eth.o
 obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK)	+= fsl-dpaa2-ptp.o
 
 fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o
+fsl-dpaa2-eth-${CONFIG_DEBUG_FS} += dpaa2-eth-debugfs.o
 fsl-dpaa2-ptp-objs	:= dpaa2-ptp.o dprtc.o
 
 # Needed by the tracing framework
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
new file mode 100644
index 000000000000..a027f4a9d0cc
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2015 Freescale Semiconductor Inc.
+ * Copyright 2018-2019 NXP
+ */
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include "dpaa2-eth.h"
+#include "dpaa2-eth-debugfs.h"
+
+#define DPAA2_ETH_DBG_ROOT "dpaa2-eth"
+
+static struct dentry *dpaa2_dbg_root;
+
+static int dpaa2_dbg_cpu_show(struct seq_file *file, void *offset)
+{
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private;
+	struct rtnl_link_stats64 *stats;
+	struct dpaa2_eth_drv_stats *extras;
+	int i;
+
+	seq_printf(file, "Per-CPU stats for %s\n", priv->net_dev->name);
+	seq_printf(file, "%s%16s%16s%16s%16s%16s%16s%16s%16s%16s\n",
+		   "CPU", "Rx", "Rx Err", "Rx SG", "Tx", "Tx Err", "Tx conf",
+		   "Tx SG", "Tx realloc", "Enq busy");
+
+	for_each_online_cpu(i) {
+		stats = per_cpu_ptr(priv->percpu_stats, i);
+		extras = per_cpu_ptr(priv->percpu_extras, i);
+		seq_printf(file, "%3d%16llu%16llu%16llu%16llu%16llu%16llu%16llu%16llu%16llu\n",
+			   i,
+			   stats->rx_packets,
+			   stats->rx_errors,
+			   extras->rx_sg_frames,
+			   stats->tx_packets,
+			   stats->tx_errors,
+			   extras->tx_conf_frames,
+			   extras->tx_sg_frames,
+			   extras->tx_reallocs,
+			   extras->tx_portal_busy);
+	}
+
+	return 0;
+}
+
+static int dpaa2_dbg_cpu_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)inode->i_private;
+
+	err = single_open(file, dpaa2_dbg_cpu_show, priv);
+	if (err < 0)
+		netdev_err(priv->net_dev, "single_open() failed\n");
+
+	return err;
+}
+
+static const struct file_operations dpaa2_dbg_cpu_ops = {
+	.open = dpaa2_dbg_cpu_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static char *fq_type_to_str(struct dpaa2_eth_fq *fq)
+{
+	switch (fq->type) {
+	case DPAA2_RX_FQ:
+		return "Rx";
+	case DPAA2_TX_CONF_FQ:
+		return "Tx conf";
+	default:
+		return "N/A";
+	}
+}
+
+static int dpaa2_dbg_fqs_show(struct seq_file *file, void *offset)
+{
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private;
+	struct dpaa2_eth_fq *fq;
+	u32 fcnt, bcnt;
+	int i, err;
+
+	seq_printf(file, "FQ stats for %s:\n", priv->net_dev->name);
+	seq_printf(file, "%s%16s%16s%16s%16s\n",
+		   "VFQID", "CPU", "Type", "Frames", "Pending frames");
+
+	for (i = 0; i <  priv->num_fqs; i++) {
+		fq = &priv->fq[i];
+		err = dpaa2_io_query_fq_count(NULL, fq->fqid, &fcnt, &bcnt);
+		if (err)
+			fcnt = 0;
+
+		seq_printf(file, "%5d%16d%16s%16llu%16u\n",
+			   fq->fqid,
+			   fq->target_cpu,
+			   fq_type_to_str(fq),
+			   fq->stats.frames,
+			   fcnt);
+	}
+
+	return 0;
+}
+
+static int dpaa2_dbg_fqs_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)inode->i_private;
+
+	err = single_open(file, dpaa2_dbg_fqs_show, priv);
+	if (err < 0)
+		netdev_err(priv->net_dev, "single_open() failed\n");
+
+	return err;
+}
+
+static const struct file_operations dpaa2_dbg_fq_ops = {
+	.open = dpaa2_dbg_fqs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset)
+{
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private;
+	struct dpaa2_eth_channel *ch;
+	int i;
+
+	seq_printf(file, "Channel stats for %s:\n", priv->net_dev->name);
+	seq_printf(file, "%s%16s%16s%16s%16s\n",
+		   "CHID", "CPU", "Deq busy", "CDANs", "Buf count");
+
+	for (i = 0; i < priv->num_channels; i++) {
+		ch = priv->channel[i];
+		seq_printf(file, "%4d%16d%16llu%16llu%16d\n",
+			   ch->ch_id,
+			   ch->nctx.desired_cpu,
+			   ch->stats.dequeue_portal_busy,
+			   ch->stats.cdan,
+			   ch->buf_count);
+	}
+
+	return 0;
+}
+
+static int dpaa2_dbg_ch_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)inode->i_private;
+
+	err = single_open(file, dpaa2_dbg_ch_show, priv);
+	if (err < 0)
+		netdev_err(priv->net_dev, "single_open() failed\n");
+
+	return err;
+}
+
+static const struct file_operations dpaa2_dbg_ch_ops = {
+	.open = dpaa2_dbg_ch_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void dpaa2_dbg_add(struct dpaa2_eth_priv *priv)
+{
+	if (!dpaa2_dbg_root)
+		return;
+
+	/* Create a directory for the interface */
+	priv->dbg.dir = debugfs_create_dir(priv->net_dev->name,
+					   dpaa2_dbg_root);
+	if (!priv->dbg.dir) {
+		netdev_err(priv->net_dev, "debugfs_create_dir() failed\n");
+		return;
+	}
+
+	/* per-cpu stats file */
+	priv->dbg.cpu_stats = debugfs_create_file("cpu_stats", 0444,
+						  priv->dbg.dir, priv,
+						  &dpaa2_dbg_cpu_ops);
+	if (!priv->dbg.cpu_stats) {
+		netdev_err(priv->net_dev, "debugfs_create_file() failed\n");
+		goto err_cpu_stats;
+	}
+
+	/* per-fq stats file */
+	priv->dbg.fq_stats = debugfs_create_file("fq_stats", 0444,
+						 priv->dbg.dir, priv,
+						 &dpaa2_dbg_fq_ops);
+	if (!priv->dbg.fq_stats) {
+		netdev_err(priv->net_dev, "debugfs_create_file() failed\n");
+		goto err_fq_stats;
+	}
+
+	/* per-fq stats file */
+	priv->dbg.ch_stats = debugfs_create_file("ch_stats", 0444,
+						 priv->dbg.dir, priv,
+						 &dpaa2_dbg_ch_ops);
+	if (!priv->dbg.fq_stats) {
+		netdev_err(priv->net_dev, "debugfs_create_file() failed\n");
+		goto err_ch_stats;
+	}
+
+	return;
+
+err_ch_stats:
+	debugfs_remove(priv->dbg.fq_stats);
+err_fq_stats:
+	debugfs_remove(priv->dbg.cpu_stats);
+err_cpu_stats:
+	debugfs_remove(priv->dbg.dir);
+}
+
+void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv)
+{
+	debugfs_remove(priv->dbg.fq_stats);
+	debugfs_remove(priv->dbg.ch_stats);
+	debugfs_remove(priv->dbg.cpu_stats);
+	debugfs_remove(priv->dbg.dir);
+}
+
+void dpaa2_eth_dbg_init(void)
+{
+	dpaa2_dbg_root = debugfs_create_dir(DPAA2_ETH_DBG_ROOT, NULL);
+	if (!dpaa2_dbg_root) {
+		pr_err("DPAA2-ETH: debugfs create failed\n");
+		return;
+	}
+
+	pr_debug("DPAA2-ETH: debugfs created\n");
+}
+
+void dpaa2_eth_dbg_exit(void)
+{
+	debugfs_remove(dpaa2_dbg_root);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h
new file mode 100644
index 000000000000..4f63de997a26
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2015 Freescale Semiconductor Inc.
+ * Copyright 2018-2019 NXP
+ */
+#ifndef DPAA2_ETH_DEBUGFS_H
+#define DPAA2_ETH_DEBUGFS_H
+
+#include <linux/dcache.h>
+
+struct dpaa2_eth_priv;
+
+struct dpaa2_debugfs {
+	struct dentry *dir;
+	struct dentry *fq_stats;
+	struct dentry *ch_stats;
+	struct dentry *cpu_stats;
+};
+
+#ifdef CONFIG_DEBUG_FS
+void dpaa2_eth_dbg_init(void);
+void dpaa2_eth_dbg_exit(void);
+void dpaa2_dbg_add(struct dpaa2_eth_priv *priv);
+void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv);
+#else
+static inline void dpaa2_eth_dbg_init(void) {}
+static inline void dpaa2_eth_dbg_exit(void) {}
+static inline void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) {}
+static inline void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv) {}
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* DPAA2_ETH_DEBUGFS_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 1ca9a18139ec..0acb11557ed1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -86,16 +86,16 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_BIDIRECTIONAL);
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 
-		skb_free_frag(sg_vaddr);
+		free_pages((unsigned long)sg_vaddr, 0);
 		if (dpaa2_sg_is_final(&sgt[i]))
 			break;
 	}
 
 free_buf:
-	skb_free_frag(vaddr);
+	free_pages((unsigned long)vaddr, 0);
 }
 
 /* Build a linear skb based on a single-buffer frame descriptor */
@@ -109,7 +109,7 @@ static struct sk_buff *build_linear_skb(struct dpaa2_eth_channel *ch,
 
 	ch->buf_count--;
 
-	skb = build_skb(fd_vaddr, DPAA2_ETH_SKB_SIZE);
+	skb = build_skb(fd_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -144,19 +144,19 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_single(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_BIDIRECTIONAL);
+		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
 
 		if (i == 0) {
 			/* We build the skb around the first data buffer */
-			skb = build_skb(sg_vaddr, DPAA2_ETH_SKB_SIZE);
+			skb = build_skb(sg_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE);
 			if (unlikely(!skb)) {
 				/* Free the first SG entry now, since we already
 				 * unmapped it and obtained the virtual address
 				 */
-				skb_free_frag(sg_vaddr);
+				free_pages((unsigned long)sg_vaddr, 0);
 
 				/* We still need to subtract the buffers used
 				 * by this FD from our software counter
@@ -211,9 +211,9 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
 
 	for (i = 0; i < count; i++) {
 		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_single(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_BIDIRECTIONAL);
-		skb_free_frag(vaddr);
+		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
+		free_pages((unsigned long)vaddr, 0);
 	}
 }
 
@@ -264,9 +264,7 @@ static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
 
 	fq = &priv->fq[queue_id];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = dpaa2_io_service_enqueue_qd(fq->channel->dpio,
-						  priv->tx_qdid, 0,
-						  fq->tx_qdbin, fd);
+		err = priv->enqueue(priv, fq, fd, 0);
 		if (err != -EBUSY)
 			break;
 	}
@@ -298,6 +296,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 	xdp.data_end = xdp.data + dpaa2_fd_get_len(fd);
 	xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
 	xdp_set_data_meta_invalid(&xdp);
+	xdp.rxq = &ch->xdp_rxq;
 
 	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
@@ -330,8 +329,20 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv,
 		xdp_release_buf(priv, ch, addr);
 		ch->stats.xdp_drop++;
 		break;
+	case XDP_REDIRECT:
+		dma_unmap_page(priv->net_dev->dev.parent, addr,
+			       DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL);
+		ch->buf_count--;
+		xdp.data_hard_start = vaddr;
+		err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
+		if (unlikely(err))
+			ch->stats.xdp_drop++;
+		else
+			ch->stats.xdp_redirect++;
+		break;
 	}
 
+	ch->xdp.res |= xdp_act;
 out:
 	rcu_read_unlock();
 	return xdp_act;
@@ -378,16 +389,16 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			return;
 		}
 
-		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_BIDIRECTIONAL);
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
 		WARN_ON(priv->xdp_prog);
 
-		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_BIDIRECTIONAL);
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
-		skb_free_frag(vaddr);
+		free_pages((unsigned long)vaddr, 0);
 		percpu_extras->rx_sg_frames++;
 		percpu_extras->rx_sg_bytes += dpaa2_fd_get_len(fd);
 	} else {
@@ -424,7 +435,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	percpu_stats->rx_packets++;
 	percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
 
-	napi_gro_receive(&ch->napi, skb);
+	list_add_tail(&skb->list, ch->rx_list);
 
 	return;
 
@@ -544,7 +555,7 @@ static int build_sg_fd(struct dpaa2_eth_priv *priv,
 	/* Prepare the HW SGT structure */
 	sgt_buf_size = priv->tx_data_offset +
 		       sizeof(struct dpaa2_sg_entry) *  num_dma_bufs;
-	sgt_buf = netdev_alloc_frag(sgt_buf_size + DPAA2_ETH_TX_BUF_ALIGN);
+	sgt_buf = napi_alloc_frag(sgt_buf_size + DPAA2_ETH_TX_BUF_ALIGN);
 	if (unlikely(!sgt_buf)) {
 		err = -ENOMEM;
 		goto sgt_buf_alloc_failed;
@@ -573,10 +584,11 @@ static int build_sg_fd(struct dpaa2_eth_priv *priv,
 	 * all of them on Tx Conf.
 	 */
 	swa = (struct dpaa2_eth_swa *)sgt_buf;
-	swa->skb = skb;
-	swa->scl = scl;
-	swa->num_sg = num_sg;
-	swa->sgt_size = sgt_buf_size;
+	swa->type = DPAA2_ETH_SWA_SG;
+	swa->sg.skb = skb;
+	swa->sg.scl = scl;
+	swa->sg.num_sg = num_sg;
+	swa->sg.sgt_size = sgt_buf_size;
 
 	/* Separately map the SGT buffer */
 	addr = dma_map_single(dev, sgt_buf, sgt_buf_size, DMA_BIDIRECTIONAL);
@@ -611,7 +623,7 @@ static int build_single_fd(struct dpaa2_eth_priv *priv,
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	u8 *buffer_start, *aligned_start;
-	struct sk_buff **skbh;
+	struct dpaa2_eth_swa *swa;
 	dma_addr_t addr;
 
 	buffer_start = skb->data - dpaa2_eth_needed_headroom(priv, skb);
@@ -628,8 +640,9 @@ static int build_single_fd(struct dpaa2_eth_priv *priv,
 	 * (in the private data area) such that we can release it
 	 * on Tx confirm
 	 */
-	skbh = (struct sk_buff **)buffer_start;
-	*skbh = skb;
+	swa = (struct dpaa2_eth_swa *)buffer_start;
+	swa->type = DPAA2_ETH_SWA_SINGLE;
+	swa->single.skb = skb;
 
 	addr = dma_map_single(dev, buffer_start,
 			      skb_tail_pointer(skb) - buffer_start,
@@ -657,47 +670,65 @@ static int build_single_fd(struct dpaa2_eth_priv *priv,
  * dpaa2_eth_tx().
  */
 static void free_tx_fd(const struct dpaa2_eth_priv *priv,
-		       const struct dpaa2_fd *fd)
+		       struct dpaa2_eth_fq *fq,
+		       const struct dpaa2_fd *fd, bool in_napi)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	dma_addr_t fd_addr;
-	struct sk_buff **skbh, *skb;
+	struct sk_buff *skb = NULL;
 	unsigned char *buffer_start;
 	struct dpaa2_eth_swa *swa;
 	u8 fd_format = dpaa2_fd_get_format(fd);
+	u32 fd_len = dpaa2_fd_get_len(fd);
 
 	fd_addr = dpaa2_fd_get_addr(fd);
-	skbh = dpaa2_iova_to_virt(priv->iommu_domain, fd_addr);
+	buffer_start = dpaa2_iova_to_virt(priv->iommu_domain, fd_addr);
+	swa = (struct dpaa2_eth_swa *)buffer_start;
 
 	if (fd_format == dpaa2_fd_single) {
-		skb = *skbh;
-		buffer_start = (unsigned char *)skbh;
-		/* Accessing the skb buffer is safe before dma unmap, because
-		 * we didn't map the actual skb shell.
-		 */
-		dma_unmap_single(dev, fd_addr,
-				 skb_tail_pointer(skb) - buffer_start,
-				 DMA_BIDIRECTIONAL);
+		if (swa->type == DPAA2_ETH_SWA_SINGLE) {
+			skb = swa->single.skb;
+			/* Accessing the skb buffer is safe before dma unmap,
+			 * because we didn't map the actual skb shell.
+			 */
+			dma_unmap_single(dev, fd_addr,
+					 skb_tail_pointer(skb) - buffer_start,
+					 DMA_BIDIRECTIONAL);
+		} else {
+			WARN_ONCE(swa->type != DPAA2_ETH_SWA_XDP, "Wrong SWA type");
+			dma_unmap_single(dev, fd_addr, swa->xdp.dma_size,
+					 DMA_BIDIRECTIONAL);
+		}
 	} else if (fd_format == dpaa2_fd_sg) {
-		swa = (struct dpaa2_eth_swa *)skbh;
-		skb = swa->skb;
+		skb = swa->sg.skb;
 
 		/* Unmap the scatterlist */
-		dma_unmap_sg(dev, swa->scl, swa->num_sg, DMA_BIDIRECTIONAL);
-		kfree(swa->scl);
+		dma_unmap_sg(dev, swa->sg.scl, swa->sg.num_sg,
+			     DMA_BIDIRECTIONAL);
+		kfree(swa->sg.scl);
 
 		/* Unmap the SGT buffer */
-		dma_unmap_single(dev, fd_addr, swa->sgt_size,
+		dma_unmap_single(dev, fd_addr, swa->sg.sgt_size,
 				 DMA_BIDIRECTIONAL);
 	} else {
 		netdev_dbg(priv->net_dev, "Invalid FD format\n");
 		return;
 	}
 
+	if (swa->type != DPAA2_ETH_SWA_XDP && in_napi) {
+		fq->dq_frames++;
+		fq->dq_bytes += fd_len;
+	}
+
+	if (swa->type == DPAA2_ETH_SWA_XDP) {
+		xdp_return_frame(swa->xdp.xdpf);
+		return;
+	}
+
 	/* Get the timestamp value */
 	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
 		struct skb_shared_hwtstamps shhwtstamps;
-		__le64 *ts = dpaa2_get_ts(skbh, true);
+		__le64 *ts = dpaa2_get_ts(buffer_start, true);
 		u64 ns;
 
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
@@ -709,10 +740,10 @@ static void free_tx_fd(const struct dpaa2_eth_priv *priv,
 
 	/* Free SGT buffer allocated on tx */
 	if (fd_format != dpaa2_fd_single)
-		skb_free_frag(skbh);
+		skb_free_frag(buffer_start);
 
 	/* Move on with skb release */
-	dev_kfree_skb(skb);
+	napi_consume_skb(skb, in_napi);
 }
 
 static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
@@ -726,6 +757,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	u16 queue_mapping;
 	unsigned int needed_headroom;
 	u32 fd_len;
+	u8 prio = 0;
 	int err, i;
 
 	percpu_stats = this_cpu_ptr(priv->percpu_stats);
@@ -783,11 +815,29 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	 * a queue affined to the same core that processed the Rx frame
 	 */
 	queue_mapping = skb_get_queue_mapping(skb);
+
+	if (net_dev->num_tc) {
+		prio = netdev_txq_to_tc(net_dev, queue_mapping);
+		/* Hardware interprets priority level 0 as being the highest,
+		 * so we need to do a reverse mapping to the netdev tc index
+		 */
+		prio = net_dev->num_tc - prio - 1;
+		/* We have only one FQ array entry for all Tx hardware queues
+		 * with the same flow id (but different priority levels)
+		 */
+		queue_mapping %= dpaa2_eth_queue_count(priv);
+	}
 	fq = &priv->fq[queue_mapping];
+
+	fd_len = dpaa2_fd_get_len(&fd);
+	nq = netdev_get_tx_queue(net_dev, queue_mapping);
+	netdev_tx_sent_queue(nq, fd_len);
+
+	/* Everything that happens after this enqueues might race with
+	 * the Tx confirmation callback for this frame
+	 */
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = dpaa2_io_service_enqueue_qd(fq->channel->dpio,
-						  priv->tx_qdid, 0,
-						  fq->tx_qdbin, &fd);
+		err = priv->enqueue(priv, fq, &fd, prio);
 		if (err != -EBUSY)
 			break;
 	}
@@ -795,14 +845,11 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	if (unlikely(err < 0)) {
 		percpu_stats->tx_errors++;
 		/* Clean up everything, including freeing the skb */
-		free_tx_fd(priv, &fd);
+		free_tx_fd(priv, fq, &fd, false);
+		netdev_tx_completed_queue(nq, 1, fd_len);
 	} else {
-		fd_len = dpaa2_fd_get_len(&fd);
 		percpu_stats->tx_packets++;
 		percpu_stats->tx_bytes += fd_len;
-
-		nq = netdev_get_tx_queue(net_dev, queue_mapping);
-		netdev_tx_sent_queue(nq, fd_len);
 	}
 
 	return NETDEV_TX_OK;
@@ -832,12 +879,9 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 	percpu_extras->tx_conf_frames++;
 	percpu_extras->tx_conf_bytes += fd_len;
 
-	fq->dq_frames++;
-	fq->dq_bytes += fd_len;
-
 	/* Check frame errors in the FD field */
 	fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK;
-	free_tx_fd(priv, fd);
+	free_tx_fd(priv, fq, fd, true);
 
 	if (likely(!fd_errors))
 		return;
@@ -903,7 +947,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	u64 buf_array[DPAA2_ETH_BUFS_PER_CMD];
-	void *buf;
+	struct page *page;
 	dma_addr_t addr;
 	int i, err;
 
@@ -911,14 +955,16 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		/* Allocate buffer visible to WRIOP + skb shared info +
 		 * alignment padding
 		 */
-		buf = napi_alloc_frag(dpaa2_eth_buf_raw_size(priv));
-		if (unlikely(!buf))
+		/* allocate one page for each Rx buffer. WRIOP sees
+		 * the entire page except for a tailroom reserved for
+		 * skb shared info
+		 */
+		page = dev_alloc_pages(0);
+		if (!page)
 			goto err_alloc;
 
-		buf = PTR_ALIGN(buf, priv->rx_buf_align);
-
-		addr = dma_map_single(dev, buf, DPAA2_ETH_RX_BUF_SIZE,
-				      DMA_BIDIRECTIONAL);
+		addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE,
+				    DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
 
@@ -926,7 +972,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 
 		/* tracing point */
 		trace_dpaa2_eth_buf_seed(priv->net_dev,
-					 buf, dpaa2_eth_buf_raw_size(priv),
+					 page, DPAA2_ETH_RX_BUF_RAW_SIZE,
 					 addr, DPAA2_ETH_RX_BUF_SIZE,
 					 bpid);
 	}
@@ -948,7 +994,7 @@ release_bufs:
 	return i;
 
 err_map:
-	skb_free_frag(buf);
+	__free_pages(page, 0);
 err_alloc:
 	/* If we managed to allocate at least some buffers,
 	 * release them to hardware
@@ -964,13 +1010,6 @@ static int seed_pool(struct dpaa2_eth_priv *priv, u16 bpid)
 	int i, j;
 	int new_count;
 
-	/* This is the lazy seeding of Rx buffer pools.
-	 * dpaa2_add_bufs() is also used on the Rx hotpath and calls
-	 * napi_alloc_frag(). The trouble with that is that it in turn ends up
-	 * calling this_cpu_ptr(), which mandates execution in atomic context.
-	 * Rather than splitting up the code, do a one-off preempt disable.
-	 */
-	preempt_disable();
 	for (j = 0; j < priv->num_channels; j++) {
 		for (i = 0; i < DPAA2_ETH_NUM_BUFS;
 		     i += DPAA2_ETH_BUFS_PER_CMD) {
@@ -978,12 +1017,10 @@ static int seed_pool(struct dpaa2_eth_priv *priv, u16 bpid)
 			priv->channel[j]->buf_count += new_count;
 
 			if (new_count < DPAA2_ETH_BUFS_PER_CMD) {
-				preempt_enable();
 				return -ENOMEM;
 			}
 		}
 	}
-	preempt_enable();
 
 	return 0;
 }
@@ -1080,11 +1117,16 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	struct dpaa2_eth_fq *fq, *txc_fq = NULL;
 	struct netdev_queue *nq;
 	int store_cleaned, work_done;
+	struct list_head rx_list;
 	int err;
 
 	ch = container_of(napi, struct dpaa2_eth_channel, napi);
+	ch->xdp.res = 0;
 	priv = ch->priv;
 
+	INIT_LIST_HEAD(&rx_list);
+	ch->rx_list = &rx_list;
+
 	do {
 		err = pull_channel(ch);
 		if (unlikely(err))
@@ -1128,7 +1170,9 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	work_done = max(rx_cleaned, 1);
 
 out:
-	if (txc_fq) {
+	netif_receive_skb_list(ch->rx_list);
+
+	if (txc_fq && txc_fq->dq_frames) {
 		nq = netdev_get_tx_queue(priv->net_dev, txc_fq->flowid);
 		netdev_tx_completed_queue(nq, txc_fq->dq_frames,
 					  txc_fq->dq_bytes);
@@ -1136,6 +1180,9 @@ out:
 		txc_fq->dq_bytes = 0;
 	}
 
+	if (ch->xdp.res & XDP_REDIRECT)
+		xdp_do_flush_map();
+
 	return work_done;
 }
 
@@ -1243,34 +1290,36 @@ enable_err:
 	return err;
 }
 
-/* The DPIO store must be empty when we call this,
- * at the end of every NAPI cycle.
- */
-static u32 drain_channel(struct dpaa2_eth_channel *ch)
+/* Total number of in-flight frames on ingress queues */
+static u32 ingress_fq_count(struct dpaa2_eth_priv *priv)
 {
-	u32 drained = 0, total = 0;
+	struct dpaa2_eth_fq *fq;
+	u32 fcnt = 0, bcnt = 0, total = 0;
+	int i, err;
 
-	do {
-		pull_channel(ch);
-		drained = consume_frames(ch, NULL);
-		total += drained;
-	} while (drained);
+	for (i = 0; i < priv->num_fqs; i++) {
+		fq = &priv->fq[i];
+		err = dpaa2_io_query_fq_count(NULL, fq->fqid, &fcnt, &bcnt);
+		if (err) {
+			netdev_warn(priv->net_dev, "query_fq_count failed");
+			break;
+		}
+		total += fcnt;
+	}
 
 	return total;
 }
 
-static u32 drain_ingress_frames(struct dpaa2_eth_priv *priv)
+static void wait_for_fq_empty(struct dpaa2_eth_priv *priv)
 {
-	struct dpaa2_eth_channel *ch;
-	int i;
-	u32 drained = 0;
-
-	for (i = 0; i < priv->num_channels; i++) {
-		ch = priv->channel[i];
-		drained += drain_channel(ch);
-	}
+	int retries = 10;
+	u32 pending;
 
-	return drained;
+	do {
+		pending = ingress_fq_count(priv);
+		if (pending)
+			msleep(100);
+	} while (pending && --retries);
 }
 
 static int dpaa2_eth_stop(struct net_device *net_dev)
@@ -1278,14 +1327,22 @@ static int dpaa2_eth_stop(struct net_device *net_dev)
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	int dpni_enabled = 0;
 	int retries = 10;
-	u32 drained;
 
 	netif_tx_stop_all_queues(net_dev);
 	netif_carrier_off(net_dev);
 
-	/* Loop while dpni_disable() attempts to drain the egress FQs
-	 * and confirm them back to us.
+	/* On dpni_disable(), the MC firmware will:
+	 * - stop MAC Rx and wait for all Rx frames to be enqueued to software
+	 * - cut off WRIOP dequeues from egress FQs and wait until transmission
+	 * of all in flight Tx frames is finished (and corresponding Tx conf
+	 * frames are enqueued back to software)
+	 *
+	 * Before calling dpni_disable(), we wait for all Tx frames to arrive
+	 * on WRIOP. After it finishes, wait until all remaining frames on Rx
+	 * and Tx conf queues are consumed on NAPI poll.
 	 */
+	msleep(500);
+
 	do {
 		dpni_disable(priv->mc_io, 0, priv->mc_token);
 		dpni_is_enabled(priv->mc_io, 0, priv->mc_token, &dpni_enabled);
@@ -1300,19 +1357,9 @@ static int dpaa2_eth_stop(struct net_device *net_dev)
 		 */
 	}
 
-	/* Wait for NAPI to complete on every core and disable it.
-	 * In particular, this will also prevent NAPI from being rescheduled if
-	 * a new CDAN is serviced, effectively discarding the CDAN. We therefore
-	 * don't even need to disarm the channels, except perhaps for the case
-	 * of a huge coalescing value.
-	 */
+	wait_for_fq_empty(priv);
 	disable_ch_napi(priv);
 
-	 /* Manually drain the Rx and TxConf queues */
-	drained = drain_ingress_frames(priv);
-	if (drained)
-		netdev_dbg(net_dev, "Drained %d frames.\n", drained);
-
 	/* Empty the buffer pool */
 	drain_pool(priv);
 
@@ -1730,6 +1777,177 @@ static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	return 0;
 }
 
+static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
+				    struct xdp_frame *xdpf)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	struct device *dev = net_dev->dev.parent;
+	struct rtnl_link_stats64 *percpu_stats;
+	struct dpaa2_eth_drv_stats *percpu_extras;
+	unsigned int needed_headroom;
+	struct dpaa2_eth_swa *swa;
+	struct dpaa2_eth_fq *fq;
+	struct dpaa2_fd fd;
+	void *buffer_start, *aligned_start;
+	dma_addr_t addr;
+	int err, i;
+
+	/* We require a minimum headroom to be able to transmit the frame.
+	 * Otherwise return an error and let the original net_device handle it
+	 */
+	needed_headroom = dpaa2_eth_needed_headroom(priv, NULL);
+	if (xdpf->headroom < needed_headroom)
+		return -EINVAL;
+
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+	percpu_extras = this_cpu_ptr(priv->percpu_extras);
+
+	/* Setup the FD fields */
+	memset(&fd, 0, sizeof(fd));
+
+	/* Align FD address, if possible */
+	buffer_start = xdpf->data - needed_headroom;
+	aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN,
+				  DPAA2_ETH_TX_BUF_ALIGN);
+	if (aligned_start >= xdpf->data - xdpf->headroom)
+		buffer_start = aligned_start;
+
+	swa = (struct dpaa2_eth_swa *)buffer_start;
+	/* fill in necessary fields here */
+	swa->type = DPAA2_ETH_SWA_XDP;
+	swa->xdp.dma_size = xdpf->data + xdpf->len - buffer_start;
+	swa->xdp.xdpf = xdpf;
+
+	addr = dma_map_single(dev, buffer_start,
+			      swa->xdp.dma_size,
+			      DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(dev, addr))) {
+		percpu_stats->tx_dropped++;
+		return -ENOMEM;
+	}
+
+	dpaa2_fd_set_addr(&fd, addr);
+	dpaa2_fd_set_offset(&fd, xdpf->data - buffer_start);
+	dpaa2_fd_set_len(&fd, xdpf->len);
+	dpaa2_fd_set_format(&fd, dpaa2_fd_single);
+	dpaa2_fd_set_ctrl(&fd, FD_CTRL_PTA);
+
+	fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
+	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
+		err = priv->enqueue(priv, fq, &fd, 0);
+		if (err != -EBUSY)
+			break;
+	}
+	percpu_extras->tx_portal_busy += i;
+	if (unlikely(err < 0)) {
+		percpu_stats->tx_errors++;
+		/* let the Rx device handle the cleanup */
+		return err;
+	}
+
+	percpu_stats->tx_packets++;
+	percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd);
+
+	return 0;
+}
+
+static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
+			      struct xdp_frame **frames, u32 flags)
+{
+	int drops = 0;
+	int i, err;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	if (!netif_running(net_dev))
+		return -ENETDOWN;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+
+		err = dpaa2_eth_xdp_xmit_frame(net_dev, xdpf);
+		if (err) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	return n - drops;
+}
+
+static int update_xps(struct dpaa2_eth_priv *priv)
+{
+	struct net_device *net_dev = priv->net_dev;
+	struct cpumask xps_mask;
+	struct dpaa2_eth_fq *fq;
+	int i, num_queues, netdev_queues;
+	int err = 0;
+
+	num_queues = dpaa2_eth_queue_count(priv);
+	netdev_queues = (net_dev->num_tc ? : 1) * num_queues;
+
+	/* The first <num_queues> entries in priv->fq array are Tx/Tx conf
+	 * queues, so only process those
+	 */
+	for (i = 0; i < netdev_queues; i++) {
+		fq = &priv->fq[i % num_queues];
+
+		cpumask_clear(&xps_mask);
+		cpumask_set_cpu(fq->target_cpu, &xps_mask);
+
+		err = netif_set_xps_queue(net_dev, &xps_mask, i);
+		if (err) {
+			netdev_warn_once(net_dev, "Error setting XPS queue\n");
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int dpaa2_eth_setup_tc(struct net_device *net_dev,
+			      enum tc_setup_type type, void *type_data)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	struct tc_mqprio_qopt *mqprio = type_data;
+	u8 num_tc, num_queues;
+	int i;
+
+	if (type != TC_SETUP_QDISC_MQPRIO)
+		return -EINVAL;
+
+	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	num_queues = dpaa2_eth_queue_count(priv);
+	num_tc = mqprio->num_tc;
+
+	if (num_tc == net_dev->num_tc)
+		return 0;
+
+	if (num_tc  > dpaa2_eth_tc_count(priv)) {
+		netdev_err(net_dev, "Max %d traffic classes supported\n",
+			   dpaa2_eth_tc_count(priv));
+		return -EINVAL;
+	}
+
+	if (!num_tc) {
+		netdev_reset_tc(net_dev);
+		netif_set_real_num_tx_queues(net_dev, num_queues);
+		goto out;
+	}
+
+	netdev_set_num_tc(net_dev, num_tc);
+	netif_set_real_num_tx_queues(net_dev, num_tc * num_queues);
+
+	for (i = 0; i < num_tc; i++)
+		netdev_set_tc_queue(net_dev, i, num_queues, i * num_queues);
+
+out:
+	update_xps(priv);
+
+	return 0;
+}
+
 static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_open = dpaa2_eth_open,
 	.ndo_start_xmit = dpaa2_eth_tx,
@@ -1741,6 +1959,8 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_do_ioctl = dpaa2_eth_ioctl,
 	.ndo_change_mtu = dpaa2_eth_change_mtu,
 	.ndo_bpf = dpaa2_eth_xdp,
+	.ndo_xdp_xmit = dpaa2_eth_xdp_xmit,
+	.ndo_setup_tc = dpaa2_eth_setup_tc,
 };
 
 static void cdan_cb(struct dpaa2_io_notification_ctx *ctx)
@@ -1829,7 +2049,7 @@ alloc_channel(struct dpaa2_eth_priv *priv)
 
 	channel->dpcon = setup_dpcon(priv);
 	if (IS_ERR_OR_NULL(channel->dpcon)) {
-		err = PTR_ERR(channel->dpcon);
+		err = PTR_ERR_OR_ZERO(channel->dpcon);
 		goto err_setup;
 	}
 
@@ -1885,7 +2105,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 		/* Try to allocate a channel */
 		channel = alloc_channel(priv);
 		if (IS_ERR_OR_NULL(channel)) {
-			err = PTR_ERR(channel);
+			err = PTR_ERR_OR_ZERO(channel);
 			if (err != -EPROBE_DEFER)
 				dev_info(dev,
 					 "No affine channel for cpu %d and above\n", i);
@@ -1902,7 +2122,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 
 		/* Register the new context */
 		channel->dpio = dpaa2_io_service_select(i);
-		err = dpaa2_io_service_register(channel->dpio, nctx);
+		err = dpaa2_io_service_register(channel->dpio, nctx, dev);
 		if (err) {
 			dev_dbg(dev, "No affine DPIO for cpu %d\n", i);
 			/* If no affine DPIO for this core, there's probably
@@ -1942,7 +2162,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 	return 0;
 
 err_set_cdan:
-	dpaa2_io_service_deregister(channel->dpio, nctx);
+	dpaa2_io_service_deregister(channel->dpio, nctx, dev);
 err_service_reg:
 	free_channel(priv, channel);
 err_alloc_ch:
@@ -1962,13 +2182,14 @@ err_alloc_ch:
 
 static void free_dpio(struct dpaa2_eth_priv *priv)
 {
-	int i;
+	struct device *dev = priv->net_dev->dev.parent;
 	struct dpaa2_eth_channel *ch;
+	int i;
 
 	/* deregister CDAN notifications and free channels */
 	for (i = 0; i < priv->num_channels; i++) {
 		ch = priv->channel[i];
-		dpaa2_io_service_deregister(ch->dpio, &ch->nctx);
+		dpaa2_io_service_deregister(ch->dpio, &ch->nctx, dev);
 		free_channel(priv, ch);
 	}
 }
@@ -1994,10 +2215,9 @@ static struct dpaa2_eth_channel *get_affine_channel(struct dpaa2_eth_priv *priv,
 static void set_fq_affinity(struct dpaa2_eth_priv *priv)
 {
 	struct device *dev = priv->net_dev->dev.parent;
-	struct cpumask xps_mask;
 	struct dpaa2_eth_fq *fq;
 	int rx_cpu, txc_cpu;
-	int i, err;
+	int i;
 
 	/* For each FQ, pick one channel/CPU to deliver frames to.
 	 * This may well change at runtime, either through irqbalance or
@@ -2016,17 +2236,6 @@ static void set_fq_affinity(struct dpaa2_eth_priv *priv)
 			break;
 		case DPAA2_TX_CONF_FQ:
 			fq->target_cpu = txc_cpu;
-
-			/* Tell the stack to affine to txc_cpu the Tx queue
-			 * associated with the confirmation one
-			 */
-			cpumask_clear(&xps_mask);
-			cpumask_set_cpu(txc_cpu, &xps_mask);
-			err = netif_set_xps_queue(priv->net_dev, &xps_mask,
-						  fq->flowid);
-			if (err)
-				dev_err(dev, "Error setting XPS queue\n");
-
 			txc_cpu = cpumask_next(txc_cpu, &priv->dpio_cpumask);
 			if (txc_cpu >= nr_cpu_ids)
 				txc_cpu = cpumask_first(&priv->dpio_cpumask);
@@ -2036,6 +2245,8 @@ static void set_fq_affinity(struct dpaa2_eth_priv *priv)
 		}
 		fq->channel = get_affine_channel(priv, fq->target_cpu);
 	}
+
+	update_xps(priv);
 }
 
 static void setup_fqs(struct dpaa2_eth_priv *priv)
@@ -2134,6 +2345,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_buffer_layout buf_layout = {0};
+	u16 rx_buf_align;
 	int err;
 
 	/* We need to check for WRIOP version 1.0.0, but depending on the MC
@@ -2142,9 +2354,9 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	 */
 	if (priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(0, 0, 0) ||
 	    priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(1, 0, 0))
-		priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1;
+		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1;
 	else
-		priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
+		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
 
 	/* tx buffer */
 	buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE;
@@ -2184,7 +2396,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	/* rx buffer */
 	buf_layout.pass_frame_status = true;
 	buf_layout.pass_parser_result = true;
-	buf_layout.data_align = priv->rx_buf_align;
+	buf_layout.data_align = rx_buf_align;
 	buf_layout.data_head_room = dpaa2_eth_rx_head_room(priv);
 	buf_layout.private_data_size = 0;
 	buf_layout.options = DPNI_BUF_LAYOUT_OPT_PARSER_RESULT |
@@ -2202,6 +2414,35 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	return 0;
 }
 
+#define DPNI_ENQUEUE_FQID_VER_MAJOR	7
+#define DPNI_ENQUEUE_FQID_VER_MINOR	9
+
+static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv,
+				       struct dpaa2_eth_fq *fq,
+				       struct dpaa2_fd *fd, u8 prio)
+{
+	return dpaa2_io_service_enqueue_qd(fq->channel->dpio,
+					   priv->tx_qdid, prio,
+					   fq->tx_qdbin, fd);
+}
+
+static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv,
+				       struct dpaa2_eth_fq *fq,
+				       struct dpaa2_fd *fd, u8 prio)
+{
+	return dpaa2_io_service_enqueue_fq(fq->channel->dpio,
+					   fq->tx_fqid[prio], fd);
+}
+
+static void set_enqueue_mode(struct dpaa2_eth_priv *priv)
+{
+	if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR,
+				   DPNI_ENQUEUE_FQID_VER_MINOR) < 0)
+		priv->enqueue = dpaa2_eth_enqueue_qd;
+	else
+		priv->enqueue = dpaa2_eth_enqueue_fq;
+}
+
 /* Configure the DPNI object this interface is associated with */
 static int setup_dpni(struct fsl_mc_device *ls_dev)
 {
@@ -2255,6 +2496,8 @@ static int setup_dpni(struct fsl_mc_device *ls_dev)
 	if (err)
 		goto close;
 
+	set_enqueue_mode(priv);
+
 	priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) *
 				       dpaa2_eth_fs_count(priv), GFP_KERNEL);
 	if (!priv->cls_rules)
@@ -2320,6 +2563,21 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv,
 		return err;
 	}
 
+	/* xdp_rxq setup */
+	err = xdp_rxq_info_reg(&fq->channel->xdp_rxq, priv->net_dev,
+			       fq->flowid);
+	if (err) {
+		dev_err(dev, "xdp_rxq_info_reg failed\n");
+		return err;
+	}
+
+	err = xdp_rxq_info_reg_mem_model(&fq->channel->xdp_rxq,
+					 MEM_TYPE_PAGE_ORDER0, NULL);
+	if (err) {
+		dev_err(dev, "xdp_rxq_info_reg_mem_model failed\n");
+		return err;
+	}
+
 	return 0;
 }
 
@@ -2329,15 +2587,20 @@ static int setup_tx_flow(struct dpaa2_eth_priv *priv,
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_queue queue;
 	struct dpni_queue_id qid;
-	int err;
+	int i, err;
 
-	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
-			     DPNI_QUEUE_TX, 0, fq->flowid, &queue, &qid);
-	if (err) {
-		dev_err(dev, "dpni_get_queue(TX) failed\n");
-		return err;
+	for (i = 0; i < dpaa2_eth_tc_count(priv); i++) {
+		err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
+				     DPNI_QUEUE_TX, i, fq->flowid,
+				     &queue, &qid);
+		if (err) {
+			dev_err(dev, "dpni_get_queue(TX) failed\n");
+			return err;
+		}
+		fq->tx_fqid[i] = qid.fqid;
 	}
 
+	/* All Tx queues belonging to the same flowid have the same qdbin */
 	fq->tx_qdbin = qid.qdbin;
 
 	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
@@ -2373,10 +2636,12 @@ static const struct dpaa2_eth_dist_fields dist_fields[] = {
 		.rxnfc_field = RXH_L2DA,
 		.cls_prot = NET_PROT_ETH,
 		.cls_field = NH_FLD_ETH_DA,
+		.id = DPAA2_ETH_DIST_ETHDST,
 		.size = 6,
 	}, {
 		.cls_prot = NET_PROT_ETH,
 		.cls_field = NH_FLD_ETH_SA,
+		.id = DPAA2_ETH_DIST_ETHSRC,
 		.size = 6,
 	}, {
 		/* This is the last ethertype field parsed:
@@ -2385,28 +2650,33 @@ static const struct dpaa2_eth_dist_fields dist_fields[] = {
 		 */
 		.cls_prot = NET_PROT_ETH,
 		.cls_field = NH_FLD_ETH_TYPE,
+		.id = DPAA2_ETH_DIST_ETHTYPE,
 		.size = 2,
 	}, {
 		/* VLAN header */
 		.rxnfc_field = RXH_VLAN,
 		.cls_prot = NET_PROT_VLAN,
 		.cls_field = NH_FLD_VLAN_TCI,
+		.id = DPAA2_ETH_DIST_VLAN,
 		.size = 2,
 	}, {
 		/* IP header */
 		.rxnfc_field = RXH_IP_SRC,
 		.cls_prot = NET_PROT_IP,
 		.cls_field = NH_FLD_IP_SRC,
+		.id = DPAA2_ETH_DIST_IPSRC,
 		.size = 4,
 	}, {
 		.rxnfc_field = RXH_IP_DST,
 		.cls_prot = NET_PROT_IP,
 		.cls_field = NH_FLD_IP_DST,
+		.id = DPAA2_ETH_DIST_IPDST,
 		.size = 4,
 	}, {
 		.rxnfc_field = RXH_L3_PROTO,
 		.cls_prot = NET_PROT_IP,
 		.cls_field = NH_FLD_IP_PROTO,
+		.id = DPAA2_ETH_DIST_IPPROTO,
 		.size = 1,
 	}, {
 		/* Using UDP ports, this is functionally equivalent to raw
@@ -2415,11 +2685,13 @@ static const struct dpaa2_eth_dist_fields dist_fields[] = {
 		.rxnfc_field = RXH_L4_B_0_1,
 		.cls_prot = NET_PROT_UDP,
 		.cls_field = NH_FLD_UDP_PORT_SRC,
+		.id = DPAA2_ETH_DIST_L4SRC,
 		.size = 2,
 	}, {
 		.rxnfc_field = RXH_L4_B_2_3,
 		.cls_prot = NET_PROT_UDP,
 		.cls_field = NH_FLD_UDP_PORT_DST,
+		.id = DPAA2_ETH_DIST_L4DST,
 		.size = 2,
 	},
 };
@@ -2485,12 +2757,15 @@ static int config_cls_key(struct dpaa2_eth_priv *priv, dma_addr_t key)
 }
 
 /* Size of the Rx flow classification key */
-int dpaa2_eth_cls_key_size(void)
+int dpaa2_eth_cls_key_size(u64 fields)
 {
 	int i, size = 0;
 
-	for (i = 0; i < ARRAY_SIZE(dist_fields); i++)
+	for (i = 0; i < ARRAY_SIZE(dist_fields); i++) {
+		if (!(fields & dist_fields[i].id))
+			continue;
 		size += dist_fields[i].size;
+	}
 
 	return size;
 }
@@ -2511,6 +2786,24 @@ int dpaa2_eth_cls_fld_off(int prot, int field)
 	return 0;
 }
 
+/* Prune unused fields from the classification rule.
+ * Used when masking is not supported
+ */
+void dpaa2_eth_cls_trim_rule(void *key_mem, u64 fields)
+{
+	int off = 0, new_off = 0;
+	int i, size;
+
+	for (i = 0; i < ARRAY_SIZE(dist_fields); i++) {
+		size = dist_fields[i].size;
+		if (dist_fields[i].id & fields) {
+			memcpy(key_mem + new_off, key_mem + off, size);
+			new_off += size;
+		}
+		off += size;
+	}
+}
+
 /* Set Rx distribution (hash or flow classification) key
  * flags is a combination of RXH_ bits
  */
@@ -2532,14 +2825,13 @@ static int dpaa2_eth_set_dist_key(struct net_device *net_dev,
 		struct dpkg_extract *key =
 			&cls_cfg.extracts[cls_cfg.num_extracts];
 
-		/* For Rx hashing key we set only the selected fields.
-		 * For Rx flow classification key we set all supported fields
+		/* For both Rx hashing and classification keys
+		 * we set only the selected fields.
 		 */
-		if (type == DPAA2_ETH_RX_DIST_HASH) {
-			if (!(flags & dist_fields[i].rxnfc_field))
-				continue;
+		if (!(flags & dist_fields[i].id))
+			continue;
+		if (type == DPAA2_ETH_RX_DIST_HASH)
 			rx_hash_fields |= dist_fields[i].rxnfc_field;
-		}
 
 		if (cls_cfg.num_extracts >= DPKG_MAX_NUM_OF_EXTRACTS) {
 			dev_err(dev, "error adding key extraction rule, too many rules?\n");
@@ -2594,16 +2886,28 @@ free_key:
 int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags)
 {
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	u64 key = 0;
+	int i;
 
 	if (!dpaa2_eth_hash_enabled(priv))
 		return -EOPNOTSUPP;
 
-	return dpaa2_eth_set_dist_key(net_dev, DPAA2_ETH_RX_DIST_HASH, flags);
+	for (i = 0; i < ARRAY_SIZE(dist_fields); i++)
+		if (dist_fields[i].rxnfc_field & flags)
+			key |= dist_fields[i].id;
+
+	return dpaa2_eth_set_dist_key(net_dev, DPAA2_ETH_RX_DIST_HASH, key);
 }
 
-static int dpaa2_eth_set_cls(struct dpaa2_eth_priv *priv)
+int dpaa2_eth_set_cls(struct net_device *net_dev, u64 flags)
+{
+	return dpaa2_eth_set_dist_key(net_dev, DPAA2_ETH_RX_DIST_CLS, flags);
+}
+
+static int dpaa2_eth_set_default_cls(struct dpaa2_eth_priv *priv)
 {
 	struct device *dev = priv->net_dev->dev.parent;
+	int err;
 
 	/* Check if we actually support Rx flow classification */
 	if (dpaa2_eth_has_legacy_dist(priv)) {
@@ -2611,8 +2915,7 @@ static int dpaa2_eth_set_cls(struct dpaa2_eth_priv *priv)
 		return -EOPNOTSUPP;
 	}
 
-	if (priv->dpni_attrs.options & DPNI_OPT_NO_FS ||
-	    !(priv->dpni_attrs.options & DPNI_OPT_HAS_KEY_MASKING)) {
+	if (!dpaa2_eth_fs_enabled(priv)) {
 		dev_dbg(dev, "Rx cls disabled in DPNI options\n");
 		return -EOPNOTSUPP;
 	}
@@ -2622,9 +2925,21 @@ static int dpaa2_eth_set_cls(struct dpaa2_eth_priv *priv)
 		return -EOPNOTSUPP;
 	}
 
+	/* If there is no support for masking in the classification table,
+	 * we don't set a default key, as it will depend on the rules
+	 * added by the user at runtime.
+	 */
+	if (!dpaa2_eth_fs_mask_enabled(priv))
+		goto out;
+
+	err = dpaa2_eth_set_cls(priv->net_dev, DPAA2_ETH_DIST_ALL);
+	if (err)
+		return err;
+
+out:
 	priv->rx_cls_enabled = 1;
 
-	return dpaa2_eth_set_dist_key(priv->net_dev, DPAA2_ETH_RX_DIST_CLS, 0);
+	return 0;
 }
 
 /* Bind the DPNI to its needed objects and resources: buffer pool, DPIOs,
@@ -2659,7 +2974,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv)
 	/* Configure the flow classification key; it includes all
 	 * supported header fields and cannot be modified at runtime
 	 */
-	err = dpaa2_eth_set_cls(priv);
+	err = dpaa2_eth_set_default_cls(priv);
 	if (err && err != -EOPNOTSUPP)
 		dev_err(dev, "Failed to configure Rx classification key\n");
 
@@ -2986,7 +3301,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	dev = &dpni_dev->dev;
 
 	/* Net device */
-	net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA2_ETH_MAX_TX_QUEUES);
+	net_dev = alloc_etherdev_mq(sizeof(*priv), DPAA2_ETH_MAX_NETDEV_QUEUES);
 	if (!net_dev) {
 		dev_err(dev, "alloc_etherdev_mq() failed\n");
 		return -ENOMEM;
@@ -3083,6 +3398,10 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 		goto err_netdev_reg;
 	}
 
+#ifdef CONFIG_DEBUG_FS
+	dpaa2_dbg_add(priv);
+#endif
+
 	dev_info(dev, "Probed interface %s\n", net_dev->name);
 	return 0;
 
@@ -3126,6 +3445,9 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 	net_dev = dev_get_drvdata(dev);
 	priv = netdev_priv(net_dev);
 
+#ifdef CONFIG_DEBUG_FS
+	dpaa2_dbg_remove(priv);
+#endif
 	unregister_netdev(net_dev);
 
 	if (priv->do_link_poll)
@@ -3170,4 +3492,25 @@ static struct fsl_mc_driver dpaa2_eth_driver = {
 	.match_id_table = dpaa2_eth_match_id_table
 };
 
-module_fsl_mc_driver(dpaa2_eth_driver);
+static int __init dpaa2_eth_driver_init(void)
+{
+	int err;
+
+	dpaa2_eth_dbg_init();
+	err = fsl_mc_driver_register(&dpaa2_eth_driver);
+	if (err) {
+		dpaa2_eth_dbg_exit();
+		return err;
+	}
+
+	return 0;
+}
+
+static void __exit dpaa2_eth_driver_exit(void)
+{
+	dpaa2_eth_dbg_exit();
+	fsl_mc_driver_unregister(&dpaa2_eth_driver);
+}
+
+module_init(dpaa2_eth_driver_init);
+module_exit(dpaa2_eth_driver_exit);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 69c965de192b..9af18c24221f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -16,6 +16,7 @@
 #include "dpni-cmd.h"
 
 #include "dpaa2-eth-trace.h"
+#include "dpaa2-eth-debugfs.h"
 
 #define DPAA2_WRIOP_VERSION(x, y, z) ((x) << 10 | (y) << 5 | (z) << 0)
 
@@ -52,7 +53,8 @@
  */
 #define DPAA2_ETH_MAX_FRAMES_PER_QUEUE	(DPAA2_ETH_TAILDROP_THRESH / 64)
 #define DPAA2_ETH_NUM_BUFS		(DPAA2_ETH_MAX_FRAMES_PER_QUEUE + 256)
-#define DPAA2_ETH_REFILL_THRESH		DPAA2_ETH_MAX_FRAMES_PER_QUEUE
+#define DPAA2_ETH_REFILL_THRESH \
+	(DPAA2_ETH_NUM_BUFS - DPAA2_ETH_BUFS_PER_CMD)
 
 /* Maximum number of buffers that can be acquired/released through a single
  * QBMan command
@@ -62,9 +64,11 @@
 /* Hardware requires alignment for ingress/egress buffer addresses */
 #define DPAA2_ETH_TX_BUF_ALIGN		64
 
-#define DPAA2_ETH_RX_BUF_SIZE		2048
-#define DPAA2_ETH_SKB_SIZE \
-	(DPAA2_ETH_RX_BUF_SIZE + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define DPAA2_ETH_RX_BUF_RAW_SIZE	PAGE_SIZE
+#define DPAA2_ETH_RX_BUF_TAILROOM \
+	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
+#define DPAA2_ETH_RX_BUF_SIZE \
+	(DPAA2_ETH_RX_BUF_RAW_SIZE - DPAA2_ETH_RX_BUF_TAILROOM)
 
 /* Hardware annotation area in RX/TX buffers */
 #define DPAA2_ETH_RX_HWA_SIZE		64
@@ -85,12 +89,33 @@
  */
 #define DPAA2_ETH_SWA_SIZE		64
 
+/* We store different information in the software annotation area of a Tx frame
+ * based on what type of frame it is
+ */
+enum dpaa2_eth_swa_type {
+	DPAA2_ETH_SWA_SINGLE,
+	DPAA2_ETH_SWA_SG,
+	DPAA2_ETH_SWA_XDP,
+};
+
 /* Must keep this struct smaller than DPAA2_ETH_SWA_SIZE */
 struct dpaa2_eth_swa {
-	struct sk_buff *skb;
-	struct scatterlist *scl;
-	int num_sg;
-	int sgt_size;
+	enum dpaa2_eth_swa_type type;
+	union {
+		struct {
+			struct sk_buff *skb;
+		} single;
+		struct {
+			struct sk_buff *skb;
+			struct scatterlist *scl;
+			int num_sg;
+			int sgt_size;
+		} sg;
+		struct {
+			int dma_size;
+			struct xdp_frame *xdpf;
+		} xdp;
+	};
 };
 
 /* Annotation valid bits in FD FRC */
@@ -253,13 +278,17 @@ struct dpaa2_eth_ch_stats {
 	__u64 xdp_drop;
 	__u64 xdp_tx;
 	__u64 xdp_tx_err;
+	__u64 xdp_redirect;
 };
 
 /* Maximum number of queues associated with a DPNI */
+#define DPAA2_ETH_MAX_TCS		8
 #define DPAA2_ETH_MAX_RX_QUEUES		16
 #define DPAA2_ETH_MAX_TX_QUEUES		16
 #define DPAA2_ETH_MAX_QUEUES		(DPAA2_ETH_MAX_RX_QUEUES + \
 					DPAA2_ETH_MAX_TX_QUEUES)
+#define DPAA2_ETH_MAX_NETDEV_QUEUES	\
+	(DPAA2_ETH_MAX_TX_QUEUES * DPAA2_ETH_MAX_TCS)
 
 #define DPAA2_ETH_MAX_DPCONS		16
 
@@ -273,7 +302,9 @@ struct dpaa2_eth_priv;
 struct dpaa2_eth_fq {
 	u32 fqid;
 	u32 tx_qdbin;
+	u32 tx_fqid[DPAA2_ETH_MAX_TCS];
 	u16 flowid;
+	u8 tc;
 	int target_cpu;
 	u32 dq_frames;
 	u32 dq_bytes;
@@ -291,6 +322,7 @@ struct dpaa2_eth_ch_xdp {
 	struct bpf_prog *prog;
 	u64 drop_bufs[DPAA2_ETH_BUFS_PER_CMD];
 	int drop_cnt;
+	unsigned int res;
 };
 
 struct dpaa2_eth_channel {
@@ -305,6 +337,8 @@ struct dpaa2_eth_channel {
 	int buf_count;
 	struct dpaa2_eth_ch_stats stats;
 	struct dpaa2_eth_ch_xdp xdp;
+	struct xdp_rxq_info xdp_rxq;
+	struct list_head *rx_list;
 };
 
 struct dpaa2_eth_dist_fields {
@@ -312,6 +346,7 @@ struct dpaa2_eth_dist_fields {
 	enum net_prot cls_prot;
 	int cls_field;
 	int size;
+	u64 id;
 };
 
 struct dpaa2_eth_cls_rule {
@@ -325,6 +360,9 @@ struct dpaa2_eth_priv {
 
 	u8 num_fqs;
 	struct dpaa2_eth_fq fq[DPAA2_ETH_MAX_QUEUES];
+	int (*enqueue)(struct dpaa2_eth_priv *priv,
+		       struct dpaa2_eth_fq *fq,
+		       struct dpaa2_fd *fd, u8 prio);
 
 	u8 num_channels;
 	struct dpaa2_eth_channel *channel[DPAA2_ETH_MAX_DPCONS];
@@ -342,7 +380,6 @@ struct dpaa2_eth_priv {
 	bool rx_tstamp; /* Rx timestamping enabled */
 
 	u16 tx_qdid;
-	u16 rx_buf_align;
 	struct fsl_mc_io *mc_io;
 	/* Cores which have an affine DPIO/DPCON.
 	 * This is the cpu set on which Rx and Tx conf frames are processed
@@ -362,9 +399,13 @@ struct dpaa2_eth_priv {
 
 	/* enabled ethtool hashing bits */
 	u64 rx_hash_fields;
+	u64 rx_cls_fields;
 	struct dpaa2_eth_cls_rule *cls_rules;
 	u8 rx_cls_enabled;
 	struct bpf_prog *xdp_prog;
+#ifdef CONFIG_DEBUG_FS
+	struct dpaa2_debugfs dbg;
+#endif
 };
 
 #define DPAA2_RXH_SUPPORTED	(RXH_L2DA | RXH_VLAN | RXH_L3_PROTO \
@@ -402,22 +443,38 @@ static inline int dpaa2_eth_cmp_dpni_ver(struct dpaa2_eth_priv *priv,
 	(dpaa2_eth_cmp_dpni_ver((priv), DPNI_RX_DIST_KEY_VER_MAJOR,	\
 				DPNI_RX_DIST_KEY_VER_MINOR) < 0)
 
+#define dpaa2_eth_fs_enabled(priv)	\
+	(!((priv)->dpni_attrs.options & DPNI_OPT_NO_FS))
+
+#define dpaa2_eth_fs_mask_enabled(priv)	\
+	((priv)->dpni_attrs.options & DPNI_OPT_HAS_KEY_MASKING)
+
 #define dpaa2_eth_fs_count(priv)        \
 	((priv)->dpni_attrs.fs_entries)
 
+#define dpaa2_eth_tc_count(priv)	\
+	((priv)->dpni_attrs.num_tcs)
+
+/* We have exactly one {Rx, Tx conf} queue per channel */
+#define dpaa2_eth_queue_count(priv)     \
+	((priv)->num_channels)
+
 enum dpaa2_eth_rx_dist {
 	DPAA2_ETH_RX_DIST_HASH,
 	DPAA2_ETH_RX_DIST_CLS
 };
 
-/* Hardware only sees DPAA2_ETH_RX_BUF_SIZE, but the skb built around
- * the buffer also needs space for its shared info struct, and we need
- * to allocate enough to accommodate hardware alignment restrictions
- */
-static inline unsigned int dpaa2_eth_buf_raw_size(struct dpaa2_eth_priv *priv)
-{
-	return DPAA2_ETH_SKB_SIZE + priv->rx_buf_align;
-}
+/* Unique IDs for the supported Rx classification header fields */
+#define DPAA2_ETH_DIST_ETHDST		BIT(0)
+#define DPAA2_ETH_DIST_ETHSRC		BIT(1)
+#define DPAA2_ETH_DIST_ETHTYPE		BIT(2)
+#define DPAA2_ETH_DIST_VLAN		BIT(3)
+#define DPAA2_ETH_DIST_IPSRC		BIT(4)
+#define DPAA2_ETH_DIST_IPDST		BIT(5)
+#define DPAA2_ETH_DIST_IPPROTO		BIT(6)
+#define DPAA2_ETH_DIST_L4SRC		BIT(7)
+#define DPAA2_ETH_DIST_L4DST		BIT(8)
+#define DPAA2_ETH_DIST_ALL		(~0ULL)
 
 static inline
 unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
@@ -425,6 +482,12 @@ unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
 {
 	unsigned int headroom = DPAA2_ETH_SWA_SIZE;
 
+	/* If we don't have an skb (e.g. XDP buffer), we only need space for
+	 * the software annotation area
+	 */
+	if (!skb)
+		return headroom;
+
 	/* For non-linear skbs we have no headroom requirement, as we build a
 	 * SG frame with a newly allocated SGT buffer
 	 */
@@ -443,18 +506,13 @@ unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
  */
 static inline unsigned int dpaa2_eth_rx_head_room(struct dpaa2_eth_priv *priv)
 {
-	return priv->tx_data_offset + DPAA2_ETH_TX_BUF_ALIGN -
-	       DPAA2_ETH_RX_HWA_SIZE;
-}
-
-/* We have exactly one {Rx, Tx conf} queue per channel */
-static int dpaa2_eth_queue_count(struct dpaa2_eth_priv *priv)
-{
-	return priv->num_channels;
+	return priv->tx_data_offset - DPAA2_ETH_RX_HWA_SIZE;
 }
 
 int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags);
-int dpaa2_eth_cls_key_size(void);
+int dpaa2_eth_set_cls(struct net_device *net_dev, u64 key);
+int dpaa2_eth_cls_key_size(u64 key);
 int dpaa2_eth_cls_fld_off(int prot, int field);
+void dpaa2_eth_cls_trim_rule(void *key_mem, u64 fields);
 
 #endif	/* __DPAA2_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index a7389e722c49..7b182f4b263c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/net_tstamp.h>
+#include <linux/nospec.h>
 
 #include "dpni.h"	/* DPNI_LINK_OPT_* */
 #include "dpaa2-eth.h"
@@ -48,6 +49,7 @@ static char dpaa2_ethtool_extras[][ETH_GSTRING_LEN] = {
 	"[drv] xdp drop",
 	"[drv] xdp tx",
 	"[drv] xdp tx errors",
+	"[drv] xdp redirect",
 	/* FQ stats */
 	"[qbman] rx pending frames",
 	"[qbman] rx pending bytes",
@@ -263,7 +265,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 }
 
 static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
-			 void *key, void *mask)
+			 void *key, void *mask, u64 *fields)
 {
 	int off;
 
@@ -271,18 +273,21 @@ static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
 		off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE);
 		*(__be16 *)(key + off) = eth_value->h_proto;
 		*(__be16 *)(mask + off) = eth_mask->h_proto;
+		*fields |= DPAA2_ETH_DIST_ETHTYPE;
 	}
 
 	if (!is_zero_ether_addr(eth_mask->h_source)) {
 		off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_SA);
 		ether_addr_copy(key + off, eth_value->h_source);
 		ether_addr_copy(mask + off, eth_mask->h_source);
+		*fields |= DPAA2_ETH_DIST_ETHSRC;
 	}
 
 	if (!is_zero_ether_addr(eth_mask->h_dest)) {
 		off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_DA);
 		ether_addr_copy(key + off, eth_value->h_dest);
 		ether_addr_copy(mask + off, eth_mask->h_dest);
+		*fields |= DPAA2_ETH_DIST_ETHDST;
 	}
 
 	return 0;
@@ -290,7 +295,7 @@ static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
 
 static int prep_uip_rule(struct ethtool_usrip4_spec *uip_value,
 			 struct ethtool_usrip4_spec *uip_mask,
-			 void *key, void *mask)
+			 void *key, void *mask, u64 *fields)
 {
 	int off;
 	u32 tmp_value, tmp_mask;
@@ -302,18 +307,21 @@ static int prep_uip_rule(struct ethtool_usrip4_spec *uip_value,
 		off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_SRC);
 		*(__be32 *)(key + off) = uip_value->ip4src;
 		*(__be32 *)(mask + off) = uip_mask->ip4src;
+		*fields |= DPAA2_ETH_DIST_IPSRC;
 	}
 
 	if (uip_mask->ip4dst) {
 		off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_DST);
 		*(__be32 *)(key + off) = uip_value->ip4dst;
 		*(__be32 *)(mask + off) = uip_mask->ip4dst;
+		*fields |= DPAA2_ETH_DIST_IPDST;
 	}
 
 	if (uip_mask->proto) {
 		off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_PROTO);
 		*(u8 *)(key + off) = uip_value->proto;
 		*(u8 *)(mask + off) = uip_mask->proto;
+		*fields |= DPAA2_ETH_DIST_IPPROTO;
 	}
 
 	if (uip_mask->l4_4_bytes) {
@@ -323,23 +331,26 @@ static int prep_uip_rule(struct ethtool_usrip4_spec *uip_value,
 		off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_SRC);
 		*(__be16 *)(key + off) = htons(tmp_value >> 16);
 		*(__be16 *)(mask + off) = htons(tmp_mask >> 16);
+		*fields |= DPAA2_ETH_DIST_L4SRC;
 
 		off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_DST);
 		*(__be16 *)(key + off) = htons(tmp_value & 0xFFFF);
 		*(__be16 *)(mask + off) = htons(tmp_mask & 0xFFFF);
+		*fields |= DPAA2_ETH_DIST_L4DST;
 	}
 
 	/* Only apply the rule for IPv4 frames */
 	off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE);
 	*(__be16 *)(key + off) = htons(ETH_P_IP);
 	*(__be16 *)(mask + off) = htons(0xFFFF);
+	*fields |= DPAA2_ETH_DIST_ETHTYPE;
 
 	return 0;
 }
 
 static int prep_l4_rule(struct ethtool_tcpip4_spec *l4_value,
 			struct ethtool_tcpip4_spec *l4_mask,
-			void *key, void *mask, u8 l4_proto)
+			void *key, void *mask, u8 l4_proto, u64 *fields)
 {
 	int off;
 
@@ -350,41 +361,47 @@ static int prep_l4_rule(struct ethtool_tcpip4_spec *l4_value,
 		off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_SRC);
 		*(__be32 *)(key + off) = l4_value->ip4src;
 		*(__be32 *)(mask + off) = l4_mask->ip4src;
+		*fields |= DPAA2_ETH_DIST_IPSRC;
 	}
 
 	if (l4_mask->ip4dst) {
 		off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_DST);
 		*(__be32 *)(key + off) = l4_value->ip4dst;
 		*(__be32 *)(mask + off) = l4_mask->ip4dst;
+		*fields |= DPAA2_ETH_DIST_IPDST;
 	}
 
 	if (l4_mask->psrc) {
 		off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_SRC);
 		*(__be16 *)(key + off) = l4_value->psrc;
 		*(__be16 *)(mask + off) = l4_mask->psrc;
+		*fields |= DPAA2_ETH_DIST_L4SRC;
 	}
 
 	if (l4_mask->pdst) {
 		off = dpaa2_eth_cls_fld_off(NET_PROT_UDP, NH_FLD_UDP_PORT_DST);
 		*(__be16 *)(key + off) = l4_value->pdst;
 		*(__be16 *)(mask + off) = l4_mask->pdst;
+		*fields |= DPAA2_ETH_DIST_L4DST;
 	}
 
 	/* Only apply the rule for IPv4 frames with the specified L4 proto */
 	off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_TYPE);
 	*(__be16 *)(key + off) = htons(ETH_P_IP);
 	*(__be16 *)(mask + off) = htons(0xFFFF);
+	*fields |= DPAA2_ETH_DIST_ETHTYPE;
 
 	off = dpaa2_eth_cls_fld_off(NET_PROT_IP, NH_FLD_IP_PROTO);
 	*(u8 *)(key + off) = l4_proto;
 	*(u8 *)(mask + off) = 0xFF;
+	*fields |= DPAA2_ETH_DIST_IPPROTO;
 
 	return 0;
 }
 
 static int prep_ext_rule(struct ethtool_flow_ext *ext_value,
 			 struct ethtool_flow_ext *ext_mask,
-			 void *key, void *mask)
+			 void *key, void *mask, u64 *fields)
 {
 	int off;
 
@@ -395,6 +412,7 @@ static int prep_ext_rule(struct ethtool_flow_ext *ext_value,
 		off = dpaa2_eth_cls_fld_off(NET_PROT_VLAN, NH_FLD_VLAN_TCI);
 		*(__be16 *)(key + off) = ext_value->vlan_tci;
 		*(__be16 *)(mask + off) = ext_mask->vlan_tci;
+		*fields |= DPAA2_ETH_DIST_VLAN;
 	}
 
 	return 0;
@@ -402,7 +420,7 @@ static int prep_ext_rule(struct ethtool_flow_ext *ext_value,
 
 static int prep_mac_ext_rule(struct ethtool_flow_ext *ext_value,
 			     struct ethtool_flow_ext *ext_mask,
-			     void *key, void *mask)
+			     void *key, void *mask, u64 *fields)
 {
 	int off;
 
@@ -410,36 +428,38 @@ static int prep_mac_ext_rule(struct ethtool_flow_ext *ext_value,
 		off = dpaa2_eth_cls_fld_off(NET_PROT_ETH, NH_FLD_ETH_DA);
 		ether_addr_copy(key + off, ext_value->h_dest);
 		ether_addr_copy(mask + off, ext_mask->h_dest);
+		*fields |= DPAA2_ETH_DIST_ETHDST;
 	}
 
 	return 0;
 }
 
-static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask)
+static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask,
+			 u64 *fields)
 {
 	int err;
 
 	switch (fs->flow_type & 0xFF) {
 	case ETHER_FLOW:
 		err = prep_eth_rule(&fs->h_u.ether_spec, &fs->m_u.ether_spec,
-				    key, mask);
+				    key, mask, fields);
 		break;
 	case IP_USER_FLOW:
 		err = prep_uip_rule(&fs->h_u.usr_ip4_spec,
-				    &fs->m_u.usr_ip4_spec, key, mask);
+				    &fs->m_u.usr_ip4_spec, key, mask, fields);
 		break;
 	case TCP_V4_FLOW:
 		err = prep_l4_rule(&fs->h_u.tcp_ip4_spec, &fs->m_u.tcp_ip4_spec,
-				   key, mask, IPPROTO_TCP);
+				   key, mask, IPPROTO_TCP, fields);
 		break;
 	case UDP_V4_FLOW:
 		err = prep_l4_rule(&fs->h_u.udp_ip4_spec, &fs->m_u.udp_ip4_spec,
-				   key, mask, IPPROTO_UDP);
+				   key, mask, IPPROTO_UDP, fields);
 		break;
 	case SCTP_V4_FLOW:
 		err = prep_l4_rule(&fs->h_u.sctp_ip4_spec,
 				   &fs->m_u.sctp_ip4_spec, key, mask,
-				   IPPROTO_SCTP);
+				   IPPROTO_SCTP, fields);
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -449,13 +469,14 @@ static int prep_cls_rule(struct ethtool_rx_flow_spec *fs, void *key, void *mask)
 		return err;
 
 	if (fs->flow_type & FLOW_EXT) {
-		err = prep_ext_rule(&fs->h_ext, &fs->m_ext, key, mask);
+		err = prep_ext_rule(&fs->h_ext, &fs->m_ext, key, mask, fields);
 		if (err)
 			return err;
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT) {
-		err = prep_mac_ext_rule(&fs->h_ext, &fs->m_ext, key, mask);
+		err = prep_mac_ext_rule(&fs->h_ext, &fs->m_ext, key, mask,
+					fields);
 		if (err)
 			return err;
 	}
@@ -472,6 +493,7 @@ static int do_cls_rule(struct net_device *net_dev,
 	struct dpni_rule_cfg rule_cfg = { 0 };
 	struct dpni_fs_action_cfg fs_act = { 0 };
 	dma_addr_t key_iova;
+	u64 fields = 0;
 	void *key_buf;
 	int err;
 
@@ -479,7 +501,7 @@ static int do_cls_rule(struct net_device *net_dev,
 	    fs->ring_cookie >= dpaa2_eth_queue_count(priv))
 		return -EINVAL;
 
-	rule_cfg.key_size = dpaa2_eth_cls_key_size();
+	rule_cfg.key_size = dpaa2_eth_cls_key_size(DPAA2_ETH_DIST_ALL);
 
 	/* allocate twice the key size, for the actual key and for mask */
 	key_buf = kzalloc(rule_cfg.key_size * 2, GFP_KERNEL);
@@ -487,10 +509,36 @@ static int do_cls_rule(struct net_device *net_dev,
 		return -ENOMEM;
 
 	/* Fill the key and mask memory areas */
-	err = prep_cls_rule(fs, key_buf, key_buf + rule_cfg.key_size);
+	err = prep_cls_rule(fs, key_buf, key_buf + rule_cfg.key_size, &fields);
 	if (err)
 		goto free_mem;
 
+	if (!dpaa2_eth_fs_mask_enabled(priv)) {
+		/* Masking allows us to configure a maximal key during init and
+		 * use it for all flow steering rules. Without it, we include
+		 * in the key only the fields actually used, so we need to
+		 * extract the others from the final key buffer.
+		 *
+		 * Program the FS key if needed, or return error if previously
+		 * set key can't be used for the current rule. User needs to
+		 * delete existing rules in this case to allow for the new one.
+		 */
+		if (!priv->rx_cls_fields) {
+			err = dpaa2_eth_set_cls(net_dev, fields);
+			if (err)
+				goto free_mem;
+
+			priv->rx_cls_fields = fields;
+		} else if (priv->rx_cls_fields != fields) {
+			netdev_err(net_dev, "No support for multiple FS keys, need to delete existing rules\n");
+			err = -EOPNOTSUPP;
+			goto free_mem;
+		}
+
+		dpaa2_eth_cls_trim_rule(key_buf, fields);
+		rule_cfg.key_size = dpaa2_eth_cls_key_size(fields);
+	}
+
 	key_iova = dma_map_single(dev, key_buf, rule_cfg.key_size * 2,
 				  DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, key_iova)) {
@@ -499,7 +547,8 @@ static int do_cls_rule(struct net_device *net_dev,
 	}
 
 	rule_cfg.key_iova = key_iova;
-	rule_cfg.mask_iova = key_iova + rule_cfg.key_size;
+	if (dpaa2_eth_fs_mask_enabled(priv))
+		rule_cfg.mask_iova = key_iova + rule_cfg.key_size;
 
 	if (add) {
 		if (fs->ring_cookie == RX_CLS_FLOW_DISC)
@@ -521,6 +570,17 @@ free_mem:
 	return err;
 }
 
+static int num_rules(struct dpaa2_eth_priv *priv)
+{
+	int i, rules = 0;
+
+	for (i = 0; i < dpaa2_eth_fs_count(priv); i++)
+		if (priv->cls_rules[i].in_use)
+			rules++;
+
+	return rules;
+}
+
 static int update_cls_rule(struct net_device *net_dev,
 			   struct ethtool_rx_flow_spec *new_fs,
 			   int location)
@@ -544,6 +604,9 @@ static int update_cls_rule(struct net_device *net_dev,
 			return err;
 
 		rule->in_use = 0;
+
+		if (!dpaa2_eth_fs_mask_enabled(priv) && !num_rules(priv))
+			priv->rx_cls_fields = 0;
 	}
 
 	/* If no new entry to add, return here */
@@ -580,14 +643,14 @@ static int dpaa2_eth_get_rxnfc(struct net_device *net_dev,
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		rxnfc->rule_cnt = 0;
-		for (i = 0; i < max_rules; i++)
-			if (priv->cls_rules[i].in_use)
-				rxnfc->rule_cnt++;
+		rxnfc->rule_cnt = num_rules(priv);
 		rxnfc->data = max_rules;
 		break;
 	case ETHTOOL_GRXCLSRULE:
 		if (rxnfc->fs.location >= max_rules)
 			return -EINVAL;
+		rxnfc->fs.location = array_index_nospec(rxnfc->fs.location,
+							max_rules);
 		if (!priv->cls_rules[rxnfc->fs.location].in_use)
 			return -EINVAL;
 		rxnfc->fs = priv->cls_rules[rxnfc->fs.location].fs;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
index 9b150db3b510..a9503aea527f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
@@ -5,114 +5,58 @@
  */
 
 #include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/ptp_clock_kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/msi.h>
 #include <linux/fsl/mc.h>
+#include <linux/fsl/ptp_qoriq.h>
 
 #include "dpaa2-ptp.h"
 
-struct ptp_dpaa2_priv {
-	struct fsl_mc_device *ptp_mc_dev;
-	struct ptp_clock *clock;
-	struct ptp_clock_info caps;
-	u32 freq_comp;
-};
-
-/* PTP clock operations */
-static int ptp_dpaa2_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+static int dpaa2_ptp_enable(struct ptp_clock_info *ptp,
+			    struct ptp_clock_request *rq, int on)
 {
-	struct ptp_dpaa2_priv *ptp_dpaa2 =
-		container_of(ptp, struct ptp_dpaa2_priv, caps);
-	struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev;
-	struct device *dev = &mc_dev->dev;
-	u64 adj;
-	u32 diff, tmr_add;
-	int neg_adj = 0;
-	int err = 0;
-
-	if (ppb < 0) {
-		neg_adj = 1;
-		ppb = -ppb;
-	}
-
-	tmr_add = ptp_dpaa2->freq_comp;
-	adj = tmr_add;
-	adj *= ppb;
-	diff = div_u64(adj, 1000000000ULL);
-
-	tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;
+	struct ptp_qoriq *ptp_qoriq = container_of(ptp, struct ptp_qoriq, caps);
+	struct fsl_mc_device *mc_dev;
+	struct device *dev;
+	u32 mask = 0;
+	u32 bit;
+	int err;
 
-	err = dprtc_set_freq_compensation(mc_dev->mc_io, 0,
-					  mc_dev->mc_handle, tmr_add);
-	if (err)
-		dev_err(dev, "dprtc_set_freq_compensation err %d\n", err);
-	return err;
-}
+	dev = ptp_qoriq->dev;
+	mc_dev = to_fsl_mc_device(dev);
 
-static int ptp_dpaa2_adjtime(struct ptp_clock_info *ptp, s64 delta)
-{
-	struct ptp_dpaa2_priv *ptp_dpaa2 =
-		container_of(ptp, struct ptp_dpaa2_priv, caps);
-	struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev;
-	struct device *dev = &mc_dev->dev;
-	s64 now;
-	int err = 0;
+	switch (rq->type) {
+	case PTP_CLK_REQ_PPS:
+		bit = DPRTC_EVENT_PPS;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
-	err = dprtc_get_time(mc_dev->mc_io, 0, mc_dev->mc_handle, &now);
-	if (err) {
-		dev_err(dev, "dprtc_get_time err %d\n", err);
+	err = dprtc_get_irq_mask(mc_dev->mc_io, 0, mc_dev->mc_handle,
+				 DPRTC_IRQ_INDEX, &mask);
+	if (err < 0) {
+		dev_err(dev, "dprtc_get_irq_mask(): %d\n", err);
 		return err;
 	}
 
-	now += delta;
+	if (on)
+		mask |= bit;
+	else
+		mask &= ~bit;
 
-	err = dprtc_set_time(mc_dev->mc_io, 0, mc_dev->mc_handle, now);
-	if (err)
-		dev_err(dev, "dprtc_set_time err %d\n", err);
-	return err;
-}
-
-static int ptp_dpaa2_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
-{
-	struct ptp_dpaa2_priv *ptp_dpaa2 =
-		container_of(ptp, struct ptp_dpaa2_priv, caps);
-	struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev;
-	struct device *dev = &mc_dev->dev;
-	u64 ns;
-	u32 remainder;
-	int err = 0;
-
-	err = dprtc_get_time(mc_dev->mc_io, 0, mc_dev->mc_handle, &ns);
-	if (err) {
-		dev_err(dev, "dprtc_get_time err %d\n", err);
+	err = dprtc_set_irq_mask(mc_dev->mc_io, 0, mc_dev->mc_handle,
+				 DPRTC_IRQ_INDEX, mask);
+	if (err < 0) {
+		dev_err(dev, "dprtc_set_irq_mask(): %d\n", err);
 		return err;
 	}
 
-	ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
-	ts->tv_nsec = remainder;
-	return err;
-}
-
-static int ptp_dpaa2_settime(struct ptp_clock_info *ptp,
-			     const struct timespec64 *ts)
-{
-	struct ptp_dpaa2_priv *ptp_dpaa2 =
-		container_of(ptp, struct ptp_dpaa2_priv, caps);
-	struct fsl_mc_device *mc_dev = ptp_dpaa2->ptp_mc_dev;
-	struct device *dev = &mc_dev->dev;
-	u64 ns;
-	int err = 0;
-
-	ns = ts->tv_sec * 1000000000ULL;
-	ns += ts->tv_nsec;
-
-	err = dprtc_set_time(mc_dev->mc_io, 0, mc_dev->mc_handle, ns);
-	if (err)
-		dev_err(dev, "dprtc_set_time err %d\n", err);
-	return err;
+	return 0;
 }
 
-static const struct ptp_clock_info ptp_dpaa2_caps = {
+static const struct ptp_clock_info dpaa2_ptp_caps = {
 	.owner		= THIS_MODULE,
 	.name		= "DPAA2 PTP Clock",
 	.max_adj	= 512000,
@@ -121,21 +65,58 @@ static const struct ptp_clock_info ptp_dpaa2_caps = {
 	.n_per_out	= 3,
 	.n_pins		= 0,
 	.pps		= 1,
-	.adjfreq	= ptp_dpaa2_adjfreq,
-	.adjtime	= ptp_dpaa2_adjtime,
-	.gettime64	= ptp_dpaa2_gettime,
-	.settime64	= ptp_dpaa2_settime,
+	.adjfine	= ptp_qoriq_adjfine,
+	.adjtime	= ptp_qoriq_adjtime,
+	.gettime64	= ptp_qoriq_gettime,
+	.settime64	= ptp_qoriq_settime,
+	.enable		= dpaa2_ptp_enable,
 };
 
+static irqreturn_t dpaa2_ptp_irq_handler_thread(int irq, void *priv)
+{
+	struct ptp_qoriq *ptp_qoriq = priv;
+	struct ptp_clock_event event;
+	struct fsl_mc_device *mc_dev;
+	struct device *dev;
+	u32 status = 0;
+	int err;
+
+	dev = ptp_qoriq->dev;
+	mc_dev = to_fsl_mc_device(dev);
+
+	err = dprtc_get_irq_status(mc_dev->mc_io, 0, mc_dev->mc_handle,
+				   DPRTC_IRQ_INDEX, &status);
+	if (unlikely(err)) {
+		dev_err(dev, "dprtc_get_irq_status err %d\n", err);
+		return IRQ_NONE;
+	}
+
+	if (status & DPRTC_EVENT_PPS) {
+		event.type = PTP_CLOCK_PPS;
+		ptp_clock_event(ptp_qoriq->clock, &event);
+	}
+
+	err = dprtc_clear_irq_status(mc_dev->mc_io, 0, mc_dev->mc_handle,
+				     DPRTC_IRQ_INDEX, status);
+	if (unlikely(err)) {
+		dev_err(dev, "dprtc_clear_irq_status err %d\n", err);
+		return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
+}
+
 static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 {
 	struct device *dev = &mc_dev->dev;
-	struct ptp_dpaa2_priv *ptp_dpaa2;
-	u32 tmr_add = 0;
+	struct fsl_mc_device_irq *irq;
+	struct ptp_qoriq *ptp_qoriq;
+	struct device_node *node;
+	void __iomem *base;
 	int err;
 
-	ptp_dpaa2 = devm_kzalloc(dev, sizeof(*ptp_dpaa2), GFP_KERNEL);
-	if (!ptp_dpaa2)
+	ptp_qoriq = devm_kzalloc(dev, sizeof(*ptp_qoriq), GFP_KERNEL);
+	if (!ptp_qoriq)
 		return -ENOMEM;
 
 	err = fsl_mc_portal_allocate(mc_dev, 0, &mc_dev->mc_io);
@@ -154,30 +135,60 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 		goto err_free_mcp;
 	}
 
-	ptp_dpaa2->ptp_mc_dev = mc_dev;
+	ptp_qoriq->dev = dev;
 
-	err = dprtc_get_freq_compensation(mc_dev->mc_io, 0,
-					  mc_dev->mc_handle, &tmr_add);
-	if (err) {
-		dev_err(dev, "dprtc_get_freq_compensation err %d\n", err);
+	node = of_find_compatible_node(NULL, NULL, "fsl,dpaa2-ptp");
+	if (!node) {
+		err = -ENODEV;
 		goto err_close;
 	}
 
-	ptp_dpaa2->freq_comp = tmr_add;
-	ptp_dpaa2->caps = ptp_dpaa2_caps;
+	dev->of_node = node;
 
-	ptp_dpaa2->clock = ptp_clock_register(&ptp_dpaa2->caps, dev);
-	if (IS_ERR(ptp_dpaa2->clock)) {
-		err = PTR_ERR(ptp_dpaa2->clock);
+	base = of_iomap(node, 0);
+	if (!base) {
+		err = -ENOMEM;
 		goto err_close;
 	}
 
-	dpaa2_phc_index = ptp_clock_index(ptp_dpaa2->clock);
+	err = fsl_mc_allocate_irqs(mc_dev);
+	if (err) {
+		dev_err(dev, "MC irqs allocation failed\n");
+		goto err_unmap;
+	}
+
+	irq = mc_dev->irqs[0];
+	ptp_qoriq->irq = irq->msi_desc->irq;
 
-	dev_set_drvdata(dev, ptp_dpaa2);
+	err = devm_request_threaded_irq(dev, ptp_qoriq->irq, NULL,
+					dpaa2_ptp_irq_handler_thread,
+					IRQF_NO_SUSPEND | IRQF_ONESHOT,
+					dev_name(dev), ptp_qoriq);
+	if (err < 0) {
+		dev_err(dev, "devm_request_threaded_irq(): %d\n", err);
+		goto err_free_mc_irq;
+	}
+
+	err = dprtc_set_irq_enable(mc_dev->mc_io, 0, mc_dev->mc_handle,
+				   DPRTC_IRQ_INDEX, 1);
+	if (err < 0) {
+		dev_err(dev, "dprtc_set_irq_enable(): %d\n", err);
+		goto err_free_mc_irq;
+	}
+
+	err = ptp_qoriq_init(ptp_qoriq, base, &dpaa2_ptp_caps);
+	if (err)
+		goto err_free_mc_irq;
+
+	dpaa2_phc_index = ptp_qoriq->phc_index;
+	dev_set_drvdata(dev, ptp_qoriq);
 
 	return 0;
 
+err_free_mc_irq:
+	fsl_mc_free_irqs(mc_dev);
+err_unmap:
+	iounmap(base);
 err_close:
 	dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
 err_free_mcp:
@@ -188,12 +199,15 @@ err_exit:
 
 static int dpaa2_ptp_remove(struct fsl_mc_device *mc_dev)
 {
-	struct ptp_dpaa2_priv *ptp_dpaa2;
 	struct device *dev = &mc_dev->dev;
+	struct ptp_qoriq *ptp_qoriq;
+
+	ptp_qoriq = dev_get_drvdata(dev);
 
-	ptp_dpaa2 = dev_get_drvdata(dev);
-	ptp_clock_unregister(ptp_dpaa2->clock);
+	dpaa2_phc_index = -1;
+	ptp_qoriq_free(ptp_qoriq);
 
+	fsl_mc_free_irqs(mc_dev);
 	dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle);
 	fsl_mc_portal_free(mc_dev->mc_io);
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
index 9af4ac71f347..720cd50f5895 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
@@ -17,22 +17,54 @@
 #define DPRTC_CMDID_CLOSE			DPRTC_CMD(0x800)
 #define DPRTC_CMDID_OPEN			DPRTC_CMD(0x810)
 
-#define DPRTC_CMDID_SET_FREQ_COMPENSATION	DPRTC_CMD(0x1d1)
-#define DPRTC_CMDID_GET_FREQ_COMPENSATION	DPRTC_CMD(0x1d2)
-#define DPRTC_CMDID_GET_TIME			DPRTC_CMD(0x1d3)
-#define DPRTC_CMDID_SET_TIME			DPRTC_CMD(0x1d4)
+#define DPRTC_CMDID_SET_IRQ_ENABLE		DPRTC_CMD(0x012)
+#define DPRTC_CMDID_GET_IRQ_ENABLE		DPRTC_CMD(0x013)
+#define DPRTC_CMDID_SET_IRQ_MASK		DPRTC_CMD(0x014)
+#define DPRTC_CMDID_GET_IRQ_MASK		DPRTC_CMD(0x015)
+#define DPRTC_CMDID_GET_IRQ_STATUS		DPRTC_CMD(0x016)
+#define DPRTC_CMDID_CLEAR_IRQ_STATUS		DPRTC_CMD(0x017)
 
 #pragma pack(push, 1)
 struct dprtc_cmd_open {
 	__le32 dprtc_id;
 };
 
-struct dprtc_get_freq_compensation {
-	__le32 freq_compensation;
+struct dprtc_cmd_get_irq {
+	__le32 pad;
+	u8 irq_index;
 };
 
-struct dprtc_time {
-	__le64 time;
+struct dprtc_cmd_set_irq_enable {
+	u8 en;
+	u8 pad[3];
+	u8 irq_index;
+};
+
+struct dprtc_rsp_get_irq_enable {
+	u8 en;
+};
+
+struct dprtc_cmd_set_irq_mask {
+	__le32 mask;
+	u8 irq_index;
+};
+
+struct dprtc_rsp_get_irq_mask {
+	__le32 mask;
+};
+
+struct dprtc_cmd_get_irq_status {
+	__le32 status;
+	u8 irq_index;
+};
+
+struct dprtc_rsp_get_irq_status {
+	__le32 status;
+};
+
+struct dprtc_cmd_clear_irq_status {
+	__le32 status;
+	u8 irq_index;
 };
 
 #pragma pack(pop)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc.c b/drivers/net/ethernet/freescale/dpaa2/dprtc.c
index c13e09bc7b9d..ed52a34fa6a1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dprtc.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dprtc.c
@@ -74,121 +74,220 @@ int dprtc_close(struct fsl_mc_io *mc_io,
 }
 
 /**
- * dprtc_set_freq_compensation() - Sets a new frequency compensation value.
+ * dprtc_set_irq_enable() - Set overall interrupt state.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPRTC object
+ * @irq_index:	The interrupt index to configure
+ * @en:		Interrupt state - enable = 1, disable = 0
  *
- * @mc_io:		Pointer to MC portal's I/O object
- * @cmd_flags:		Command flags; one or more of 'MC_CMD_FLAG_'
- * @token:		Token of DPRTC object
- * @freq_compensation:	The new frequency compensation value to set.
+ * Allows GPP software to control when interrupts are generated.
+ * Each interrupt can have up to 32 causes.  The enable/disable control's the
+ * overall interrupt state. if the interrupt is disabled no causes will cause
+ * an interrupt.
  *
  * Return:	'0' on Success; Error code otherwise.
  */
-int dprtc_set_freq_compensation(struct fsl_mc_io *mc_io,
-				u32 cmd_flags,
-				u16 token,
-				u32 freq_compensation)
+int dprtc_set_irq_enable(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 u8 irq_index,
+			 u8 en)
 {
-	struct dprtc_get_freq_compensation *cmd_params;
+	struct dprtc_cmd_set_irq_enable *cmd_params;
 	struct fsl_mc_command cmd = { 0 };
 
-	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_SET_FREQ_COMPENSATION,
+	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_SET_IRQ_ENABLE,
 					  cmd_flags,
 					  token);
-	cmd_params = (struct dprtc_get_freq_compensation *)cmd.params;
-	cmd_params->freq_compensation = cpu_to_le32(freq_compensation);
+	cmd_params = (struct dprtc_cmd_set_irq_enable *)cmd.params;
+	cmd_params->irq_index = irq_index;
+	cmd_params->en = en;
 
 	return mc_send_command(mc_io, &cmd);
 }
 
 /**
- * dprtc_get_freq_compensation() - Retrieves the frequency compensation value
+ * dprtc_get_irq_enable() - Get overall interrupt state
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPRTC object
+ * @irq_index:	The interrupt index to configure
+ * @en:		Returned interrupt state - enable = 1, disable = 0
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dprtc_get_irq_enable(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 u8 irq_index,
+			 u8 *en)
+{
+	struct dprtc_rsp_get_irq_enable *rsp_params;
+	struct dprtc_cmd_get_irq *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+	int err;
+
+	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_GET_IRQ_ENABLE,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dprtc_cmd_get_irq *)cmd.params;
+	cmd_params->irq_index = irq_index;
+
+	err = mc_send_command(mc_io, &cmd);
+	if (err)
+		return err;
+
+	rsp_params = (struct dprtc_rsp_get_irq_enable *)cmd.params;
+	*en = rsp_params->en;
+
+	return 0;
+}
+
+/**
+ * dprtc_set_irq_mask() - Set interrupt mask.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPRTC object
+ * @irq_index:	The interrupt index to configure
+ * @mask:	Event mask to trigger interrupt;
+ *		each bit:
+ *			0 = ignore event
+ *			1 = consider event for asserting IRQ
+ *
+ * Every interrupt can have up to 32 causes and the interrupt model supports
+ * masking/unmasking each cause independently
+ *
+ * Return:	'0' on Success; Error code otherwise.
+ */
+int dprtc_set_irq_mask(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       u8 irq_index,
+		       u32 mask)
+{
+	struct dprtc_cmd_set_irq_mask *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_SET_IRQ_MASK,
+					  cmd_flags,
+					  token);
+	cmd_params = (struct dprtc_cmd_set_irq_mask *)cmd.params;
+	cmd_params->mask = cpu_to_le32(mask);
+	cmd_params->irq_index = irq_index;
+
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dprtc_get_irq_mask() - Get interrupt mask.
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPRTC object
+ * @irq_index:	The interrupt index to configure
+ * @mask:	Returned event mask to trigger interrupt
  *
- * @mc_io:		Pointer to MC portal's I/O object
- * @cmd_flags:		Command flags; one or more of 'MC_CMD_FLAG_'
- * @token:		Token of DPRTC object
- * @freq_compensation:	Frequency compensation value
+ * Every interrupt can have up to 32 causes and the interrupt model supports
+ * masking/unmasking each cause independently
  *
  * Return:	'0' on Success; Error code otherwise.
  */
-int dprtc_get_freq_compensation(struct fsl_mc_io *mc_io,
-				u32 cmd_flags,
-				u16 token,
-				u32 *freq_compensation)
+int dprtc_get_irq_mask(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       u8 irq_index,
+		       u32 *mask)
 {
-	struct dprtc_get_freq_compensation *rsp_params;
+	struct dprtc_rsp_get_irq_mask *rsp_params;
+	struct dprtc_cmd_get_irq *cmd_params;
 	struct fsl_mc_command cmd = { 0 };
 	int err;
 
-	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_GET_FREQ_COMPENSATION,
+	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_GET_IRQ_MASK,
 					  cmd_flags,
 					  token);
+	cmd_params = (struct dprtc_cmd_get_irq *)cmd.params;
+	cmd_params->irq_index = irq_index;
 
 	err = mc_send_command(mc_io, &cmd);
 	if (err)
 		return err;
 
-	rsp_params = (struct dprtc_get_freq_compensation *)cmd.params;
-	*freq_compensation = le32_to_cpu(rsp_params->freq_compensation);
+	rsp_params = (struct dprtc_rsp_get_irq_mask *)cmd.params;
+	*mask = le32_to_cpu(rsp_params->mask);
 
 	return 0;
 }
 
 /**
- * dprtc_get_time() - Returns the current RTC time.
+ * dprtc_get_irq_status() - Get the current status of any pending interrupts.
  *
  * @mc_io:	Pointer to MC portal's I/O object
  * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
  * @token:	Token of DPRTC object
- * @time:	Current RTC time.
+ * @irq_index:	The interrupt index to configure
+ * @status:	Returned interrupts status - one bit per cause:
+ *			0 = no interrupt pending
+ *			1 = interrupt pending
  *
  * Return:	'0' on Success; Error code otherwise.
  */
-int dprtc_get_time(struct fsl_mc_io *mc_io,
-		   u32 cmd_flags,
-		   u16 token,
-		   uint64_t *time)
+int dprtc_get_irq_status(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 u8 irq_index,
+			 u32 *status)
 {
-	struct dprtc_time *rsp_params;
+	struct dprtc_cmd_get_irq_status *cmd_params;
+	struct dprtc_rsp_get_irq_status *rsp_params;
 	struct fsl_mc_command cmd = { 0 };
 	int err;
 
-	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_GET_TIME,
+	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_GET_IRQ_STATUS,
 					  cmd_flags,
 					  token);
+	cmd_params = (struct dprtc_cmd_get_irq_status *)cmd.params;
+	cmd_params->status = cpu_to_le32(*status);
+	cmd_params->irq_index = irq_index;
 
 	err = mc_send_command(mc_io, &cmd);
 	if (err)
 		return err;
 
-	rsp_params = (struct dprtc_time *)cmd.params;
-	*time = le64_to_cpu(rsp_params->time);
+	rsp_params = (struct dprtc_rsp_get_irq_status *)cmd.params;
+	*status = le32_to_cpu(rsp_params->status);
 
 	return 0;
 }
 
 /**
- * dprtc_set_time() - Updates current RTC time.
+ * dprtc_clear_irq_status() - Clear a pending interrupt's status
  *
  * @mc_io:	Pointer to MC portal's I/O object
  * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
  * @token:	Token of DPRTC object
- * @time:	New RTC time.
+ * @irq_index:	The interrupt index to configure
+ * @status:	Bits to clear (W1C) - one bit per cause:
+ *			0 = don't change
+ *			1 = clear status bit
  *
  * Return:	'0' on Success; Error code otherwise.
  */
-int dprtc_set_time(struct fsl_mc_io *mc_io,
-		   u32 cmd_flags,
-		   u16 token,
-		   uint64_t time)
+int dprtc_clear_irq_status(struct fsl_mc_io *mc_io,
+			   u32 cmd_flags,
+			   u16 token,
+			   u8 irq_index,
+			   u32 status)
 {
-	struct dprtc_time *cmd_params;
+	struct dprtc_cmd_clear_irq_status *cmd_params;
 	struct fsl_mc_command cmd = { 0 };
 
-	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_SET_TIME,
+	cmd.header = mc_encode_cmd_header(DPRTC_CMDID_CLEAR_IRQ_STATUS,
 					  cmd_flags,
 					  token);
-	cmd_params = (struct dprtc_time *)cmd.params;
-	cmd_params->time = cpu_to_le64(time);
+	cmd_params = (struct dprtc_cmd_clear_irq_status *)cmd.params;
+	cmd_params->irq_index = irq_index;
+	cmd_params->status = cpu_to_le32(status);
 
 	return mc_send_command(mc_io, &cmd);
 }
diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc.h b/drivers/net/ethernet/freescale/dpaa2/dprtc.h
index fe19618d6cdf..be7914c1634d 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dprtc.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dprtc.h
@@ -13,6 +13,14 @@
 
 struct fsl_mc_io;
 
+/**
+ * Number of irq's
+ */
+#define DPRTC_MAX_IRQ_NUM	1
+#define DPRTC_IRQ_INDEX		0
+
+#define DPRTC_EVENT_PPS		0x08000000
+
 int dprtc_open(struct fsl_mc_io *mc_io,
 	       u32 cmd_flags,
 	       int dprtc_id,
@@ -22,24 +30,40 @@ int dprtc_close(struct fsl_mc_io *mc_io,
 		u32 cmd_flags,
 		u16 token);
 
-int dprtc_set_freq_compensation(struct fsl_mc_io *mc_io,
-				u32 cmd_flags,
-				u16 token,
-				u32 freq_compensation);
-
-int dprtc_get_freq_compensation(struct fsl_mc_io *mc_io,
-				u32 cmd_flags,
-				u16 token,
-				u32 *freq_compensation);
-
-int dprtc_get_time(struct fsl_mc_io *mc_io,
-		   u32 cmd_flags,
-		   u16 token,
-		   uint64_t *time);
-
-int dprtc_set_time(struct fsl_mc_io *mc_io,
-		   u32 cmd_flags,
-		   u16 token,
-		   uint64_t time);
+int dprtc_set_irq_enable(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 u8 irq_index,
+			 u8 en);
+
+int dprtc_get_irq_enable(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 u8 irq_index,
+			 u8 *en);
+
+int dprtc_set_irq_mask(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       u8 irq_index,
+		       u32 mask);
+
+int dprtc_get_irq_mask(struct fsl_mc_io *mc_io,
+		       u32 cmd_flags,
+		       u16 token,
+		       u8 irq_index,
+		       u32 *mask);
+
+int dprtc_get_irq_status(struct fsl_mc_io *mc_io,
+			 u32 cmd_flags,
+			 u16 token,
+			 u8 irq_index,
+			 u32 *status);
+
+int dprtc_clear_irq_status(struct fsl_mc_io *mc_io,
+			   u32 cmd_flags,
+			   u16 token,
+			   u8 irq_index,
+			   u32 status);
 
 #endif /* __FSL_DPRTC_H */
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
new file mode 100644
index 000000000000..ed0d010c7cf2
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -0,0 +1,41 @@
+# SPDX-License-Identifier: GPL-2.0
+config FSL_ENETC
+	tristate "ENETC PF driver"
+	depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST)
+	help
+	  This driver supports NXP ENETC gigabit ethernet controller PCIe
+	  physical function (PF) devices, managing ENETC Ports at a privileged
+	  level.
+
+	  If compiled as module (M), the module name is fsl-enetc.
+
+config FSL_ENETC_VF
+	tristate "ENETC VF driver"
+	depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST)
+	help
+	  This driver supports NXP ENETC gigabit ethernet controller PCIe
+	  virtual function (VF) devices enabled by the ENETC PF driver.
+
+	  If compiled as module (M), the module name is fsl-enetc-vf.
+
+config FSL_ENETC_PTP_CLOCK
+	tristate "ENETC PTP clock driver"
+	depends on PTP_1588_CLOCK_QORIQ && (FSL_ENETC || FSL_ENETC_VF)
+	default y
+	help
+	  This driver adds support for using the ENETC 1588 timer
+	  as a PTP clock. This clock is only useful if your PTP
+	  programs are getting hardware time stamps on the PTP Ethernet
+	  packets using the SO_TIMESTAMPING API.
+
+	  If compiled as module (M), the module name is fsl-enetc-ptp.
+
+config FSL_ENETC_HW_TIMESTAMPING
+	bool "ENETC hardware timestamping support"
+	depends on FSL_ENETC || FSL_ENETC_VF
+	help
+	  Enable hardware timestamping support on the Ethernet packets
+	  using the SO_TIMESTAMPING API. Because the RX BD ring dynamic
+	  allocation has not been supported and it is too expensive to use
+	  extended RX BDs if timestamping is not used, this option enables
+	  extended RX BDs in order to support hardware timestamping.
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
new file mode 100644
index 000000000000..7139e414dccf
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o
+fsl-enetc-$(CONFIG_FSL_ENETC) += enetc.o enetc_cbdr.o enetc_ethtool.o \
+				 enetc_mdio.o
+fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o
+fsl-enetc-objs := enetc_pf.o $(fsl-enetc-y)
+
+obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o
+
+ifeq ($(CONFIG_FSL_ENETC)$(CONFIG_FSL_ENETC_VF), yy)
+fsl-enetc-vf-objs := enetc_vf.o
+else
+fsl-enetc-vf-$(CONFIG_FSL_ENETC_VF) += enetc.o enetc_cbdr.o \
+				       enetc_ethtool.o
+fsl-enetc-vf-objs := enetc_vf.o $(fsl-enetc-vf-y)
+endif
+
+obj-$(CONFIG_FSL_ENETC_PTP_CLOCK) += fsl-enetc-ptp.o
+fsl-enetc-ptp-$(CONFIG_FSL_ENETC_PTP_CLOCK) += enetc_ptp.o
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
new file mode 100644
index 000000000000..223709443ea4
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -0,0 +1,1812 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include "enetc.h"
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/of_mdio.h>
+#include <linux/vmalloc.h>
+
+/* ENETC overhead: optional extension BD + 1 BD gap */
+#define ENETC_TXBDS_NEEDED(val)	((val) + 2)
+/* max # of chained Tx BDs is 15, including head and extension BD */
+#define ENETC_MAX_SKB_FRAGS	13
+#define ENETC_TXBDS_MAX_NEEDED	ENETC_TXBDS_NEEDED(ENETC_MAX_SKB_FRAGS + 1)
+
+static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+			      int active_offloads);
+
+netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_bdr *tx_ring;
+	int count;
+
+	tx_ring = priv->tx_ring[skb->queue_mapping];
+
+	if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS))
+		if (unlikely(skb_linearize(skb)))
+			goto drop_packet_err;
+
+	count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */
+	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) {
+		netif_stop_subqueue(ndev, tx_ring->index);
+		return NETDEV_TX_BUSY;
+	}
+
+	count = enetc_map_tx_buffs(tx_ring, skb, priv->active_offloads);
+	if (unlikely(!count))
+		goto drop_packet_err;
+
+	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED)
+		netif_stop_subqueue(ndev, tx_ring->index);
+
+	return NETDEV_TX_OK;
+
+drop_packet_err:
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+static bool enetc_tx_csum(struct sk_buff *skb, union enetc_tx_bd *txbd)
+{
+	int l3_start, l3_hsize;
+	u16 l3_flags, l4_flags;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return false;
+
+	switch (skb->csum_offset) {
+	case offsetof(struct tcphdr, check):
+		l4_flags = ENETC_TXBD_L4_TCP;
+		break;
+	case offsetof(struct udphdr, check):
+		l4_flags = ENETC_TXBD_L4_UDP;
+		break;
+	default:
+		skb_checksum_help(skb);
+		return false;
+	}
+
+	l3_start = skb_network_offset(skb);
+	l3_hsize = skb_network_header_len(skb);
+
+	l3_flags = 0;
+	if (skb->protocol == htons(ETH_P_IPV6))
+		l3_flags = ENETC_TXBD_L3_IPV6;
+
+	/* write BD fields */
+	txbd->l3_csoff = enetc_txbd_l3_csoff(l3_start, l3_hsize, l3_flags);
+	txbd->l4_csoff = l4_flags;
+
+	return true;
+}
+
+static void enetc_unmap_tx_buff(struct enetc_bdr *tx_ring,
+				struct enetc_tx_swbd *tx_swbd)
+{
+	if (tx_swbd->is_dma_page)
+		dma_unmap_page(tx_ring->dev, tx_swbd->dma,
+			       tx_swbd->len, DMA_TO_DEVICE);
+	else
+		dma_unmap_single(tx_ring->dev, tx_swbd->dma,
+				 tx_swbd->len, DMA_TO_DEVICE);
+	tx_swbd->dma = 0;
+}
+
+static void enetc_free_tx_skb(struct enetc_bdr *tx_ring,
+			      struct enetc_tx_swbd *tx_swbd)
+{
+	if (tx_swbd->dma)
+		enetc_unmap_tx_buff(tx_ring, tx_swbd);
+
+	if (tx_swbd->skb) {
+		dev_kfree_skb_any(tx_swbd->skb);
+		tx_swbd->skb = NULL;
+	}
+}
+
+static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+			      int active_offloads)
+{
+	struct enetc_tx_swbd *tx_swbd;
+	struct skb_frag_struct *frag;
+	int len = skb_headlen(skb);
+	union enetc_tx_bd temp_bd;
+	union enetc_tx_bd *txbd;
+	bool do_vlan, do_tstamp;
+	int i, count = 0;
+	unsigned int f;
+	dma_addr_t dma;
+	u8 flags = 0;
+
+	i = tx_ring->next_to_use;
+	txbd = ENETC_TXBD(*tx_ring, i);
+	prefetchw(txbd);
+
+	dma = dma_map_single(tx_ring->dev, skb->data, len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(tx_ring->dev, dma)))
+		goto dma_err;
+
+	temp_bd.addr = cpu_to_le64(dma);
+	temp_bd.buf_len = cpu_to_le16(len);
+	temp_bd.lstatus = 0;
+
+	tx_swbd = &tx_ring->tx_swbd[i];
+	tx_swbd->dma = dma;
+	tx_swbd->len = len;
+	tx_swbd->is_dma_page = 0;
+	count++;
+
+	do_vlan = skb_vlan_tag_present(skb);
+	do_tstamp = (active_offloads & ENETC_F_TX_TSTAMP) &&
+		    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP);
+	tx_swbd->do_tstamp = do_tstamp;
+	tx_swbd->check_wb = tx_swbd->do_tstamp;
+
+	if (do_vlan || do_tstamp)
+		flags |= ENETC_TXBD_FLAGS_EX;
+
+	if (enetc_tx_csum(skb, &temp_bd))
+		flags |= ENETC_TXBD_FLAGS_CSUM | ENETC_TXBD_FLAGS_L4CS;
+
+	/* first BD needs frm_len and offload flags set */
+	temp_bd.frm_len = cpu_to_le16(skb->len);
+	temp_bd.flags = flags;
+
+	if (flags & ENETC_TXBD_FLAGS_EX) {
+		u8 e_flags = 0;
+		*txbd = temp_bd;
+		enetc_clear_tx_bd(&temp_bd);
+
+		/* add extension BD for VLAN and/or timestamping */
+		flags = 0;
+		tx_swbd++;
+		txbd++;
+		i++;
+		if (unlikely(i == tx_ring->bd_count)) {
+			i = 0;
+			tx_swbd = tx_ring->tx_swbd;
+			txbd = ENETC_TXBD(*tx_ring, 0);
+		}
+		prefetchw(txbd);
+
+		if (do_vlan) {
+			temp_bd.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb));
+			temp_bd.ext.tpid = 0; /* < C-TAG */
+			e_flags |= ENETC_TXBD_E_FLAGS_VLAN_INS;
+		}
+
+		if (do_tstamp) {
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+			e_flags |= ENETC_TXBD_E_FLAGS_TWO_STEP_PTP;
+		}
+
+		temp_bd.ext.e_flags = e_flags;
+		count++;
+	}
+
+	frag = &skb_shinfo(skb)->frags[0];
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++, frag++) {
+		len = skb_frag_size(frag);
+		dma = skb_frag_dma_map(tx_ring->dev, frag, 0, len,
+				       DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_ring->dev, dma))
+			goto dma_err;
+
+		*txbd = temp_bd;
+		enetc_clear_tx_bd(&temp_bd);
+
+		flags = 0;
+		tx_swbd++;
+		txbd++;
+		i++;
+		if (unlikely(i == tx_ring->bd_count)) {
+			i = 0;
+			tx_swbd = tx_ring->tx_swbd;
+			txbd = ENETC_TXBD(*tx_ring, 0);
+		}
+		prefetchw(txbd);
+
+		temp_bd.addr = cpu_to_le64(dma);
+		temp_bd.buf_len = cpu_to_le16(len);
+
+		tx_swbd->dma = dma;
+		tx_swbd->len = len;
+		tx_swbd->is_dma_page = 1;
+		count++;
+	}
+
+	/* last BD needs 'F' bit set */
+	flags |= ENETC_TXBD_FLAGS_F;
+	temp_bd.flags = flags;
+	*txbd = temp_bd;
+
+	tx_ring->tx_swbd[i].skb = skb;
+
+	enetc_bdr_idx_inc(tx_ring, &i);
+	tx_ring->next_to_use = i;
+
+	/* let H/W know BD ring has been updated */
+	enetc_wr_reg(tx_ring->tpir, i); /* includes wmb() */
+
+	return count;
+
+dma_err:
+	dev_err(tx_ring->dev, "DMA map error");
+
+	do {
+		tx_swbd = &tx_ring->tx_swbd[i];
+		enetc_free_tx_skb(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	} while (count--);
+
+	return 0;
+}
+
+static irqreturn_t enetc_msix(int irq, void *data)
+{
+	struct enetc_int_vector	*v = data;
+	int i;
+
+	/* disable interrupts */
+	enetc_wr_reg(v->rbier, 0);
+
+	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0);
+
+	napi_schedule_irqoff(&v->napi);
+
+	return IRQ_HANDLED;
+}
+
+static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget);
+static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
+			       struct napi_struct *napi, int work_limit);
+
+static int enetc_poll(struct napi_struct *napi, int budget)
+{
+	struct enetc_int_vector
+		*v = container_of(napi, struct enetc_int_vector, napi);
+	bool complete = true;
+	int work_done;
+	int i;
+
+	for (i = 0; i < v->count_tx_rings; i++)
+		if (!enetc_clean_tx_ring(&v->tx_ring[i], budget))
+			complete = false;
+
+	work_done = enetc_clean_rx_ring(&v->rx_ring, napi, budget);
+	if (work_done == budget)
+		complete = false;
+
+	if (!complete)
+		return budget;
+
+	napi_complete_done(napi, work_done);
+
+	/* enable interrupts */
+	enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE);
+
+	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i),
+			     ENETC_TBIER_TXTIE);
+
+	return work_done;
+}
+
+static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci)
+{
+	int pi = enetc_rd_reg(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK;
+
+	return pi >= ci ? pi - ci : tx_ring->bd_count - ci + pi;
+}
+
+static void enetc_get_tx_tstamp(struct enetc_hw *hw, union enetc_tx_bd *txbd,
+				u64 *tstamp)
+{
+	u32 lo, hi, tstamp_lo;
+
+	lo = enetc_rd(hw, ENETC_SICTR0);
+	hi = enetc_rd(hw, ENETC_SICTR1);
+	tstamp_lo = le32_to_cpu(txbd->wb.tstamp);
+	if (lo <= tstamp_lo)
+		hi -= 1;
+	*tstamp = (u64)hi << 32 | tstamp_lo;
+}
+
+static void enetc_tstamp_tx(struct sk_buff *skb, u64 tstamp)
+{
+	struct skb_shared_hwtstamps shhwtstamps;
+
+	if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) {
+		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+		shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+		skb_tstamp_tx(skb, &shhwtstamps);
+	}
+}
+
+static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
+{
+	struct net_device *ndev = tx_ring->ndev;
+	int tx_frm_cnt = 0, tx_byte_cnt = 0;
+	struct enetc_tx_swbd *tx_swbd;
+	int i, bds_to_clean;
+	bool do_tstamp;
+	u64 tstamp = 0;
+
+	i = tx_ring->next_to_clean;
+	tx_swbd = &tx_ring->tx_swbd[i];
+	bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+
+	do_tstamp = false;
+
+	while (bds_to_clean && tx_frm_cnt < ENETC_DEFAULT_TX_WORK) {
+		bool is_eof = !!tx_swbd->skb;
+
+		if (unlikely(tx_swbd->check_wb)) {
+			struct enetc_ndev_priv *priv = netdev_priv(ndev);
+			union enetc_tx_bd *txbd;
+
+			txbd = ENETC_TXBD(*tx_ring, i);
+
+			if (txbd->flags & ENETC_TXBD_FLAGS_W &&
+			    tx_swbd->do_tstamp) {
+				enetc_get_tx_tstamp(&priv->si->hw, txbd,
+						    &tstamp);
+				do_tstamp = true;
+			}
+		}
+
+		if (likely(tx_swbd->dma))
+			enetc_unmap_tx_buff(tx_ring, tx_swbd);
+
+		if (is_eof) {
+			if (unlikely(do_tstamp)) {
+				enetc_tstamp_tx(tx_swbd->skb, tstamp);
+				do_tstamp = false;
+			}
+			napi_consume_skb(tx_swbd->skb, napi_budget);
+			tx_swbd->skb = NULL;
+		}
+
+		tx_byte_cnt += tx_swbd->len;
+
+		bds_to_clean--;
+		tx_swbd++;
+		i++;
+		if (unlikely(i == tx_ring->bd_count)) {
+			i = 0;
+			tx_swbd = tx_ring->tx_swbd;
+		}
+
+		/* BD iteration loop end */
+		if (is_eof) {
+			tx_frm_cnt++;
+			/* re-arm interrupt source */
+			enetc_wr_reg(tx_ring->idr, BIT(tx_ring->index) |
+				     BIT(16 + tx_ring->index));
+		}
+
+		if (unlikely(!bds_to_clean))
+			bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+	}
+
+	tx_ring->next_to_clean = i;
+	tx_ring->stats.packets += tx_frm_cnt;
+	tx_ring->stats.bytes += tx_byte_cnt;
+
+	if (unlikely(tx_frm_cnt && netif_carrier_ok(ndev) &&
+		     __netif_subqueue_stopped(ndev, tx_ring->index) &&
+		     (enetc_bd_unused(tx_ring) >= ENETC_TXBDS_MAX_NEEDED))) {
+		netif_wake_subqueue(ndev, tx_ring->index);
+	}
+
+	return tx_frm_cnt != ENETC_DEFAULT_TX_WORK;
+}
+
+static bool enetc_new_page(struct enetc_bdr *rx_ring,
+			   struct enetc_rx_swbd *rx_swbd)
+{
+	struct page *page;
+	dma_addr_t addr;
+
+	page = dev_alloc_page();
+	if (unlikely(!page))
+		return false;
+
+	addr = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(rx_ring->dev, addr))) {
+		__free_page(page);
+
+		return false;
+	}
+
+	rx_swbd->dma = addr;
+	rx_swbd->page = page;
+	rx_swbd->page_offset = ENETC_RXB_PAD;
+
+	return true;
+}
+
+static int enetc_refill_rx_ring(struct enetc_bdr *rx_ring, const int buff_cnt)
+{
+	struct enetc_rx_swbd *rx_swbd;
+	union enetc_rx_bd *rxbd;
+	int i, j;
+
+	i = rx_ring->next_to_use;
+	rx_swbd = &rx_ring->rx_swbd[i];
+	rxbd = ENETC_RXBD(*rx_ring, i);
+
+	for (j = 0; j < buff_cnt; j++) {
+		/* try reuse page */
+		if (unlikely(!rx_swbd->page)) {
+			if (unlikely(!enetc_new_page(rx_ring, rx_swbd))) {
+				rx_ring->stats.rx_alloc_errs++;
+				break;
+			}
+		}
+
+		/* update RxBD */
+		rxbd->w.addr = cpu_to_le64(rx_swbd->dma +
+					   rx_swbd->page_offset);
+		/* clear 'R" as well */
+		rxbd->r.lstatus = 0;
+
+		rx_swbd++;
+		rxbd++;
+		i++;
+		if (unlikely(i == rx_ring->bd_count)) {
+			i = 0;
+			rx_swbd = rx_ring->rx_swbd;
+			rxbd = ENETC_RXBD(*rx_ring, 0);
+		}
+	}
+
+	if (likely(j)) {
+		rx_ring->next_to_alloc = i; /* keep track from page reuse */
+		rx_ring->next_to_use = i;
+		/* update ENETC's consumer index */
+		enetc_wr_reg(rx_ring->rcir, i);
+	}
+
+	return j;
+}
+
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+static void enetc_get_rx_tstamp(struct net_device *ndev,
+				union enetc_rx_bd *rxbd,
+				struct sk_buff *skb)
+{
+	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 lo, hi, tstamp_lo;
+	u64 tstamp;
+
+	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TSTMP) {
+		lo = enetc_rd(hw, ENETC_SICTR0);
+		hi = enetc_rd(hw, ENETC_SICTR1);
+		tstamp_lo = le32_to_cpu(rxbd->r.tstamp);
+		if (lo <= tstamp_lo)
+			hi -= 1;
+
+		tstamp = (u64)hi << 32 | tstamp_lo;
+		memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+		shhwtstamps->hwtstamp = ns_to_ktime(tstamp);
+	}
+}
+#endif
+
+static void enetc_get_offloads(struct enetc_bdr *rx_ring,
+			       union enetc_rx_bd *rxbd, struct sk_buff *skb)
+{
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+	struct enetc_ndev_priv *priv = netdev_priv(rx_ring->ndev);
+#endif
+	/* TODO: hashing */
+	if (rx_ring->ndev->features & NETIF_F_RXCSUM) {
+		u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
+
+		skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
+		skb->ip_summed = CHECKSUM_COMPLETE;
+	}
+
+	/* copy VLAN to skb, if one is extracted, for now we assume it's a
+	 * standard TPID, but HW also supports custom values
+	 */
+	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN)
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       le16_to_cpu(rxbd->r.vlan_opt));
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+	if (priv->active_offloads & ENETC_F_RX_TSTAMP)
+		enetc_get_rx_tstamp(rx_ring->ndev, rxbd, skb);
+#endif
+}
+
+static void enetc_process_skb(struct enetc_bdr *rx_ring,
+			      struct sk_buff *skb)
+{
+	skb_record_rx_queue(skb, rx_ring->index);
+	skb->protocol = eth_type_trans(skb, rx_ring->ndev);
+}
+
+static bool enetc_page_reusable(struct page *page)
+{
+	return (!page_is_pfmemalloc(page) && page_ref_count(page) == 1);
+}
+
+static void enetc_reuse_page(struct enetc_bdr *rx_ring,
+			     struct enetc_rx_swbd *old)
+{
+	struct enetc_rx_swbd *new;
+
+	new = &rx_ring->rx_swbd[rx_ring->next_to_alloc];
+
+	/* next buf that may reuse a page */
+	enetc_bdr_idx_inc(rx_ring, &rx_ring->next_to_alloc);
+
+	/* copy page reference */
+	*new = *old;
+}
+
+static struct enetc_rx_swbd *enetc_get_rx_buff(struct enetc_bdr *rx_ring,
+					       int i, u16 size)
+{
+	struct enetc_rx_swbd *rx_swbd = &rx_ring->rx_swbd[i];
+
+	dma_sync_single_range_for_cpu(rx_ring->dev, rx_swbd->dma,
+				      rx_swbd->page_offset,
+				      size, DMA_FROM_DEVICE);
+	return rx_swbd;
+}
+
+static void enetc_put_rx_buff(struct enetc_bdr *rx_ring,
+			      struct enetc_rx_swbd *rx_swbd)
+{
+	if (likely(enetc_page_reusable(rx_swbd->page))) {
+		rx_swbd->page_offset ^= ENETC_RXB_TRUESIZE;
+		page_ref_inc(rx_swbd->page);
+
+		enetc_reuse_page(rx_ring, rx_swbd);
+
+		/* sync for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, rx_swbd->dma,
+						 rx_swbd->page_offset,
+						 ENETC_RXB_DMA_SIZE,
+						 DMA_FROM_DEVICE);
+	} else {
+		dma_unmap_page(rx_ring->dev, rx_swbd->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+	}
+
+	rx_swbd->page = NULL;
+}
+
+static struct sk_buff *enetc_map_rx_buff_to_skb(struct enetc_bdr *rx_ring,
+						int i, u16 size)
+{
+	struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size);
+	struct sk_buff *skb;
+	void *ba;
+
+	ba = page_address(rx_swbd->page) + rx_swbd->page_offset;
+	skb = build_skb(ba - ENETC_RXB_PAD, ENETC_RXB_TRUESIZE);
+	if (unlikely(!skb)) {
+		rx_ring->stats.rx_alloc_errs++;
+		return NULL;
+	}
+
+	skb_reserve(skb, ENETC_RXB_PAD);
+	__skb_put(skb, size);
+
+	enetc_put_rx_buff(rx_ring, rx_swbd);
+
+	return skb;
+}
+
+static void enetc_add_rx_buff_to_skb(struct enetc_bdr *rx_ring, int i,
+				     u16 size, struct sk_buff *skb)
+{
+	struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size);
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_swbd->page,
+			rx_swbd->page_offset, size, ENETC_RXB_TRUESIZE);
+
+	enetc_put_rx_buff(rx_ring, rx_swbd);
+}
+
+#define ENETC_RXBD_BUNDLE 16 /* # of BDs to update at once */
+
+static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
+			       struct napi_struct *napi, int work_limit)
+{
+	int rx_frm_cnt = 0, rx_byte_cnt = 0;
+	int cleaned_cnt, i;
+
+	cleaned_cnt = enetc_bd_unused(rx_ring);
+	/* next descriptor to process */
+	i = rx_ring->next_to_clean;
+
+	while (likely(rx_frm_cnt < work_limit)) {
+		union enetc_rx_bd *rxbd;
+		struct sk_buff *skb;
+		u32 bd_status;
+		u16 size;
+
+		if (cleaned_cnt >= ENETC_RXBD_BUNDLE) {
+			int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt);
+
+			cleaned_cnt -= count;
+		}
+
+		rxbd = ENETC_RXBD(*rx_ring, i);
+		bd_status = le32_to_cpu(rxbd->r.lstatus);
+		if (!bd_status)
+			break;
+
+		enetc_wr_reg(rx_ring->idr, BIT(rx_ring->index));
+		dma_rmb(); /* for reading other rxbd fields */
+		size = le16_to_cpu(rxbd->r.buf_len);
+		skb = enetc_map_rx_buff_to_skb(rx_ring, i, size);
+		if (!skb)
+			break;
+
+		enetc_get_offloads(rx_ring, rxbd, skb);
+
+		cleaned_cnt++;
+		rxbd++;
+		i++;
+		if (unlikely(i == rx_ring->bd_count)) {
+			i = 0;
+			rxbd = ENETC_RXBD(*rx_ring, 0);
+		}
+
+		if (unlikely(bd_status &
+			     ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) {
+			dev_kfree_skb(skb);
+			while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
+				dma_rmb();
+				bd_status = le32_to_cpu(rxbd->r.lstatus);
+				rxbd++;
+				i++;
+				if (unlikely(i == rx_ring->bd_count)) {
+					i = 0;
+					rxbd = ENETC_RXBD(*rx_ring, 0);
+				}
+			}
+
+			rx_ring->ndev->stats.rx_dropped++;
+			rx_ring->ndev->stats.rx_errors++;
+
+			break;
+		}
+
+		/* not last BD in frame? */
+		while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
+			bd_status = le32_to_cpu(rxbd->r.lstatus);
+			size = ENETC_RXB_DMA_SIZE;
+
+			if (bd_status & ENETC_RXBD_LSTATUS_F) {
+				dma_rmb();
+				size = le16_to_cpu(rxbd->r.buf_len);
+			}
+
+			enetc_add_rx_buff_to_skb(rx_ring, i, size, skb);
+
+			cleaned_cnt++;
+			rxbd++;
+			i++;
+			if (unlikely(i == rx_ring->bd_count)) {
+				i = 0;
+				rxbd = ENETC_RXBD(*rx_ring, 0);
+			}
+		}
+
+		rx_byte_cnt += skb->len;
+
+		enetc_process_skb(rx_ring, skb);
+
+		napi_gro_receive(napi, skb);
+
+		rx_frm_cnt++;
+	}
+
+	rx_ring->next_to_clean = i;
+
+	rx_ring->stats.packets += rx_frm_cnt;
+	rx_ring->stats.bytes += rx_byte_cnt;
+
+	return rx_frm_cnt;
+}
+
+/* Probing and Init */
+#define ENETC_MAX_RFS_SIZE 64
+void enetc_get_si_caps(struct enetc_si *si)
+{
+	struct enetc_hw *hw = &si->hw;
+	u32 val;
+
+	/* find out how many of various resources we have to work with */
+	val = enetc_rd(hw, ENETC_SICAPR0);
+	si->num_rx_rings = (val >> 16) & 0xff;
+	si->num_tx_rings = val & 0xff;
+
+	val = enetc_rd(hw, ENETC_SIRFSCAPR);
+	si->num_fs_entries = ENETC_SIRFSCAPR_GET_NUM_RFS(val);
+	si->num_fs_entries = min(si->num_fs_entries, ENETC_MAX_RFS_SIZE);
+
+	si->num_rss = 0;
+	val = enetc_rd(hw, ENETC_SIPCAPR0);
+	if (val & ENETC_SIPCAPR0_RSS) {
+		val = enetc_rd(hw, ENETC_SIRSSCAPR);
+		si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(val);
+	}
+}
+
+static int enetc_dma_alloc_bdr(struct enetc_bdr *r, size_t bd_size)
+{
+	r->bd_base = dma_alloc_coherent(r->dev, r->bd_count * bd_size,
+					&r->bd_dma_base, GFP_KERNEL);
+	if (!r->bd_base)
+		return -ENOMEM;
+
+	/* h/w requires 128B alignment */
+	if (!IS_ALIGNED(r->bd_dma_base, 128)) {
+		dma_free_coherent(r->dev, r->bd_count * bd_size, r->bd_base,
+				  r->bd_dma_base);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int enetc_alloc_txbdr(struct enetc_bdr *txr)
+{
+	int err;
+
+	txr->tx_swbd = vzalloc(txr->bd_count * sizeof(struct enetc_tx_swbd));
+	if (!txr->tx_swbd)
+		return -ENOMEM;
+
+	err = enetc_dma_alloc_bdr(txr, sizeof(union enetc_tx_bd));
+	if (err) {
+		vfree(txr->tx_swbd);
+		return err;
+	}
+
+	txr->next_to_clean = 0;
+	txr->next_to_use = 0;
+
+	return 0;
+}
+
+static void enetc_free_txbdr(struct enetc_bdr *txr)
+{
+	int size, i;
+
+	for (i = 0; i < txr->bd_count; i++)
+		enetc_free_tx_skb(txr, &txr->tx_swbd[i]);
+
+	size = txr->bd_count * sizeof(union enetc_tx_bd);
+
+	dma_free_coherent(txr->dev, size, txr->bd_base, txr->bd_dma_base);
+	txr->bd_base = NULL;
+
+	vfree(txr->tx_swbd);
+	txr->tx_swbd = NULL;
+}
+
+static int enetc_alloc_tx_resources(struct enetc_ndev_priv *priv)
+{
+	int i, err;
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		err = enetc_alloc_txbdr(priv->tx_ring[i]);
+
+		if (err)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	while (i-- > 0)
+		enetc_free_txbdr(priv->tx_ring[i]);
+
+	return err;
+}
+
+static void enetc_free_tx_resources(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_free_txbdr(priv->tx_ring[i]);
+}
+
+static int enetc_alloc_rxbdr(struct enetc_bdr *rxr)
+{
+	int err;
+
+	rxr->rx_swbd = vzalloc(rxr->bd_count * sizeof(struct enetc_rx_swbd));
+	if (!rxr->rx_swbd)
+		return -ENOMEM;
+
+	err = enetc_dma_alloc_bdr(rxr, sizeof(union enetc_rx_bd));
+	if (err) {
+		vfree(rxr->rx_swbd);
+		return err;
+	}
+
+	rxr->next_to_clean = 0;
+	rxr->next_to_use = 0;
+	rxr->next_to_alloc = 0;
+
+	return 0;
+}
+
+static void enetc_free_rxbdr(struct enetc_bdr *rxr)
+{
+	int size;
+
+	size = rxr->bd_count * sizeof(union enetc_rx_bd);
+
+	dma_free_coherent(rxr->dev, size, rxr->bd_base, rxr->bd_dma_base);
+	rxr->bd_base = NULL;
+
+	vfree(rxr->rx_swbd);
+	rxr->rx_swbd = NULL;
+}
+
+static int enetc_alloc_rx_resources(struct enetc_ndev_priv *priv)
+{
+	int i, err;
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		err = enetc_alloc_rxbdr(priv->rx_ring[i]);
+
+		if (err)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	while (i-- > 0)
+		enetc_free_rxbdr(priv->rx_ring[i]);
+
+	return err;
+}
+
+static void enetc_free_rx_resources(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_free_rxbdr(priv->rx_ring[i]);
+}
+
+static void enetc_free_tx_ring(struct enetc_bdr *tx_ring)
+{
+	int i;
+
+	if (!tx_ring->tx_swbd)
+		return;
+
+	for (i = 0; i < tx_ring->bd_count; i++) {
+		struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+		enetc_free_tx_skb(tx_ring, tx_swbd);
+	}
+
+	tx_ring->next_to_clean = 0;
+	tx_ring->next_to_use = 0;
+}
+
+static void enetc_free_rx_ring(struct enetc_bdr *rx_ring)
+{
+	int i;
+
+	if (!rx_ring->rx_swbd)
+		return;
+
+	for (i = 0; i < rx_ring->bd_count; i++) {
+		struct enetc_rx_swbd *rx_swbd = &rx_ring->rx_swbd[i];
+
+		if (!rx_swbd->page)
+			continue;
+
+		dma_unmap_page(rx_ring->dev, rx_swbd->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+		__free_page(rx_swbd->page);
+		rx_swbd->page = NULL;
+	}
+
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+	rx_ring->next_to_alloc = 0;
+}
+
+static void enetc_free_rxtx_rings(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_free_rx_ring(priv->rx_ring[i]);
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_free_tx_ring(priv->tx_ring[i]);
+}
+
+static int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+{
+	int size = cbdr->bd_count * sizeof(struct enetc_cbd);
+
+	cbdr->bd_base = dma_alloc_coherent(dev, size, &cbdr->bd_dma_base,
+					   GFP_KERNEL);
+	if (!cbdr->bd_base)
+		return -ENOMEM;
+
+	/* h/w requires 128B alignment */
+	if (!IS_ALIGNED(cbdr->bd_dma_base, 128)) {
+		dma_free_coherent(dev, size, cbdr->bd_base, cbdr->bd_dma_base);
+		return -EINVAL;
+	}
+
+	cbdr->next_to_clean = 0;
+	cbdr->next_to_use = 0;
+
+	return 0;
+}
+
+static void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+{
+	int size = cbdr->bd_count * sizeof(struct enetc_cbd);
+
+	dma_free_coherent(dev, size, cbdr->bd_base, cbdr->bd_dma_base);
+	cbdr->bd_base = NULL;
+}
+
+static void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr)
+{
+	/* set CBDR cache attributes */
+	enetc_wr(hw, ENETC_SICAR2,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+
+	enetc_wr(hw, ENETC_SICBDRBAR0, lower_32_bits(cbdr->bd_dma_base));
+	enetc_wr(hw, ENETC_SICBDRBAR1, upper_32_bits(cbdr->bd_dma_base));
+	enetc_wr(hw, ENETC_SICBDRLENR, ENETC_RTBLENR_LEN(cbdr->bd_count));
+
+	enetc_wr(hw, ENETC_SICBDRPIR, 0);
+	enetc_wr(hw, ENETC_SICBDRCIR, 0);
+
+	/* enable ring */
+	enetc_wr(hw, ENETC_SICBDRMR, BIT(31));
+
+	cbdr->pir = hw->reg + ENETC_SICBDRPIR;
+	cbdr->cir = hw->reg + ENETC_SICBDRCIR;
+}
+
+static void enetc_clear_cbdr(struct enetc_hw *hw)
+{
+	enetc_wr(hw, ENETC_SICBDRMR, 0);
+}
+
+static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups)
+{
+	int *rss_table;
+	int i;
+
+	rss_table = kmalloc_array(si->num_rss, sizeof(*rss_table), GFP_KERNEL);
+	if (!rss_table)
+		return -ENOMEM;
+
+	/* Set up RSS table defaults */
+	for (i = 0; i < si->num_rss; i++)
+		rss_table[i] = i % num_groups;
+
+	enetc_set_rss_table(si, rss_table, si->num_rss);
+
+	kfree(rss_table);
+
+	return 0;
+}
+
+static int enetc_configure_si(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+	struct enetc_hw *hw = &si->hw;
+	int err;
+
+	enetc_setup_cbdr(hw, &si->cbd_ring);
+	/* set SI cache attributes */
+	enetc_wr(hw, ENETC_SICAR0,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+	enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI);
+	/* enable SI */
+	enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN);
+
+	if (si->num_rss) {
+		err = enetc_setup_default_rss_table(si, priv->num_rx_rings);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+void enetc_init_si_rings_params(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+	int cpus = num_online_cpus();
+
+	priv->tx_bd_count = ENETC_BDR_DEFAULT_SIZE;
+	priv->rx_bd_count = ENETC_BDR_DEFAULT_SIZE;
+
+	/* Enable all available TX rings in order to configure as many
+	 * priorities as possible, when needed.
+	 * TODO: Make # of TX rings run-time configurable
+	 */
+	priv->num_rx_rings = min_t(int, cpus, si->num_rx_rings);
+	priv->num_tx_rings = si->num_tx_rings;
+	priv->bdr_int_num = cpus;
+
+	/* SI specific */
+	si->cbd_ring.bd_count = ENETC_CBDR_DEFAULT_SIZE;
+}
+
+int enetc_alloc_si_resources(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+	int err;
+
+	err = enetc_alloc_cbdr(priv->dev, &si->cbd_ring);
+	if (err)
+		return err;
+
+	priv->cls_rules = kcalloc(si->num_fs_entries, sizeof(*priv->cls_rules),
+				  GFP_KERNEL);
+	if (!priv->cls_rules) {
+		err = -ENOMEM;
+		goto err_alloc_cls;
+	}
+
+	err = enetc_configure_si(priv);
+	if (err)
+		goto err_config_si;
+
+	return 0;
+
+err_config_si:
+	kfree(priv->cls_rules);
+err_alloc_cls:
+	enetc_clear_cbdr(&si->hw);
+	enetc_free_cbdr(priv->dev, &si->cbd_ring);
+
+	return err;
+}
+
+void enetc_free_si_resources(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+
+	enetc_clear_cbdr(&si->hw);
+	enetc_free_cbdr(priv->dev, &si->cbd_ring);
+
+	kfree(priv->cls_rules);
+}
+
+static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring)
+{
+	int idx = tx_ring->index;
+	u32 tbmr;
+
+	enetc_txbdr_wr(hw, idx, ENETC_TBBAR0,
+		       lower_32_bits(tx_ring->bd_dma_base));
+
+	enetc_txbdr_wr(hw, idx, ENETC_TBBAR1,
+		       upper_32_bits(tx_ring->bd_dma_base));
+
+	WARN_ON(!IS_ALIGNED(tx_ring->bd_count, 64)); /* multiple of 64 */
+	enetc_txbdr_wr(hw, idx, ENETC_TBLENR,
+		       ENETC_RTBLENR_LEN(tx_ring->bd_count));
+
+	/* clearing PI/CI registers for Tx not supported, adjust sw indexes */
+	tx_ring->next_to_use = enetc_txbdr_rd(hw, idx, ENETC_TBPIR);
+	tx_ring->next_to_clean = enetc_txbdr_rd(hw, idx, ENETC_TBCIR);
+
+	/* enable Tx ints by setting pkt thr to 1 */
+	enetc_txbdr_wr(hw, idx, ENETC_TBICIR0, ENETC_TBICIR0_ICEN | 0x1);
+
+	tbmr = ENETC_TBMR_EN;
+	if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX)
+		tbmr |= ENETC_TBMR_VIH;
+
+	/* enable ring */
+	enetc_txbdr_wr(hw, idx, ENETC_TBMR, tbmr);
+
+	tx_ring->tpir = hw->reg + ENETC_BDR(TX, idx, ENETC_TBPIR);
+	tx_ring->tcir = hw->reg + ENETC_BDR(TX, idx, ENETC_TBCIR);
+	tx_ring->idr = hw->reg + ENETC_SITXIDR;
+}
+
+static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
+{
+	int idx = rx_ring->index;
+	u32 rbmr;
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBBAR0,
+		       lower_32_bits(rx_ring->bd_dma_base));
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBBAR1,
+		       upper_32_bits(rx_ring->bd_dma_base));
+
+	WARN_ON(!IS_ALIGNED(rx_ring->bd_count, 64)); /* multiple of 64 */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBLENR,
+		       ENETC_RTBLENR_LEN(rx_ring->bd_count));
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBBSR, ENETC_RXB_DMA_SIZE);
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0);
+
+	/* enable Rx ints by setting pkt thr to 1 */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBICIR0, ENETC_RBICIR0_ICEN | 0x1);
+
+	rbmr = ENETC_RBMR_EN;
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+	rbmr |= ENETC_RBMR_BDS;
+#endif
+	if (rx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		rbmr |= ENETC_RBMR_VTE;
+
+	rx_ring->rcir = hw->reg + ENETC_BDR(RX, idx, ENETC_RBCIR);
+	rx_ring->idr = hw->reg + ENETC_SIRXIDR;
+
+	enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring));
+
+	/* enable ring */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr);
+}
+
+static void enetc_setup_bdrs(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_setup_txbdr(&priv->si->hw, priv->tx_ring[i]);
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_setup_rxbdr(&priv->si->hw, priv->rx_ring[i]);
+}
+
+static void enetc_clear_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
+{
+	int idx = rx_ring->index;
+
+	/* disable EN bit on ring */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBMR, 0);
+}
+
+static void enetc_clear_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring)
+{
+	int delay = 8, timeout = 100;
+	int idx = tx_ring->index;
+
+	/* disable EN bit on ring */
+	enetc_txbdr_wr(hw, idx, ENETC_TBMR, 0);
+
+	/* wait for busy to clear */
+	while (delay < timeout &&
+	       enetc_txbdr_rd(hw, idx, ENETC_TBSR) & ENETC_TBSR_BUSY) {
+		msleep(delay);
+		delay *= 2;
+	}
+
+	if (delay >= timeout)
+		netdev_warn(tx_ring->ndev, "timeout for tx ring #%d clear\n",
+			    idx);
+}
+
+static void enetc_clear_bdrs(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_clear_txbdr(&priv->si->hw, priv->tx_ring[i]);
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_clear_rxbdr(&priv->si->hw, priv->rx_ring[i]);
+
+	udelay(1);
+}
+
+static int enetc_setup_irqs(struct enetc_ndev_priv *priv)
+{
+	struct pci_dev *pdev = priv->si->pdev;
+	cpumask_t cpu_mask;
+	int i, j, err;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i);
+		struct enetc_int_vector *v = priv->int_vector[i];
+		int entry = ENETC_BDR_INT_BASE_IDX + i;
+		struct enetc_hw *hw = &priv->si->hw;
+
+		snprintf(v->name, sizeof(v->name), "%s-rxtx%d",
+			 priv->ndev->name, i);
+		err = request_irq(irq, enetc_msix, 0, v->name, v);
+		if (err) {
+			dev_err(priv->dev, "request_irq() failed!\n");
+			goto irq_err;
+		}
+
+		v->tbier_base = hw->reg + ENETC_BDR(TX, 0, ENETC_TBIER);
+		v->rbier = hw->reg + ENETC_BDR(RX, i, ENETC_RBIER);
+
+		enetc_wr(hw, ENETC_SIMSIRRV(i), entry);
+
+		for (j = 0; j < v->count_tx_rings; j++) {
+			int idx = v->tx_ring[j].index;
+
+			enetc_wr(hw, ENETC_SIMSITRV(idx), entry);
+		}
+		cpumask_clear(&cpu_mask);
+		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
+		irq_set_affinity_hint(irq, &cpu_mask);
+	}
+
+	return 0;
+
+irq_err:
+	while (i--) {
+		int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i);
+
+		irq_set_affinity_hint(irq, NULL);
+		free_irq(irq, priv->int_vector[i]);
+	}
+
+	return err;
+}
+
+static void enetc_free_irqs(struct enetc_ndev_priv *priv)
+{
+	struct pci_dev *pdev = priv->si->pdev;
+	int i;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i);
+
+		irq_set_affinity_hint(irq, NULL);
+		free_irq(irq, priv->int_vector[i]);
+	}
+}
+
+static void enetc_enable_interrupts(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	/* enable Tx & Rx event indication */
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		enetc_rxbdr_wr(&priv->si->hw, i,
+			       ENETC_RBIER, ENETC_RBIER_RXTIE);
+	}
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		enetc_txbdr_wr(&priv->si->hw, i,
+			       ENETC_TBIER, ENETC_TBIER_TXTIE);
+	}
+}
+
+static void enetc_disable_interrupts(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_txbdr_wr(&priv->si->hw, i, ENETC_TBIER, 0);
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_rxbdr_wr(&priv->si->hw, i, ENETC_RBIER, 0);
+}
+
+static void adjust_link(struct net_device *ndev)
+{
+	struct phy_device *phydev = ndev->phydev;
+
+	phy_print_status(phydev);
+}
+
+static int enetc_phy_connect(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct phy_device *phydev;
+
+	if (!priv->phy_node)
+		return 0; /* phy-less mode */
+
+	phydev = of_phy_connect(ndev, priv->phy_node, &adjust_link,
+				0, priv->if_mode);
+	if (!phydev) {
+		dev_err(&ndev->dev, "could not attach to PHY\n");
+		return -ENODEV;
+	}
+
+	phy_attached_info(phydev);
+
+	return 0;
+}
+
+int enetc_open(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i, err;
+
+	err = enetc_setup_irqs(priv);
+	if (err)
+		return err;
+
+	err = enetc_phy_connect(ndev);
+	if (err)
+		goto err_phy_connect;
+
+	err = enetc_alloc_tx_resources(priv);
+	if (err)
+		goto err_alloc_tx;
+
+	err = enetc_alloc_rx_resources(priv);
+	if (err)
+		goto err_alloc_rx;
+
+	enetc_setup_bdrs(priv);
+
+	err = netif_set_real_num_tx_queues(ndev, priv->num_tx_rings);
+	if (err)
+		goto err_set_queues;
+
+	err = netif_set_real_num_rx_queues(ndev, priv->num_rx_rings);
+	if (err)
+		goto err_set_queues;
+
+	for (i = 0; i < priv->bdr_int_num; i++)
+		napi_enable(&priv->int_vector[i]->napi);
+
+	enetc_enable_interrupts(priv);
+
+	if (ndev->phydev)
+		phy_start(ndev->phydev);
+	else
+		netif_carrier_on(ndev);
+
+	netif_tx_start_all_queues(ndev);
+
+	return 0;
+
+err_set_queues:
+	enetc_free_rx_resources(priv);
+err_alloc_rx:
+	enetc_free_tx_resources(priv);
+err_alloc_tx:
+	if (ndev->phydev)
+		phy_disconnect(ndev->phydev);
+err_phy_connect:
+	enetc_free_irqs(priv);
+
+	return err;
+}
+
+int enetc_close(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i;
+
+	netif_tx_stop_all_queues(ndev);
+
+	if (ndev->phydev) {
+		phy_stop(ndev->phydev);
+		phy_disconnect(ndev->phydev);
+	} else {
+		netif_carrier_off(ndev);
+	}
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		napi_synchronize(&priv->int_vector[i]->napi);
+		napi_disable(&priv->int_vector[i]->napi);
+	}
+
+	enetc_disable_interrupts(priv);
+	enetc_clear_bdrs(priv);
+
+	enetc_free_rxtx_rings(priv);
+	enetc_free_rx_resources(priv);
+	enetc_free_tx_resources(priv);
+	enetc_free_irqs(priv);
+
+	return 0;
+}
+
+int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+		   void *type_data)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct tc_mqprio_qopt *mqprio = type_data;
+	struct enetc_bdr *tx_ring;
+	u8 num_tc;
+	int i;
+
+	if (type != TC_SETUP_QDISC_MQPRIO)
+		return -EOPNOTSUPP;
+
+	mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+	num_tc = mqprio->num_tc;
+
+	if (!num_tc) {
+		netdev_reset_tc(ndev);
+		netif_set_real_num_tx_queues(ndev, priv->num_tx_rings);
+
+		/* Reset all ring priorities to 0 */
+		for (i = 0; i < priv->num_tx_rings; i++) {
+			tx_ring = priv->tx_ring[i];
+			enetc_set_bdr_prio(&priv->si->hw, tx_ring->index, 0);
+		}
+
+		return 0;
+	}
+
+	/* Check if we have enough BD rings available to accommodate all TCs */
+	if (num_tc > priv->num_tx_rings) {
+		netdev_err(ndev, "Max %d traffic classes supported\n",
+			   priv->num_tx_rings);
+		return -EINVAL;
+	}
+
+	/* For the moment, we use only one BD ring per TC.
+	 *
+	 * Configure num_tc BD rings with increasing priorities.
+	 */
+	for (i = 0; i < num_tc; i++) {
+		tx_ring = priv->tx_ring[i];
+		enetc_set_bdr_prio(&priv->si->hw, tx_ring->index, i);
+	}
+
+	/* Reset the number of netdev queues based on the TC count */
+	netif_set_real_num_tx_queues(ndev, num_tc);
+
+	netdev_set_num_tc(ndev, num_tc);
+
+	/* Each TC is associated with one netdev queue */
+	for (i = 0; i < num_tc; i++)
+		netdev_set_tc_queue(ndev, i, 1, i);
+
+	return 0;
+}
+
+struct net_device_stats *enetc_get_stats(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	unsigned long packets = 0, bytes = 0;
+	int i;
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		packets += priv->rx_ring[i]->stats.packets;
+		bytes	+= priv->rx_ring[i]->stats.bytes;
+	}
+
+	stats->rx_packets = packets;
+	stats->rx_bytes = bytes;
+	bytes = 0;
+	packets = 0;
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		packets += priv->tx_ring[i]->stats.packets;
+		bytes	+= priv->tx_ring[i]->stats.bytes;
+	}
+
+	stats->tx_packets = packets;
+	stats->tx_bytes = bytes;
+
+	return stats;
+}
+
+static int enetc_set_rss(struct net_device *ndev, int en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 reg;
+
+	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
+
+	reg = enetc_rd(hw, ENETC_SIMR);
+	reg &= ~ENETC_SIMR_RSSE;
+	reg |= (en) ? ENETC_SIMR_RSSE : 0;
+	enetc_wr(hw, ENETC_SIMR, reg);
+
+	return 0;
+}
+
+int enetc_set_features(struct net_device *ndev,
+		       netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+
+	if (changed & NETIF_F_RXHASH)
+		enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH));
+
+	return 0;
+}
+
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct hwtstamp_config config;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		priv->active_offloads &= ~ENETC_F_TX_TSTAMP;
+		break;
+	case HWTSTAMP_TX_ON:
+		priv->active_offloads |= ENETC_F_TX_TSTAMP;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		priv->active_offloads &= ~ENETC_F_RX_TSTAMP;
+		break;
+	default:
+		priv->active_offloads |= ENETC_F_RX_TSTAMP;
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+	       -EFAULT : 0;
+}
+
+static int enetc_hwtstamp_get(struct net_device *ndev, struct ifreq *ifr)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct hwtstamp_config config;
+
+	config.flags = 0;
+
+	if (priv->active_offloads & ENETC_F_TX_TSTAMP)
+		config.tx_type = HWTSTAMP_TX_ON;
+	else
+		config.tx_type = HWTSTAMP_TX_OFF;
+
+	config.rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ?
+			    HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE;
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+	       -EFAULT : 0;
+}
+#endif
+
+int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
+{
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+	if (cmd == SIOCSHWTSTAMP)
+		return enetc_hwtstamp_set(ndev, rq);
+	if (cmd == SIOCGHWTSTAMP)
+		return enetc_hwtstamp_get(ndev, rq);
+#endif
+	return -EINVAL;
+}
+
+int enetc_alloc_msix(struct enetc_ndev_priv *priv)
+{
+	struct pci_dev *pdev = priv->si->pdev;
+	int size, v_tx_rings;
+	int i, n, err, nvec;
+
+	nvec = ENETC_BDR_INT_BASE_IDX + priv->bdr_int_num;
+	/* allocate MSIX for both messaging and Rx/Tx interrupts */
+	n = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_MSIX);
+
+	if (n < 0)
+		return n;
+
+	if (n != nvec)
+		return -EPERM;
+
+	/* # of tx rings per int vector */
+	v_tx_rings = priv->num_tx_rings / priv->bdr_int_num;
+	size = sizeof(struct enetc_int_vector) +
+	       sizeof(struct enetc_bdr) * v_tx_rings;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		struct enetc_int_vector *v;
+		struct enetc_bdr *bdr;
+		int j;
+
+		v = kzalloc(size, GFP_KERNEL);
+		if (!v) {
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		priv->int_vector[i] = v;
+
+		netif_napi_add(priv->ndev, &v->napi, enetc_poll,
+			       NAPI_POLL_WEIGHT);
+		v->count_tx_rings = v_tx_rings;
+
+		for (j = 0; j < v_tx_rings; j++) {
+			int idx;
+
+			/* default tx ring mapping policy */
+			if (priv->bdr_int_num == ENETC_MAX_BDR_INT)
+				idx = 2 * j + i; /* 2 CPUs */
+			else
+				idx = j + i * v_tx_rings; /* default */
+
+			__set_bit(idx, &v->tx_rings_map);
+			bdr = &v->tx_ring[j];
+			bdr->index = idx;
+			bdr->ndev = priv->ndev;
+			bdr->dev = priv->dev;
+			bdr->bd_count = priv->tx_bd_count;
+			priv->tx_ring[idx] = bdr;
+		}
+
+		bdr = &v->rx_ring;
+		bdr->index = i;
+		bdr->ndev = priv->ndev;
+		bdr->dev = priv->dev;
+		bdr->bd_count = priv->rx_bd_count;
+		priv->rx_ring[i] = bdr;
+	}
+
+	return 0;
+
+fail:
+	while (i--) {
+		netif_napi_del(&priv->int_vector[i]->napi);
+		kfree(priv->int_vector[i]);
+	}
+
+	pci_free_irq_vectors(pdev);
+
+	return err;
+}
+
+void enetc_free_msix(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		struct enetc_int_vector *v = priv->int_vector[i];
+
+		netif_napi_del(&v->napi);
+	}
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		priv->rx_ring[i] = NULL;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		priv->tx_ring[i] = NULL;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		kfree(priv->int_vector[i]);
+		priv->int_vector[i] = NULL;
+	}
+
+	/* disable all MSIX for this device */
+	pci_free_irq_vectors(priv->si->pdev);
+}
+
+static void enetc_kfree_si(struct enetc_si *si)
+{
+	char *p = (char *)si - si->pad;
+
+	kfree(p);
+}
+
+static void enetc_detect_errata(struct enetc_si *si)
+{
+	if (si->pdev->revision == ENETC_REV1)
+		si->errata = ENETC_ERR_TXCSUM | ENETC_ERR_VLAN_ISOL |
+			     ENETC_ERR_UCMCSWP;
+}
+
+int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv)
+{
+	struct enetc_si *si, *p;
+	struct enetc_hw *hw;
+	size_t alloc_size;
+	int err, len;
+
+	pcie_flr(pdev);
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "device enable failed\n");
+		return err;
+	}
+
+	/* set up for high or low dma */
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev,
+				"DMA configuration failed: 0x%x\n", err);
+			goto err_dma;
+		}
+	}
+
+	err = pci_request_mem_regions(pdev, name);
+	if (err) {
+		dev_err(&pdev->dev, "pci_request_regions failed err=%d\n", err);
+		goto err_pci_mem_reg;
+	}
+
+	pci_set_master(pdev);
+
+	alloc_size = sizeof(struct enetc_si);
+	if (sizeof_priv) {
+		/* align priv to 32B */
+		alloc_size = ALIGN(alloc_size, ENETC_SI_ALIGN);
+		alloc_size += sizeof_priv;
+	}
+	/* force 32B alignment for enetc_si */
+	alloc_size += ENETC_SI_ALIGN - 1;
+
+	p = kzalloc(alloc_size, GFP_KERNEL);
+	if (!p) {
+		err = -ENOMEM;
+		goto err_alloc_si;
+	}
+
+	si = PTR_ALIGN(p, ENETC_SI_ALIGN);
+	si->pad = (char *)si - (char *)p;
+
+	pci_set_drvdata(pdev, si);
+	si->pdev = pdev;
+	hw = &si->hw;
+
+	len = pci_resource_len(pdev, ENETC_BAR_REGS);
+	hw->reg = ioremap(pci_resource_start(pdev, ENETC_BAR_REGS), len);
+	if (!hw->reg) {
+		err = -ENXIO;
+		dev_err(&pdev->dev, "ioremap() failed\n");
+		goto err_ioremap;
+	}
+	if (len > ENETC_PORT_BASE)
+		hw->port = hw->reg + ENETC_PORT_BASE;
+	if (len > ENETC_GLOBAL_BASE)
+		hw->global = hw->reg + ENETC_GLOBAL_BASE;
+
+	enetc_detect_errata(si);
+
+	return 0;
+
+err_ioremap:
+	enetc_kfree_si(si);
+err_alloc_si:
+	pci_release_mem_regions(pdev);
+err_pci_mem_reg:
+err_dma:
+	pci_disable_device(pdev);
+
+	return err;
+}
+
+void enetc_pci_remove(struct pci_dev *pdev)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_hw *hw = &si->hw;
+
+	iounmap(hw->reg);
+	enetc_kfree_si(si);
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
new file mode 100644
index 000000000000..541b4e2073fe
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -0,0 +1,246 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2017-2019 NXP */
+
+#include <linux/timer.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/dma-mapping.h>
+#include <linux/skbuff.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include <linux/phy.h>
+
+#include "enetc_hw.h"
+
+#define ENETC_MAC_MAXFRM_SIZE	9600
+#define ENETC_MAX_MTU		(ENETC_MAC_MAXFRM_SIZE - \
+				(ETH_FCS_LEN + ETH_HLEN + VLAN_HLEN))
+
+struct enetc_tx_swbd {
+	struct sk_buff *skb;
+	dma_addr_t dma;
+	u16 len;
+	u8 is_dma_page:1;
+	u8 check_wb:1;
+	u8 do_tstamp:1;
+};
+
+#define ENETC_RX_MAXFRM_SIZE	ENETC_MAC_MAXFRM_SIZE
+#define ENETC_RXB_TRUESIZE	2048 /* PAGE_SIZE >> 1 */
+#define ENETC_RXB_PAD		NET_SKB_PAD /* add extra space if needed */
+#define ENETC_RXB_DMA_SIZE	\
+	(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD)
+
+struct enetc_rx_swbd {
+	dma_addr_t dma;
+	struct page *page;
+	u16 page_offset;
+};
+
+struct enetc_ring_stats {
+	unsigned int packets;
+	unsigned int bytes;
+	unsigned int rx_alloc_errs;
+};
+
+#define ENETC_BDR_DEFAULT_SIZE	1024
+#define ENETC_DEFAULT_TX_WORK	256
+
+struct enetc_bdr {
+	struct device *dev; /* for DMA mapping */
+	struct net_device *ndev;
+	void *bd_base; /* points to Rx or Tx BD ring */
+	union {
+		void __iomem *tpir;
+		void __iomem *rcir;
+	};
+	u16 index;
+	int bd_count; /* # of BDs */
+	int next_to_use;
+	int next_to_clean;
+	union {
+		struct enetc_tx_swbd *tx_swbd;
+		struct enetc_rx_swbd *rx_swbd;
+	};
+	union {
+		void __iomem *tcir; /* Tx */
+		int next_to_alloc; /* Rx */
+	};
+	void __iomem *idr; /* Interrupt Detect Register pointer */
+
+	struct enetc_ring_stats stats;
+
+	dma_addr_t bd_dma_base;
+} ____cacheline_aligned_in_smp;
+
+static inline void enetc_bdr_idx_inc(struct enetc_bdr *bdr, int *i)
+{
+	if (unlikely(++*i == bdr->bd_count))
+		*i = 0;
+}
+
+static inline int enetc_bd_unused(struct enetc_bdr *bdr)
+{
+	if (bdr->next_to_clean > bdr->next_to_use)
+		return bdr->next_to_clean - bdr->next_to_use - 1;
+
+	return bdr->bd_count + bdr->next_to_clean - bdr->next_to_use - 1;
+}
+
+/* Control BD ring */
+#define ENETC_CBDR_DEFAULT_SIZE	64
+struct enetc_cbdr {
+	void *bd_base; /* points to Rx or Tx BD ring */
+	void __iomem *pir;
+	void __iomem *cir;
+
+	int bd_count; /* # of BDs */
+	int next_to_use;
+	int next_to_clean;
+
+	dma_addr_t bd_dma_base;
+};
+
+#define ENETC_TXBD(BDR, i) (&(((union enetc_tx_bd *)((BDR).bd_base))[i]))
+#define ENETC_RXBD(BDR, i) (&(((union enetc_rx_bd *)((BDR).bd_base))[i]))
+
+struct enetc_msg_swbd {
+	void *vaddr;
+	dma_addr_t dma;
+	int size;
+};
+
+#define ENETC_REV1	0x1
+enum enetc_errata {
+	ENETC_ERR_TXCSUM	= BIT(0),
+	ENETC_ERR_VLAN_ISOL	= BIT(1),
+	ENETC_ERR_UCMCSWP	= BIT(2),
+};
+
+/* PCI IEP device data */
+struct enetc_si {
+	struct pci_dev *pdev;
+	struct enetc_hw hw;
+	enum enetc_errata errata;
+
+	struct net_device *ndev; /* back ref. */
+
+	struct enetc_cbdr cbd_ring;
+
+	int num_rx_rings; /* how many rings are available in the SI */
+	int num_tx_rings;
+	int num_fs_entries;
+	int num_rss; /* number of RSS buckets */
+	unsigned short pad;
+};
+
+#define ENETC_SI_ALIGN	32
+
+static inline void *enetc_si_priv(const struct enetc_si *si)
+{
+	return (char *)si + ALIGN(sizeof(struct enetc_si), ENETC_SI_ALIGN);
+}
+
+static inline bool enetc_si_is_pf(struct enetc_si *si)
+{
+	return !!(si->hw.port);
+}
+
+#define ENETC_MAX_NUM_TXQS	8
+#define ENETC_INT_NAME_MAX	(IFNAMSIZ + 8)
+
+struct enetc_int_vector {
+	void __iomem *rbier;
+	void __iomem *tbier_base;
+	unsigned long tx_rings_map;
+	int count_tx_rings;
+	struct napi_struct napi;
+	char name[ENETC_INT_NAME_MAX];
+
+	struct enetc_bdr rx_ring ____cacheline_aligned_in_smp;
+	struct enetc_bdr tx_ring[0];
+};
+
+struct enetc_cls_rule {
+	struct ethtool_rx_flow_spec fs;
+	int used;
+};
+
+#define ENETC_MAX_BDR_INT	2 /* fixed to max # of available cpus */
+
+/* TODO: more hardware offloads */
+enum enetc_active_offloads {
+	ENETC_F_RX_TSTAMP	= BIT(0),
+	ENETC_F_TX_TSTAMP	= BIT(1),
+};
+
+struct enetc_ndev_priv {
+	struct net_device *ndev;
+	struct device *dev; /* dma-mapping device */
+	struct enetc_si *si;
+
+	int bdr_int_num; /* number of Rx/Tx ring interrupts */
+	struct enetc_int_vector *int_vector[ENETC_MAX_BDR_INT];
+	u16 num_rx_rings, num_tx_rings;
+	u16 rx_bd_count, tx_bd_count;
+
+	u16 msg_enable;
+	int active_offloads;
+
+	struct enetc_bdr *tx_ring[16];
+	struct enetc_bdr *rx_ring[16];
+
+	struct enetc_cls_rule *cls_rules;
+
+	struct device_node *phy_node;
+	phy_interface_t if_mode;
+};
+
+/* Messaging */
+
+/* VF-PF set primary MAC address message format */
+struct enetc_msg_cmd_set_primary_mac {
+	struct enetc_msg_cmd_header header;
+	struct sockaddr mac;
+};
+
+#define ENETC_CBD(R, i)	(&(((struct enetc_cbd *)((R).bd_base))[i]))
+
+#define ENETC_CBDR_TIMEOUT	1000 /* usecs */
+
+/* PTP driver exports */
+extern int enetc_phc_index;
+
+/* SI common */
+int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv);
+void enetc_pci_remove(struct pci_dev *pdev);
+int enetc_alloc_msix(struct enetc_ndev_priv *priv);
+void enetc_free_msix(struct enetc_ndev_priv *priv);
+void enetc_get_si_caps(struct enetc_si *si);
+void enetc_init_si_rings_params(struct enetc_ndev_priv *priv);
+int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
+void enetc_free_si_resources(struct enetc_ndev_priv *priv);
+
+int enetc_open(struct net_device *ndev);
+int enetc_close(struct net_device *ndev);
+netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev);
+struct net_device_stats *enetc_get_stats(struct net_device *ndev);
+int enetc_set_features(struct net_device *ndev,
+		       netdev_features_t features);
+int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd);
+int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+		   void *type_data);
+
+/* ethtool */
+void enetc_set_ethtool_ops(struct net_device *ndev);
+
+/* control buffer descriptor ring (CBDR) */
+int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
+			    char *mac_addr, int si_map);
+int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
+int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse,
+		       int index);
+void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes);
+int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count);
+int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
new file mode 100644
index 000000000000..de466b71bf8f
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include "enetc.h"
+
+static void enetc_clean_cbdr(struct enetc_si *si)
+{
+	struct enetc_cbdr *ring = &si->cbd_ring;
+	struct enetc_cbd *dest_cbd;
+	int i, status;
+
+	i = ring->next_to_clean;
+
+	while (enetc_rd_reg(ring->cir) != i) {
+		dest_cbd = ENETC_CBD(*ring, i);
+		status = dest_cbd->status_flags & ENETC_CBD_STATUS_MASK;
+		if (status)
+			dev_warn(&si->pdev->dev, "CMD err %04x for cmd %04x\n",
+				 status, dest_cbd->cmd);
+
+		memset(dest_cbd, 0, sizeof(*dest_cbd));
+
+		i = (i + 1) % ring->bd_count;
+	}
+
+	ring->next_to_clean = i;
+}
+
+static int enetc_cbd_unused(struct enetc_cbdr *r)
+{
+	return (r->next_to_clean - r->next_to_use - 1 + r->bd_count) %
+		r->bd_count;
+}
+
+static int enetc_send_cmd(struct enetc_si *si, struct enetc_cbd *cbd)
+{
+	struct enetc_cbdr *ring = &si->cbd_ring;
+	int timeout = ENETC_CBDR_TIMEOUT;
+	struct enetc_cbd *dest_cbd;
+	int i;
+
+	if (unlikely(!ring->bd_base))
+		return -EIO;
+
+	if (unlikely(!enetc_cbd_unused(ring)))
+		enetc_clean_cbdr(si);
+
+	i = ring->next_to_use;
+	dest_cbd = ENETC_CBD(*ring, i);
+
+	/* copy command to the ring */
+	*dest_cbd = *cbd;
+	i = (i + 1) % ring->bd_count;
+
+	ring->next_to_use = i;
+	/* let H/W know BD ring has been updated */
+	enetc_wr_reg(ring->pir, i);
+
+	do {
+		if (enetc_rd_reg(ring->cir) == i)
+			break;
+		udelay(10); /* cannot sleep, rtnl_lock() */
+		timeout -= 10;
+	} while (timeout);
+
+	if (!timeout)
+		return -EBUSY;
+
+	enetc_clean_cbdr(si);
+
+	return 0;
+}
+
+int enetc_clear_mac_flt_entry(struct enetc_si *si, int index)
+{
+	struct enetc_cbd cbd;
+
+	memset(&cbd, 0, sizeof(cbd));
+
+	cbd.cls = 1;
+	cbd.status_flags = ENETC_CBD_FLAGS_SF;
+	cbd.index = cpu_to_le16(index);
+
+	return enetc_send_cmd(si, &cbd);
+}
+
+int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
+			    char *mac_addr, int si_map)
+{
+	struct enetc_cbd cbd;
+	u32 upper;
+	u16 lower;
+
+	memset(&cbd, 0, sizeof(cbd));
+
+	/* fill up the "set" descriptor */
+	cbd.cls = 1;
+	cbd.status_flags = ENETC_CBD_FLAGS_SF;
+	cbd.index = cpu_to_le16(index);
+	cbd.opt[3] = cpu_to_le32(si_map);
+	/* enable entry */
+	cbd.opt[0] = cpu_to_le32(BIT(31));
+
+	upper = *(const u32 *)mac_addr;
+	lower = *(const u16 *)(mac_addr + 4);
+	cbd.addr[0] = cpu_to_le32(upper);
+	cbd.addr[1] = cpu_to_le32(lower);
+
+	return enetc_send_cmd(si, &cbd);
+}
+
+#define RFSE_ALIGN	64
+/* Set entry in RFS table */
+int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse,
+		       int index)
+{
+	struct enetc_cbd cbd = {.cmd = 0};
+	dma_addr_t dma, dma_align;
+	void *tmp, *tmp_align;
+	int err;
+
+	/* fill up the "set" descriptor */
+	cbd.cmd = 0;
+	cbd.cls = 4;
+	cbd.index = cpu_to_le16(index);
+	cbd.length = cpu_to_le16(sizeof(*rfse));
+	cbd.opt[3] = cpu_to_le32(0); /* SI */
+
+	tmp = dma_alloc_coherent(&si->pdev->dev, sizeof(*rfse) + RFSE_ALIGN,
+				 &dma, GFP_KERNEL);
+	if (!tmp) {
+		dev_err(&si->pdev->dev, "DMA mapping of RFS entry failed!\n");
+		return -ENOMEM;
+	}
+
+	dma_align = ALIGN(dma, RFSE_ALIGN);
+	tmp_align = PTR_ALIGN(tmp, RFSE_ALIGN);
+	memcpy(tmp_align, rfse, sizeof(*rfse));
+
+	cbd.addr[0] = cpu_to_le32(lower_32_bits(dma_align));
+	cbd.addr[1] = cpu_to_le32(upper_32_bits(dma_align));
+
+	err = enetc_send_cmd(si, &cbd);
+	if (err)
+		dev_err(&si->pdev->dev, "FS entry add failed (%d)!", err);
+
+	dma_free_coherent(&si->pdev->dev, sizeof(*rfse) + RFSE_ALIGN,
+			  tmp, dma);
+
+	return err;
+}
+
+#define RSSE_ALIGN	64
+static int enetc_cmd_rss_table(struct enetc_si *si, u32 *table, int count,
+			       bool read)
+{
+	struct enetc_cbd cbd = {.cmd = 0};
+	dma_addr_t dma, dma_align;
+	u8 *tmp, *tmp_align;
+	int err, i;
+
+	if (count < RSSE_ALIGN)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	tmp = dma_alloc_coherent(&si->pdev->dev, count + RSSE_ALIGN,
+				 &dma, GFP_KERNEL);
+	if (!tmp) {
+		dev_err(&si->pdev->dev, "DMA mapping of RSS table failed!\n");
+		return -ENOMEM;
+	}
+	dma_align = ALIGN(dma, RSSE_ALIGN);
+	tmp_align = PTR_ALIGN(tmp, RSSE_ALIGN);
+
+	if (!read)
+		for (i = 0; i < count; i++)
+			tmp_align[i] = (u8)(table[i]);
+
+	/* fill up the descriptor */
+	cbd.cmd = read ? 2 : 1;
+	cbd.cls = 3;
+	cbd.length = cpu_to_le16(count);
+
+	cbd.addr[0] = cpu_to_le32(lower_32_bits(dma_align));
+	cbd.addr[1] = cpu_to_le32(upper_32_bits(dma_align));
+
+	err = enetc_send_cmd(si, &cbd);
+	if (err)
+		dev_err(&si->pdev->dev, "RSS cmd failed (%d)!", err);
+
+	if (read)
+		for (i = 0; i < count; i++)
+			table[i] = tmp_align[i];
+
+	dma_free_coherent(&si->pdev->dev, count + RSSE_ALIGN, tmp, dma);
+
+	return err;
+}
+
+/* Get RSS table */
+int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count)
+{
+	return enetc_cmd_rss_table(si, table, count, true);
+}
+
+/* Set RSS table */
+int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count)
+{
+	return enetc_cmd_rss_table(si, (u32 *)table, count, false);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
new file mode 100644
index 000000000000..fcb52efec075
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -0,0 +1,630 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include <linux/net_tstamp.h>
+#include <linux/module.h>
+#include "enetc.h"
+
+static const u32 enetc_si_regs[] = {
+	ENETC_SIMR, ENETC_SIPMAR0, ENETC_SIPMAR1, ENETC_SICBDRMR,
+	ENETC_SICBDRSR,	ENETC_SICBDRBAR0, ENETC_SICBDRBAR1, ENETC_SICBDRPIR,
+	ENETC_SICBDRCIR, ENETC_SICBDRLENR, ENETC_SICAPR0, ENETC_SICAPR1,
+	ENETC_SIUEFDCR
+};
+
+static const u32 enetc_txbdr_regs[] = {
+	ENETC_TBMR, ENETC_TBSR, ENETC_TBBAR0, ENETC_TBBAR1,
+	ENETC_TBPIR, ENETC_TBCIR, ENETC_TBLENR, ENETC_TBIER
+};
+
+static const u32 enetc_rxbdr_regs[] = {
+	ENETC_RBMR, ENETC_RBSR, ENETC_RBBSR, ENETC_RBCIR, ENETC_RBBAR0,
+	ENETC_RBBAR1, ENETC_RBPIR, ENETC_RBLENR, ENETC_RBICIR0, ENETC_RBIER
+};
+
+static const u32 enetc_port_regs[] = {
+	ENETC_PMR, ENETC_PSR, ENETC_PSIPMR, ENETC_PSIPMAR0(0),
+	ENETC_PSIPMAR1(0), ENETC_PTXMBAR, ENETC_PCAPR0, ENETC_PCAPR1,
+	ENETC_PSICFGR0(0), ENETC_PRFSCAPR, ENETC_PTCMSDUR(0),
+	ENETC_PM0_CMD_CFG, ENETC_PM0_MAXFRM, ENETC_PM0_IF_MODE
+};
+
+static int enetc_get_reglen(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int len;
+
+	len = ARRAY_SIZE(enetc_si_regs);
+	len += ARRAY_SIZE(enetc_txbdr_regs) * priv->num_tx_rings;
+	len += ARRAY_SIZE(enetc_rxbdr_regs) * priv->num_rx_rings;
+
+	if (hw->port)
+		len += ARRAY_SIZE(enetc_port_regs);
+
+	len *= sizeof(u32) * 2; /* store 2 entries per reg: addr and value */
+
+	return len;
+}
+
+static void enetc_get_regs(struct net_device *ndev, struct ethtool_regs *regs,
+			   void *regbuf)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 *buf = (u32 *)regbuf;
+	int i, j;
+	u32 addr;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_si_regs); i++) {
+		*buf++ = enetc_si_regs[i];
+		*buf++ = enetc_rd(hw, enetc_si_regs[i]);
+	}
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		for (j = 0; j < ARRAY_SIZE(enetc_txbdr_regs); j++) {
+			addr = ENETC_BDR(TX, i, enetc_txbdr_regs[j]);
+
+			*buf++ = addr;
+			*buf++ = enetc_rd(hw, addr);
+		}
+	}
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		for (j = 0; j < ARRAY_SIZE(enetc_rxbdr_regs); j++) {
+			addr = ENETC_BDR(RX, i, enetc_rxbdr_regs[j]);
+
+			*buf++ = addr;
+			*buf++ = enetc_rd(hw, addr);
+		}
+	}
+
+	if (!hw->port)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_port_regs); i++) {
+		addr = ENETC_PORT_BASE + enetc_port_regs[i];
+		*buf++ = addr;
+		*buf++ = enetc_rd(hw, addr);
+	}
+}
+
+static const struct {
+	int reg;
+	char name[ETH_GSTRING_LEN];
+} enetc_si_counters[] =  {
+	{ ENETC_SIROCT, "SI rx octets" },
+	{ ENETC_SIRFRM, "SI rx frames" },
+	{ ENETC_SIRUCA, "SI rx u-cast frames" },
+	{ ENETC_SIRMCA, "SI rx m-cast frames" },
+	{ ENETC_SITOCT, "SI tx octets" },
+	{ ENETC_SITFRM, "SI tx frames" },
+	{ ENETC_SITUCA, "SI tx u-cast frames" },
+	{ ENETC_SITMCA, "SI tx m-cast frames" },
+	{ ENETC_RBDCR(0), "Rx ring  0 discarded frames" },
+	{ ENETC_RBDCR(1), "Rx ring  1 discarded frames" },
+	{ ENETC_RBDCR(2), "Rx ring  2 discarded frames" },
+	{ ENETC_RBDCR(3), "Rx ring  3 discarded frames" },
+	{ ENETC_RBDCR(4), "Rx ring  4 discarded frames" },
+	{ ENETC_RBDCR(5), "Rx ring  5 discarded frames" },
+	{ ENETC_RBDCR(6), "Rx ring  6 discarded frames" },
+	{ ENETC_RBDCR(7), "Rx ring  7 discarded frames" },
+	{ ENETC_RBDCR(8), "Rx ring  8 discarded frames" },
+	{ ENETC_RBDCR(9), "Rx ring  9 discarded frames" },
+	{ ENETC_RBDCR(10), "Rx ring 10 discarded frames" },
+	{ ENETC_RBDCR(11), "Rx ring 11 discarded frames" },
+	{ ENETC_RBDCR(12), "Rx ring 12 discarded frames" },
+	{ ENETC_RBDCR(13), "Rx ring 13 discarded frames" },
+	{ ENETC_RBDCR(14), "Rx ring 14 discarded frames" },
+	{ ENETC_RBDCR(15), "Rx ring 15 discarded frames" },
+};
+
+static const struct {
+	int reg;
+	char name[ETH_GSTRING_LEN];
+} enetc_port_counters[] = {
+	{ ENETC_PM0_REOCT,  "MAC rx ethernet octets" },
+	{ ENETC_PM0_RALN,   "MAC rx alignment errors" },
+	{ ENETC_PM0_RXPF,   "MAC rx valid pause frames" },
+	{ ENETC_PM0_RFRM,   "MAC rx valid frames" },
+	{ ENETC_PM0_RFCS,   "MAC rx fcs errors" },
+	{ ENETC_PM0_RVLAN,  "MAC rx VLAN frames" },
+	{ ENETC_PM0_RERR,   "MAC rx frame errors" },
+	{ ENETC_PM0_RUCA,   "MAC rx unicast frames" },
+	{ ENETC_PM0_RMCA,   "MAC rx multicast frames" },
+	{ ENETC_PM0_RBCA,   "MAC rx broadcast frames" },
+	{ ENETC_PM0_RDRP,   "MAC rx dropped packets" },
+	{ ENETC_PM0_RPKT,   "MAC rx packets" },
+	{ ENETC_PM0_RUND,   "MAC rx undersized packets" },
+	{ ENETC_PM0_R64,    "MAC rx 64 byte packets" },
+	{ ENETC_PM0_R127,   "MAC rx 65-127 byte packets" },
+	{ ENETC_PM0_R255,   "MAC rx 128-255 byte packets" },
+	{ ENETC_PM0_R511,   "MAC rx 256-511 byte packets" },
+	{ ENETC_PM0_R1023,  "MAC rx 512-1023 byte packets" },
+	{ ENETC_PM0_R1518,  "MAC rx 1024-1518 byte packets" },
+	{ ENETC_PM0_R1519X, "MAC rx 1519 to max-octet packets" },
+	{ ENETC_PM0_ROVR,   "MAC rx oversized packets" },
+	{ ENETC_PM0_RJBR,   "MAC rx jabber packets" },
+	{ ENETC_PM0_RFRG,   "MAC rx fragment packets" },
+	{ ENETC_PM0_RCNP,   "MAC rx control packets" },
+	{ ENETC_PM0_RDRNTP, "MAC rx fifo drop" },
+	{ ENETC_PM0_TEOCT,  "MAC tx ethernet octets" },
+	{ ENETC_PM0_TOCT,   "MAC tx octets" },
+	{ ENETC_PM0_TCRSE,  "MAC tx carrier sense errors" },
+	{ ENETC_PM0_TXPF,   "MAC tx valid pause frames" },
+	{ ENETC_PM0_TFRM,   "MAC tx frames" },
+	{ ENETC_PM0_TFCS,   "MAC tx fcs errors" },
+	{ ENETC_PM0_TVLAN,  "MAC tx VLAN frames" },
+	{ ENETC_PM0_TERR,   "MAC tx frames" },
+	{ ENETC_PM0_TUCA,   "MAC tx unicast frames" },
+	{ ENETC_PM0_TMCA,   "MAC tx multicast frames" },
+	{ ENETC_PM0_TBCA,   "MAC tx broadcast frames" },
+	{ ENETC_PM0_TPKT,   "MAC tx packets" },
+	{ ENETC_PM0_TUND,   "MAC tx undersized packets" },
+	{ ENETC_PM0_T127,   "MAC tx 65-127 byte packets" },
+	{ ENETC_PM0_T1023,  "MAC tx 512-1023 byte packets" },
+	{ ENETC_PM0_T1518,  "MAC tx 1024-1518 byte packets" },
+	{ ENETC_PM0_TCNP,   "MAC tx control packets" },
+	{ ENETC_PM0_TDFR,   "MAC tx deferred packets" },
+	{ ENETC_PM0_TMCOL,  "MAC tx multiple collisions" },
+	{ ENETC_PM0_TSCOL,  "MAC tx single collisions" },
+	{ ENETC_PM0_TLCOL,  "MAC tx late collisions" },
+	{ ENETC_PM0_TECOL,  "MAC tx excessive collisions" },
+	{ ENETC_UFDMF,      "SI MAC nomatch u-cast discards" },
+	{ ENETC_MFDMF,      "SI MAC nomatch m-cast discards" },
+	{ ENETC_PBFDSIR,    "SI MAC nomatch b-cast discards" },
+	{ ENETC_PUFDVFR,    "SI VLAN nomatch u-cast discards" },
+	{ ENETC_PMFDVFR,    "SI VLAN nomatch m-cast discards" },
+	{ ENETC_PBFDVFR,    "SI VLAN nomatch b-cast discards" },
+	{ ENETC_PFDMSAPR,   "SI pruning discarded frames" },
+	{ ENETC_PICDR(0),   "ICM DR0 discarded frames" },
+	{ ENETC_PICDR(1),   "ICM DR1 discarded frames" },
+	{ ENETC_PICDR(2),   "ICM DR2 discarded frames" },
+	{ ENETC_PICDR(3),   "ICM DR3 discarded frames" },
+};
+
+static const char rx_ring_stats[][ETH_GSTRING_LEN] = {
+	"Rx ring %2d frames",
+	"Rx ring %2d alloc errors",
+};
+
+static const char tx_ring_stats[][ETH_GSTRING_LEN] = {
+	"Tx ring %2d frames",
+};
+
+static int enetc_get_sset_count(struct net_device *ndev, int sset)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	if (sset == ETH_SS_STATS)
+		return ARRAY_SIZE(enetc_si_counters) +
+			ARRAY_SIZE(tx_ring_stats) * priv->num_tx_rings +
+			ARRAY_SIZE(rx_ring_stats) * priv->num_rx_rings +
+			(enetc_si_is_pf(priv->si) ?
+			ARRAY_SIZE(enetc_port_counters) : 0);
+
+	return -EOPNOTSUPP;
+}
+
+static void enetc_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	u8 *p = data;
+	int i, j;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(enetc_si_counters); i++) {
+			strlcpy(p, enetc_si_counters[i].name, ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < priv->num_tx_rings; i++) {
+			for (j = 0; j < ARRAY_SIZE(tx_ring_stats); j++) {
+				snprintf(p, ETH_GSTRING_LEN, tx_ring_stats[j],
+					 i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+		for (i = 0; i < priv->num_rx_rings; i++) {
+			for (j = 0; j < ARRAY_SIZE(rx_ring_stats); j++) {
+				snprintf(p, ETH_GSTRING_LEN, rx_ring_stats[j],
+					 i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
+		if (!enetc_si_is_pf(priv->si))
+			break;
+
+		for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++) {
+			strlcpy(p, enetc_port_counters[i].name,
+				ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	}
+}
+
+static void enetc_get_ethtool_stats(struct net_device *ndev,
+				    struct ethtool_stats *stats, u64 *data)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int i, o = 0;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_si_counters); i++)
+		data[o++] = enetc_rd64(hw, enetc_si_counters[i].reg);
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		data[o++] = priv->tx_ring[i]->stats.packets;
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		data[o++] = priv->rx_ring[i]->stats.packets;
+		data[o++] = priv->rx_ring[i]->stats.rx_alloc_errs;
+	}
+
+	if (!enetc_si_is_pf(priv->si))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++)
+		data[o++] = enetc_port_rd(hw, enetc_port_counters[i].reg);
+}
+
+#define ENETC_RSSHASH_L3 (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO | RXH_IP_SRC | \
+			  RXH_IP_DST)
+#define ENETC_RSSHASH_L4 (ENETC_RSSHASH_L3 | RXH_L4_B_0_1 | RXH_L4_B_2_3)
+static int enetc_get_rsshash(struct ethtool_rxnfc *rxnfc)
+{
+	static const u32 rsshash[] = {
+			[TCP_V4_FLOW]    = ENETC_RSSHASH_L4,
+			[UDP_V4_FLOW]    = ENETC_RSSHASH_L4,
+			[SCTP_V4_FLOW]   = ENETC_RSSHASH_L4,
+			[AH_ESP_V4_FLOW] = ENETC_RSSHASH_L3,
+			[IPV4_FLOW]      = ENETC_RSSHASH_L3,
+			[TCP_V6_FLOW]    = ENETC_RSSHASH_L4,
+			[UDP_V6_FLOW]    = ENETC_RSSHASH_L4,
+			[SCTP_V6_FLOW]   = ENETC_RSSHASH_L4,
+			[AH_ESP_V6_FLOW] = ENETC_RSSHASH_L3,
+			[IPV6_FLOW]      = ENETC_RSSHASH_L3,
+			[ETHER_FLOW]     = 0,
+	};
+
+	if (rxnfc->flow_type >= ARRAY_SIZE(rsshash))
+		return -EINVAL;
+
+	rxnfc->data = rsshash[rxnfc->flow_type];
+
+	return 0;
+}
+
+/* current HW spec does byte reversal on everything including MAC addresses */
+static void ether_addr_copy_swap(u8 *dst, const u8 *src)
+{
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dst[i] = src[ETH_ALEN - i - 1];
+}
+
+static int enetc_set_cls_entry(struct enetc_si *si,
+			       struct ethtool_rx_flow_spec *fs, bool en)
+{
+	struct ethtool_tcpip4_spec *l4ip4_h, *l4ip4_m;
+	struct ethtool_usrip4_spec *l3ip4_h, *l3ip4_m;
+	struct ethhdr *eth_h, *eth_m;
+	struct enetc_cmd_rfse rfse = { {0} };
+
+	if (!en)
+		goto done;
+
+	switch (fs->flow_type & 0xff) {
+	case TCP_V4_FLOW:
+		l4ip4_h = &fs->h_u.tcp_ip4_spec;
+		l4ip4_m = &fs->m_u.tcp_ip4_spec;
+		goto l4ip4;
+	case UDP_V4_FLOW:
+		l4ip4_h = &fs->h_u.udp_ip4_spec;
+		l4ip4_m = &fs->m_u.udp_ip4_spec;
+		goto l4ip4;
+	case SCTP_V4_FLOW:
+		l4ip4_h = &fs->h_u.sctp_ip4_spec;
+		l4ip4_m = &fs->m_u.sctp_ip4_spec;
+l4ip4:
+		rfse.sip_h[0] = l4ip4_h->ip4src;
+		rfse.sip_m[0] = l4ip4_m->ip4src;
+		rfse.dip_h[0] = l4ip4_h->ip4dst;
+		rfse.dip_m[0] = l4ip4_m->ip4dst;
+		rfse.sport_h = ntohs(l4ip4_h->psrc);
+		rfse.sport_m = ntohs(l4ip4_m->psrc);
+		rfse.dport_h = ntohs(l4ip4_h->pdst);
+		rfse.dport_m = ntohs(l4ip4_m->pdst);
+		if (l4ip4_m->tos)
+			netdev_warn(si->ndev, "ToS field is not supported and was ignored\n");
+		rfse.ethtype_h = ETH_P_IP; /* IPv4 */
+		rfse.ethtype_m = 0xffff;
+		break;
+	case IP_USER_FLOW:
+		l3ip4_h = &fs->h_u.usr_ip4_spec;
+		l3ip4_m = &fs->m_u.usr_ip4_spec;
+
+		rfse.sip_h[0] = l3ip4_h->ip4src;
+		rfse.sip_m[0] = l3ip4_m->ip4src;
+		rfse.dip_h[0] = l3ip4_h->ip4dst;
+		rfse.dip_m[0] = l3ip4_m->ip4dst;
+		if (l3ip4_m->tos)
+			netdev_warn(si->ndev, "ToS field is not supported and was ignored\n");
+		rfse.ethtype_h = ETH_P_IP; /* IPv4 */
+		rfse.ethtype_m = 0xffff;
+		break;
+	case ETHER_FLOW:
+		eth_h = &fs->h_u.ether_spec;
+		eth_m = &fs->m_u.ether_spec;
+
+		ether_addr_copy_swap(rfse.smac_h, eth_h->h_source);
+		ether_addr_copy_swap(rfse.smac_m, eth_m->h_source);
+		ether_addr_copy_swap(rfse.dmac_h, eth_h->h_dest);
+		ether_addr_copy_swap(rfse.dmac_m, eth_m->h_dest);
+		rfse.ethtype_h = ntohs(eth_h->h_proto);
+		rfse.ethtype_m = ntohs(eth_m->h_proto);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	rfse.mode |= ENETC_RFSE_EN;
+	if (fs->ring_cookie != RX_CLS_FLOW_DISC) {
+		rfse.mode |= ENETC_RFSE_MODE_BD;
+		rfse.result = fs->ring_cookie;
+	}
+done:
+	return enetc_set_fs_entry(si, &rfse, fs->location);
+}
+
+static int enetc_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
+			   u32 *rule_locs)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i, j;
+
+	switch (rxnfc->cmd) {
+	case ETHTOOL_GRXRINGS:
+		rxnfc->data = priv->num_rx_rings;
+		break;
+	case ETHTOOL_GRXFH:
+		/* get RSS hash config */
+		return enetc_get_rsshash(rxnfc);
+	case ETHTOOL_GRXCLSRLCNT:
+		/* total number of entries */
+		rxnfc->data = priv->si->num_fs_entries;
+		/* number of entries in use */
+		rxnfc->rule_cnt = 0;
+		for (i = 0; i < priv->si->num_fs_entries; i++)
+			if (priv->cls_rules[i].used)
+				rxnfc->rule_cnt++;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		if (rxnfc->fs.location >= priv->si->num_fs_entries)
+			return -EINVAL;
+
+		/* get entry x */
+		rxnfc->fs = priv->cls_rules[rxnfc->fs.location].fs;
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		/* total number of entries */
+		rxnfc->data = priv->si->num_fs_entries;
+		/* array of indexes of used entries */
+		j = 0;
+		for (i = 0; i < priv->si->num_fs_entries; i++) {
+			if (!priv->cls_rules[i].used)
+				continue;
+			if (j == rxnfc->rule_cnt)
+				return -EMSGSIZE;
+			rule_locs[j++] = i;
+		}
+		/* number of entries in use */
+		rxnfc->rule_cnt = j;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int enetc_set_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int err;
+
+	switch (rxnfc->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		if (rxnfc->fs.location >= priv->si->num_fs_entries)
+			return -EINVAL;
+
+		if (rxnfc->fs.ring_cookie >= priv->num_rx_rings &&
+		    rxnfc->fs.ring_cookie != RX_CLS_FLOW_DISC)
+			return -EINVAL;
+
+		err = enetc_set_cls_entry(priv->si, &rxnfc->fs, true);
+		if (err)
+			return err;
+		priv->cls_rules[rxnfc->fs.location].fs = rxnfc->fs;
+		priv->cls_rules[rxnfc->fs.location].used = 1;
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		if (rxnfc->fs.location >= priv->si->num_fs_entries)
+			return -EINVAL;
+
+		err = enetc_set_cls_entry(priv->si, &rxnfc->fs, false);
+		if (err)
+			return err;
+		priv->cls_rules[rxnfc->fs.location].used = 0;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static u32 enetc_get_rxfh_key_size(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	/* return the size of the RX flow hash key.  PF only */
+	return (priv->si->hw.port) ? ENETC_RSSHASH_KEY_SIZE : 0;
+}
+
+static u32 enetc_get_rxfh_indir_size(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	/* return the size of the RX flow hash indirection table */
+	return priv->si->num_rss;
+}
+
+static int enetc_get_rxfh(struct net_device *ndev, u32 *indir, u8 *key,
+			  u8 *hfunc)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int err = 0, i;
+
+	/* return hash function */
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
+	/* return hash key */
+	if (key && hw->port)
+		for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
+			((u32 *)key)[i] = enetc_port_rd(hw, ENETC_PRSSK(i));
+
+	/* return RSS table */
+	if (indir)
+		err = enetc_get_rss_table(priv->si, indir, priv->si->num_rss);
+
+	return err;
+}
+
+void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
+{
+	int i;
+
+	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
+		enetc_port_wr(hw, ENETC_PRSSK(i), ((u32 *)bytes)[i]);
+}
+
+static int enetc_set_rxfh(struct net_device *ndev, const u32 *indir,
+			  const u8 *key, const u8 hfunc)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int err = 0;
+
+	/* set hash key, if PF */
+	if (key && hw->port)
+		enetc_set_rss_key(hw, key);
+
+	/* set RSS table */
+	if (indir)
+		err = enetc_set_rss_table(priv->si, indir, priv->si->num_rss);
+
+	return err;
+}
+
+static void enetc_get_ringparam(struct net_device *ndev,
+				struct ethtool_ringparam *ring)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	ring->rx_pending = priv->rx_bd_count;
+	ring->tx_pending = priv->tx_bd_count;
+
+	/* do some h/w sanity checks for BDR length */
+	if (netif_running(ndev)) {
+		struct enetc_hw *hw = &priv->si->hw;
+		u32 val = enetc_rxbdr_rd(hw, 0, ENETC_RBLENR);
+
+		if (val != priv->rx_bd_count)
+			netif_err(priv, hw, ndev, "RxBDR[RBLENR] = %d!\n", val);
+
+		val = enetc_txbdr_rd(hw, 0, ENETC_TBLENR);
+
+		if (val != priv->tx_bd_count)
+			netif_err(priv, hw, ndev, "TxBDR[TBLENR] = %d!\n", val);
+	}
+}
+
+static int enetc_get_ts_info(struct net_device *ndev,
+			     struct ethtool_ts_info *info)
+{
+	int *phc_idx;
+
+	phc_idx = symbol_get(enetc_phc_index);
+	if (phc_idx) {
+		info->phc_index = *phc_idx;
+		symbol_put(enetc_phc_index);
+	} else {
+		info->phc_index = -1;
+	}
+
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
+			 (1 << HWTSTAMP_TX_ON);
+	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+			   (1 << HWTSTAMP_FILTER_ALL);
+#else
+	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
+				SOF_TIMESTAMPING_SOFTWARE;
+#endif
+	return 0;
+}
+
+static const struct ethtool_ops enetc_pf_ethtool_ops = {
+	.get_regs_len = enetc_get_reglen,
+	.get_regs = enetc_get_regs,
+	.get_sset_count = enetc_get_sset_count,
+	.get_strings = enetc_get_strings,
+	.get_ethtool_stats = enetc_get_ethtool_stats,
+	.get_rxnfc = enetc_get_rxnfc,
+	.set_rxnfc = enetc_set_rxnfc,
+	.get_rxfh_key_size = enetc_get_rxfh_key_size,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
+	.get_ringparam = enetc_get_ringparam,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+	.get_link = ethtool_op_get_link,
+	.get_ts_info = enetc_get_ts_info,
+};
+
+static const struct ethtool_ops enetc_vf_ethtool_ops = {
+	.get_regs_len = enetc_get_reglen,
+	.get_regs = enetc_get_regs,
+	.get_sset_count = enetc_get_sset_count,
+	.get_strings = enetc_get_strings,
+	.get_ethtool_stats = enetc_get_ethtool_stats,
+	.get_rxnfc = enetc_get_rxnfc,
+	.set_rxnfc = enetc_set_rxnfc,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
+	.get_ringparam = enetc_get_ringparam,
+	.get_link = ethtool_op_get_link,
+	.get_ts_info = enetc_get_ts_info,
+};
+
+void enetc_set_ethtool_ops(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	if (enetc_si_is_pf(priv->si))
+		ndev->ethtool_ops = &enetc_pf_ethtool_ops;
+	else
+		ndev->ethtool_ops = &enetc_vf_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
new file mode 100644
index 000000000000..88276299f447
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -0,0 +1,556 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2017-2019 NXP */
+
+#include <linux/bitops.h>
+
+/* ENETC device IDs */
+#define ENETC_DEV_ID_PF		0xe100
+#define ENETC_DEV_ID_VF		0xef00
+#define ENETC_DEV_ID_PTP	0xee02
+
+/* ENETC register block BAR */
+#define ENETC_BAR_REGS	0
+
+/** SI regs, offset: 0h */
+#define ENETC_SIMR	0
+#define ENETC_SIMR_EN	BIT(31)
+#define ENETC_SIMR_RSSE	BIT(0)
+#define ENETC_SICTR0	0x18
+#define ENETC_SICTR1	0x1c
+#define ENETC_SIPCAPR0	0x20
+#define ENETC_SIPCAPR0_RSS	BIT(8)
+#define ENETC_SIPCAPR1	0x24
+#define ENETC_SITGTGR	0x30
+#define ENETC_SIRBGCR	0x38
+/* cache attribute registers for transactions initiated by ENETC */
+#define ENETC_SICAR0	0x40
+#define ENETC_SICAR1	0x44
+#define ENETC_SICAR2	0x48
+/* rd snoop, no alloc
+ * wr snoop, no alloc, partial cache line update for BDs and full cache line
+ * update for data
+ */
+#define ENETC_SICAR_RD_COHERENT	0x2b2b0000
+#define ENETC_SICAR_WR_COHERENT	0x00006727
+#define ENETC_SICAR_MSI	0x00300030 /* rd/wr device, no snoop, no alloc */
+
+#define ENETC_SIPMAR0	0x80
+#define ENETC_SIPMAR1	0x84
+
+/* VF-PF Message passing */
+#define ENETC_DEFAULT_MSG_SIZE	1024	/* and max size */
+/* msg size encoding: default and max msg value of 1024B encoded as 0 */
+static inline u32 enetc_vsi_set_msize(u32 size)
+{
+	return size < ENETC_DEFAULT_MSG_SIZE ? size >> 5 : 0;
+}
+
+#define ENETC_PSIMSGRR	0x204
+#define ENETC_PSIMSGRR_MR_MASK	GENMASK(2, 1)
+#define ENETC_PSIMSGRR_MR(n) BIT((n) + 1) /* n = VSI index */
+#define ENETC_PSIVMSGRCVAR0(n)	(0x210 + (n) * 0x8) /* n = VSI index */
+#define ENETC_PSIVMSGRCVAR1(n)	(0x214 + (n) * 0x8)
+
+#define ENETC_VSIMSGSR	0x204	/* RO */
+#define ENETC_VSIMSGSR_MB	BIT(0)
+#define ENETC_VSIMSGSR_MS	BIT(1)
+#define ENETC_VSIMSGSNDAR0	0x210
+#define ENETC_VSIMSGSNDAR1	0x214
+
+#define ENETC_SIMSGSR_SET_MC(val) ((val) << 16)
+#define ENETC_SIMSGSR_GET_MC(val) ((val) >> 16)
+
+/* SI statistics */
+#define ENETC_SIROCT	0x300
+#define ENETC_SIRFRM	0x308
+#define ENETC_SIRUCA	0x310
+#define ENETC_SIRMCA	0x318
+#define ENETC_SITOCT	0x320
+#define ENETC_SITFRM	0x328
+#define ENETC_SITUCA	0x330
+#define ENETC_SITMCA	0x338
+#define ENETC_RBDCR(n)	(0x8180 + (n) * 0x200)
+
+/* Control BDR regs */
+#define ENETC_SICBDRMR		0x800
+#define ENETC_SICBDRSR		0x804	/* RO */
+#define ENETC_SICBDRBAR0	0x810
+#define ENETC_SICBDRBAR1	0x814
+#define ENETC_SICBDRPIR		0x818
+#define ENETC_SICBDRCIR		0x81c
+#define ENETC_SICBDRLENR	0x820
+
+#define ENETC_SICAPR0	0x900
+#define ENETC_SICAPR1	0x904
+
+#define ENETC_PSIIER	0xa00
+#define ENETC_PSIIER_MR_MASK	GENMASK(2, 1)
+#define ENETC_PSIIDR	0xa08
+#define ENETC_SITXIDR	0xa18
+#define ENETC_SIRXIDR	0xa28
+#define ENETC_SIMSIVR	0xa30
+
+#define ENETC_SIMSITRV(n) (0xB00 + (n) * 0x4)
+#define ENETC_SIMSIRRV(n) (0xB80 + (n) * 0x4)
+
+#define ENETC_SIUEFDCR	0xe28
+
+#define ENETC_SIRFSCAPR	0x1200
+#define ENETC_SIRFSCAPR_GET_NUM_RFS(val) ((val) & 0x7f)
+#define ENETC_SIRSSCAPR	0x1600
+#define ENETC_SIRSSCAPR_GET_NUM_RSS(val) (BIT((val) & 0xf) * 32)
+
+/** SI BDR sub-blocks, n = 0..7 */
+enum enetc_bdr_type {TX, RX};
+#define ENETC_BDR_OFF(i)	((i) * 0x200)
+#define ENETC_BDR(t, i, r)	(0x8000 + (t) * 0x100 + ENETC_BDR_OFF(i) + (r))
+/* RX BDR reg offsets */
+#define ENETC_RBMR	0
+#define ENETC_RBMR_BDS	BIT(2)
+#define ENETC_RBMR_VTE	BIT(5)
+#define ENETC_RBMR_EN	BIT(31)
+#define ENETC_RBSR	0x4
+#define ENETC_RBBSR	0x8
+#define ENETC_RBCIR	0xc
+#define ENETC_RBBAR0	0x10
+#define ENETC_RBBAR1	0x14
+#define ENETC_RBPIR	0x18
+#define ENETC_RBLENR	0x20
+#define ENETC_RBIER	0xa0
+#define ENETC_RBIER_RXTIE	BIT(0)
+#define ENETC_RBIDR	0xa4
+#define ENETC_RBICIR0	0xa8
+#define ENETC_RBICIR0_ICEN	BIT(31)
+
+/* TX BDR reg offsets */
+#define ENETC_TBMR	0
+#define ENETC_TBSR_BUSY	BIT(0)
+#define ENETC_TBMR_VIH	BIT(9)
+#define ENETC_TBMR_PRIO_MASK		GENMASK(2, 0)
+#define ENETC_TBMR_SET_PRIO(val)	((val) & ENETC_TBMR_PRIO_MASK)
+#define ENETC_TBMR_EN	BIT(31)
+#define ENETC_TBSR	0x4
+#define ENETC_TBBAR0	0x10
+#define ENETC_TBBAR1	0x14
+#define ENETC_TBPIR	0x18
+#define ENETC_TBCIR	0x1c
+#define ENETC_TBCIR_IDX_MASK	0xffff
+#define ENETC_TBLENR	0x20
+#define ENETC_TBIER	0xa0
+#define ENETC_TBIER_TXTIE	BIT(0)
+#define ENETC_TBIDR	0xa4
+#define ENETC_TBICIR0	0xa8
+#define ENETC_TBICIR0_ICEN	BIT(31)
+
+#define ENETC_RTBLENR_LEN(n)	((n) & ~0x7)
+
+/* Port regs, offset: 1_0000h */
+#define ENETC_PORT_BASE		0x10000
+#define ENETC_PMR		0x0000
+#define ENETC_PMR_EN	GENMASK(18, 16)
+#define ENETC_PSR		0x0004 /* RO */
+#define ENETC_PSIPMR		0x0018
+#define ENETC_PSIPMR_SET_UP(n)	BIT(n) /* n = SI index */
+#define ENETC_PSIPMR_SET_MP(n)	BIT((n) + 16)
+#define ENETC_PSIPVMR		0x001c
+#define ENETC_VLAN_PROMISC_MAP_ALL	0x7
+#define ENETC_PSIPVMR_SET_VP(simap)	((simap) & 0x7)
+#define ENETC_PSIPVMR_SET_VUTA(simap)	(((simap) & 0x7) << 16)
+#define ENETC_PSIPMAR0(n)	(0x0100 + (n) * 0x8) /* n = SI index */
+#define ENETC_PSIPMAR1(n)	(0x0104 + (n) * 0x8)
+#define ENETC_PVCLCTR		0x0208
+#define ENETC_VLAN_TYPE_C	BIT(0)
+#define ENETC_VLAN_TYPE_S	BIT(1)
+#define ENETC_PVCLCTR_OVTPIDL(bmp)	((bmp) & 0xff) /* VLAN_TYPE */
+#define ENETC_PSIVLANR(n)	(0x0240 + (n) * 4) /* n = SI index */
+#define ENETC_PSIVLAN_EN	BIT(31)
+#define ENETC_PSIVLAN_SET_QOS(val)	((u32)(val) << 12)
+#define ENETC_PTXMBAR		0x0608
+#define ENETC_PCAPR0		0x0900
+#define ENETC_PCAPR0_RXBDR(val)	((val) >> 24)
+#define ENETC_PCAPR0_TXBDR(val)	(((val) >> 16) & 0xff)
+#define ENETC_PCAPR1		0x0904
+#define ENETC_PSICFGR0(n)	(0x0940 + (n) * 0xc)  /* n = SI index */
+#define ENETC_PSICFGR0_SET_TXBDR(val)	((val) & 0xff)
+#define ENETC_PSICFGR0_SET_RXBDR(val)	(((val) & 0xff) << 16)
+#define ENETC_PSICFGR0_VTE	BIT(12)
+#define ENETC_PSICFGR0_SIVIE	BIT(14)
+#define ENETC_PSICFGR0_ASE	BIT(15)
+#define ENETC_PSICFGR0_SIVC(bmp)	(((bmp) & 0xff) << 24) /* VLAN_TYPE */
+
+#define ENETC_PTCCBSR0(n)	(0x1110 + (n) * 8) /* n = 0 to 7*/
+#define ENETC_PTCCBSR1(n)	(0x1114 + (n) * 8) /* n = 0 to 7*/
+#define ENETC_RSSHASH_KEY_SIZE	40
+#define ENETC_PRSSK(n)		(0x1410 + (n) * 4) /* n = [0..9] */
+#define ENETC_PSIVLANFMR	0x1700
+#define ENETC_PSIVLANFMR_VS	BIT(0)
+#define ENETC_PRFSMR		0x1800
+#define ENETC_PRFSMR_RFSE	BIT(31)
+#define ENETC_PRFSCAPR		0x1804
+#define ENETC_PRFSCAPR_GET_NUM_RFS(val)	((((val) & 0xf) + 1) * 16)
+#define ENETC_PSIRFSCFGR(n)	(0x1814 + (n) * 4) /* n = SI index */
+#define ENETC_PFPMR		0x1900
+#define ENETC_PFPMR_PMACE	BIT(1)
+#define ENETC_PFPMR_MWLM	BIT(0)
+#define ENETC_PSIUMHFR0(n, err)	(((err) ? 0x1d08 : 0x1d00) + (n) * 0x10)
+#define ENETC_PSIUMHFR1(n)	(0x1d04 + (n) * 0x10)
+#define ENETC_PSIMMHFR0(n, err)	(((err) ? 0x1d00 : 0x1d08) + (n) * 0x10)
+#define ENETC_PSIMMHFR1(n)	(0x1d0c + (n) * 0x10)
+#define ENETC_PSIVHFR0(n)	(0x1e00 + (n) * 8) /* n = SI index */
+#define ENETC_PSIVHFR1(n)	(0x1e04 + (n) * 8) /* n = SI index */
+#define ENETC_MMCSR		0x1f00
+#define ENETC_MMCSR_ME		BIT(16)
+#define ENETC_PTCMSDUR(n)	(0x2020 + (n) * 4) /* n = TC index [0..7] */
+
+#define ENETC_PM0_CMD_CFG	0x8008
+#define ENETC_PM1_CMD_CFG	0x9008
+#define ENETC_PM0_TX_EN		BIT(0)
+#define ENETC_PM0_RX_EN		BIT(1)
+#define ENETC_PM0_PROMISC	BIT(4)
+#define ENETC_PM0_CMD_XGLP	BIT(10)
+#define ENETC_PM0_CMD_TXP	BIT(11)
+#define ENETC_PM0_CMD_PHY_TX_EN	BIT(15)
+#define ENETC_PM0_CMD_SFD	BIT(21)
+#define ENETC_PM0_MAXFRM	0x8014
+#define ENETC_SET_TX_MTU(val)	((val) << 16)
+#define ENETC_SET_MAXFRM(val)	((val) & 0xffff)
+#define ENETC_PM0_IF_MODE	0x8300
+#define ENETC_PMO_IFM_RG	BIT(2)
+#define ENETC_PM0_IFM_RLP	(BIT(5) | BIT(11))
+#define ENETC_PM0_IFM_RGAUTO	(BIT(15) | ENETC_PMO_IFM_RG | BIT(1))
+#define ENETC_PM0_IFM_XGMII	BIT(12)
+
+/* MAC counters */
+#define ENETC_PM0_REOCT		0x8100
+#define ENETC_PM0_RALN		0x8110
+#define ENETC_PM0_RXPF		0x8118
+#define ENETC_PM0_RFRM		0x8120
+#define ENETC_PM0_RFCS		0x8128
+#define ENETC_PM0_RVLAN		0x8130
+#define ENETC_PM0_RERR		0x8138
+#define ENETC_PM0_RUCA		0x8140
+#define ENETC_PM0_RMCA		0x8148
+#define ENETC_PM0_RBCA		0x8150
+#define ENETC_PM0_RDRP		0x8158
+#define ENETC_PM0_RPKT		0x8160
+#define ENETC_PM0_RUND		0x8168
+#define ENETC_PM0_R64		0x8170
+#define ENETC_PM0_R127		0x8178
+#define ENETC_PM0_R255		0x8180
+#define ENETC_PM0_R511		0x8188
+#define ENETC_PM0_R1023		0x8190
+#define ENETC_PM0_R1518		0x8198
+#define ENETC_PM0_R1519X	0x81A0
+#define ENETC_PM0_ROVR		0x81A8
+#define ENETC_PM0_RJBR		0x81B0
+#define ENETC_PM0_RFRG		0x81B8
+#define ENETC_PM0_RCNP		0x81C0
+#define ENETC_PM0_RDRNTP	0x81C8
+#define ENETC_PM0_TEOCT		0x8200
+#define ENETC_PM0_TOCT		0x8208
+#define ENETC_PM0_TCRSE		0x8210
+#define ENETC_PM0_TXPF		0x8218
+#define ENETC_PM0_TFRM		0x8220
+#define ENETC_PM0_TFCS		0x8228
+#define ENETC_PM0_TVLAN		0x8230
+#define ENETC_PM0_TERR		0x8238
+#define ENETC_PM0_TUCA		0x8240
+#define ENETC_PM0_TMCA		0x8248
+#define ENETC_PM0_TBCA		0x8250
+#define ENETC_PM0_TPKT		0x8260
+#define ENETC_PM0_TUND		0x8268
+#define ENETC_PM0_T127		0x8278
+#define ENETC_PM0_T1023		0x8290
+#define ENETC_PM0_T1518		0x8298
+#define ENETC_PM0_TCNP		0x82C0
+#define ENETC_PM0_TDFR		0x82D0
+#define ENETC_PM0_TMCOL		0x82D8
+#define ENETC_PM0_TSCOL		0x82E0
+#define ENETC_PM0_TLCOL		0x82E8
+#define ENETC_PM0_TECOL		0x82F0
+
+/* Port counters */
+#define ENETC_PICDR(n)		(0x0700 + (n) * 8) /* n = [0..3] */
+#define ENETC_PBFDSIR		0x0810
+#define ENETC_PFDMSAPR		0x0814
+#define ENETC_UFDMF		0x1680
+#define ENETC_MFDMF		0x1684
+#define ENETC_PUFDVFR		0x1780
+#define ENETC_PMFDVFR		0x1784
+#define ENETC_PBFDVFR		0x1788
+
+/** Global regs, offset: 2_0000h */
+#define ENETC_GLOBAL_BASE	0x20000
+#define ENETC_G_EIPBRR0		0x0bf8
+#define ENETC_G_EIPBRR1		0x0bfc
+#define ENETC_G_EPFBLPR(n)	(0xd00 + 4 * (n))
+#define ENETC_G_EPFBLPR1_XGMII	0x80000000
+
+/* PCI device info */
+struct enetc_hw {
+	/* SI registers, used by all PCI functions */
+	void __iomem *reg;
+	/* Port registers, PF only */
+	void __iomem *port;
+	/* IP global registers, PF only */
+	void __iomem *global;
+};
+
+/* general register accessors */
+#define enetc_rd_reg(reg)	ioread32((reg))
+#define enetc_wr_reg(reg, val)	iowrite32((val), (reg))
+#ifdef ioread64
+#define enetc_rd_reg64(reg)	ioread64((reg))
+#else
+/* using this to read out stats on 32b systems */
+static inline u64 enetc_rd_reg64(void __iomem *reg)
+{
+	u32 low, high, tmp;
+
+	do {
+		high = ioread32(reg + 4);
+		low = ioread32(reg);
+		tmp = ioread32(reg + 4);
+	} while (high != tmp);
+
+	return le64_to_cpu((__le64)high << 32 | low);
+}
+#endif
+
+#define enetc_rd(hw, off)		enetc_rd_reg((hw)->reg + (off))
+#define enetc_wr(hw, off, val)		enetc_wr_reg((hw)->reg + (off), val)
+#define enetc_rd64(hw, off)		enetc_rd_reg64((hw)->reg + (off))
+/* port register accessors - PF only */
+#define enetc_port_rd(hw, off)		enetc_rd_reg((hw)->port + (off))
+#define enetc_port_wr(hw, off, val)	enetc_wr_reg((hw)->port + (off), val)
+/* global register accessors - PF only */
+#define enetc_global_rd(hw, off)	enetc_rd_reg((hw)->global + (off))
+#define enetc_global_wr(hw, off, val)	enetc_wr_reg((hw)->global + (off), val)
+/* BDR register accessors, see ENETC_BDR() */
+#define enetc_bdr_rd(hw, t, n, off) \
+				enetc_rd(hw, ENETC_BDR(t, n, off))
+#define enetc_bdr_wr(hw, t, n, off, val) \
+				enetc_wr(hw, ENETC_BDR(t, n, off), val)
+#define enetc_txbdr_rd(hw, n, off) enetc_bdr_rd(hw, TX, n, off)
+#define enetc_rxbdr_rd(hw, n, off) enetc_bdr_rd(hw, RX, n, off)
+#define enetc_txbdr_wr(hw, n, off, val) \
+				enetc_bdr_wr(hw, TX, n, off, val)
+#define enetc_rxbdr_wr(hw, n, off, val) \
+				enetc_bdr_wr(hw, RX, n, off, val)
+
+/* Buffer Descriptors (BD) */
+union enetc_tx_bd {
+	struct {
+		__le64 addr;
+		__le16 buf_len;
+		__le16 frm_len;
+		union {
+			struct {
+				__le16 l3_csoff;
+				u8 l4_csoff;
+				u8 flags;
+			}; /* default layout */
+			__le32 lstatus;
+		};
+	};
+	struct {
+		__le32 tstamp;
+		__le16 tpid;
+		__le16 vid;
+		u8 reserved[6];
+		u8 e_flags;
+		u8 flags;
+	} ext; /* Tx BD extension */
+	struct {
+		__le32 tstamp;
+		u8 reserved[10];
+		u8 status;
+		u8 flags;
+	} wb; /* writeback descriptor */
+};
+
+#define ENETC_TXBD_FLAGS_L4CS	BIT(0)
+#define ENETC_TXBD_FLAGS_W	BIT(2)
+#define ENETC_TXBD_FLAGS_CSUM	BIT(3)
+#define ENETC_TXBD_FLAGS_EX	BIT(6)
+#define ENETC_TXBD_FLAGS_F	BIT(7)
+
+static inline void enetc_clear_tx_bd(union enetc_tx_bd *txbd)
+{
+	memset(txbd, 0, sizeof(*txbd));
+}
+
+/* L3 csum flags */
+#define ENETC_TXBD_L3_IPCS	BIT(7)
+#define ENETC_TXBD_L3_IPV6	BIT(15)
+
+#define ENETC_TXBD_L3_START_MASK	GENMASK(6, 0)
+#define ENETC_TXBD_L3_SET_HSIZE(val)	((((val) >> 2) & 0x7f) << 8)
+
+/* Extension flags */
+#define ENETC_TXBD_E_FLAGS_VLAN_INS	BIT(0)
+#define ENETC_TXBD_E_FLAGS_TWO_STEP_PTP	BIT(2)
+
+static inline __le16 enetc_txbd_l3_csoff(int start, int hdr_sz, u16 l3_flags)
+{
+	return cpu_to_le16(l3_flags | ENETC_TXBD_L3_SET_HSIZE(hdr_sz) |
+			   (start & ENETC_TXBD_L3_START_MASK));
+}
+
+/* L4 csum flags */
+#define ENETC_TXBD_L4_UDP	BIT(5)
+#define ENETC_TXBD_L4_TCP	BIT(6)
+
+union enetc_rx_bd {
+	struct {
+		__le64 addr;
+		u8 reserved[8];
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+		u8 reserved1[16];
+#endif
+	} w;
+	struct {
+		__le16 inet_csum;
+		__le16 parse_summary;
+		__le32 rss_hash;
+		__le16 buf_len;
+		__le16 vlan_opt;
+		union {
+			struct {
+				__le16 flags;
+				__le16 error;
+			};
+			__le32 lstatus;
+		};
+#ifdef CONFIG_FSL_ENETC_HW_TIMESTAMPING
+		__le32 tstamp;
+		u8 reserved[12];
+#endif
+	} r;
+};
+
+#define ENETC_RXBD_LSTATUS_R	BIT(30)
+#define ENETC_RXBD_LSTATUS_F	BIT(31)
+#define ENETC_RXBD_ERR_MASK	0xff
+#define ENETC_RXBD_LSTATUS(flags)	((flags) << 16)
+#define ENETC_RXBD_FLAG_VLAN	BIT(9)
+#define ENETC_RXBD_FLAG_TSTMP	BIT(10)
+
+#define ENETC_MAC_ADDR_FILT_CNT	8 /* # of supported entries per port */
+#define EMETC_MAC_ADDR_FILT_RES	3 /* # of reserved entries at the beginning */
+#define ENETC_MAX_NUM_VFS	2
+
+struct enetc_cbd {
+	union {
+		struct {
+			__le32 addr[2];
+			__le32 opt[4];
+		};
+		__le32 data[6];
+	};
+	__le16 index;
+	__le16 length;
+	u8 cmd;
+	u8 cls;
+	u8 _res;
+	u8 status_flags;
+};
+
+#define ENETC_CBD_FLAGS_SF	BIT(7) /* short format */
+#define ENETC_CBD_STATUS_MASK	0xf
+
+struct enetc_cmd_rfse {
+	u8 smac_h[6];
+	u8 smac_m[6];
+	u8 dmac_h[6];
+	u8 dmac_m[6];
+	u32 sip_h[4];
+	u32 sip_m[4];
+	u32 dip_h[4];
+	u32 dip_m[4];
+	u16 ethtype_h;
+	u16 ethtype_m;
+	u16 ethtype4_h;
+	u16 ethtype4_m;
+	u16 sport_h;
+	u16 sport_m;
+	u16 dport_h;
+	u16 dport_m;
+	u16 vlan_h;
+	u16 vlan_m;
+	u8 proto_h;
+	u8 proto_m;
+	u16 flags;
+	u16 result;
+	u16 mode;
+};
+
+#define ENETC_RFSE_EN	BIT(15)
+#define ENETC_RFSE_MODE_BD	2
+
+static inline void enetc_get_primary_mac_addr(struct enetc_hw *hw, u8 *addr)
+{
+	*(u32 *)addr = __raw_readl(hw->reg + ENETC_SIPMAR0);
+	*(u16 *)(addr + 4) = __raw_readw(hw->reg + ENETC_SIPMAR1);
+}
+
+#define ENETC_SI_INT_IDX	0
+/* base index for Rx/Tx interrupts */
+#define ENETC_BDR_INT_BASE_IDX	1
+
+/* Messaging */
+
+/* Command completion status */
+enum enetc_msg_cmd_status {
+	ENETC_MSG_CMD_STATUS_OK,
+	ENETC_MSG_CMD_STATUS_FAIL
+};
+
+/* VSI-PSI command message types */
+enum enetc_msg_cmd_type {
+	ENETC_MSG_CMD_MNG_MAC = 1, /* manage MAC address */
+	ENETC_MSG_CMD_MNG_RX_MAC_FILTER,/* manage RX MAC table */
+	ENETC_MSG_CMD_MNG_RX_VLAN_FILTER /* manage RX VLAN table */
+};
+
+/* VSI-PSI command action types */
+enum enetc_msg_cmd_action_type {
+	ENETC_MSG_CMD_MNG_ADD = 1,
+	ENETC_MSG_CMD_MNG_REMOVE
+};
+
+/* PSI-VSI command header format */
+struct enetc_msg_cmd_header {
+	u16 type;	/* command class type */
+	u16 id;		/* denotes the specific required action */
+};
+
+/* Common H/W utility functions */
+
+static inline void enetc_enable_rxvlan(struct enetc_hw *hw, int si_idx,
+				       bool en)
+{
+	u32 val = enetc_rxbdr_rd(hw, si_idx, ENETC_RBMR);
+
+	val = (val & ~ENETC_RBMR_VTE) | (en ? ENETC_RBMR_VTE : 0);
+	enetc_rxbdr_wr(hw, si_idx, ENETC_RBMR, val);
+}
+
+static inline void enetc_enable_txvlan(struct enetc_hw *hw, int si_idx,
+				       bool en)
+{
+	u32 val = enetc_txbdr_rd(hw, si_idx, ENETC_TBMR);
+
+	val = (val & ~ENETC_TBMR_VIH) | (en ? ENETC_TBMR_VIH : 0);
+	enetc_txbdr_wr(hw, si_idx, ENETC_TBMR, val);
+}
+
+static inline void enetc_set_bdr_prio(struct enetc_hw *hw, int bdr_idx,
+				      int prio)
+{
+	u32 val = enetc_txbdr_rd(hw, bdr_idx, ENETC_TBMR);
+
+	val &= ~ENETC_TBMR_PRIO_MASK;
+	val |= ENETC_TBMR_SET_PRIO(prio);
+	enetc_txbdr_wr(hw, bdr_idx, ENETC_TBMR, val);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
new file mode 100644
index 000000000000..77b9cd10ba2b
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2019 NXP */
+
+#include <linux/mdio.h>
+#include <linux/of_mdio.h>
+#include <linux/iopoll.h>
+#include <linux/of.h>
+
+#include "enetc_pf.h"
+
+struct enetc_mdio_regs {
+	u32	mdio_cfg;	/* MDIO configuration and status */
+	u32	mdio_ctl;	/* MDIO control */
+	u32	mdio_data;	/* MDIO data */
+	u32	mdio_addr;	/* MDIO address */
+};
+
+#define bus_to_enetc_regs(bus)	(struct enetc_mdio_regs __iomem *)((bus)->priv)
+
+#define ENETC_MDIO_REG_OFFSET	0x1c00
+#define ENETC_MDC_DIV		258
+
+#define MDIO_CFG_CLKDIV(x)	((((x) >> 1) & 0xff) << 8)
+#define MDIO_CFG_BSY		BIT(0)
+#define MDIO_CFG_RD_ER		BIT(1)
+#define MDIO_CFG_ENC45		BIT(6)
+ /* external MDIO only - driven on neg MDC edge */
+#define MDIO_CFG_NEG		BIT(23)
+
+#define MDIO_CTL_DEV_ADDR(x)	((x) & 0x1f)
+#define MDIO_CTL_PORT_ADDR(x)	(((x) & 0x1f) << 5)
+#define MDIO_CTL_READ		BIT(15)
+#define MDIO_DATA(x)		((x) & 0xffff)
+
+#define TIMEOUT	1000
+static int enetc_mdio_wait_complete(struct enetc_mdio_regs __iomem *regs)
+{
+	u32 val;
+
+	return readx_poll_timeout(enetc_rd_reg, &regs->mdio_cfg, val,
+				  !(val & MDIO_CFG_BSY), 10, 10 * TIMEOUT);
+}
+
+static int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum,
+			    u16 value)
+{
+	struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus);
+	u32 mdio_ctl, mdio_cfg;
+	u16 dev_addr;
+	int ret;
+
+	mdio_cfg = MDIO_CFG_CLKDIV(ENETC_MDC_DIV) | MDIO_CFG_NEG;
+	if (regnum & MII_ADDR_C45) {
+		dev_addr = (regnum >> 16) & 0x1f;
+		mdio_cfg |= MDIO_CFG_ENC45;
+	} else {
+		/* clause 22 (ie 1G) */
+		dev_addr = regnum & 0x1f;
+		mdio_cfg &= ~MDIO_CFG_ENC45;
+	}
+
+	enetc_wr_reg(&regs->mdio_cfg, mdio_cfg);
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	/* set port and dev addr */
+	mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr);
+	enetc_wr_reg(&regs->mdio_ctl, mdio_ctl);
+
+	/* set the register address */
+	if (regnum & MII_ADDR_C45) {
+		enetc_wr_reg(&regs->mdio_addr, regnum & 0xffff);
+
+		ret = enetc_mdio_wait_complete(regs);
+		if (ret)
+			return ret;
+	}
+
+	/* write the value */
+	enetc_wr_reg(&regs->mdio_data, MDIO_DATA(value));
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
+{
+	struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus);
+	u32 mdio_ctl, mdio_cfg;
+	u16 dev_addr, value;
+	int ret;
+
+	mdio_cfg = MDIO_CFG_CLKDIV(ENETC_MDC_DIV) | MDIO_CFG_NEG;
+	if (regnum & MII_ADDR_C45) {
+		dev_addr = (regnum >> 16) & 0x1f;
+		mdio_cfg |= MDIO_CFG_ENC45;
+	} else {
+		dev_addr = regnum & 0x1f;
+		mdio_cfg &= ~MDIO_CFG_ENC45;
+	}
+
+	enetc_wr_reg(&regs->mdio_cfg, mdio_cfg);
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	/* set port and device addr */
+	mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr);
+	enetc_wr_reg(&regs->mdio_ctl, mdio_ctl);
+
+	/* set the register address */
+	if (regnum & MII_ADDR_C45) {
+		enetc_wr_reg(&regs->mdio_addr, regnum & 0xffff);
+
+		ret = enetc_mdio_wait_complete(regs);
+		if (ret)
+			return ret;
+	}
+
+	/* initiate the read */
+	enetc_wr_reg(&regs->mdio_ctl, mdio_ctl | MDIO_CTL_READ);
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	/* return all Fs if nothing was there */
+	if (enetc_rd_reg(&regs->mdio_cfg) & MDIO_CFG_RD_ER) {
+		dev_dbg(&bus->dev,
+			"Error while reading PHY%d reg at %d.%hhu\n",
+			phy_id, dev_addr, regnum);
+		return 0xffff;
+	}
+
+	value = enetc_rd_reg(&regs->mdio_data) & 0xffff;
+
+	return value;
+}
+
+int enetc_mdio_probe(struct enetc_pf *pf)
+{
+	struct device *dev = &pf->si->pdev->dev;
+	struct enetc_mdio_regs __iomem *regs;
+	struct device_node *np;
+	struct mii_bus *bus;
+	int ret;
+
+	bus = mdiobus_alloc_size(sizeof(regs));
+	if (!bus)
+		return -ENOMEM;
+
+	bus->name = "Freescale ENETC MDIO Bus";
+	bus->read = enetc_mdio_read;
+	bus->write = enetc_mdio_write;
+	bus->parent = dev;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
+
+	/* store the enetc mdio base address for this bus */
+	regs = pf->si->hw.port + ENETC_MDIO_REG_OFFSET;
+	bus->priv = regs;
+
+	np = of_get_child_by_name(dev->of_node, "mdio");
+	if (!np) {
+		dev_err(dev, "MDIO node missing\n");
+		ret = -EINVAL;
+		goto err_registration;
+	}
+
+	ret = of_mdiobus_register(bus, np);
+	if (ret) {
+		of_node_put(np);
+		dev_err(dev, "cannot register MDIO bus\n");
+		goto err_registration;
+	}
+
+	of_node_put(np);
+	pf->mdio = bus;
+
+	return 0;
+
+err_registration:
+	mdiobus_free(bus);
+
+	return ret;
+}
+
+void enetc_mdio_remove(struct enetc_pf *pf)
+{
+	if (pf->mdio) {
+		mdiobus_unregister(pf->mdio);
+		mdiobus_free(pf->mdio);
+	}
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_msg.c b/drivers/net/ethernet/freescale/enetc/enetc_msg.c
new file mode 100644
index 000000000000..40d22ebe9224
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_msg.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include "enetc_pf.h"
+
+static void enetc_msg_disable_mr_int(struct enetc_hw *hw)
+{
+	u32 psiier = enetc_rd(hw, ENETC_PSIIER);
+	/* disable MR int source(s) */
+	enetc_wr(hw, ENETC_PSIIER, psiier & ~ENETC_PSIIER_MR_MASK);
+}
+
+static void enetc_msg_enable_mr_int(struct enetc_hw *hw)
+{
+	u32 psiier = enetc_rd(hw, ENETC_PSIIER);
+
+	enetc_wr(hw, ENETC_PSIIER, psiier | ENETC_PSIIER_MR_MASK);
+}
+
+static irqreturn_t enetc_msg_psi_msix(int irq, void *data)
+{
+	struct enetc_si *si = (struct enetc_si *)data;
+	struct enetc_pf *pf = enetc_si_priv(si);
+
+	enetc_msg_disable_mr_int(&si->hw);
+	schedule_work(&pf->msg_task);
+
+	return IRQ_HANDLED;
+}
+
+static void enetc_msg_task(struct work_struct *work)
+{
+	struct enetc_pf *pf = container_of(work, struct enetc_pf, msg_task);
+	struct enetc_hw *hw = &pf->si->hw;
+	unsigned long mr_mask;
+	int i;
+
+	for (;;) {
+		mr_mask = enetc_rd(hw, ENETC_PSIMSGRR) & ENETC_PSIMSGRR_MR_MASK;
+		if (!mr_mask) {
+			/* re-arm MR interrupts, w1c the IDR reg */
+			enetc_wr(hw, ENETC_PSIIDR, ENETC_PSIIER_MR_MASK);
+			enetc_msg_enable_mr_int(hw);
+			return;
+		}
+
+		for (i = 0; i < pf->num_vfs; i++) {
+			u32 psimsgrr;
+			u16 msg_code;
+
+			if (!(ENETC_PSIMSGRR_MR(i) & mr_mask))
+				continue;
+
+			enetc_msg_handle_rxmsg(pf, i, &msg_code);
+
+			psimsgrr = ENETC_SIMSGSR_SET_MC(msg_code);
+			psimsgrr |= ENETC_PSIMSGRR_MR(i); /* w1c */
+			enetc_wr(hw, ENETC_PSIMSGRR, psimsgrr);
+		}
+	}
+}
+
+/* Init */
+static int enetc_msg_alloc_mbx(struct enetc_si *si, int idx)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct device *dev = &si->pdev->dev;
+	struct enetc_hw *hw = &si->hw;
+	struct enetc_msg_swbd *msg;
+	u32 val;
+
+	msg = &pf->rxmsg[idx];
+	/* allocate and set receive buffer */
+	msg->size = ENETC_DEFAULT_MSG_SIZE;
+
+	msg->vaddr = dma_alloc_coherent(dev, msg->size, &msg->dma,
+					GFP_KERNEL);
+	if (!msg->vaddr) {
+		dev_err(dev, "msg: fail to alloc dma buffer of size: %d\n",
+			msg->size);
+		return -ENOMEM;
+	}
+
+	/* set multiple of 32 bytes */
+	val = lower_32_bits(msg->dma);
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR0(idx), val);
+	val = upper_32_bits(msg->dma);
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR1(idx), val);
+
+	return 0;
+}
+
+static void enetc_msg_free_mbx(struct enetc_si *si, int idx)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	struct enetc_msg_swbd *msg;
+
+	msg = &pf->rxmsg[idx];
+	dma_free_coherent(&si->pdev->dev, msg->size, msg->vaddr, msg->dma);
+	memset(msg, 0, sizeof(*msg));
+
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR0(idx), 0);
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR1(idx), 0);
+}
+
+int enetc_msg_psi_init(struct enetc_pf *pf)
+{
+	struct enetc_si *si = pf->si;
+	int vector, i, err;
+
+	/* register message passing interrupt handler */
+	snprintf(pf->msg_int_name, sizeof(pf->msg_int_name), "%s-vfmsg",
+		 si->ndev->name);
+	vector = pci_irq_vector(si->pdev, ENETC_SI_INT_IDX);
+	err = request_irq(vector, enetc_msg_psi_msix, 0, pf->msg_int_name, si);
+	if (err) {
+		dev_err(&si->pdev->dev,
+			"PSI messaging: request_irq() failed!\n");
+		return err;
+	}
+
+	/* set one IRQ entry for PSI message receive notification (SI int) */
+	enetc_wr(&si->hw, ENETC_SIMSIVR, ENETC_SI_INT_IDX);
+
+	/* initialize PSI mailbox */
+	INIT_WORK(&pf->msg_task, enetc_msg_task);
+
+	for (i = 0; i < pf->num_vfs; i++) {
+		err = enetc_msg_alloc_mbx(si, i);
+		if (err)
+			goto err_init_mbx;
+	}
+
+	/* enable MR interrupts */
+	enetc_msg_enable_mr_int(&si->hw);
+
+	return 0;
+
+err_init_mbx:
+	for (i--; i >= 0; i--)
+		enetc_msg_free_mbx(si, i);
+
+	free_irq(vector, si);
+
+	return err;
+}
+
+void enetc_msg_psi_free(struct enetc_pf *pf)
+{
+	struct enetc_si *si = pf->si;
+	int i;
+
+	cancel_work_sync(&pf->msg_task);
+
+	/* disable MR interrupts */
+	enetc_msg_disable_mr_int(&si->hw);
+
+	for (i = 0; i < pf->num_vfs; i++)
+		enetc_msg_free_mbx(si, i);
+
+	/* de-register message passing interrupt handler */
+	free_irq(pci_irq_vector(si->pdev, ENETC_SI_INT_IDX), si);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
new file mode 100644
index 000000000000..258b3cb38a6f
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -0,0 +1,945 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include "enetc_pf.h"
+
+#define ENETC_DRV_VER_MAJ 1
+#define ENETC_DRV_VER_MIN 0
+
+#define ENETC_DRV_VER_STR __stringify(ENETC_DRV_VER_MAJ) "." \
+			  __stringify(ENETC_DRV_VER_MIN)
+static const char enetc_drv_ver[] = ENETC_DRV_VER_STR;
+#define ENETC_DRV_NAME_STR "ENETC PF driver"
+static const char enetc_drv_name[] = ENETC_DRV_NAME_STR;
+
+static void enetc_pf_get_primary_mac_addr(struct enetc_hw *hw, int si, u8 *addr)
+{
+	u32 upper = __raw_readl(hw->port + ENETC_PSIPMAR0(si));
+	u16 lower = __raw_readw(hw->port + ENETC_PSIPMAR1(si));
+
+	*(u32 *)addr = upper;
+	*(u16 *)(addr + 4) = lower;
+}
+
+static void enetc_pf_set_primary_mac_addr(struct enetc_hw *hw, int si,
+					  const u8 *addr)
+{
+	u32 upper = *(const u32 *)addr;
+	u16 lower = *(const u16 *)(addr + 4);
+
+	__raw_writel(upper, hw->port + ENETC_PSIPMAR0(si));
+	__raw_writew(lower, hw->port + ENETC_PSIPMAR1(si));
+}
+
+static int enetc_pf_set_mac_addr(struct net_device *ndev, void *addr)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(ndev->dev_addr, saddr->sa_data, ndev->addr_len);
+	enetc_pf_set_primary_mac_addr(&priv->si->hw, 0, saddr->sa_data);
+
+	return 0;
+}
+
+static void enetc_set_vlan_promisc(struct enetc_hw *hw, char si_map)
+{
+	u32 val = enetc_port_rd(hw, ENETC_PSIPVMR);
+
+	val &= ~ENETC_PSIPVMR_SET_VP(ENETC_VLAN_PROMISC_MAP_ALL);
+	enetc_port_wr(hw, ENETC_PSIPVMR, ENETC_PSIPVMR_SET_VP(si_map) | val);
+}
+
+static bool enetc_si_vlan_promisc_is_on(struct enetc_pf *pf, int si_idx)
+{
+	return pf->vlan_promisc_simap & BIT(si_idx);
+}
+
+static bool enetc_vlan_filter_is_on(struct enetc_pf *pf)
+{
+	int i;
+
+	for_each_set_bit(i, pf->active_vlans, VLAN_N_VID)
+		return true;
+
+	return false;
+}
+
+static void enetc_enable_si_vlan_promisc(struct enetc_pf *pf, int si_idx)
+{
+	pf->vlan_promisc_simap |= BIT(si_idx);
+	enetc_set_vlan_promisc(&pf->si->hw, pf->vlan_promisc_simap);
+}
+
+static void enetc_disable_si_vlan_promisc(struct enetc_pf *pf, int si_idx)
+{
+	pf->vlan_promisc_simap &= ~BIT(si_idx);
+	enetc_set_vlan_promisc(&pf->si->hw, pf->vlan_promisc_simap);
+}
+
+static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
+{
+	u32 val = 0;
+
+	if (vlan)
+		val = ENETC_PSIVLAN_EN | ENETC_PSIVLAN_SET_QOS(qos) | vlan;
+
+	enetc_port_wr(hw, ENETC_PSIVLANR(si), val);
+}
+
+static int enetc_mac_addr_hash_idx(const u8 *addr)
+{
+	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
+	u64 mask = 0;
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		mask |= BIT_ULL(i * 6);
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
+
+	return res;
+}
+
+static void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
+{
+	filter->mac_addr_cnt = 0;
+
+	bitmap_zero(filter->mac_hash_table,
+		    ENETC_MADDR_HASH_TBL_SZ);
+}
+
+static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
+					 const unsigned char *addr)
+{
+	/* add exact match addr */
+	ether_addr_copy(filter->mac_addr, addr);
+	filter->mac_addr_cnt++;
+}
+
+static void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+					 const unsigned char *addr)
+{
+	int idx = enetc_mac_addr_hash_idx(addr);
+
+	/* add hash table entry */
+	__set_bit(idx, filter->mac_hash_table);
+	filter->mac_addr_cnt++;
+}
+
+static void enetc_clear_mac_ht_flt(struct enetc_si *si, int si_idx, int type)
+{
+	bool err = si->errata & ENETC_ERR_UCMCSWP;
+
+	if (type == UC) {
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR0(si_idx, err), 0);
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR1(si_idx), 0);
+	} else { /* MC */
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR0(si_idx, err), 0);
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR1(si_idx), 0);
+	}
+}
+
+static void enetc_set_mac_ht_flt(struct enetc_si *si, int si_idx, int type,
+				 u32 *hash)
+{
+	bool err = si->errata & ENETC_ERR_UCMCSWP;
+
+	if (type == UC) {
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR0(si_idx, err), *hash);
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR1(si_idx), *(hash + 1));
+	} else { /* MC */
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR0(si_idx, err), *hash);
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR1(si_idx), *(hash + 1));
+	}
+}
+
+static void enetc_sync_mac_filters(struct enetc_pf *pf)
+{
+	struct enetc_mac_filter *f = pf->mac_filter;
+	struct enetc_si *si = pf->si;
+	int i, pos;
+
+	pos = EMETC_MAC_ADDR_FILT_RES;
+
+	for (i = 0; i < MADDR_TYPE; i++, f++) {
+		bool em = (f->mac_addr_cnt == 1) && (i == UC);
+		bool clear = !f->mac_addr_cnt;
+
+		if (clear) {
+			if (i == UC)
+				enetc_clear_mac_flt_entry(si, pos);
+
+			enetc_clear_mac_ht_flt(si, 0, i);
+			continue;
+		}
+
+		/* exact match filter */
+		if (em) {
+			int err;
+
+			enetc_clear_mac_ht_flt(si, 0, UC);
+
+			err = enetc_set_mac_flt_entry(si, pos, f->mac_addr,
+						      BIT(0));
+			if (!err)
+				continue;
+
+			/* fallback to HT filtering */
+			dev_warn(&si->pdev->dev, "fallback to HT filt (%d)\n",
+				 err);
+		}
+
+		/* hash table filter, clear EM filter for UC entries */
+		if (i == UC)
+			enetc_clear_mac_flt_entry(si, pos);
+
+		enetc_set_mac_ht_flt(si, 0, i, (u32 *)f->mac_hash_table);
+	}
+}
+
+static void enetc_pf_set_rx_mode(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	struct enetc_hw *hw = &priv->si->hw;
+	bool uprom = false, mprom = false;
+	struct enetc_mac_filter *filter;
+	struct netdev_hw_addr *ha;
+	u32 psipmr = 0;
+	bool em;
+
+	if (ndev->flags & IFF_PROMISC) {
+		/* enable promisc mode for SI0 (PF) */
+		psipmr = ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0);
+		uprom = true;
+		mprom = true;
+		/* enable VLAN promisc mode for SI0 */
+		if (!enetc_si_vlan_promisc_is_on(pf, 0))
+			enetc_enable_si_vlan_promisc(pf, 0);
+
+	} else if (ndev->flags & IFF_ALLMULTI) {
+		/* enable multi cast promisc mode for SI0 (PF) */
+		psipmr = ENETC_PSIPMR_SET_MP(0);
+		mprom = true;
+	}
+
+	/* first 2 filter entries belong to PF */
+	if (!uprom) {
+		/* Update unicast filters */
+		filter = &pf->mac_filter[UC];
+		enetc_reset_mac_addr_filter(filter);
+
+		em = (netdev_uc_count(ndev) == 1);
+		netdev_for_each_uc_addr(ha, ndev) {
+			if (em) {
+				enetc_add_mac_addr_em_filter(filter, ha->addr);
+				break;
+			}
+
+			enetc_add_mac_addr_ht_filter(filter, ha->addr);
+		}
+	}
+
+	if (!mprom) {
+		/* Update multicast filters */
+		filter = &pf->mac_filter[MC];
+		enetc_reset_mac_addr_filter(filter);
+
+		netdev_for_each_mc_addr(ha, ndev) {
+			if (!is_multicast_ether_addr(ha->addr))
+				continue;
+
+			enetc_add_mac_addr_ht_filter(filter, ha->addr);
+		}
+	}
+
+	if (!uprom || !mprom)
+		/* update PF entries */
+		enetc_sync_mac_filters(pf);
+
+	psipmr |= enetc_port_rd(hw, ENETC_PSIPMR) &
+		  ~(ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0));
+	enetc_port_wr(hw, ENETC_PSIPMR, psipmr);
+}
+
+static void enetc_set_vlan_ht_filter(struct enetc_hw *hw, int si_idx,
+				     u32 *hash)
+{
+	enetc_port_wr(hw, ENETC_PSIVHFR0(si_idx), *hash);
+	enetc_port_wr(hw, ENETC_PSIVHFR1(si_idx), *(hash + 1));
+}
+
+static int enetc_vid_hash_idx(unsigned int vid)
+{
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
+
+	return res;
+}
+
+static void enetc_sync_vlan_ht_filter(struct enetc_pf *pf, bool rehash)
+{
+	int i;
+
+	if (rehash) {
+		bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
+
+		for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
+			int hidx = enetc_vid_hash_idx(i);
+
+			__set_bit(hidx, pf->vlan_ht_filter);
+		}
+	}
+
+	enetc_set_vlan_ht_filter(&pf->si->hw, 0, (u32 *)pf->vlan_ht_filter);
+}
+
+static int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	int idx;
+
+	if (enetc_si_vlan_promisc_is_on(pf, 0))
+		enetc_disable_si_vlan_promisc(pf, 0);
+
+	__set_bit(vid, pf->active_vlans);
+
+	idx = enetc_vid_hash_idx(vid);
+	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
+		enetc_sync_vlan_ht_filter(pf, false);
+
+	return 0;
+}
+
+static int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+	__clear_bit(vid, pf->active_vlans);
+	enetc_sync_vlan_ht_filter(pf, true);
+
+	if (!enetc_vlan_filter_is_on(pf))
+		enetc_enable_si_vlan_promisc(pf, 0);
+
+	return 0;
+}
+
+static void enetc_set_loopback(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 reg;
+
+	reg = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
+	if (reg & ENETC_PMO_IFM_RG) {
+		/* RGMII mode */
+		reg = (reg & ~ENETC_PM0_IFM_RLP) |
+		      (en ? ENETC_PM0_IFM_RLP : 0);
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, reg);
+	} else {
+		/* assume SGMII mode */
+		reg = enetc_port_rd(hw, ENETC_PM0_CMD_CFG);
+		reg = (reg & ~ENETC_PM0_CMD_XGLP) |
+		      (en ? ENETC_PM0_CMD_XGLP : 0);
+		reg = (reg & ~ENETC_PM0_CMD_PHY_TX_EN) |
+		      (en ? ENETC_PM0_CMD_PHY_TX_EN : 0);
+		enetc_port_wr(hw, ENETC_PM0_CMD_CFG, reg);
+		enetc_port_wr(hw, ENETC_PM1_CMD_CFG, reg);
+	}
+}
+
+static int enetc_pf_set_vf_mac(struct net_device *ndev, int vf, u8 *mac)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	struct enetc_vf_state *vf_state;
+
+	if (vf >= pf->total_vfs)
+		return -EINVAL;
+
+	if (!is_valid_ether_addr(mac))
+		return -EADDRNOTAVAIL;
+
+	vf_state = &pf->vf_state[vf];
+	vf_state->flags |= ENETC_VF_FLAG_PF_SET_MAC;
+	enetc_pf_set_primary_mac_addr(&priv->si->hw, vf + 1, mac);
+	return 0;
+}
+
+static int enetc_pf_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan,
+				u8 qos, __be16 proto)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+	if (priv->si->errata & ENETC_ERR_VLAN_ISOL)
+		return -EOPNOTSUPP;
+
+	if (vf >= pf->total_vfs)
+		return -EINVAL;
+
+	if (proto != htons(ETH_P_8021Q))
+		/* only C-tags supported for now */
+		return -EPROTONOSUPPORT;
+
+	enetc_set_isol_vlan(&priv->si->hw, vf + 1, vlan, qos);
+	return 0;
+}
+
+static int enetc_pf_set_vf_spoofchk(struct net_device *ndev, int vf, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	u32 cfgr;
+
+	if (vf >= pf->total_vfs)
+		return -EINVAL;
+
+	cfgr = enetc_port_rd(&priv->si->hw, ENETC_PSICFGR0(vf + 1));
+	cfgr = (cfgr & ~ENETC_PSICFGR0_ASE) | (en ? ENETC_PSICFGR0_ASE : 0);
+	enetc_port_wr(&priv->si->hw, ENETC_PSICFGR0(vf + 1), cfgr);
+
+	return 0;
+}
+
+static void enetc_port_setup_primary_mac_address(struct enetc_si *si)
+{
+	unsigned char mac_addr[MAX_ADDR_LEN];
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	int i;
+
+	/* check MAC addresses for PF and all VFs, if any is 0 set it ro rand */
+	for (i = 0; i < pf->total_vfs + 1; i++) {
+		enetc_pf_get_primary_mac_addr(hw, i, mac_addr);
+		if (!is_zero_ether_addr(mac_addr))
+			continue;
+		eth_random_addr(mac_addr);
+		dev_info(&si->pdev->dev, "no MAC address specified for SI%d, using %pM\n",
+			 i, mac_addr);
+		enetc_pf_set_primary_mac_addr(hw, i, mac_addr);
+	}
+}
+
+static void enetc_port_assign_rfs_entries(struct enetc_si *si)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	int num_entries, vf_entries, i;
+	u32 val;
+
+	/* split RFS entries between functions */
+	val = enetc_port_rd(hw, ENETC_PRFSCAPR);
+	num_entries = ENETC_PRFSCAPR_GET_NUM_RFS(val);
+	vf_entries = num_entries / (pf->total_vfs + 1);
+
+	for (i = 0; i < pf->total_vfs; i++)
+		enetc_port_wr(hw, ENETC_PSIRFSCFGR(i + 1), vf_entries);
+	enetc_port_wr(hw, ENETC_PSIRFSCFGR(0),
+		      num_entries - vf_entries * pf->total_vfs);
+
+	/* enable RFS on port */
+	enetc_port_wr(hw, ENETC_PRFSMR, ENETC_PRFSMR_RFSE);
+}
+
+static void enetc_port_si_configure(struct enetc_si *si)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	int num_rings, i;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC_PCAPR0);
+	num_rings = min(ENETC_PCAPR0_RXBDR(val), ENETC_PCAPR0_TXBDR(val));
+
+	val = ENETC_PSICFGR0_SET_TXBDR(ENETC_PF_NUM_RINGS);
+	val |= ENETC_PSICFGR0_SET_RXBDR(ENETC_PF_NUM_RINGS);
+
+	if (unlikely(num_rings < ENETC_PF_NUM_RINGS)) {
+		val = ENETC_PSICFGR0_SET_TXBDR(num_rings);
+		val |= ENETC_PSICFGR0_SET_RXBDR(num_rings);
+
+		dev_warn(&si->pdev->dev, "Found %d rings, expected %d!\n",
+			 num_rings, ENETC_PF_NUM_RINGS);
+
+		num_rings = 0;
+	}
+
+	/* Add default one-time settings for SI0 (PF) */
+	val |= ENETC_PSICFGR0_SIVC(ENETC_VLAN_TYPE_C | ENETC_VLAN_TYPE_S);
+
+	enetc_port_wr(hw, ENETC_PSICFGR0(0), val);
+
+	if (num_rings)
+		num_rings -= ENETC_PF_NUM_RINGS;
+
+	/* Configure the SIs for each available VF */
+	val = ENETC_PSICFGR0_SIVC(ENETC_VLAN_TYPE_C | ENETC_VLAN_TYPE_S);
+	val |= ENETC_PSICFGR0_VTE | ENETC_PSICFGR0_SIVIE;
+
+	if (num_rings) {
+		num_rings /= pf->total_vfs;
+		val |= ENETC_PSICFGR0_SET_TXBDR(num_rings);
+		val |= ENETC_PSICFGR0_SET_RXBDR(num_rings);
+	}
+
+	for (i = 0; i < pf->total_vfs; i++)
+		enetc_port_wr(hw, ENETC_PSICFGR0(i + 1), val);
+
+	/* Port level VLAN settings */
+	val = ENETC_PVCLCTR_OVTPIDL(ENETC_VLAN_TYPE_C | ENETC_VLAN_TYPE_S);
+	enetc_port_wr(hw, ENETC_PVCLCTR, val);
+	/* use outer tag for VLAN filtering */
+	enetc_port_wr(hw, ENETC_PSIVLANFMR, ENETC_PSIVLANFMR_VS);
+}
+
+static void enetc_configure_port_mac(struct enetc_hw *hw)
+{
+	enetc_port_wr(hw, ENETC_PM0_MAXFRM,
+		      ENETC_SET_MAXFRM(ENETC_RX_MAXFRM_SIZE));
+
+	enetc_port_wr(hw, ENETC_PTCMSDUR(0), ENETC_MAC_MAXFRM_SIZE);
+	enetc_port_wr(hw, ENETC_PTXMBAR, 2 * ENETC_MAC_MAXFRM_SIZE);
+
+	enetc_port_wr(hw, ENETC_PM0_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN |
+		      ENETC_PM0_CMD_TXP	| ENETC_PM0_PROMISC |
+		      ENETC_PM0_TX_EN | ENETC_PM0_RX_EN);
+
+	enetc_port_wr(hw, ENETC_PM1_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN |
+		      ENETC_PM0_CMD_TXP	| ENETC_PM0_PROMISC |
+		      ENETC_PM0_TX_EN | ENETC_PM0_RX_EN);
+	/* set auto-speed for RGMII */
+	if (enetc_port_rd(hw, ENETC_PM0_IF_MODE) & ENETC_PMO_IFM_RG)
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_RGAUTO);
+	if (enetc_global_rd(hw, ENETC_G_EPFBLPR(1)) == ENETC_G_EPFBLPR1_XGMII)
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_XGMII);
+}
+
+static void enetc_configure_port_pmac(struct enetc_hw *hw)
+{
+	u32 temp;
+
+	/* Set pMAC step lock */
+	temp = enetc_port_rd(hw, ENETC_PFPMR);
+	enetc_port_wr(hw, ENETC_PFPMR,
+		      temp | ENETC_PFPMR_PMACE | ENETC_PFPMR_MWLM);
+
+	temp = enetc_port_rd(hw, ENETC_MMCSR);
+	enetc_port_wr(hw, ENETC_MMCSR, temp | ENETC_MMCSR_ME);
+}
+
+static void enetc_configure_port(struct enetc_pf *pf)
+{
+	u8 hash_key[ENETC_RSSHASH_KEY_SIZE];
+	struct enetc_hw *hw = &pf->si->hw;
+
+	enetc_configure_port_pmac(hw);
+
+	enetc_configure_port_mac(hw);
+
+	enetc_port_si_configure(pf->si);
+
+	/* set up hash key */
+	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
+	enetc_set_rss_key(hw, hash_key);
+
+	/* split up RFS entries */
+	enetc_port_assign_rfs_entries(pf->si);
+
+	/* fix-up primary MAC addresses, if not set already */
+	enetc_port_setup_primary_mac_address(pf->si);
+
+	/* enforce VLAN promisc mode for all SIs */
+	pf->vlan_promisc_simap = ENETC_VLAN_PROMISC_MAP_ALL;
+	enetc_set_vlan_promisc(hw, pf->vlan_promisc_simap);
+
+	enetc_port_wr(hw, ENETC_PSIPMR, 0);
+
+	/* enable port */
+	enetc_port_wr(hw, ENETC_PMR, ENETC_PMR_EN);
+}
+
+/* Messaging */
+static u16 enetc_msg_pf_set_vf_primary_mac_addr(struct enetc_pf *pf,
+						int vf_id)
+{
+	struct enetc_vf_state *vf_state = &pf->vf_state[vf_id];
+	struct enetc_msg_swbd *msg = &pf->rxmsg[vf_id];
+	struct enetc_msg_cmd_set_primary_mac *cmd;
+	struct device *dev = &pf->si->pdev->dev;
+	u16 cmd_id;
+	char *addr;
+
+	cmd = (struct enetc_msg_cmd_set_primary_mac *)msg->vaddr;
+	cmd_id = cmd->header.id;
+	if (cmd_id != ENETC_MSG_CMD_MNG_ADD)
+		return ENETC_MSG_CMD_STATUS_FAIL;
+
+	addr = cmd->mac.sa_data;
+	if (vf_state->flags & ENETC_VF_FLAG_PF_SET_MAC)
+		dev_warn(dev, "Attempt to override PF set mac addr for VF%d\n",
+			 vf_id);
+	else
+		enetc_pf_set_primary_mac_addr(&pf->si->hw, vf_id + 1, addr);
+
+	return ENETC_MSG_CMD_STATUS_OK;
+}
+
+void enetc_msg_handle_rxmsg(struct enetc_pf *pf, int vf_id, u16 *status)
+{
+	struct enetc_msg_swbd *msg = &pf->rxmsg[vf_id];
+	struct device *dev = &pf->si->pdev->dev;
+	struct enetc_msg_cmd_header *cmd_hdr;
+	u16 cmd_type;
+
+	*status = ENETC_MSG_CMD_STATUS_OK;
+	cmd_hdr = (struct enetc_msg_cmd_header *)msg->vaddr;
+	cmd_type = cmd_hdr->type;
+
+	switch (cmd_type) {
+	case ENETC_MSG_CMD_MNG_MAC:
+		*status = enetc_msg_pf_set_vf_primary_mac_addr(pf, vf_id);
+		break;
+	default:
+		dev_err(dev, "command not supported (cmd_type: 0x%x)\n",
+			cmd_type);
+	}
+}
+
+#ifdef CONFIG_PCI_IOV
+static int enetc_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	int err;
+
+	if (!num_vfs) {
+		enetc_msg_psi_free(pf);
+		kfree(pf->vf_state);
+		pf->num_vfs = 0;
+		pci_disable_sriov(pdev);
+	} else {
+		pf->num_vfs = num_vfs;
+
+		pf->vf_state = kcalloc(num_vfs, sizeof(struct enetc_vf_state),
+				       GFP_KERNEL);
+		if (!pf->vf_state) {
+			pf->num_vfs = 0;
+			return -ENOMEM;
+		}
+
+		err = enetc_msg_psi_init(pf);
+		if (err) {
+			dev_err(&pdev->dev, "enetc_msg_psi_init (%d)\n", err);
+			goto err_msg_psi;
+		}
+
+		err = pci_enable_sriov(pdev, num_vfs);
+		if (err) {
+			dev_err(&pdev->dev, "pci_enable_sriov err %d\n", err);
+			goto err_en_sriov;
+		}
+	}
+
+	return num_vfs;
+
+err_en_sriov:
+	enetc_msg_psi_free(pf);
+err_msg_psi:
+	kfree(pf->vf_state);
+	pf->num_vfs = 0;
+
+	return err;
+}
+#else
+#define enetc_sriov_configure(pdev, num_vfs)	(void)0
+#endif
+
+static int enetc_pf_set_features(struct net_device *ndev,
+				 netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
+		enetc_enable_rxvlan(&priv->si->hw, 0,
+				    !!(features & NETIF_F_HW_VLAN_CTAG_RX));
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_TX)
+		enetc_enable_txvlan(&priv->si->hw, 0,
+				    !!(features & NETIF_F_HW_VLAN_CTAG_TX));
+
+	if (changed & NETIF_F_LOOPBACK)
+		enetc_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK));
+
+	return enetc_set_features(ndev, features);
+}
+
+static const struct net_device_ops enetc_ndev_ops = {
+	.ndo_open		= enetc_open,
+	.ndo_stop		= enetc_close,
+	.ndo_start_xmit		= enetc_xmit,
+	.ndo_get_stats		= enetc_get_stats,
+	.ndo_set_mac_address	= enetc_pf_set_mac_addr,
+	.ndo_set_rx_mode	= enetc_pf_set_rx_mode,
+	.ndo_vlan_rx_add_vid	= enetc_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= enetc_vlan_rx_del_vid,
+	.ndo_set_vf_mac		= enetc_pf_set_vf_mac,
+	.ndo_set_vf_vlan	= enetc_pf_set_vf_vlan,
+	.ndo_set_vf_spoofchk	= enetc_pf_set_vf_spoofchk,
+	.ndo_set_features	= enetc_pf_set_features,
+	.ndo_do_ioctl		= enetc_ioctl,
+	.ndo_setup_tc		= enetc_setup_tc,
+};
+
+static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
+				  const struct net_device_ops *ndev_ops)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	SET_NETDEV_DEV(ndev, &si->pdev->dev);
+	priv->ndev = ndev;
+	priv->si = si;
+	priv->dev = &si->pdev->dev;
+	si->ndev = ndev;
+
+	priv->msg_enable = (NETIF_MSG_WOL << 1) - 1;
+	ndev->netdev_ops = ndev_ops;
+	enetc_set_ethtool_ops(ndev);
+	ndev->watchdog_timeo = 5 * HZ;
+	ndev->max_mtu = ENETC_MAX_MTU;
+
+	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+			    NETIF_F_LOOPBACK;
+	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG |
+			 NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			 NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX |
+			 NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	if (si->num_rss)
+		ndev->hw_features |= NETIF_F_RXHASH;
+
+	if (si->errata & ENETC_ERR_TXCSUM) {
+		ndev->hw_features &= ~NETIF_F_HW_CSUM;
+		ndev->features &= ~NETIF_F_HW_CSUM;
+	}
+
+	ndev->priv_flags |= IFF_UNICAST_FLT;
+
+	/* pick up primary MAC address from SI */
+	enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr);
+}
+
+static int enetc_of_get_phy(struct enetc_ndev_priv *priv)
+{
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	struct device_node *np = priv->dev->of_node;
+	int err;
+
+	if (!np) {
+		dev_err(priv->dev, "missing ENETC port node\n");
+		return -ENODEV;
+	}
+
+	priv->phy_node = of_parse_phandle(np, "phy-handle", 0);
+	if (!priv->phy_node) {
+		if (!of_phy_is_fixed_link(np)) {
+			dev_err(priv->dev, "PHY not specified\n");
+			return -ENODEV;
+		}
+
+		err = of_phy_register_fixed_link(np);
+		if (err < 0) {
+			dev_err(priv->dev, "fixed link registration failed\n");
+			return err;
+		}
+
+		priv->phy_node = of_node_get(np);
+	}
+
+	if (!of_phy_is_fixed_link(np)) {
+		err = enetc_mdio_probe(pf);
+		if (err) {
+			of_node_put(priv->phy_node);
+			return err;
+		}
+	}
+
+	priv->if_mode = of_get_phy_mode(np);
+	if (priv->if_mode < 0) {
+		dev_err(priv->dev, "missing phy type\n");
+		of_node_put(priv->phy_node);
+		if (of_phy_is_fixed_link(np))
+			of_phy_deregister_fixed_link(np);
+		else
+			enetc_mdio_remove(pf);
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void enetc_of_put_phy(struct enetc_ndev_priv *priv)
+{
+	struct device_node *np = priv->dev->of_node;
+
+	if (np && of_phy_is_fixed_link(np))
+		of_phy_deregister_fixed_link(np);
+	if (priv->phy_node)
+		of_node_put(priv->phy_node);
+}
+
+static int enetc_pf_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *ent)
+{
+	struct enetc_ndev_priv *priv;
+	struct net_device *ndev;
+	struct enetc_si *si;
+	struct enetc_pf *pf;
+	int err;
+
+	if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) {
+		dev_info(&pdev->dev, "device is disabled, skipping\n");
+		return -ENODEV;
+	}
+
+	err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf));
+	if (err) {
+		dev_err(&pdev->dev, "PCI probing failed\n");
+		return err;
+	}
+
+	si = pci_get_drvdata(pdev);
+	if (!si->hw.port || !si->hw.global) {
+		err = -ENODEV;
+		dev_err(&pdev->dev, "could not map PF space, probing a VF?\n");
+		goto err_map_pf_space;
+	}
+
+	pf = enetc_si_priv(si);
+	pf->si = si;
+	pf->total_vfs = pci_sriov_get_totalvfs(pdev);
+
+	enetc_configure_port(pf);
+
+	enetc_get_si_caps(si);
+
+	ndev = alloc_etherdev_mq(sizeof(*priv), ENETC_MAX_NUM_TXQS);
+	if (!ndev) {
+		err = -ENOMEM;
+		dev_err(&pdev->dev, "netdev creation failed\n");
+		goto err_alloc_netdev;
+	}
+
+	enetc_pf_netdev_setup(si, ndev, &enetc_ndev_ops);
+
+	priv = netdev_priv(ndev);
+
+	enetc_init_si_rings_params(priv);
+
+	err = enetc_alloc_si_resources(priv);
+	if (err) {
+		dev_err(&pdev->dev, "SI resource alloc failed\n");
+		goto err_alloc_si_res;
+	}
+
+	err = enetc_alloc_msix(priv);
+	if (err) {
+		dev_err(&pdev->dev, "MSIX alloc failed\n");
+		goto err_alloc_msix;
+	}
+
+	err = enetc_of_get_phy(priv);
+	if (err)
+		dev_warn(&pdev->dev, "Fallback to PHY-less operation\n");
+
+	err = register_netdev(ndev);
+	if (err)
+		goto err_reg_netdev;
+
+	netif_carrier_off(ndev);
+
+	netif_info(priv, probe, ndev, "%s v%s\n",
+		   enetc_drv_name, enetc_drv_ver);
+
+	return 0;
+
+err_reg_netdev:
+	enetc_of_put_phy(priv);
+	enetc_free_msix(priv);
+err_alloc_msix:
+	enetc_free_si_resources(priv);
+err_alloc_si_res:
+	si->ndev = NULL;
+	free_netdev(ndev);
+err_alloc_netdev:
+err_map_pf_space:
+	enetc_pci_remove(pdev);
+
+	return err;
+}
+
+static void enetc_pf_remove(struct pci_dev *pdev)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_ndev_priv *priv;
+
+	if (pf->num_vfs)
+		enetc_sriov_configure(pdev, 0);
+
+	priv = netdev_priv(si->ndev);
+	netif_info(priv, drv, si->ndev, "%s v%s remove\n",
+		   enetc_drv_name, enetc_drv_ver);
+
+	unregister_netdev(si->ndev);
+
+	enetc_mdio_remove(pf);
+	enetc_of_put_phy(priv);
+
+	enetc_free_msix(priv);
+
+	enetc_free_si_resources(priv);
+
+	free_netdev(si->ndev);
+
+	enetc_pci_remove(pdev);
+}
+
+static const struct pci_device_id enetc_pf_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF) },
+	{ 0, } /* End of table. */
+};
+MODULE_DEVICE_TABLE(pci, enetc_pf_id_table);
+
+static struct pci_driver enetc_pf_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = enetc_pf_id_table,
+	.probe = enetc_pf_probe,
+	.remove = enetc_pf_remove,
+#ifdef CONFIG_PCI_IOV
+	.sriov_configure = enetc_sriov_configure,
+#endif
+};
+module_pci_driver(enetc_pf_driver);
+
+MODULE_DESCRIPTION(ENETC_DRV_NAME_STR);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(ENETC_DRV_VER_STR);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
new file mode 100644
index 000000000000..10dd1b53bb08
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2017-2019 NXP */
+
+#include "enetc.h"
+
+#define ENETC_PF_NUM_RINGS	8
+
+enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
+#define ENETC_MAX_NUM_MAC_FLT	((ENETC_MAX_NUM_VFS + 1) * MADDR_TYPE)
+
+#define ENETC_MADDR_HASH_TBL_SZ	64
+struct enetc_mac_filter {
+	union {
+		char mac_addr[ETH_ALEN];
+		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
+	};
+	int mac_addr_cnt;
+};
+
+#define ENETC_VLAN_HT_SIZE	64
+
+enum enetc_vf_flags {
+	ENETC_VF_FLAG_PF_SET_MAC	= BIT(0),
+};
+
+struct enetc_vf_state {
+	enum enetc_vf_flags flags;
+};
+
+struct enetc_pf {
+	struct enetc_si *si;
+	int num_vfs; /* number of active VFs, after sriov_init */
+	int total_vfs; /* max number of VFs, set for PF at probe */
+	struct enetc_vf_state *vf_state;
+
+	struct enetc_mac_filter mac_filter[ENETC_MAX_NUM_MAC_FLT];
+
+	struct enetc_msg_swbd rxmsg[ENETC_MAX_NUM_VFS];
+	struct work_struct msg_task;
+	char msg_int_name[ENETC_INT_NAME_MAX];
+
+	char vlan_promisc_simap; /* bitmap of SIs in VLAN promisc mode */
+	DECLARE_BITMAP(vlan_ht_filter, ENETC_VLAN_HT_SIZE);
+	DECLARE_BITMAP(active_vlans, VLAN_N_VID);
+
+	struct mii_bus *mdio; /* saved for cleanup */
+};
+
+int enetc_msg_psi_init(struct enetc_pf *pf);
+void enetc_msg_psi_free(struct enetc_pf *pf);
+void enetc_msg_handle_rxmsg(struct enetc_pf *pf, int mbox_id, u16 *status);
+
+/* MDIO */
+int enetc_mdio_probe(struct enetc_pf *pf);
+void enetc_mdio_remove(struct enetc_pf *pf);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c
new file mode 100644
index 000000000000..2fd2586e42bf
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2019 NXP */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/fsl/ptp_qoriq.h>
+
+#include "enetc.h"
+
+int enetc_phc_index = -1;
+EXPORT_SYMBOL(enetc_phc_index);
+
+static struct ptp_clock_info enetc_ptp_caps = {
+	.owner		= THIS_MODULE,
+	.name		= "ENETC PTP clock",
+	.max_adj	= 512000,
+	.n_alarm	= 0,
+	.n_ext_ts	= 2,
+	.n_per_out	= 0,
+	.n_pins		= 0,
+	.pps		= 1,
+	.adjfine	= ptp_qoriq_adjfine,
+	.adjtime	= ptp_qoriq_adjtime,
+	.gettime64	= ptp_qoriq_gettime,
+	.settime64	= ptp_qoriq_settime,
+	.enable		= ptp_qoriq_enable,
+};
+
+static int enetc_ptp_probe(struct pci_dev *pdev,
+			   const struct pci_device_id *ent)
+{
+	struct ptp_qoriq *ptp_qoriq;
+	void __iomem *base;
+	int err, len, n;
+
+	if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) {
+		dev_info(&pdev->dev, "device is disabled, skipping\n");
+		return -ENODEV;
+	}
+
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "device enable failed\n");
+		return err;
+	}
+
+	/* set up for high or low dma */
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev,
+				"DMA configuration failed: 0x%x\n", err);
+			goto err_dma;
+		}
+	}
+
+	err = pci_request_mem_regions(pdev, KBUILD_MODNAME);
+	if (err) {
+		dev_err(&pdev->dev, "pci_request_regions failed err=%d\n", err);
+		goto err_pci_mem_reg;
+	}
+
+	pci_set_master(pdev);
+
+	ptp_qoriq = kzalloc(sizeof(*ptp_qoriq), GFP_KERNEL);
+	if (!ptp_qoriq) {
+		err = -ENOMEM;
+		goto err_alloc_ptp;
+	}
+
+	len = pci_resource_len(pdev, ENETC_BAR_REGS);
+
+	base = ioremap(pci_resource_start(pdev, ENETC_BAR_REGS), len);
+	if (!base) {
+		err = -ENXIO;
+		dev_err(&pdev->dev, "ioremap() failed\n");
+		goto err_ioremap;
+	}
+
+	/* Allocate 1 interrupt */
+	n = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX);
+	if (n != 1) {
+		err = -EPERM;
+		goto err_irq;
+	}
+
+	ptp_qoriq->irq = pci_irq_vector(pdev, 0);
+
+	err = request_irq(ptp_qoriq->irq, ptp_qoriq_isr, 0, DRIVER, ptp_qoriq);
+	if (err) {
+		dev_err(&pdev->dev, "request_irq() failed!\n");
+		goto err_irq;
+	}
+
+	ptp_qoriq->dev = &pdev->dev;
+
+	err = ptp_qoriq_init(ptp_qoriq, base, &enetc_ptp_caps);
+	if (err)
+		goto err_no_clock;
+
+	enetc_phc_index = ptp_qoriq->phc_index;
+	pci_set_drvdata(pdev, ptp_qoriq);
+
+	return 0;
+
+err_no_clock:
+	free_irq(ptp_qoriq->irq, ptp_qoriq);
+err_irq:
+	iounmap(base);
+err_ioremap:
+	kfree(ptp_qoriq);
+err_alloc_ptp:
+	pci_release_mem_regions(pdev);
+err_pci_mem_reg:
+err_dma:
+	pci_disable_device(pdev);
+
+	return err;
+}
+
+static void enetc_ptp_remove(struct pci_dev *pdev)
+{
+	struct ptp_qoriq *ptp_qoriq = pci_get_drvdata(pdev);
+
+	enetc_phc_index = -1;
+	ptp_qoriq_free(ptp_qoriq);
+	kfree(ptp_qoriq);
+
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static const struct pci_device_id enetc_ptp_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PTP) },
+	{ 0, } /* End of table. */
+};
+MODULE_DEVICE_TABLE(pci, enetc_ptp_id_table);
+
+static struct pci_driver enetc_ptp_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = enetc_ptp_id_table,
+	.probe = enetc_ptp_probe,
+	.remove = enetc_ptp_remove,
+};
+module_pci_driver(enetc_ptp_driver);
+
+MODULE_DESCRIPTION("ENETC PTP clock driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
new file mode 100644
index 000000000000..ebd21bf4cfa1
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include <linux/module.h>
+#include "enetc.h"
+
+#define ENETC_DRV_VER_MAJ 1
+#define ENETC_DRV_VER_MIN 0
+
+#define ENETC_DRV_VER_STR __stringify(ENETC_DRV_VER_MAJ) "." \
+			  __stringify(ENETC_DRV_VER_MIN)
+static const char enetc_drv_ver[] = ENETC_DRV_VER_STR;
+#define ENETC_DRV_NAME_STR "ENETC VF driver"
+static const char enetc_drv_name[] = ENETC_DRV_NAME_STR;
+
+/* Messaging */
+static void enetc_msg_vsi_write_msg(struct enetc_hw *hw,
+				    struct enetc_msg_swbd *msg)
+{
+	u32 val;
+
+	val = enetc_vsi_set_msize(msg->size) | lower_32_bits(msg->dma);
+	enetc_wr(hw, ENETC_VSIMSGSNDAR1, upper_32_bits(msg->dma));
+	enetc_wr(hw, ENETC_VSIMSGSNDAR0, val);
+}
+
+static int enetc_msg_vsi_send(struct enetc_si *si, struct enetc_msg_swbd *msg)
+{
+	int timeout = 100;
+	u32 vsimsgsr;
+
+	enetc_msg_vsi_write_msg(&si->hw, msg);
+
+	do {
+		vsimsgsr = enetc_rd(&si->hw, ENETC_VSIMSGSR);
+		if (!(vsimsgsr & ENETC_VSIMSGSR_MB))
+			break;
+
+		usleep_range(1000, 2000);
+	} while (--timeout);
+
+	if (!timeout)
+		return -ETIMEDOUT;
+
+	/* check for message delivery error */
+	if (vsimsgsr & ENETC_VSIMSGSR_MS) {
+		dev_err(&si->pdev->dev, "VSI command execute error: %d\n",
+			ENETC_SIMSGSR_GET_MC(vsimsgsr));
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int enetc_msg_vsi_set_primary_mac_addr(struct enetc_ndev_priv *priv,
+					      struct sockaddr *saddr)
+{
+	struct enetc_msg_cmd_set_primary_mac *cmd;
+	struct enetc_msg_swbd msg;
+	int err;
+
+	msg.size = ALIGN(sizeof(struct enetc_msg_cmd_set_primary_mac), 64);
+	msg.vaddr = dma_alloc_coherent(priv->dev, msg.size, &msg.dma,
+				       GFP_KERNEL);
+	if (!msg.vaddr) {
+		dev_err(priv->dev, "Failed to alloc Tx msg (size: %d)\n",
+			msg.size);
+		return -ENOMEM;
+	}
+
+	cmd = (struct enetc_msg_cmd_set_primary_mac *)msg.vaddr;
+	cmd->header.type = ENETC_MSG_CMD_MNG_MAC;
+	cmd->header.id = ENETC_MSG_CMD_MNG_ADD;
+	memcpy(&cmd->mac, saddr, sizeof(struct sockaddr));
+
+	/* send the command and wait */
+	err = enetc_msg_vsi_send(priv->si, &msg);
+
+	dma_free_coherent(priv->dev, msg.size, msg.vaddr, msg.dma);
+
+	return err;
+}
+
+static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct sockaddr *saddr = addr;
+	int err;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	err = enetc_msg_vsi_set_primary_mac_addr(priv, saddr);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int enetc_vf_set_features(struct net_device *ndev,
+				 netdev_features_t features)
+{
+	return enetc_set_features(ndev, features);
+}
+
+/* Probing/ Init */
+static const struct net_device_ops enetc_ndev_ops = {
+	.ndo_open		= enetc_open,
+	.ndo_stop		= enetc_close,
+	.ndo_start_xmit		= enetc_xmit,
+	.ndo_get_stats		= enetc_get_stats,
+	.ndo_set_mac_address	= enetc_vf_set_mac_addr,
+	.ndo_set_features	= enetc_vf_set_features,
+	.ndo_do_ioctl		= enetc_ioctl,
+	.ndo_setup_tc		= enetc_setup_tc,
+};
+
+static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
+				  const struct net_device_ops *ndev_ops)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	SET_NETDEV_DEV(ndev, &si->pdev->dev);
+	priv->ndev = ndev;
+	priv->si = si;
+	priv->dev = &si->pdev->dev;
+	si->ndev = ndev;
+
+	priv->msg_enable = (NETIF_MSG_IFUP << 1) - 1;
+	ndev->netdev_ops = ndev_ops;
+	enetc_set_ethtool_ops(ndev);
+	ndev->watchdog_timeo = 5 * HZ;
+	ndev->max_mtu = ENETC_MAX_MTU;
+
+	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			    NETIF_F_HW_VLAN_CTAG_TX |
+			    NETIF_F_HW_VLAN_CTAG_RX;
+	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG |
+			 NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			 NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX;
+
+	if (si->num_rss)
+		ndev->hw_features |= NETIF_F_RXHASH;
+
+	if (si->errata & ENETC_ERR_TXCSUM) {
+		ndev->hw_features &= ~NETIF_F_HW_CSUM;
+		ndev->features &= ~NETIF_F_HW_CSUM;
+	}
+
+	/* pick up primary MAC address from SI */
+	enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr);
+}
+
+static int enetc_vf_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *ent)
+{
+	struct enetc_ndev_priv *priv;
+	struct net_device *ndev;
+	struct enetc_si *si;
+	int err;
+
+	err = enetc_pci_probe(pdev, KBUILD_MODNAME, 0);
+	if (err) {
+		dev_err(&pdev->dev, "PCI probing failed\n");
+		return err;
+	}
+
+	si = pci_get_drvdata(pdev);
+
+	enetc_get_si_caps(si);
+
+	ndev = alloc_etherdev_mq(sizeof(*priv), ENETC_MAX_NUM_TXQS);
+	if (!ndev) {
+		err = -ENOMEM;
+		dev_err(&pdev->dev, "netdev creation failed\n");
+		goto err_alloc_netdev;
+	}
+
+	enetc_vf_netdev_setup(si, ndev, &enetc_ndev_ops);
+
+	priv = netdev_priv(ndev);
+
+	enetc_init_si_rings_params(priv);
+
+	err = enetc_alloc_si_resources(priv);
+	if (err) {
+		dev_err(&pdev->dev, "SI resource alloc failed\n");
+		goto err_alloc_si_res;
+	}
+
+	err = enetc_alloc_msix(priv);
+	if (err) {
+		dev_err(&pdev->dev, "MSIX alloc failed\n");
+		goto err_alloc_msix;
+	}
+
+	err = register_netdev(ndev);
+	if (err)
+		goto err_reg_netdev;
+
+	netif_carrier_off(ndev);
+
+	netif_info(priv, probe, ndev, "%s v%s\n",
+		   enetc_drv_name, enetc_drv_ver);
+
+	return 0;
+
+err_reg_netdev:
+	enetc_free_msix(priv);
+err_alloc_msix:
+	enetc_free_si_resources(priv);
+err_alloc_si_res:
+	si->ndev = NULL;
+	free_netdev(ndev);
+err_alloc_netdev:
+	enetc_pci_remove(pdev);
+
+	return err;
+}
+
+static void enetc_vf_remove(struct pci_dev *pdev)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_ndev_priv *priv;
+
+	priv = netdev_priv(si->ndev);
+	netif_info(priv, drv, si->ndev, "%s v%s remove\n",
+		   enetc_drv_name, enetc_drv_ver);
+	unregister_netdev(si->ndev);
+
+	enetc_free_msix(priv);
+
+	enetc_free_si_resources(priv);
+
+	free_netdev(si->ndev);
+
+	enetc_pci_remove(pdev);
+}
+
+static const struct pci_device_id enetc_vf_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_VF) },
+	{ 0, } /* End of table. */
+};
+MODULE_DEVICE_TABLE(pci, enetc_vf_id_table);
+
+static struct pci_driver enetc_vf_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = enetc_vf_id_table,
+	.probe = enetc_vf_probe,
+	.remove = enetc_vf_remove,
+};
+module_pci_driver(enetc_vf_driver);
+
+MODULE_DESCRIPTION(ENETC_DRV_NAME_STR);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(ENETC_DRV_VER_STR);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2370dc204202..9d459ccf251d 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1655,7 +1655,7 @@ static void fec_get_mac(struct net_device *ndev)
 		struct device_node *np = fep->pdev->dev.of_node;
 		if (np) {
 			const char *mac = of_get_mac_address(np);
-			if (mac)
+			if (!IS_ERR(mac))
 				iap = (unsigned char *) mac;
 		}
 	}
@@ -1689,10 +1689,10 @@ static void fec_get_mac(struct net_device *ndev)
 	 */
 	if (!is_valid_ether_addr(iap)) {
 		/* Report it and use a random ethernet address instead */
-		netdev_err(ndev, "Invalid MAC address: %pM\n", iap);
+		dev_err(&fep->pdev->dev, "Invalid MAC address: %pM\n", iap);
 		eth_hw_addr_random(ndev);
-		netdev_info(ndev, "Using random MAC address: %pM\n",
-			    ndev->dev_addr);
+		dev_info(&fep->pdev->dev, "Using random MAC address: %pM\n",
+			 ndev->dev_addr);
 		return;
 	}
 
@@ -1840,13 +1840,9 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 	int ret;
 
 	if (enable) {
-		ret = clk_prepare_enable(fep->clk_ahb);
-		if (ret)
-			return ret;
-
 		ret = clk_prepare_enable(fep->clk_enet_out);
 		if (ret)
-			goto failed_clk_enet_out;
+			return ret;
 
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1866,7 +1862,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 
 		phy_reset_after_clk_enable(ndev->phydev);
 	} else {
-		clk_disable_unprepare(fep->clk_ahb);
 		clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1885,8 +1880,6 @@ failed_clk_ref:
 failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
 }
@@ -2098,6 +2091,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev)
 #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
 	defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
 	defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
+static __u32 fec_enet_register_version = 2;
 static u32 fec_enet_register_offset[] = {
 	FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
 	FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
@@ -2128,6 +2122,7 @@ static u32 fec_enet_register_offset[] = {
 	IEEE_R_FDXFC, IEEE_R_OCTETS_OK
 };
 #else
+static __u32 fec_enet_register_version = 1;
 static u32 fec_enet_register_offset[] = {
 	FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0,
 	FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0,
@@ -2149,6 +2144,8 @@ static void fec_enet_get_regs(struct net_device *ndev,
 	u32 *buf = (u32 *)regbuf;
 	u32 i, off;
 
+	regs->version = fec_enet_register_version;
+
 	memset(buf, 0, regs->len);
 
 	for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
@@ -2449,30 +2446,31 @@ static int
 fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct device *dev = &fep->pdev->dev;
 	unsigned int cycle;
 
 	if (!(fep->quirks & FEC_QUIRK_HAS_COALESCE))
 		return -EOPNOTSUPP;
 
 	if (ec->rx_max_coalesced_frames > 255) {
-		pr_err("Rx coalesced frames exceed hardware limitation\n");
+		dev_err(dev, "Rx coalesced frames exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	if (ec->tx_max_coalesced_frames > 255) {
-		pr_err("Tx coalesced frame exceed hardware limitation\n");
+		dev_err(dev, "Tx coalesced frame exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
 	if (cycle > 0xFFFF) {
-		pr_err("Rx coalesced usec exceed hardware limitation\n");
+		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
 	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
 	if (cycle > 0xFFFF) {
-		pr_err("Rx coalesced usec exceed hardware limitation\n");
+		dev_err(dev, "Rx coalesced usec exceed hardware limitation\n");
 		return -EINVAL;
 	}
 
@@ -3466,6 +3464,9 @@ fec_probe(struct platform_device *pdev)
 	ret = clk_prepare_enable(fep->clk_ipg);
 	if (ret)
 		goto failed_clk_ipg;
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		goto failed_clk_ahb;
 
 	fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
@@ -3473,7 +3474,6 @@ fec_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev,
 				"Failed to enable phy regulator: %d\n", ret);
-			clk_disable_unprepare(fep->clk_ipg);
 			goto failed_regulator;
 		}
 	} else {
@@ -3556,9 +3556,12 @@ failed_init:
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
 failed_reset:
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ahb);
+failed_clk_ahb:
+	clk_disable_unprepare(fep->clk_ipg);
 failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
@@ -3682,6 +3685,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
+	clk_disable_unprepare(fep->clk_ahb);
 	clk_disable_unprepare(fep->clk_ipg);
 
 	return 0;
@@ -3691,8 +3695,20 @@ static int __maybe_unused fec_runtime_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	int ret;
 
-	return clk_prepare_enable(fep->clk_ipg);
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		return ret;
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
+	return 0;
+
+failed_clk_ipg:
+	clk_disable_unprepare(fep->clk_ahb);
+	return ret;
 }
 
 static const struct dev_pm_ops fec_pm_ops = {
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index c1968b3ecec8..30cdb246d020 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -902,8 +902,8 @@ static int mpc52xx_fec_probe(struct platform_device *op)
 	 * First try to read MAC address from DT
 	 */
 	mac_addr = of_get_mac_address(np);
-	if (mac_addr) {
-		memcpy(ndev->dev_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr)) {
+		ether_addr_copy(ndev->dev_addr, mac_addr);
 	} else {
 		struct mpc52xx_fec __iomem *fec = priv->fec;
 
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7e892b1cbd3d..19e2365be7d8 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -617,7 +617,7 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx)
 	fep->ptp_clock = ptp_clock_register(&fep->ptp_caps, &pdev->dev);
 	if (IS_ERR(fep->ptp_clock)) {
 		fep->ptp_clock = NULL;
-		pr_err("ptp_clock_register failed\n");
+		dev_err(&pdev->dev, "ptp_clock_register failed\n");
 	}
 
 	schedule_delayed_work(&fep->time_keep, HZ);
diff --git a/drivers/net/ethernet/freescale/fman/Kconfig b/drivers/net/ethernet/freescale/fman/Kconfig
index dc0850b3b517..0139cb9042ec 100644
--- a/drivers/net/ethernet/freescale/fman/Kconfig
+++ b/drivers/net/ethernet/freescale/fman/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config FSL_FMAN
 	tristate "FMan support"
 	depends on FSL_SOC || ARCH_LAYERSCAPE || COMPILE_TEST
diff --git a/drivers/net/ethernet/freescale/fman/fman_keygen.c b/drivers/net/ethernet/freescale/fman/fman_keygen.c
index f54da3c684d0..e1bdfed16134 100644
--- a/drivers/net/ethernet/freescale/fman/fman_keygen.c
+++ b/drivers/net/ethernet/freescale/fman/fman_keygen.c
@@ -144,7 +144,8 @@
 /* Hash Key extraction fields: */
 #define DEFAULT_HASH_KEY_EXTRACT_FIELDS		\
 	(KG_SCH_KN_IPSRC1 | KG_SCH_KN_IPDST1 | \
-	    KG_SCH_KN_L4PSRC | KG_SCH_KN_L4PDST)
+	 KG_SCH_KN_L4PSRC | KG_SCH_KN_L4PDST | \
+	 KG_SCH_KN_IPSEC_SPI)
 
 /* Default values to be used as hash key in case IPv4 or L4 (TCP, UDP)
  * don't exist in the frame
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 71f4205f14e7..7ab8095db192 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -724,12 +724,12 @@ static int mac_probe(struct platform_device *_of_dev)
 
 	/* Get the MAC address */
 	mac_addr = of_get_mac_address(mac_node);
-	if (!mac_addr) {
+	if (IS_ERR(mac_addr)) {
 		dev_err(dev, "of_get_mac_address(%pOF) failed\n", mac_node);
 		err = -EINVAL;
 		goto _return_of_get_parent;
 	}
-	memcpy(mac_dev->addr, mac_addr, sizeof(mac_dev->addr));
+	ether_addr_copy(mac_dev->addr, mac_addr);
 
 	/* Get the port handles */
 	nph = of_count_phandle_with_args(mac_node, "fsl,fman-ports", NULL);
@@ -855,9 +855,7 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (err < 0)
 		dev_err(dev, "fman_set_mac_active_pause() = %d\n", err);
 
-	dev_info(dev, "FMan MAC address: %02hx:%02hx:%02hx:%02hx:%02hx:%02hx\n",
-		 mac_dev->addr[0], mac_dev->addr[1], mac_dev->addr[2],
-		 mac_dev->addr[3], mac_dev->addr[4], mac_dev->addr[5]);
+	dev_info(dev, "FMan MAC address: %pM\n", mac_dev->addr);
 
 	priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev);
 	if (IS_ERR(priv->eth_dev)) {
diff --git a/drivers/net/ethernet/freescale/fs_enet/Kconfig b/drivers/net/ethernet/freescale/fs_enet/Kconfig
index be92229f2c2a..245d9a68a71f 100644
--- a/drivers/net/ethernet/freescale/fs_enet/Kconfig
+++ b/drivers/net/ethernet/freescale/fs_enet/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config FS_ENET
        tristate "Freescale Ethernet Driver"
        depends on NET_VENDOR_FREESCALE && (CPM1 || CPM2 || PPC_MPC512x)
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 7c548ed535da..5fad73b2e123 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -1014,8 +1014,8 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	spin_lock_init(&fep->tx_lock);
 
 	mac_addr = of_get_mac_address(ofdev->dev.of_node);
-	if (mac_addr)
-		memcpy(ndev->dev_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(ndev->dev_addr, mac_addr);
 
 	ret = fep->ops->allocate_bd(ndev);
 	if (ret)
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 88a396fd242f..c6481bd61239 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Freescale PowerQUICC Ethernet Driver -- MIIM bus implementation
  * Provides Bus interface for MIIM regs
@@ -8,12 +9,6 @@
  * Copyright 2002-2004, 2008-2009 Freescale Semiconductor, Inc.
  *
  * Based on gianfar_mii.c and ucc_geth_mii.c (Li Yang, Kim Phillips)
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 45fcc96be90e..7ea19e173339 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* drivers/net/ethernet/freescale/gianfar.c
  *
  * Gianfar Ethernet Driver
@@ -12,11 +13,6 @@
  * Copyright 2002-2009, 2011-2013 Freescale Semiconductor, Inc.
  * Copyright 2007 MontaVista Software, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  *  Gianfar:  AKA Lambda Draconis, "Dragon"
  *  RA 11 31 24.2
  *  Dec +69 19 52
@@ -872,8 +868,8 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 
 	mac_addr = of_get_mac_address(np);
 
-	if (mac_addr)
-		memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(dev->dev_addr, mac_addr);
 
 	if (model && !strcasecmp(model, "TSEC"))
 		priv->device_flags |= FSL_GIANFAR_DEV_HAS_GIGABIT |
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 8e42c0246611..f2af96349c7b 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/freescale/gianfar.h
  *
@@ -11,11 +12,6 @@
  *
  * Copyright 2002-2009, 2011-2013 Freescale Semiconductor, Inc.
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  *  Still left to do:
  *      -Add support for module parameters
  *	-Add patch for ethtool phys id
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 241325c35cb4..3433b46b90c1 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  drivers/net/ethernet/freescale/gianfar_ethtool.c
  *
@@ -10,10 +11,6 @@
  *  Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com>
  *
  *  Copyright 2003-2006, 2008-2009, 2011 Freescale Semiconductor, Inc.
- *
- *  This software may be used and distributed according to
- *  the terms of the GNU Public License, Version 2, incorporated herein
- *  by reference.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -1492,7 +1489,7 @@ static int gfar_get_ts_info(struct net_device *dev,
 	struct gfar_private *priv = netdev_priv(dev);
 	struct platform_device *ptp_dev;
 	struct device_node *ptp_node;
-	struct qoriq_ptp *ptp = NULL;
+	struct ptp_qoriq *ptp = NULL;
 
 	info->phc_index = -1;
 
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index eb3e65e8868f..f839fa94ebdd 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2006-2009 Freescale Semicondutor, Inc. All rights reserved.
  *
@@ -6,11 +7,6 @@
  *
  * Description:
  * QE UCC Gigabit Ethernet Driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -3910,8 +3906,8 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	}
 
 	mac_addr = of_get_mac_address(np);
-	if (mac_addr)
-		memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(dev->dev_addr, mac_addr);
 
 	ugeth->ug_info = ug_info;
 	ugeth->dev = device;
diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h
index 5da19b440a6a..a86a42131fc7 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.h
+++ b/drivers/net/ethernet/freescale/ucc_geth.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) Freescale Semicondutor, Inc. 2006-2009. All rights reserved.
  *
@@ -9,11 +10,6 @@
  * Changelog:
  * Jun 28, 2006 Li Yang <LeoLi@freescale.com>
  * - Rearrange code and style fixes
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #ifndef __UCC_GETH_H__
 #define __UCC_GETH_H__
diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 0beee2cc2ddd..dfebacf443fc 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2007 Freescale Semiconductor, Inc. All rights reserved.
  *
@@ -8,11 +9,6 @@
  * Limitation:
  * Can only get/set settings of the first queue.
  * Need to re-open the interface manually after changing some parameters.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -252,14 +248,12 @@ uec_set_ringparam(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	if (netif_running(netdev))
+		return -EBUSY;
+
 	ug_info->bdRingLenRx[queue] = ring->rx_pending;
 	ug_info->bdRingLenTx[queue] = ring->tx_pending;
 
-	if (netif_running(netdev)) {
-		/* FIXME: restart automatically */
-		netdev_info(netdev, "Please re-open the interface\n");
-	}
-
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/fujitsu/Kconfig b/drivers/net/ethernet/fujitsu/Kconfig
index faee34e44a35..cee99f20d2c2 100644
--- a/drivers/net/ethernet/fujitsu/Kconfig
+++ b/drivers/net/ethernet/fujitsu/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Fujitsu Network device configuration
 #
diff --git a/drivers/net/ethernet/fujitsu/Makefile b/drivers/net/ethernet/fujitsu/Makefile
index 21561fdcc69f..74feebbf4572 100644
--- a/drivers/net/ethernet/fujitsu/Makefile
+++ b/drivers/net/ethernet/fujitsu/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Fujitsu network device drivers.
 #
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index a69cd19a55ae..1eca0fdb9933 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -547,6 +547,11 @@ static int fmvj18x_get_hwinfo(struct pcmcia_device *link, u_char *node_id)
 	return -1;
 
     base = ioremap(link->resource[2]->start, resource_size(link->resource[2]));
+    if (!base) {
+	    pcmcia_release_window(link, link->resource[2]);
+	    return -ENOMEM;
+    }
+
     pcmcia_map_mem_page(link, link->resource[2], 0);
 
     /*
diff --git a/drivers/net/ethernet/google/Kconfig b/drivers/net/ethernet/google/Kconfig
new file mode 100644
index 000000000000..b8f04d052fda
--- /dev/null
+++ b/drivers/net/ethernet/google/Kconfig
@@ -0,0 +1,27 @@
+#
+# Google network device configuration
+#
+
+config NET_VENDOR_GOOGLE
+	bool "Google Devices"
+	default y
+	help
+	  If you have a network (Ethernet) device belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Google devices. If you say Y, you will be asked
+	  for your specific device in the following questions.
+
+if NET_VENDOR_GOOGLE
+
+config GVE
+	tristate "Google Virtual NIC (gVNIC) support"
+	depends on PCI_MSI
+	help
+	  This driver supports Google Virtual NIC (gVNIC)"
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called gve.
+
+endif #NET_VENDOR_GOOGLE
diff --git a/drivers/net/ethernet/google/Makefile b/drivers/net/ethernet/google/Makefile
new file mode 100644
index 000000000000..402cc3ba1639
--- /dev/null
+++ b/drivers/net/ethernet/google/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Google network device drivers.
+#
+
+obj-$(CONFIG_GVE) += gve/
diff --git a/drivers/net/ethernet/google/gve/Makefile b/drivers/net/ethernet/google/gve/Makefile
new file mode 100644
index 000000000000..3354ce40eb97
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/Makefile
@@ -0,0 +1,4 @@
+# Makefile for the Google virtual Ethernet (gve) driver
+
+obj-$(CONFIG_GVE) += gve.o
+gve-objs := gve_main.o gve_tx.o gve_rx.o gve_ethtool.o gve_adminq.o
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
new file mode 100644
index 000000000000..92372dc43be8
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -0,0 +1,459 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ * Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#ifndef _GVE_H_
+#define _GVE_H_
+
+#include <linux/dma-mapping.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+#include <linux/u64_stats_sync.h>
+#include "gve_desc.h"
+
+#ifndef PCI_VENDOR_ID_GOOGLE
+#define PCI_VENDOR_ID_GOOGLE	0x1ae0
+#endif
+
+#define PCI_DEV_ID_GVNIC	0x0042
+
+#define GVE_REGISTER_BAR	0
+#define GVE_DOORBELL_BAR	2
+
+/* Driver can alloc up to 2 segments for the header and 2 for the payload. */
+#define GVE_TX_MAX_IOVEC	4
+/* 1 for management, 1 for rx, 1 for tx */
+#define GVE_MIN_MSIX 3
+
+/* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
+struct gve_rx_desc_queue {
+	struct gve_rx_desc *desc_ring; /* the descriptor ring */
+	dma_addr_t bus; /* the bus for the desc_ring */
+	u32 cnt; /* free-running total number of completed packets */
+	u32 fill_cnt; /* free-running total number of descriptors posted */
+	u32 mask; /* masks the cnt to the size of the ring */
+	u8 seqno; /* the next expected seqno for this desc*/
+};
+
+/* The page info for a single slot in the RX data queue */
+struct gve_rx_slot_page_info {
+	struct page *page;
+	void *page_address;
+	u32 page_offset; /* offset to write to in page */
+};
+
+/* A list of pages registered with the device during setup and used by a queue
+ * as buffers
+ */
+struct gve_queue_page_list {
+	u32 id; /* unique id */
+	u32 num_entries;
+	struct page **pages; /* list of num_entries pages */
+	dma_addr_t *page_buses; /* the dma addrs of the pages */
+};
+
+/* Each slot in the data ring has a 1:1 mapping to a slot in the desc ring */
+struct gve_rx_data_queue {
+	struct gve_rx_data_slot *data_ring; /* read by NIC */
+	dma_addr_t data_bus; /* dma mapping of the slots */
+	struct gve_rx_slot_page_info *page_info; /* page info of the buffers */
+	struct gve_queue_page_list *qpl; /* qpl assigned to this queue */
+	u32 mask; /* masks the cnt to the size of the ring */
+	u32 cnt; /* free-running total number of completed packets */
+};
+
+struct gve_priv;
+
+/* An RX ring that contains a power-of-two sized desc and data ring. */
+struct gve_rx_ring {
+	struct gve_priv *gve;
+	struct gve_rx_desc_queue desc;
+	struct gve_rx_data_queue data;
+	u64 rbytes; /* free-running bytes received */
+	u64 rpackets; /* free-running packets received */
+	u32 q_num; /* queue index */
+	u32 ntfy_id; /* notification block index */
+	struct gve_queue_resources *q_resources; /* head and tail pointer idx */
+	dma_addr_t q_resources_bus; /* dma address for the queue resources */
+	struct u64_stats_sync statss; /* sync stats for 32bit archs */
+};
+
+/* A TX desc ring entry */
+union gve_tx_desc {
+	struct gve_tx_pkt_desc pkt; /* first desc for a packet */
+	struct gve_tx_seg_desc seg; /* subsequent descs for a packet */
+};
+
+/* Tracks the memory in the fifo occupied by a segment of a packet */
+struct gve_tx_iovec {
+	u32 iov_offset; /* offset into this segment */
+	u32 iov_len; /* length */
+	u32 iov_padding; /* padding associated with this segment */
+};
+
+/* Tracks the memory in the fifo occupied by the skb. Mapped 1:1 to a desc
+ * ring entry but only used for a pkt_desc not a seg_desc
+ */
+struct gve_tx_buffer_state {
+	struct sk_buff *skb; /* skb for this pkt */
+	struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */
+};
+
+/* A TX buffer - each queue has one */
+struct gve_tx_fifo {
+	void *base; /* address of base of FIFO */
+	u32 size; /* total size */
+	atomic_t available; /* how much space is still available */
+	u32 head; /* offset to write at */
+	struct gve_queue_page_list *qpl; /* QPL mapped into this FIFO */
+};
+
+/* A TX ring that contains a power-of-two sized desc ring and a FIFO buffer */
+struct gve_tx_ring {
+	/* Cacheline 0 -- Accessed & dirtied during transmit */
+	struct gve_tx_fifo tx_fifo;
+	u32 req; /* driver tracked head pointer */
+	u32 done; /* driver tracked tail pointer */
+
+	/* Cacheline 1 -- Accessed & dirtied during gve_clean_tx_done */
+	__be32 last_nic_done ____cacheline_aligned; /* NIC tail pointer */
+	u64 pkt_done; /* free-running - total packets completed */
+	u64 bytes_done; /* free-running - total bytes completed */
+
+	/* Cacheline 2 -- Read-mostly fields */
+	union gve_tx_desc *desc ____cacheline_aligned;
+	struct gve_tx_buffer_state *info; /* Maps 1:1 to a desc */
+	struct netdev_queue *netdev_txq;
+	struct gve_queue_resources *q_resources; /* head and tail pointer idx */
+	u32 mask; /* masks req and done down to queue size */
+
+	/* Slow-path fields */
+	u32 q_num ____cacheline_aligned; /* queue idx */
+	u32 stop_queue; /* count of queue stops */
+	u32 wake_queue; /* count of queue wakes */
+	u32 ntfy_id; /* notification block index */
+	dma_addr_t bus; /* dma address of the descr ring */
+	dma_addr_t q_resources_bus; /* dma address of the queue resources */
+	struct u64_stats_sync statss; /* sync stats for 32bit archs */
+} ____cacheline_aligned;
+
+/* Wraps the info for one irq including the napi struct and the queues
+ * associated with that irq.
+ */
+struct gve_notify_block {
+	__be32 irq_db_index; /* idx into Bar2 - set by device, must be 1st */
+	char name[IFNAMSIZ + 16]; /* name registered with the kernel */
+	struct napi_struct napi; /* kernel napi struct for this block */
+	struct gve_priv *priv;
+	struct gve_tx_ring *tx; /* tx rings on this block */
+	struct gve_rx_ring *rx; /* rx rings on this block */
+} ____cacheline_aligned;
+
+/* Tracks allowed and current queue settings */
+struct gve_queue_config {
+	u16 max_queues;
+	u16 num_queues; /* current */
+};
+
+/* Tracks the available and used qpl IDs */
+struct gve_qpl_config {
+	u32 qpl_map_size; /* map memory size */
+	unsigned long *qpl_id_map; /* bitmap of used qpl ids */
+};
+
+struct gve_priv {
+	struct net_device *dev;
+	struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */
+	struct gve_rx_ring *rx; /* array of rx_cfg.num_queues */
+	struct gve_queue_page_list *qpls; /* array of num qpls */
+	struct gve_notify_block *ntfy_blocks; /* array of num_ntfy_blks */
+	dma_addr_t ntfy_block_bus;
+	struct msix_entry *msix_vectors; /* array of num_ntfy_blks + 1 */
+	char mgmt_msix_name[IFNAMSIZ + 16];
+	u32 mgmt_msix_idx;
+	__be32 *counter_array; /* array of num_event_counters */
+	dma_addr_t counter_array_bus;
+
+	u16 num_event_counters;
+	u16 tx_desc_cnt; /* num desc per ring */
+	u16 rx_desc_cnt; /* num desc per ring */
+	u16 tx_pages_per_qpl; /* tx buffer length */
+	u16 rx_pages_per_qpl; /* rx buffer length */
+	u64 max_registered_pages;
+	u64 num_registered_pages; /* num pages registered with NIC */
+	u32 rx_copybreak; /* copy packets smaller than this */
+	u16 default_num_queues; /* default num queues to set up */
+
+	struct gve_queue_config tx_cfg;
+	struct gve_queue_config rx_cfg;
+	struct gve_qpl_config qpl_cfg; /* map used QPL ids */
+	u32 num_ntfy_blks; /* spilt between TX and RX so must be even */
+
+	struct gve_registers __iomem *reg_bar0; /* see gve_register.h */
+	__be32 __iomem *db_bar2; /* "array" of doorbells */
+	u32 msg_enable;	/* level for netif* netdev print macros	*/
+	struct pci_dev *pdev;
+
+	/* metrics */
+	u32 tx_timeo_cnt;
+
+	/* Admin queue - see gve_adminq.h*/
+	union gve_adminq_command *adminq;
+	dma_addr_t adminq_bus_addr;
+	u32 adminq_mask; /* masks prod_cnt to adminq size */
+	u32 adminq_prod_cnt; /* free-running count of AQ cmds executed */
+
+	struct workqueue_struct *gve_wq;
+	struct work_struct service_task;
+	unsigned long service_task_flags;
+	unsigned long state_flags;
+};
+
+enum gve_service_task_flags {
+	GVE_PRIV_FLAGS_DO_RESET			= BIT(1),
+	GVE_PRIV_FLAGS_RESET_IN_PROGRESS	= BIT(2),
+	GVE_PRIV_FLAGS_PROBE_IN_PROGRESS	= BIT(3),
+};
+
+enum gve_state_flags {
+	GVE_PRIV_FLAGS_ADMIN_QUEUE_OK		= BIT(1),
+	GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK	= BIT(2),
+	GVE_PRIV_FLAGS_DEVICE_RINGS_OK		= BIT(3),
+	GVE_PRIV_FLAGS_NAPI_ENABLED		= BIT(4),
+};
+
+static inline bool gve_get_do_reset(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_DO_RESET, &priv->service_task_flags);
+}
+
+static inline void gve_set_do_reset(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_DO_RESET, &priv->service_task_flags);
+}
+
+static inline void gve_clear_do_reset(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_DO_RESET, &priv->service_task_flags);
+}
+
+static inline bool gve_get_reset_in_progress(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_RESET_IN_PROGRESS,
+			&priv->service_task_flags);
+}
+
+static inline void gve_set_reset_in_progress(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_RESET_IN_PROGRESS, &priv->service_task_flags);
+}
+
+static inline void gve_clear_reset_in_progress(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_RESET_IN_PROGRESS, &priv->service_task_flags);
+}
+
+static inline bool gve_get_probe_in_progress(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_PROBE_IN_PROGRESS,
+			&priv->service_task_flags);
+}
+
+static inline void gve_set_probe_in_progress(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_PROBE_IN_PROGRESS, &priv->service_task_flags);
+}
+
+static inline void gve_clear_probe_in_progress(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_PROBE_IN_PROGRESS, &priv->service_task_flags);
+}
+
+static inline bool gve_get_admin_queue_ok(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_ADMIN_QUEUE_OK, &priv->state_flags);
+}
+
+static inline void gve_set_admin_queue_ok(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_ADMIN_QUEUE_OK, &priv->state_flags);
+}
+
+static inline void gve_clear_admin_queue_ok(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_ADMIN_QUEUE_OK, &priv->state_flags);
+}
+
+static inline bool gve_get_device_resources_ok(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK, &priv->state_flags);
+}
+
+static inline void gve_set_device_resources_ok(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK, &priv->state_flags);
+}
+
+static inline void gve_clear_device_resources_ok(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK, &priv->state_flags);
+}
+
+static inline bool gve_get_device_rings_ok(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_DEVICE_RINGS_OK, &priv->state_flags);
+}
+
+static inline void gve_set_device_rings_ok(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_DEVICE_RINGS_OK, &priv->state_flags);
+}
+
+static inline void gve_clear_device_rings_ok(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_DEVICE_RINGS_OK, &priv->state_flags);
+}
+
+static inline bool gve_get_napi_enabled(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_NAPI_ENABLED, &priv->state_flags);
+}
+
+static inline void gve_set_napi_enabled(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_NAPI_ENABLED, &priv->state_flags);
+}
+
+static inline void gve_clear_napi_enabled(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_NAPI_ENABLED, &priv->state_flags);
+}
+
+/* Returns the address of the ntfy_blocks irq doorbell
+ */
+static inline __be32 __iomem *gve_irq_doorbell(struct gve_priv *priv,
+					       struct gve_notify_block *block)
+{
+	return &priv->db_bar2[be32_to_cpu(block->irq_db_index)];
+}
+
+/* Returns the index into ntfy_blocks of the given tx ring's block
+ */
+static inline u32 gve_tx_idx_to_ntfy(struct gve_priv *priv, u32 queue_idx)
+{
+	return queue_idx;
+}
+
+/* Returns the index into ntfy_blocks of the given rx ring's block
+ */
+static inline u32 gve_rx_idx_to_ntfy(struct gve_priv *priv, u32 queue_idx)
+{
+	return (priv->num_ntfy_blks / 2) + queue_idx;
+}
+
+/* Returns the number of tx queue page lists
+ */
+static inline u32 gve_num_tx_qpls(struct gve_priv *priv)
+{
+	return priv->tx_cfg.num_queues;
+}
+
+/* Returns the number of rx queue page lists
+ */
+static inline u32 gve_num_rx_qpls(struct gve_priv *priv)
+{
+	return priv->rx_cfg.num_queues;
+}
+
+/* Returns a pointer to the next available tx qpl in the list of qpls
+ */
+static inline
+struct gve_queue_page_list *gve_assign_tx_qpl(struct gve_priv *priv)
+{
+	int id = find_first_zero_bit(priv->qpl_cfg.qpl_id_map,
+				     priv->qpl_cfg.qpl_map_size);
+
+	/* we are out of tx qpls */
+	if (id >= gve_num_tx_qpls(priv))
+		return NULL;
+
+	set_bit(id, priv->qpl_cfg.qpl_id_map);
+	return &priv->qpls[id];
+}
+
+/* Returns a pointer to the next available rx qpl in the list of qpls
+ */
+static inline
+struct gve_queue_page_list *gve_assign_rx_qpl(struct gve_priv *priv)
+{
+	int id = find_next_zero_bit(priv->qpl_cfg.qpl_id_map,
+				    priv->qpl_cfg.qpl_map_size,
+				    gve_num_tx_qpls(priv));
+
+	/* we are out of rx qpls */
+	if (id == priv->qpl_cfg.qpl_map_size)
+		return NULL;
+
+	set_bit(id, priv->qpl_cfg.qpl_id_map);
+	return &priv->qpls[id];
+}
+
+/* Unassigns the qpl with the given id
+ */
+static inline void gve_unassign_qpl(struct gve_priv *priv, int id)
+{
+	clear_bit(id, priv->qpl_cfg.qpl_id_map);
+}
+
+/* Returns the correct dma direction for tx and rx qpls
+ */
+static inline enum dma_data_direction gve_qpl_dma_dir(struct gve_priv *priv,
+						      int id)
+{
+	if (id < gve_num_tx_qpls(priv))
+		return DMA_TO_DEVICE;
+	else
+		return DMA_FROM_DEVICE;
+}
+
+/* Returns true if the max mtu allows page recycling */
+static inline bool gve_can_recycle_pages(struct net_device *dev)
+{
+	/* We can't recycle the pages if we can't fit a packet into half a
+	 * page.
+	 */
+	return dev->max_mtu <= PAGE_SIZE / 2;
+}
+
+/* buffers */
+int gve_alloc_page(struct device *dev, struct page **page, dma_addr_t *dma,
+		   enum dma_data_direction);
+void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
+		   enum dma_data_direction);
+/* tx handling */
+netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev);
+bool gve_tx_poll(struct gve_notify_block *block, int budget);
+int gve_tx_alloc_rings(struct gve_priv *priv);
+void gve_tx_free_rings(struct gve_priv *priv);
+__be32 gve_tx_load_event_counter(struct gve_priv *priv,
+				 struct gve_tx_ring *tx);
+/* rx handling */
+void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx);
+bool gve_rx_poll(struct gve_notify_block *block, int budget);
+int gve_rx_alloc_rings(struct gve_priv *priv);
+void gve_rx_free_rings(struct gve_priv *priv);
+bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget,
+		       netdev_features_t feat);
+/* Reset */
+void gve_schedule_reset(struct gve_priv *priv);
+int gve_reset(struct gve_priv *priv, bool attempt_teardown);
+int gve_adjust_queues(struct gve_priv *priv,
+		      struct gve_queue_config new_rx_config,
+		      struct gve_queue_config new_tx_config);
+/* exported by ethtool.c */
+extern const struct ethtool_ops gve_ethtool_ops;
+/* needed by ethtool */
+extern const char gve_version_str[];
+#endif /* _GVE_H_ */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
new file mode 100644
index 000000000000..c3ba7baf0107
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/pci.h>
+#include "gve.h"
+#include "gve_adminq.h"
+#include "gve_register.h"
+
+#define GVE_MAX_ADMINQ_RELEASE_CHECK	500
+#define GVE_ADMINQ_SLEEP_LEN		20
+#define GVE_MAX_ADMINQ_EVENT_COUNTER_CHECK	100
+
+int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
+{
+	priv->adminq = dma_alloc_coherent(dev, PAGE_SIZE,
+					  &priv->adminq_bus_addr, GFP_KERNEL);
+	if (unlikely(!priv->adminq))
+		return -ENOMEM;
+
+	priv->adminq_mask = (PAGE_SIZE / sizeof(union gve_adminq_command)) - 1;
+	priv->adminq_prod_cnt = 0;
+
+	/* Setup Admin queue with the device */
+	iowrite32be(priv->adminq_bus_addr / PAGE_SIZE,
+		    &priv->reg_bar0->adminq_pfn);
+
+	gve_set_admin_queue_ok(priv);
+	return 0;
+}
+
+void gve_adminq_release(struct gve_priv *priv)
+{
+	int i = 0;
+
+	/* Tell the device the adminq is leaving */
+	iowrite32be(0x0, &priv->reg_bar0->adminq_pfn);
+	while (ioread32be(&priv->reg_bar0->adminq_pfn)) {
+		/* If this is reached the device is unrecoverable and still
+		 * holding memory. Continue looping to avoid memory corruption,
+		 * but WARN so it is visible what is going on.
+		 */
+		if (i == GVE_MAX_ADMINQ_RELEASE_CHECK)
+			WARN(1, "Unrecoverable platform error!");
+		i++;
+		msleep(GVE_ADMINQ_SLEEP_LEN);
+	}
+	gve_clear_device_rings_ok(priv);
+	gve_clear_device_resources_ok(priv);
+	gve_clear_admin_queue_ok(priv);
+}
+
+void gve_adminq_free(struct device *dev, struct gve_priv *priv)
+{
+	if (!gve_get_admin_queue_ok(priv))
+		return;
+	gve_adminq_release(priv);
+	dma_free_coherent(dev, PAGE_SIZE, priv->adminq, priv->adminq_bus_addr);
+	gve_clear_admin_queue_ok(priv);
+}
+
+static void gve_adminq_kick_cmd(struct gve_priv *priv, u32 prod_cnt)
+{
+	iowrite32be(prod_cnt, &priv->reg_bar0->adminq_doorbell);
+}
+
+static bool gve_adminq_wait_for_cmd(struct gve_priv *priv, u32 prod_cnt)
+{
+	int i;
+
+	for (i = 0; i < GVE_MAX_ADMINQ_EVENT_COUNTER_CHECK; i++) {
+		if (ioread32be(&priv->reg_bar0->adminq_event_counter)
+		    == prod_cnt)
+			return true;
+		msleep(GVE_ADMINQ_SLEEP_LEN);
+	}
+
+	return false;
+}
+
+static int gve_adminq_parse_err(struct device *dev, u32 status)
+{
+	if (status != GVE_ADMINQ_COMMAND_PASSED &&
+	    status != GVE_ADMINQ_COMMAND_UNSET)
+		dev_err(dev, "AQ command failed with status %d\n", status);
+
+	switch (status) {
+	case GVE_ADMINQ_COMMAND_PASSED:
+		return 0;
+	case GVE_ADMINQ_COMMAND_UNSET:
+		dev_err(dev, "parse_aq_err: err and status both unset, this should not be possible.\n");
+		return -EINVAL;
+	case GVE_ADMINQ_COMMAND_ERROR_ABORTED:
+	case GVE_ADMINQ_COMMAND_ERROR_CANCELLED:
+	case GVE_ADMINQ_COMMAND_ERROR_DATALOSS:
+	case GVE_ADMINQ_COMMAND_ERROR_FAILED_PRECONDITION:
+	case GVE_ADMINQ_COMMAND_ERROR_UNAVAILABLE:
+		return -EAGAIN;
+	case GVE_ADMINQ_COMMAND_ERROR_ALREADY_EXISTS:
+	case GVE_ADMINQ_COMMAND_ERROR_INTERNAL_ERROR:
+	case GVE_ADMINQ_COMMAND_ERROR_INVALID_ARGUMENT:
+	case GVE_ADMINQ_COMMAND_ERROR_NOT_FOUND:
+	case GVE_ADMINQ_COMMAND_ERROR_OUT_OF_RANGE:
+	case GVE_ADMINQ_COMMAND_ERROR_UNKNOWN_ERROR:
+		return -EINVAL;
+	case GVE_ADMINQ_COMMAND_ERROR_DEADLINE_EXCEEDED:
+		return -ETIME;
+	case GVE_ADMINQ_COMMAND_ERROR_PERMISSION_DENIED:
+	case GVE_ADMINQ_COMMAND_ERROR_UNAUTHENTICATED:
+		return -EACCES;
+	case GVE_ADMINQ_COMMAND_ERROR_RESOURCE_EXHAUSTED:
+		return -ENOMEM;
+	case GVE_ADMINQ_COMMAND_ERROR_UNIMPLEMENTED:
+		return -ENOTSUPP;
+	default:
+		dev_err(dev, "parse_aq_err: unknown status code %d\n", status);
+		return -EINVAL;
+	}
+}
+
+/* This function is not threadsafe - the caller is responsible for any
+ * necessary locks.
+ */
+int gve_adminq_execute_cmd(struct gve_priv *priv,
+			   union gve_adminq_command *cmd_orig)
+{
+	union gve_adminq_command *cmd;
+	u32 status = 0;
+	u32 prod_cnt;
+
+	cmd = &priv->adminq[priv->adminq_prod_cnt & priv->adminq_mask];
+	priv->adminq_prod_cnt++;
+	prod_cnt = priv->adminq_prod_cnt;
+
+	memcpy(cmd, cmd_orig, sizeof(*cmd_orig));
+
+	gve_adminq_kick_cmd(priv, prod_cnt);
+	if (!gve_adminq_wait_for_cmd(priv, prod_cnt)) {
+		dev_err(&priv->pdev->dev, "AQ command timed out, need to reset AQ\n");
+		return -ENOTRECOVERABLE;
+	}
+
+	memcpy(cmd_orig, cmd, sizeof(*cmd));
+	status = be32_to_cpu(READ_ONCE(cmd->status));
+	return gve_adminq_parse_err(&priv->pdev->dev, status);
+}
+
+/* The device specifies that the management vector can either be the first irq
+ * or the last irq. ntfy_blk_msix_base_idx indicates the first irq assigned to
+ * the ntfy blks. It if is 0 then the management vector is last, if it is 1 then
+ * the management vector is first.
+ *
+ * gve arranges the msix vectors so that the management vector is last.
+ */
+#define GVE_NTFY_BLK_BASE_MSIX_IDX	0
+int gve_adminq_configure_device_resources(struct gve_priv *priv,
+					  dma_addr_t counter_array_bus_addr,
+					  u32 num_counters,
+					  dma_addr_t db_array_bus_addr,
+					  u32 num_ntfy_blks)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_CONFIGURE_DEVICE_RESOURCES);
+	cmd.configure_device_resources =
+		(struct gve_adminq_configure_device_resources) {
+		.counter_array = cpu_to_be64(counter_array_bus_addr),
+		.num_counters = cpu_to_be32(num_counters),
+		.irq_db_addr = cpu_to_be64(db_array_bus_addr),
+		.num_irq_dbs = cpu_to_be32(num_ntfy_blks),
+		.irq_db_stride = cpu_to_be32(sizeof(priv->ntfy_blocks[0])),
+		.ntfy_blk_msix_base_idx =
+					cpu_to_be32(GVE_NTFY_BLK_BASE_MSIX_IDX),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_deconfigure_device_resources(struct gve_priv *priv)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES);
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index)
+{
+	struct gve_tx_ring *tx = &priv->tx[queue_index];
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_TX_QUEUE);
+	cmd.create_tx_queue = (struct gve_adminq_create_tx_queue) {
+		.queue_id = cpu_to_be32(queue_index),
+		.reserved = 0,
+		.queue_resources_addr = cpu_to_be64(tx->q_resources_bus),
+		.tx_ring_addr = cpu_to_be64(tx->bus),
+		.queue_page_list_id = cpu_to_be32(tx->tx_fifo.qpl->id),
+		.ntfy_id = cpu_to_be32(tx->ntfy_id),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index)
+{
+	struct gve_rx_ring *rx = &priv->rx[queue_index];
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE);
+	cmd.create_rx_queue = (struct gve_adminq_create_rx_queue) {
+		.queue_id = cpu_to_be32(queue_index),
+		.index = cpu_to_be32(queue_index),
+		.reserved = 0,
+		.ntfy_id = cpu_to_be32(rx->ntfy_id),
+		.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
+		.rx_desc_ring_addr = cpu_to_be64(rx->desc.bus),
+		.rx_data_ring_addr = cpu_to_be64(rx->data.data_bus),
+		.queue_page_list_id = cpu_to_be32(rx->data.qpl->id),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_TX_QUEUE);
+	cmd.destroy_tx_queue = (struct gve_adminq_destroy_tx_queue) {
+		.queue_id = cpu_to_be32(queue_index),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_RX_QUEUE);
+	cmd.destroy_rx_queue = (struct gve_adminq_destroy_rx_queue) {
+		.queue_id = cpu_to_be32(queue_index),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_describe_device(struct gve_priv *priv)
+{
+	struct gve_device_descriptor *descriptor;
+	union gve_adminq_command cmd;
+	dma_addr_t descriptor_bus;
+	int err = 0;
+	u8 *mac;
+	u16 mtu;
+
+	memset(&cmd, 0, sizeof(cmd));
+	descriptor = dma_alloc_coherent(&priv->pdev->dev, PAGE_SIZE,
+					&descriptor_bus, GFP_KERNEL);
+	if (!descriptor)
+		return -ENOMEM;
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESCRIBE_DEVICE);
+	cmd.describe_device.device_descriptor_addr =
+						cpu_to_be64(descriptor_bus);
+	cmd.describe_device.device_descriptor_version =
+			cpu_to_be32(GVE_ADMINQ_DEVICE_DESCRIPTOR_VERSION);
+	cmd.describe_device.available_length = cpu_to_be32(PAGE_SIZE);
+
+	err = gve_adminq_execute_cmd(priv, &cmd);
+	if (err)
+		goto free_device_descriptor;
+
+	priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
+	if (priv->tx_desc_cnt * sizeof(priv->tx->desc[0]) < PAGE_SIZE) {
+		netif_err(priv, drv, priv->dev, "Tx desc count %d too low\n",
+			  priv->tx_desc_cnt);
+		err = -EINVAL;
+		goto free_device_descriptor;
+	}
+	priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries);
+	if (priv->rx_desc_cnt * sizeof(priv->rx->desc.desc_ring[0])
+	    < PAGE_SIZE ||
+	    priv->rx_desc_cnt * sizeof(priv->rx->data.data_ring[0])
+	    < PAGE_SIZE) {
+		netif_err(priv, drv, priv->dev, "Rx desc count %d too low\n",
+			  priv->rx_desc_cnt);
+		err = -EINVAL;
+		goto free_device_descriptor;
+	}
+	priv->max_registered_pages =
+				be64_to_cpu(descriptor->max_registered_pages);
+	mtu = be16_to_cpu(descriptor->mtu);
+	if (mtu < ETH_MIN_MTU) {
+		netif_err(priv, drv, priv->dev, "MTU %d below minimum MTU\n",
+			  mtu);
+		err = -EINVAL;
+		goto free_device_descriptor;
+	}
+	priv->dev->max_mtu = mtu;
+	priv->num_event_counters = be16_to_cpu(descriptor->counters);
+	ether_addr_copy(priv->dev->dev_addr, descriptor->mac);
+	mac = descriptor->mac;
+	netif_info(priv, drv, priv->dev, "MAC addr: %pM\n", mac);
+	priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl);
+	priv->rx_pages_per_qpl = be16_to_cpu(descriptor->rx_pages_per_qpl);
+	if (priv->rx_pages_per_qpl < priv->rx_desc_cnt) {
+		netif_err(priv, drv, priv->dev, "rx_pages_per_qpl cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n",
+			  priv->rx_pages_per_qpl);
+		priv->rx_desc_cnt = priv->rx_pages_per_qpl;
+	}
+	priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues);
+
+free_device_descriptor:
+	dma_free_coherent(&priv->pdev->dev, sizeof(*descriptor), descriptor,
+			  descriptor_bus);
+	return err;
+}
+
+int gve_adminq_register_page_list(struct gve_priv *priv,
+				  struct gve_queue_page_list *qpl)
+{
+	struct device *hdev = &priv->pdev->dev;
+	u32 num_entries = qpl->num_entries;
+	u32 size = num_entries * sizeof(qpl->page_buses[0]);
+	union gve_adminq_command cmd;
+	dma_addr_t page_list_bus;
+	__be64 *page_list;
+	int err;
+	int i;
+
+	memset(&cmd, 0, sizeof(cmd));
+	page_list = dma_alloc_coherent(hdev, size, &page_list_bus, GFP_KERNEL);
+	if (!page_list)
+		return -ENOMEM;
+
+	for (i = 0; i < num_entries; i++)
+		page_list[i] = cpu_to_be64(qpl->page_buses[i]);
+
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_REGISTER_PAGE_LIST);
+	cmd.reg_page_list = (struct gve_adminq_register_page_list) {
+		.page_list_id = cpu_to_be32(qpl->id),
+		.num_pages = cpu_to_be32(num_entries),
+		.page_address_list_addr = cpu_to_be64(page_list_bus),
+	};
+
+	err = gve_adminq_execute_cmd(priv, &cmd);
+	dma_free_coherent(hdev, size, page_list, page_list_bus);
+	return err;
+}
+
+int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_UNREGISTER_PAGE_LIST);
+	cmd.unreg_page_list = (struct gve_adminq_unregister_page_list) {
+		.page_list_id = cpu_to_be32(page_list_id),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_SET_DRIVER_PARAMETER);
+	cmd.set_driver_param = (struct gve_adminq_set_driver_parameter) {
+		.parameter_type = cpu_to_be32(GVE_SET_PARAM_MTU),
+		.parameter_value = cpu_to_be64(mtu),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
new file mode 100644
index 000000000000..4dfa06edc0f8
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ * Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#ifndef _GVE_ADMINQ_H
+#define _GVE_ADMINQ_H
+
+#include <linux/build_bug.h>
+
+/* Admin queue opcodes */
+enum gve_adminq_opcodes {
+	GVE_ADMINQ_DESCRIBE_DEVICE		= 0x1,
+	GVE_ADMINQ_CONFIGURE_DEVICE_RESOURCES	= 0x2,
+	GVE_ADMINQ_REGISTER_PAGE_LIST		= 0x3,
+	GVE_ADMINQ_UNREGISTER_PAGE_LIST		= 0x4,
+	GVE_ADMINQ_CREATE_TX_QUEUE		= 0x5,
+	GVE_ADMINQ_CREATE_RX_QUEUE		= 0x6,
+	GVE_ADMINQ_DESTROY_TX_QUEUE		= 0x7,
+	GVE_ADMINQ_DESTROY_RX_QUEUE		= 0x8,
+	GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES	= 0x9,
+	GVE_ADMINQ_SET_DRIVER_PARAMETER		= 0xB,
+};
+
+/* Admin queue status codes */
+enum gve_adminq_statuses {
+	GVE_ADMINQ_COMMAND_UNSET			= 0x0,
+	GVE_ADMINQ_COMMAND_PASSED			= 0x1,
+	GVE_ADMINQ_COMMAND_ERROR_ABORTED		= 0xFFFFFFF0,
+	GVE_ADMINQ_COMMAND_ERROR_ALREADY_EXISTS		= 0xFFFFFFF1,
+	GVE_ADMINQ_COMMAND_ERROR_CANCELLED		= 0xFFFFFFF2,
+	GVE_ADMINQ_COMMAND_ERROR_DATALOSS		= 0xFFFFFFF3,
+	GVE_ADMINQ_COMMAND_ERROR_DEADLINE_EXCEEDED	= 0xFFFFFFF4,
+	GVE_ADMINQ_COMMAND_ERROR_FAILED_PRECONDITION	= 0xFFFFFFF5,
+	GVE_ADMINQ_COMMAND_ERROR_INTERNAL_ERROR		= 0xFFFFFFF6,
+	GVE_ADMINQ_COMMAND_ERROR_INVALID_ARGUMENT	= 0xFFFFFFF7,
+	GVE_ADMINQ_COMMAND_ERROR_NOT_FOUND		= 0xFFFFFFF8,
+	GVE_ADMINQ_COMMAND_ERROR_OUT_OF_RANGE		= 0xFFFFFFF9,
+	GVE_ADMINQ_COMMAND_ERROR_PERMISSION_DENIED	= 0xFFFFFFFA,
+	GVE_ADMINQ_COMMAND_ERROR_UNAUTHENTICATED	= 0xFFFFFFFB,
+	GVE_ADMINQ_COMMAND_ERROR_RESOURCE_EXHAUSTED	= 0xFFFFFFFC,
+	GVE_ADMINQ_COMMAND_ERROR_UNAVAILABLE		= 0xFFFFFFFD,
+	GVE_ADMINQ_COMMAND_ERROR_UNIMPLEMENTED		= 0xFFFFFFFE,
+	GVE_ADMINQ_COMMAND_ERROR_UNKNOWN_ERROR		= 0xFFFFFFFF,
+};
+
+#define GVE_ADMINQ_DEVICE_DESCRIPTOR_VERSION 1
+
+/* All AdminQ command structs should be naturally packed. The static_assert
+ * calls make sure this is the case at compile time.
+ */
+
+struct gve_adminq_describe_device {
+	__be64 device_descriptor_addr;
+	__be32 device_descriptor_version;
+	__be32 available_length;
+};
+
+static_assert(sizeof(struct gve_adminq_describe_device) == 16);
+
+struct gve_device_descriptor {
+	__be64 max_registered_pages;
+	__be16 reserved1;
+	__be16 tx_queue_entries;
+	__be16 rx_queue_entries;
+	__be16 default_num_queues;
+	__be16 mtu;
+	__be16 counters;
+	__be16 tx_pages_per_qpl;
+	__be16 rx_pages_per_qpl;
+	u8  mac[ETH_ALEN];
+	__be16 num_device_options;
+	__be16 total_length;
+	u8  reserved2[6];
+};
+
+static_assert(sizeof(struct gve_device_descriptor) == 40);
+
+struct device_option {
+	__be32 option_id;
+	__be32 option_length;
+};
+
+static_assert(sizeof(struct device_option) == 8);
+
+struct gve_adminq_configure_device_resources {
+	__be64 counter_array;
+	__be64 irq_db_addr;
+	__be32 num_counters;
+	__be32 num_irq_dbs;
+	__be32 irq_db_stride;
+	__be32 ntfy_blk_msix_base_idx;
+};
+
+static_assert(sizeof(struct gve_adminq_configure_device_resources) == 32);
+
+struct gve_adminq_register_page_list {
+	__be32 page_list_id;
+	__be32 num_pages;
+	__be64 page_address_list_addr;
+};
+
+static_assert(sizeof(struct gve_adminq_register_page_list) == 16);
+
+struct gve_adminq_unregister_page_list {
+	__be32 page_list_id;
+};
+
+static_assert(sizeof(struct gve_adminq_unregister_page_list) == 4);
+
+struct gve_adminq_create_tx_queue {
+	__be32 queue_id;
+	__be32 reserved;
+	__be64 queue_resources_addr;
+	__be64 tx_ring_addr;
+	__be32 queue_page_list_id;
+	__be32 ntfy_id;
+};
+
+static_assert(sizeof(struct gve_adminq_create_tx_queue) == 32);
+
+struct gve_adminq_create_rx_queue {
+	__be32 queue_id;
+	__be32 index;
+	__be32 reserved;
+	__be32 ntfy_id;
+	__be64 queue_resources_addr;
+	__be64 rx_desc_ring_addr;
+	__be64 rx_data_ring_addr;
+	__be32 queue_page_list_id;
+	u8 padding[4];
+};
+
+static_assert(sizeof(struct gve_adminq_create_rx_queue) == 48);
+
+/* Queue resources that are shared with the device */
+struct gve_queue_resources {
+	union {
+		struct {
+			__be32 db_index;	/* Device -> Guest */
+			__be32 counter_index;	/* Device -> Guest */
+		};
+		u8 reserved[64];
+	};
+};
+
+static_assert(sizeof(struct gve_queue_resources) == 64);
+
+struct gve_adminq_destroy_tx_queue {
+	__be32 queue_id;
+};
+
+static_assert(sizeof(struct gve_adminq_destroy_tx_queue) == 4);
+
+struct gve_adminq_destroy_rx_queue {
+	__be32 queue_id;
+};
+
+static_assert(sizeof(struct gve_adminq_destroy_rx_queue) == 4);
+
+/* GVE Set Driver Parameter Types */
+enum gve_set_driver_param_types {
+	GVE_SET_PARAM_MTU	= 0x1,
+};
+
+struct gve_adminq_set_driver_parameter {
+	__be32 parameter_type;
+	u8 reserved[4];
+	__be64 parameter_value;
+};
+
+static_assert(sizeof(struct gve_adminq_set_driver_parameter) == 16);
+
+union gve_adminq_command {
+	struct {
+		__be32 opcode;
+		__be32 status;
+		union {
+			struct gve_adminq_configure_device_resources
+						configure_device_resources;
+			struct gve_adminq_create_tx_queue create_tx_queue;
+			struct gve_adminq_create_rx_queue create_rx_queue;
+			struct gve_adminq_destroy_tx_queue destroy_tx_queue;
+			struct gve_adminq_destroy_rx_queue destroy_rx_queue;
+			struct gve_adminq_describe_device describe_device;
+			struct gve_adminq_register_page_list reg_page_list;
+			struct gve_adminq_unregister_page_list unreg_page_list;
+			struct gve_adminq_set_driver_parameter set_driver_param;
+		};
+	};
+	u8 reserved[64];
+};
+
+static_assert(sizeof(union gve_adminq_command) == 64);
+
+int gve_adminq_alloc(struct device *dev, struct gve_priv *priv);
+void gve_adminq_free(struct device *dev, struct gve_priv *priv);
+void gve_adminq_release(struct gve_priv *priv);
+int gve_adminq_execute_cmd(struct gve_priv *priv,
+			   union gve_adminq_command *cmd_orig);
+int gve_adminq_describe_device(struct gve_priv *priv);
+int gve_adminq_configure_device_resources(struct gve_priv *priv,
+					  dma_addr_t counter_array_bus_addr,
+					  u32 num_counters,
+					  dma_addr_t db_array_bus_addr,
+					  u32 num_ntfy_blks);
+int gve_adminq_deconfigure_device_resources(struct gve_priv *priv);
+int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_register_page_list(struct gve_priv *priv,
+				  struct gve_queue_page_list *qpl);
+int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id);
+int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu);
+#endif /* _GVE_ADMINQ_H */
diff --git a/drivers/net/ethernet/google/gve/gve_desc.h b/drivers/net/ethernet/google/gve/gve_desc.h
new file mode 100644
index 000000000000..54779871d52e
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_desc.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ * Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+/* GVE Transmit Descriptor formats */
+
+#ifndef _GVE_DESC_H_
+#define _GVE_DESC_H_
+
+#include <linux/build_bug.h>
+
+/* A note on seg_addrs
+ *
+ * Base addresses encoded in seg_addr are not assumed to be physical
+ * addresses. The ring format assumes these come from some linear address
+ * space. This could be physical memory, kernel virtual memory, user virtual
+ * memory. gVNIC uses lists of registered pages. Each queue is assumed
+ * to be associated with a single such linear address space to ensure a
+ * consistent meaning for seg_addrs posted to its rings.
+ */
+
+struct gve_tx_pkt_desc {
+	u8	type_flags;  /* desc type is lower 4 bits, flags upper */
+	u8	l4_csum_offset;  /* relative offset of L4 csum word */
+	u8	l4_hdr_offset;  /* Offset of start of L4 headers in packet */
+	u8	desc_cnt;  /* Total descriptors for this packet */
+	__be16	len;  /* Total length of this packet (in bytes) */
+	__be16	seg_len;  /* Length of this descriptor's segment */
+	__be64	seg_addr;  /* Base address (see note) of this segment */
+} __packed;
+
+struct gve_tx_seg_desc {
+	u8	type_flags;	/* type is lower 4 bits, flags upper	*/
+	u8	l3_offset;	/* TSO: 2 byte units to start of IPH	*/
+	__be16	reserved;
+	__be16	mss;		/* TSO MSS				*/
+	__be16	seg_len;
+	__be64	seg_addr;
+} __packed;
+
+/* GVE Transmit Descriptor Types */
+#define	GVE_TXD_STD		(0x0 << 4) /* Std with Host Address	*/
+#define	GVE_TXD_TSO		(0x1 << 4) /* TSO with Host Address	*/
+#define	GVE_TXD_SEG		(0x2 << 4) /* Seg with Host Address	*/
+
+/* GVE Transmit Descriptor Flags for Std Pkts */
+#define	GVE_TXF_L4CSUM	BIT(0)	/* Need csum offload */
+#define	GVE_TXF_TSTAMP	BIT(2)	/* Timestamp required */
+
+/* GVE Transmit Descriptor Flags for TSO Segs */
+#define	GVE_TXSF_IPV6	BIT(1)	/* IPv6 TSO */
+
+/* GVE Receive Packet Descriptor */
+/* The start of an ethernet packet comes 2 bytes into the rx buffer.
+ * gVNIC adds this padding so that both the DMA and the L3/4 protocol header
+ * access is aligned.
+ */
+#define GVE_RX_PAD 2
+
+struct gve_rx_desc {
+	u8	padding[48];
+	__be32	rss_hash;  /* Receive-side scaling hash (Toeplitz for gVNIC) */
+	__be16	mss;
+	__be16	reserved;  /* Reserved to zero */
+	u8	hdr_len;  /* Header length (L2-L4) including padding */
+	u8	hdr_off;  /* 64-byte-scaled offset into RX_DATA entry */
+	__sum16	csum;  /* 1's-complement partial checksum of L3+ bytes */
+	__be16	len;  /* Length of the received packet */
+	__be16	flags_seq;  /* Flags [15:3] and sequence number [2:0] (1-7) */
+} __packed;
+static_assert(sizeof(struct gve_rx_desc) == 64);
+
+/* As with the Tx ring format, the qpl_offset entries below are offsets into an
+ * ordered list of registered pages.
+ */
+struct gve_rx_data_slot {
+	/* byte offset into the rx registered segment of this slot */
+	__be64 qpl_offset;
+};
+
+/* GVE Recive Packet Descriptor Seq No */
+#define GVE_SEQNO(x) (be16_to_cpu(x) & 0x7)
+
+/* GVE Recive Packet Descriptor Flags */
+#define GVE_RXFLG(x)	cpu_to_be16(1 << (3 + (x)))
+#define	GVE_RXF_FRAG	GVE_RXFLG(3)	/* IP Fragment			*/
+#define	GVE_RXF_IPV4	GVE_RXFLG(4)	/* IPv4				*/
+#define	GVE_RXF_IPV6	GVE_RXFLG(5)	/* IPv6				*/
+#define	GVE_RXF_TCP	GVE_RXFLG(6)	/* TCP Packet			*/
+#define	GVE_RXF_UDP	GVE_RXFLG(7)	/* UDP Packet			*/
+#define	GVE_RXF_ERR	GVE_RXFLG(8)	/* Packet Error Detected	*/
+
+/* GVE IRQ */
+#define GVE_IRQ_ACK	BIT(31)
+#define GVE_IRQ_MASK	BIT(30)
+#define GVE_IRQ_EVENT	BIT(29)
+
+static inline bool gve_needs_rss(__be16 flag)
+{
+	if (flag & GVE_RXF_FRAG)
+		return false;
+	if (flag & (GVE_RXF_IPV4 | GVE_RXF_IPV6))
+		return true;
+	return false;
+}
+
+static inline u8 gve_next_seqno(u8 seq)
+{
+	return (seq + 1) == 8 ? 1 : seq + 1;
+}
+#endif /* _GVE_DESC_H_ */
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
new file mode 100644
index 000000000000..26540b856541
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#include <linux/rtnetlink.h>
+#include "gve.h"
+
+static void gve_get_drvinfo(struct net_device *netdev,
+			    struct ethtool_drvinfo *info)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	strlcpy(info->driver, "gve", sizeof(info->driver));
+	strlcpy(info->version, gve_version_str, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(priv->pdev), sizeof(info->bus_info));
+}
+
+static void gve_set_msglevel(struct net_device *netdev, u32 value)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	priv->msg_enable = value;
+}
+
+static u32 gve_get_msglevel(struct net_device *netdev)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	return priv->msg_enable;
+}
+
+static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = {
+	"rx_packets", "tx_packets", "rx_bytes", "tx_bytes",
+	"rx_dropped", "tx_dropped", "tx_timeouts",
+};
+
+#define GVE_MAIN_STATS_LEN  ARRAY_SIZE(gve_gstrings_main_stats)
+#define NUM_GVE_TX_CNTS	5
+#define NUM_GVE_RX_CNTS	2
+
+static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+	char *s = (char *)data;
+	int i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	memcpy(s, *gve_gstrings_main_stats,
+	       sizeof(gve_gstrings_main_stats));
+	s += sizeof(gve_gstrings_main_stats);
+	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+		snprintf(s, ETH_GSTRING_LEN, "rx_desc_cnt[%u]", i);
+		s += ETH_GSTRING_LEN;
+		snprintf(s, ETH_GSTRING_LEN, "rx_desc_fill_cnt[%u]", i);
+		s += ETH_GSTRING_LEN;
+	}
+	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
+		snprintf(s, ETH_GSTRING_LEN, "tx_req[%u]", i);
+		s += ETH_GSTRING_LEN;
+		snprintf(s, ETH_GSTRING_LEN, "tx_done[%u]", i);
+		s += ETH_GSTRING_LEN;
+		snprintf(s, ETH_GSTRING_LEN, "tx_wake[%u]", i);
+		s += ETH_GSTRING_LEN;
+		snprintf(s, ETH_GSTRING_LEN, "tx_stop[%u]", i);
+		s += ETH_GSTRING_LEN;
+		snprintf(s, ETH_GSTRING_LEN, "tx_event_counter[%u]", i);
+		s += ETH_GSTRING_LEN;
+	}
+}
+
+static int gve_get_sset_count(struct net_device *netdev, int sset)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return GVE_MAIN_STATS_LEN +
+		       (priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS) +
+		       (priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void
+gve_get_ethtool_stats(struct net_device *netdev,
+		      struct ethtool_stats *stats, u64 *data)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+	u64 rx_pkts, rx_bytes, tx_pkts, tx_bytes;
+	unsigned int start;
+	int ring;
+	int i;
+
+	ASSERT_RTNL();
+
+	for (rx_pkts = 0, rx_bytes = 0, ring = 0;
+	     ring < priv->rx_cfg.num_queues; ring++) {
+		if (priv->rx) {
+			do {
+				start =
+				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				rx_pkts += priv->rx[ring].rpackets;
+				rx_bytes += priv->rx[ring].rbytes;
+			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+						       start));
+		}
+	}
+	for (tx_pkts = 0, tx_bytes = 0, ring = 0;
+	     ring < priv->tx_cfg.num_queues; ring++) {
+		if (priv->tx) {
+			do {
+				start =
+				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				tx_pkts += priv->tx[ring].pkt_done;
+				tx_bytes += priv->tx[ring].bytes_done;
+			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+						       start));
+		}
+	}
+
+	i = 0;
+	data[i++] = rx_pkts;
+	data[i++] = tx_pkts;
+	data[i++] = rx_bytes;
+	data[i++] = tx_bytes;
+	/* Skip rx_dropped and tx_dropped */
+	i += 2;
+	data[i++] = priv->tx_timeo_cnt;
+	i = GVE_MAIN_STATS_LEN;
+
+	/* walk RX rings */
+	if (priv->rx) {
+		for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
+			struct gve_rx_ring *rx = &priv->rx[ring];
+
+			data[i++] = rx->desc.cnt;
+			data[i++] = rx->desc.fill_cnt;
+		}
+	} else {
+		i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS;
+	}
+	/* walk TX rings */
+	if (priv->tx) {
+		for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) {
+			struct gve_tx_ring *tx = &priv->tx[ring];
+
+			data[i++] = tx->req;
+			data[i++] = tx->done;
+			data[i++] = tx->wake_queue;
+			data[i++] = tx->stop_queue;
+			data[i++] = be32_to_cpu(gve_tx_load_event_counter(priv,
+									  tx));
+		}
+	} else {
+		i += priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS;
+	}
+}
+
+static void gve_get_channels(struct net_device *netdev,
+			     struct ethtool_channels *cmd)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	cmd->max_rx = priv->rx_cfg.max_queues;
+	cmd->max_tx = priv->tx_cfg.max_queues;
+	cmd->max_other = 0;
+	cmd->max_combined = 0;
+	cmd->rx_count = priv->rx_cfg.num_queues;
+	cmd->tx_count = priv->tx_cfg.num_queues;
+	cmd->other_count = 0;
+	cmd->combined_count = 0;
+}
+
+static int gve_set_channels(struct net_device *netdev,
+			    struct ethtool_channels *cmd)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+	struct gve_queue_config new_tx_cfg = priv->tx_cfg;
+	struct gve_queue_config new_rx_cfg = priv->rx_cfg;
+	struct ethtool_channels old_settings;
+	int new_tx = cmd->tx_count;
+	int new_rx = cmd->rx_count;
+
+	gve_get_channels(netdev, &old_settings);
+
+	/* Changing combined is not allowed allowed */
+	if (cmd->combined_count != old_settings.combined_count)
+		return -EINVAL;
+
+	if (!new_rx || !new_tx)
+		return -EINVAL;
+
+	if (!netif_carrier_ok(netdev)) {
+		priv->tx_cfg.num_queues = new_tx;
+		priv->rx_cfg.num_queues = new_rx;
+		return 0;
+	}
+
+	new_tx_cfg.num_queues = new_tx;
+	new_rx_cfg.num_queues = new_rx;
+
+	return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg);
+}
+
+static void gve_get_ringparam(struct net_device *netdev,
+			      struct ethtool_ringparam *cmd)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	cmd->rx_max_pending = priv->rx_desc_cnt;
+	cmd->tx_max_pending = priv->tx_desc_cnt;
+	cmd->rx_pending = priv->rx_desc_cnt;
+	cmd->tx_pending = priv->tx_desc_cnt;
+}
+
+static int gve_user_reset(struct net_device *netdev, u32 *flags)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	if (*flags == ETH_RESET_ALL) {
+		*flags = 0;
+		return gve_reset(priv, true);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+const struct ethtool_ops gve_ethtool_ops = {
+	.get_drvinfo = gve_get_drvinfo,
+	.get_strings = gve_get_strings,
+	.get_sset_count = gve_get_sset_count,
+	.get_ethtool_stats = gve_get_ethtool_stats,
+	.set_msglevel = gve_set_msglevel,
+	.get_msglevel = gve_get_msglevel,
+	.set_channels = gve_set_channels,
+	.get_channels = gve_get_channels,
+	.get_link = ethtool_op_get_link,
+	.get_ringparam = gve_get_ringparam,
+	.reset = gve_user_reset,
+};
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
new file mode 100644
index 000000000000..24f16e3368cd
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -0,0 +1,1232 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#include <linux/cpumask.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+#include <net/sch_generic.h>
+#include "gve.h"
+#include "gve_adminq.h"
+#include "gve_register.h"
+
+#define GVE_DEFAULT_RX_COPYBREAK	(256)
+
+#define DEFAULT_MSG_LEVEL	(NETIF_MSG_DRV | NETIF_MSG_LINK)
+#define GVE_VERSION		"1.0.0"
+#define GVE_VERSION_PREFIX	"GVE-"
+
+const char gve_version_str[] = GVE_VERSION;
+static const char gve_version_prefix[] = GVE_VERSION_PREFIX;
+
+static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	unsigned int start;
+	int ring;
+
+	if (priv->rx) {
+		for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
+			do {
+				start =
+				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				s->rx_packets += priv->rx[ring].rpackets;
+				s->rx_bytes += priv->rx[ring].rbytes;
+			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+						       start));
+		}
+	}
+	if (priv->tx) {
+		for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) {
+			do {
+				start =
+				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				s->tx_packets += priv->tx[ring].pkt_done;
+				s->tx_bytes += priv->tx[ring].bytes_done;
+			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+						       start));
+		}
+	}
+}
+
+static int gve_alloc_counter_array(struct gve_priv *priv)
+{
+	priv->counter_array =
+		dma_alloc_coherent(&priv->pdev->dev,
+				   priv->num_event_counters *
+				   sizeof(*priv->counter_array),
+				   &priv->counter_array_bus, GFP_KERNEL);
+	if (!priv->counter_array)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void gve_free_counter_array(struct gve_priv *priv)
+{
+	dma_free_coherent(&priv->pdev->dev,
+			  priv->num_event_counters *
+			  sizeof(*priv->counter_array),
+			  priv->counter_array, priv->counter_array_bus);
+	priv->counter_array = NULL;
+}
+
+static irqreturn_t gve_mgmnt_intr(int irq, void *arg)
+{
+	struct gve_priv *priv = arg;
+
+	queue_work(priv->gve_wq, &priv->service_task);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t gve_intr(int irq, void *arg)
+{
+	struct gve_notify_block *block = arg;
+	struct gve_priv *priv = block->priv;
+
+	iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block));
+	napi_schedule_irqoff(&block->napi);
+	return IRQ_HANDLED;
+}
+
+static int gve_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct gve_notify_block *block;
+	__be32 __iomem *irq_doorbell;
+	bool reschedule = false;
+	struct gve_priv *priv;
+
+	block = container_of(napi, struct gve_notify_block, napi);
+	priv = block->priv;
+
+	if (block->tx)
+		reschedule |= gve_tx_poll(block, budget);
+	if (block->rx)
+		reschedule |= gve_rx_poll(block, budget);
+
+	if (reschedule)
+		return budget;
+
+	napi_complete(napi);
+	irq_doorbell = gve_irq_doorbell(priv, block);
+	iowrite32be(GVE_IRQ_ACK | GVE_IRQ_EVENT, irq_doorbell);
+
+	/* Double check we have no extra work.
+	 * Ensure unmask synchronizes with checking for work.
+	 */
+	dma_rmb();
+	if (block->tx)
+		reschedule |= gve_tx_poll(block, -1);
+	if (block->rx)
+		reschedule |= gve_rx_poll(block, -1);
+	if (reschedule && napi_reschedule(napi))
+		iowrite32be(GVE_IRQ_MASK, irq_doorbell);
+
+	return 0;
+}
+
+static int gve_alloc_notify_blocks(struct gve_priv *priv)
+{
+	int num_vecs_requested = priv->num_ntfy_blks + 1;
+	char *name = priv->dev->name;
+	unsigned int active_cpus;
+	int vecs_enabled;
+	int i, j;
+	int err;
+
+	priv->msix_vectors = kvzalloc(num_vecs_requested *
+				      sizeof(*priv->msix_vectors), GFP_KERNEL);
+	if (!priv->msix_vectors)
+		return -ENOMEM;
+	for (i = 0; i < num_vecs_requested; i++)
+		priv->msix_vectors[i].entry = i;
+	vecs_enabled = pci_enable_msix_range(priv->pdev, priv->msix_vectors,
+					     GVE_MIN_MSIX, num_vecs_requested);
+	if (vecs_enabled < 0) {
+		dev_err(&priv->pdev->dev, "Could not enable min msix %d/%d\n",
+			GVE_MIN_MSIX, vecs_enabled);
+		err = vecs_enabled;
+		goto abort_with_msix_vectors;
+	}
+	if (vecs_enabled != num_vecs_requested) {
+		int new_num_ntfy_blks = (vecs_enabled - 1) & ~0x1;
+		int vecs_per_type = new_num_ntfy_blks / 2;
+		int vecs_left = new_num_ntfy_blks % 2;
+
+		priv->num_ntfy_blks = new_num_ntfy_blks;
+		priv->tx_cfg.max_queues = min_t(int, priv->tx_cfg.max_queues,
+						vecs_per_type);
+		priv->rx_cfg.max_queues = min_t(int, priv->rx_cfg.max_queues,
+						vecs_per_type + vecs_left);
+		dev_err(&priv->pdev->dev,
+			"Could not enable desired msix, only enabled %d, adjusting tx max queues to %d, and rx max queues to %d\n",
+			vecs_enabled, priv->tx_cfg.max_queues,
+			priv->rx_cfg.max_queues);
+		if (priv->tx_cfg.num_queues > priv->tx_cfg.max_queues)
+			priv->tx_cfg.num_queues = priv->tx_cfg.max_queues;
+		if (priv->rx_cfg.num_queues > priv->rx_cfg.max_queues)
+			priv->rx_cfg.num_queues = priv->rx_cfg.max_queues;
+	}
+	/* Half the notification blocks go to TX and half to RX */
+	active_cpus = min_t(int, priv->num_ntfy_blks / 2, num_online_cpus());
+
+	/* Setup Management Vector  - the last vector */
+	snprintf(priv->mgmt_msix_name, sizeof(priv->mgmt_msix_name), "%s-mgmnt",
+		 name);
+	err = request_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector,
+			  gve_mgmnt_intr, 0, priv->mgmt_msix_name, priv);
+	if (err) {
+		dev_err(&priv->pdev->dev, "Did not receive management vector.\n");
+		goto abort_with_msix_enabled;
+	}
+	priv->ntfy_blocks =
+		dma_alloc_coherent(&priv->pdev->dev,
+				   priv->num_ntfy_blks *
+				   sizeof(*priv->ntfy_blocks),
+				   &priv->ntfy_block_bus, GFP_KERNEL);
+	if (!priv->ntfy_blocks) {
+		err = -ENOMEM;
+		goto abort_with_mgmt_vector;
+	}
+	/* Setup the other blocks - the first n-1 vectors */
+	for (i = 0; i < priv->num_ntfy_blks; i++) {
+		struct gve_notify_block *block = &priv->ntfy_blocks[i];
+		int msix_idx = i;
+
+		snprintf(block->name, sizeof(block->name), "%s-ntfy-block.%d",
+			 name, i);
+		block->priv = priv;
+		err = request_irq(priv->msix_vectors[msix_idx].vector,
+				  gve_intr, 0, block->name, block);
+		if (err) {
+			dev_err(&priv->pdev->dev,
+				"Failed to receive msix vector %d\n", i);
+			goto abort_with_some_ntfy_blocks;
+		}
+		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
+				      get_cpu_mask(i % active_cpus));
+	}
+	return 0;
+abort_with_some_ntfy_blocks:
+	for (j = 0; j < i; j++) {
+		struct gve_notify_block *block = &priv->ntfy_blocks[j];
+		int msix_idx = j;
+
+		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
+				      NULL);
+		free_irq(priv->msix_vectors[msix_idx].vector, block);
+	}
+	dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks *
+			  sizeof(*priv->ntfy_blocks),
+			  priv->ntfy_blocks, priv->ntfy_block_bus);
+	priv->ntfy_blocks = NULL;
+abort_with_mgmt_vector:
+	free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv);
+abort_with_msix_enabled:
+	pci_disable_msix(priv->pdev);
+abort_with_msix_vectors:
+	kfree(priv->msix_vectors);
+	priv->msix_vectors = NULL;
+	return err;
+}
+
+static void gve_free_notify_blocks(struct gve_priv *priv)
+{
+	int i;
+
+	/* Free the irqs */
+	for (i = 0; i < priv->num_ntfy_blks; i++) {
+		struct gve_notify_block *block = &priv->ntfy_blocks[i];
+		int msix_idx = i;
+
+		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
+				      NULL);
+		free_irq(priv->msix_vectors[msix_idx].vector, block);
+	}
+	dma_free_coherent(&priv->pdev->dev,
+			  priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks),
+			  priv->ntfy_blocks, priv->ntfy_block_bus);
+	priv->ntfy_blocks = NULL;
+	free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv);
+	pci_disable_msix(priv->pdev);
+	kfree(priv->msix_vectors);
+	priv->msix_vectors = NULL;
+}
+
+static int gve_setup_device_resources(struct gve_priv *priv)
+{
+	int err;
+
+	err = gve_alloc_counter_array(priv);
+	if (err)
+		return err;
+	err = gve_alloc_notify_blocks(priv);
+	if (err)
+		goto abort_with_counter;
+	err = gve_adminq_configure_device_resources(priv,
+						    priv->counter_array_bus,
+						    priv->num_event_counters,
+						    priv->ntfy_block_bus,
+						    priv->num_ntfy_blks);
+	if (unlikely(err)) {
+		dev_err(&priv->pdev->dev,
+			"could not setup device_resources: err=%d\n", err);
+		err = -ENXIO;
+		goto abort_with_ntfy_blocks;
+	}
+	gve_set_device_resources_ok(priv);
+	return 0;
+abort_with_ntfy_blocks:
+	gve_free_notify_blocks(priv);
+abort_with_counter:
+	gve_free_counter_array(priv);
+	return err;
+}
+
+static void gve_trigger_reset(struct gve_priv *priv);
+
+static void gve_teardown_device_resources(struct gve_priv *priv)
+{
+	int err;
+
+	/* Tell device its resources are being freed */
+	if (gve_get_device_resources_ok(priv)) {
+		err = gve_adminq_deconfigure_device_resources(priv);
+		if (err) {
+			dev_err(&priv->pdev->dev,
+				"Could not deconfigure device resources: err=%d\n",
+				err);
+			gve_trigger_reset(priv);
+		}
+	}
+	gve_free_counter_array(priv);
+	gve_free_notify_blocks(priv);
+	gve_clear_device_resources_ok(priv);
+}
+
+static void gve_add_napi(struct gve_priv *priv, int ntfy_idx)
+{
+	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+
+	netif_napi_add(priv->dev, &block->napi, gve_napi_poll,
+		       NAPI_POLL_WEIGHT);
+}
+
+static void gve_remove_napi(struct gve_priv *priv, int ntfy_idx)
+{
+	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+
+	netif_napi_del(&block->napi);
+}
+
+static int gve_register_qpls(struct gve_priv *priv)
+{
+	int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv);
+	int err;
+	int i;
+
+	for (i = 0; i < num_qpls; i++) {
+		err = gve_adminq_register_page_list(priv, &priv->qpls[i]);
+		if (err) {
+			netif_err(priv, drv, priv->dev,
+				  "failed to register queue page list %d\n",
+				  priv->qpls[i].id);
+			/* This failure will trigger a reset - no need to clean
+			 * up
+			 */
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int gve_unregister_qpls(struct gve_priv *priv)
+{
+	int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv);
+	int err;
+	int i;
+
+	for (i = 0; i < num_qpls; i++) {
+		err = gve_adminq_unregister_page_list(priv, priv->qpls[i].id);
+		/* This failure will trigger a reset - no need to clean up */
+		if (err) {
+			netif_err(priv, drv, priv->dev,
+				  "Failed to unregister queue page list %d\n",
+				  priv->qpls[i].id);
+			return err;
+		}
+	}
+	return 0;
+}
+
+static int gve_create_rings(struct gve_priv *priv)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
+		err = gve_adminq_create_tx_queue(priv, i);
+		if (err) {
+			netif_err(priv, drv, priv->dev, "failed to create tx queue %d\n",
+				  i);
+			/* This failure will trigger a reset - no need to clean
+			 * up
+			 */
+			return err;
+		}
+		netif_dbg(priv, drv, priv->dev, "created tx queue %d\n", i);
+	}
+	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+		err = gve_adminq_create_rx_queue(priv, i);
+		if (err) {
+			netif_err(priv, drv, priv->dev, "failed to create rx queue %d\n",
+				  i);
+			/* This failure will trigger a reset - no need to clean
+			 * up
+			 */
+			return err;
+		}
+		/* Rx data ring has been prefilled with packet buffers at
+		 * queue allocation time.
+		 * Write the doorbell to provide descriptor slots and packet
+		 * buffers to the NIC.
+		 */
+		gve_rx_write_doorbell(priv, &priv->rx[i]);
+		netif_dbg(priv, drv, priv->dev, "created rx queue %d\n", i);
+	}
+
+	return 0;
+}
+
+static int gve_alloc_rings(struct gve_priv *priv)
+{
+	int ntfy_idx;
+	int err;
+	int i;
+
+	/* Setup tx rings */
+	priv->tx = kvzalloc(priv->tx_cfg.num_queues * sizeof(*priv->tx),
+			    GFP_KERNEL);
+	if (!priv->tx)
+		return -ENOMEM;
+	err = gve_tx_alloc_rings(priv);
+	if (err)
+		goto free_tx;
+	/* Setup rx rings */
+	priv->rx = kvzalloc(priv->rx_cfg.num_queues * sizeof(*priv->rx),
+			    GFP_KERNEL);
+	if (!priv->rx) {
+		err = -ENOMEM;
+		goto free_tx_queue;
+	}
+	err = gve_rx_alloc_rings(priv);
+	if (err)
+		goto free_rx;
+	/* Add tx napi & init sync stats*/
+	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
+		u64_stats_init(&priv->tx[i].statss);
+		ntfy_idx = gve_tx_idx_to_ntfy(priv, i);
+		gve_add_napi(priv, ntfy_idx);
+	}
+	/* Add rx napi  & init sync stats*/
+	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+		u64_stats_init(&priv->rx[i].statss);
+		ntfy_idx = gve_rx_idx_to_ntfy(priv, i);
+		gve_add_napi(priv, ntfy_idx);
+	}
+
+	return 0;
+
+free_rx:
+	kfree(priv->rx);
+	priv->rx = NULL;
+free_tx_queue:
+	gve_tx_free_rings(priv);
+free_tx:
+	kfree(priv->tx);
+	priv->tx = NULL;
+	return err;
+}
+
+static int gve_destroy_rings(struct gve_priv *priv)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
+		err = gve_adminq_destroy_tx_queue(priv, i);
+		if (err) {
+			netif_err(priv, drv, priv->dev,
+				  "failed to destroy tx queue %d\n",
+				  i);
+			/* This failure will trigger a reset - no need to clean
+			 * up
+			 */
+			return err;
+		}
+		netif_dbg(priv, drv, priv->dev, "destroyed tx queue %d\n", i);
+	}
+	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+		err = gve_adminq_destroy_rx_queue(priv, i);
+		if (err) {
+			netif_err(priv, drv, priv->dev,
+				  "failed to destroy rx queue %d\n",
+				  i);
+			/* This failure will trigger a reset - no need to clean
+			 * up
+			 */
+			return err;
+		}
+		netif_dbg(priv, drv, priv->dev, "destroyed rx queue %d\n", i);
+	}
+	return 0;
+}
+
+static void gve_free_rings(struct gve_priv *priv)
+{
+	int ntfy_idx;
+	int i;
+
+	if (priv->tx) {
+		for (i = 0; i < priv->tx_cfg.num_queues; i++) {
+			ntfy_idx = gve_tx_idx_to_ntfy(priv, i);
+			gve_remove_napi(priv, ntfy_idx);
+		}
+		gve_tx_free_rings(priv);
+		kfree(priv->tx);
+		priv->tx = NULL;
+	}
+	if (priv->rx) {
+		for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+			ntfy_idx = gve_rx_idx_to_ntfy(priv, i);
+			gve_remove_napi(priv, ntfy_idx);
+		}
+		gve_rx_free_rings(priv);
+		kfree(priv->rx);
+		priv->rx = NULL;
+	}
+}
+
+int gve_alloc_page(struct device *dev, struct page **page, dma_addr_t *dma,
+		   enum dma_data_direction dir)
+{
+	*page = alloc_page(GFP_KERNEL);
+	if (!*page)
+		return -ENOMEM;
+	*dma = dma_map_page(dev, *page, 0, PAGE_SIZE, dir);
+	if (dma_mapping_error(dev, *dma)) {
+		put_page(*page);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id,
+				     int pages)
+{
+	struct gve_queue_page_list *qpl = &priv->qpls[id];
+	int err;
+	int i;
+
+	if (pages + priv->num_registered_pages > priv->max_registered_pages) {
+		netif_err(priv, drv, priv->dev,
+			  "Reached max number of registered pages %llu > %llu\n",
+			  pages + priv->num_registered_pages,
+			  priv->max_registered_pages);
+		return -EINVAL;
+	}
+
+	qpl->id = id;
+	qpl->num_entries = pages;
+	qpl->pages = kvzalloc(pages * sizeof(*qpl->pages), GFP_KERNEL);
+	/* caller handles clean up */
+	if (!qpl->pages)
+		return -ENOMEM;
+	qpl->page_buses = kvzalloc(pages * sizeof(*qpl->page_buses),
+				   GFP_KERNEL);
+	/* caller handles clean up */
+	if (!qpl->page_buses)
+		return -ENOMEM;
+
+	for (i = 0; i < pages; i++) {
+		err = gve_alloc_page(&priv->pdev->dev, &qpl->pages[i],
+				     &qpl->page_buses[i],
+				     gve_qpl_dma_dir(priv, id));
+		/* caller handles clean up */
+		if (err)
+			return -ENOMEM;
+	}
+	priv->num_registered_pages += pages;
+
+	return 0;
+}
+
+void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
+		   enum dma_data_direction dir)
+{
+	if (!dma_mapping_error(dev, dma))
+		dma_unmap_page(dev, dma, PAGE_SIZE, dir);
+	if (page)
+		put_page(page);
+}
+
+static void gve_free_queue_page_list(struct gve_priv *priv,
+				     int id)
+{
+	struct gve_queue_page_list *qpl = &priv->qpls[id];
+	int i;
+
+	if (!qpl->pages)
+		return;
+	if (!qpl->page_buses)
+		goto free_pages;
+
+	for (i = 0; i < qpl->num_entries; i++)
+		gve_free_page(&priv->pdev->dev, qpl->pages[i],
+			      qpl->page_buses[i], gve_qpl_dma_dir(priv, id));
+
+	kfree(qpl->page_buses);
+free_pages:
+	kfree(qpl->pages);
+	priv->num_registered_pages -= qpl->num_entries;
+}
+
+static int gve_alloc_qpls(struct gve_priv *priv)
+{
+	int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv);
+	int i, j;
+	int err;
+
+	priv->qpls = kvzalloc(num_qpls * sizeof(*priv->qpls), GFP_KERNEL);
+	if (!priv->qpls)
+		return -ENOMEM;
+
+	for (i = 0; i < gve_num_tx_qpls(priv); i++) {
+		err = gve_alloc_queue_page_list(priv, i,
+						priv->tx_pages_per_qpl);
+		if (err)
+			goto free_qpls;
+	}
+	for (; i < num_qpls; i++) {
+		err = gve_alloc_queue_page_list(priv, i,
+						priv->rx_pages_per_qpl);
+		if (err)
+			goto free_qpls;
+	}
+
+	priv->qpl_cfg.qpl_map_size = BITS_TO_LONGS(num_qpls) *
+				     sizeof(unsigned long) * BITS_PER_BYTE;
+	priv->qpl_cfg.qpl_id_map = kvzalloc(BITS_TO_LONGS(num_qpls) *
+					    sizeof(unsigned long), GFP_KERNEL);
+	if (!priv->qpl_cfg.qpl_id_map) {
+		err = -ENOMEM;
+		goto free_qpls;
+	}
+
+	return 0;
+
+free_qpls:
+	for (j = 0; j <= i; j++)
+		gve_free_queue_page_list(priv, j);
+	kfree(priv->qpls);
+	return err;
+}
+
+static void gve_free_qpls(struct gve_priv *priv)
+{
+	int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv);
+	int i;
+
+	kfree(priv->qpl_cfg.qpl_id_map);
+
+	for (i = 0; i < num_qpls; i++)
+		gve_free_queue_page_list(priv, i);
+
+	kfree(priv->qpls);
+}
+
+/* Use this to schedule a reset when the device is capable of continuing
+ * to handle other requests in its current state. If it is not, do a reset
+ * in thread instead.
+ */
+void gve_schedule_reset(struct gve_priv *priv)
+{
+	gve_set_do_reset(priv);
+	queue_work(priv->gve_wq, &priv->service_task);
+}
+
+static void gve_reset_and_teardown(struct gve_priv *priv, bool was_up);
+static int gve_reset_recovery(struct gve_priv *priv, bool was_up);
+static void gve_turndown(struct gve_priv *priv);
+static void gve_turnup(struct gve_priv *priv);
+
+static int gve_open(struct net_device *dev)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	int err;
+
+	err = gve_alloc_qpls(priv);
+	if (err)
+		return err;
+	err = gve_alloc_rings(priv);
+	if (err)
+		goto free_qpls;
+
+	err = netif_set_real_num_tx_queues(dev, priv->tx_cfg.num_queues);
+	if (err)
+		goto free_rings;
+	err = netif_set_real_num_rx_queues(dev, priv->rx_cfg.num_queues);
+	if (err)
+		goto free_rings;
+
+	err = gve_register_qpls(priv);
+	if (err)
+		goto reset;
+	err = gve_create_rings(priv);
+	if (err)
+		goto reset;
+	gve_set_device_rings_ok(priv);
+
+	gve_turnup(priv);
+	netif_carrier_on(dev);
+	return 0;
+
+free_rings:
+	gve_free_rings(priv);
+free_qpls:
+	gve_free_qpls(priv);
+	return err;
+
+reset:
+	/* This must have been called from a reset due to the rtnl lock
+	 * so just return at this point.
+	 */
+	if (gve_get_reset_in_progress(priv))
+		return err;
+	/* Otherwise reset before returning */
+	gve_reset_and_teardown(priv, true);
+	/* if this fails there is nothing we can do so just ignore the return */
+	gve_reset_recovery(priv, false);
+	/* return the original error */
+	return err;
+}
+
+static int gve_close(struct net_device *dev)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	int err;
+
+	netif_carrier_off(dev);
+	if (gve_get_device_rings_ok(priv)) {
+		gve_turndown(priv);
+		err = gve_destroy_rings(priv);
+		if (err)
+			goto err;
+		err = gve_unregister_qpls(priv);
+		if (err)
+			goto err;
+		gve_clear_device_rings_ok(priv);
+	}
+
+	gve_free_rings(priv);
+	gve_free_qpls(priv);
+	return 0;
+
+err:
+	/* This must have been called from a reset due to the rtnl lock
+	 * so just return at this point.
+	 */
+	if (gve_get_reset_in_progress(priv))
+		return err;
+	/* Otherwise reset before returning */
+	gve_reset_and_teardown(priv, true);
+	return gve_reset_recovery(priv, false);
+}
+
+int gve_adjust_queues(struct gve_priv *priv,
+		      struct gve_queue_config new_rx_config,
+		      struct gve_queue_config new_tx_config)
+{
+	int err;
+
+	if (netif_carrier_ok(priv->dev)) {
+		/* To make this process as simple as possible we teardown the
+		 * device, set the new configuration, and then bring the device
+		 * up again.
+		 */
+		err = gve_close(priv->dev);
+		/* we have already tried to reset in close,
+		 * just fail at this point
+		 */
+		if (err)
+			return err;
+		priv->tx_cfg = new_tx_config;
+		priv->rx_cfg = new_rx_config;
+
+		err = gve_open(priv->dev);
+		if (err)
+			goto err;
+
+		return 0;
+	}
+	/* Set the config for the next up. */
+	priv->tx_cfg = new_tx_config;
+	priv->rx_cfg = new_rx_config;
+
+	return 0;
+err:
+	netif_err(priv, drv, priv->dev,
+		  "Adjust queues failed! !!! DISABLING ALL QUEUES !!!\n");
+	gve_turndown(priv);
+	return err;
+}
+
+static void gve_turndown(struct gve_priv *priv)
+{
+	int idx;
+
+	if (netif_carrier_ok(priv->dev))
+		netif_carrier_off(priv->dev);
+
+	if (!gve_get_napi_enabled(priv))
+		return;
+
+	/* Disable napi to prevent more work from coming in */
+	for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) {
+		int ntfy_idx = gve_tx_idx_to_ntfy(priv, idx);
+		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+
+		napi_disable(&block->napi);
+	}
+	for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
+		int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
+		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+
+		napi_disable(&block->napi);
+	}
+
+	/* Stop tx queues */
+	netif_tx_disable(priv->dev);
+
+	gve_clear_napi_enabled(priv);
+}
+
+static void gve_turnup(struct gve_priv *priv)
+{
+	int idx;
+
+	/* Start the tx queues */
+	netif_tx_start_all_queues(priv->dev);
+
+	/* Enable napi and unmask interrupts for all queues */
+	for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) {
+		int ntfy_idx = gve_tx_idx_to_ntfy(priv, idx);
+		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+
+		napi_enable(&block->napi);
+		iowrite32be(0, gve_irq_doorbell(priv, block));
+	}
+	for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
+		int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
+		struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+
+		napi_enable(&block->napi);
+		iowrite32be(0, gve_irq_doorbell(priv, block));
+	}
+
+	gve_set_napi_enabled(priv);
+}
+
+static void gve_tx_timeout(struct net_device *dev)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+
+	gve_schedule_reset(priv);
+	priv->tx_timeo_cnt++;
+}
+
+static const struct net_device_ops gve_netdev_ops = {
+	.ndo_start_xmit		=	gve_tx,
+	.ndo_open		=	gve_open,
+	.ndo_stop		=	gve_close,
+	.ndo_get_stats64	=	gve_get_stats,
+	.ndo_tx_timeout         =       gve_tx_timeout,
+};
+
+static void gve_handle_status(struct gve_priv *priv, u32 status)
+{
+	if (GVE_DEVICE_STATUS_RESET_MASK & status) {
+		dev_info(&priv->pdev->dev, "Device requested reset.\n");
+		gve_set_do_reset(priv);
+	}
+}
+
+static void gve_handle_reset(struct gve_priv *priv)
+{
+	/* A service task will be scheduled at the end of probe to catch any
+	 * resets that need to happen, and we don't want to reset until
+	 * probe is done.
+	 */
+	if (gve_get_probe_in_progress(priv))
+		return;
+
+	if (gve_get_do_reset(priv)) {
+		rtnl_lock();
+		gve_reset(priv, false);
+		rtnl_unlock();
+	}
+}
+
+/* Handle NIC status register changes and reset requests */
+static void gve_service_task(struct work_struct *work)
+{
+	struct gve_priv *priv = container_of(work, struct gve_priv,
+					     service_task);
+
+	gve_handle_status(priv,
+			  ioread32be(&priv->reg_bar0->device_status));
+
+	gve_handle_reset(priv);
+}
+
+static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
+{
+	int num_ntfy;
+	int err;
+
+	/* Set up the adminq */
+	err = gve_adminq_alloc(&priv->pdev->dev, priv);
+	if (err) {
+		dev_err(&priv->pdev->dev,
+			"Failed to alloc admin queue: err=%d\n", err);
+		return err;
+	}
+
+	if (skip_describe_device)
+		goto setup_device;
+
+	/* Get the initial information we need from the device */
+	err = gve_adminq_describe_device(priv);
+	if (err) {
+		dev_err(&priv->pdev->dev,
+			"Could not get device information: err=%d\n", err);
+		goto err;
+	}
+	if (priv->dev->max_mtu > PAGE_SIZE) {
+		priv->dev->max_mtu = PAGE_SIZE;
+		err = gve_adminq_set_mtu(priv, priv->dev->mtu);
+		if (err) {
+			netif_err(priv, drv, priv->dev, "Could not set mtu");
+			goto err;
+		}
+	}
+	priv->dev->mtu = priv->dev->max_mtu;
+	num_ntfy = pci_msix_vec_count(priv->pdev);
+	if (num_ntfy <= 0) {
+		dev_err(&priv->pdev->dev,
+			"could not count MSI-x vectors: err=%d\n", num_ntfy);
+		err = num_ntfy;
+		goto err;
+	} else if (num_ntfy < GVE_MIN_MSIX) {
+		dev_err(&priv->pdev->dev, "gve needs at least %d MSI-x vectors, but only has %d\n",
+			GVE_MIN_MSIX, num_ntfy);
+		err = -EINVAL;
+		goto err;
+	}
+
+	priv->num_registered_pages = 0;
+	priv->rx_copybreak = GVE_DEFAULT_RX_COPYBREAK;
+	/* gvnic has one Notification Block per MSI-x vector, except for the
+	 * management vector
+	 */
+	priv->num_ntfy_blks = (num_ntfy - 1) & ~0x1;
+	priv->mgmt_msix_idx = priv->num_ntfy_blks;
+
+	priv->tx_cfg.max_queues =
+		min_t(int, priv->tx_cfg.max_queues, priv->num_ntfy_blks / 2);
+	priv->rx_cfg.max_queues =
+		min_t(int, priv->rx_cfg.max_queues, priv->num_ntfy_blks / 2);
+
+	priv->tx_cfg.num_queues = priv->tx_cfg.max_queues;
+	priv->rx_cfg.num_queues = priv->rx_cfg.max_queues;
+	if (priv->default_num_queues > 0) {
+		priv->tx_cfg.num_queues = min_t(int, priv->default_num_queues,
+						priv->tx_cfg.num_queues);
+		priv->rx_cfg.num_queues = min_t(int, priv->default_num_queues,
+						priv->rx_cfg.num_queues);
+	}
+
+	netif_info(priv, drv, priv->dev, "TX queues %d, RX queues %d\n",
+		   priv->tx_cfg.num_queues, priv->rx_cfg.num_queues);
+	netif_info(priv, drv, priv->dev, "Max TX queues %d, Max RX queues %d\n",
+		   priv->tx_cfg.max_queues, priv->rx_cfg.max_queues);
+
+setup_device:
+	err = gve_setup_device_resources(priv);
+	if (!err)
+		return 0;
+err:
+	gve_adminq_free(&priv->pdev->dev, priv);
+	return err;
+}
+
+static void gve_teardown_priv_resources(struct gve_priv *priv)
+{
+	gve_teardown_device_resources(priv);
+	gve_adminq_free(&priv->pdev->dev, priv);
+}
+
+static void gve_trigger_reset(struct gve_priv *priv)
+{
+	/* Reset the device by releasing the AQ */
+	gve_adminq_release(priv);
+}
+
+static void gve_reset_and_teardown(struct gve_priv *priv, bool was_up)
+{
+	gve_trigger_reset(priv);
+	/* With the reset having already happened, close cannot fail */
+	if (was_up)
+		gve_close(priv->dev);
+	gve_teardown_priv_resources(priv);
+}
+
+static int gve_reset_recovery(struct gve_priv *priv, bool was_up)
+{
+	int err;
+
+	err = gve_init_priv(priv, true);
+	if (err)
+		goto err;
+	if (was_up) {
+		err = gve_open(priv->dev);
+		if (err)
+			goto err;
+	}
+	return 0;
+err:
+	dev_err(&priv->pdev->dev, "Reset failed! !!! DISABLING ALL QUEUES !!!\n");
+	gve_turndown(priv);
+	return err;
+}
+
+int gve_reset(struct gve_priv *priv, bool attempt_teardown)
+{
+	bool was_up = netif_carrier_ok(priv->dev);
+	int err;
+
+	dev_info(&priv->pdev->dev, "Performing reset\n");
+	gve_clear_do_reset(priv);
+	gve_set_reset_in_progress(priv);
+	/* If we aren't attempting to teardown normally, just go turndown and
+	 * reset right away.
+	 */
+	if (!attempt_teardown) {
+		gve_turndown(priv);
+		gve_reset_and_teardown(priv, was_up);
+	} else {
+		/* Otherwise attempt to close normally */
+		if (was_up) {
+			err = gve_close(priv->dev);
+			/* If that fails reset as we did above */
+			if (err)
+				gve_reset_and_teardown(priv, was_up);
+		}
+		/* Clean up any remaining resources */
+		gve_teardown_priv_resources(priv);
+	}
+
+	/* Set it all back up */
+	err = gve_reset_recovery(priv, was_up);
+	gve_clear_reset_in_progress(priv);
+	return err;
+}
+
+static void gve_write_version(u8 __iomem *driver_version_register)
+{
+	const char *c = gve_version_prefix;
+
+	while (*c) {
+		writeb(*c, driver_version_register);
+		c++;
+	}
+
+	c = gve_version_str;
+	while (*c) {
+		writeb(*c, driver_version_register);
+		c++;
+	}
+	writeb('\n', driver_version_register);
+}
+
+static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	int max_tx_queues, max_rx_queues;
+	struct net_device *dev;
+	__be32 __iomem *db_bar;
+	struct gve_registers __iomem *reg_bar;
+	struct gve_priv *priv;
+	int err;
+
+	err = pci_enable_device(pdev);
+	if (err)
+		return -ENXIO;
+
+	err = pci_request_regions(pdev, "gvnic-cfg");
+	if (err)
+		goto abort_with_enabled;
+
+	pci_set_master(pdev);
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set dma mask: err=%d\n", err);
+		goto abort_with_pci_region;
+	}
+
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_err(&pdev->dev,
+			"Failed to set consistent dma mask: err=%d\n", err);
+		goto abort_with_pci_region;
+	}
+
+	reg_bar = pci_iomap(pdev, GVE_REGISTER_BAR, 0);
+	if (!reg_bar) {
+		dev_err(&pdev->dev, "Failed to map pci bar!\n");
+		err = -ENOMEM;
+		goto abort_with_pci_region;
+	}
+
+	db_bar = pci_iomap(pdev, GVE_DOORBELL_BAR, 0);
+	if (!db_bar) {
+		dev_err(&pdev->dev, "Failed to map doorbell bar!\n");
+		err = -ENOMEM;
+		goto abort_with_reg_bar;
+	}
+
+	gve_write_version(&reg_bar->driver_version);
+	/* Get max queues to alloc etherdev */
+	max_rx_queues = ioread32be(&reg_bar->max_tx_queues);
+	max_tx_queues = ioread32be(&reg_bar->max_rx_queues);
+	/* Alloc and setup the netdev and priv */
+	dev = alloc_etherdev_mqs(sizeof(*priv), max_tx_queues, max_rx_queues);
+	if (!dev) {
+		dev_err(&pdev->dev, "could not allocate netdev\n");
+		goto abort_with_db_bar;
+	}
+	SET_NETDEV_DEV(dev, &pdev->dev);
+	pci_set_drvdata(pdev, dev);
+	dev->ethtool_ops = &gve_ethtool_ops;
+	dev->netdev_ops = &gve_netdev_ops;
+	/* advertise features */
+	dev->hw_features = NETIF_F_HIGHDMA;
+	dev->hw_features |= NETIF_F_SG;
+	dev->hw_features |= NETIF_F_HW_CSUM;
+	dev->hw_features |= NETIF_F_TSO;
+	dev->hw_features |= NETIF_F_TSO6;
+	dev->hw_features |= NETIF_F_TSO_ECN;
+	dev->hw_features |= NETIF_F_RXCSUM;
+	dev->hw_features |= NETIF_F_RXHASH;
+	dev->features = dev->hw_features;
+	dev->watchdog_timeo = 5 * HZ;
+	dev->min_mtu = ETH_MIN_MTU;
+	netif_carrier_off(dev);
+
+	priv = netdev_priv(dev);
+	priv->dev = dev;
+	priv->pdev = pdev;
+	priv->msg_enable = DEFAULT_MSG_LEVEL;
+	priv->reg_bar0 = reg_bar;
+	priv->db_bar2 = db_bar;
+	priv->service_task_flags = 0x0;
+	priv->state_flags = 0x0;
+
+	gve_set_probe_in_progress(priv);
+	priv->gve_wq = alloc_ordered_workqueue("gve", 0);
+	if (!priv->gve_wq) {
+		dev_err(&pdev->dev, "Could not allocate workqueue");
+		err = -ENOMEM;
+		goto abort_with_netdev;
+	}
+	INIT_WORK(&priv->service_task, gve_service_task);
+	priv->tx_cfg.max_queues = max_tx_queues;
+	priv->rx_cfg.max_queues = max_rx_queues;
+
+	err = gve_init_priv(priv, false);
+	if (err)
+		goto abort_with_wq;
+
+	err = register_netdev(dev);
+	if (err)
+		goto abort_with_wq;
+
+	dev_info(&pdev->dev, "GVE version %s\n", gve_version_str);
+	gve_clear_probe_in_progress(priv);
+	queue_work(priv->gve_wq, &priv->service_task);
+	return 0;
+
+abort_with_wq:
+	destroy_workqueue(priv->gve_wq);
+
+abort_with_netdev:
+	free_netdev(dev);
+
+abort_with_db_bar:
+	pci_iounmap(pdev, db_bar);
+
+abort_with_reg_bar:
+	pci_iounmap(pdev, reg_bar);
+
+abort_with_pci_region:
+	pci_release_regions(pdev);
+
+abort_with_enabled:
+	pci_disable_device(pdev);
+	return -ENXIO;
+}
+EXPORT_SYMBOL(gve_probe);
+
+static void gve_remove(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct gve_priv *priv = netdev_priv(netdev);
+	__be32 __iomem *db_bar = priv->db_bar2;
+	void __iomem *reg_bar = priv->reg_bar0;
+
+	unregister_netdev(netdev);
+	gve_teardown_priv_resources(priv);
+	destroy_workqueue(priv->gve_wq);
+	free_netdev(netdev);
+	pci_iounmap(pdev, db_bar);
+	pci_iounmap(pdev, reg_bar);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static const struct pci_device_id gve_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_GOOGLE, PCI_DEV_ID_GVNIC) },
+	{ }
+};
+
+static struct pci_driver gvnic_driver = {
+	.name		= "gvnic",
+	.id_table	= gve_id_table,
+	.probe		= gve_probe,
+	.remove		= gve_remove,
+};
+
+module_pci_driver(gvnic_driver);
+
+MODULE_DEVICE_TABLE(pci, gve_id_table);
+MODULE_AUTHOR("Google, Inc.");
+MODULE_DESCRIPTION("gVNIC Driver");
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_VERSION(GVE_VERSION);
diff --git a/drivers/net/ethernet/google/gve/gve_register.h b/drivers/net/ethernet/google/gve/gve_register.h
new file mode 100644
index 000000000000..84ab8893aadd
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_register.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ * Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#ifndef _GVE_REGISTER_H_
+#define _GVE_REGISTER_H_
+
+/* Fixed Configuration Registers */
+struct gve_registers {
+	__be32	device_status;
+	__be32	driver_status;
+	__be32	max_tx_queues;
+	__be32	max_rx_queues;
+	__be32	adminq_pfn;
+	__be32	adminq_doorbell;
+	__be32	adminq_event_counter;
+	u8	reserved[3];
+	u8	driver_version;
+};
+
+enum gve_device_status_flags {
+	GVE_DEVICE_STATUS_RESET_MASK		= BIT(1),
+	GVE_DEVICE_STATUS_LINK_STATUS_MASK	= BIT(2),
+};
+#endif /* _GVE_REGISTER_H_ */
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
new file mode 100644
index 000000000000..c1aeabd1c594
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -0,0 +1,446 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#include "gve.h"
+#include "gve_adminq.h"
+#include <linux/etherdevice.h>
+
+static void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx)
+{
+	struct gve_notify_block *block =
+			&priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_idx)];
+
+	block->rx = NULL;
+}
+
+static void gve_rx_free_ring(struct gve_priv *priv, int idx)
+{
+	struct gve_rx_ring *rx = &priv->rx[idx];
+	struct device *dev = &priv->pdev->dev;
+	size_t bytes;
+	u32 slots;
+
+	gve_rx_remove_from_block(priv, idx);
+
+	bytes = sizeof(struct gve_rx_desc) * priv->rx_desc_cnt;
+	dma_free_coherent(dev, bytes, rx->desc.desc_ring, rx->desc.bus);
+	rx->desc.desc_ring = NULL;
+
+	dma_free_coherent(dev, sizeof(*rx->q_resources),
+			  rx->q_resources, rx->q_resources_bus);
+	rx->q_resources = NULL;
+
+	gve_unassign_qpl(priv, rx->data.qpl->id);
+	rx->data.qpl = NULL;
+	kfree(rx->data.page_info);
+
+	slots = rx->data.mask + 1;
+	bytes = sizeof(*rx->data.data_ring) * slots;
+	dma_free_coherent(dev, bytes, rx->data.data_ring,
+			  rx->data.data_bus);
+	rx->data.data_ring = NULL;
+	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
+}
+
+static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info,
+				struct gve_rx_data_slot *slot,
+				dma_addr_t addr, struct page *page)
+{
+	page_info->page = page;
+	page_info->page_offset = 0;
+	page_info->page_address = page_address(page);
+	slot->qpl_offset = cpu_to_be64(addr);
+}
+
+static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
+{
+	struct gve_priv *priv = rx->gve;
+	u32 slots;
+	int i;
+
+	/* Allocate one page per Rx queue slot. Each page is split into two
+	 * packet buffers, when possible we "page flip" between the two.
+	 */
+	slots = rx->data.mask + 1;
+
+	rx->data.page_info = kvzalloc(slots *
+				      sizeof(*rx->data.page_info), GFP_KERNEL);
+	if (!rx->data.page_info)
+		return -ENOMEM;
+
+	rx->data.qpl = gve_assign_rx_qpl(priv);
+
+	for (i = 0; i < slots; i++) {
+		struct page *page = rx->data.qpl->pages[i];
+		dma_addr_t addr = i * PAGE_SIZE;
+
+		gve_setup_rx_buffer(&rx->data.page_info[i],
+				    &rx->data.data_ring[i], addr, page);
+	}
+
+	return slots;
+}
+
+static void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx)
+{
+	u32 ntfy_idx = gve_rx_idx_to_ntfy(priv, queue_idx);
+	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+	struct gve_rx_ring *rx = &priv->rx[queue_idx];
+
+	block->rx = rx;
+	rx->ntfy_id = ntfy_idx;
+}
+
+static int gve_rx_alloc_ring(struct gve_priv *priv, int idx)
+{
+	struct gve_rx_ring *rx = &priv->rx[idx];
+	struct device *hdev = &priv->pdev->dev;
+	u32 slots, npages;
+	int filled_pages;
+	size_t bytes;
+	int err;
+
+	netif_dbg(priv, drv, priv->dev, "allocating rx ring\n");
+	/* Make sure everything is zeroed to start with */
+	memset(rx, 0, sizeof(*rx));
+
+	rx->gve = priv;
+	rx->q_num = idx;
+
+	slots = priv->rx_pages_per_qpl;
+	rx->data.mask = slots - 1;
+
+	/* alloc rx data ring */
+	bytes = sizeof(*rx->data.data_ring) * slots;
+	rx->data.data_ring = dma_alloc_coherent(hdev, bytes,
+						&rx->data.data_bus,
+						GFP_KERNEL);
+	if (!rx->data.data_ring)
+		return -ENOMEM;
+	filled_pages = gve_prefill_rx_pages(rx);
+	if (filled_pages < 0) {
+		err = -ENOMEM;
+		goto abort_with_slots;
+	}
+	rx->desc.fill_cnt = filled_pages;
+	/* Ensure data ring slots (packet buffers) are visible. */
+	dma_wmb();
+
+	/* Alloc gve_queue_resources */
+	rx->q_resources =
+		dma_alloc_coherent(hdev,
+				   sizeof(*rx->q_resources),
+				   &rx->q_resources_bus,
+				   GFP_KERNEL);
+	if (!rx->q_resources) {
+		err = -ENOMEM;
+		goto abort_filled;
+	}
+	netif_dbg(priv, drv, priv->dev, "rx[%d]->data.data_bus=%lx\n", idx,
+		  (unsigned long)rx->data.data_bus);
+
+	/* alloc rx desc ring */
+	bytes = sizeof(struct gve_rx_desc) * priv->rx_desc_cnt;
+	npages = bytes / PAGE_SIZE;
+	if (npages * PAGE_SIZE != bytes) {
+		err = -EIO;
+		goto abort_with_q_resources;
+	}
+
+	rx->desc.desc_ring = dma_alloc_coherent(hdev, bytes, &rx->desc.bus,
+						GFP_KERNEL);
+	if (!rx->desc.desc_ring) {
+		err = -ENOMEM;
+		goto abort_with_q_resources;
+	}
+	rx->desc.mask = slots - 1;
+	rx->desc.cnt = 0;
+	rx->desc.seqno = 1;
+	gve_rx_add_to_block(priv, idx);
+
+	return 0;
+
+abort_with_q_resources:
+	dma_free_coherent(hdev, sizeof(*rx->q_resources),
+			  rx->q_resources, rx->q_resources_bus);
+	rx->q_resources = NULL;
+abort_filled:
+	kfree(rx->data.page_info);
+abort_with_slots:
+	bytes = sizeof(*rx->data.data_ring) * slots;
+	dma_free_coherent(hdev, bytes, rx->data.data_ring, rx->data.data_bus);
+	rx->data.data_ring = NULL;
+
+	return err;
+}
+
+int gve_rx_alloc_rings(struct gve_priv *priv)
+{
+	int err = 0;
+	int i;
+
+	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+		err = gve_rx_alloc_ring(priv, i);
+		if (err) {
+			netif_err(priv, drv, priv->dev,
+				  "Failed to alloc rx ring=%d: err=%d\n",
+				  i, err);
+			break;
+		}
+	}
+	/* Unallocate if there was an error */
+	if (err) {
+		int j;
+
+		for (j = 0; j < i; j++)
+			gve_rx_free_ring(priv, j);
+	}
+	return err;
+}
+
+void gve_rx_free_rings(struct gve_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->rx_cfg.num_queues; i++)
+		gve_rx_free_ring(priv, i);
+}
+
+void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx)
+{
+	u32 db_idx = be32_to_cpu(rx->q_resources->db_index);
+
+	iowrite32be(rx->desc.fill_cnt, &priv->db_bar2[db_idx]);
+}
+
+static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
+{
+	if (likely(pkt_flags & (GVE_RXF_TCP | GVE_RXF_UDP)))
+		return PKT_HASH_TYPE_L4;
+	if (pkt_flags & (GVE_RXF_IPV4 | GVE_RXF_IPV6))
+		return PKT_HASH_TYPE_L3;
+	return PKT_HASH_TYPE_L2;
+}
+
+static struct sk_buff *gve_rx_copy(struct net_device *dev,
+				   struct napi_struct *napi,
+				   struct gve_rx_slot_page_info *page_info,
+				   u16 len)
+{
+	struct sk_buff *skb = napi_alloc_skb(napi, len);
+	void *va = page_info->page_address + GVE_RX_PAD +
+		   page_info->page_offset;
+
+	if (unlikely(!skb))
+		return NULL;
+
+	__skb_put(skb, len);
+
+	skb_copy_to_linear_data(skb, va, len);
+
+	skb->protocol = eth_type_trans(skb, dev);
+	return skb;
+}
+
+static struct sk_buff *gve_rx_add_frags(struct net_device *dev,
+					struct napi_struct *napi,
+					struct gve_rx_slot_page_info *page_info,
+					u16 len)
+{
+	struct sk_buff *skb = napi_get_frags(napi);
+
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_add_rx_frag(skb, 0, page_info->page,
+			page_info->page_offset +
+			GVE_RX_PAD, len, PAGE_SIZE / 2);
+
+	return skb;
+}
+
+static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info,
+			     struct gve_rx_data_slot *data_ring)
+{
+	u64 addr = be64_to_cpu(data_ring->qpl_offset);
+
+	page_info->page_offset ^= PAGE_SIZE / 2;
+	addr ^= PAGE_SIZE / 2;
+	data_ring->qpl_offset = cpu_to_be64(addr);
+}
+
+static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
+		   netdev_features_t feat)
+{
+	struct gve_rx_slot_page_info *page_info;
+	struct gve_priv *priv = rx->gve;
+	struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi;
+	struct net_device *dev = priv->dev;
+	struct sk_buff *skb;
+	int pagecount;
+	u16 len;
+	u32 idx;
+
+	/* drop this packet */
+	if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR))
+		return true;
+
+	len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD;
+	idx = rx->data.cnt & rx->data.mask;
+	page_info = &rx->data.page_info[idx];
+
+	/* gvnic can only receive into registered segments. If the buffer
+	 * can't be recycled, our only choice is to copy the data out of
+	 * it so that we can return it to the device.
+	 */
+
+	if (PAGE_SIZE == 4096) {
+		if (len <= priv->rx_copybreak) {
+			/* Just copy small packets */
+			skb = gve_rx_copy(dev, napi, page_info, len);
+			goto have_skb;
+		}
+		if (unlikely(!gve_can_recycle_pages(dev))) {
+			skb = gve_rx_copy(dev, napi, page_info, len);
+			goto have_skb;
+		}
+		pagecount = page_count(page_info->page);
+		if (pagecount == 1) {
+			/* No part of this page is used by any SKBs; we attach
+			 * the page fragment to a new SKB and pass it up the
+			 * stack.
+			 */
+			skb = gve_rx_add_frags(dev, napi, page_info, len);
+			if (!skb)
+				return true;
+			/* Make sure the kernel stack can't release the page */
+			get_page(page_info->page);
+			/* "flip" to other packet buffer on this page */
+			gve_rx_flip_buff(page_info, &rx->data.data_ring[idx]);
+		} else if (pagecount >= 2) {
+			/* We have previously passed the other half of this
+			 * page up the stack, but it has not yet been freed.
+			 */
+			skb = gve_rx_copy(dev, napi, page_info, len);
+		} else {
+			WARN(pagecount < 1, "Pagecount should never be < 1");
+			return false;
+		}
+	} else {
+		skb = gve_rx_copy(dev, napi, page_info, len);
+	}
+
+have_skb:
+	/* We didn't manage to allocate an skb but we haven't had any
+	 * reset worthy failures.
+	 */
+	if (!skb)
+		return true;
+
+	rx->data.cnt++;
+
+	if (likely(feat & NETIF_F_RXCSUM)) {
+		/* NIC passes up the partial sum */
+		if (rx_desc->csum)
+			skb->ip_summed = CHECKSUM_COMPLETE;
+		else
+			skb->ip_summed = CHECKSUM_NONE;
+		skb->csum = csum_unfold(rx_desc->csum);
+	}
+
+	/* parse flags & pass relevant info up */
+	if (likely(feat & NETIF_F_RXHASH) &&
+	    gve_needs_rss(rx_desc->flags_seq))
+		skb_set_hash(skb, be32_to_cpu(rx_desc->rss_hash),
+			     gve_rss_type(rx_desc->flags_seq));
+
+	if (skb_is_nonlinear(skb))
+		napi_gro_frags(napi);
+	else
+		napi_gro_receive(napi, skb);
+	return true;
+}
+
+static bool gve_rx_work_pending(struct gve_rx_ring *rx)
+{
+	struct gve_rx_desc *desc;
+	__be16 flags_seq;
+	u32 next_idx;
+
+	next_idx = rx->desc.cnt & rx->desc.mask;
+	desc = rx->desc.desc_ring + next_idx;
+
+	flags_seq = desc->flags_seq;
+	/* Make sure we have synchronized the seq no with the device */
+	smp_rmb();
+
+	return (GVE_SEQNO(flags_seq) == rx->desc.seqno);
+}
+
+bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget,
+		       netdev_features_t feat)
+{
+	struct gve_priv *priv = rx->gve;
+	struct gve_rx_desc *desc;
+	u32 cnt = rx->desc.cnt;
+	u32 idx = cnt & rx->desc.mask;
+	u32 work_done = 0;
+	u64 bytes = 0;
+
+	desc = rx->desc.desc_ring + idx;
+	while ((GVE_SEQNO(desc->flags_seq) == rx->desc.seqno) &&
+	       work_done < budget) {
+		netif_info(priv, rx_status, priv->dev,
+			   "[%d] idx=%d desc=%p desc->flags_seq=0x%x\n",
+			   rx->q_num, idx, desc, desc->flags_seq);
+		netif_info(priv, rx_status, priv->dev,
+			   "[%d] seqno=%d rx->desc.seqno=%d\n",
+			   rx->q_num, GVE_SEQNO(desc->flags_seq),
+			   rx->desc.seqno);
+		bytes += be16_to_cpu(desc->len) - GVE_RX_PAD;
+		if (!gve_rx(rx, desc, feat))
+			gve_schedule_reset(priv);
+		cnt++;
+		idx = cnt & rx->desc.mask;
+		desc = rx->desc.desc_ring + idx;
+		rx->desc.seqno = gve_next_seqno(rx->desc.seqno);
+		work_done++;
+	}
+
+	if (!work_done)
+		return false;
+
+	u64_stats_update_begin(&rx->statss);
+	rx->rpackets += work_done;
+	rx->rbytes += bytes;
+	u64_stats_update_end(&rx->statss);
+	rx->desc.cnt = cnt;
+	rx->desc.fill_cnt += work_done;
+
+	/* restock desc ring slots */
+	dma_wmb();	/* Ensure descs are visible before ringing doorbell */
+	gve_rx_write_doorbell(priv, rx);
+	return gve_rx_work_pending(rx);
+}
+
+bool gve_rx_poll(struct gve_notify_block *block, int budget)
+{
+	struct gve_rx_ring *rx = block->rx;
+	netdev_features_t feat;
+	bool repoll = false;
+
+	feat = block->napi.dev->features;
+
+	/* If budget is 0, do all the work */
+	if (budget == 0)
+		budget = INT_MAX;
+
+	if (budget > 0)
+		repoll |= gve_clean_rx_done(rx, budget, feat);
+	else
+		repoll |= gve_rx_work_pending(rx);
+	return repoll;
+}
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
new file mode 100644
index 000000000000..778b87b5a06c
--- /dev/null
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -0,0 +1,584 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Google virtual Ethernet (gve) driver
+ *
+ * Copyright (C) 2015-2019 Google, Inc.
+ */
+
+#include "gve.h"
+#include "gve_adminq.h"
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/vmalloc.h>
+#include <linux/skbuff.h>
+
+static inline void gve_tx_put_doorbell(struct gve_priv *priv,
+				       struct gve_queue_resources *q_resources,
+				       u32 val)
+{
+	iowrite32be(val, &priv->db_bar2[be32_to_cpu(q_resources->db_index)]);
+}
+
+/* gvnic can only transmit from a Registered Segment.
+ * We copy skb payloads into the registered segment before writing Tx
+ * descriptors and ringing the Tx doorbell.
+ *
+ * gve_tx_fifo_* manages the Registered Segment as a FIFO - clients must
+ * free allocations in the order they were allocated.
+ */
+
+static int gve_tx_fifo_init(struct gve_priv *priv, struct gve_tx_fifo *fifo)
+{
+	fifo->base = vmap(fifo->qpl->pages, fifo->qpl->num_entries, VM_MAP,
+			  PAGE_KERNEL);
+	if (unlikely(!fifo->base)) {
+		netif_err(priv, drv, priv->dev, "Failed to vmap fifo, qpl_id = %d\n",
+			  fifo->qpl->id);
+		return -ENOMEM;
+	}
+
+	fifo->size = fifo->qpl->num_entries * PAGE_SIZE;
+	atomic_set(&fifo->available, fifo->size);
+	fifo->head = 0;
+	return 0;
+}
+
+static void gve_tx_fifo_release(struct gve_priv *priv, struct gve_tx_fifo *fifo)
+{
+	WARN(atomic_read(&fifo->available) != fifo->size,
+	     "Releasing non-empty fifo");
+
+	vunmap(fifo->base);
+}
+
+static int gve_tx_fifo_pad_alloc_one_frag(struct gve_tx_fifo *fifo,
+					  size_t bytes)
+{
+	return (fifo->head + bytes < fifo->size) ? 0 : fifo->size - fifo->head;
+}
+
+static bool gve_tx_fifo_can_alloc(struct gve_tx_fifo *fifo, size_t bytes)
+{
+	return (atomic_read(&fifo->available) <= bytes) ? false : true;
+}
+
+/* gve_tx_alloc_fifo - Allocate fragment(s) from Tx FIFO
+ * @fifo: FIFO to allocate from
+ * @bytes: Allocation size
+ * @iov: Scatter-gather elements to fill with allocation fragment base/len
+ *
+ * Returns number of valid elements in iov[] or negative on error.
+ *
+ * Allocations from a given FIFO must be externally synchronized but concurrent
+ * allocation and frees are allowed.
+ */
+static int gve_tx_alloc_fifo(struct gve_tx_fifo *fifo, size_t bytes,
+			     struct gve_tx_iovec iov[2])
+{
+	size_t overflow, padding;
+	u32 aligned_head;
+	int nfrags = 0;
+
+	if (!bytes)
+		return 0;
+
+	/* This check happens before we know how much padding is needed to
+	 * align to a cacheline boundary for the payload, but that is fine,
+	 * because the FIFO head always start aligned, and the FIFO's boundaries
+	 * are aligned, so if there is space for the data, there is space for
+	 * the padding to the next alignment.
+	 */
+	WARN(!gve_tx_fifo_can_alloc(fifo, bytes),
+	     "Reached %s when there's not enough space in the fifo", __func__);
+
+	nfrags++;
+
+	iov[0].iov_offset = fifo->head;
+	iov[0].iov_len = bytes;
+	fifo->head += bytes;
+
+	if (fifo->head > fifo->size) {
+		/* If the allocation did not fit in the tail fragment of the
+		 * FIFO, also use the head fragment.
+		 */
+		nfrags++;
+		overflow = fifo->head - fifo->size;
+		iov[0].iov_len -= overflow;
+		iov[1].iov_offset = 0;	/* Start of fifo*/
+		iov[1].iov_len = overflow;
+
+		fifo->head = overflow;
+	}
+
+	/* Re-align to a cacheline boundary */
+	aligned_head = L1_CACHE_ALIGN(fifo->head);
+	padding = aligned_head - fifo->head;
+	iov[nfrags - 1].iov_padding = padding;
+	atomic_sub(bytes + padding, &fifo->available);
+	fifo->head = aligned_head;
+
+	if (fifo->head == fifo->size)
+		fifo->head = 0;
+
+	return nfrags;
+}
+
+/* gve_tx_free_fifo - Return space to Tx FIFO
+ * @fifo: FIFO to return fragments to
+ * @bytes: Bytes to free
+ */
+static void gve_tx_free_fifo(struct gve_tx_fifo *fifo, size_t bytes)
+{
+	atomic_add(bytes, &fifo->available);
+}
+
+static void gve_tx_remove_from_block(struct gve_priv *priv, int queue_idx)
+{
+	struct gve_notify_block *block =
+			&priv->ntfy_blocks[gve_tx_idx_to_ntfy(priv, queue_idx)];
+
+	block->tx = NULL;
+}
+
+static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
+			     u32 to_do, bool try_to_wake);
+
+static void gve_tx_free_ring(struct gve_priv *priv, int idx)
+{
+	struct gve_tx_ring *tx = &priv->tx[idx];
+	struct device *hdev = &priv->pdev->dev;
+	size_t bytes;
+	u32 slots;
+
+	gve_tx_remove_from_block(priv, idx);
+	slots = tx->mask + 1;
+	gve_clean_tx_done(priv, tx, tx->req, false);
+	netdev_tx_reset_queue(tx->netdev_txq);
+
+	dma_free_coherent(hdev, sizeof(*tx->q_resources),
+			  tx->q_resources, tx->q_resources_bus);
+	tx->q_resources = NULL;
+
+	gve_tx_fifo_release(priv, &tx->tx_fifo);
+	gve_unassign_qpl(priv, tx->tx_fifo.qpl->id);
+	tx->tx_fifo.qpl = NULL;
+
+	bytes = sizeof(*tx->desc) * slots;
+	dma_free_coherent(hdev, bytes, tx->desc, tx->bus);
+	tx->desc = NULL;
+
+	vfree(tx->info);
+	tx->info = NULL;
+
+	netif_dbg(priv, drv, priv->dev, "freed tx queue %d\n", idx);
+}
+
+static void gve_tx_add_to_block(struct gve_priv *priv, int queue_idx)
+{
+	int ntfy_idx = gve_tx_idx_to_ntfy(priv, queue_idx);
+	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
+	struct gve_tx_ring *tx = &priv->tx[queue_idx];
+
+	block->tx = tx;
+	tx->ntfy_id = ntfy_idx;
+}
+
+static int gve_tx_alloc_ring(struct gve_priv *priv, int idx)
+{
+	struct gve_tx_ring *tx = &priv->tx[idx];
+	struct device *hdev = &priv->pdev->dev;
+	u32 slots = priv->tx_desc_cnt;
+	size_t bytes;
+
+	/* Make sure everything is zeroed to start */
+	memset(tx, 0, sizeof(*tx));
+	tx->q_num = idx;
+
+	tx->mask = slots - 1;
+
+	/* alloc metadata */
+	tx->info = vzalloc(sizeof(*tx->info) * slots);
+	if (!tx->info)
+		return -ENOMEM;
+
+	/* alloc tx queue */
+	bytes = sizeof(*tx->desc) * slots;
+	tx->desc = dma_alloc_coherent(hdev, bytes, &tx->bus, GFP_KERNEL);
+	if (!tx->desc)
+		goto abort_with_info;
+
+	tx->tx_fifo.qpl = gve_assign_tx_qpl(priv);
+
+	/* map Tx FIFO */
+	if (gve_tx_fifo_init(priv, &tx->tx_fifo))
+		goto abort_with_desc;
+
+	tx->q_resources =
+		dma_alloc_coherent(hdev,
+				   sizeof(*tx->q_resources),
+				   &tx->q_resources_bus,
+				   GFP_KERNEL);
+	if (!tx->q_resources)
+		goto abort_with_fifo;
+
+	netif_dbg(priv, drv, priv->dev, "tx[%d]->bus=%lx\n", idx,
+		  (unsigned long)tx->bus);
+	tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx);
+	gve_tx_add_to_block(priv, idx);
+
+	return 0;
+
+abort_with_fifo:
+	gve_tx_fifo_release(priv, &tx->tx_fifo);
+abort_with_desc:
+	dma_free_coherent(hdev, bytes, tx->desc, tx->bus);
+	tx->desc = NULL;
+abort_with_info:
+	vfree(tx->info);
+	tx->info = NULL;
+	return -ENOMEM;
+}
+
+int gve_tx_alloc_rings(struct gve_priv *priv)
+{
+	int err = 0;
+	int i;
+
+	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
+		err = gve_tx_alloc_ring(priv, i);
+		if (err) {
+			netif_err(priv, drv, priv->dev,
+				  "Failed to alloc tx ring=%d: err=%d\n",
+				  i, err);
+			break;
+		}
+	}
+	/* Unallocate if there was an error */
+	if (err) {
+		int j;
+
+		for (j = 0; j < i; j++)
+			gve_tx_free_ring(priv, j);
+	}
+	return err;
+}
+
+void gve_tx_free_rings(struct gve_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->tx_cfg.num_queues; i++)
+		gve_tx_free_ring(priv, i);
+}
+
+/* gve_tx_avail - Calculates the number of slots available in the ring
+ * @tx: tx ring to check
+ *
+ * Returns the number of slots available
+ *
+ * The capacity of the queue is mask + 1. We don't need to reserve an entry.
+ **/
+static inline u32 gve_tx_avail(struct gve_tx_ring *tx)
+{
+	return tx->mask + 1 - (tx->req - tx->done);
+}
+
+static inline int gve_skb_fifo_bytes_required(struct gve_tx_ring *tx,
+					      struct sk_buff *skb)
+{
+	int pad_bytes, align_hdr_pad;
+	int bytes;
+	int hlen;
+
+	hlen = skb_is_gso(skb) ? skb_checksum_start_offset(skb) +
+				 tcp_hdrlen(skb) : skb_headlen(skb);
+
+	pad_bytes = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo,
+						   hlen);
+	/* We need to take into account the header alignment padding. */
+	align_hdr_pad = L1_CACHE_ALIGN(hlen) - hlen;
+	bytes = align_hdr_pad + pad_bytes + skb->len;
+
+	return bytes;
+}
+
+/* The most descriptors we could need are 3 - 1 for the headers, 1 for
+ * the beginning of the payload at the end of the FIFO, and 1 if the
+ * payload wraps to the beginning of the FIFO.
+ */
+#define MAX_TX_DESC_NEEDED	3
+
+/* Check if sufficient resources (descriptor ring space, FIFO space) are
+ * available to transmit the given number of bytes.
+ */
+static inline bool gve_can_tx(struct gve_tx_ring *tx, int bytes_required)
+{
+	return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED &&
+		gve_tx_fifo_can_alloc(&tx->tx_fifo, bytes_required));
+}
+
+/* Stops the queue if the skb cannot be transmitted. */
+static int gve_maybe_stop_tx(struct gve_tx_ring *tx, struct sk_buff *skb)
+{
+	int bytes_required;
+
+	bytes_required = gve_skb_fifo_bytes_required(tx, skb);
+	if (likely(gve_can_tx(tx, bytes_required)))
+		return 0;
+
+	/* No space, so stop the queue */
+	tx->stop_queue++;
+	netif_tx_stop_queue(tx->netdev_txq);
+	smp_mb();	/* sync with restarting queue in gve_clean_tx_done() */
+
+	/* Now check for resources again, in case gve_clean_tx_done() freed
+	 * resources after we checked and we stopped the queue after
+	 * gve_clean_tx_done() checked.
+	 *
+	 * gve_maybe_stop_tx()			gve_clean_tx_done()
+	 *   nsegs/can_alloc test failed
+	 *					  gve_tx_free_fifo()
+	 *					  if (tx queue stopped)
+	 *					    netif_tx_queue_wake()
+	 *   netif_tx_stop_queue()
+	 *   Need to check again for space here!
+	 */
+	if (likely(!gve_can_tx(tx, bytes_required)))
+		return -EBUSY;
+
+	netif_tx_start_queue(tx->netdev_txq);
+	tx->wake_queue++;
+	return 0;
+}
+
+static void gve_tx_fill_pkt_desc(union gve_tx_desc *pkt_desc,
+				 struct sk_buff *skb, bool is_gso,
+				 int l4_hdr_offset, u32 desc_cnt,
+				 u16 hlen, u64 addr)
+{
+	/* l4_hdr_offset and csum_offset are in units of 16-bit words */
+	if (is_gso) {
+		pkt_desc->pkt.type_flags = GVE_TXD_TSO | GVE_TXF_L4CSUM;
+		pkt_desc->pkt.l4_csum_offset = skb->csum_offset >> 1;
+		pkt_desc->pkt.l4_hdr_offset = l4_hdr_offset >> 1;
+	} else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
+		pkt_desc->pkt.type_flags = GVE_TXD_STD | GVE_TXF_L4CSUM;
+		pkt_desc->pkt.l4_csum_offset = skb->csum_offset >> 1;
+		pkt_desc->pkt.l4_hdr_offset = l4_hdr_offset >> 1;
+	} else {
+		pkt_desc->pkt.type_flags = GVE_TXD_STD;
+		pkt_desc->pkt.l4_csum_offset = 0;
+		pkt_desc->pkt.l4_hdr_offset = 0;
+	}
+	pkt_desc->pkt.desc_cnt = desc_cnt;
+	pkt_desc->pkt.len = cpu_to_be16(skb->len);
+	pkt_desc->pkt.seg_len = cpu_to_be16(hlen);
+	pkt_desc->pkt.seg_addr = cpu_to_be64(addr);
+}
+
+static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc,
+				 struct sk_buff *skb, bool is_gso,
+				 u16 len, u64 addr)
+{
+	seg_desc->seg.type_flags = GVE_TXD_SEG;
+	if (is_gso) {
+		if (skb_is_gso_v6(skb))
+			seg_desc->seg.type_flags |= GVE_TXSF_IPV6;
+		seg_desc->seg.l3_offset = skb_network_offset(skb) >> 1;
+		seg_desc->seg.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
+	}
+	seg_desc->seg.seg_len = cpu_to_be16(len);
+	seg_desc->seg.seg_addr = cpu_to_be64(addr);
+}
+
+static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb)
+{
+	int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset;
+	union gve_tx_desc *pkt_desc, *seg_desc;
+	struct gve_tx_buffer_state *info;
+	bool is_gso = skb_is_gso(skb);
+	u32 idx = tx->req & tx->mask;
+	int payload_iov = 2;
+	int copy_offset;
+	u32 next_idx;
+	int i;
+
+	info = &tx->info[idx];
+	pkt_desc = &tx->desc[idx];
+
+	l4_hdr_offset = skb_checksum_start_offset(skb);
+	/* If the skb is gso, then we want the tcp header in the first segment
+	 * otherwise we want the linear portion of the skb (which will contain
+	 * the checksum because skb->csum_start and skb->csum_offset are given
+	 * relative to skb->head) in the first segment.
+	 */
+	hlen = is_gso ? l4_hdr_offset + tcp_hdrlen(skb) :
+			skb_headlen(skb);
+
+	info->skb =  skb;
+	/* We don't want to split the header, so if necessary, pad to the end
+	 * of the fifo and then put the header at the beginning of the fifo.
+	 */
+	pad_bytes = gve_tx_fifo_pad_alloc_one_frag(&tx->tx_fifo, hlen);
+	hdr_nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, hlen + pad_bytes,
+				       &info->iov[0]);
+	WARN(!hdr_nfrags, "hdr_nfrags should never be 0!");
+	payload_nfrags = gve_tx_alloc_fifo(&tx->tx_fifo, skb->len - hlen,
+					   &info->iov[payload_iov]);
+
+	gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset,
+			     1 + payload_nfrags, hlen,
+			     info->iov[hdr_nfrags - 1].iov_offset);
+
+	skb_copy_bits(skb, 0,
+		      tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset,
+		      hlen);
+	copy_offset = hlen;
+
+	for (i = payload_iov; i < payload_nfrags + payload_iov; i++) {
+		next_idx = (tx->req + 1 + i - payload_iov) & tx->mask;
+		seg_desc = &tx->desc[next_idx];
+
+		gve_tx_fill_seg_desc(seg_desc, skb, is_gso,
+				     info->iov[i].iov_len,
+				     info->iov[i].iov_offset);
+
+		skb_copy_bits(skb, copy_offset,
+			      tx->tx_fifo.base + info->iov[i].iov_offset,
+			      info->iov[i].iov_len);
+		copy_offset += info->iov[i].iov_len;
+	}
+
+	return 1 + payload_nfrags;
+}
+
+netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
+{
+	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_tx_ring *tx;
+	int nsegs;
+
+	WARN(skb_get_queue_mapping(skb) > priv->tx_cfg.num_queues,
+	     "skb queue index out of range");
+	tx = &priv->tx[skb_get_queue_mapping(skb)];
+	if (unlikely(gve_maybe_stop_tx(tx, skb))) {
+		/* We need to ring the txq doorbell -- we have stopped the Tx
+		 * queue for want of resources, but prior calls to gve_tx()
+		 * may have added descriptors without ringing the doorbell.
+		 */
+
+		/* Ensure tx descs from a prior gve_tx are visible before
+		 * ringing doorbell.
+		 */
+		dma_wmb();
+		gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
+		return NETDEV_TX_BUSY;
+	}
+	nsegs = gve_tx_add_skb(tx, skb);
+
+	netdev_tx_sent_queue(tx->netdev_txq, skb->len);
+	skb_tx_timestamp(skb);
+
+	/* give packets to NIC */
+	tx->req += nsegs;
+
+	if (!netif_xmit_stopped(tx->netdev_txq) && netdev_xmit_more())
+		return NETDEV_TX_OK;
+
+	/* Ensure tx descs are visible before ringing doorbell */
+	dma_wmb();
+	gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
+	return NETDEV_TX_OK;
+}
+
+#define GVE_TX_START_THRESH	PAGE_SIZE
+
+static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx,
+			     u32 to_do, bool try_to_wake)
+{
+	struct gve_tx_buffer_state *info;
+	u64 pkts = 0, bytes = 0;
+	size_t space_freed = 0;
+	struct sk_buff *skb;
+	int i, j;
+	u32 idx;
+
+	for (j = 0; j < to_do; j++) {
+		idx = tx->done & tx->mask;
+		netif_info(priv, tx_done, priv->dev,
+			   "[%d] %s: idx=%d (req=%u done=%u)\n",
+			   tx->q_num, __func__, idx, tx->req, tx->done);
+		info = &tx->info[idx];
+		skb = info->skb;
+
+		/* Mark as free */
+		if (skb) {
+			info->skb = NULL;
+			bytes += skb->len;
+			pkts++;
+			dev_consume_skb_any(skb);
+			/* FIFO free */
+			for (i = 0; i < ARRAY_SIZE(info->iov); i++) {
+				space_freed += info->iov[i].iov_len +
+					       info->iov[i].iov_padding;
+				info->iov[i].iov_len = 0;
+				info->iov[i].iov_padding = 0;
+			}
+		}
+		tx->done++;
+	}
+
+	gve_tx_free_fifo(&tx->tx_fifo, space_freed);
+	u64_stats_update_begin(&tx->statss);
+	tx->bytes_done += bytes;
+	tx->pkt_done += pkts;
+	u64_stats_update_end(&tx->statss);
+	netdev_tx_completed_queue(tx->netdev_txq, pkts, bytes);
+
+	/* start the queue if we've stopped it */
+#ifndef CONFIG_BQL
+	/* Make sure that the doorbells are synced */
+	smp_mb();
+#endif
+	if (try_to_wake && netif_tx_queue_stopped(tx->netdev_txq) &&
+	    likely(gve_can_tx(tx, GVE_TX_START_THRESH))) {
+		tx->wake_queue++;
+		netif_tx_wake_queue(tx->netdev_txq);
+	}
+
+	return pkts;
+}
+
+__be32 gve_tx_load_event_counter(struct gve_priv *priv,
+				 struct gve_tx_ring *tx)
+{
+	u32 counter_index = be32_to_cpu((tx->q_resources->counter_index));
+
+	return READ_ONCE(priv->counter_array[counter_index]);
+}
+
+bool gve_tx_poll(struct gve_notify_block *block, int budget)
+{
+	struct gve_priv *priv = block->priv;
+	struct gve_tx_ring *tx = block->tx;
+	bool repoll = false;
+	u32 nic_done;
+	u32 to_do;
+
+	/* If budget is 0, do all the work */
+	if (budget == 0)
+		budget = INT_MAX;
+
+	/* Find out how much work there is to be done */
+	tx->last_nic_done = gve_tx_load_event_counter(priv, tx);
+	nic_done = be32_to_cpu(tx->last_nic_done);
+	if (budget > 0) {
+		/* Do as much work as we have that the budget will
+		 * allow
+		 */
+		to_do = min_t(u32, (nic_done - tx->done), budget);
+		gve_clean_tx_done(priv, tx, to_do, true);
+	}
+	/* If we still have work we want to repoll */
+	repoll |= (nic_done != tx->done);
+	return repoll;
+}
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index fee4664c9189..3892a2062404 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # HISILICON device configuration
 #
@@ -45,6 +46,16 @@ config HIP04_ETH
 	  If you wish to compile a kernel for a hardware with hisilicon p04 SoC and
 	  want to use the internal ethernet then you should answer Y to this.
 
+config HI13X1_GMAC
+	bool "Hisilicon HI13X1 Network Device Support"
+	depends on HIP04_ETH
+	help
+	  If you wish to compile a kernel for a hardware with hisilicon hi13x1_gamc
+	  then you should answer Y to this. This makes this driver suitable for use
+	  on certain boards such as the HI13X1.
+
+	  If you are unsure, say N.
+
 config HNS_MDIO
 	tristate
 	select PHYLIB
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index f9a4e76c5a8b..d60452845539 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 
 /* Copyright (c) 2014 Linaro Ltd.
  * Copyright (c) 2014 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/module.h>
@@ -20,6 +16,8 @@
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 
+#define SC_PPE_RESET_DREQ		0x026C
+
 #define PPE_CFG_RX_ADDR			0x100
 #define PPE_CFG_POOL_GRP		0x300
 #define PPE_CFG_RX_BUF_SIZE		0x400
@@ -37,10 +35,23 @@
 #define GE_MODE_CHANGE_REG		0x1b4
 #define GE_RECV_CONTROL_REG		0x1e0
 #define GE_STATION_MAC_ADDRESS		0x210
-#define PPE_CFG_CPU_ADD_ADDR		0x580
-#define PPE_CFG_MAX_FRAME_LEN_REG	0x408
+
 #define PPE_CFG_BUS_CTRL_REG		0x424
 #define PPE_CFG_RX_CTRL_REG		0x428
+
+#if defined(CONFIG_HI13X1_GMAC)
+#define PPE_CFG_CPU_ADD_ADDR		0x6D0
+#define PPE_CFG_MAX_FRAME_LEN_REG	0x500
+#define PPE_CFG_RX_PKT_MODE_REG		0x504
+#define PPE_CFG_QOS_VMID_GEN		0x520
+#define PPE_CFG_RX_PKT_INT		0x740
+#define PPE_INTEN			0x700
+#define PPE_INTSTS			0x708
+#define PPE_RINT			0x704
+#define PPE_CFG_STS_MODE		0x880
+#else
+#define PPE_CFG_CPU_ADD_ADDR		0x580
+#define PPE_CFG_MAX_FRAME_LEN_REG	0x408
 #define PPE_CFG_RX_PKT_MODE_REG		0x438
 #define PPE_CFG_QOS_VMID_GEN		0x500
 #define PPE_CFG_RX_PKT_INT		0x538
@@ -48,8 +59,12 @@
 #define PPE_INTSTS			0x608
 #define PPE_RINT			0x604
 #define PPE_CFG_STS_MODE		0x700
+#endif /* CONFIG_HI13X1_GMAC */
+
 #define PPE_HIS_RX_PKT_CNT		0x804
 
+#define RESET_DREQ_ALL			0xffffffff
+
 /* REG_INTERRUPT */
 #define RCV_INT				BIT(10)
 #define RCV_NOBUF			BIT(8)
@@ -61,8 +76,15 @@
 /* TX descriptor config */
 #define TX_FREE_MEM			BIT(0)
 #define TX_READ_ALLOC_L3		BIT(1)
-#define TX_FINISH_CACHE_INV		BIT(2)
+#if defined(CONFIG_HI13X1_GMAC)
+#define TX_CLEAR_WB			BIT(7)
+#define TX_RELEASE_TO_PPE		BIT(4)
+#define TX_FINISH_CACHE_INV		BIT(6)
+#define TX_POOL_SHIFT			16
+#else
 #define TX_CLEAR_WB			BIT(4)
+#define TX_FINISH_CACHE_INV		BIT(2)
+#endif
 #define TX_L3_CHECKSUM			BIT(5)
 #define TX_LOOP_BACK			BIT(11)
 
@@ -97,18 +119,35 @@
 #define GE_RX_PORT_EN			BIT(1)
 #define GE_TX_PORT_EN			BIT(2)
 
-#define PPE_CFG_STS_RX_PKT_CNT_RC	BIT(12)
-
 #define PPE_CFG_RX_PKT_ALIGN		BIT(18)
-#define PPE_CFG_QOS_VMID_MODE		BIT(14)
+
+#if defined(CONFIG_HI13X1_GMAC)
+#define PPE_CFG_QOS_VMID_GRP_SHIFT	4
+#define PPE_CFG_RX_CTRL_ALIGN_SHIFT	7
+#define PPE_CFG_STS_RX_PKT_CNT_RC	BIT(0)
+#define PPE_CFG_QOS_VMID_MODE		BIT(15)
+#define PPE_CFG_BUS_LOCAL_REL		(BIT(9) | BIT(15) | BIT(19) | BIT(23))
+
+/* buf unit size is cache_line_size, which is 64, so the shift is 6 */
+#define PPE_BUF_SIZE_SHIFT		6
+#define PPE_TX_BUF_HOLD			BIT(31)
+#define CACHE_LINE_MASK			0x3F
+#else
 #define PPE_CFG_QOS_VMID_GRP_SHIFT	8
+#define PPE_CFG_RX_CTRL_ALIGN_SHIFT	11
+#define PPE_CFG_STS_RX_PKT_CNT_RC	BIT(12)
+#define PPE_CFG_QOS_VMID_MODE		BIT(14)
+#define PPE_CFG_BUS_LOCAL_REL		BIT(14)
+
+/* buf unit size is 1, so the shift is 6 */
+#define PPE_BUF_SIZE_SHIFT		0
+#define PPE_TX_BUF_HOLD			0
+#endif /* CONFIG_HI13X1_GMAC */
 
 #define PPE_CFG_RX_FIFO_FSFU		BIT(11)
 #define PPE_CFG_RX_DEPTH_SHIFT		16
 #define PPE_CFG_RX_START_SHIFT		0
-#define PPE_CFG_RX_CTRL_ALIGN_SHIFT	11
 
-#define PPE_CFG_BUS_LOCAL_REL		BIT(14)
 #define PPE_CFG_BUS_BIG_ENDIEN		BIT(0)
 
 #define RX_DESC_NUM			128
@@ -132,26 +171,50 @@
 #define HIP04_MIN_TX_COALESCE_FRAMES	100
 
 struct tx_desc {
+#if defined(CONFIG_HI13X1_GMAC)
+	u32 reserved1[2];
+	u32 send_addr;
+	u16 send_size;
+	u16 data_offset;
+	u32 reserved2[7];
+	u32 cfg;
+	u32 wb_addr;
+	u32 reserved3[3];
+#else
 	u32 send_addr;
 	u32 send_size;
 	u32 next_addr;
 	u32 cfg;
 	u32 wb_addr;
+#endif
 } __aligned(64);
 
 struct rx_desc {
+#if defined(CONFIG_HI13X1_GMAC)
+	u32 reserved1[3];
+	u16 pkt_len;
+	u16 reserved_16;
+	u32 reserved2[6];
+	u32 pkt_err;
+	u32 reserved3[5];
+#else
 	u16 reserved_16;
 	u16 pkt_len;
 	u32 reserve1[3];
 	u32 pkt_err;
 	u32 reserve2[4];
+#endif
 };
 
 struct hip04_priv {
 	void __iomem *base;
+#if defined(CONFIG_HI13X1_GMAC)
+	void __iomem *sysctrl_base;
+#endif
 	int phy_mode;
 	int chan;
 	unsigned int port;
+	unsigned int group;
 	unsigned int speed;
 	unsigned int duplex;
 	unsigned int reg_inten;
@@ -225,6 +288,13 @@ static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex)
 	writel_relaxed(val, priv->base + GE_MODE_CHANGE_REG);
 }
 
+static void hip04_reset_dreq(struct hip04_priv *priv)
+{
+#if defined(CONFIG_HI13X1_GMAC)
+	writel_relaxed(RESET_DREQ_ALL, priv->sysctrl_base + SC_PPE_RESET_DREQ);
+#endif
+}
+
 static void hip04_reset_ppe(struct hip04_priv *priv)
 {
 	u32 val, tmp, timeout = 0;
@@ -245,14 +315,14 @@ static void hip04_config_fifo(struct hip04_priv *priv)
 	val |= PPE_CFG_STS_RX_PKT_CNT_RC;
 	writel_relaxed(val, priv->base + PPE_CFG_STS_MODE);
 
-	val = BIT(priv->port);
+	val = BIT(priv->group);
 	regmap_write(priv->map, priv->port * 4 + PPE_CFG_POOL_GRP, val);
 
-	val = priv->port << PPE_CFG_QOS_VMID_GRP_SHIFT;
+	val = priv->group << PPE_CFG_QOS_VMID_GRP_SHIFT;
 	val |= PPE_CFG_QOS_VMID_MODE;
 	writel_relaxed(val, priv->base + PPE_CFG_QOS_VMID_GEN);
 
-	val = RX_BUF_SIZE;
+	val = RX_BUF_SIZE >> PPE_BUF_SIZE_SHIFT;
 	regmap_write(priv->map, priv->port * 4 + PPE_CFG_RX_BUF_SIZE, val);
 
 	val = RX_DESC_NUM << PPE_CFG_RX_DEPTH_SHIFT;
@@ -289,8 +359,10 @@ static void hip04_config_fifo(struct hip04_priv *priv)
 	val |= GE_RX_STRIP_PAD | GE_RX_PAD_EN;
 	writel_relaxed(val, priv->base + GE_RECV_CONTROL_REG);
 
+#ifndef CONFIG_HI13X1_GMAC
 	val = GE_AUTO_NEG_CTL;
 	writel_relaxed(val, priv->base + GE_TX_LOCAL_PAGE_REG);
+#endif
 }
 
 static void hip04_mac_enable(struct net_device *ndev)
@@ -333,12 +405,18 @@ static void hip04_mac_disable(struct net_device *ndev)
 
 static void hip04_set_xmit_desc(struct hip04_priv *priv, dma_addr_t phys)
 {
-	writel(phys, priv->base + PPE_CFG_CPU_ADD_ADDR);
+	u32 val;
+
+	val = phys >> PPE_BUF_SIZE_SHIFT | PPE_TX_BUF_HOLD;
+	writel(val, priv->base + PPE_CFG_CPU_ADD_ADDR);
 }
 
 static void hip04_set_recv_desc(struct hip04_priv *priv, dma_addr_t phys)
 {
-	regmap_write(priv->map, priv->port * 4 + PPE_CFG_RX_ADDR, phys);
+	u32 val;
+
+	val = phys >> PPE_BUF_SIZE_SHIFT;
+	regmap_write(priv->map, priv->port * 4 + PPE_CFG_RX_ADDR, val);
 }
 
 static u32 hip04_recv_cnt(struct hip04_priv *priv)
@@ -446,11 +524,20 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	priv->tx_skb[tx_head] = skb;
 	priv->tx_phys[tx_head] = phys;
-	desc->send_addr = cpu_to_be32(phys);
-	desc->send_size = cpu_to_be32(skb->len);
-	desc->cfg = cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV);
+
+	desc->send_size = (__force u32)cpu_to_be32(skb->len);
+#if defined(CONFIG_HI13X1_GMAC)
+	desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV
+		| TX_RELEASE_TO_PPE | priv->port << TX_POOL_SHIFT);
+	desc->data_offset = (__force u32)cpu_to_be32(phys & CACHE_LINE_MASK);
+	desc->send_addr =  (__force u32)cpu_to_be32(phys & ~CACHE_LINE_MASK);
+#else
+	desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV);
+	desc->send_addr = (__force u32)cpu_to_be32(phys);
+#endif
 	phys = priv->tx_desc_dma + tx_head * sizeof(struct tx_desc);
-	desc->wb_addr = cpu_to_be32(phys);
+	desc->wb_addr = (__force u32)cpu_to_be32(phys +
+		offsetof(struct tx_desc, send_addr));
 	skb_tx_timestamp(skb);
 
 	hip04_set_xmit_desc(priv, phys);
@@ -511,8 +598,8 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 		priv->rx_phys[priv->rx_head] = 0;
 
 		desc = (struct rx_desc *)skb->data;
-		len = be16_to_cpu(desc->pkt_len);
-		err = be32_to_cpu(desc->pkt_err);
+		len = be16_to_cpu((__force __be16)desc->pkt_len);
+		err = be32_to_cpu((__force __be32)desc->pkt_err);
 
 		if (0 == len) {
 			dev_kfree_skb_any(skb);
@@ -812,7 +899,6 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	struct of_phandle_args arg;
 	struct net_device *ndev;
 	struct hip04_priv *priv;
-	struct resource *res;
 	int irq;
 	int ret;
 
@@ -825,14 +911,21 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ndev);
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(d, res);
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
 		goto init_fail;
 	}
 
-	ret = of_parse_phandle_with_fixed_args(node, "port-handle", 2, 0, &arg);
+#if defined(CONFIG_HI13X1_GMAC)
+	priv->sysctrl_base = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(priv->sysctrl_base)) {
+		ret = PTR_ERR(priv->sysctrl_base);
+		goto init_fail;
+	}
+#endif
+
+	ret = of_parse_phandle_with_fixed_args(node, "port-handle", 3, 0, &arg);
 	if (ret < 0) {
 		dev_warn(d, "no port-handle\n");
 		goto init_fail;
@@ -840,6 +933,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 
 	priv->port = arg.args[0];
 	priv->chan = arg.args[1] * RX_DESC_NUM;
+	priv->group = arg.args[2];
 
 	hrtimer_init(&priv->tx_coalesce_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 
@@ -900,6 +994,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	ndev->irq = irq;
 	netif_napi_add(ndev, &priv->napi, hip04_rx_poll, NAPI_POLL_WEIGHT);
 
+	hip04_reset_dreq(priv);
 	hip04_reset_ppe(priv);
 	if (priv->phy_mode == PHY_INTERFACE_MODE_MII)
 		hip04_config_port(ndev, SPEED_100, DUPLEX_FULL);
diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c
index 2c2808830e95..689f18e3100f 100644
--- a/drivers/net/ethernet/hisilicon/hisi_femac.c
+++ b/drivers/net/ethernet/hisilicon/hisi_femac.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Hisilicon Fast Ethernet MAC Driver
  *
  * Copyright (c) 2016 HiSilicon Technologies Co., Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/circ_buf.h>
@@ -793,7 +781,6 @@ static int hisi_femac_drv_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *node = dev->of_node;
-	struct resource *res;
 	struct net_device *ndev;
 	struct hisi_femac_priv *priv;
 	struct phy_device *phy;
@@ -811,15 +798,13 @@ static int hisi_femac_drv_probe(struct platform_device *pdev)
 	priv->dev = dev;
 	priv->ndev = ndev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->port_base = devm_ioremap_resource(dev, res);
+	priv->port_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->port_base)) {
 		ret = PTR_ERR(priv->port_base);
 		goto out_free_netdev;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	priv->glb_base = devm_ioremap_resource(dev, res);
+	priv->glb_base = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(priv->glb_base)) {
 		ret = PTR_ERR(priv->glb_base);
 		goto out_free_netdev;
@@ -870,7 +855,7 @@ static int hisi_femac_drv_probe(struct platform_device *pdev)
 			   phy_modes(phy->interface));
 
 	mac_addr = of_get_mac_address(node);
-	if (mac_addr)
+	if (!IS_ERR(mac_addr))
 		ether_addr_copy(ndev->dev_addr, mac_addr);
 	if (!is_valid_ether_addr(ndev->dev_addr)) {
 		eth_hw_addr_random(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index e5d853b7b454..349970557c52 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* Copyright (c) 2014 Linaro Ltd.
  * Copyright (c) 2014 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/module.h>
@@ -1101,7 +1097,6 @@ static int hix5hd2_dev_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id = NULL;
 	struct net_device *ndev;
 	struct hix5hd2_priv *priv;
-	struct resource *res;
 	struct mii_bus *bus;
 	const char *mac_addr;
 	int ret;
@@ -1123,15 +1118,13 @@ static int hix5hd2_dev_probe(struct platform_device *pdev)
 	}
 	priv->hw_cap = (unsigned long)of_id->data;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->base = devm_ioremap_resource(dev, res);
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base)) {
 		ret = PTR_ERR(priv->base);
 		goto out_free_netdev;
 	}
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	priv->ctrl_base = devm_ioremap_resource(dev, res);
+	priv->ctrl_base = devm_platform_ioremap_resource(pdev, 1);
 	if (IS_ERR(priv->ctrl_base)) {
 		ret = PTR_ERR(priv->ctrl_base);
 		goto out_free_netdev;
@@ -1229,7 +1222,7 @@ static int hix5hd2_dev_probe(struct platform_device *pdev)
 	}
 
 	mac_addr = of_get_mac_address(node);
-	if (mac_addr)
+	if (!IS_ERR(mac_addr))
 		ether_addr_copy(ndev->dev_addr, mac_addr);
 	if (!is_valid_ether_addr(ndev->dev_addr)) {
 		eth_hw_addr_random(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 79d03f8ee7b1..6d0457eb4faa 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/dma-mapping.h>
@@ -150,7 +146,6 @@ out_buffer_fail:
 /* free desc along with its attached buffer */
 static void hnae_free_desc(struct hnae_ring *ring)
 {
-	hnae_free_buffers(ring);
 	dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr,
 			 ring->desc_num * sizeof(ring->desc[0]),
 			 ring_to_dma_dir(ring));
@@ -183,6 +178,9 @@ static int hnae_alloc_desc(struct hnae_ring *ring)
 /* fini ring, also free the buffer for the ring */
 static void hnae_fini_ring(struct hnae_ring *ring)
 {
+	if (is_rx_ring(ring))
+		hnae_free_buffers(ring);
+
 	hnae_free_desc(ring);
 	kfree(ring->desc_cb);
 	ring->desc_cb = NULL;
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 08a750fb60c4..e9c67c06bfd2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef __HNAE_H
@@ -357,7 +353,7 @@ struct hnae_buf_ops {
 };
 
 struct hnae_queue {
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	phys_addr_t phy_base;
 	struct hnae_ae_dev *dev;	/* the device who use this queue */
 	struct hnae_ring rx_ring ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index a78bfafd212c..b43dec0560a8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 1790cdafd9b8..7fb7a419607d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.h
index 44fe3010dc6d..ec266e7fff83 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _HNS_GMAC_H
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index a97228c93831..8aace2de0cc9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/acpi.h>
@@ -370,7 +366,7 @@ int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn)
 static void hns_mac_param_get(struct mac_params *param,
 			      struct hns_mac_cb *mac_cb)
 {
-	param->vaddr = (void *)mac_cb->vaddr;
+	param->vaddr = mac_cb->vaddr;
 	param->mac_mode = hns_get_enet_interface(mac_cb);
 	ether_addr_copy(param->addr, mac_cb->addr_entry_idx[0].addr);
 	param->mac_id = mac_cb->mac_id;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index fbc75341bef7..3278bf471ddf 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _HNS_DSAF_MAC_H
@@ -187,7 +183,7 @@ struct mac_statistics {
 /*mac para struct ,mac get param from nic or dsaf when initialize*/
 struct mac_params {
 	char addr[ETH_ALEN];
-	void *vaddr; /*virtual address*/
+	u8 __iomem *vaddr; /*virtual address*/
 	struct device *dev;
 	u8 mac_id;
 	/**< Ethernet operation mode (MAC-PHY interface and speed) */
@@ -402,7 +398,7 @@ struct mac_driver {
 	enum mac_mode mac_mode;
 	u8 mac_id;
 	struct hns_mac_cb *mac_cb;
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	unsigned int mac_en_flg;/*you'd better don't enable mac twice*/
 	unsigned int virt_dev_num;
 	struct device *dev;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 3b9e74be5fbd..c1eba421ba82 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/acpi.h>
@@ -1602,8 +1598,6 @@ static void hns_dsaf_set_mac_key(
 		       DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
 	dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
 		       DSAF_TBL_TCAM_KEY_PORT_S, port);
-
-	mac_key->low.bits.port_vlan = le16_to_cpu(mac_key->low.bits.port_vlan);
 }
 
 /**
@@ -1663,8 +1657,8 @@ int hns_dsaf_set_mac_uc_entry(
 	/* default config dvc to 0 */
 	mac_data.tbl_ucast_dvc = 0;
 	mac_data.tbl_ucast_out_port = mac_entry->port_num;
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+	tcam_data.tbl_tcam_data_high = mac_key.high.val;
+	tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 	hns_dsaf_tcam_uc_cfg(dsaf_dev, entry_index, &tcam_data, &mac_data);
 
@@ -1786,9 +1780,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 				     0xff,
 				     mc_mask);
 
-		mask_key.high.val = le32_to_cpu(mask_key.high.val);
-		mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
 		pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
 	}
 
@@ -1840,8 +1831,8 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 		dsaf_dev->ae_dev.name, mac_key.high.val,
 		mac_key.low.val, entry_index);
 
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+	tcam_data.tbl_tcam_data_high = mac_key.high.val;
+	tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 	/* config mc entry with mask */
 	hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data,
@@ -1956,9 +1947,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 		/* config key mask */
 		hns_dsaf_set_mac_key(dsaf_dev, &mask_key, 0x00, 0xff, mc_mask);
 
-		mask_key.high.val = le32_to_cpu(mask_key.high.val);
-		mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
 		pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
 	}
 
@@ -2012,8 +2000,8 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 		soft_mac_entry += entry_index;
 		soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX;
 	} else { /* not zero, just del port, update */
-		tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-		tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+		tcam_data.tbl_tcam_data_high = mac_key.high.val;
+		tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 		hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index,
 				     &tcam_data,
@@ -2750,6 +2738,17 @@ int hns_dsaf_get_regs_count(void)
 	return DSAF_DUMP_REGS_NUM;
 }
 
+static int hns_dsaf_get_port_id(u8 port)
+{
+	if (port < DSAF_SERVICE_NW_NUM)
+		return port;
+
+	if (port >= DSAF_BASE_INNER_PORT_NUM)
+		return port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
+
+	return -EINVAL;
+}
+
 static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 {
 	struct dsaf_tbl_tcam_ucast_cfg tbl_tcam_ucast = {0, 1, 0, 0, 0x80};
@@ -2766,7 +2765,7 @@ static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 	struct hns_mac_cb *mac_cb;
 	u8 addr[ETH_ALEN] = {0};
 	u8 port_num;
-	u16 mskid;
+	int mskid;
 
 	/* promisc use vague table match with vlanid = 0 & macaddr = 0 */
 	hns_dsaf_set_mac_key(dsaf_dev, &mac_key, 0x00, port, addr);
@@ -2815,23 +2814,33 @@ static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 	memset(&temp_key, 0x0, sizeof(temp_key));
 	mask_entry.addr[0] = 0x01;
 	hns_dsaf_set_mac_key(dsaf_dev, &mask_key, mask_entry.in_vlan_id,
-			     port, mask_entry.addr);
+			     0xf, mask_entry.addr);
 	tbl_tcam_mcast.tbl_mcast_item_vld = 1;
 	tbl_tcam_mcast.tbl_mcast_old_en = 0;
 
-	if (port < DSAF_SERVICE_NW_NUM) {
-		mskid = port;
-	} else if (port >= DSAF_BASE_INNER_PORT_NUM) {
-		mskid = port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
-	} else {
+	/* set MAC port to handle multicast */
+	mskid = hns_dsaf_get_port_id(port);
+	if (mskid == -EINVAL) {
 		dev_err(dsaf_dev->dev, "%s,pnum(%d)error,key(%#x:%#x)\n",
 			dsaf_dev->ae_dev.name, port,
 			mask_key.high.val, mask_key.low.val);
 		return;
 	}
+	dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
+		     mskid % 32, 1);
 
+	/* set pool bit map to handle multicast */
+	mskid = hns_dsaf_get_port_id(port_num);
+	if (mskid == -EINVAL) {
+		dev_err(dsaf_dev->dev,
+			"%s, pool bit map pnum(%d)error,key(%#x:%#x)\n",
+			dsaf_dev->ae_dev.name, port_num,
+			mask_key.high.val, mask_key.low.val);
+		return;
+	}
 	dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
 		     mskid % 32, 1);
+
 	memcpy(&temp_key, &mask_key, sizeof(mask_key));
 	hns_dsaf_tcam_mc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_mc,
 				   (struct dsaf_tbl_tcam_data *)(&mask_key),
@@ -3081,6 +3090,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 	dsaf_dev = dev_get_drvdata(&pdev->dev);
 	if (!dsaf_dev) {
 		dev_err(&pdev->dev, "dsaf_dev is NULL\n");
+		put_device(&pdev->dev);
 		return -ENODEV;
 	}
 
@@ -3088,6 +3098,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 	if (AE_IS_VER1(dsaf_dev->dsaf_ver)) {
 		dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n",
 			dsaf_dev->ae_dev.name);
+		put_device(&pdev->dev);
 		return -ENODEV;
 	}
 
@@ -3126,6 +3137,9 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 		dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1);
 		dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit);
 	}
+
+	put_device(&pdev->dev);
+
 	return 0;
 }
 EXPORT_SYMBOL(hns_dsaf_roce_reset);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 0e1cd99831a6..cba04bfa0b3f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef __HNS_DSAF_MAIN_H
@@ -467,4 +463,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     u8 mac_id, u8 port_num);
 int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port);
 
+int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset);
+
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 16294cd3c954..bb6586d0e5af 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include "hns_dsaf_mac.h"
@@ -670,7 +666,7 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en)
 		dsaf_set_field(origin, 1ull << 10, 10, en);
 		dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin);
 	} else {
-		u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
+		u8 __iomem *base_addr = mac_cb->serdes_vaddr +
 				(mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
 		dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, en);
 	}
@@ -758,7 +754,7 @@ struct dsaf_misc_op *hns_misc_op_get(struct dsaf_device *dsaf_dev)
 	return (void *)misc_op;
 }
 
-static int hns_dsaf_dev_match(struct device *dev, void *fwnode)
+static int hns_dsaf_dev_match(struct device *dev, const void *fwnode)
 {
 	return dev->fwnode == fwnode;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h
index 310e80261366..f64c6667dd05 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _HNS_DSAF_MISC_H
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 0942e4916d9d..2b34b553acf3 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/module.h>
@@ -61,7 +57,7 @@ void hns_ppe_set_indir_table(struct hns_ppe_cb *ppe_cb,
 	}
 }
 
-static void __iomem *
+static u8 __iomem *
 hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common)
 {
 	return ppe_common->dsaf_dev->ppe_base + PPE_COMMON_REG_OFFSET;
@@ -83,8 +79,9 @@ static int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
 	else
 		ppe_num = HNS_PPE_DEBUG_NW_ENGINE_NUM;
 
-	ppe_common = devm_kzalloc(dsaf_dev->dev, sizeof(*ppe_common) +
-		ppe_num * sizeof(struct hns_ppe_cb), GFP_KERNEL);
+	ppe_common = devm_kzalloc(dsaf_dev->dev,
+				  struct_size(ppe_common, ppe_cb, ppe_num),
+				  GFP_KERNEL);
 	if (!ppe_common)
 		return -ENOMEM;
 
@@ -110,8 +107,8 @@ hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index)
 	dsaf_dev->ppe_common[comm_index] = NULL;
 }
 
-static void __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
-					int ppe_idx)
+static u8 __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
+				      int ppe_idx)
 {
 	return ppe_common->dsaf_dev->ppe_base + ppe_idx * PPE_REG_OFFSET;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
index f670e63a5a01..2721f1f1ab42 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _HNS_DSAF_PPE_H
@@ -80,7 +76,7 @@ struct hns_ppe_cb {
 	struct hns_ppe_hw_stats hw_stats;
 
 	u8 index;	/* index in a ppe common device */
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	int virq;
 	u32 rss_indir_table[HNS_PPEV2_RSS_IND_TBL_SIZE]; /*shadow indir tab */
 	u32 rss_key[HNS_PPEV2_RSS_KEY_NUM]; /* rss hash key */
@@ -89,7 +85,7 @@ struct hns_ppe_cb {
 struct ppe_common_cb {
 	struct device *dev;
 	struct dsaf_device *dsaf_dev;
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 
 	enum ppe_common_mode ppe_mode;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 5d64519b9b1d..5453597ec629 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/cdev.h>
@@ -458,7 +454,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 		mdnum_ppkt = HNS_RCB_RING_MAX_BD_PER_PKT;
 	} else {
 		ring = &q->tx_ring;
-		ring->io_base = (u8 __iomem *)ring_pair_cb->q.io_base +
+		ring->io_base = ring_pair_cb->q.io_base +
 			HNS_RCB_TX_REG_OFFSET;
 		irq_idx = HNS_RCB_IRQ_IDX_TX;
 		mdnum_ppkt = is_ver1 ? HNS_RCB_RING_MAX_TXBD_PER_PKT :
@@ -764,7 +760,7 @@ static int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
 	}
 }
 
-static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
+static u8 __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
 {
 	struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev;
 
@@ -788,8 +784,9 @@ int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev,
 	int ring_num = hns_rcb_get_ring_num(dsaf_dev);
 
 	rcb_common =
-		devm_kzalloc(dsaf_dev->dev, sizeof(*rcb_common) +
-			ring_num * sizeof(struct ring_pair_cb), GFP_KERNEL);
+		devm_kzalloc(dsaf_dev->dev,
+			     struct_size(rcb_common, ring_pair_cb, ring_num),
+			     GFP_KERNEL);
 	if (!rcb_common) {
 		dev_err(dsaf_dev->dev, "rcb common devm_kzalloc fail!\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
index 2319b772a271..3741befb914e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _HNS_DSAF_RCB_H
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index b9733b0b8482..47ccb6e0fcaa 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _DSAF_REG_H_
@@ -1018,7 +1014,7 @@
 #define XGMAC_PAUSE_CTL_RSP_MODE_B	2
 #define XGMAC_PAUSE_CTL_TX_XOFF_B	3
 
-static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
+static inline void dsaf_write_reg(u8 __iomem *base, u32 reg, u32 value)
 {
 	writel(value, base + reg);
 }
@@ -1053,7 +1049,7 @@ static inline int dsaf_read_syscon(struct regmap *base, u32 reg, u32 *val)
 #define dsaf_set_bit(origin, shift, val) \
 	dsaf_set_field((origin), (1ull << (shift)), (shift), (val))
 
-static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline void dsaf_set_reg_field(u8 __iomem *base, u32 reg, u32 mask,
 				      u32 shift, u32 val)
 {
 	u32 origin = dsaf_read_reg(base, reg);
@@ -1073,7 +1069,7 @@ static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask,
 #define dsaf_get_bit(origin, shift) \
 	dsaf_get_field((origin), (1ull << (shift)), (shift))
 
-static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline u32 dsaf_get_reg_field(u8 __iomem *base, u32 reg, u32 mask,
 				     u32 shift)
 {
 	u32 origin;
@@ -1089,11 +1085,11 @@ static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask,
 	dsaf_get_reg_field((dev)->io_base, (reg), (1ull << (bit)), (bit))
 
 #define dsaf_write_b(addr, data)\
-	writeb((data), (__iomem unsigned char *)(addr))
+	writeb((data), (__iomem u8 *)(addr))
 #define dsaf_read_b(addr)\
-	readb((__iomem unsigned char *)(addr))
+	readb((__iomem u8 *)(addr))
 
 #define hns_mac_reg_read64(drv, offset) \
-	readq((__iomem void *)(((u8 *)(drv)->io_base + 0xc00 + (offset))))
+	readq((__iomem void *)(((drv)->io_base + 0xc00 + (offset))))
 
 #endif	/* _DSAF_REG_H */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index ba4316910dea..0a3dbab2dfc9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/io-64-nonatomic-hi-lo.h>
@@ -129,7 +125,7 @@ static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv)
 	dsaf_set_bit(val, XGMAC_UNIDIR_EN_B, 0);
 	dsaf_set_bit(val, XGMAC_RF_TX_EN_B, 1);
 	dsaf_set_field(val, XGMAC_LF_RF_INSERT_M, XGMAC_LF_RF_INSERT_S, 0);
-	dsaf_write_reg(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
+	dsaf_write_dev(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
 }
 
 /**
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h
index da6c5343d3e1..e1b3db980712 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _HNS_XGMAC_H
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 60e7d7ae3787..2235dd55fab2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/clk.h>
@@ -29,9 +25,6 @@
 
 #define SERVICE_TIMER_HZ (1 * HZ)
 
-#define NIC_TX_CLEAN_MAX_NUM 256
-#define NIC_RX_CLEAN_MAX_NUM 64
-
 #define RCB_IRQ_NOT_INITED 0
 #define RCB_IRQ_INITED 1
 #define HNS_BUFFER_SIZE_2048 2048
@@ -376,8 +369,6 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 	wmb(); /* commit all data before submit */
 	assert(skb->queue_mapping < priv->ae_handle->q_num);
 	hnae_queue_xmit(priv->ae_handle->qs[skb->queue_mapping], buf_num);
-	ring->stats.tx_pkts++;
-	ring->stats.tx_bytes += skb->len;
 
 	return NETDEV_TX_OK;
 
@@ -603,7 +594,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 	} else {
 		ring->stats.seg_pkt_cnt++;
 
-		pull_len = eth_get_headlen(va, HNS_RX_HEAD_SIZE);
+		pull_len = eth_get_headlen(ndev, va, HNS_RX_HEAD_SIZE);
 		memcpy(__skb_put(skb, pull_len), va,
 		       ALIGN(pull_len, sizeof(long)));
 
@@ -999,6 +990,9 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 		/* issue prefetch for next Tx descriptor */
 		prefetch(&ring->desc_cb[ring->next_to_clean]);
 	}
+	/* update tx ring statistics. */
+	ring->stats.tx_pkts += pkts;
+	ring->stats.tx_bytes += bytes;
 
 	NETIF_TX_UNLOCK(ring);
 
@@ -1964,8 +1958,7 @@ static void hns_nic_get_stats64(struct net_device *ndev,
 
 static u16
 hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
-		     struct net_device *sb_dev,
-		     select_queue_fallback_t fallback)
+		     struct net_device *sb_dev)
 {
 	struct ethhdr *eth_hdr = (struct ethhdr *)skb->data;
 	struct hns_nic_priv *priv = netdev_priv(ndev);
@@ -1975,7 +1968,7 @@ hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	    is_multicast_ether_addr(eth_hdr->h_dest))
 		return 0;
 	else
-		return fallback(ndev, skb, NULL);
+		return netdev_pick_tx(ndev, skb, NULL);
 }
 
 static const struct net_device_ops hns_nic_netdev_ops = {
@@ -2152,7 +2145,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
 			hns_nic_tx_fini_pro_v2;
 
 		netif_napi_add(priv->netdev, &rd->napi,
-			       hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM);
+			       hns_nic_common_poll, NAPI_POLL_WEIGHT);
 		rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
 	}
 	for (i = h->q_num; i < h->q_num * 2; i++) {
@@ -2165,7 +2158,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
 			hns_nic_rx_fini_pro_v2;
 
 		netif_napi_add(priv->netdev, &rd->napi,
-			       hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM);
+			       hns_nic_common_poll, NAPI_POLL_WEIGHT);
 		rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
 	}
 
@@ -2377,6 +2370,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 		ndev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
 			NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6;
+		ndev->vlan_features |= NETIF_F_TSO | NETIF_F_TSO6;
 		ndev->max_mtu = MAC_MAX_MTU_V2 -
 				(ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
 		break;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
index 26e9afcbdd50..ffa9d6573f54 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h
@@ -1,10 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef __HNS_ENET_H
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index ce15d2350db9..717fccc2efba 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/etherdevice.h>
@@ -339,6 +335,7 @@ static int __lb_setup(struct net_device *ndev,
 static int __lb_up(struct net_device *ndev,
 		   enum hnae_loop loop_mode)
 {
+#define NIC_LB_TEST_WAIT_PHY_LINK_TIME 300
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
 	int speed, duplex;
@@ -365,6 +362,9 @@ static int __lb_up(struct net_device *ndev,
 
 	h->dev->ops->adjust_link(h, speed, duplex);
 
+	/* wait adjust link done and phy ready */
+	msleep(NIC_LB_TEST_WAIT_PHY_LINK_TIME);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 691d12174902..8ad5292eebbe 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -21,6 +21,7 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_SET_MACVLAN,		/* (VF -> PF) set unicast filter */
 	HCLGE_MBX_API_NEGOTIATE,	/* (VF -> PF) negotiate API version */
 	HCLGE_MBX_GET_QINFO,		/* (VF -> PF) get queue config */
+	HCLGE_MBX_GET_QDEPTH,		/* (VF -> PF) get queue depth */
 	HCLGE_MBX_GET_TCINFO,		/* (VF -> PF) get TC config */
 	HCLGE_MBX_GET_RETA,		/* (VF -> PF) get RETA */
 	HCLGE_MBX_GET_RSS_KEY,		/* (VF -> PF) get RSS key */
@@ -40,6 +41,12 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_SET_ALIVE,		/* (VF -> PF) set alive state */
 	HCLGE_MBX_SET_MTU,		/* (VF -> PF) set mtu */
 	HCLGE_MBX_GET_QID_IN_PF,	/* (VF -> PF) get queue id in pf */
+	HCLGE_MBX_LINK_STAT_MODE,	/* (PF -> VF) link mode has changed */
+	HCLGE_MBX_GET_LINK_MODE,	/* (VF -> PF) get the link mode of pf */
+	HLCGE_MBX_PUSH_VLAN_INFO,	/* (PF -> VF) push port base vlan */
+	HCLGE_MBX_GET_MEDIA_TYPE,       /* (VF -> PF) get media type */
+
+	HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */
 };
 
 /* below are per-VF mac-vlan subcodes */
@@ -57,6 +64,8 @@ enum hclge_mbx_vlan_cfg_subcode {
 	HCLGE_MBX_VLAN_FILTER = 0,	/* set vlan filter */
 	HCLGE_MBX_VLAN_TX_OFF_CFG,	/* set tx side vlan offload */
 	HCLGE_MBX_VLAN_RX_OFF_CFG,	/* set rx side vlan offload */
+	HCLGE_MBX_PORT_BASE_VLAN_CFG,	/* set port based vlan configuration */
+	HCLGE_MBX_GET_PORT_BASE_VLAN_STATE,	/* get port based vlan state */
 };
 
 #define HCLGE_MBX_MAX_MSG_SIZE	16
@@ -75,12 +84,15 @@ struct hclgevf_mbx_resp_status {
 struct hclge_mbx_vf_to_pf_cmd {
 	u8 rsv;
 	u8 mbx_src_vfid; /* Auto filled by IMP */
-	u8 rsv1[2];
+	u8 mbx_need_resp;
+	u8 rsv1[1];
 	u8 msg_len;
 	u8 rsv2[3];
 	u8 msg[HCLGE_MBX_MAX_MSG_SIZE];
 };
 
+#define HCLGE_MBX_NEED_RESP_BIT		BIT(0)
+
 struct hclge_mbx_pf_to_vf_cmd {
 	u8 dest_vfid;
 	u8 rsv[3];
@@ -102,7 +114,7 @@ struct hclgevf_mbx_arq_ring {
 	struct hclgevf_dev *hdev;
 	u32 head;
 	u32 tail;
-	u32 count;
+	atomic_t count;
 	u16 msg_q[HCLGE_MBX_MAX_ARQ_MSG_NUM][HCLGE_MBX_MAX_ARQ_MSG_SIZE];
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 781e5dee3c70..908d4f45c06a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -16,29 +16,26 @@ static LIST_HEAD(hnae3_ae_dev_list);
  */
 static DEFINE_MUTEX(hnae3_common_lock);
 
-static bool hnae3_client_match(enum hnae3_client_type client_type,
-			       enum hnae3_dev_type dev_type)
+static bool hnae3_client_match(enum hnae3_client_type client_type)
 {
-	if ((dev_type == HNAE3_DEV_KNIC) && (client_type == HNAE3_CLIENT_KNIC ||
-					     client_type == HNAE3_CLIENT_ROCE))
-		return true;
-
-	if (dev_type == HNAE3_DEV_UNIC && client_type == HNAE3_CLIENT_UNIC)
+	if (client_type == HNAE3_CLIENT_KNIC ||
+	    client_type == HNAE3_CLIENT_ROCE)
 		return true;
 
 	return false;
 }
 
 void hnae3_set_client_init_flag(struct hnae3_client *client,
-				struct hnae3_ae_dev *ae_dev, int inited)
+				struct hnae3_ae_dev *ae_dev,
+				unsigned int inited)
 {
+	if (!client || !ae_dev)
+		return;
+
 	switch (client->type) {
 	case HNAE3_CLIENT_KNIC:
 		hnae3_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
 		break;
-	case HNAE3_CLIENT_UNIC:
-		hnae3_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited);
-		break;
 	case HNAE3_CLIENT_ROCE:
 		hnae3_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited);
 		break;
@@ -58,10 +55,6 @@ static int hnae3_get_client_init_flag(struct hnae3_client *client,
 		inited = hnae3_get_bit(ae_dev->flag,
 				       HNAE3_KNIC_CLIENT_INITED_B);
 		break;
-	case HNAE3_CLIENT_UNIC:
-		inited = hnae3_get_bit(ae_dev->flag,
-				       HNAE3_UNIC_CLIENT_INITED_B);
-		break;
 	case HNAE3_CLIENT_ROCE:
 		inited = hnae3_get_bit(ae_dev->flag,
 				       HNAE3_ROCE_CLIENT_INITED_B);
@@ -73,34 +66,38 @@ static int hnae3_get_client_init_flag(struct hnae3_client *client,
 	return inited;
 }
 
-static int hnae3_match_n_instantiate(struct hnae3_client *client,
-				     struct hnae3_ae_dev *ae_dev, bool is_reg)
+static int hnae3_init_client_instance(struct hnae3_client *client,
+				      struct hnae3_ae_dev *ae_dev)
 {
 	int ret;
 
 	/* check if this client matches the type of ae_dev */
-	if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
+	if (!(hnae3_client_match(client->type) &&
 	      hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
 		return 0;
 	}
 
-	/* now, (un-)instantiate client by calling lower layer */
-	if (is_reg) {
-		ret = ae_dev->ops->init_client_instance(client, ae_dev);
-		if (ret)
-			dev_err(&ae_dev->pdev->dev,
-				"fail to instantiate client, ret = %d\n", ret);
+	ret = ae_dev->ops->init_client_instance(client, ae_dev);
+	if (ret)
+		dev_err(&ae_dev->pdev->dev,
+			"fail to instantiate client, ret = %d\n", ret);
 
-		return ret;
-	}
+	return ret;
+}
+
+static void hnae3_uninit_client_instance(struct hnae3_client *client,
+					 struct hnae3_ae_dev *ae_dev)
+{
+	/* check if this client matches the type of ae_dev */
+	if (!(hnae3_client_match(client->type) &&
+	      hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B)))
+		return;
 
 	if (hnae3_get_client_init_flag(client, ae_dev)) {
 		ae_dev->ops->uninit_client_instance(client, ae_dev);
 
 		hnae3_set_client_init_flag(client, ae_dev, 0);
 	}
-
-	return 0;
 }
 
 int hnae3_register_client(struct hnae3_client *client)
@@ -109,6 +106,9 @@ int hnae3_register_client(struct hnae3_client *client)
 	struct hnae3_ae_dev *ae_dev;
 	int ret = 0;
 
+	if (!client)
+		return -ENODEV;
+
 	mutex_lock(&hnae3_common_lock);
 	/* one system should only have one client for every type */
 	list_for_each_entry(client_tmp, &hnae3_client_list, node) {
@@ -123,7 +123,7 @@ int hnae3_register_client(struct hnae3_client *client)
 		/* if the client could not be initialized on current port, for
 		 * any error reasons, move on to next available port
 		 */
-		ret = hnae3_match_n_instantiate(client, ae_dev, true);
+		ret = hnae3_init_client_instance(client, ae_dev);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
 				"match and instantiation failed for port, ret = %d\n",
@@ -141,10 +141,13 @@ void hnae3_unregister_client(struct hnae3_client *client)
 {
 	struct hnae3_ae_dev *ae_dev;
 
+	if (!client)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 	/* un-initialize the client on every matched port */
 	list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
-		hnae3_match_n_instantiate(client, ae_dev, false);
+		hnae3_uninit_client_instance(client, ae_dev);
 	}
 
 	list_del(&client->node);
@@ -163,6 +166,9 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 	struct hnae3_client *client;
 	int ret = 0;
 
+	if (!ae_algo)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 
 	list_add_tail(&ae_algo->node, &hnae3_ae_algo_list);
@@ -173,8 +179,12 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 		if (!id)
 			continue;
 
-		/* ae_dev init should set flag */
+		if (!ae_algo->ops) {
+			dev_err(&ae_dev->pdev->dev, "ae_algo ops are null\n");
+			continue;
+		}
 		ae_dev->ops = ae_algo->ops;
+
 		ret = ae_algo->ops->init_ae_dev(ae_dev);
 		if (ret) {
 			dev_err(&ae_dev->pdev->dev,
@@ -182,13 +192,14 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 			continue;
 		}
 
+		/* ae_dev init should set flag */
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 
 		/* check the client list for the match with this ae_dev type and
 		 * initialize the figure out client instance
 		 */
 		list_for_each_entry(client, &hnae3_client_list, node) {
-			ret = hnae3_match_n_instantiate(client, ae_dev, true);
+			ret = hnae3_init_client_instance(client, ae_dev);
 			if (ret)
 				dev_err(&ae_dev->pdev->dev,
 					"match and instantiation failed, ret = %d\n",
@@ -209,6 +220,9 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
 	struct hnae3_ae_dev *ae_dev;
 	struct hnae3_client *client;
 
+	if (!ae_algo)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_dev */
 	list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
@@ -223,10 +237,11 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
 		 * un-initialize the figure out client instance
 		 */
 		list_for_each_entry(client, &hnae3_client_list, node)
-			hnae3_match_n_instantiate(client, ae_dev, false);
+			hnae3_uninit_client_instance(client, ae_dev);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+		ae_dev->ops = NULL;
 	}
 
 	list_del(&ae_algo->node);
@@ -238,13 +253,16 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo);
  * @ae_dev: the AE device
  * NOTE: the duplicated name will not be checked
  */
-void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
+int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	const struct pci_device_id *id;
 	struct hnae3_ae_algo *ae_algo;
 	struct hnae3_client *client;
 	int ret = 0;
 
+	if (!ae_dev)
+		return -ENODEV;
+
 	mutex_lock(&hnae3_common_lock);
 
 	list_add_tail(&ae_dev->node, &hnae3_ae_dev_list);
@@ -255,14 +273,13 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 		if (!id)
 			continue;
 
-		ae_dev->ops = ae_algo->ops;
-
-		if (!ae_dev->ops) {
-			dev_err(&ae_dev->pdev->dev, "ae_dev ops are null\n");
+		if (!ae_algo->ops) {
+			dev_err(&ae_dev->pdev->dev, "ae_algo ops are null\n");
+			ret = -EOPNOTSUPP;
 			goto out_err;
 		}
+		ae_dev->ops = ae_algo->ops;
 
-		/* ae_dev init should set flag */
 		ret = ae_dev->ops->init_ae_dev(ae_dev);
 		if (ret) {
 			dev_err(&ae_dev->pdev->dev,
@@ -270,6 +287,7 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 			goto out_err;
 		}
 
+		/* ae_dev init should set flag */
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 		break;
 	}
@@ -278,15 +296,22 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 	 * initialize the figure out client instance
 	 */
 	list_for_each_entry(client, &hnae3_client_list, node) {
-		ret = hnae3_match_n_instantiate(client, ae_dev, true);
+		ret = hnae3_init_client_instance(client, ae_dev);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
 				"match and instantiation failed, ret = %d\n",
 				ret);
 	}
 
+	mutex_unlock(&hnae3_common_lock);
+
+	return 0;
+
 out_err:
+	list_del(&ae_dev->node);
 	mutex_unlock(&hnae3_common_lock);
+
+	return ret;
 }
 EXPORT_SYMBOL(hnae3_register_ae_dev);
 
@@ -299,6 +324,9 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
 	struct hnae3_ae_algo *ae_algo;
 	struct hnae3_client *client;
 
+	if (!ae_dev)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_algo */
 	list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) {
@@ -310,10 +338,11 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
 			continue;
 
 		list_for_each_entry(client, &hnae3_client_list, node)
-			hnae3_match_n_instantiate(client, ae_dev, false);
+			hnae3_uninit_client_instance(client, ae_dev);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+		ae_dev->ops = NULL;
 	}
 
 	list_del(&ae_dev->node);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 36eab37d8a40..48c7b70fc2c4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -87,7 +87,8 @@ struct hnae3_queue {
 	struct hnae3_handle *handle;
 	int tqp_index;	/* index in a handle */
 	u32 buf_size;	/* size for hnae_desc->addr, preset by AE */
-	u16 desc_num;	/* total number of desc */
+	u16 tx_desc_num;/* total number of tx desc */
+	u16 rx_desc_num;/* total number of rx desc */
 };
 
 /*hnae3 loop mode*/
@@ -101,15 +102,9 @@ enum hnae3_loop {
 
 enum hnae3_client_type {
 	HNAE3_CLIENT_KNIC,
-	HNAE3_CLIENT_UNIC,
 	HNAE3_CLIENT_ROCE,
 };
 
-enum hnae3_dev_type {
-	HNAE3_DEV_KNIC,
-	HNAE3_DEV_UNIC,
-};
-
 /* mac media type */
 enum hnae3_media_type {
 	HNAE3_MEDIA_TYPE_UNKNOWN,
@@ -119,11 +114,31 @@ enum hnae3_media_type {
 	HNAE3_MEDIA_TYPE_NONE,
 };
 
+/* must be consistent with definition in firmware */
+enum hnae3_module_type {
+	HNAE3_MODULE_TYPE_UNKNOWN	= 0x00,
+	HNAE3_MODULE_TYPE_FIBRE_LR	= 0x01,
+	HNAE3_MODULE_TYPE_FIBRE_SR	= 0x02,
+	HNAE3_MODULE_TYPE_AOC		= 0x03,
+	HNAE3_MODULE_TYPE_CR		= 0x04,
+	HNAE3_MODULE_TYPE_KR		= 0x05,
+	HNAE3_MODULE_TYPE_TP		= 0x06,
+
+};
+
+enum hnae3_fec_mode {
+	HNAE3_FEC_AUTO = 0,
+	HNAE3_FEC_BASER,
+	HNAE3_FEC_RS,
+	HNAE3_FEC_USER_DEF,
+};
+
 enum hnae3_reset_notify_type {
 	HNAE3_UP_CLIENT,
 	HNAE3_DOWN_CLIENT,
 	HNAE3_INIT_CLIENT,
 	HNAE3_UNINIT_CLIENT,
+	HNAE3_RESTORE_CLIENT,
 };
 
 enum hnae3_reset_type {
@@ -133,7 +148,6 @@ enum hnae3_reset_type {
 	HNAE3_VF_FULL_RESET,
 	HNAE3_FLR_RESET,
 	HNAE3_FUNC_RESET,
-	HNAE3_CORE_RESET,
 	HNAE3_GLOBAL_RESET,
 	HNAE3_IMP_RESET,
 	HNAE3_UNKNOWN_RESET,
@@ -145,6 +159,13 @@ enum hnae3_flr_state {
 	HNAE3_FLR_DONE,
 };
 
+enum hnae3_port_base_vlan_state {
+	HNAE3_PORT_BASE_VLAN_DISABLE,
+	HNAE3_PORT_BASE_VLAN_ENABLE,
+	HNAE3_PORT_BASE_VLAN_MODIFY,
+	HNAE3_PORT_BASE_VLAN_NOCHANGE,
+};
+
 struct hnae3_vector_info {
 	u8 __iomem *io_addr;
 	int vector;
@@ -192,7 +213,7 @@ struct hnae3_ae_dev {
 	const struct hnae3_ae_ops *ops;
 	struct list_head node;
 	u32 flag;
-	enum hnae3_dev_type dev_type;
+	unsigned long hw_err_reset_req;
 	enum hnae3_reset_type reset_type;
 	void *priv;
 };
@@ -220,10 +241,10 @@ struct hnae3_ae_dev {
  *   non-ok
  * get_ksettings_an_result()
  *   Get negotiation status,speed and duplex
- * update_speed_duplex_h()
- *   Update hardware speed and duplex
  * get_media_type()
  *   Get media type of MAC
+ * check_port_speed()
+ *   Check target speed whether is supported
  * adjust_link()
  *   Adjust link status
  * set_loopback()
@@ -240,6 +261,10 @@ struct hnae3_ae_dev {
  *   set auto autonegotiation of pause frame use
  * get_autoneg()
  *   get auto autonegotiation of pause frame use
+ * restart_autoneg()
+ *   restart autonegotiation
+ * halt_autoneg()
+ *   halt/resume autonegotiation when autonegotiation on
  * get_coalesce_usecs()
  *   get usecs to delay a TX interrupt after a packet is sent
  * get_rx_max_coalesced_frames()
@@ -308,10 +333,14 @@ struct hnae3_ae_dev {
  *   Set vlan filter config of Ports
  * set_vf_vlan_filter()
  *   Set vlan filter config of vf
+ * restore_vlan_table()
+ *   Restore vlan filter entries after reset
  * enable_hw_strip_rxvtag()
  *   Enable/disable hardware strip vlan tag of packets received
  * set_gro_en
  *   Enable/disable HW GRO
+ * add_arfs_entry
+ *   Check the 5-tuples of flow, and create flow director rule
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
@@ -330,11 +359,15 @@ struct hnae3_ae_ops {
 	void (*get_ksettings_an_result)(struct hnae3_handle *handle,
 					u8 *auto_neg, u32 *speed, u8 *duplex);
 
-	int (*update_speed_duplex_h)(struct hnae3_handle *handle);
 	int (*cfg_mac_speed_dup_h)(struct hnae3_handle *handle, int speed,
 				   u8 duplex);
 
-	void (*get_media_type)(struct hnae3_handle *handle, u8 *media_type);
+	void (*get_media_type)(struct hnae3_handle *handle, u8 *media_type,
+			       u8 *module_type);
+	int (*check_port_speed)(struct hnae3_handle *handle, u32 speed);
+	void (*get_fec)(struct hnae3_handle *handle, u8 *fec_ability,
+			u8 *fec_mode);
+	int (*set_fec)(struct hnae3_handle *handle, u32 fec_mode);
 	void (*adjust_link)(struct hnae3_handle *handle, int speed, int duplex);
 	int (*set_loopback)(struct hnae3_handle *handle,
 			    enum hnae3_loop loop_mode, bool en);
@@ -350,6 +383,8 @@ struct hnae3_ae_ops {
 
 	int (*set_autoneg)(struct hnae3_handle *handle, bool enable);
 	int (*get_autoneg)(struct hnae3_handle *handle);
+	int (*restart_autoneg)(struct hnae3_handle *handle);
+	int (*halt_autoneg)(struct hnae3_handle *handle, bool halt);
 
 	void (*get_coalesce_usecs)(struct hnae3_handle *handle,
 				   u32 *tx_usecs, u32 *rx_usecs);
@@ -382,7 +417,8 @@ struct hnae3_ae_ops {
 	void (*update_stats)(struct hnae3_handle *handle,
 			     struct net_device_stats *net_stats);
 	void (*get_stats)(struct hnae3_handle *handle, u64 *data);
-
+	void (*get_mac_pause_stats)(struct hnae3_handle *handle, u64 *tx_cnt,
+				    u64 *rx_cnt);
 	void (*get_strings)(struct hnae3_handle *handle,
 			    u32 stringset, u8 *data);
 	int (*get_sset_count)(struct hnae3_handle *handle, int stringset);
@@ -426,13 +462,16 @@ struct hnae3_ae_ops {
 				  u16 vlan, u8 qos, __be16 proto);
 	int (*enable_hw_strip_rxvtag)(struct hnae3_handle *handle, bool enable);
 	void (*reset_event)(struct pci_dev *pdev, struct hnae3_handle *handle);
+	enum hnae3_reset_type (*get_reset_level)(struct hnae3_ae_dev *ae_dev,
+						 unsigned long *addr);
 	void (*set_default_reset_request)(struct hnae3_ae_dev *ae_dev,
 					  enum hnae3_reset_type rst_type);
 	void (*get_channels)(struct hnae3_handle *handle,
 			     struct ethtool_channels *ch);
 	void (*get_tqps_and_rss_info)(struct hnae3_handle *h,
 				      u16 *alloc_tqps, u16 *max_rss_size);
-	int (*set_channels)(struct hnae3_handle *handle, u32 new_tqps_num);
+	int (*set_channels)(struct hnae3_handle *handle, u32 new_tqps_num,
+			    bool rxfh_configured);
 	void (*get_flowctrl_adv)(struct hnae3_handle *handle,
 				 u32 *flowctrl_adv);
 	int (*set_led_id)(struct hnae3_handle *handle,
@@ -454,14 +493,19 @@ struct hnae3_ae_ops {
 				struct ethtool_rxnfc *cmd, u32 *rule_locs);
 	int (*restore_fd_rules)(struct hnae3_handle *handle);
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
-	int (*dbg_run_cmd)(struct hnae3_handle *handle, char *cmd_buf);
+	int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id,
+			      u16 flow_id, struct flow_keys *fkeys);
+	int (*dbg_run_cmd)(struct hnae3_handle *handle, const char *cmd_buf);
 	pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev);
 	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
 	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
 	unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
-	int (*set_gro_en)(struct hnae3_handle *handle, int enable);
+	int (*set_gro_en)(struct hnae3_handle *handle, bool enable);
 	u16 (*get_global_queue_id)(struct hnae3_handle *handle, u16 queue_id);
 	void (*set_timer_task)(struct hnae3_handle *handle, bool enable);
+	int (*mac_connect_phy)(struct hnae3_handle *handle);
+	void (*mac_disconnect_phy)(struct hnae3_handle *handle);
+	void (*restore_vlan_table)(struct hnae3_handle *handle);
 };
 
 struct hnae3_dcb_ops {
@@ -475,7 +519,6 @@ struct hnae3_dcb_ops {
 	u8   (*getdcbx)(struct hnae3_handle *);
 	u8   (*setdcbx)(struct hnae3_handle *, u8);
 
-	int (*map_update)(struct hnae3_handle *);
 	int (*setup_tc)(struct hnae3_handle *, u8, u8 *);
 };
 
@@ -500,8 +543,10 @@ struct hnae3_tc_info {
 struct hnae3_knic_private_info {
 	struct net_device *netdev; /* Set by KNIC client when init instance */
 	u16 rss_size;		   /* Allocated RSS queues */
+	u16 req_rss_size;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;
+	u16 num_rx_desc;
 
 	u8 num_tc;		   /* Total number of enabled TCs */
 	u8 prio_tc[HNAE3_MAX_USER_PRIO];  /* TC indexed by prio */
@@ -533,7 +578,9 @@ struct hnae3_roce_private_info {
 struct hnae3_unic_private_info {
 	struct net_device *netdev;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;
+	u16 num_rx_desc;
+
 	u16 num_tqps;	/* total number of tqps in this handle */
 	struct hnae3_queue **tqp;  /* array base of all TQPs of this instance */
 };
@@ -569,8 +616,13 @@ struct hnae3_handle {
 
 	u32 numa_node_mask;	/* for multi-chip support */
 
+	enum hnae3_port_base_vlan_state port_base_vlan_state;
+
 	u8 netdev_flags;
 	struct dentry *hnae3_dbgfs;
+
+	/* Network interface message level enabled bits */
+	u32 msg_enable;
 };
 
 #define hnae3_set_field(origin, mask, shift, val) \
@@ -585,7 +637,7 @@ struct hnae3_handle {
 #define hnae3_get_bit(origin, shift) \
 	hnae3_get_field((origin), (0x1 << (shift)), (shift))
 
-void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
+int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
 void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
 
 void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo);
@@ -595,5 +647,6 @@ void hnae3_unregister_client(struct hnae3_client *client);
 int hnae3_register_client(struct hnae3_client *client);
 
 void hnae3_set_client_init_flag(struct hnae3_client *client,
-				struct hnae3_ae_dev *ae_dev, int inited);
+				struct hnae3_ae_dev *ae_dev,
+				unsigned int inited);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
index b6fabbbdfd5b..d2ec4c573bf8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
@@ -4,8 +4,7 @@
 #include "hnae3.h"
 #include "hns3_enet.h"
 
-static
-int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
+static int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
@@ -18,8 +17,7 @@ int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
 	return -EOPNOTSUPP;
 }
 
-static
-int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
+static int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
@@ -32,8 +30,7 @@ int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
 	return -EOPNOTSUPP;
 }
 
-static
-int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+static int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
@@ -46,8 +43,7 @@ int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
 	return -EOPNOTSUPP;
 }
 
-static
-int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
+static int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 0de543faa5b1..a4b937286f55 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -11,7 +11,8 @@
 
 static struct dentry *hns3_dbgfs_root;
 
-static int hns3_dbg_queue_info(struct hnae3_handle *h, char *cmd_buf)
+static int hns3_dbg_queue_info(struct hnae3_handle *h,
+			       const char *cmd_buf)
 {
 	struct hns3_nic_priv *priv = h->priv;
 	struct hns3_nic_ring_data *ring_data;
@@ -155,7 +156,7 @@ static int hns3_dbg_queue_map(struct hnae3_handle *h)
 	return 0;
 }
 
-static int hns3_dbg_bd_info(struct hnae3_handle *h, char *cmd_buf)
+static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf)
 {
 	struct hns3_nic_priv *priv = h->priv;
 	struct hns3_nic_ring_data *ring_data;
@@ -239,6 +240,10 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "queue info [number]\n");
 	dev_info(&h->pdev->dev, "queue map\n");
 	dev_info(&h->pdev->dev, "bd info [q_num] <bd index>\n");
+
+	if (!hns3_is_phys_func(h->pdev))
+		return;
+
 	dev_info(&h->pdev->dev, "dump fd tcam\n");
 	dev_info(&h->pdev->dev, "dump tc\n");
 	dev_info(&h->pdev->dev, "dump tm map [q_num]\n");
@@ -247,6 +252,10 @@ static void hns3_dbg_help(struct hnae3_handle *h)
 	dev_info(&h->pdev->dev, "dump qos pri map\n");
 	dev_info(&h->pdev->dev, "dump qos buf cfg\n");
 	dev_info(&h->pdev->dev, "dump mng tbl\n");
+	dev_info(&h->pdev->dev, "dump reset info\n");
+	dev_info(&h->pdev->dev, "dump m7 info\n");
+	dev_info(&h->pdev->dev, "dump ncl_config <offset> <length>(in hex)\n");
+	dev_info(&h->pdev->dev, "dump mac tnl status\n");
 
 	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
 	strncat(printf_buf, "dump reg [[bios common] [ssu <prt_id>]",
@@ -341,6 +350,8 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
 		ret = hns3_dbg_bd_info(handle, cmd_buf);
 	else if (handle->ae_algo->ops->dbg_run_cmd)
 		ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf);
+	else
+		ret = -EOPNOTSUPP;
 
 	if (ret)
 		hns3_dbg_help(handle);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 1bf7a5f116a0..310afa708831 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -4,6 +4,9 @@
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
@@ -14,6 +17,7 @@
 #include <linux/sctp.h>
 #include <linux/vermagic.h>
 #include <net/gre.h>
+#include <net/ip6_checksum.h>
 #include <net/pkt_cls.h>
 #include <net/tcp.h>
 #include <net/vxlan.h>
@@ -21,8 +25,10 @@
 #include "hnae3.h"
 #include "hns3_enet.h"
 
-static void hns3_clear_all_ring(struct hnae3_handle *h);
-static void hns3_force_clear_all_rx_ring(struct hnae3_handle *h);
+#define hns3_set_field(origin, shift, val)	((origin) |= ((val) << (shift)))
+#define hns3_tx_bd_count(S)	DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE)
+
+static void hns3_clear_all_ring(struct hnae3_handle *h, bool force);
 static void hns3_remove_hw_addr(struct net_device *netdev);
 
 static const char hns3_driver_name[] = "hns3";
@@ -32,6 +38,13 @@ static const char hns3_driver_string[] =
 static const char hns3_copyright[] = "Copyright (c) 2017 Huawei Corporation.";
 static struct hnae3_client client;
 
+static int debug = -1;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, " Network interface message level setting");
+
+#define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \
+			   NETIF_MSG_IFDOWN | NETIF_MSG_IFUP)
+
 /* hns3_pci_tbl - PCI Device ID Table
  *
  * Last entry must be all 0s
@@ -64,28 +77,11 @@ static irqreturn_t hns3_irq_handle(int irq, void *vector)
 {
 	struct hns3_enet_tqp_vector *tqp_vector = vector;
 
-	napi_schedule(&tqp_vector->napi);
+	napi_schedule_irqoff(&tqp_vector->napi);
 
 	return IRQ_HANDLED;
 }
 
-/* This callback function is used to set affinity changes to the irq affinity
- * masks when the irq_set_affinity_notifier function is used.
- */
-static void hns3_nic_irq_affinity_notify(struct irq_affinity_notify *notify,
-					 const cpumask_t *mask)
-{
-	struct hns3_enet_tqp_vector *tqp_vectors =
-		container_of(notify, struct hns3_enet_tqp_vector,
-			     affinity_notify);
-
-	tqp_vectors->affinity_mask = *mask;
-}
-
-static void hns3_nic_irq_affinity_release(struct kref *ref)
-{
-}
-
 static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv)
 {
 	struct hns3_enet_tqp_vector *tqp_vectors;
@@ -97,8 +93,7 @@ static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv)
 		if (tqp_vectors->irq_init_flag != HNS3_VECTOR_INITED)
 			continue;
 
-		/* clear the affinity notifier and affinity mask */
-		irq_set_affinity_notifier(tqp_vectors->vector_irq, NULL);
+		/* clear the affinity mask */
 		irq_set_affinity_hint(tqp_vectors->vector_irq, NULL);
 
 		/* release the irq resource */
@@ -143,20 +138,14 @@ static int hns3_nic_init_irq(struct hns3_nic_priv *priv)
 		tqp_vectors->name[HNAE3_INT_NAME_LEN - 1] = '\0';
 
 		ret = request_irq(tqp_vectors->vector_irq, hns3_irq_handle, 0,
-				  tqp_vectors->name,
-				       tqp_vectors);
+				  tqp_vectors->name, tqp_vectors);
 		if (ret) {
 			netdev_err(priv->netdev, "request irq(%d) fail\n",
 				   tqp_vectors->vector_irq);
+			hns3_nic_uninit_irq(priv);
 			return ret;
 		}
 
-		tqp_vectors->affinity_notify.notify =
-					hns3_nic_irq_affinity_notify;
-		tqp_vectors->affinity_notify.release =
-					hns3_nic_irq_affinity_release;
-		irq_set_affinity_notifier(tqp_vectors->vector_irq,
-					  &tqp_vectors->affinity_notify);
 		irq_set_affinity_hint(tqp_vectors->vector_irq,
 				      &tqp_vectors->affinity_mask);
 
@@ -287,8 +276,7 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev)
 	ret = netif_set_real_num_tx_queues(netdev, queue_size);
 	if (ret) {
 		netdev_err(netdev,
-			   "netif_set_real_num_tx_queues fail, ret=%d!\n",
-			   ret);
+			   "netif_set_real_num_tx_queues fail, ret=%d!\n", ret);
 		return ret;
 	}
 
@@ -330,6 +318,40 @@ static void hns3_tqp_disable(struct hnae3_queue *tqp)
 	hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
 }
 
+static void hns3_free_rx_cpu_rmap(struct net_device *netdev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
+	netdev->rx_cpu_rmap = NULL;
+#endif
+}
+
+static int hns3_set_rx_cpu_rmap(struct net_device *netdev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hns3_enet_tqp_vector *tqp_vector;
+	int i, ret;
+
+	if (!netdev->rx_cpu_rmap) {
+		netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->vector_num);
+		if (!netdev->rx_cpu_rmap)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < priv->vector_num; i++) {
+		tqp_vector = &priv->tqp_vector[i];
+		ret = irq_cpu_rmap_add(netdev->rx_cpu_rmap,
+				       tqp_vector->vector_irq);
+		if (ret) {
+			hns3_free_rx_cpu_rmap(netdev);
+			return ret;
+		}
+	}
+#endif
+	return 0;
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -341,13 +363,20 @@ static int hns3_nic_net_up(struct net_device *netdev)
 	if (ret)
 		return ret;
 
+	/* the device can work without cpu rmap, only aRFS needs it */
+	ret = hns3_set_rx_cpu_rmap(netdev);
+	if (ret)
+		netdev_warn(netdev, "set rx cpu rmap fail, ret=%d!\n", ret);
+
 	/* get irq resource for all vectors */
 	ret = hns3_nic_init_irq(priv);
 	if (ret) {
-		netdev_err(netdev, "hns init irq failed! ret=%d\n", ret);
-		return ret;
+		netdev_err(netdev, "init irq failed! ret=%d\n", ret);
+		goto free_rmap;
 	}
 
+	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
+
 	/* enable the vectors */
 	for (i = 0; i < priv->vector_num; i++)
 		hns3_vector_enable(&priv->tqp_vector[i]);
@@ -361,11 +390,10 @@ static int hns3_nic_net_up(struct net_device *netdev)
 	if (ret)
 		goto out_start_err;
 
-	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
-
 	return 0;
 
 out_start_err:
+	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 	while (j--)
 		hns3_tqp_disable(h->kinfo.tqp[j]);
 
@@ -373,10 +401,34 @@ out_start_err:
 		hns3_vector_disable(&priv->tqp_vector[j]);
 
 	hns3_nic_uninit_irq(priv);
-
+free_rmap:
+	hns3_free_rx_cpu_rmap(netdev);
 	return ret;
 }
 
+static void hns3_config_xps(struct hns3_nic_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->vector_num; i++) {
+		struct hns3_enet_tqp_vector *tqp_vector = &priv->tqp_vector[i];
+		struct hns3_enet_ring *ring = tqp_vector->tx_group.ring;
+
+		while (ring) {
+			int ret;
+
+			ret = netif_set_xps_queue(priv->netdev,
+						  &tqp_vector->affinity_mask,
+						  ring->tqp->tqp_index);
+			if (ret)
+				netdev_warn(priv->netdev,
+					    "set xps queue failed: %d", ret);
+
+			ring = ring->next;
+		}
+	}
+}
+
 static int hns3_nic_net_open(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -395,23 +447,35 @@ static int hns3_nic_net_open(struct net_device *netdev)
 
 	ret = hns3_nic_net_up(netdev);
 	if (ret) {
-		netdev_err(netdev,
-			   "hns net up fail, ret=%d!\n", ret);
+		netdev_err(netdev, "net up fail, ret=%d!\n", ret);
 		return ret;
 	}
 
 	kinfo = &h->kinfo;
-	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
-		netdev_set_prio_tc_map(netdev, i,
-				       kinfo->prio_tc[i]);
-	}
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
+		netdev_set_prio_tc_map(netdev, i, kinfo->prio_tc[i]);
 
 	if (h->ae_algo->ops->set_timer_task)
 		h->ae_algo->ops->set_timer_task(priv->ae_handle, true);
 
+	hns3_config_xps(priv);
 	return 0;
 }
 
+static void hns3_reset_tx_queue(struct hnae3_handle *h)
+{
+	struct net_device *ndev = h->kinfo.netdev;
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct netdev_queue *dev_queue;
+	u32 i;
+
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
+		dev_queue = netdev_get_tx_queue(ndev,
+						priv->ring_data[i].queue_index);
+		netdev_tx_reset_queue(dev_queue);
+	}
+}
+
 static void hns3_nic_net_down(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -432,10 +496,19 @@ static void hns3_nic_net_down(struct net_device *netdev)
 	if (ops->stop)
 		ops->stop(priv->ae_handle);
 
+	hns3_free_rx_cpu_rmap(netdev);
+
 	/* free irq resources */
 	hns3_nic_uninit_irq(priv);
 
-	hns3_clear_all_ring(priv->ae_handle);
+	/* delay ring buffer clearing to hns3_reset_notify_uninit_enet
+	 * during reset process, because driver may not be able
+	 * to disable the ring through firmware when downing the netdev.
+	 */
+	if (!hns3_nic_resetting(netdev))
+		hns3_clear_all_ring(priv->ae_handle, false);
+
+	hns3_reset_tx_queue(priv->ae_handle);
 }
 
 static int hns3_nic_net_stop(struct net_device *netdev)
@@ -506,7 +579,7 @@ static u8 hns3_get_netdev_flags(struct net_device *netdev)
 	u8 flags = 0;
 
 	if (netdev->flags & IFF_PROMISC) {
-		flags = HNAE3_USER_UPE | HNAE3_USER_MPE;
+		flags = HNAE3_USER_UPE | HNAE3_USER_MPE | HNAE3_BPE;
 	} else {
 		flags |= HNAE3_VLAN_FLTR;
 		if (netdev->flags & IFF_ALLMULTI)
@@ -541,13 +614,13 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev)
 		}
 	}
 
-	hns3_update_promisc_mode(netdev, new_flags);
 	/* User mode Promisc mode enable and vlan filtering is disabled to
 	 * let all packets in. MAC-VLAN Table overflow Promisc enabled and
 	 * vlan fitering is enabled
 	 */
 	hns3_enable_vlan_filter(netdev, new_flags & HNAE3_VLAN_FLTR);
 	h->netdev_flags = new_flags;
+	hns3_update_promisc_mode(netdev, new_flags);
 }
 
 int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags)
@@ -594,7 +667,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 		return 0;
 
 	ret = skb_cow_head(skb, 0);
-	if (ret)
+	if (unlikely(ret))
 		return ret;
 
 	l3.hdr = skb_network_header(skb);
@@ -606,7 +679,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 	if (l3.v4->version == 4)
 		l3.v4->check = 0;
 
-	/* tunnel packet.*/
+	/* tunnel packet */
 	if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
 					 SKB_GSO_GRE_CSUM |
 					 SKB_GSO_UDP_TUNNEL |
@@ -631,19 +704,18 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 			l3.v4->check = 0;
 	}
 
-	/* normal or tunnel packet*/
+	/* normal or tunnel packet */
 	l4_offset = l4.hdr - skb->data;
-	hdr_len = (l4.tcp->doff * 4) + l4_offset;
+	hdr_len = (l4.tcp->doff << 2) + l4_offset;
 
-	/* remove payload length from inner pseudo checksum when tso*/
+	/* remove payload length from inner pseudo checksum when tso */
 	l4_paylen = skb->len - l4_offset;
 	csum_replace_by_diff(&l4.tcp->check,
 			     (__force __wsum)htonl(l4_paylen));
 
 	/* find the txbd field values */
 	*paylen = skb->len - hdr_len;
-	hnae3_set_bit(*type_cs_vlan_tso,
-		      HNS3_TXD_TSO_B, 1);
+	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_TSO_B, 1);
 
 	/* get MSS for TSO */
 	*mss = skb_shinfo(skb)->gso_size;
@@ -654,11 +726,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto,
 				u8 *il4_proto)
 {
-	union {
-		struct iphdr *v4;
-		struct ipv6hdr *v6;
-		unsigned char *hdr;
-	} l3;
+	union l3_hdr_info l3;
 	unsigned char *l4_hdr;
 	unsigned char *exthdr;
 	u8 l4_proto_tmp;
@@ -707,110 +775,6 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto,
 	return 0;
 }
 
-static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
-				u8 il4_proto, u32 *type_cs_vlan_tso,
-				u32 *ol_type_vlan_len_msec)
-{
-	union {
-		struct iphdr *v4;
-		struct ipv6hdr *v6;
-		unsigned char *hdr;
-	} l3;
-	union {
-		struct tcphdr *tcp;
-		struct udphdr *udp;
-		struct gre_base_hdr *gre;
-		unsigned char *hdr;
-	} l4;
-	unsigned char *l2_hdr;
-	u8 l4_proto = ol4_proto;
-	u32 ol2_len;
-	u32 ol3_len;
-	u32 ol4_len;
-	u32 l2_len;
-	u32 l3_len;
-
-	l3.hdr = skb_network_header(skb);
-	l4.hdr = skb_transport_header(skb);
-
-	/* compute L2 header size for normal packet, defined in 2 Bytes */
-	l2_len = l3.hdr - skb->data;
-	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-			HNS3_TXD_L2LEN_S, l2_len >> 1);
-
-	/* tunnel packet*/
-	if (skb->encapsulation) {
-		/* compute OL2 header size, defined in 2 Bytes */
-		ol2_len = l2_len;
-		hnae3_set_field(*ol_type_vlan_len_msec,
-				HNS3_TXD_L2LEN_M,
-				HNS3_TXD_L2LEN_S, ol2_len >> 1);
-
-		/* compute OL3 header size, defined in 4 Bytes */
-		ol3_len = l4.hdr - l3.hdr;
-		hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
-				HNS3_TXD_L3LEN_S, ol3_len >> 2);
-
-		/* MAC in UDP, MAC in GRE (0x6558)*/
-		if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) {
-			/* switch MAC header ptr from outer to inner header.*/
-			l2_hdr = skb_inner_mac_header(skb);
-
-			/* compute OL4 header size, defined in 4 Bytes. */
-			ol4_len = l2_hdr - l4.hdr;
-			hnae3_set_field(*ol_type_vlan_len_msec,
-					HNS3_TXD_L4LEN_M, HNS3_TXD_L4LEN_S,
-					ol4_len >> 2);
-
-			/* switch IP header ptr from outer to inner header */
-			l3.hdr = skb_inner_network_header(skb);
-
-			/* compute inner l2 header size, defined in 2 Bytes. */
-			l2_len = l3.hdr - l2_hdr;
-			hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-					HNS3_TXD_L2LEN_S, l2_len >> 1);
-		} else {
-			/* skb packet types not supported by hardware,
-			 * txbd len fild doesn't be filled.
-			 */
-			return;
-		}
-
-		/* switch L4 header pointer from outer to inner */
-		l4.hdr = skb_inner_transport_header(skb);
-
-		l4_proto = il4_proto;
-	}
-
-	/* compute inner(/normal) L3 header size, defined in 4 Bytes */
-	l3_len = l4.hdr - l3.hdr;
-	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
-			HNS3_TXD_L3LEN_S, l3_len >> 2);
-
-	/* compute inner(/normal) L4 header size, defined in 4 Bytes */
-	switch (l4_proto) {
-	case IPPROTO_TCP:
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-				HNS3_TXD_L4LEN_S, l4.tcp->doff);
-		break;
-	case IPPROTO_SCTP:
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-				HNS3_TXD_L4LEN_S,
-				(sizeof(struct sctphdr) >> 2));
-		break;
-	case IPPROTO_UDP:
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-				HNS3_TXD_L4LEN_S,
-				(sizeof(struct udphdr) >> 2));
-		break;
-	default:
-		/* skb packet types not supported by hardware,
-		 * txbd len fild doesn't be filled.
-		 */
-		return;
-	}
-}
-
 /* when skb->encapsulation is 0, skb->ip_summed is CHECKSUM_PARTIAL
  * and it is udp packet, which has a dest port as the IANA assigned.
  * the hardware is expected to do the checksum offload, but the
@@ -819,17 +783,12 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
  */
 static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 {
-#define IANA_VXLAN_PORT	4789
-	union {
-		struct tcphdr *tcp;
-		struct udphdr *udp;
-		struct gre_base_hdr *gre;
-		unsigned char *hdr;
-	} l4;
+	union l4_hdr_info l4;
 
 	l4.hdr = skb_transport_header(skb);
 
-	if (!(!skb->encapsulation && l4.udp->dest == htons(IANA_VXLAN_PORT)))
+	if (!(!skb->encapsulation &&
+	      l4.udp->dest == htons(IANA_VXLAN_UDP_PORT)))
 		return false;
 
 	skb_checksum_help(skb);
@@ -837,54 +796,71 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 	return true;
 }
 
-static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
-				   u8 il4_proto, u32 *type_cs_vlan_tso,
-				   u32 *ol_type_vlan_len_msec)
+static void hns3_set_outer_l2l3l4(struct sk_buff *skb, u8 ol4_proto,
+				  u32 *ol_type_vlan_len_msec)
+{
+	u32 l2_len, l3_len, l4_len;
+	unsigned char *il2_hdr;
+	union l3_hdr_info l3;
+	union l4_hdr_info l4;
+
+	l3.hdr = skb_network_header(skb);
+	l4.hdr = skb_transport_header(skb);
+
+	/* compute OL2 header size, defined in 2 Bytes */
+	l2_len = l3.hdr - skb->data;
+	hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L2LEN_S, l2_len >> 1);
+
+	/* compute OL3 header size, defined in 4 Bytes */
+	l3_len = l4.hdr - l3.hdr;
+	hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_S, l3_len >> 2);
+
+	il2_hdr = skb_inner_mac_header(skb);
+	/* compute OL4 header size, defined in 4 Bytes */
+	l4_len = il2_hdr - l4.hdr;
+	hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_S, l4_len >> 2);
+
+	/* define outer network header type */
+	if (skb->protocol == htons(ETH_P_IP)) {
+		if (skb_is_gso(skb))
+			hns3_set_field(*ol_type_vlan_len_msec,
+				       HNS3_TXD_OL3T_S,
+				       HNS3_OL3T_IPV4_CSUM);
+		else
+			hns3_set_field(*ol_type_vlan_len_msec,
+				       HNS3_TXD_OL3T_S,
+				       HNS3_OL3T_IPV4_NO_CSUM);
+
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_S,
+			       HNS3_OL3T_IPV6);
+	}
+
+	if (ol4_proto == IPPROTO_UDP)
+		hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_TUNTYPE_S,
+			       HNS3_TUN_MAC_IN_UDP);
+	else if (ol4_proto == IPPROTO_GRE)
+		hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_TUNTYPE_S,
+			       HNS3_TUN_NVGRE);
+}
+
+static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto,
+			   u8 il4_proto, u32 *type_cs_vlan_tso,
+			   u32 *ol_type_vlan_len_msec)
 {
-	union {
-		struct iphdr *v4;
-		struct ipv6hdr *v6;
-		unsigned char *hdr;
-	} l3;
+	unsigned char *l2_hdr = skb->data;
 	u32 l4_proto = ol4_proto;
+	union l4_hdr_info l4;
+	union l3_hdr_info l3;
+	u32 l2_len, l3_len;
 
+	l4.hdr = skb_transport_header(skb);
 	l3.hdr = skb_network_header(skb);
 
-	/* define OL3 type and tunnel type(OL4).*/
+	/* handle encapsulation skb */
 	if (skb->encapsulation) {
-		/* define outer network header type.*/
-		if (skb->protocol == htons(ETH_P_IP)) {
-			if (skb_is_gso(skb))
-				hnae3_set_field(*ol_type_vlan_len_msec,
-						HNS3_TXD_OL3T_M,
-						HNS3_TXD_OL3T_S,
-						HNS3_OL3T_IPV4_CSUM);
-			else
-				hnae3_set_field(*ol_type_vlan_len_msec,
-						HNS3_TXD_OL3T_M,
-						HNS3_TXD_OL3T_S,
-						HNS3_OL3T_IPV4_NO_CSUM);
-
-		} else if (skb->protocol == htons(ETH_P_IPV6)) {
-			hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
-					HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
-		}
-
-		/* define tunnel type(OL4).*/
-		switch (l4_proto) {
-		case IPPROTO_UDP:
-			hnae3_set_field(*ol_type_vlan_len_msec,
-					HNS3_TXD_TUNTYPE_M,
-					HNS3_TXD_TUNTYPE_S,
-					HNS3_TUN_MAC_IN_UDP);
-			break;
-		case IPPROTO_GRE:
-			hnae3_set_field(*ol_type_vlan_len_msec,
-					HNS3_TXD_TUNTYPE_M,
-					HNS3_TXD_TUNTYPE_S,
-					HNS3_TUN_NVGRE);
-			break;
-		default:
+		/* If this is a not UDP/GRE encapsulation skb */
+		if (!(ol4_proto == IPPROTO_UDP || ol4_proto == IPPROTO_GRE)) {
 			/* drop the skb tunnel packet if hardware don't support,
 			 * because hardware can't calculate csum when TSO.
 			 */
@@ -898,48 +874,62 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 			return 0;
 		}
 
+		hns3_set_outer_l2l3l4(skb, ol4_proto, ol_type_vlan_len_msec);
+
+		/* switch to inner header */
+		l2_hdr = skb_inner_mac_header(skb);
 		l3.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
 		l4_proto = il4_proto;
 	}
 
 	if (l3.v4->version == 4) {
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-				HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_S,
+			       HNS3_L3T_IPV4);
 
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
 		if (skb_is_gso(skb))
-			hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
+			hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
 	} else if (l3.v6->version == 6) {
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-				HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_S,
+			       HNS3_L3T_IPV6);
 	}
 
+	/* compute inner(/normal) L2 header size, defined in 2 Bytes */
+	l2_len = l3.hdr - l2_hdr;
+	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_S, l2_len >> 1);
+
+	/* compute inner(/normal) L3 header size, defined in 4 Bytes */
+	l3_len = l4.hdr - l3.hdr;
+	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_S, l3_len >> 2);
+
+	/* compute inner(/normal) L4 header size, defined in 4 Bytes */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
-		hnae3_set_field(*type_cs_vlan_tso,
-				HNS3_TXD_L4T_M,
-				HNS3_TXD_L4T_S,
-				HNS3_L4T_TCP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
+			       HNS3_L4T_TCP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
+			       l4.tcp->doff);
 		break;
 	case IPPROTO_UDP:
 		if (hns3_tunnel_csum_bug(skb))
 			break;
 
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
-		hnae3_set_field(*type_cs_vlan_tso,
-				HNS3_TXD_L4T_M,
-				HNS3_TXD_L4T_S,
-				HNS3_L4T_UDP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
+			       HNS3_L4T_UDP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
+			       (sizeof(struct udphdr) >> 2));
 		break;
 	case IPPROTO_SCTP:
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
-		hnae3_set_field(*type_cs_vlan_tso,
-				HNS3_TXD_L4T_M,
-				HNS3_TXD_L4T_S,
-				HNS3_L4T_SCTP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
+			       HNS3_L4T_SCTP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
+			       (sizeof(struct sctphdr) >> 2));
 		break;
 	default:
 		/* drop the skb tunnel packet if hardware don't support,
@@ -961,11 +951,9 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
 {
 	/* Config bd buffer end */
-	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
-			HNS3_TXD_BDTYPE_S, 0);
-	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
-	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
-	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
+	if (!!frag_end)
+		hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, 1U);
+	hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1U);
 }
 
 static int hns3_fill_desc_vtags(struct sk_buff *skb,
@@ -977,6 +965,16 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 {
 #define HNS3_TX_VLAN_PRIO_SHIFT 13
 
+	struct hnae3_handle *handle = tx_ring->tqp->handle;
+
+	/* Since HW limitation, if port based insert VLAN enabled, only one VLAN
+	 * header is allowed in skb, otherwise it will cause RAS error.
+	 */
+	if (unlikely(skb_vlan_tagged_multi(skb) &&
+		     handle->port_base_vlan_state ==
+		     HNAE3_PORT_BASE_VLAN_ENABLE))
+		return -EINVAL;
+
 	if (skb->protocol == htons(ETH_P_8021Q) &&
 	    !(tx_ring->tqp->handle->kinfo.netdev->features &
 	    NETIF_F_HW_VLAN_CTAG_TX)) {
@@ -998,10 +996,18 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		 * and use inner_vtag in one tag case.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q)) {
-			hnae3_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
-			*out_vtag = vlan_tag;
+			if (handle->port_base_vlan_state ==
+			    HNAE3_PORT_BASE_VLAN_DISABLE){
+				hns3_set_field(*out_vlan_flag,
+					       HNS3_TXD_OVLAN_B, 1);
+				*out_vtag = vlan_tag;
+			} else {
+				hns3_set_field(*inner_vlan_flag,
+					       HNS3_TXD_VLAN_B, 1);
+				*inner_vtag = vlan_tag;
+			}
 		} else {
-			hnae3_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
+			hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
 			*inner_vtag = vlan_tag;
 		}
 	} else if (skb->protocol == htons(ETH_P_8021Q)) {
@@ -1009,7 +1015,7 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		int rc;
 
 		rc = skb_cow_head(skb, 0);
-		if (rc < 0)
+		if (unlikely(rc < 0))
 			return rc;
 		vhdr = (struct vlan_ethhdr *)skb->data;
 		vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority & 0x7)
@@ -1021,31 +1027,26 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 }
 
 static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
-			  int size, int frag_end, enum hns_desc_type type)
+			  unsigned int size, int frag_end,
+			  enum hns_desc_type type)
 {
 	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
 	struct hns3_desc *desc = &ring->desc[ring->next_to_use];
 	struct device *dev = ring_to_dev(ring);
-	u32 ol_type_vlan_len_msec = 0;
-	u16 bdtp_fe_sc_vld_ra_ri = 0;
 	struct skb_frag_struct *frag;
 	unsigned int frag_buf_num;
-	u32 type_cs_vlan_tso = 0;
-	struct sk_buff *skb;
-	u16 inner_vtag = 0;
-	u16 out_vtag = 0;
-	unsigned int k;
-	int sizeoflast;
-	u32 paylen = 0;
+	int k, sizeoflast;
 	dma_addr_t dma;
-	u16 mss = 0;
-	u8 ol4_proto;
-	u8 il4_proto;
-	int ret;
 
 	if (type == DESC_TYPE_SKB) {
-		skb = (struct sk_buff *)priv;
-		paylen = skb->len;
+		struct sk_buff *skb = (struct sk_buff *)priv;
+		u32 ol_type_vlan_len_msec = 0;
+		u32 type_cs_vlan_tso = 0;
+		u32 paylen = skb->len;
+		u16 inner_vtag = 0;
+		u16 out_vtag = 0;
+		u16 mss = 0;
+		int ret;
 
 		ret = hns3_fill_desc_vtags(skb, ring, &type_cs_vlan_tso,
 					   &ol_type_vlan_len_msec,
@@ -1054,31 +1055,30 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 			return ret;
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			u8 ol4_proto, il4_proto;
+
 			skb_reset_mac_len(skb);
 
 			ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
-			if (ret)
+			if (unlikely(ret))
 				return ret;
-			hns3_set_l2l3l4_len(skb, ol4_proto, il4_proto,
-					    &type_cs_vlan_tso,
-					    &ol_type_vlan_len_msec);
-			ret = hns3_set_l3l4_type_csum(skb, ol4_proto, il4_proto,
-						      &type_cs_vlan_tso,
-						      &ol_type_vlan_len_msec);
-			if (ret)
+
+			ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto,
+					      &type_cs_vlan_tso,
+					      &ol_type_vlan_len_msec);
+			if (unlikely(ret))
 				return ret;
 
 			ret = hns3_set_tso(skb, &paylen, &mss,
 					   &type_cs_vlan_tso);
-			if (ret)
+			if (unlikely(ret))
 				return ret;
 		}
 
 		/* Set txbd */
 		desc->tx.ol_type_vlan_len_msec =
 			cpu_to_le32(ol_type_vlan_len_msec);
-		desc->tx.type_cs_vlan_tso_len =
-			cpu_to_le32(type_cs_vlan_tso);
+		desc->tx.type_cs_vlan_tso_len =	cpu_to_le32(type_cs_vlan_tso);
 		desc->tx.paylen = cpu_to_le32(paylen);
 		desc->tx.mss = cpu_to_le16(mss);
 		desc->tx.vlan_tag = cpu_to_le16(inner_vtag);
@@ -1090,36 +1090,54 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 		dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE);
 	}
 
-	if (dma_mapping_error(ring->dev, dma)) {
+	if (unlikely(dma_mapping_error(dev, dma))) {
 		ring->stats.sw_err_cnt++;
 		return -ENOMEM;
 	}
 
 	desc_cb->length = size;
 
-	frag_buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE;
-	sizeoflast = size % HNS3_MAX_BD_SIZE;
+	if (likely(size <= HNS3_MAX_BD_SIZE)) {
+		u16 bdtp_fe_sc_vld_ra_ri = 0;
+
+		desc_cb->priv = priv;
+		desc_cb->dma = dma;
+		desc_cb->type = type;
+		desc->addr = cpu_to_le64(dma);
+		desc->tx.send_size = cpu_to_le16(size);
+		hns3_set_txbd_baseinfo(&bdtp_fe_sc_vld_ra_ri, frag_end);
+		desc->tx.bdtp_fe_sc_vld_ra_ri =
+			cpu_to_le16(bdtp_fe_sc_vld_ra_ri);
+
+		ring_ptr_move_fw(ring, next_to_use);
+		return 0;
+	}
+
+	frag_buf_num = hns3_tx_bd_count(size);
+	sizeoflast = size & HNS3_TX_LAST_SIZE_M;
 	sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE;
 
 	/* When frag size is bigger than hardware limit, split this frag */
 	for (k = 0; k < frag_buf_num; k++) {
+		u16 bdtp_fe_sc_vld_ra_ri = 0;
+
 		/* The txbd's baseinfo of DESC_TYPE_PAGE & DESC_TYPE_SKB */
 		desc_cb->priv = priv;
 		desc_cb->dma = dma + HNS3_MAX_BD_SIZE * k;
 		desc_cb->type = (type == DESC_TYPE_SKB && !k) ?
-					DESC_TYPE_SKB : DESC_TYPE_PAGE;
+				DESC_TYPE_SKB : DESC_TYPE_PAGE;
 
 		/* now, fill the descriptor */
 		desc->addr = cpu_to_le64(dma + HNS3_MAX_BD_SIZE * k);
 		desc->tx.send_size = cpu_to_le16((k == frag_buf_num - 1) ?
-				(u16)sizeoflast : (u16)HNS3_MAX_BD_SIZE);
+				     (u16)sizeoflast : (u16)HNS3_MAX_BD_SIZE);
 		hns3_set_txbd_baseinfo(&bdtp_fe_sc_vld_ra_ri,
 				       frag_end && (k == frag_buf_num - 1) ?
 						1 : 0);
 		desc->tx.bdtp_fe_sc_vld_ra_ri =
 				cpu_to_le16(bdtp_fe_sc_vld_ra_ri);
 
-		/* move ring pointer to next.*/
+		/* move ring pointer to next */
 		ring_ptr_move_fw(ring, next_to_use);
 
 		desc_cb = &ring->desc_cb[ring->next_to_use];
@@ -1129,54 +1147,110 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	return 0;
 }
 
-static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum,
-				   struct hns3_enet_ring *ring)
+static int hns3_nic_bd_num(struct sk_buff *skb)
 {
-	struct sk_buff *skb = *out_skb;
-	struct skb_frag_struct *frag;
-	int bdnum_for_frag;
-	int frag_num;
-	int buf_num;
-	int size;
-	int i;
+	int size = skb_headlen(skb);
+	int i, bd_num;
 
-	size = skb_headlen(skb);
-	buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE;
+	/* if the total len is within the max bd limit */
+	if (likely(skb->len <= HNS3_MAX_BD_SIZE))
+		return skb_shinfo(skb)->nr_frags + 1;
+
+	bd_num = hns3_tx_bd_count(size);
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
+		int frag_bd_num;
 
-	frag_num = skb_shinfo(skb)->nr_frags;
-	for (i = 0; i < frag_num; i++) {
-		frag = &skb_shinfo(skb)->frags[i];
 		size = skb_frag_size(frag);
-		bdnum_for_frag =
-			(size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE;
-		if (bdnum_for_frag > HNS3_MAX_BD_PER_FRAG)
+		frag_bd_num = hns3_tx_bd_count(size);
+
+		if (unlikely(frag_bd_num > HNS3_MAX_BD_PER_FRAG))
 			return -ENOMEM;
 
-		buf_num += bdnum_for_frag;
+		bd_num += frag_bd_num;
 	}
 
-	if (buf_num > ring_space(ring))
-		return -EBUSY;
+	return bd_num;
+}
 
-	*bnum = buf_num;
-	return 0;
+static unsigned int hns3_gso_hdr_len(struct sk_buff *skb)
+{
+	if (!skb->encapsulation)
+		return skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+	return skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
+}
+
+/* HW need every continuous 8 buffer data to be larger than MSS,
+ * we simplify it by ensuring skb_headlen + the first continuous
+ * 7 frags to to be larger than gso header len + mss, and the remaining
+ * continuous 7 frags to be larger than MSS except the last 7 frags.
+ */
+static bool hns3_skb_need_linearized(struct sk_buff *skb)
+{
+	int bd_limit = HNS3_MAX_BD_PER_FRAG - 1;
+	unsigned int tot_len = 0;
+	int i;
+
+	for (i = 0; i < bd_limit; i++)
+		tot_len += skb_frag_size(&skb_shinfo(skb)->frags[i]);
+
+	/* ensure headlen + the first 7 frags is greater than mss + header
+	 * and the first 7 frags is greater than mss.
+	 */
+	if (((tot_len + skb_headlen(skb)) < (skb_shinfo(skb)->gso_size +
+	    hns3_gso_hdr_len(skb))) || (tot_len < skb_shinfo(skb)->gso_size))
+		return true;
+
+	/* ensure the remaining continuous 7 buffer is greater than mss */
+	for (i = 0; i < (skb_shinfo(skb)->nr_frags - bd_limit - 1); i++) {
+		tot_len -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
+		tot_len += skb_frag_size(&skb_shinfo(skb)->frags[i + bd_limit]);
+
+		if (tot_len < skb_shinfo(skb)->gso_size)
+			return true;
+	}
+
+	return false;
 }
 
-static int hns3_nic_maybe_stop_tx(struct sk_buff **out_skb, int *bnum,
-				  struct hns3_enet_ring *ring)
+static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
+				  struct sk_buff **out_skb)
 {
 	struct sk_buff *skb = *out_skb;
-	int buf_num;
+	int bd_num;
 
-	/* No. of segments (plus a header) */
-	buf_num = skb_shinfo(skb)->nr_frags + 1;
+	bd_num = hns3_nic_bd_num(skb);
+	if (bd_num < 0)
+		return bd_num;
 
-	if (unlikely(ring_space(ring) < buf_num))
-		return -EBUSY;
+	if (unlikely(bd_num > HNS3_MAX_BD_PER_FRAG)) {
+		struct sk_buff *new_skb;
 
-	*bnum = buf_num;
+		if (skb_is_gso(skb) && !hns3_skb_need_linearized(skb))
+			goto out;
 
-	return 0;
+		bd_num = hns3_tx_bd_count(skb->len);
+		if (unlikely(ring_space(ring) < bd_num))
+			return -EBUSY;
+		/* manual split the send packet */
+		new_skb = skb_copy(skb, GFP_ATOMIC);
+		if (!new_skb)
+			return -ENOMEM;
+		dev_kfree_skb_any(skb);
+		*out_skb = new_skb;
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.tx_copy++;
+		u64_stats_update_end(&ring->syncp);
+	}
+
+out:
+	if (unlikely(ring_space(ring) < bd_num))
+		return -EBUSY;
+
+	return bd_num;
 }
 
 static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
@@ -1189,6 +1263,9 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
 		if (ring->next_to_use == next_to_use_orig)
 			break;
 
+		/* rollback one */
+		ring_ptr_move_bw(ring, next_to_use);
+
 		/* unmap the descriptor dma address */
 		if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB)
 			dma_unmap_single(dev,
@@ -1202,9 +1279,7 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig)
 				       DMA_TO_DEVICE);
 
 		ring->desc_cb[ring->next_to_use].length = 0;
-
-		/* rollback one */
-		ring_ptr_move_bw(ring, next_to_use);
+		ring->desc_cb[ring->next_to_use].dma = 0;
 	}
 }
 
@@ -1217,7 +1292,6 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	struct netdev_queue *dev_queue;
 	struct skb_frag_struct *frag;
 	int next_to_use_head;
-	int next_to_use_frag;
 	int buf_num;
 	int seg_num;
 	int size;
@@ -1227,22 +1301,23 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 	/* Prefetch the data used later */
 	prefetch(skb->data);
 
-	switch (priv->ops.maybe_stop_tx(&skb, &buf_num, ring)) {
-	case -EBUSY:
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.tx_busy++;
-		u64_stats_update_end(&ring->syncp);
+	buf_num = hns3_nic_maybe_stop_tx(ring, &skb);
+	if (unlikely(buf_num <= 0)) {
+		if (buf_num == -EBUSY) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.tx_busy++;
+			u64_stats_update_end(&ring->syncp);
+			goto out_net_tx_busy;
+		} else if (buf_num == -ENOMEM) {
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.sw_err_cnt++;
+			u64_stats_update_end(&ring->syncp);
+		}
 
-		goto out_net_tx_busy;
-	case -ENOMEM:
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.sw_err_cnt++;
-		u64_stats_update_end(&ring->syncp);
-		netdev_err(netdev, "no memory to xmit!\n");
+		if (net_ratelimit())
+			netdev_err(netdev, "xmit error: %d!\n", buf_num);
 
 		goto out_err_tx_ok;
-	default:
-		break;
 	}
 
 	/* No. of segments (plus a header) */
@@ -1252,23 +1327,22 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	next_to_use_head = ring->next_to_use;
 
-	ret = priv->ops.fill_desc(ring, skb, size, seg_num == 1 ? 1 : 0,
-				  DESC_TYPE_SKB);
-	if (ret)
-		goto head_fill_err;
+	ret = hns3_fill_desc(ring, skb, size, seg_num == 1 ? 1 : 0,
+			     DESC_TYPE_SKB);
+	if (unlikely(ret))
+		goto fill_err;
 
-	next_to_use_frag = ring->next_to_use;
 	/* Fill the fragments */
 	for (i = 1; i < seg_num; i++) {
 		frag = &skb_shinfo(skb)->frags[i - 1];
 		size = skb_frag_size(frag);
 
-		ret = priv->ops.fill_desc(ring, frag, size,
-					  seg_num - 1 == i ? 1 : 0,
-					  DESC_TYPE_PAGE);
+		ret = hns3_fill_desc(ring, frag, size,
+				     seg_num - 1 == i ? 1 : 0,
+				     DESC_TYPE_PAGE);
 
-		if (ret)
-			goto frag_fill_err;
+		if (unlikely(ret))
+			goto fill_err;
 	}
 
 	/* Complete translate all packets */
@@ -1281,10 +1355,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	return NETDEV_TX_OK;
 
-frag_fill_err:
-	hns3_clear_desc(ring, next_to_use_frag);
-
-head_fill_err:
+fill_err:
 	hns3_clear_desc(ring, next_to_use_head);
 
 out_err_tx_ok:
@@ -1344,48 +1415,33 @@ static int hns3_nic_set_features(struct net_device *netdev,
 	netdev_features_t changed = netdev->features ^ features;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
+	bool enable;
 	int ret;
 
-	if (changed & (NETIF_F_TSO | NETIF_F_TSO6)) {
-		if (features & (NETIF_F_TSO | NETIF_F_TSO6))
-			priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tso;
-		else
-			priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx;
-	}
-
 	if (changed & (NETIF_F_GRO_HW) && h->ae_algo->ops->set_gro_en) {
-		if (features & NETIF_F_GRO_HW)
-			ret = h->ae_algo->ops->set_gro_en(h, true);
-		else
-			ret = h->ae_algo->ops->set_gro_en(h, false);
+		enable = !!(features & NETIF_F_GRO_HW);
+		ret = h->ae_algo->ops->set_gro_en(h, enable);
 		if (ret)
 			return ret;
 	}
 
 	if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) &&
 	    h->ae_algo->ops->enable_vlan_filter) {
-		if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
-			h->ae_algo->ops->enable_vlan_filter(h, true);
-		else
-			h->ae_algo->ops->enable_vlan_filter(h, false);
+		enable = !!(features & NETIF_F_HW_VLAN_CTAG_FILTER);
+		h->ae_algo->ops->enable_vlan_filter(h, enable);
 	}
 
 	if ((changed & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    h->ae_algo->ops->enable_hw_strip_rxvtag) {
-		if (features & NETIF_F_HW_VLAN_CTAG_RX)
-			ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, true);
-		else
-			ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, false);
-
+		enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX);
+		ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, enable);
 		if (ret)
 			return ret;
 	}
 
 	if ((changed & NETIF_F_NTUPLE) && h->ae_algo->ops->enable_fd) {
-		if (features & NETIF_F_NTUPLE)
-			h->ae_algo->ops->enable_fd(h, true);
-		else
-			h->ae_algo->ops->enable_fd(h, false);
+		enable = !!(features & NETIF_F_NTUPLE);
+		h->ae_algo->ops->enable_fd(h, enable);
 	}
 
 	netdev->features = features;
@@ -1399,7 +1455,12 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 	int queue_num = priv->ae_handle->kinfo.num_tqps;
 	struct hnae3_handle *handle = priv->ae_handle;
 	struct hns3_enet_ring *ring;
+	u64 rx_length_errors = 0;
+	u64 rx_crc_errors = 0;
+	u64 rx_multicast = 0;
 	unsigned int start;
+	u64 tx_errors = 0;
+	u64 rx_errors = 0;
 	unsigned int idx;
 	u64 tx_bytes = 0;
 	u64 rx_bytes = 0;
@@ -1420,8 +1481,8 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			tx_bytes += ring->stats.tx_bytes;
 			tx_pkts += ring->stats.tx_pkts;
-			tx_drop += ring->stats.tx_busy;
 			tx_drop += ring->stats.sw_err_cnt;
+			tx_errors += ring->stats.sw_err_cnt;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -1430,9 +1491,12 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			rx_bytes += ring->stats.rx_bytes;
 			rx_pkts += ring->stats.rx_pkts;
-			rx_drop += ring->stats.non_vld_descs;
-			rx_drop += ring->stats.err_pkt_len;
 			rx_drop += ring->stats.l2_err;
+			rx_errors += ring->stats.l2_err;
+			rx_errors += ring->stats.l3l4_csum_err;
+			rx_crc_errors += ring->stats.l2_err;
+			rx_multicast += ring->stats.rx_multicast;
+			rx_length_errors += ring->stats.err_pkt_len;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 	}
 
@@ -1441,15 +1505,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 	stats->rx_bytes = rx_bytes;
 	stats->rx_packets = rx_pkts;
 
-	stats->rx_errors = netdev->stats.rx_errors;
-	stats->multicast = netdev->stats.multicast;
-	stats->rx_length_errors = netdev->stats.rx_length_errors;
-	stats->rx_crc_errors = netdev->stats.rx_crc_errors;
+	stats->rx_errors = rx_errors;
+	stats->multicast = rx_multicast;
+	stats->rx_length_errors = rx_length_errors;
+	stats->rx_crc_errors = rx_crc_errors;
 	stats->rx_missed_errors = netdev->stats.rx_missed_errors;
 
-	stats->tx_errors = netdev->stats.tx_errors;
-	stats->rx_dropped = rx_drop + netdev->stats.rx_dropped;
-	stats->tx_dropped = tx_drop + netdev->stats.tx_dropped;
+	stats->tx_errors = tx_errors;
+	stats->rx_dropped = rx_drop;
+	stats->tx_dropped = tx_drop;
 	stats->collisions = netdev->stats.collisions;
 	stats->rx_over_errors = netdev->stats.rx_over_errors;
 	stats->rx_frame_errors = netdev->stats.rx_frame_errors;
@@ -1466,14 +1530,12 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 {
 	struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
-	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hnae3_knic_private_info *kinfo = &h->kinfo;
 	u8 *prio_tc = mqprio_qopt->qopt.prio_tc_map;
+	struct hnae3_knic_private_info *kinfo;
 	u8 tc = mqprio_qopt->qopt.num_tc;
 	u16 mode = mqprio_qopt->mode;
 	u8 hw = mqprio_qopt->qopt.hw;
-	bool if_running;
-	int ret;
+	struct hnae3_handle *h;
 
 	if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
 	       mode == TC_MQPRIO_MODE_CHANNEL) || (!hw && tc == 0)))
@@ -1485,24 +1547,11 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	if (!netdev)
 		return -EINVAL;
 
-	if_running = netif_running(netdev);
-	if (if_running) {
-		hns3_nic_net_stop(netdev);
-		msleep(100);
-	}
+	h = hns3_get_handle(netdev);
+	kinfo = &h->kinfo;
 
-	ret = (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
+	return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
 		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
-	if (ret)
-		goto out;
-
-	ret = hns3_nic_set_real_num_queue(netdev);
-
-out:
-	if (if_running)
-		hns3_nic_net_open(netdev);
-
-	return ret;
 }
 
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
@@ -1518,15 +1567,11 @@ static int hns3_vlan_rx_add_vid(struct net_device *netdev,
 				__be16 proto, u16 vid)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret = -EIO;
 
 	if (h->ae_algo->ops->set_vlan_filter)
 		ret = h->ae_algo->ops->set_vlan_filter(h, proto, vid, false);
 
-	if (!ret)
-		set_bit(vid, priv->active_vlans);
-
 	return ret;
 }
 
@@ -1534,33 +1579,11 @@ static int hns3_vlan_rx_kill_vid(struct net_device *netdev,
 				 __be16 proto, u16 vid)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret = -EIO;
 
 	if (h->ae_algo->ops->set_vlan_filter)
 		ret = h->ae_algo->ops->set_vlan_filter(h, proto, vid, true);
 
-	if (!ret)
-		clear_bit(vid, priv->active_vlans);
-
-	return ret;
-}
-
-static int hns3_restore_vlan(struct net_device *netdev)
-{
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	int ret = 0;
-	u16 vid;
-
-	for_each_set_bit(vid, priv->active_vlans, VLAN_N_VID) {
-		ret = hns3_vlan_rx_add_vid(netdev, htons(ETH_P_8021Q), vid);
-		if (ret) {
-			netdev_err(netdev, "Restore vlan: %d filter, ret:%d\n",
-				   vid, ret);
-			return ret;
-		}
-	}
-
 	return ret;
 }
 
@@ -1572,7 +1595,7 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 
 	if (h->ae_algo->ops->set_vf_vlan_filter)
 		ret = h->ae_algo->ops->set_vf_vlan_filter(h, vf, vlan,
-						   qos, vlan_proto);
+							  qos, vlan_proto);
 
 	return ret;
 }
@@ -1582,6 +1605,9 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	int ret;
 
+	if (hns3_nic_resetting(netdev))
+		return -EBUSY;
+
 	if (!h->ae_algo->ops->set_mtu)
 		return -EOPNOTSUPP;
 
@@ -1598,13 +1624,19 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
+	struct hnae3_handle *h = hns3_get_handle(ndev);
 	struct hns3_enet_ring *tx_ring = NULL;
+	struct napi_struct *napi;
 	int timeout_queue = 0;
 	int hw_head, hw_tail;
+	int fbd_num, fbd_oft;
+	int ebd_num, ebd_oft;
+	int bd_num, bd_err;
+	int ring_en, tc;
 	int i;
 
 	/* Find the stopped queue the same way the stack does */
-	for (i = 0; i < ndev->real_num_tx_queues; i++) {
+	for (i = 0; i < ndev->num_tx_queues; i++) {
 		struct netdev_queue *q;
 		unsigned long trans_start;
 
@@ -1625,21 +1657,66 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev)
 		return false;
 	}
 
+	priv->tx_timeout_count++;
+
 	tx_ring = priv->ring_data[timeout_queue].ring;
+	napi = &tx_ring->tqp_vector->napi;
+
+	netdev_info(ndev,
+		    "tx_timeout count: %llu, queue id: %d, SW_NTU: 0x%x, SW_NTC: 0x%x, napi state: %lu\n",
+		    priv->tx_timeout_count, timeout_queue, tx_ring->next_to_use,
+		    tx_ring->next_to_clean, napi->state);
+
+	netdev_info(ndev,
+		    "tx_pkts: %llu, tx_bytes: %llu, io_err_cnt: %llu, sw_err_cnt: %llu\n",
+		    tx_ring->stats.tx_pkts, tx_ring->stats.tx_bytes,
+		    tx_ring->stats.io_err_cnt, tx_ring->stats.sw_err_cnt);
+
+	netdev_info(ndev,
+		    "seg_pkt_cnt: %llu, tx_err_cnt: %llu, restart_queue: %llu, tx_busy: %llu\n",
+		    tx_ring->stats.seg_pkt_cnt, tx_ring->stats.tx_err_cnt,
+		    tx_ring->stats.restart_queue, tx_ring->stats.tx_busy);
+
+	/* When mac received many pause frames continuous, it's unable to send
+	 * packets, which may cause tx timeout
+	 */
+	if (h->ae_algo->ops->update_stats &&
+	    h->ae_algo->ops->get_mac_pause_stats) {
+		u64 tx_pause_cnt, rx_pause_cnt;
+
+		h->ae_algo->ops->update_stats(h, &ndev->stats);
+		h->ae_algo->ops->get_mac_pause_stats(h, &tx_pause_cnt,
+						     &rx_pause_cnt);
+		netdev_info(ndev, "tx_pause_cnt: %llu, rx_pause_cnt: %llu\n",
+			    tx_pause_cnt, rx_pause_cnt);
+	}
 
 	hw_head = readl_relaxed(tx_ring->tqp->io_base +
 				HNS3_RING_TX_RING_HEAD_REG);
 	hw_tail = readl_relaxed(tx_ring->tqp->io_base +
 				HNS3_RING_TX_RING_TAIL_REG);
+	fbd_num = readl_relaxed(tx_ring->tqp->io_base +
+				HNS3_RING_TX_RING_FBDNUM_REG);
+	fbd_oft = readl_relaxed(tx_ring->tqp->io_base +
+				HNS3_RING_TX_RING_OFFSET_REG);
+	ebd_num = readl_relaxed(tx_ring->tqp->io_base +
+				HNS3_RING_TX_RING_EBDNUM_REG);
+	ebd_oft = readl_relaxed(tx_ring->tqp->io_base +
+				HNS3_RING_TX_RING_EBD_OFFSET_REG);
+	bd_num = readl_relaxed(tx_ring->tqp->io_base +
+			       HNS3_RING_TX_RING_BD_NUM_REG);
+	bd_err = readl_relaxed(tx_ring->tqp->io_base +
+			       HNS3_RING_TX_RING_BD_ERR_REG);
+	ring_en = readl_relaxed(tx_ring->tqp->io_base + HNS3_RING_EN_REG);
+	tc = readl_relaxed(tx_ring->tqp->io_base + HNS3_RING_TX_RING_TC_REG);
+
 	netdev_info(ndev,
-		    "tx_timeout count: %llu, queue id: %d, SW_NTU: 0x%x, SW_NTC: 0x%x, HW_HEAD: 0x%x, HW_TAIL: 0x%x, INT: 0x%x\n",
-		    priv->tx_timeout_count,
-		    timeout_queue,
-		    tx_ring->next_to_use,
-		    tx_ring->next_to_clean,
-		    hw_head,
-		    hw_tail,
+		    "BD_NUM: 0x%x HW_HEAD: 0x%x, HW_TAIL: 0x%x, BD_ERR: 0x%x, INT: 0x%x\n",
+		    bd_num, hw_head, hw_tail, bd_err,
 		    readl(tx_ring->tqp_vector->mask_addr));
+	netdev_info(ndev,
+		    "RING_EN: 0x%x, TC: 0x%x, FBD_NUM: 0x%x FBD_OFT: 0x%x, EBD_NUM: 0x%x, EBD_OFT: 0x%x\n",
+		    ring_en, tc, fbd_num, fbd_oft, ebd_num, ebd_oft);
 
 	return true;
 }
@@ -1652,8 +1729,6 @@ static void hns3_nic_net_timeout(struct net_device *ndev)
 	if (!hns3_get_tx_timeo_queue_info(ndev))
 		return;
 
-	priv->tx_timeout_count++;
-
 	/* request the reset, and let the hclge to determine
 	 * which reset level should be done
 	 */
@@ -1661,6 +1736,32 @@ static void hns3_nic_net_timeout(struct net_device *ndev)
 		h->ae_algo->ops->reset_event(h->pdev, h);
 }
 
+#ifdef CONFIG_RFS_ACCEL
+static int hns3_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+			      u16 rxq_index, u32 flow_id)
+{
+	struct hnae3_handle *h = hns3_get_handle(dev);
+	struct flow_keys fkeys;
+
+	if (!h->ae_algo->ops->add_arfs_entry)
+		return -EOPNOTSUPP;
+
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
+	if (!skb_flow_dissect_flow_keys(skb, &fkeys, 0))
+		return -EPROTONOSUPPORT;
+
+	if ((fkeys.basic.n_proto != htons(ETH_P_IP) &&
+	     fkeys.basic.n_proto != htons(ETH_P_IPV6)) ||
+	    (fkeys.basic.ip_proto != IPPROTO_TCP &&
+	     fkeys.basic.ip_proto != IPPROTO_UDP))
+		return -EPROTONOSUPPORT;
+
+	return h->ae_algo->ops->add_arfs_entry(h, rxq_index, flow_id, &fkeys);
+}
+#endif
+
 static const struct net_device_ops hns3_nic_netdev_ops = {
 	.ndo_open		= hns3_nic_net_open,
 	.ndo_stop		= hns3_nic_net_stop,
@@ -1676,9 +1777,13 @@ static const struct net_device_ops hns3_nic_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= hns3_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= hns3_vlan_rx_kill_vid,
 	.ndo_set_vf_vlan	= hns3_ndo_set_vf_vlan,
+#ifdef CONFIG_RFS_ACCEL
+	.ndo_rx_flow_steer	= hns3_rx_flow_steer,
+#endif
+
 };
 
-static bool hns3_is_phys_func(struct pci_dev *pdev)
+bool hns3_is_phys_func(struct pci_dev *pdev)
 {
 	u32 dev_id = pdev->device;
 
@@ -1741,8 +1846,7 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct hnae3_ae_dev *ae_dev;
 	int ret;
 
-	ae_dev = devm_kzalloc(&pdev->dev, sizeof(*ae_dev),
-			      GFP_KERNEL);
+	ae_dev = devm_kzalloc(&pdev->dev, sizeof(*ae_dev), GFP_KERNEL);
 	if (!ae_dev) {
 		ret = -ENOMEM;
 		return ret;
@@ -1750,14 +1854,17 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ae_dev->pdev = pdev;
 	ae_dev->flag = ent->driver_data;
-	ae_dev->dev_type = HNAE3_DEV_KNIC;
 	ae_dev->reset_type = HNAE3_NONE_RESET;
 	hns3_get_dev_capability(pdev, ae_dev);
 	pci_set_drvdata(pdev, ae_dev);
 
-	hnae3_register_ae_dev(ae_dev);
+	ret = hnae3_register_ae_dev(ae_dev);
+	if (ret) {
+		devm_kfree(&pdev->dev, ae_dev);
+		pci_set_drvdata(pdev, NULL);
+	}
 
-	return 0;
+	return ret;
 }
 
 /* hns3_remove - Device removal routine
@@ -1771,6 +1878,7 @@ static void hns3_remove(struct pci_dev *pdev)
 		hns3_disable_sriov(pdev);
 
 	hnae3_unregister_ae_dev(ae_dev);
+	pci_set_drvdata(pdev, NULL);
 }
 
 /**
@@ -1829,9 +1937,9 @@ static pci_ers_result_t hns3_error_detected(struct pci_dev *pdev,
 	if (state == pci_channel_io_perm_failure)
 		return PCI_ERS_RESULT_DISCONNECT;
 
-	if (!ae_dev) {
+	if (!ae_dev || !ae_dev->ops) {
 		dev_err(&pdev->dev,
-			"Can't recover - error happened during device init\n");
+			"Can't recover - error happened before device initialized\n");
 		return PCI_ERS_RESULT_NONE;
 	}
 
@@ -1846,13 +1954,24 @@ static pci_ers_result_t hns3_error_detected(struct pci_dev *pdev,
 static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+	const struct hnae3_ae_ops *ops;
+	enum hnae3_reset_type reset_type;
 	struct device *dev = &pdev->dev;
 
-	dev_info(dev, "requesting reset due to PCI error\n");
+	if (!ae_dev || !ae_dev->ops)
+		return PCI_ERS_RESULT_NONE;
 
+	ops = ae_dev->ops;
 	/* request the reset */
-	if (ae_dev->ops->reset_event) {
-		ae_dev->ops->reset_event(pdev, NULL);
+	if (ops->reset_event) {
+		if (ae_dev->hw_err_reset_req) {
+			reset_type = ops->get_reset_level(ae_dev,
+						&ae_dev->hw_err_reset_req);
+			ops->set_default_reset_request(ae_dev, reset_type);
+			dev_info(dev, "requesting reset due to PCI error\n");
+			ops->reset_event(pdev, NULL);
+		}
+
 		return PCI_ERS_RESULT_RECOVERED;
 	}
 
@@ -1935,8 +2054,7 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC;
 
 	if (pdev->revision >= 0x21) {
-		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER |
-			NETIF_F_GRO_HW;
+		netdev->hw_features |= NETIF_F_GRO_HW;
 		netdev->features |= NETIF_F_GRO_HW;
 
 		if (!(h->flags & HNAE3_SUPPORT_VF)) {
@@ -2101,7 +2219,7 @@ out_buffer_fail:
 	return ret;
 }
 
-/* detach a in-used buffer and replace with a reserved one  */
+/* detach a in-used buffer and replace with a reserved one */
 static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
 				struct hns3_desc_cb *res_cb)
 {
@@ -2114,22 +2232,35 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
 static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i)
 {
 	ring->desc_cb[i].reuse_flag = 0;
-	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma
-		+ ring->desc_cb[i].page_offset);
+	ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
+					 ring->desc_cb[i].page_offset);
 	ring->desc[i].rx.bd_base_info = 0;
 }
 
-static void hns3_nic_reclaim_one_desc(struct hns3_enet_ring *ring, int *bytes,
-				      int *pkts)
+static void hns3_nic_reclaim_desc(struct hns3_enet_ring *ring, int head,
+				  int *bytes, int *pkts)
 {
-	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean];
+	int ntc = ring->next_to_clean;
+	struct hns3_desc_cb *desc_cb;
 
-	(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
-	(*bytes) += desc_cb->length;
-	/* desc_cb will be cleaned, after hnae3_free_buffer_detach*/
-	hns3_free_buffer_detach(ring, ring->next_to_clean);
+	while (head != ntc) {
+		desc_cb = &ring->desc_cb[ntc];
+		(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
+		(*bytes) += desc_cb->length;
+		/* desc_cb will be cleaned, after hnae3_free_buffer_detach */
+		hns3_free_buffer_detach(ring, ntc);
 
-	ring_ptr_move_fw(ring, next_to_clean);
+		if (++ntc == ring->desc_num)
+			ntc = 0;
+
+		/* Issue prefetch for next Tx descriptor */
+		prefetch(&ring->desc_cb[ntc]);
+	}
+
+	/* This smp_store_release() pairs with smp_load_acquire() in
+	 * ring_space called by hns3_nic_net_xmit.
+	 */
+	smp_store_release(&ring->next_to_clean, ntc);
 }
 
 static int is_valid_clean_head(struct hns3_enet_ring *ring, int h)
@@ -2169,11 +2300,7 @@ void hns3_clean_tx_ring(struct hns3_enet_ring *ring)
 
 	bytes = 0;
 	pkts = 0;
-	while (head != ring->next_to_clean) {
-		hns3_nic_reclaim_one_desc(ring, &bytes, &pkts);
-		/* Issue prefetch for next Tx descriptor */
-		prefetch(&ring->desc_cb[ring->next_to_clean]);
-	}
+	hns3_nic_reclaim_desc(ring, head, &bytes, &pkts);
 
 	ring->tqp_vector->tx_group.total_bytes += bytes;
 	ring->tqp_vector->tx_group.total_packets += pkts;
@@ -2208,8 +2335,8 @@ static int hns3_desc_unused(struct hns3_enet_ring *ring)
 	return ((ntc >= ntu) ? 0 : ring->desc_num) + ntc - ntu;
 }
 
-static void
-hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, int cleand_count)
+static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
+				      int cleand_count)
 {
 	struct hns3_desc_cb *desc_cb;
 	struct hns3_desc_cb res_cbs;
@@ -2235,6 +2362,10 @@ hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, int cleand_count)
 				break;
 			}
 			hns3_replace_buffer(ring, ring->next_to_use, &res_cbs);
+
+			u64_stats_update_begin(&ring->syncp);
+			ring->stats.non_reuse_pg++;
+			u64_stats_update_end(&ring->syncp);
 		}
 
 		ring_ptr_move_fw(ring, next_to_use);
@@ -2248,64 +2379,95 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 				struct hns3_enet_ring *ring, int pull_len,
 				struct hns3_desc_cb *desc_cb)
 {
-	struct hns3_desc *desc;
-	u32 truesize;
-	int size;
-	int last_offset;
-	bool twobufs;
-
-	twobufs = ((PAGE_SIZE < 8192) &&
-		hnae3_buf_size(ring) == HNS3_BUFFER_SIZE_2048);
-
-	desc = &ring->desc[ring->next_to_clean];
-	size = le16_to_cpu(desc->rx.size);
-
-	truesize = hnae3_buf_size(ring);
-
-	if (!twobufs)
-		last_offset = hnae3_page_size(ring) - hnae3_buf_size(ring);
+	struct hns3_desc *desc = &ring->desc[ring->next_to_clean];
+	int size = le16_to_cpu(desc->rx.size);
+	u32 truesize = hnae3_buf_size(ring);
 
 	skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
 			size - pull_len, truesize);
 
-	 /* Avoid re-using remote pages,flag default unreuse */
-	if (unlikely(page_to_nid(desc_cb->priv) != numa_node_id()))
-		return;
-
-	if (twobufs) {
-		/* If we are only owner of page we can reuse it */
-		if (likely(page_count(desc_cb->priv) == 1)) {
-			/* Flip page offset to other buffer */
-			desc_cb->page_offset ^= truesize;
-
-			desc_cb->reuse_flag = 1;
-			/* bump ref count on page before it is given*/
-			get_page(desc_cb->priv);
-		}
+	/* Avoid re-using remote pages, or the stack is still using the page
+	 * when page_offset rollback to zero, flag default unreuse
+	 */
+	if (unlikely(page_to_nid(desc_cb->priv) != numa_mem_id()) ||
+	    (!desc_cb->page_offset && page_count(desc_cb->priv) > 1))
 		return;
-	}
 
 	/* Move offset up to the next cache line */
 	desc_cb->page_offset += truesize;
 
-	if (desc_cb->page_offset <= last_offset) {
+	if (desc_cb->page_offset + truesize <= hnae3_page_size(ring)) {
+		desc_cb->reuse_flag = 1;
+		/* Bump ref count on page before it is given */
+		get_page(desc_cb->priv);
+	} else if (page_count(desc_cb->priv) == 1) {
 		desc_cb->reuse_flag = 1;
-		/* Bump ref count on page before it is given*/
+		desc_cb->page_offset = 0;
 		get_page(desc_cb->priv);
 	}
 }
 
+static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
+{
+	__be16 type = skb->protocol;
+	struct tcphdr *th;
+	int depth = 0;
+
+	while (eth_type_vlan(type)) {
+		struct vlan_hdr *vh;
+
+		if ((depth + VLAN_HLEN) > skb_headlen(skb))
+			return -EFAULT;
+
+		vh = (struct vlan_hdr *)(skb->data + depth);
+		type = vh->h_vlan_encapsulated_proto;
+		depth += VLAN_HLEN;
+	}
+
+	skb_set_network_header(skb, depth);
+
+	if (type == htons(ETH_P_IP)) {
+		const struct iphdr *iph = ip_hdr(skb);
+
+		depth += sizeof(struct iphdr);
+		skb_set_transport_header(skb, depth);
+		th = tcp_hdr(skb);
+		th->check = ~tcp_v4_check(skb->len - depth, iph->saddr,
+					  iph->daddr, 0);
+	} else if (type == htons(ETH_P_IPV6)) {
+		const struct ipv6hdr *iph = ipv6_hdr(skb);
+
+		depth += sizeof(struct ipv6hdr);
+		skb_set_transport_header(skb, depth);
+		th = tcp_hdr(skb);
+		th->check = ~tcp_v6_check(skb->len - depth, &iph->saddr,
+					  &iph->daddr, 0);
+	} else {
+		netdev_err(skb->dev,
+			   "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n",
+			   be16_to_cpu(type), depth);
+		return -EFAULT;
+	}
+
+	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+	if (th->cwr)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+	if (l234info & BIT(HNS3_RXD_GRO_FIXID_B))
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID;
+
+	skb->csum_start = (unsigned char *)th - skb->head;
+	skb->csum_offset = offsetof(struct tcphdr, check);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	return 0;
+}
+
 static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
-			     struct hns3_desc *desc)
+			     u32 l234info, u32 bd_base_info, u32 ol_info)
 {
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
 	int l3_type, l4_type;
-	u32 bd_base_info;
 	int ol4_type;
-	u32 l234info;
-
-	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-	l234info = le32_to_cpu(desc->rx.l234_info);
 
 	skb->ip_summed = CHECKSUM_NONE;
 
@@ -2314,20 +2476,13 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	if (!(netdev->features & NETIF_F_RXCSUM))
 		return;
 
-	/* We MUST enable hardware checksum before enabling hardware GRO */
-	if (skb_shinfo(skb)->gso_size) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		return;
-	}
-
 	/* check if hardware has done checksum */
-	if (!hnae3_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
+	if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
 		return;
 
-	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L3E_B) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_L4E_B) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) {
+	if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
+				 BIT(HNS3_RXD_OL3E_B) |
+				 BIT(HNS3_RXD_OL4E_B)))) {
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.l3l4_csum_err++;
 		u64_stats_update_end(&ring->syncp);
@@ -2335,12 +2490,7 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		return;
 	}
 
-	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
-				  HNS3_RXD_L3ID_S);
-	l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
-				  HNS3_RXD_L4ID_S);
-
-	ol4_type = hnae3_get_field(l234info, HNS3_RXD_OL4ID_M,
+	ol4_type = hnae3_get_field(ol_info, HNS3_RXD_OL4ID_M,
 				   HNS3_RXD_OL4ID_S);
 	switch (ol4_type) {
 	case HNS3_OL4_TYPE_MAC_IN_UDP:
@@ -2348,6 +2498,11 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		skb->csum_level = 1;
 		/* fall through */
 	case HNS3_OL4_TYPE_NO_TUN:
+		l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+					  HNS3_RXD_L3ID_S);
+		l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
+					  HNS3_RXD_L4ID_S);
+
 		/* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */
 		if ((l3_type == HNS3_L3_TYPE_IPV4 ||
 		     l3_type == HNS3_L3_TYPE_IPV6) &&
@@ -2373,6 +2528,7 @@ static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 				struct hns3_desc *desc, u32 l234info,
 				u16 *vlan_tag)
 {
+	struct hnae3_handle *handle = ring->tqp->handle;
 	struct pci_dev *pdev = ring->tqp->handle->pdev;
 
 	if (pdev->revision == 0x20) {
@@ -2385,21 +2541,42 @@ static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 
 #define HNS3_STRP_OUTER_VLAN	0x1
 #define HNS3_STRP_INNER_VLAN	0x2
+#define HNS3_STRP_BOTH		0x3
 
+	/* Hardware always insert VLAN tag into RX descriptor when
+	 * remove the tag from packet, driver needs to determine
+	 * reporting which tag to stack.
+	 */
 	switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
 				HNS3_RXD_STRP_TAGP_S)) {
 	case HNS3_STRP_OUTER_VLAN:
+		if (handle->port_base_vlan_state !=
+				HNAE3_PORT_BASE_VLAN_DISABLE)
+			return false;
+
 		*vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
 		return true;
 	case HNS3_STRP_INNER_VLAN:
+		if (handle->port_base_vlan_state !=
+				HNAE3_PORT_BASE_VLAN_DISABLE)
+			return false;
+
 		*vlan_tag = le16_to_cpu(desc->rx.vlan_tag);
 		return true;
+	case HNS3_STRP_BOTH:
+		if (handle->port_base_vlan_state ==
+				HNAE3_PORT_BASE_VLAN_DISABLE)
+			*vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
+		else
+			*vlan_tag = le16_to_cpu(desc->rx.vlan_tag);
+
+		return true;
 	default:
 		return false;
 	}
 }
 
-static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
+static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
 			  unsigned char *va)
 {
 #define HNS3_NEED_ADD_FRAG	1
@@ -2428,7 +2605,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
 		memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
 
 		/* We can reuse buffer as-is, just make sure it is local */
-		if (likely(page_to_nid(desc_cb->priv) == numa_node_id()))
+		if (likely(page_to_nid(desc_cb->priv) == numa_mem_id()))
 			desc_cb->reuse_flag = 1;
 		else /* This page cannot be reused so discard it */
 			put_page(desc_cb->priv);
@@ -2440,7 +2617,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
 	ring->stats.seg_pkt_cnt++;
 	u64_stats_update_end(&ring->syncp);
 
-	ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
+	ring->pull_len = eth_get_headlen(netdev, va, HNS3_RX_HEAD_SIZE);
 	__skb_put(skb, ring->pull_len);
 	hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len,
 			    desc_cb);
@@ -2465,18 +2642,20 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 	 */
 	if (pending) {
 		pre_bd = (ring->next_to_clean - 1 + ring->desc_num) %
-			ring->desc_num;
+			 ring->desc_num;
 		pre_desc = &ring->desc[pre_bd];
 		bd_base_info = le32_to_cpu(pre_desc->rx.bd_base_info);
 	} else {
 		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 	}
 
-	while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
+	while (!(bd_base_info & BIT(HNS3_RXD_FE_B))) {
 		desc = &ring->desc[ring->next_to_clean];
 		desc_cb = &ring->desc_cb[ring->next_to_clean];
 		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-		if (!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))
+		/* make sure HW write desc complete */
+		dma_rmb();
+		if (!(bd_base_info & BIT(HNS3_RXD_VLD_B)))
 			return -ENXIO;
 
 		if (unlikely(ring->frag_num >= MAX_SKB_FRAGS)) {
@@ -2513,71 +2692,135 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
 	return 0;
 }
 
-static void hns3_set_gro_param(struct sk_buff *skb, u32 l234info,
-			       u32 bd_base_info)
+static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring,
+				     struct sk_buff *skb, u32 l234info,
+				     u32 bd_base_info, u32 ol_info)
 {
-	u16 gro_count;
 	u32 l3_type;
 
-	gro_count = hnae3_get_field(l234info, HNS3_RXD_GRO_COUNT_M,
-				    HNS3_RXD_GRO_COUNT_S);
+	skb_shinfo(skb)->gso_size = hnae3_get_field(bd_base_info,
+						    HNS3_RXD_GRO_SIZE_M,
+						    HNS3_RXD_GRO_SIZE_S);
 	/* if there is no HW GRO, do not set gro params */
-	if (!gro_count)
-		return;
+	if (!skb_shinfo(skb)->gso_size) {
+		hns3_rx_checksum(ring, skb, l234info, bd_base_info, ol_info);
+		return 0;
+	}
 
-	/* tcp_gro_complete() will copy NAPI_GRO_CB(skb)->count
-	 * to skb_shinfo(skb)->gso_segs
-	 */
-	NAPI_GRO_CB(skb)->count = gro_count;
+	NAPI_GRO_CB(skb)->count = hnae3_get_field(l234info,
+						  HNS3_RXD_GRO_COUNT_M,
+						  HNS3_RXD_GRO_COUNT_S);
 
-	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
-				  HNS3_RXD_L3ID_S);
+	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S);
 	if (l3_type == HNS3_L3_TYPE_IPV4)
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 	else if (l3_type == HNS3_L3_TYPE_IPV6)
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 	else
-		return;
+		return -EFAULT;
 
-	skb_shinfo(skb)->gso_size = hnae3_get_field(bd_base_info,
-						    HNS3_RXD_GRO_SIZE_M,
-						    HNS3_RXD_GRO_SIZE_S);
-	if (skb_shinfo(skb)->gso_size)
-		tcp_gro_complete(skb);
+	return  hns3_gro_complete(skb, l234info);
 }
 
 static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
-				     struct sk_buff *skb)
+				     struct sk_buff *skb, u32 rss_hash)
 {
 	struct hnae3_handle *handle = ring->tqp->handle;
 	enum pkt_hash_types rss_type;
-	struct hns3_desc *desc;
-	int last_bd;
-
-	/* When driver handle the rss type, ring->next_to_clean indicates the
-	 * first descriptor of next packet, need -1 here.
-	 */
-	last_bd = (ring->next_to_clean - 1 + ring->desc_num) % ring->desc_num;
-	desc = &ring->desc[last_bd];
 
-	if (le32_to_cpu(desc->rx.rss_hash))
+	if (rss_hash)
 		rss_type = handle->kinfo.rss_type;
 	else
 		rss_type = PKT_HASH_TYPE_NONE;
 
-	skb_set_hash(skb, le32_to_cpu(desc->rx.rss_hash), rss_type);
+	skb_set_hash(skb, rss_hash, rss_type);
+}
+
+static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb)
+{
+	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	enum hns3_pkt_l2t_type l2_frame_type;
+	u32 bd_base_info, l234info, ol_info;
+	struct hns3_desc *desc;
+	unsigned int len;
+	int pre_ntc, ret;
+
+	/* bdinfo handled below is only valid on the last BD of the
+	 * current packet, and ring->next_to_clean indicates the first
+	 * descriptor of next packet, so need - 1 below.
+	 */
+	pre_ntc = ring->next_to_clean ? (ring->next_to_clean - 1) :
+					(ring->desc_num - 1);
+	desc = &ring->desc[pre_ntc];
+	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+	l234info = le32_to_cpu(desc->rx.l234_info);
+	ol_info = le32_to_cpu(desc->rx.ol_info);
+
+	/* Based on hw strategy, the tag offloaded will be stored at
+	 * ot_vlan_tag in two layer tag case, and stored at vlan_tag
+	 * in one layer tag case.
+	 */
+	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
+		u16 vlan_tag;
+
+		if (hns3_parse_vlan_tag(ring, desc, l234info, &vlan_tag))
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       vlan_tag);
+	}
+
+	if (unlikely(!desc->rx.pkt_len || (l234info & (BIT(HNS3_RXD_TRUNCAT_B) |
+				  BIT(HNS3_RXD_L2E_B))))) {
+		u64_stats_update_begin(&ring->syncp);
+		if (l234info & BIT(HNS3_RXD_L2E_B))
+			ring->stats.l2_err++;
+		else
+			ring->stats.err_pkt_len++;
+		u64_stats_update_end(&ring->syncp);
+
+		return -EFAULT;
+	}
+
+	len = skb->len;
+
+	/* Do update ip stack process */
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	/* This is needed in order to enable forwarding support */
+	ret = hns3_set_gro_and_checksum(ring, skb, l234info,
+					bd_base_info, ol_info);
+	if (unlikely(ret)) {
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.rx_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+		return ret;
+	}
+
+	l2_frame_type = hnae3_get_field(l234info, HNS3_RXD_DMAC_M,
+					HNS3_RXD_DMAC_S);
+
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.rx_pkts++;
+	ring->stats.rx_bytes += len;
+
+	if (l2_frame_type == HNS3_L2_TYPE_MULTICAST)
+		ring->stats.rx_multicast++;
+
+	u64_stats_update_end(&ring->syncp);
+
+	ring->tqp_vector->rx_group.total_bytes += len;
+
+	hns3_set_rx_skb_rss_type(ring, skb, le32_to_cpu(desc->rx.rss_hash));
+	return 0;
 }
 
 static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 			     struct sk_buff **out_skb)
 {
-	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
 	struct sk_buff *skb = ring->skb;
 	struct hns3_desc_cb *desc_cb;
 	struct hns3_desc *desc;
+	unsigned int length;
 	u32 bd_base_info;
-	u32 l234info;
-	int length;
 	int ret;
 
 	desc = &ring->desc[ring->next_to_clean];
@@ -2589,7 +2832,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
 	/* Check valid BD */
-	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
+	if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B))))
 		return -ENXIO;
 
 	if (!skb)
@@ -2636,75 +2879,24 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 		       ALIGN(ring->pull_len, sizeof(long)));
 	}
 
-	l234info = le32_to_cpu(desc->rx.l234_info);
-	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-
-	/* Based on hw strategy, the tag offloaded will be stored at
-	 * ot_vlan_tag in two layer tag case, and stored at vlan_tag
-	 * in one layer tag case.
-	 */
-	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
-		u16 vlan_tag;
-
-		if (hns3_parse_vlan_tag(ring, desc, l234info, &vlan_tag))
-			__vlan_hwaccel_put_tag(skb,
-					       htons(ETH_P_8021Q),
-					       vlan_tag);
-	}
-
-	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.non_vld_descs++;
-		u64_stats_update_end(&ring->syncp);
-
-		dev_kfree_skb_any(skb);
-		return -EINVAL;
-	}
-
-	if (unlikely((!desc->rx.pkt_len) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.err_pkt_len++;
-		u64_stats_update_end(&ring->syncp);
-
-		dev_kfree_skb_any(skb);
-		return -EFAULT;
-	}
-
-	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.l2_err++;
-		u64_stats_update_end(&ring->syncp);
-
+	ret = hns3_handle_bdinfo(ring, skb);
+	if (unlikely(ret)) {
 		dev_kfree_skb_any(skb);
-		return -EFAULT;
+		return ret;
 	}
 
-	u64_stats_update_begin(&ring->syncp);
-	ring->stats.rx_pkts++;
-	ring->stats.rx_bytes += skb->len;
-	u64_stats_update_end(&ring->syncp);
-
-	ring->tqp_vector->rx_group.total_bytes += skb->len;
-
-	/* This is needed in order to enable forwarding support */
-	hns3_set_gro_param(skb, l234info, bd_base_info);
-
-	hns3_rx_checksum(ring, skb, desc);
+	skb_record_rx_queue(skb, ring->tqp->tqp_index);
 	*out_skb = skb;
-	hns3_set_rx_skb_rss_type(ring, skb);
 
 	return 0;
 }
 
-int hns3_clean_rx_ring(
-		struct hns3_enet_ring *ring, int budget,
-		void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *))
+int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
+		       void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *))
 {
 #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
-	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
 	int recv_pkts, recv_bds, clean_count, err;
-	int unused_count = hns3_desc_unused(ring) - ring->pending_buf;
+	int unused_count = hns3_desc_unused(ring);
 	struct sk_buff *skb = ring->skb;
 	int num;
 
@@ -2713,6 +2905,7 @@ int hns3_clean_rx_ring(
 
 	recv_pkts = 0, recv_bds = 0, clean_count = 0;
 	num -= unused_count;
+	unused_count -= ring->pending_buf;
 
 	while (recv_pkts < budget && recv_bds < num) {
 		/* Reuse or realloc buffers */
@@ -2739,8 +2932,6 @@ int hns3_clean_rx_ring(
 			continue;
 		}
 
-		/* Do update ip stack process */
-		skb->protocol = eth_type_trans(skb, netdev);
 		rx_fn(ring, skb);
 		recv_bds += ring->pending_buf;
 		clean_count += ring->pending_buf;
@@ -2753,42 +2944,25 @@ int hns3_clean_rx_ring(
 out:
 	/* Make all data has been write before submit */
 	if (clean_count + unused_count > 0)
-		hns3_nic_alloc_rx_buffers(ring,
-					  clean_count + unused_count);
+		hns3_nic_alloc_rx_buffers(ring, clean_count + unused_count);
 
 	return recv_pkts;
 }
 
-static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
+static bool hns3_get_new_flow_lvl(struct hns3_enet_ring_group *ring_group)
 {
-	struct hns3_enet_tqp_vector *tqp_vector =
-					ring_group->ring->tqp_vector;
+#define HNS3_RX_LOW_BYTE_RATE 10000
+#define HNS3_RX_MID_BYTE_RATE 20000
+#define HNS3_RX_ULTRA_PACKET_RATE 40
+
 	enum hns3_flow_level_range new_flow_level;
-	int packets_per_msecs;
-	int bytes_per_msecs;
+	struct hns3_enet_tqp_vector *tqp_vector;
+	int packets_per_msecs, bytes_per_msecs;
 	u32 time_passed_ms;
-	u16 new_int_gl;
-
-	if (!ring_group->coal.int_gl || !tqp_vector->last_jiffies)
-		return false;
-
-	if (ring_group->total_packets == 0) {
-		ring_group->coal.int_gl = HNS3_INT_GL_50K;
-		ring_group->coal.flow_level = HNS3_FLOW_LOW;
-		return true;
-	}
 
-	/* Simple throttlerate management
-	 * 0-10MB/s   lower     (50000 ints/s)
-	 * 10-20MB/s   middle    (20000 ints/s)
-	 * 20-1249MB/s high      (18000 ints/s)
-	 * > 40000pps  ultra     (8000 ints/s)
-	 */
-	new_flow_level = ring_group->coal.flow_level;
-	new_int_gl = ring_group->coal.int_gl;
+	tqp_vector = ring_group->ring->tqp_vector;
 	time_passed_ms =
 		jiffies_to_msecs(jiffies - tqp_vector->last_jiffies);
-
 	if (!time_passed_ms)
 		return false;
 
@@ -2798,9 +2972,14 @@ static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
 	do_div(ring_group->total_bytes, time_passed_ms);
 	bytes_per_msecs = ring_group->total_bytes;
 
-#define HNS3_RX_LOW_BYTE_RATE 10000
-#define HNS3_RX_MID_BYTE_RATE 20000
+	new_flow_level = ring_group->coal.flow_level;
 
+	/* Simple throttlerate management
+	 * 0-10MB/s   lower     (50000 ints/s)
+	 * 10-20MB/s   middle    (20000 ints/s)
+	 * 20-1249MB/s high      (18000 ints/s)
+	 * > 40000pps  ultra     (8000 ints/s)
+	 */
 	switch (new_flow_level) {
 	case HNS3_FLOW_LOW:
 		if (bytes_per_msecs > HNS3_RX_LOW_BYTE_RATE)
@@ -2820,13 +2999,40 @@ static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
 		break;
 	}
 
-#define HNS3_RX_ULTRA_PACKET_RATE 40
-
 	if (packets_per_msecs > HNS3_RX_ULTRA_PACKET_RATE &&
 	    &tqp_vector->rx_group == ring_group)
 		new_flow_level = HNS3_FLOW_ULTRA;
 
-	switch (new_flow_level) {
+	ring_group->total_bytes = 0;
+	ring_group->total_packets = 0;
+	ring_group->coal.flow_level = new_flow_level;
+
+	return true;
+}
+
+static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
+{
+	struct hns3_enet_tqp_vector *tqp_vector;
+	u16 new_int_gl;
+
+	if (!ring_group->ring)
+		return false;
+
+	tqp_vector = ring_group->ring->tqp_vector;
+	if (!tqp_vector->last_jiffies)
+		return false;
+
+	if (ring_group->total_packets == 0) {
+		ring_group->coal.int_gl = HNS3_INT_GL_50K;
+		ring_group->coal.flow_level = HNS3_FLOW_LOW;
+		return true;
+	}
+
+	if (!hns3_get_new_flow_lvl(ring_group))
+		return false;
+
+	new_int_gl = ring_group->coal.int_gl;
+	switch (ring_group->coal.flow_level) {
 	case HNS3_FLOW_LOW:
 		new_int_gl = HNS3_INT_GL_50K;
 		break;
@@ -2843,9 +3049,6 @@ static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
 		break;
 	}
 
-	ring_group->total_bytes = 0;
-	ring_group->total_packets = 0;
-	ring_group->coal.flow_level = new_flow_level;
 	if (new_int_gl != ring_group->coal.int_gl) {
 		ring_group->coal.int_gl = new_int_gl;
 		return true;
@@ -2872,7 +3075,7 @@ static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector)
 	}
 
 	if (tx_group->coal.gl_adapt_enable) {
-		tx_update = hns3_get_new_int_gl(&tqp_vector->tx_group);
+		tx_update = hns3_get_new_int_gl(tx_group);
 		if (tx_update)
 			hns3_set_vector_coalesce_tx_gl(tqp_vector,
 						       tx_group->coal.int_gl);
@@ -2890,7 +3093,7 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	struct hns3_enet_tqp_vector *tqp_vector =
 		container_of(napi, struct hns3_enet_tqp_vector, napi);
 	bool clean_complete = true;
-	int rx_budget;
+	int rx_budget = budget;
 
 	if (unlikely(test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) {
 		napi_complete(napi);
@@ -2904,7 +3107,8 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 		hns3_clean_tx_ring(ring);
 
 	/* make sure rx ring budget not smaller than 1 */
-	rx_budget = max(budget / tqp_vector->num_tqps, 1);
+	if (tqp_vector->num_tqps > 1)
+		rx_budget = max(budget / tqp_vector->num_tqps, 1);
 
 	hns3_for_each_ring(ring, tqp_vector->rx_group) {
 		int rx_cleaned = hns3_clean_rx_ring(ring, rx_budget,
@@ -3145,6 +3349,7 @@ static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv)
 	if (!vector)
 		return -ENOMEM;
 
+	/* save the actual available vector number */
 	vector_num = h->ae_algo->ops->get_vector(h, vector_num, vector);
 
 	priv->vector_num = vector_num;
@@ -3175,43 +3380,36 @@ static void hns3_clear_ring_group(struct hns3_enet_ring_group *group)
 	group->count = 0;
 }
 
-static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
+static void hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
 {
 	struct hnae3_ring_chain_node vector_ring_chain;
 	struct hnae3_handle *h = priv->ae_handle;
 	struct hns3_enet_tqp_vector *tqp_vector;
-	int i, ret;
+	int i;
 
 	for (i = 0; i < priv->vector_num; i++) {
 		tqp_vector = &priv->tqp_vector[i];
 
-		ret = hns3_get_vector_ring_chain(tqp_vector,
-						 &vector_ring_chain);
-		if (ret)
-			return ret;
+		if (!tqp_vector->rx_group.ring && !tqp_vector->tx_group.ring)
+			continue;
 
-		ret = h->ae_algo->ops->unmap_ring_from_vector(h,
+		hns3_get_vector_ring_chain(tqp_vector, &vector_ring_chain);
+
+		h->ae_algo->ops->unmap_ring_from_vector(h,
 			tqp_vector->vector_irq, &vector_ring_chain);
-		if (ret)
-			return ret;
 
 		hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
 
 		if (tqp_vector->irq_init_flag == HNS3_VECTOR_INITED) {
-			irq_set_affinity_notifier(tqp_vector->vector_irq,
-						  NULL);
 			irq_set_affinity_hint(tqp_vector->vector_irq, NULL);
 			free_irq(tqp_vector->vector_irq, tqp_vector);
 			tqp_vector->irq_init_flag = HNS3_VECTOR_NOT_INITED;
 		}
 
-		priv->ring_data[i].ring->irq_init_flag = HNS3_VECTOR_NOT_INITED;
 		hns3_clear_ring_group(&tqp_vector->rx_group);
 		hns3_clear_ring_group(&tqp_vector->tx_group);
 		netif_napi_del(&priv->tqp_vector[i].napi);
 	}
-
-	return 0;
 }
 
 static int hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
@@ -3234,22 +3432,25 @@ static int hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
 }
 
 static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
-			     int ring_type)
+			     unsigned int ring_type)
 {
 	struct hns3_nic_ring_data *ring_data = priv->ring_data;
 	int queue_num = priv->ae_handle->kinfo.num_tqps;
 	struct pci_dev *pdev = priv->ae_handle->pdev;
 	struct hns3_enet_ring *ring;
+	int desc_num;
 
 	ring = devm_kzalloc(&pdev->dev, sizeof(*ring), GFP_KERNEL);
 	if (!ring)
 		return -ENOMEM;
 
 	if (ring_type == HNAE3_RING_TYPE_TX) {
+		desc_num = priv->ae_handle->kinfo.num_tx_desc;
 		ring_data[q->tqp_index].ring = ring;
 		ring_data[q->tqp_index].queue_index = q->tqp_index;
 		ring->io_base = (u8 __iomem *)q->io_base + HNS3_TX_REG_OFFSET;
 	} else {
+		desc_num = priv->ae_handle->kinfo.num_rx_desc;
 		ring_data[q->tqp_index + queue_num].ring = ring;
 		ring_data[q->tqp_index + queue_num].queue_index = q->tqp_index;
 		ring->io_base = q->io_base;
@@ -3263,7 +3464,7 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 	ring->dev = priv->dev;
 	ring->desc_dma_addr = 0;
 	ring->buf_size = q->buf_size;
-	ring->desc_num = q->desc_num;
+	ring->desc_num = desc_num;
 	ring->next_to_use = 0;
 	ring->next_to_clean = 0;
 
@@ -3317,6 +3518,7 @@ err:
 	}
 
 	devm_kfree(&pdev->dev, priv->ring_data);
+	priv->ring_data = NULL;
 	return ret;
 }
 
@@ -3325,12 +3527,16 @@ static void hns3_put_ring_config(struct hns3_nic_priv *priv)
 	struct hnae3_handle *h = priv->ae_handle;
 	int i;
 
+	if (!priv->ring_data)
+		return;
+
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
 		devm_kfree(priv->dev, priv->ring_data[i].ring);
 		devm_kfree(priv->dev,
 			   priv->ring_data[i + h->kinfo.num_tqps].ring);
 	}
 	devm_kfree(priv->dev, priv->ring_data);
+	priv->ring_data = NULL;
 }
 
 static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
@@ -3340,8 +3546,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
 	if (ring->desc_num <= 0 || ring->buf_size <= 0)
 		return -EINVAL;
 
-	ring->desc_cb = kcalloc(ring->desc_num, sizeof(ring->desc_cb[0]),
-				GFP_KERNEL);
+	ring->desc_cb = devm_kcalloc(ring_to_dev(ring), ring->desc_num,
+				     sizeof(ring->desc_cb[0]), GFP_KERNEL);
 	if (!ring->desc_cb) {
 		ret = -ENOMEM;
 		goto out;
@@ -3362,7 +3568,7 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
 out_with_desc:
 	hns3_free_desc(ring);
 out_with_desc_cb:
-	kfree(ring->desc_cb);
+	devm_kfree(ring_to_dev(ring), ring->desc_cb);
 	ring->desc_cb = NULL;
 out:
 	return ret;
@@ -3371,10 +3577,15 @@ out:
 static void hns3_fini_ring(struct hns3_enet_ring *ring)
 {
 	hns3_free_desc(ring);
-	kfree(ring->desc_cb);
+	devm_kfree(ring_to_dev(ring), ring->desc_cb);
 	ring->desc_cb = NULL;
 	ring->next_to_clean = 0;
 	ring->next_to_use = 0;
+	ring->pending_buf = 0;
+	if (ring->skb) {
+		dev_kfree_skb_any(ring->skb);
+		ring->skb = NULL;
+	}
 }
 
 static int hns3_buf_size2type(u32 buf_size)
@@ -3407,8 +3618,7 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring)
 	struct hnae3_queue *q = ring->tqp;
 
 	if (!HNAE3_IS_TX_RING(ring)) {
-		hns3_write_dev(q, HNS3_RING_RX_RING_BASEADDR_L_REG,
-			       (u32)dma);
+		hns3_write_dev(q, HNS3_RING_RX_RING_BASEADDR_L_REG, (u32)dma);
 		hns3_write_dev(q, HNS3_RING_RX_RING_BASEADDR_H_REG,
 			       (u32)((dma >> 31) >> 1));
 
@@ -3515,6 +3725,25 @@ static int hns3_init_mac_addr(struct net_device *netdev, bool init)
 	return ret;
 }
 
+static int hns3_init_phy(struct net_device *netdev)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	int ret = 0;
+
+	if (h->ae_algo->ops->mac_connect_phy)
+		ret = h->ae_algo->ops->mac_connect_phy(h);
+
+	return ret;
+}
+
+static void hns3_uninit_phy(struct net_device *netdev)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (h->ae_algo->ops->mac_disconnect_phy)
+		h->ae_algo->ops->mac_disconnect_phy(h);
+}
+
 static int hns3_restore_fd_rules(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
@@ -3534,18 +3763,6 @@ static void hns3_del_all_fd_rules(struct net_device *netdev, bool clear_list)
 		h->ae_algo->ops->del_all_fd_entries(h, clear_list);
 }
 
-static void hns3_nic_set_priv_ops(struct net_device *netdev)
-{
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-
-	priv->ops.fill_desc = hns3_fill_desc;
-	if ((netdev->features & NETIF_F_TSO) ||
-	    (netdev->features & NETIF_F_TSO6))
-		priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tso;
-	else
-		priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx;
-}
-
 static int hns3_client_start(struct hnae3_handle *handle)
 {
 	if (!handle->ae_algo->ops->client_start)
@@ -3562,6 +3779,21 @@ static void hns3_client_stop(struct hnae3_handle *handle)
 	handle->ae_algo->ops->client_stop(handle);
 }
 
+static void hns3_info_show(struct hns3_nic_priv *priv)
+{
+	struct hnae3_knic_private_info *kinfo = &priv->ae_handle->kinfo;
+
+	dev_info(priv->dev, "MAC address: %pM\n", priv->netdev->dev_addr);
+	dev_info(priv->dev, "Task queue pairs numbers: %d\n", kinfo->num_tqps);
+	dev_info(priv->dev, "RSS size: %d\n", kinfo->rss_size);
+	dev_info(priv->dev, "Allocated RSS size: %d\n", kinfo->req_rss_size);
+	dev_info(priv->dev, "RX buffer length: %d\n", kinfo->rx_buf_len);
+	dev_info(priv->dev, "Desc num per TX queue: %d\n", kinfo->num_tx_desc);
+	dev_info(priv->dev, "Desc num per RX queue: %d\n", kinfo->num_rx_desc);
+	dev_info(priv->dev, "Total number of enabled TCs: %d\n", kinfo->num_tc);
+	dev_info(priv->dev, "Max mtu size: %d\n", priv->netdev->max_mtu);
+}
+
 static int hns3_client_init(struct hnae3_handle *handle)
 {
 	struct pci_dev *pdev = handle->pdev;
@@ -3581,6 +3813,9 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
 	priv->tx_timeout_count = 0;
+	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
+
+	handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);
 
 	handle->kinfo.netdev = netdev;
 	handle->priv = (void *)priv;
@@ -3594,7 +3829,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	netdev->netdev_ops = &hns3_nic_netdev_ops;
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 	hns3_ethtool_set_ops(netdev);
-	hns3_nic_set_priv_ops(netdev);
 
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
@@ -3623,6 +3857,10 @@ static int hns3_client_init(struct hnae3_handle *handle)
 		goto out_init_ring_data;
 	}
 
+	ret = hns3_init_phy(netdev);
+	if (ret)
+		goto out_init_phy;
+
 	ret = register_netdev(netdev);
 	if (ret) {
 		dev_err(priv->dev, "probe register netdev fail!\n");
@@ -3632,7 +3870,7 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	ret = hns3_client_start(handle);
 	if (ret) {
 		dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
-			goto out_reg_netdev_fail;
+		goto out_client_start;
 	}
 
 	hns3_dcbnl_setup(handle);
@@ -3644,11 +3882,19 @@ static int hns3_client_init(struct hnae3_handle *handle)
 
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
+	if (netif_msg_drv(handle))
+		hns3_info_show(priv);
+
 	return ret;
 
+out_client_start:
+	unregister_netdev(netdev);
 out_reg_netdev_fail:
+	hns3_uninit_phy(netdev);
+out_init_phy:
+	hns3_uninit_all_ring(priv);
 out_init_ring_data:
-	(void)hns3_nic_uninit_vector_data(priv);
+	hns3_nic_uninit_vector_data(priv);
 out_init_vector_data:
 	hns3_nic_dealloc_vector_data(priv);
 out_alloc_vector_data:
@@ -3665,13 +3911,15 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
 
-	hns3_client_stop(handle);
-
 	hns3_remove_hw_addr(netdev);
 
 	if (netdev->reg_state != NETREG_UNINITIALIZED)
 		unregister_netdev(netdev);
 
+	hns3_client_stop(handle);
+
+	hns3_uninit_phy(netdev);
+
 	if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
 		netdev_warn(netdev, "already uninitialized\n");
 		goto out_netdev_free;
@@ -3679,11 +3927,9 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	hns3_del_all_fd_rules(netdev, true);
 
-	hns3_force_clear_all_rx_ring(handle);
+	hns3_clear_all_ring(handle, true);
 
-	ret = hns3_nic_uninit_vector_data(priv);
-	if (ret)
-		netdev_err(netdev, "uninit vector error\n");
+	hns3_nic_uninit_vector_data(priv);
 
 	ret = hns3_nic_dealloc_vector_data(priv);
 	if (ret)
@@ -3697,8 +3943,6 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	hns3_dbg_uninit(handle);
 
-	priv->ring_data = NULL;
-
 out_netdev_free:
 	free_netdev(netdev);
 }
@@ -3713,11 +3957,13 @@ static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup)
 	if (linkup) {
 		netif_carrier_on(netdev);
 		netif_tx_wake_all_queues(netdev);
-		netdev_info(netdev, "link up\n");
+		if (netif_msg_link(handle))
+			netdev_info(netdev, "link up\n");
 	} else {
 		netif_carrier_off(netdev);
 		netif_tx_stop_all_queues(netdev);
-		netdev_info(netdev, "link down\n");
+		if (netif_msg_link(handle))
+			netdev_info(netdev, "link down\n");
 	}
 }
 
@@ -3725,8 +3971,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct net_device *ndev = kinfo->netdev;
-	bool if_running;
-	int ret;
 
 	if (tc > HNAE3_MAX_TC)
 		return -EINVAL;
@@ -3734,25 +3978,7 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 	if (!ndev)
 		return -ENODEV;
 
-	if_running = netif_running(ndev);
-
-	if (if_running) {
-		(void)hns3_nic_net_stop(ndev);
-		msleep(100);
-	}
-
-	ret = (kinfo->dcb_ops && kinfo->dcb_ops->map_update) ?
-		kinfo->dcb_ops->map_update(handle) : -EOPNOTSUPP;
-	if (ret)
-		goto err_out;
-
-	ret = hns3_nic_set_real_num_queue(ndev);
-
-err_out:
-	if (if_running)
-		(void)hns3_nic_net_open(ndev);
-
-	return ret;
+	return hns3_nic_set_real_num_queue(ndev);
 }
 
 static int hns3_recover_hw_addr(struct net_device *ndev)
@@ -3761,12 +3987,13 @@ static int hns3_recover_hw_addr(struct net_device *ndev)
 	struct netdev_hw_addr *ha, *tmp;
 	int ret = 0;
 
+	netif_addr_lock_bh(ndev);
 	/* go through and sync uc_addr entries to the device */
 	list = &ndev->uc;
 	list_for_each_entry_safe(ha, tmp, &list->list, list) {
 		ret = hns3_nic_uc_sync(ndev, ha->addr);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* go through and sync mc_addr entries to the device */
@@ -3774,9 +4001,11 @@ static int hns3_recover_hw_addr(struct net_device *ndev)
 	list_for_each_entry_safe(ha, tmp, &list->list, list) {
 		ret = hns3_nic_mc_sync(ndev, ha->addr);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+out:
+	netif_addr_unlock_bh(ndev);
 	return ret;
 }
 
@@ -3787,6 +4016,7 @@ static void hns3_remove_hw_addr(struct net_device *netdev)
 
 	hns3_nic_uc_unsync(netdev, netdev->dev_addr);
 
+	netif_addr_lock_bh(netdev);
 	/* go through and unsync uc_addr entries to the device */
 	list = &netdev->uc;
 	list_for_each_entry_safe(ha, tmp, &list->list, list)
@@ -3797,6 +4027,8 @@ static void hns3_remove_hw_addr(struct net_device *netdev)
 	list_for_each_entry_safe(ha, tmp, &list->list, list)
 		if (ha->refcount > 1)
 			hns3_nic_mc_unsync(netdev, ha->addr);
+
+	netif_addr_unlock_bh(netdev);
 }
 
 static void hns3_clear_tx_ring(struct hns3_enet_ring *ring)
@@ -3832,12 +4064,18 @@ static int hns3_clear_rx_ring(struct hns3_enet_ring *ring)
 					    ret);
 				return ret;
 			}
-			hns3_replace_buffer(ring, ring->next_to_use,
-					    &res_cbs);
+			hns3_replace_buffer(ring, ring->next_to_use, &res_cbs);
 		}
 		ring_ptr_move_fw(ring, next_to_use);
 	}
 
+	/* Free the pending skb in rx ring */
+	if (ring->skb) {
+		dev_kfree_skb_any(ring->skb);
+		ring->skb = NULL;
+		ring->pending_buf = 0;
+	}
+
 	return 0;
 }
 
@@ -3858,40 +4096,26 @@ static void hns3_force_clear_rx_ring(struct hns3_enet_ring *ring)
 	}
 }
 
-static void hns3_force_clear_all_rx_ring(struct hnae3_handle *h)
-{
-	struct net_device *ndev = h->kinfo.netdev;
-	struct hns3_nic_priv *priv = netdev_priv(ndev);
-	struct hns3_enet_ring *ring;
-	u32 i;
-
-	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		ring = priv->ring_data[i + h->kinfo.num_tqps].ring;
-		hns3_force_clear_rx_ring(ring);
-	}
-}
-
-static void hns3_clear_all_ring(struct hnae3_handle *h)
+static void hns3_clear_all_ring(struct hnae3_handle *h, bool force)
 {
 	struct net_device *ndev = h->kinfo.netdev;
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	u32 i;
 
 	for (i = 0; i < h->kinfo.num_tqps; i++) {
-		struct netdev_queue *dev_queue;
 		struct hns3_enet_ring *ring;
 
 		ring = priv->ring_data[i].ring;
 		hns3_clear_tx_ring(ring);
-		dev_queue = netdev_get_tx_queue(ndev,
-						priv->ring_data[i].queue_index);
-		netdev_tx_reset_queue(dev_queue);
 
 		ring = priv->ring_data[i + h->kinfo.num_tqps].ring;
 		/* Continue to clear other rings even if clearing some
 		 * rings failed.
 		 */
-		hns3_clear_rx_ring(ring);
+		if (force)
+			hns3_force_clear_rx_ring(ring);
+		else
+			hns3_clear_rx_ring(ring);
 	}
 }
 
@@ -4001,7 +4225,7 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
 		if (ret) {
 			set_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
 			netdev_err(kinfo->netdev,
-				   "hns net up fail, ret=%d!\n", ret);
+				   "net up fail, ret=%d!\n", ret);
 			return ret;
 		}
 	}
@@ -4013,41 +4237,18 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 {
 	struct net_device *netdev = handle->kinfo.netdev;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	bool vlan_filter_enable;
 	int ret;
 
-	ret = hns3_init_mac_addr(netdev, false);
-	if (ret)
-		return ret;
-
-	ret = hns3_recover_hw_addr(netdev);
-	if (ret)
-		return ret;
-
-	ret = hns3_update_promisc_mode(netdev, handle->netdev_flags);
-	if (ret)
-		return ret;
-
-	vlan_filter_enable = netdev->flags & IFF_PROMISC ? false : true;
-	hns3_enable_vlan_filter(netdev, vlan_filter_enable);
-
-	/* Hardware table is only clear when pf resets */
-	if (!(handle->flags & HNAE3_SUPPORT_VF)) {
-		ret = hns3_restore_vlan(netdev);
-		if (ret)
-			return ret;
-	}
+	/* Carrier off reporting is important to ethtool even BEFORE open */
+	netif_carrier_off(netdev);
 
-	ret = hns3_restore_fd_rules(netdev);
+	ret = hns3_get_ring_config(priv);
 	if (ret)
 		return ret;
 
-	/* Carrier off reporting is important to ethtool even BEFORE open */
-	netif_carrier_off(netdev);
-
 	ret = hns3_nic_alloc_vector_data(priv);
 	if (ret)
-		return ret;
+		goto err_put_ring;
 
 	hns3_restore_coal(priv);
 
@@ -4059,37 +4260,70 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 	if (ret)
 		goto err_uninit_vector;
 
+	ret = hns3_client_start(handle);
+	if (ret) {
+		dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
+		goto err_uninit_ring;
+	}
+
 	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
 	return ret;
 
+err_uninit_ring:
+	hns3_uninit_all_ring(priv);
 err_uninit_vector:
 	hns3_nic_uninit_vector_data(priv);
-	priv->ring_data = NULL;
 err_dealloc_vector:
 	hns3_nic_dealloc_vector_data(priv);
+err_put_ring:
+	hns3_put_ring_config(priv);
 
 	return ret;
 }
 
+static int hns3_reset_notify_restore_enet(struct hnae3_handle *handle)
+{
+	struct net_device *netdev = handle->kinfo.netdev;
+	bool vlan_filter_enable;
+	int ret;
+
+	ret = hns3_init_mac_addr(netdev, false);
+	if (ret)
+		return ret;
+
+	ret = hns3_recover_hw_addr(netdev);
+	if (ret)
+		return ret;
+
+	ret = hns3_update_promisc_mode(netdev, handle->netdev_flags);
+	if (ret)
+		return ret;
+
+	vlan_filter_enable = netdev->flags & IFF_PROMISC ? false : true;
+	hns3_enable_vlan_filter(netdev, vlan_filter_enable);
+
+	if (handle->ae_algo->ops->restore_vlan_table)
+		handle->ae_algo->ops->restore_vlan_table(handle);
+
+	return hns3_restore_fd_rules(netdev);
+}
+
 static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 {
 	struct net_device *netdev = handle->kinfo.netdev;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
 
-	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+	if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
 		netdev_warn(netdev, "already uninitialized\n");
 		return 0;
 	}
 
-	hns3_force_clear_all_rx_ring(handle);
+	hns3_clear_all_ring(handle, true);
+	hns3_reset_tx_queue(priv->ae_handle);
 
-	ret = hns3_nic_uninit_vector_data(priv);
-	if (ret) {
-		netdev_err(netdev, "uninit vector error\n");
-		return ret;
-	}
+	hns3_nic_uninit_vector_data(priv);
 
 	hns3_store_coal(priv);
 
@@ -4101,7 +4335,7 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 	if (ret)
 		netdev_err(netdev, "uninit ring error\n");
 
-	clear_bit(HNS3_NIC_STATE_INITED, &priv->state);
+	hns3_put_ring_config(priv);
 
 	return ret;
 }
@@ -4124,6 +4358,9 @@ static int hns3_reset_notify(struct hnae3_handle *handle,
 	case HNAE3_UNINIT_CLIENT:
 		ret = hns3_reset_notify_uninit_enet(handle);
 		break;
+	case HNAE3_RESTORE_CLIENT:
+		ret = hns3_reset_notify_restore_enet(handle);
+		break;
 	default:
 		break;
 	}
@@ -4131,57 +4368,12 @@ static int hns3_reset_notify(struct hnae3_handle *handle,
 	return ret;
 }
 
-static int hns3_modify_tqp_num(struct net_device *netdev, u16 new_tqp_num)
-{
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = hns3_get_handle(netdev);
-	int ret;
-
-	ret = h->ae_algo->ops->set_channels(h, new_tqp_num);
-	if (ret)
-		return ret;
-
-	ret = hns3_get_ring_config(priv);
-	if (ret)
-		return ret;
-
-	ret = hns3_nic_alloc_vector_data(priv);
-	if (ret)
-		goto err_alloc_vector;
-
-	hns3_restore_coal(priv);
-
-	ret = hns3_nic_init_vector_data(priv);
-	if (ret)
-		goto err_uninit_vector;
-
-	ret = hns3_init_all_ring(priv);
-	if (ret)
-		goto err_put_ring;
-
-	return 0;
-
-err_put_ring:
-	hns3_put_ring_config(priv);
-err_uninit_vector:
-	hns3_nic_uninit_vector_data(priv);
-err_alloc_vector:
-	hns3_nic_dealloc_vector_data(priv);
-	return ret;
-}
-
-static int hns3_adjust_tqps_num(u8 num_tc, u32 new_tqp_num)
-{
-	return (new_tqp_num / num_tc) * num_tc;
-}
-
 int hns3_set_channels(struct net_device *netdev,
 		      struct ethtool_channels *ch)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
-	bool if_running = netif_running(netdev);
+	bool rxfh_configured = netif_is_rxfh_configured(netdev);
 	u32 new_tqp_num = ch->combined_count;
 	u16 org_tqp_num;
 	int ret;
@@ -4190,39 +4382,29 @@ int hns3_set_channels(struct net_device *netdev,
 		return -EINVAL;
 
 	if (new_tqp_num > hns3_get_max_available_channels(h) ||
-	    new_tqp_num < kinfo->num_tc) {
+	    new_tqp_num < 1) {
 		dev_err(&netdev->dev,
-			"Change tqps fail, the tqp range is from %d to %d",
-			kinfo->num_tc,
+			"Change tqps fail, the tqp range is from 1 to %d",
 			hns3_get_max_available_channels(h));
 		return -EINVAL;
 	}
 
-	new_tqp_num = hns3_adjust_tqps_num(kinfo->num_tc, new_tqp_num);
-	if (kinfo->num_tqps == new_tqp_num)
+	if (kinfo->rss_size == new_tqp_num)
 		return 0;
 
-	if (if_running)
-		hns3_nic_net_stop(netdev);
-
-	ret = hns3_nic_uninit_vector_data(priv);
-	if (ret) {
-		dev_err(&netdev->dev,
-			"Unbind vector with tqp fail, nothing is changed");
-		goto open_netdev;
-	}
-
-	hns3_store_coal(priv);
-
-	hns3_nic_dealloc_vector_data(priv);
+	ret = hns3_reset_notify(h, HNAE3_DOWN_CLIENT);
+	if (ret)
+		return ret;
 
-	hns3_uninit_all_ring(priv);
-	hns3_put_ring_config(priv);
+	ret = hns3_reset_notify(h, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
 
 	org_tqp_num = h->kinfo.num_tqps;
-	ret = hns3_modify_tqp_num(netdev, new_tqp_num);
+	ret = h->ae_algo->ops->set_channels(h, new_tqp_num, rxfh_configured);
 	if (ret) {
-		ret = hns3_modify_tqp_num(netdev, org_tqp_num);
+		ret = h->ae_algo->ops->set_channels(h, org_tqp_num,
+						    rxfh_configured);
 		if (ret) {
 			/* If revert to old tqp failed, fatal error occurred */
 			dev_err(&netdev->dev,
@@ -4232,12 +4414,11 @@ int hns3_set_channels(struct net_device *netdev,
 		dev_info(&netdev->dev,
 			 "Change tqp num fail, Revert to old tqp num");
 	}
+	ret = hns3_reset_notify(h, HNAE3_INIT_CLIENT);
+	if (ret)
+		return ret;
 
-open_netdev:
-	if (if_running)
-		hns3_nic_net_open(netdev);
-
-	return ret;
+	return hns3_reset_notify(h, HNAE3_UP_CLIENT);
 }
 
 static const struct hnae3_client_ops client_ops = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index e55995e93bb0..848b866761df 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -42,8 +42,10 @@ enum hns3_nic_state {
 #define HNS3_RING_TX_RING_HEAD_REG		0x0005C
 #define HNS3_RING_TX_RING_FBDNUM_REG		0x00060
 #define HNS3_RING_TX_RING_OFFSET_REG		0x00064
+#define HNS3_RING_TX_RING_EBDNUM_REG		0x00068
 #define HNS3_RING_TX_RING_PKTNUM_RECORD_REG	0x0006C
-
+#define HNS3_RING_TX_RING_EBD_OFFSET_REG	0x00070
+#define HNS3_RING_TX_RING_BD_ERR_REG		0x00074
 #define HNS3_RING_PREFETCH_EN_REG		0x0007C
 #define HNS3_RING_CFG_VF_NUM_REG		0x00080
 #define HNS3_RING_ASID_REG			0x0008C
@@ -74,7 +76,7 @@ enum hns3_nic_state {
 #define HNS3_RING_NAME_LEN			16
 #define HNS3_BUFFER_SIZE_2048			2048
 #define HNS3_RING_MAX_PENDING			32768
-#define HNS3_RING_MIN_PENDING			8
+#define HNS3_RING_MIN_PENDING			24
 #define HNS3_RING_BD_MULTIPLE			8
 /* max frame size of mac */
 #define HNS3_MAC_MAX_FRAME			9728
@@ -143,7 +145,7 @@ enum hns3_nic_state {
 #define HNS3_RXD_TSIND_M			(0x7 << HNS3_RXD_TSIND_S)
 #define HNS3_RXD_LKBK_B				15
 #define HNS3_RXD_GRO_SIZE_S			16
-#define HNS3_RXD_GRO_SIZE_M			(0x3ff << HNS3_RXD_GRO_SIZE_S)
+#define HNS3_RXD_GRO_SIZE_M			(0x3fff << HNS3_RXD_GRO_SIZE_S)
 
 #define HNS3_TXD_L3T_S				0
 #define HNS3_TXD_L3T_M				(0x3 << HNS3_TXD_L3T_S)
@@ -184,6 +186,8 @@ enum hns3_nic_state {
 #define HNS3_TXD_MSS_S				0
 #define HNS3_TXD_MSS_M				(0x3fff << HNS3_TXD_MSS_S)
 
+#define HNS3_TX_LAST_SIZE_M                    0xffff
+
 #define HNS3_VECTOR_TX_IRQ			BIT_ULL(0)
 #define HNS3_VECTOR_RX_IRQ			BIT_ULL(1)
 
@@ -202,6 +206,13 @@ enum hns3_nic_state {
 
 #define HNS3_RING_EN_B				0
 
+enum hns3_pkt_l2t_type {
+	HNS3_L2_TYPE_UNICAST,
+	HNS3_L2_TYPE_MULTICAST,
+	HNS3_L2_TYPE_BROADCAST,
+	HNS3_L2_TYPE_INVALID,
+};
+
 enum hns3_pkt_l3t_type {
 	HNS3_L3T_NONE,
 	HNS3_L3T_IPV6,
@@ -365,6 +376,7 @@ struct ring_stats {
 			u64 tx_err_cnt;
 			u64 restart_queue;
 			u64 tx_busy;
+			u64 tx_copy;
 		};
 		struct {
 			u64 rx_pkts;
@@ -372,10 +384,11 @@ struct ring_stats {
 			u64 rx_err_cnt;
 			u64 reuse_pg_cnt;
 			u64 err_pkt_len;
-			u64 non_vld_descs;
 			u64 err_bd_num;
 			u64 l2_err;
 			u64 l3l4_csum_err;
+			u64 rx_multicast;
+			u64 non_reuse_pg;
 		};
 	};
 };
@@ -387,7 +400,6 @@ struct hns3_enet_ring {
 	struct hns3_enet_ring *next;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	struct hnae3_queue *tqp;
-	char ring_name[HNS3_RING_NAME_LEN];
 	struct device *dev; /* will be used for DMA mapping of descriptors */
 
 	/* statistic */
@@ -397,9 +409,6 @@ struct hns3_enet_ring {
 	dma_addr_t desc_dma_addr;
 	u32 buf_size;       /* size for hnae_desc->addr, preset by AE */
 	u16 desc_num;       /* total number of desc */
-	u16 max_desc_num_per_pkt;
-	u16 max_raw_data_sz_per_desc;
-	u16 max_pkt_size;
 	int next_to_use;    /* idx of next spare desc */
 
 	/* idx of lastest sent desc, the ring is empty when equal to
@@ -407,15 +416,11 @@ struct hns3_enet_ring {
 	 */
 	int next_to_clean;
 
-	int pull_len; /* head length for current packet */
+	u32 pull_len; /* head length for current packet */
 	u32 frag_num;
 	unsigned char *va; /* first buffer address for current packet */
 
 	u32 flag;          /* ring attribute */
-	int irq_init_flag;
-
-	int numa_node;
-	cpumask_t affinity_mask;
 
 	int pending_buf;
 	struct sk_buff *skb;
@@ -433,14 +438,6 @@ struct hns3_nic_ring_data {
 	void (*fini_process)(struct hns3_nic_ring_data *);
 };
 
-struct hns3_nic_ops {
-	int (*fill_desc)(struct hns3_enet_ring *ring, void *priv,
-			 int size, int frag_end, enum hns_desc_type type);
-	int (*maybe_stop_tx)(struct sk_buff **out_skb,
-			     int *bnum, struct hns3_enet_ring *ring);
-	void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum);
-};
-
 enum hns3_flow_level_range {
 	HNS3_FLOW_LOW = 0,
 	HNS3_FLOW_MID = 1,
@@ -448,25 +445,6 @@ enum hns3_flow_level_range {
 	HNS3_FLOW_ULTRA = 3,
 };
 
-enum hns3_link_mode_bits {
-	HNS3_LM_FIBRE_BIT = BIT(0),
-	HNS3_LM_AUTONEG_BIT = BIT(1),
-	HNS3_LM_TP_BIT = BIT(2),
-	HNS3_LM_PAUSE_BIT = BIT(3),
-	HNS3_LM_BACKPLANE_BIT = BIT(4),
-	HNS3_LM_10BASET_HALF_BIT = BIT(5),
-	HNS3_LM_10BASET_FULL_BIT = BIT(6),
-	HNS3_LM_100BASET_HALF_BIT = BIT(7),
-	HNS3_LM_100BASET_FULL_BIT = BIT(8),
-	HNS3_LM_1000BASET_FULL_BIT = BIT(9),
-	HNS3_LM_10000BASEKR_FULL_BIT = BIT(10),
-	HNS3_LM_25000BASEKR_FULL_BIT = BIT(11),
-	HNS3_LM_40000BASELR4_FULL_BIT = BIT(12),
-	HNS3_LM_50000BASEKR2_FULL_BIT = BIT(13),
-	HNS3_LM_100000BASEKR4_FULL_BIT = BIT(14),
-	HNS3_LM_COUNT = 15
-};
-
 #define HNS3_INT_GL_MAX			0x1FE0
 #define HNS3_INT_GL_50K			0x0014
 #define HNS3_INT_GL_20K			0x0032
@@ -530,7 +508,6 @@ struct hns3_nic_priv {
 	u32 port_id;
 	struct net_device *netdev;
 	struct device *dev;
-	struct hns3_nic_ops ops;
 
 	/**
 	 * the cb for nic to manage the ring buffer, the first half of the
@@ -553,7 +530,6 @@ struct hns3_nic_priv {
 	struct notifier_block notifier_block;
 	/* Vxlan/Geneve information */
 	struct hns3_udp_tunnel udp_tnl[HNS3_UDP_TNL_MAX];
-	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	struct hns3_enet_coalesce tx_coal;
 	struct hns3_enet_coalesce rx_coal;
 };
@@ -567,21 +543,20 @@ union l3_hdr_info {
 union l4_hdr_info {
 	struct tcphdr *tcp;
 	struct udphdr *udp;
+	struct gre_base_hdr *gre;
 	unsigned char *hdr;
 };
 
-/* the distance between [begin, end) in a ring buffer
- * note: there is a unuse slot between the begin and the end
- */
-static inline int ring_dist(struct hns3_enet_ring *ring, int begin, int end)
-{
-	return (end - begin + ring->desc_num) % ring->desc_num;
-}
-
 static inline int ring_space(struct hns3_enet_ring *ring)
 {
-	return ring->desc_num -
-		ring_dist(ring, ring->next_to_clean, ring->next_to_use) - 1;
+	/* This smp_load_acquire() pairs with smp_store_release() in
+	 * hns3_nic_reclaim_one_desc called by hns3_clean_tx_ring.
+	 */
+	int begin = smp_load_acquire(&ring->next_to_clean);
+	int end = READ_ONCE(ring->next_to_use);
+
+	return ((end >= begin) ? (ring->desc_num - end + begin) :
+			(begin - end)) - 1;
 }
 
 static inline int is_ring_empty(struct hns3_enet_ring *ring)
@@ -626,7 +601,7 @@ static inline bool hns3_nic_resetting(struct net_device *netdev)
 #define hnae3_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
 		(tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG)
 
-#define ring_to_dev(ring) (&(ring)->tqp->handle->pdev->dev)
+#define ring_to_dev(ring) ((ring)->dev)
 
 #define ring_to_dma_dir(ring) (HNAE3_IS_TX_RING(ring) ? \
 	DMA_TO_DEVICE : DMA_FROM_DEVICE)
@@ -635,7 +610,7 @@ static inline bool hns3_nic_resetting(struct net_device *netdev)
 
 #define hnae3_buf_size(_ring) ((_ring)->buf_size)
 #define hnae3_page_order(_ring) (get_order(hnae3_buf_size(_ring)))
-#define hnae3_page_size(_ring) (PAGE_SIZE << hnae3_page_order(_ring))
+#define hnae3_page_size(_ring) (PAGE_SIZE << (u32)hnae3_page_order(_ring))
 
 /* iterator for handling rings in ring group */
 #define hns3_for_each_ring(pos, head) \
@@ -659,6 +634,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv);
 int hns3_uninit_all_ring(struct hns3_nic_priv *priv);
 int hns3_nic_reset_all_ring(struct hnae3_handle *h);
 netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev);
+bool hns3_is_phys_func(struct pci_dev *pdev);
 int hns3_clean_rx_ring(
 		struct hns3_enet_ring *ring, int budget,
 		void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *));
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index e678b6939da3..5bff98a9b0dc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -29,6 +29,7 @@ static const struct hns3_stats hns3_txq_stats[] = {
 	HNS3_TQP_STAT("errors", tx_err_cnt),
 	HNS3_TQP_STAT("wake", restart_queue),
 	HNS3_TQP_STAT("busy", tx_busy),
+	HNS3_TQP_STAT("copy", tx_copy),
 };
 
 #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats)
@@ -43,10 +44,11 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 	HNS3_TQP_STAT("errors", rx_err_cnt),
 	HNS3_TQP_STAT("reuse_pg_cnt", reuse_pg_cnt),
 	HNS3_TQP_STAT("err_pkt_len", err_pkt_len),
-	HNS3_TQP_STAT("non_vld_descs", non_vld_descs),
 	HNS3_TQP_STAT("err_bd_num", err_bd_num),
 	HNS3_TQP_STAT("l2_err", l2_err),
 	HNS3_TQP_STAT("l3l4_csum_err", l3l4_csum_err),
+	HNS3_TQP_STAT("multicast", rx_multicast),
+	HNS3_TQP_STAT("non_reuse_pg", non_reuse_pg),
 };
 
 #define HNS3_RXQ_STATS_COUNT ARRAY_SIZE(hns3_rxq_stats)
@@ -57,6 +59,7 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 #define HNS3_NIC_LB_TEST_PKT_NUM	1
 #define HNS3_NIC_LB_TEST_RING_ID	0
 #define HNS3_NIC_LB_TEST_PACKET_SIZE	128
+#define HNS3_NIC_LB_SETUP_USEC		10000
 
 /* Nic loopback test err  */
 #define HNS3_NIC_LB_TEST_NO_MEM_ERR	1
@@ -114,9 +117,9 @@ static int hns3_lp_up(struct net_device *ndev, enum hnae3_loop loop_mode)
 		return ret;
 
 	ret = hns3_lp_setup(ndev, loop_mode, true);
-	usleep_range(10000, 20000);
+	usleep_range(HNS3_NIC_LB_SETUP_USEC, HNS3_NIC_LB_SETUP_USEC * 2);
 
-	return 0;
+	return ret;
 }
 
 static int hns3_lp_down(struct net_device *ndev, enum hnae3_loop loop_mode)
@@ -129,7 +132,7 @@ static int hns3_lp_down(struct net_device *ndev, enum hnae3_loop loop_mode)
 		return ret;
 	}
 
-	usleep_range(10000, 20000);
+	usleep_range(HNS3_NIC_LB_SETUP_USEC, HNS3_NIC_LB_SETUP_USEC * 2);
 
 	return 0;
 }
@@ -146,6 +149,12 @@ static void hns3_lp_setup_skb(struct sk_buff *skb)
 	packet = skb_put(skb, HNS3_NIC_LB_TEST_PACKET_SIZE);
 
 	memcpy(ethh->h_dest, ndev->dev_addr, ETH_ALEN);
+
+	/* The dst mac addr of loopback packet is the same as the host'
+	 * mac addr, the SSU component may loop back the packet to host
+	 * before the packet reaches mac or serdes, which will defect
+	 * the purpose of mac or serdes selftest.
+	 */
 	ethh->h_dest[5] += 0x1f;
 	eth_zero_addr(ethh->h_source);
 	ethh->h_proto = htons(ETH_P_ARP);
@@ -240,11 +249,13 @@ static int hns3_lp_run_test(struct net_device *ndev, enum hnae3_loop mode)
 
 		skb_get(skb);
 		tx_ret = hns3_nic_net_xmit(skb, ndev);
-		if (tx_ret == NETDEV_TX_OK)
+		if (tx_ret == NETDEV_TX_OK) {
 			good_cnt++;
-		else
+		} else {
+			kfree_skb(skb);
 			netdev_err(ndev, "hns3_lb_run_test xmit failed: %d\n",
 				   tx_ret);
+		}
 	}
 	if (good_cnt != HNS3_NIC_LB_TEST_PKT_NUM) {
 		ret_val = HNS3_NIC_LB_TEST_TX_CNT_ERR;
@@ -324,6 +335,13 @@ static void hns3_self_test(struct net_device *ndev,
 		h->ae_algo->ops->enable_vlan_filter(h, false);
 #endif
 
+	/* Tell firmware to stop mac autoneg before loopback test start,
+	 * otherwise loopback test may be failed when the port is still
+	 * negotiating.
+	 */
+	if (h->ae_algo->ops->halt_autoneg)
+		h->ae_algo->ops->halt_autoneg(h, true);
+
 	set_bit(HNS3_NIC_STATE_TESTING, &priv->state);
 
 	for (i = 0; i < HNS3_SELF_TEST_TYPE_NUM; i++) {
@@ -333,10 +351,10 @@ static void hns3_self_test(struct net_device *ndev,
 			continue;
 
 		data[test_index] = hns3_lp_up(ndev, loop_type);
-		if (!data[test_index]) {
+		if (!data[test_index])
 			data[test_index] = hns3_lp_run_test(ndev, loop_type);
-			hns3_lp_down(ndev, loop_type);
-		}
+
+		hns3_lp_down(ndev, loop_type);
 
 		if (data[test_index])
 			eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -346,6 +364,9 @@ static void hns3_self_test(struct net_device *ndev,
 
 	clear_bit(HNS3_NIC_STATE_TESTING, &priv->state);
 
+	if (h->ae_algo->ops->halt_autoneg)
+		h->ae_algo->ops->halt_autoneg(h, false);
+
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	if (dis_vlan_filter)
 		h->ae_algo->ops->enable_vlan_filter(h, true);
@@ -432,7 +453,7 @@ static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	switch (stringset) {
 	case ETH_SS_STATS:
 		buff = hns3_get_strings_tqps(h, buff);
-		h->ae_algo->ops->get_strings(h, stringset, (u8 *)buff);
+		ops->get_strings(h, stringset, (u8 *)buff);
 		break;
 	case ETH_SS_TEST:
 		ops->get_strings(h, stringset, data);
@@ -482,6 +503,11 @@ static void hns3_get_stats(struct net_device *netdev,
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	u64 *p = data;
 
+	if (hns3_nic_resetting(netdev)) {
+		netdev_err(netdev, "dev resetting, could not get stats\n");
+		return;
+	}
+
 	if (!h->ae_algo->ops->get_stats || !h->ae_algo->ops->update_stats) {
 		netdev_err(netdev, "could not get any statistics\n");
 		return;
@@ -502,6 +528,11 @@ static void hns3_get_drvinfo(struct net_device *netdev,
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
 
+	if (!h->ae_algo->ops->get_fw_version) {
+		netdev_err(netdev, "could not get fw version!\n");
+		return;
+	}
+
 	strncpy(drvinfo->version, hns3_driver_version,
 		sizeof(drvinfo->version));
 	drvinfo->version[sizeof(drvinfo->version) - 1] = '\0';
@@ -522,7 +553,7 @@ static u32 hns3_get_link(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_status)
+	if (h->ae_algo->ops->get_status)
 		return h->ae_algo->ops->get_status(h);
 	else
 		return 0;
@@ -552,7 +583,7 @@ static void hns3_get_pauseparam(struct net_device *netdev,
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_pauseparam)
+	if (h->ae_algo->ops->get_pauseparam)
 		h->ae_algo->ops->get_pauseparam(h, &param->autoneg,
 			&param->rx_pause, &param->tx_pause);
 }
@@ -598,15 +629,13 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops;
+	u8 module_type;
 	u8 media_type;
 	u8 link_stat;
 
-	if (!h->ae_algo || !h->ae_algo->ops)
-		return -EOPNOTSUPP;
-
 	ops = h->ae_algo->ops;
 	if (ops->get_media_type)
-		ops->get_media_type(h, &media_type);
+		ops->get_media_type(h, &media_type, &module_type);
 	else
 		return -EOPNOTSUPP;
 
@@ -616,16 +645,23 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 		hns3_get_ksettings(h, cmd);
 		break;
 	case HNAE3_MEDIA_TYPE_FIBER:
-		cmd->base.port = PORT_FIBRE;
+		if (module_type == HNAE3_MODULE_TYPE_CR)
+			cmd->base.port = PORT_DA;
+		else
+			cmd->base.port = PORT_FIBRE;
+
+		hns3_get_ksettings(h, cmd);
+		break;
+	case HNAE3_MEDIA_TYPE_BACKPLANE:
+		cmd->base.port = PORT_NONE;
 		hns3_get_ksettings(h, cmd);
 		break;
 	case HNAE3_MEDIA_TYPE_COPPER:
-		if (!netdev->phydev)
-			return -EOPNOTSUPP;
-
 		cmd->base.port = PORT_TP;
-		phy_ethtool_ksettings_get(netdev->phydev, cmd);
-
+		if (!netdev->phydev)
+			hns3_get_ksettings(h, cmd);
+		else
+			phy_ethtool_ksettings_get(netdev->phydev, cmd);
 		break;
 	default:
 
@@ -645,22 +681,86 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+static int hns3_check_ksettings_param(struct net_device *netdev,
+				      const struct ethtool_link_ksettings *cmd)
+{
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	u8 module_type = HNAE3_MODULE_TYPE_UNKNOWN;
+	u8 media_type = HNAE3_MEDIA_TYPE_UNKNOWN;
+	u8 autoneg;
+	u32 speed;
+	u8 duplex;
+	int ret;
+
+	if (ops->get_ksettings_an_result) {
+		ops->get_ksettings_an_result(handle, &autoneg, &speed, &duplex);
+		if (cmd->base.autoneg == autoneg && cmd->base.speed == speed &&
+		    cmd->base.duplex == duplex)
+			return 0;
+	}
+
+	if (ops->get_media_type)
+		ops->get_media_type(handle, &media_type, &module_type);
+
+	if (cmd->base.duplex != DUPLEX_FULL &&
+	    media_type != HNAE3_MEDIA_TYPE_COPPER) {
+		netdev_err(netdev,
+			   "only copper port supports half duplex!");
+		return -EINVAL;
+	}
+
+	if (ops->check_port_speed) {
+		ret = ops->check_port_speed(handle, cmd->base.speed);
+		if (ret) {
+			netdev_err(netdev, "unsupported speed\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int hns3_set_link_ksettings(struct net_device *netdev,
 				   const struct ethtool_link_ksettings *cmd)
 {
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	int ret = 0;
+
+	/* Chip don't support this mode. */
+	if (cmd->base.speed == SPEED_1000 && cmd->base.duplex == DUPLEX_HALF)
+		return -EINVAL;
+
 	/* Only support ksettings_set for netdev with phy attached for now */
 	if (netdev->phydev)
 		return phy_ethtool_ksettings_set(netdev->phydev, cmd);
 
-	return -EOPNOTSUPP;
+	if (handle->pdev->revision == 0x20)
+		return -EOPNOTSUPP;
+
+	ret = hns3_check_ksettings_param(netdev, cmd);
+	if (ret)
+		return ret;
+
+	if (ops->set_autoneg) {
+		ret = ops->set_autoneg(handle, cmd->base.autoneg);
+		if (ret)
+			return ret;
+	}
+
+	if (ops->cfg_mac_speed_dup_h)
+		ret = ops->cfg_mac_speed_dup_h(handle, cmd->base.speed,
+					       cmd->base.duplex);
+
+	return ret;
 }
 
 static u32 hns3_get_rss_key_size(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops ||
-	    !h->ae_algo->ops->get_rss_key_size)
+	if (!h->ae_algo->ops->get_rss_key_size)
 		return 0;
 
 	return h->ae_algo->ops->get_rss_key_size(h);
@@ -670,8 +770,7 @@ static u32 hns3_get_rss_indir_size(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops ||
-	    !h->ae_algo->ops->get_rss_indir_size)
+	if (!h->ae_algo->ops->get_rss_indir_size)
 		return 0;
 
 	return h->ae_algo->ops->get_rss_indir_size(h);
@@ -682,7 +781,7 @@ static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key,
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss)
+	if (!h->ae_algo->ops->get_rss)
 		return -EOPNOTSUPP;
 
 	return h->ae_algo->ops->get_rss(h, indir, key, hfunc);
@@ -693,7 +792,7 @@ static int hns3_set_rss(struct net_device *netdev, const u32 *indir,
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss)
+	if (!h->ae_algo->ops->set_rss)
 		return -EOPNOTSUPP;
 
 	if ((h->pdev->revision == 0x20 &&
@@ -718,9 +817,6 @@ static int hns3_get_rxnfc(struct net_device *netdev,
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops)
-		return -EOPNOTSUPP;
-
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
 		cmd->data = h->kinfo.num_tqps;
@@ -748,15 +844,19 @@ static int hns3_get_rxnfc(struct net_device *netdev,
 }
 
 static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv,
-				       u32 new_desc_num)
+				       u32 tx_desc_num, u32 rx_desc_num)
 {
 	struct hnae3_handle *h = priv->ae_handle;
 	int i;
 
-	h->kinfo.num_desc = new_desc_num;
+	h->kinfo.num_tx_desc = tx_desc_num;
+	h->kinfo.num_rx_desc = rx_desc_num;
 
-	for (i = 0; i < h->kinfo.num_tqps * 2; i++)
-		priv->ring_data[i].ring->desc_num = new_desc_num;
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
+		priv->ring_data[i].ring->desc_num = tx_desc_num;
+		priv->ring_data[i + h->kinfo.num_tqps].ring->desc_num =
+			rx_desc_num;
+	}
 
 	return hns3_init_all_ring(priv);
 }
@@ -767,7 +867,9 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
 	bool if_running = netif_running(ndev);
-	u32 old_desc_num, new_desc_num;
+	u32 old_tx_desc_num, new_tx_desc_num;
+	u32 old_rx_desc_num, new_rx_desc_num;
+	int queue_num = h->kinfo.num_tqps;
 	int ret;
 
 	if (hns3_nic_resetting(ndev))
@@ -776,43 +878,41 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	if (param->rx_mini_pending || param->rx_jumbo_pending)
 		return -EINVAL;
 
-	if (param->tx_pending != param->rx_pending) {
-		netdev_err(ndev,
-			   "Descriptors of tx and rx must be equal");
-		return -EINVAL;
-	}
-
 	if (param->tx_pending > HNS3_RING_MAX_PENDING ||
-	    param->tx_pending < HNS3_RING_MIN_PENDING) {
-		netdev_err(ndev,
-			   "Descriptors requested (Tx/Rx: %d) out of range [%d-%d]\n",
-			   param->tx_pending, HNS3_RING_MIN_PENDING,
-			   HNS3_RING_MAX_PENDING);
+	    param->tx_pending < HNS3_RING_MIN_PENDING ||
+	    param->rx_pending > HNS3_RING_MAX_PENDING ||
+	    param->rx_pending < HNS3_RING_MIN_PENDING) {
+		netdev_err(ndev, "Queue depth out of range [%d-%d]\n",
+			   HNS3_RING_MIN_PENDING, HNS3_RING_MAX_PENDING);
 		return -EINVAL;
 	}
 
-	new_desc_num = param->tx_pending;
-
 	/* Hardware requires that its descriptors must be multiple of eight */
-	new_desc_num = ALIGN(new_desc_num, HNS3_RING_BD_MULTIPLE);
-	old_desc_num = h->kinfo.num_desc;
-	if (old_desc_num == new_desc_num)
+	new_tx_desc_num = ALIGN(param->tx_pending, HNS3_RING_BD_MULTIPLE);
+	new_rx_desc_num = ALIGN(param->rx_pending, HNS3_RING_BD_MULTIPLE);
+	old_tx_desc_num = priv->ring_data[0].ring->desc_num;
+	old_rx_desc_num = priv->ring_data[queue_num].ring->desc_num;
+	if (old_tx_desc_num == new_tx_desc_num &&
+	    old_rx_desc_num == new_rx_desc_num)
 		return 0;
 
 	netdev_info(ndev,
-		    "Changing descriptor count from %d to %d.\n",
-		    old_desc_num, new_desc_num);
+		    "Changing Tx/Rx ring depth from %d/%d to %d/%d\n",
+		    old_tx_desc_num, old_rx_desc_num,
+		    new_tx_desc_num, new_rx_desc_num);
 
 	if (if_running)
-		dev_close(ndev);
+		ndev->netdev_ops->ndo_stop(ndev);
 
 	ret = hns3_uninit_all_ring(priv);
 	if (ret)
 		return ret;
 
-	ret = hns3_change_all_ring_bd_num(priv, new_desc_num);
+	ret = hns3_change_all_ring_bd_num(priv, new_tx_desc_num,
+					  new_rx_desc_num);
 	if (ret) {
-		ret = hns3_change_all_ring_bd_num(priv, old_desc_num);
+		ret = hns3_change_all_ring_bd_num(priv, old_tx_desc_num,
+						  old_rx_desc_num);
 		if (ret) {
 			netdev_err(ndev,
 				   "Revert to old bd num fail, ret=%d.\n", ret);
@@ -821,7 +921,7 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	}
 
 	if (if_running)
-		ret = dev_open(ndev, NULL);
+		ret = ndev->netdev_ops->ndo_open(ndev);
 
 	return ret;
 }
@@ -830,9 +930,6 @@ static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops)
-		return -EOPNOTSUPP;
-
 	switch (cmd->cmd) {
 	case ETHTOOL_SRXFH:
 		if (h->ae_algo->ops->set_rss_tuple)
@@ -853,19 +950,36 @@ static int hns3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 
 static int hns3_nway_reset(struct net_device *netdev)
 {
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
 	struct phy_device *phy = netdev->phydev;
+	int autoneg;
 
 	if (!netif_running(netdev))
 		return 0;
 
-	/* Only support nway_reset for netdev with phy attached for now */
-	if (!phy)
+	if (hns3_nic_resetting(netdev)) {
+		netdev_err(netdev, "dev resetting!");
+		return -EBUSY;
+	}
+
+	if (!ops->get_autoneg || !ops->restart_autoneg)
 		return -EOPNOTSUPP;
 
-	if (phy->autoneg != AUTONEG_ENABLE)
+	autoneg = ops->get_autoneg(handle);
+	if (autoneg != AUTONEG_ENABLE) {
+		netdev_err(netdev,
+			   "Autoneg is off, don't support to restart it\n");
 		return -EINVAL;
+	}
+
+	if (phy)
+		return genphy_restart_aneg(phy);
+
+	if (handle->pdev->revision == 0x20)
+		return -EOPNOTSUPP;
 
-	return genphy_restart_aneg(phy);
+	return ops->restart_autoneg(handle);
 }
 
 static void hns3_get_channels(struct net_device *netdev,
@@ -1091,12 +1205,101 @@ static int hns3_set_phys_id(struct net_device *netdev,
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 
-	if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_led_id)
+	if (!h->ae_algo->ops->set_led_id)
 		return -EOPNOTSUPP;
 
 	return h->ae_algo->ops->set_led_id(h, state);
 }
 
+static u32 hns3_get_msglevel(struct net_device *netdev)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	return h->msg_enable;
+}
+
+static void hns3_set_msglevel(struct net_device *netdev, u32 msg_level)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	h->msg_enable = msg_level;
+}
+
+/* Translate local fec value into ethtool value. */
+static unsigned int loc_to_eth_fec(u8 loc_fec)
+{
+	u32 eth_fec = 0;
+
+	if (loc_fec & BIT(HNAE3_FEC_AUTO))
+		eth_fec |= ETHTOOL_FEC_AUTO;
+	if (loc_fec & BIT(HNAE3_FEC_RS))
+		eth_fec |= ETHTOOL_FEC_RS;
+	if (loc_fec & BIT(HNAE3_FEC_BASER))
+		eth_fec |= ETHTOOL_FEC_BASER;
+
+	/* if nothing is set, then FEC is off */
+	if (!eth_fec)
+		eth_fec = ETHTOOL_FEC_OFF;
+
+	return eth_fec;
+}
+
+/* Translate ethtool fec value into local value. */
+static unsigned int eth_to_loc_fec(unsigned int eth_fec)
+{
+	u32 loc_fec = 0;
+
+	if (eth_fec & ETHTOOL_FEC_OFF)
+		return loc_fec;
+
+	if (eth_fec & ETHTOOL_FEC_AUTO)
+		loc_fec |= BIT(HNAE3_FEC_AUTO);
+	if (eth_fec & ETHTOOL_FEC_RS)
+		loc_fec |= BIT(HNAE3_FEC_RS);
+	if (eth_fec & ETHTOOL_FEC_BASER)
+		loc_fec |= BIT(HNAE3_FEC_BASER);
+
+	return loc_fec;
+}
+
+static int hns3_get_fecparam(struct net_device *netdev,
+			     struct ethtool_fecparam *fec)
+{
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	u8 fec_ability;
+	u8 fec_mode;
+
+	if (handle->pdev->revision == 0x20)
+		return -EOPNOTSUPP;
+
+	if (!ops->get_fec)
+		return -EOPNOTSUPP;
+
+	ops->get_fec(handle, &fec_ability, &fec_mode);
+
+	fec->fec = loc_to_eth_fec(fec_ability);
+	fec->active_fec = loc_to_eth_fec(fec_mode);
+
+	return 0;
+}
+
+static int hns3_set_fecparam(struct net_device *netdev,
+			     struct ethtool_fecparam *fec)
+{
+	struct hnae3_handle *handle = hns3_get_handle(netdev);
+	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	u32 fec_mode;
+
+	if (handle->pdev->revision == 0x20)
+		return -EOPNOTSUPP;
+
+	if (!ops->set_fec)
+		return -EOPNOTSUPP;
+	fec_mode = eth_to_loc_fec(fec->fec);
+	return ops->set_fec(handle, fec_mode);
+}
+
 static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.get_drvinfo = hns3_get_drvinfo,
 	.get_ringparam = hns3_get_ringparam,
@@ -1114,7 +1317,11 @@ static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.get_channels = hns3_get_channels,
 	.get_coalesce = hns3_get_coalesce,
 	.set_coalesce = hns3_set_coalesce,
+	.get_regs_len = hns3_get_regs_len,
+	.get_regs = hns3_get_regs,
 	.get_link = hns3_get_link,
+	.get_msglevel = hns3_get_msglevel,
+	.set_msglevel = hns3_set_msglevel,
 };
 
 static const struct ethtool_ops hns3_ethtool_ops = {
@@ -1144,6 +1351,10 @@ static const struct ethtool_ops hns3_ethtool_ops = {
 	.get_regs_len = hns3_get_regs_len,
 	.get_regs = hns3_get_regs,
 	.set_phys_id = hns3_set_phys_id,
+	.get_msglevel = hns3_get_msglevel,
+	.set_msglevel = hns3_set_msglevel,
+	.get_fecparam = hns3_get_fecparam,
+	.set_fecparam = hns3_set_fecparam,
 };
 
 void hns3_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index fffe8c1c45d3..0fb61d440d3b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the HISILICON network device drivers.
 #
 
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
 hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index e483a6e730e6..22f6acd45d9a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -110,8 +110,7 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG,
 				upper_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG,
-				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
-				HCLGE_NIC_CMQ_ENABLE);
+				ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S);
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0);
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
 	} else {
@@ -120,8 +119,7 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG,
 				upper_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG,
-				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
-				HCLGE_NIC_CMQ_ENABLE);
+				ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S);
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0);
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
 	}
@@ -170,8 +168,16 @@ static bool hclge_is_special_opcode(u16 opcode)
 	/* these commands have several descriptors,
 	 * and use the first one to save opcode and return value
 	 */
-	u16 spec_opcode[3] = {HCLGE_OPC_STATS_64_BIT,
-		HCLGE_OPC_STATS_32_BIT, HCLGE_OPC_STATS_MAC};
+	u16 spec_opcode[] = {HCLGE_OPC_STATS_64_BIT,
+			     HCLGE_OPC_STATS_32_BIT,
+			     HCLGE_OPC_STATS_MAC,
+			     HCLGE_OPC_STATS_MAC_ALL,
+			     HCLGE_OPC_QUERY_32_BIT_REG,
+			     HCLGE_OPC_QUERY_64_BIT_REG,
+			     HCLGE_QUERY_CLEAR_MPF_RAS_INT,
+			     HCLGE_QUERY_CLEAR_PF_RAS_INT,
+			     HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT,
+			     HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT};
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) {
@@ -182,6 +188,61 @@ static bool hclge_is_special_opcode(u16 opcode)
 	return false;
 }
 
+static int hclge_cmd_convert_err_code(u16 desc_ret)
+{
+	switch (desc_ret) {
+	case HCLGE_CMD_EXEC_SUCCESS:
+		return 0;
+	case HCLGE_CMD_NO_AUTH:
+		return -EPERM;
+	case HCLGE_CMD_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case HCLGE_CMD_QUEUE_FULL:
+		return -EXFULL;
+	case HCLGE_CMD_NEXT_ERR:
+		return -ENOSR;
+	case HCLGE_CMD_UNEXE_ERR:
+		return -ENOTBLK;
+	case HCLGE_CMD_PARA_ERR:
+		return -EINVAL;
+	case HCLGE_CMD_RESULT_ERR:
+		return -ERANGE;
+	case HCLGE_CMD_TIMEOUT:
+		return -ETIME;
+	case HCLGE_CMD_HILINK_ERR:
+		return -ENOLINK;
+	case HCLGE_CMD_QUEUE_ILLEGAL:
+		return -ENXIO;
+	case HCLGE_CMD_INVALID:
+		return -EBADR;
+	default:
+		return -EIO;
+	}
+}
+
+static int hclge_cmd_check_retval(struct hclge_hw *hw, struct hclge_desc *desc,
+				  int num, int ntc)
+{
+	u16 opcode, desc_ret;
+	int handle;
+
+	opcode = le16_to_cpu(desc[0].opcode);
+	for (handle = 0; handle < num; handle++) {
+		desc[handle] = hw->cmq.csq.desc[ntc];
+		ntc++;
+		if (ntc >= hw->cmq.csq.desc_num)
+			ntc = 0;
+	}
+	if (likely(!hclge_is_special_opcode(opcode)))
+		desc_ret = le16_to_cpu(desc[num - 1].retval);
+	else
+		desc_ret = le16_to_cpu(desc[0].retval);
+
+	hw->cmq.last_status = desc_ret;
+
+	return hclge_cmd_convert_err_code(desc_ret);
+}
+
 /**
  * hclge_cmd_send - send command to command queue
  * @hw: pointer to the hw struct
@@ -194,18 +255,26 @@ static bool hclge_is_special_opcode(u16 opcode)
 int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 {
 	struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
+	struct hclge_cmq_ring *csq = &hw->cmq.csq;
 	struct hclge_desc *desc_to_use;
 	bool complete = false;
 	u32 timeout = 0;
 	int handle = 0;
 	int retval = 0;
-	u16 opcode, desc_ret;
 	int ntc;
 
 	spin_lock_bh(&hw->cmq.csq.lock);
 
-	if (num > hclge_ring_space(&hw->cmq.csq) ||
-	    test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) {
+	if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) {
+		spin_unlock_bh(&hw->cmq.csq.lock);
+		return -EBUSY;
+	}
+
+	if (num > hclge_ring_space(&hw->cmq.csq)) {
+		/* If CMDQ ring is full, SW HEAD and HW HEAD may be different,
+		 * need update the SW HEAD pointer csq->next_to_clean
+		 */
+		csq->next_to_clean = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG);
 		spin_unlock_bh(&hw->cmq.csq.lock);
 		return -EBUSY;
 	}
@@ -215,12 +284,11 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	 * which will be use for hardware to write back
 	 */
 	ntc = hw->cmq.csq.next_to_use;
-	opcode = le16_to_cpu(desc[0].opcode);
 	while (handle < num) {
 		desc_to_use = &hw->cmq.csq.desc[hw->cmq.csq.next_to_use];
 		*desc_to_use = desc[handle];
 		(hw->cmq.csq.next_to_use)++;
-		if (hw->cmq.csq.next_to_use == hw->cmq.csq.desc_num)
+		if (hw->cmq.csq.next_to_use >= hw->cmq.csq.desc_num)
 			hw->cmq.csq.next_to_use = 0;
 		handle++;
 	}
@@ -244,29 +312,9 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	}
 
 	if (!complete) {
-		retval = -EAGAIN;
+		retval = -EBADE;
 	} else {
-		handle = 0;
-		while (handle < num) {
-			/* Get the result of hardware write back */
-			desc_to_use = &hw->cmq.csq.desc[ntc];
-			desc[handle] = *desc_to_use;
-
-			if (likely(!hclge_is_special_opcode(opcode)))
-				desc_ret = le16_to_cpu(desc[handle].retval);
-			else
-				desc_ret = le16_to_cpu(desc[0].retval);
-
-			if (desc_ret == HCLGE_CMD_EXEC_SUCCESS)
-				retval = 0;
-			else
-				retval = -EIO;
-			hw->cmq.last_status = desc_ret;
-			ntc++;
-			handle++;
-			if (ntc == hw->cmq.csq.desc_num)
-				ntc = 0;
-		}
+		retval = hclge_cmd_check_retval(hw, desc, num, ntc);
 	}
 
 	/* Clean the command send queue */
@@ -341,7 +389,7 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	int ret;
 
 	spin_lock_bh(&hdev->hw.cmq.csq.lock);
-	spin_lock_bh(&hdev->hw.cmq.crq.lock);
+	spin_lock(&hdev->hw.cmq.crq.lock);
 
 	hdev->hw.cmq.csq.next_to_clean = 0;
 	hdev->hw.cmq.csq.next_to_use = 0;
@@ -350,7 +398,7 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 
 	hclge_cmd_init_regs(&hdev->hw);
 
-	spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+	spin_unlock(&hdev->hw.cmq.crq.lock);
 	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 
 	clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
@@ -359,21 +407,40 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	 * reset may happen when lower level reset is being processed.
 	 */
 	if ((hclge_is_reset_pending(hdev))) {
-		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto err_cmd_init;
 	}
 
 	ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"firmware version query failed %d\n", ret);
-		return ret;
+		goto err_cmd_init;
 	}
 	hdev->fw_version = version;
 
 	dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
 
 	return 0;
+
+err_cmd_init:
+	set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+
+	return ret;
+}
+
+static void hclge_cmd_uninit_regs(struct hclge_hw *hw)
+{
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
 }
 
 static void hclge_destroy_queue(struct hclge_cmq_ring *ring)
@@ -383,8 +450,20 @@ static void hclge_destroy_queue(struct hclge_cmq_ring *ring)
 	spin_unlock(&ring->lock);
 }
 
-void hclge_destroy_cmd_queue(struct hclge_hw *hw)
+static void hclge_destroy_cmd_queue(struct hclge_hw *hw)
 {
 	hclge_destroy_queue(&hw->cmq.csq);
 	hclge_destroy_queue(&hw->cmq.crq);
 }
+
+void hclge_cmd_uninit(struct hclge_dev *hdev)
+{
+	spin_lock_bh(&hdev->hw.cmq.csq.lock);
+	spin_lock(&hdev->hw.cmq.crq.lock);
+	set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+	hclge_cmd_uninit_regs(&hdev->hw);
+	spin_unlock(&hdev->hw.cmq.crq.lock);
+	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
+
+	hclge_destroy_cmd_queue(&hdev->hw);
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index f23042b24c09..96840d8f3e24 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -39,8 +39,16 @@ struct hclge_cmq_ring {
 enum hclge_cmd_return_status {
 	HCLGE_CMD_EXEC_SUCCESS	= 0,
 	HCLGE_CMD_NO_AUTH	= 1,
-	HCLGE_CMD_NOT_EXEC	= 2,
+	HCLGE_CMD_NOT_SUPPORTED	= 2,
 	HCLGE_CMD_QUEUE_FULL	= 3,
+	HCLGE_CMD_NEXT_ERR	= 4,
+	HCLGE_CMD_UNEXE_ERR	= 5,
+	HCLGE_CMD_PARA_ERR	= 6,
+	HCLGE_CMD_RESULT_ERR	= 7,
+	HCLGE_CMD_TIMEOUT	= 8,
+	HCLGE_CMD_HILINK_ERR	= 9,
+	HCLGE_CMD_QUEUE_ILLEGAL	= 10,
+	HCLGE_CMD_INVALID	= 11,
 };
 
 enum hclge_cmd_status {
@@ -82,6 +90,8 @@ enum hclge_opcode_type {
 	HCLGE_OPC_STATS_64_BIT		= 0x0030,
 	HCLGE_OPC_STATS_32_BIT		= 0x0031,
 	HCLGE_OPC_STATS_MAC		= 0x0032,
+	HCLGE_OPC_QUERY_MAC_REG_NUM	= 0x0033,
+	HCLGE_OPC_STATS_MAC_ALL		= 0x0034,
 
 	HCLGE_OPC_QUERY_REG_NUM		= 0x0040,
 	HCLGE_OPC_QUERY_32_BIT_REG	= 0x0041,
@@ -107,7 +117,11 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QUERY_LINK_STATUS	= 0x0307,
 	HCLGE_OPC_CONFIG_MAX_FRM_SIZE	= 0x0308,
 	HCLGE_OPC_CONFIG_SPEED_DUP	= 0x0309,
+	HCLGE_OPC_QUERY_MAC_TNL_INT	= 0x0310,
+	HCLGE_OPC_MAC_TNL_INT_EN	= 0x0311,
+	HCLGE_OPC_CLEAR_MAC_TNL_INT	= 0x0312,
 	HCLGE_OPC_SERDES_LOOPBACK       = 0x0315,
+	HCLGE_OPC_CONFIG_FEC_MODE	= 0x031A,
 
 	/* PFC/Pause commands */
 	HCLGE_OPC_CFG_MAC_PAUSE_EN      = 0x0701,
@@ -174,6 +188,9 @@ enum hclge_opcode_type {
 	HCLGE_OPC_CFG_COM_TQP_QUEUE	= 0x0B20,
 	HCLGE_OPC_RESET_TQP_QUEUE	= 0x0B22,
 
+	/* PPU commands */
+	HCLGE_OPC_PPU_PF_OTHER_INT_DFX	= 0x0B4A,
+
 	/* TSO command */
 	HCLGE_OPC_TSO_GENERIC_CONFIG	= 0x0C01,
 	HCLGE_OPC_GRO_GENERIC_CONFIG    = 0x0C10,
@@ -235,8 +252,14 @@ enum hclge_opcode_type {
 	/* Led command */
 	HCLGE_OPC_LED_STATUS_CFG	= 0xB000,
 
+	/* NCL config command */
+	HCLGE_OPC_QUERY_NCL_CONFIG	= 0x7011,
+	/* M7 stats command */
+	HCLGE_OPC_M7_STATS_BD		= 0x7012,
+	HCLGE_OPC_M7_STATS_INFO		= 0x7013,
+
 	/* SFP command */
-	HCLGE_OPC_SFP_GET_SPEED		= 0x7104,
+	HCLGE_OPC_GET_SFP_INFO		= 0x7104,
 
 	/* Error INT commands */
 	HCLGE_MAC_COMMON_INT_EN		= 0x030E,
@@ -256,6 +279,8 @@ enum hclge_opcode_type {
 	HCLGE_CONFIG_ROCEE_RAS_INT_EN	= 0x1580,
 	HCLGE_QUERY_CLEAR_ROCEE_RAS_INT = 0x1581,
 	HCLGE_ROCEE_PF_RAS_INT_CMD	= 0x1584,
+	HCLGE_QUERY_ROCEE_ECC_RAS_INFO_CMD	= 0x1585,
+	HCLGE_QUERY_ROCEE_AXI_RAS_INFO_CMD	= 0x1586,
 	HCLGE_IGU_EGU_TNL_INT_EN	= 0x1803,
 	HCLGE_IGU_COMMON_INT_EN		= 0x1806,
 	HCLGE_TM_QCN_MEM_INT_CFG	= 0x1A14,
@@ -310,16 +335,16 @@ struct hclge_ctrl_vector_chain_cmd {
 	u8 rsv;
 };
 
-#define HCLGE_TC_NUM		8
+#define HCLGE_MAX_TC_NUM		8
 #define HCLGE_TC0_PRI_BUF_EN_B	15 /* Bit 15 indicate enable or not */
 #define HCLGE_BUF_UNIT_S	7  /* Buf size is united by 128 bytes */
 struct hclge_tx_buff_alloc_cmd {
-	__le16 tx_pkt_buff[HCLGE_TC_NUM];
+	__le16 tx_pkt_buff[HCLGE_MAX_TC_NUM];
 	u8 tx_buff_rsv[8];
 };
 
 struct hclge_rx_priv_buff_cmd {
-	__le16 buf_num[HCLGE_TC_NUM];
+	__le16 buf_num[HCLGE_MAX_TC_NUM];
 	__le16 shared_buf;
 	u8 rsv[6];
 };
@@ -365,7 +390,6 @@ struct hclge_priv_buf {
 	u32 enable;	/* Enable TC private buffer or not */
 };
 
-#define HCLGE_MAX_TC_NUM	8
 struct hclge_shared_buf {
 	struct hclge_waterline self;
 	struct hclge_tc_thrd tc_thrd[HCLGE_MAX_TC_NUM];
@@ -592,9 +616,30 @@ struct hclge_config_auto_neg_cmd {
 	u8      rsv[20];
 };
 
-struct hclge_sfp_speed_cmd {
-	__le32	sfp_speed;
-	u32	rsv[5];
+struct hclge_sfp_info_cmd {
+	__le32 speed;
+	u8 query_type; /* 0: sfp speed, 1: active speed */
+	u8 active_fec;
+	u8 autoneg; /* autoneg state */
+	u8 autoneg_ability; /* whether support autoneg */
+	__le32 speed_ability; /* speed ability for current media */
+	__le32 module_type;
+	u8 rsv[8];
+};
+
+#define HCLGE_MAC_CFG_FEC_AUTO_EN_B	0
+#define HCLGE_MAC_CFG_FEC_MODE_S	1
+#define HCLGE_MAC_CFG_FEC_MODE_M	GENMASK(3, 1)
+#define HCLGE_MAC_CFG_FEC_SET_DEF_B	0
+#define HCLGE_MAC_CFG_FEC_CLR_DEF_B	1
+
+#define HCLGE_MAC_FEC_OFF		0
+#define HCLGE_MAC_FEC_BASER		1
+#define HCLGE_MAC_FEC_RS		2
+struct hclge_config_fec_cmd {
+	u8 fec_mode;
+	u8 default_config;
+	u8 rsv[22];
 };
 
 #define HCLGE_MAC_UPLINK_PORT		0x100
@@ -612,6 +657,11 @@ enum hclge_mac_vlan_tbl_opcode {
 	HCLGE_MAC_VLAN_LKUP,    /* Lookup a entry through mac_vlan key */
 };
 
+enum hclge_mac_vlan_add_resp_code {
+	HCLGE_ADD_UC_OVERFLOW = 2,	/* ADD failed for UC overflow */
+	HCLGE_ADD_MC_OVERFLOW,		/* ADD failed for MC overflow */
+};
+
 #define HCLGE_MAC_VLAN_BIT0_EN_B	0
 #define HCLGE_MAC_VLAN_BIT1_EN_B	1
 #define HCLGE_MAC_EPORT_SW_EN_B		12
@@ -645,7 +695,6 @@ struct hclge_umv_spc_alc_cmd {
 #define HCLGE_MAC_MGR_MASK_VLAN_B		BIT(0)
 #define HCLGE_MAC_MGR_MASK_MAC_B		BIT(1)
 #define HCLGE_MAC_MGR_MASK_ETHERTYPE_B		BIT(2)
-#define HCLGE_MAC_ETHERTYPE_LLDP		0x88cc
 
 struct hclge_mac_mgr_tbl_entry_cmd {
 	u8      flags;
@@ -692,7 +741,9 @@ struct hclge_mac_vlan_remove_cmd {
 struct hclge_vlan_filter_ctrl_cmd {
 	u8 vlan_type;
 	u8 vlan_fe;
-	u8 rsv[22];
+	u8 rsv1[2];
+	u8 vf_id;
+	u8 rsv2[19];
 };
 
 struct hclge_vlan_filter_pf_cfg_cmd {
@@ -841,7 +892,7 @@ struct hclge_serdes_lb_cmd {
 #define HCLGE_TOTAL_PKT_BUF		0x108000 /* 1.03125M bytes */
 #define HCLGE_DEFAULT_DV		0xA000	 /* 40k byte */
 #define HCLGE_DEFAULT_NON_DCB_DV	0x7800	/* 30K byte */
-#define HCLGE_NON_DCB_ADDITIONAL_BUF	0x200	/* 512 byte */
+#define HCLGE_NON_DCB_ADDITIONAL_BUF	0x1400	/* 5120 byte */
 
 #define HCLGE_TYPE_CRQ			0
 #define HCLGE_TYPE_CSQ			1
@@ -939,6 +990,25 @@ struct hclge_fd_ad_config_cmd {
 	u8 rsv2[8];
 };
 
+struct hclge_get_m7_bd_cmd {
+	__le32 bd_num;
+	u8 rsv[20];
+};
+
+struct hclge_query_ppu_pf_other_int_dfx_cmd {
+	__le16 over_8bd_no_fe_qid;
+	__le16 over_8bd_no_fe_vf_id;
+	__le16 tso_mss_cmp_min_err_qid;
+	__le16 tso_mss_cmp_min_err_vf_id;
+	__le16 tso_mss_cmp_max_err_qid;
+	__le16 tso_mss_cmp_max_err_vf_id;
+	__le16 tx_rd_fbd_poison_qid;
+	__le16 tx_rd_fbd_poison_vf_id;
+	__le16 rx_rd_fbd_poison_qid;
+	__le16 rx_rd_fbd_poison_vf_id;
+	u8 rsv[4];
+};
+
 int hclge_cmd_init(struct hclge_dev *hdev);
 static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value)
 {
@@ -974,6 +1044,6 @@ enum hclge_cmd_status hclge_cmd_mdio_write(struct hclge_hw *hw,
 enum hclge_cmd_status hclge_cmd_mdio_read(struct hclge_hw *hw,
 					  struct hclge_desc *desc);
 
-void hclge_destroy_cmd_queue(struct hclge_hw *hw);
+void hclge_cmd_uninit(struct hclge_dev *hdev);
 int hclge_cmd_queue_init(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index f6323b2501dc..bac4ce13f6ae 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -93,13 +93,11 @@ static int hclge_dcb_common_validate(struct hclge_dev *hdev, u8 num_tc,
 		}
 	}
 
-	for (i = 0; i < hdev->num_alloc_vport; i++) {
-		if (num_tc > hdev->vport[i].alloc_tqps) {
-			dev_err(&hdev->pdev->dev,
-				"allocated tqp(%u) checking failed, %u > tqp(%u)\n",
-				i, num_tc, hdev->vport[i].alloc_tqps);
-			return -EINVAL;
-		}
+	if (num_tc > hdev->vport[0].alloc_tqps) {
+		dev_err(&hdev->pdev->dev,
+			"allocated tqp checking failed, %u > tqp(%u)\n",
+			num_tc, hdev->vport[0].alloc_tqps);
+		return -EINVAL;
 	}
 
 	return 0;
@@ -156,21 +154,15 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
 	return 0;
 }
 
-static int hclge_map_update(struct hnae3_handle *h)
+static int hclge_map_update(struct hclge_dev *hdev)
 {
-	struct hclge_vport *vport = hclge_get_vport(h);
-	struct hclge_dev *hdev = vport->back;
 	int ret;
 
-	ret = hclge_tm_map_cfg(hdev);
+	ret = hclge_tm_schd_setup_hw(hdev);
 	if (ret)
 		return ret;
 
-	ret = hclge_tm_schd_mode_hw(hdev);
-	if (ret)
-		return ret;
-
-	ret = hclge_pause_setup_hw(hdev);
+	ret = hclge_pause_setup_hw(hdev, false);
 	if (ret)
 		return ret;
 
@@ -222,19 +214,51 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 	if (ret)
 		return ret;
 
+	if (map_changed) {
+		ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+		if (ret)
+			return ret;
+
+		ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+		if (ret)
+			return ret;
+	}
+
 	hclge_tm_schd_info_update(hdev, num_tc);
 
 	ret = hclge_ieee_ets_to_tm_info(hdev, ets);
 	if (ret)
-		return ret;
+		goto err_out;
 
 	if (map_changed) {
+		ret = hclge_map_update(hdev);
+		if (ret)
+			goto err_out;
+
 		ret = hclge_client_setup_tc(hdev);
 		if (ret)
+			goto err_out;
+
+		ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+		if (ret)
+			return ret;
+
+		ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+		if (ret)
 			return ret;
 	}
 
 	return hclge_tm_dwrr_cfg(hdev);
+
+err_out:
+	if (!map_changed)
+		return ret;
+
+	if (hclge_notify_client(hdev, HNAE3_INIT_CLIENT))
+		return ret;
+
+	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	return ret;
 }
 
 static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
@@ -283,6 +307,9 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
 		return -EINVAL;
 
+	if (pfc->pfc_en == hdev->tm_info.pfc_en)
+		return 0;
+
 	prio_tc = hdev->tm_info.prio_tc;
 	pfc_map = 0;
 
@@ -295,12 +322,12 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 		}
 	}
 
-	if (pfc_map == hdev->tm_info.hw_pfc_map)
-		return 0;
-
 	hdev->tm_info.hw_pfc_map = pfc_map;
+	hdev->tm_info.pfc_en = pfc->pfc_en;
+
+	hclge_tm_pfc_info_update(hdev);
 
-	return hclge_pause_setup_hw(hdev);
+	return hclge_pause_setup_hw(hdev, false);
 }
 
 /* DCBX configuration */
@@ -345,12 +372,24 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
 	if (ret)
 		return -EINVAL;
 
+	ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		return ret;
+
+	ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
+
 	hclge_tm_schd_info_update(hdev, tc);
 	hclge_tm_prio_tc_info_update(hdev, prio_tc);
 
-	ret = hclge_tm_init_hw(hdev);
+	ret = hclge_tm_init_hw(hdev, false);
 	if (ret)
-		return ret;
+		goto err_out;
+
+	ret = hclge_client_setup_tc(hdev);
+	if (ret)
+		goto err_out;
 
 	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
 
@@ -359,7 +398,18 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
 	else
 		hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE;
 
-	return 0;
+	ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		return ret;
+
+	return hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+
+err_out:
+	if (hclge_notify_client(hdev, HNAE3_INIT_CLIENT))
+		return ret;
+
+	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	return ret;
 }
 
 static const struct hnae3_dcb_ops hns3_dcb_ops = {
@@ -369,7 +419,6 @@ static const struct hnae3_dcb_ops hns3_dcb_ops = {
 	.ieee_setpfc	= hclge_ieee_setpfc,
 	.getdcbx	= hclge_getdcbx,
 	.setdcbx	= hclge_setdcbx,
-	.map_update	= hclge_map_update,
 	.setup_tc	= hclge_setup_tc,
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 26d80504c730..ab625c757a95 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -61,9 +61,11 @@ static int hclge_dbg_cmd_send(struct hclge_dev *hdev,
 
 static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 				      struct hclge_dbg_dfx_message *dfx_message,
-				      char *cmd_buf, int msg_num, int offset,
-				      enum hclge_opcode_type cmd)
+				      const char *cmd_buf, int msg_num,
+				      int offset, enum hclge_opcode_type cmd)
 {
+#define BD_DATA_NUM       6
+
 	struct hclge_desc *desc_src;
 	struct hclge_desc *desc;
 	int bd_num, buf_len;
@@ -92,14 +94,16 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 		return;
 	}
 
-	max = (bd_num * 6) <= msg_num ? (bd_num * 6) : msg_num;
+	max = (bd_num * BD_DATA_NUM) <= msg_num ?
+		(bd_num * BD_DATA_NUM) : msg_num;
 
 	desc = desc_src;
 	for (i = 0; i < max; i++) {
-		(((i / 6) > 0) && ((i % 6) == 0)) ? desc++ : desc;
+		((i > 0) && ((i % BD_DATA_NUM) == 0)) ? desc++ : desc;
 		if (dfx_message->flag)
 			dev_info(&hdev->pdev->dev, "%s: 0x%x\n",
-				 dfx_message->message, desc->data[i % 6]);
+				 dfx_message->message,
+				 desc->data[i % BD_DATA_NUM]);
 
 		dfx_message++;
 	}
@@ -107,7 +111,7 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
 	kfree(desc_src);
 }
 
-static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, char *cmd_buf)
+static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, const char *cmd_buf)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_dbg_bitmap_cmd *bitmap;
@@ -207,7 +211,7 @@ static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, char *cmd_buf)
 	dev_info(dev, "IGU_TX_PRI_MAP_TC_CFG: 0x%x\n", desc[0].data[5]);
 }
 
-static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, char *cmd_buf)
+static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf)
 {
 	int msg_num;
 
@@ -395,7 +399,7 @@ static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev)
 	if (ret)
 		goto err_tm_pg_cmd_send;
 
-	dev_info(&hdev->pdev->dev, "PRI_SCH pg_id: %u\n", desc.data[0]);
+	dev_info(&hdev->pdev->dev, "PRI_SCH pri_id: %u\n", desc.data[0]);
 
 	cmd = HCLGE_OPC_TM_QS_SCH_MODE_CFG;
 	hclge_cmd_setup_basic_desc(&desc, cmd, true);
@@ -403,7 +407,7 @@ static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev)
 	if (ret)
 		goto err_tm_pg_cmd_send;
 
-	dev_info(&hdev->pdev->dev, "QS_SCH pg_id: %u\n", desc.data[0]);
+	dev_info(&hdev->pdev->dev, "QS_SCH qs_id: %u\n", desc.data[0]);
 
 	cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
 	hclge_cmd_setup_basic_desc(&desc, cmd, true);
@@ -412,9 +416,9 @@ static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev)
 		goto err_tm_pg_cmd_send;
 
 	bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
-	dev_info(&hdev->pdev->dev, "BP_TO_QSET pg_id: %u\n",
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET tc_id: %u\n",
 		 bp_to_qs_map_cmd->tc_id);
-	dev_info(&hdev->pdev->dev, "BP_TO_QSET pg_shapping: 0x%x\n",
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_group_id: 0x%x\n",
 		 bp_to_qs_map_cmd->qs_group_id);
 	dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_bit_map: 0x%x\n",
 		 bp_to_qs_map_cmd->qs_bit_map);
@@ -473,7 +477,7 @@ static void hclge_dbg_dump_tm(struct hclge_dev *hdev)
 
 	nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
 	dev_info(&hdev->pdev->dev, "NQ_TO_QS nq_id: %u\n", nq_to_qs_map->nq_id);
-	dev_info(&hdev->pdev->dev, "NQ_TO_QS qset_id: %u\n",
+	dev_info(&hdev->pdev->dev, "NQ_TO_QS qset_id: 0x%x\n",
 		 nq_to_qs_map->qset_id);
 
 	cmd = HCLGE_OPC_TM_PG_WEIGHT;
@@ -537,7 +541,8 @@ err_tm_cmd_send:
 		cmd, ret);
 }
 
-static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, char *cmd_buf)
+static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev,
+				  const char *cmd_buf)
 {
 	struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
 	struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
@@ -691,7 +696,7 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev)
 	dev_info(&hdev->pdev->dev, "dump qos buf cfg\n");
 
 	tx_buf_cmd = (struct hclge_tx_buff_alloc_cmd *)desc[0].data;
-	for (i = 0; i < HCLGE_TC_NUM; i++)
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
 		dev_info(&hdev->pdev->dev, "tx_packet_buf_tc_%d: 0x%x\n", i,
 			 tx_buf_cmd->tx_pkt_buff[i]);
 
@@ -703,7 +708,7 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev)
 
 	dev_info(&hdev->pdev->dev, "\n");
 	rx_buf_cmd = (struct hclge_rx_priv_buff_cmd *)desc[0].data;
-	for (i = 0; i < HCLGE_TC_NUM; i++)
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
 		dev_info(&hdev->pdev->dev, "rx_packet_buf_tc_%d: 0x%x\n", i,
 			 rx_buf_cmd->buf_num[i]);
 
@@ -901,7 +906,166 @@ static void hclge_dbg_fd_tcam(struct hclge_dev *hdev)
 	}
 }
 
-int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
+static void hclge_dbg_dump_rst_info(struct hclge_dev *hdev)
+{
+	dev_info(&hdev->pdev->dev, "PF reset count: %d\n",
+		 hdev->rst_stats.pf_rst_cnt);
+	dev_info(&hdev->pdev->dev, "FLR reset count: %d\n",
+		 hdev->rst_stats.flr_rst_cnt);
+	dev_info(&hdev->pdev->dev, "CORE reset count: %d\n",
+		 hdev->rst_stats.core_rst_cnt);
+	dev_info(&hdev->pdev->dev, "GLOBAL reset count: %d\n",
+		 hdev->rst_stats.global_rst_cnt);
+	dev_info(&hdev->pdev->dev, "IMP reset count: %d\n",
+		 hdev->rst_stats.imp_rst_cnt);
+	dev_info(&hdev->pdev->dev, "reset done count: %d\n",
+		 hdev->rst_stats.reset_done_cnt);
+	dev_info(&hdev->pdev->dev, "HW reset done count: %d\n",
+		 hdev->rst_stats.hw_reset_done_cnt);
+	dev_info(&hdev->pdev->dev, "reset count: %d\n",
+		 hdev->rst_stats.reset_cnt);
+}
+
+void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev)
+{
+	struct hclge_desc *desc_src, *desc_tmp;
+	struct hclge_get_m7_bd_cmd *req;
+	struct hclge_desc desc;
+	u32 bd_num, buf_len;
+	int ret, i;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_M7_STATS_BD, true);
+
+	req = (struct hclge_get_m7_bd_cmd *)desc.data;
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"get firmware statistics bd number failed, ret=%d\n",
+			ret);
+		return;
+	}
+
+	bd_num = le32_to_cpu(req->bd_num);
+
+	buf_len	 = sizeof(struct hclge_desc) * bd_num;
+	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	if (!desc_src) {
+		dev_err(&hdev->pdev->dev,
+			"allocate desc for get_m7_stats failed\n");
+		return;
+	}
+
+	desc_tmp = desc_src;
+	ret  = hclge_dbg_cmd_send(hdev, desc_tmp, 0, bd_num,
+				  HCLGE_OPC_M7_STATS_INFO);
+	if (ret) {
+		kfree(desc_src);
+		dev_err(&hdev->pdev->dev,
+			"get firmware statistics failed, ret=%d\n", ret);
+		return;
+	}
+
+	for (i = 0; i < bd_num; i++) {
+		dev_info(&hdev->pdev->dev, "0x%08x  0x%08x  0x%08x\n",
+			 le32_to_cpu(desc_tmp->data[0]),
+			 le32_to_cpu(desc_tmp->data[1]),
+			 le32_to_cpu(desc_tmp->data[2]));
+		dev_info(&hdev->pdev->dev, "0x%08x  0x%08x  0x%08x\n",
+			 le32_to_cpu(desc_tmp->data[3]),
+			 le32_to_cpu(desc_tmp->data[4]),
+			 le32_to_cpu(desc_tmp->data[5]));
+
+		desc_tmp++;
+	}
+
+	kfree(desc_src);
+}
+
+/* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file
+ * @hdev: pointer to struct hclge_dev
+ * @cmd_buf: string that contains offset and length
+ */
+static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev,
+				      const char *cmd_buf)
+{
+#define HCLGE_MAX_NCL_CONFIG_OFFSET	4096
+#define HCLGE_MAX_NCL_CONFIG_LENGTH	(20 + 24 * 4)
+#define HCLGE_CMD_DATA_NUM		6
+
+	struct hclge_desc desc[5];
+	u32 byte_offset;
+	int bd_num = 5;
+	int offset;
+	int length;
+	int data0;
+	int ret;
+	int i;
+	int j;
+
+	ret = sscanf(cmd_buf, "%x %x", &offset, &length);
+	if (ret != 2 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET ||
+	    length > HCLGE_MAX_NCL_CONFIG_OFFSET - offset) {
+		dev_err(&hdev->pdev->dev, "Invalid offset or length.\n");
+		return;
+	}
+	if (offset < 0 || length <= 0) {
+		dev_err(&hdev->pdev->dev, "Non-positive offset or length.\n");
+		return;
+	}
+
+	dev_info(&hdev->pdev->dev, "offset |    data\n");
+
+	while (length > 0) {
+		data0 = offset;
+		if (length >= HCLGE_MAX_NCL_CONFIG_LENGTH)
+			data0 |= HCLGE_MAX_NCL_CONFIG_LENGTH << 16;
+		else
+			data0 |= length << 16;
+		ret = hclge_dbg_cmd_send(hdev, desc, data0, bd_num,
+					 HCLGE_OPC_QUERY_NCL_CONFIG);
+		if (ret)
+			return;
+
+		byte_offset = offset;
+		for (i = 0; i < bd_num; i++) {
+			for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) {
+				if (i == 0 && j == 0)
+					continue;
+
+				dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n",
+					 byte_offset,
+					 le32_to_cpu(desc[i].data[j]));
+				byte_offset += sizeof(u32);
+				length -= sizeof(u32);
+				if (length <= 0)
+					return;
+			}
+		}
+		offset += HCLGE_MAX_NCL_CONFIG_LENGTH;
+	}
+}
+
+/* hclge_dbg_dump_mac_tnl_status: print message about mac tnl interrupt
+ * @hdev: pointer to struct hclge_dev
+ */
+static void hclge_dbg_dump_mac_tnl_status(struct hclge_dev *hdev)
+{
+#define HCLGE_BILLION_NANO_SECONDS 1000000000
+
+	struct hclge_mac_tnl_stats stats;
+	unsigned long rem_nsec;
+
+	dev_info(&hdev->pdev->dev, "Recently generated mac tnl interruption:\n");
+
+	while (kfifo_get(&hdev->mac_tnl_log, &stats)) {
+		rem_nsec = do_div(stats.time, HCLGE_BILLION_NANO_SECONDS);
+		dev_info(&hdev->pdev->dev, "[%07lu.%03lu] status = 0x%x\n",
+			 (unsigned long)stats.time, rem_nsec / 1000,
+			 stats.status);
+	}
+}
+
+int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
@@ -924,6 +1088,15 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
 		hclge_dbg_dump_mng_table(hdev);
 	} else if (strncmp(cmd_buf, "dump reg", 8) == 0) {
 		hclge_dbg_dump_reg_cmd(hdev, cmd_buf);
+	} else if (strncmp(cmd_buf, "dump reset info", 15) == 0) {
+		hclge_dbg_dump_rst_info(hdev);
+	} else if (strncmp(cmd_buf, "dump m7 info", 12) == 0) {
+		hclge_dbg_get_m7_stats_info(hdev);
+	} else if (strncmp(cmd_buf, "dump ncl_config", 15) == 0) {
+		hclge_dbg_dump_ncl_config(hdev,
+					  &cmd_buf[sizeof("dump ncl_config")]);
+	} else if (strncmp(cmd_buf, "dump mac tnl status", 19) == 0) {
+		hclge_dbg_dump_mac_tnl_status(hdev);
 	} else {
 		dev_info(&hdev->pdev->dev, "unknown command\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index d0f654123b9b..0a7243825e7b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -4,336 +4,606 @@
 #include "hclge_err.h"
 
 static const struct hclge_hw_error hclge_imp_tcm_ecc_int[] = {
-	{ .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err" },
-	{ .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err" },
-	{ .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err" },
-	{ .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err" },
-	{ .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err" },
-	{ .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err" },
+	{ .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
-	{ .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err" },
-	{ .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err" },
-	{ .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(21), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(23), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(25), .msg = "cmdq_rocee_rx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(27), .msg = "cmdq_rocee_tx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(29), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err" },
-	{ .int_msk = BIT(31), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err" },
+	{ .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(21), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(23), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(25), .msg = "cmdq_rocee_rx_head_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(27), .msg = "cmdq_rocee_tx_head_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(29), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(31), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
-	{ .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err" },
-	{ .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err" },
-	{ .int_msk = BIT(9), .msg = "tqp_int_ctrl_odd_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "tx_que_scan_int_ecc_mbit_err" },
-	{ .int_msk = BIT(11), .msg = "rx_que_scan_int_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(9), .msg = "tqp_int_ctrl_odd_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(10), .msg = "tx_que_scan_int_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(11), .msg = "rx_que_scan_int_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_msix_sram_ecc_int[] = {
-	{ .int_msk = BIT(1), .msg = "msix_nic_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "msix_rocee_ecc_mbit_err" },
+	{ .int_msk = BIT(1), .msg = "msix_nic_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(3), .msg = "msix_rocee_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_igu_int[] = {
-	{ .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err" },
+	{ .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_igu_egu_tnl_int[] = {
-	{ .int_msk = BIT(0), .msg = "rx_buf_overflow" },
-	{ .int_msk = BIT(1), .msg = "rx_stp_fifo_overflow" },
-	{ .int_msk = BIT(2), .msg = "rx_stp_fifo_undeflow" },
-	{ .int_msk = BIT(3), .msg = "tx_buf_overflow" },
-	{ .int_msk = BIT(4), .msg = "tx_buf_underrun" },
-	{ .int_msk = BIT(5), .msg = "rx_stp_buf_overflow" },
+	{ .int_msk = BIT(0), .msg = "rx_buf_overflow",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(1), .msg = "rx_stp_fifo_overflow",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "rx_stp_fifo_undeflow",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "tx_buf_overflow",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "tx_buf_underrun",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "rx_stp_buf_overflow",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ncsi_err_int[] = {
-	{ .int_msk = BIT(1), .msg = "ncsi_tx_ecc_mbit_err" },
+	{ .int_msk = BIT(1), .msg = "ncsi_tx_ecc_mbit_err",
+	  .reset_level = HNAE3_NONE_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st1[] = {
-	{ .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_mbit_err" },
-	{ .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_erre" },
-	{ .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "rss_idt_mem2_ecc_mbit_err" },
-	{ .int_msk = BIT(11), .msg = "rss_idt_mem3_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "rss_idt_mem4_ecc_mbit_err" },
-	{ .int_msk = BIT(13), .msg = "rss_idt_mem5_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "rss_idt_mem6_ecc_mbit_err" },
-	{ .int_msk = BIT(15), .msg = "rss_idt_mem7_ecc_mbit_err" },
-	{ .int_msk = BIT(16), .msg = "rss_idt_mem8_ecc_mbit_err" },
-	{ .int_msk = BIT(17), .msg = "rss_idt_mem9_ecc_mbit_err" },
-	{ .int_msk = BIT(18), .msg = "rss_idt_mem10_ecc_m1bit_err" },
-	{ .int_msk = BIT(19), .msg = "rss_idt_mem11_ecc_mbit_err" },
-	{ .int_msk = BIT(20), .msg = "rss_idt_mem12_ecc_mbit_err" },
-	{ .int_msk = BIT(21), .msg = "rss_idt_mem13_ecc_mbit_err" },
-	{ .int_msk = BIT(22), .msg = "rss_idt_mem14_ecc_mbit_err" },
-	{ .int_msk = BIT(23), .msg = "rss_idt_mem15_ecc_mbit_err" },
-	{ .int_msk = BIT(24), .msg = "port_vlan_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(25), .msg = "mcast_linear_table_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(26), .msg = "mcast_result_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(27),
-		.msg = "flow_director_ad_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(28),
-		.msg = "flow_director_ad_mem1_ecc_mbit_err" },
-	{ .int_msk = BIT(29),
-		.msg = "rx_vlan_tag_memory_ecc_mbit_err" },
-	{ .int_msk = BIT(30),
-		.msg = "Tx_UP_mapping_config_mem_ecc_mbit_err" },
+	{ .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(10), .msg = "rss_idt_mem2_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(11), .msg = "rss_idt_mem3_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(12), .msg = "rss_idt_mem4_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(13), .msg = "rss_idt_mem5_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(14), .msg = "rss_idt_mem6_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(15), .msg = "rss_idt_mem7_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(16), .msg = "rss_idt_mem8_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(17), .msg = "rss_idt_mem9_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(18), .msg = "rss_idt_mem10_ecc_m1bit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(19), .msg = "rss_idt_mem11_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(20), .msg = "rss_idt_mem12_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(21), .msg = "rss_idt_mem13_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(22), .msg = "rss_idt_mem14_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(23), .msg = "rss_idt_mem15_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(24), .msg = "port_vlan_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(25), .msg = "mcast_linear_table_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(26), .msg = "mcast_result_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(27), .msg = "flow_director_ad_mem0_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(28), .msg = "flow_director_ad_mem1_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(29), .msg = "rx_vlan_tag_memory_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(30), .msg = "Tx_UP_mapping_config_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ppp_pf_abnormal_int[] = {
-	{ .int_msk = BIT(0), .msg = "tx_vlan_tag_err" },
-	{ .int_msk = BIT(1), .msg = "rss_list_tc_unassigned_queue_err" },
+	{ .int_msk = BIT(0), .msg = "tx_vlan_tag_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(1), .msg = "rss_list_tc_unassigned_queue_err",
+	  .reset_level = HNAE3_NONE_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st3[] = {
-	{ .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "FD_CN0_memory_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "FD_CN1_memory_ecc_mbit_err" },
-	{ .int_msk = BIT(5), .msg = "GRO_AD_memory_ecc_mbit_err" },
+	{ .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "FD_CN0_memory_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "FD_CN1_memory_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "GRO_AD_memory_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_tm_sch_rint[] = {
-	{ .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err" },
-	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err" },
-	{ .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_err" },
-	{ .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_err" },
-	{ .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_err" },
-	{ .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_err" },
-	{ .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_err" },
-	{ .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_err" },
-	{ .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_err" },
-	{ .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_err" },
-	{ .int_msk = BIT(12),
-	  .msg = "tm_sch_port_shap_offset_fifo_wr_err" },
-	{ .int_msk = BIT(13),
-	  .msg = "tm_sch_port_shap_offset_fifo_rd_err" },
-	{ .int_msk = BIT(14),
-	  .msg = "tm_sch_pg_pshap_offset_fifo_wr_err" },
-	{ .int_msk = BIT(15),
-	  .msg = "tm_sch_pg_pshap_offset_fifo_rd_err" },
-	{ .int_msk = BIT(16),
-	  .msg = "tm_sch_pg_cshap_offset_fifo_wr_err" },
-	{ .int_msk = BIT(17),
-	  .msg = "tm_sch_pg_cshap_offset_fifo_rd_err" },
-	{ .int_msk = BIT(18),
-	  .msg = "tm_sch_pri_pshap_offset_fifo_wr_err" },
-	{ .int_msk = BIT(19),
-	  .msg = "tm_sch_pri_pshap_offset_fifo_rd_err" },
-	{ .int_msk = BIT(20),
-	  .msg = "tm_sch_pri_cshap_offset_fifo_wr_err" },
-	{ .int_msk = BIT(21),
-	  .msg = "tm_sch_pri_cshap_offset_fifo_rd_err" },
-	{ .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_err" },
-	{ .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_err" },
-	{ .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_err" },
-	{ .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_err" },
-	{ .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_err" },
-	{ .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_err" },
-	{ .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_err" },
-	{ .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_err" },
-	{ .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_err" },
-	{ .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_err" },
+	{ .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(12), .msg = "tm_sch_port_shap_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(13), .msg = "tm_sch_port_shap_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(14), .msg = "tm_sch_pg_pshap_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(15), .msg = "tm_sch_pg_pshap_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(16), .msg = "tm_sch_pg_cshap_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(17), .msg = "tm_sch_pg_cshap_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(18), .msg = "tm_sch_pri_pshap_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(19), .msg = "tm_sch_pri_pshap_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(20), .msg = "tm_sch_pri_cshap_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(21), .msg = "tm_sch_pri_cshap_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_qcn_fifo_rint[] = {
-	{ .int_msk = BIT(0), .msg = "qcn_shap_gp0_sch_fifo_rd_err" },
-	{ .int_msk = BIT(1), .msg = "qcn_shap_gp0_sch_fifo_wr_err" },
-	{ .int_msk = BIT(2), .msg = "qcn_shap_gp1_sch_fifo_rd_err" },
-	{ .int_msk = BIT(3), .msg = "qcn_shap_gp1_sch_fifo_wr_err" },
-	{ .int_msk = BIT(4), .msg = "qcn_shap_gp2_sch_fifo_rd_err" },
-	{ .int_msk = BIT(5), .msg = "qcn_shap_gp2_sch_fifo_wr_err" },
-	{ .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err" },
-	{ .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err" },
-	{ .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err" },
-	{ .int_msk = BIT(9), .msg = "qcn_shap_gp0_offset_fifo_wr_err" },
-	{ .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err" },
-	{ .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err" },
-	{ .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err" },
-	{ .int_msk = BIT(13), .msg = "qcn_shap_gp2_offset_fifo_wr_err" },
-	{ .int_msk = BIT(14), .msg = "qcn_shap_gp3_offset_fifo_rd_err" },
-	{ .int_msk = BIT(15), .msg = "qcn_shap_gp3_offset_fifo_wr_err" },
-	{ .int_msk = BIT(16), .msg = "qcn_byte_info_fifo_rd_err" },
-	{ .int_msk = BIT(17), .msg = "qcn_byte_info_fifo_wr_err" },
+	{ .int_msk = BIT(0), .msg = "qcn_shap_gp0_sch_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(1), .msg = "qcn_shap_gp0_sch_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "qcn_shap_gp1_sch_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "qcn_shap_gp1_sch_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "qcn_shap_gp2_sch_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "qcn_shap_gp2_sch_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "qcn_shap_gp0_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(13), .msg = "qcn_shap_gp2_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(14), .msg = "qcn_shap_gp3_offset_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(15), .msg = "qcn_shap_gp3_offset_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(16), .msg = "qcn_byte_info_fifo_rd_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(17), .msg = "qcn_byte_info_fifo_wr_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_qcn_ecc_rint[] = {
-	{ .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "qcn_time_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(5), .msg = "qcn_fb_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(7), .msg = "qcn_link_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(9), .msg = "qcn_rate_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(11), .msg = "qcn_tmplt_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(13), .msg = "qcn_shap_cfg_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(15), .msg = "qcn_gp0_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(17), .msg = "qcn_gp1_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(19), .msg = "qcn_gp2_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(21), .msg = "qcn_gp3_barral_mem_ecc_mbit_err" },
+	{ .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "qcn_time_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "qcn_fb_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "qcn_link_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "qcn_rate_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(11), .msg = "qcn_tmplt_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(13), .msg = "qcn_shap_cfg_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(15), .msg = "qcn_gp0_barrel_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(17), .msg = "qcn_gp1_barrel_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(19), .msg = "qcn_gp2_barrel_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(21), .msg = "qcn_gp3_barral_mem_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_mac_afifo_tnl_int[] = {
-	{ .int_msk = BIT(0), .msg = "egu_cge_afifo_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "egu_cge_afifo_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "egu_lge_afifo_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "egu_lge_afifo_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "cge_igu_afifo_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err" },
-	{ .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(0), .msg = "egu_cge_afifo_ecc_1bit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(1), .msg = "egu_cge_afifo_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "egu_lge_afifo_ecc_1bit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(3), .msg = "egu_lge_afifo_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "cge_igu_afifo_ecc_1bit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(8), .msg = "cge_igu_afifo_overflow_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "lge_igu_afifo_overflow_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(10), .msg = "egu_cge_afifo_underrun_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(11), .msg = "egu_lge_afifo_underrun_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(12), .msg = "egu_ge_afifo_underrun_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(13), .msg = "ge_igu_afifo_overflow_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st2[] = {
-	{ .int_msk = BIT(13), .msg = "rpu_rx_pkt_bit32_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "rpu_rx_pkt_bit33_ecc_mbit_err" },
-	{ .int_msk = BIT(15), .msg = "rpu_rx_pkt_bit34_ecc_mbit_err" },
-	{ .int_msk = BIT(16), .msg = "rpu_rx_pkt_bit35_ecc_mbit_err" },
-	{ .int_msk = BIT(17), .msg = "rcb_tx_ring_ecc_mbit_err" },
-	{ .int_msk = BIT(18), .msg = "rcb_rx_ring_ecc_mbit_err" },
-	{ .int_msk = BIT(19), .msg = "rcb_tx_fbd_ecc_mbit_err" },
-	{ .int_msk = BIT(20), .msg = "rcb_rx_ebd_ecc_mbit_err" },
-	{ .int_msk = BIT(21), .msg = "rcb_tso_info_ecc_mbit_err" },
-	{ .int_msk = BIT(22), .msg = "rcb_tx_int_info_ecc_mbit_err" },
-	{ .int_msk = BIT(23), .msg = "rcb_rx_int_info_ecc_mbit_err" },
-	{ .int_msk = BIT(24), .msg = "tpu_tx_pkt_0_ecc_mbit_err" },
-	{ .int_msk = BIT(25), .msg = "tpu_tx_pkt_1_ecc_mbit_err" },
-	{ .int_msk = BIT(26), .msg = "rd_bus_err" },
-	{ .int_msk = BIT(27), .msg = "wr_bus_err" },
-	{ .int_msk = BIT(28), .msg = "reg_search_miss" },
-	{ .int_msk = BIT(29), .msg = "rx_q_search_miss" },
-	{ .int_msk = BIT(30), .msg = "ooo_ecc_err_detect" },
-	{ .int_msk = BIT(31), .msg = "ooo_ecc_err_multpl" },
+	{ .int_msk = BIT(13), .msg = "rpu_rx_pkt_bit32_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(14), .msg = "rpu_rx_pkt_bit33_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(15), .msg = "rpu_rx_pkt_bit34_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(16), .msg = "rpu_rx_pkt_bit35_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(17), .msg = "rcb_tx_ring_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(18), .msg = "rcb_rx_ring_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(19), .msg = "rcb_tx_fbd_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(20), .msg = "rcb_rx_ebd_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(21), .msg = "rcb_tso_info_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(22), .msg = "rcb_tx_int_info_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(23), .msg = "rcb_rx_int_info_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(24), .msg = "tpu_tx_pkt_0_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(25), .msg = "tpu_tx_pkt_1_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(26), .msg = "rd_bus_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(27), .msg = "wr_bus_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(28), .msg = "reg_search_miss",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(29), .msg = "rx_q_search_miss",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(30), .msg = "ooo_ecc_err_detect",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(31), .msg = "ooo_ecc_err_multpl",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st3[] = {
-	{ .int_msk = BIT(4), .msg = "gro_bd_ecc_mbit_err" },
-	{ .int_msk = BIT(5), .msg = "gro_context_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "rx_stash_cfg_ecc_mbit_err" },
-	{ .int_msk = BIT(7), .msg = "axi_rd_fbd_ecc_mbit_err" },
+	{ .int_msk = BIT(4), .msg = "gro_bd_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "gro_context_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "rx_stash_cfg_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "axi_rd_fbd_ecc_mbit_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ppu_pf_abnormal_int[] = {
-	{ .int_msk = BIT(0), .msg = "over_8bd_no_fe" },
-	{ .int_msk = BIT(1), .msg = "tso_mss_cmp_min_err" },
-	{ .int_msk = BIT(2), .msg = "tso_mss_cmp_max_err" },
-	{ .int_msk = BIT(3), .msg = "tx_rd_fbd_poison" },
-	{ .int_msk = BIT(4), .msg = "rx_rd_ebd_poison" },
-	{ .int_msk = BIT(5), .msg = "buf_wait_timeout" },
+	{ .int_msk = BIT(0), .msg = "over_8bd_no_fe",
+	  .reset_level = HNAE3_FUNC_RESET },
+	{ .int_msk = BIT(1), .msg = "tso_mss_cmp_min_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(2), .msg = "tso_mss_cmp_max_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(3), .msg = "tx_rd_fbd_poison",
+	  .reset_level = HNAE3_FUNC_RESET },
+	{ .int_msk = BIT(4), .msg = "rx_rd_ebd_poison",
+	  .reset_level = HNAE3_FUNC_RESET },
+	{ .int_msk = BIT(5), .msg = "buf_wait_timeout",
+	  .reset_level = HNAE3_NONE_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ssu_com_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "buf_sum_err" },
-	{ .int_msk = BIT(1), .msg = "ppp_mb_num_err" },
-	{ .int_msk = BIT(2), .msg = "ppp_mbid_err" },
-	{ .int_msk = BIT(3), .msg = "ppp_rlt_mac_err" },
-	{ .int_msk = BIT(4), .msg = "ppp_rlt_host_err" },
-	{ .int_msk = BIT(5), .msg = "cks_edit_position_err" },
-	{ .int_msk = BIT(6), .msg = "cks_edit_condition_err" },
-	{ .int_msk = BIT(7), .msg = "vlan_edit_condition_err" },
-	{ .int_msk = BIT(8), .msg = "vlan_num_ot_err" },
-	{ .int_msk = BIT(9), .msg = "vlan_num_in_err" },
+	{ .int_msk = BIT(0), .msg = "buf_sum_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(1), .msg = "ppp_mb_num_err",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(2), .msg = "ppp_mbid_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "ppp_rlt_mac_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "ppp_rlt_host_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "cks_edit_position_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "cks_edit_condition_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "vlan_edit_condition_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(8), .msg = "vlan_num_ot_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "vlan_num_in_err",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ /* sentinel */ }
+};
+
+#define HCLGE_SSU_MEM_ECC_ERR(x) \
+	{ .int_msk = BIT(x), .msg = "ssu_mem" #x "_ecc_mbit_err", \
+	  .reset_level = HNAE3_GLOBAL_RESET }
+
+static const struct hclge_hw_error hclge_ssu_mem_ecc_err_int[] = {
+	HCLGE_SSU_MEM_ECC_ERR(0),
+	HCLGE_SSU_MEM_ECC_ERR(1),
+	HCLGE_SSU_MEM_ECC_ERR(2),
+	HCLGE_SSU_MEM_ECC_ERR(3),
+	HCLGE_SSU_MEM_ECC_ERR(4),
+	HCLGE_SSU_MEM_ECC_ERR(5),
+	HCLGE_SSU_MEM_ECC_ERR(6),
+	HCLGE_SSU_MEM_ECC_ERR(7),
+	HCLGE_SSU_MEM_ECC_ERR(8),
+	HCLGE_SSU_MEM_ECC_ERR(9),
+	HCLGE_SSU_MEM_ECC_ERR(10),
+	HCLGE_SSU_MEM_ECC_ERR(11),
+	HCLGE_SSU_MEM_ECC_ERR(12),
+	HCLGE_SSU_MEM_ECC_ERR(13),
+	HCLGE_SSU_MEM_ECC_ERR(14),
+	HCLGE_SSU_MEM_ECC_ERR(15),
+	HCLGE_SSU_MEM_ECC_ERR(16),
+	HCLGE_SSU_MEM_ECC_ERR(17),
+	HCLGE_SSU_MEM_ECC_ERR(18),
+	HCLGE_SSU_MEM_ECC_ERR(19),
+	HCLGE_SSU_MEM_ECC_ERR(20),
+	HCLGE_SSU_MEM_ECC_ERR(21),
+	HCLGE_SSU_MEM_ECC_ERR(22),
+	HCLGE_SSU_MEM_ECC_ERR(23),
+	HCLGE_SSU_MEM_ECC_ERR(24),
+	HCLGE_SSU_MEM_ECC_ERR(25),
+	HCLGE_SSU_MEM_ECC_ERR(26),
+	HCLGE_SSU_MEM_ECC_ERR(27),
+	HCLGE_SSU_MEM_ECC_ERR(28),
+	HCLGE_SSU_MEM_ECC_ERR(29),
+	HCLGE_SSU_MEM_ECC_ERR(30),
+	HCLGE_SSU_MEM_ECC_ERR(31),
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
-	{ .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port" },
-	{ .int_msk = BIT(2), .msg = "igu_pkt_without_key_port" },
-	{ .int_msk = BIT(3), .msg = "roc_eof_mis_match_port" },
-	{ .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port" },
-	{ .int_msk = BIT(5), .msg = "igu_eof_mis_match_port" },
-	{ .int_msk = BIT(6), .msg = "roc_sof_mis_match_port" },
-	{ .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port" },
-	{ .int_msk = BIT(8), .msg = "igu_sof_mis_match_port" },
-	{ .int_msk = BIT(11), .msg = "ets_rd_int_rx_port" },
-	{ .int_msk = BIT(12), .msg = "ets_wr_int_rx_port" },
-	{ .int_msk = BIT(13), .msg = "ets_rd_int_tx_port" },
-	{ .int_msk = BIT(14), .msg = "ets_wr_int_tx_port" },
+	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "igu_pkt_without_key_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "roc_eof_mis_match_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "igu_eof_mis_match_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "roc_sof_mis_match_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(8), .msg = "igu_sof_mis_match_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(11), .msg = "ets_rd_int_rx_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(12), .msg = "ets_wr_int_rx_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(13), .msg = "ets_rd_int_tx_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(14), .msg = "ets_wr_int_tx_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ssu_fifo_overflow_int[] = {
-	{ .int_msk = BIT(0), .msg = "ig_mac_inf_int" },
-	{ .int_msk = BIT(1), .msg = "ig_host_inf_int" },
-	{ .int_msk = BIT(2), .msg = "ig_roc_buf_int" },
-	{ .int_msk = BIT(3), .msg = "ig_host_data_fifo_int" },
-	{ .int_msk = BIT(4), .msg = "ig_host_key_fifo_int" },
-	{ .int_msk = BIT(5), .msg = "tx_qcn_fifo_int" },
-	{ .int_msk = BIT(6), .msg = "rx_qcn_fifo_int" },
-	{ .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int" },
-	{ .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int" },
-	{ .int_msk = BIT(9), .msg = "qm_eof_fifo_int" },
-	{ .int_msk = BIT(10), .msg = "mb_rlt_fifo_int" },
-	{ .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int" },
-	{ .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int" },
-	{ .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int" },
-	{ .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int" },
-	{ .int_msk = BIT(15), .msg = "host_cmd_fifo_int" },
-	{ .int_msk = BIT(16), .msg = "mac_cmd_fifo_int" },
-	{ .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int" },
-	{ .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int" },
-	{ .int_msk = BIT(19), .msg = "dup_bitmap_empty_int" },
-	{ .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int" },
-	{ .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int" },
-	{ .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int" },
-	{ .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int" },
+	{ .int_msk = BIT(0), .msg = "ig_mac_inf_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(1), .msg = "ig_host_inf_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "ig_roc_buf_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "ig_host_data_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(4), .msg = "ig_host_key_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(5), .msg = "tx_qcn_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(6), .msg = "rx_qcn_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "qm_eof_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(10), .msg = "mb_rlt_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(15), .msg = "host_cmd_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(16), .msg = "mac_cmd_fifo_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(19), .msg = "dup_bitmap_empty_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ssu_ets_tcg_int[] = {
-	{ .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg" },
-	{ .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg" },
-	{ .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg" },
-	{ .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg" },
+	{ .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = {
-	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
-	{ .int_msk = BIT(9), .msg = "low_water_line_err_port" },
-	{ .int_msk = BIT(10), .msg = "hi_water_line_err_port" },
+	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
+	{ .int_msk = BIT(9), .msg = "low_water_line_err_port",
+	  .reset_level = HNAE3_NONE_RESET },
+	{ .int_msk = BIT(10), .msg = "hi_water_line_err_port",
+	  .reset_level = HNAE3_GLOBAL_RESET },
 	{ /* sentinel */ }
 };
 
@@ -363,12 +633,16 @@ static const struct hclge_hw_error hclge_rocee_qmm_ovf_err_int[] = {
 
 static void hclge_log_error(struct device *dev, char *reg,
 			    const struct hclge_hw_error *err,
-			    u32 err_sts)
+			    u32 err_sts, unsigned long *reset_requests)
 {
 	while (err->msg) {
-		if (err->int_msk & err_sts)
+		if (err->int_msk & err_sts) {
 			dev_warn(dev, "%s %s found [error status=0x%x]\n",
 				 reg, err->msg, err_sts);
+			if (err->reset_level &&
+			    err->reset_level != HNAE3_NONE_RESET)
+				set_bit(err->reset_level, reset_requests);
+		}
 		err++;
 	}
 }
@@ -390,25 +664,35 @@ static int hclge_cmd_query_error(struct hclge_dev *hdev,
 				 enum hclge_err_int_type int_type)
 {
 	struct device *dev = &hdev->pdev->dev;
-	int num = 1;
+	int desc_num = 1;
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc[0], cmd, true);
 	if (flag) {
 		desc[0].flag |= cpu_to_le16(flag);
 		hclge_cmd_setup_basic_desc(&desc[1], cmd, true);
-		num = 2;
+		desc_num = 2;
 	}
 	if (w_num)
 		desc[0].data[w_num] = cpu_to_le32(int_type);
 
-	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], desc_num);
 	if (ret)
 		dev_err(dev, "query error cmd failed (%d)\n", ret);
 
 	return ret;
 }
 
+static int hclge_clear_mac_tnl_int(struct hclge_dev *hdev)
+{
+	struct hclge_desc desc;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CLEAR_MAC_TNL_INT, false);
+	desc.data[0] = cpu_to_le32(HCLGE_MAC_TNL_INT_CLR);
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
 static int hclge_config_common_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
@@ -628,12 +912,27 @@ static int hclge_config_mac_err_int(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
+int hclge_config_mac_tnl_int(struct hclge_dev *hdev, bool en)
+{
+	struct hclge_desc desc;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_TNL_INT_EN, false);
+	if (en)
+		desc.data[0] = cpu_to_le32(HCLGE_MAC_TNL_INT_EN);
+	else
+		desc.data[0] = 0;
+
+	desc.data[1] = cpu_to_le32(HCLGE_MAC_TNL_INT_EN_MASK);
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
 static int hclge_config_ppu_error_interrupts(struct hclge_dev *hdev, u32 cmd,
 					     bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc[2];
-	int num = 1;
+	int desc_num = 1;
 	int ret;
 
 	/* configure PPU error interrupts */
@@ -652,7 +951,7 @@ static int hclge_config_ppu_error_interrupts(struct hclge_dev *hdev, u32 cmd,
 		desc[1].data[1] = HCLGE_PPU_MPF_ABNORMAL_INT1_EN_MASK;
 		desc[1].data[2] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN_MASK;
 		desc[1].data[3] |= HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK;
-		num = 2;
+		desc_num = 2;
 	} else if (cmd == HCLGE_PPU_MPF_OTHER_INT_CMD) {
 		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
 		if (en)
@@ -670,7 +969,7 @@ static int hclge_config_ppu_error_interrupts(struct hclge_dev *hdev, u32 cmd,
 		return -EINVAL;
 	}
 
-	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], desc_num);
 
 	return ret;
 }
@@ -761,12 +1060,51 @@ static int hclge_config_ssu_hw_err_int(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
-#define HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type) \
-	do { \
-		if (ae_dev->ops->set_default_reset_request) \
-			ae_dev->ops->set_default_reset_request(ae_dev, \
-							       reset_type); \
-	} while (0)
+/* hclge_query_bd_num: query number of buffer descriptors
+ * @hdev: pointer to struct hclge_dev
+ * @is_ras: true for ras, false for msix
+ * @mpf_bd_num: number of main PF interrupt buffer descriptors
+ * @pf_bd_num: number of not main PF interrupt buffer descriptors
+ *
+ * This function querys number of mpf and pf buffer descriptors.
+ */
+static int hclge_query_bd_num(struct hclge_dev *hdev, bool is_ras,
+			      int *mpf_bd_num, int *pf_bd_num)
+{
+	struct device *dev = &hdev->pdev->dev;
+	u32 mpf_min_bd_num, pf_min_bd_num;
+	enum hclge_opcode_type opcode;
+	struct hclge_desc desc_bd;
+	int ret;
+
+	if (is_ras) {
+		opcode = HCLGE_QUERY_RAS_INT_STS_BD_NUM;
+		mpf_min_bd_num = HCLGE_MPF_RAS_INT_MIN_BD_NUM;
+		pf_min_bd_num = HCLGE_PF_RAS_INT_MIN_BD_NUM;
+	} else {
+		opcode = HCLGE_QUERY_MSIX_INT_STS_BD_NUM;
+		mpf_min_bd_num = HCLGE_MPF_MSIX_INT_MIN_BD_NUM;
+		pf_min_bd_num = HCLGE_PF_MSIX_INT_MIN_BD_NUM;
+	}
+
+	hclge_cmd_setup_basic_desc(&desc_bd, opcode, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
+	if (ret) {
+		dev_err(dev, "fail(%d) to query msix int status bd num\n",
+			ret);
+		return ret;
+	}
+
+	*mpf_bd_num = le32_to_cpu(desc_bd.data[0]);
+	*pf_bd_num = le32_to_cpu(desc_bd.data[1]);
+	if (*mpf_bd_num < mpf_min_bd_num || *pf_bd_num < pf_min_bd_num) {
+		dev_err(dev, "Invalid bd num: mpf(%d), pf(%d)\n",
+			*mpf_bd_num, *pf_bd_num);
+		return -EINVAL;
+	}
+
+	return 0;
+}
 
 /* hclge_handle_mpf_ras_error: handle all main PF RAS errors
  * @hdev: pointer to struct hclge_dev
@@ -789,8 +1127,6 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev,
 	/* query all main PF RAS errors */
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_MPF_RAS_INT,
 				   true);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
 	if (ret) {
 		dev_err(dev, "query all mpf ras int cmd failed (%d)\n", ret);
@@ -799,77 +1135,74 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev,
 
 	/* log HNS common errors */
 	status = le32_to_cpu(desc[0].data[0]);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "IMP_TCM_ECC_INT_STS",
-				&hclge_imp_tcm_ecc_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-	}
+				&hclge_imp_tcm_ecc_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(desc[0].data[1]);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "CMDQ_MEM_ECC_INT_STS",
-				&hclge_cmdq_nic_mem_ecc_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-	}
+				&hclge_cmdq_nic_mem_ecc_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
-	if ((le32_to_cpu(desc[0].data[2])) & BIT(0)) {
+	if ((le32_to_cpu(desc[0].data[2])) & BIT(0))
 		dev_warn(dev, "imp_rd_data_poison_err found\n");
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-	}
 
 	status = le32_to_cpu(desc[0].data[3]);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "TQP_INT_ECC_INT_STS",
-				&hclge_tqp_int_ecc_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_tqp_int_ecc_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(desc[0].data[4]);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "MSIX_ECC_INT_STS",
-				&hclge_msix_sram_ecc_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_msix_sram_ecc_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log SSU(Storage Switch Unit) errors */
 	desc_data = (__le32 *)&desc[2];
 	status = le32_to_cpu(*(desc_data + 2));
-	if (status) {
-		dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_0 ssu_ecc_mbit_int[31:0]\n");
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+	if (status)
+		hclge_log_error(dev, "SSU_ECC_MULTI_BIT_INT_0",
+				&hclge_ssu_mem_ecc_err_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(*(desc_data + 3)) & BIT(0);
 	if (status) {
-		dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_ecc_mbit_int[32]\n");
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+		dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n",
+			 status);
+		set_bit(HNAE3_GLOBAL_RESET, &ae_dev->hw_err_reset_req);
 	}
 
 	status = le32_to_cpu(*(desc_data + 4)) & HCLGE_SSU_COMMON_ERR_INT_MASK;
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "SSU_COMMON_ERR_INT",
-				&hclge_ssu_com_err_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-	}
+				&hclge_ssu_com_err_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log IGU(Ingress Unit) errors */
 	desc_data = (__le32 *)&desc[3];
 	status = le32_to_cpu(*desc_data) & HCLGE_IGU_INT_MASK;
 	if (status)
 		hclge_log_error(dev, "IGU_INT_STS",
-				&hclge_igu_int[0], status);
+				&hclge_igu_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log PPP(Programmable Packet Process) errors */
 	desc_data = (__le32 *)&desc[4];
 	status = le32_to_cpu(*(desc_data + 1));
 	if (status)
 		hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST1",
-				&hclge_ppp_mpf_abnormal_int_st1[0], status);
+				&hclge_ppp_mpf_abnormal_int_st1[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPP_MPF_INT_ST3_MASK;
 	if (status)
 		hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST3",
-				&hclge_ppp_mpf_abnormal_int_st3[0], status);
+				&hclge_ppp_mpf_abnormal_int_st3[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log PPU(RCB) errors */
 	desc_data = (__le32 *)&desc[5];
@@ -877,61 +1210,53 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev,
 	if (status) {
 		dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST1 %s found\n",
 			 "rpu_rx_pkt_ecc_mbit_err");
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+		set_bit(HNAE3_GLOBAL_RESET, &ae_dev->hw_err_reset_req);
 	}
 
 	status = le32_to_cpu(*(desc_data + 2));
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
-				&hclge_ppu_mpf_abnormal_int_st2[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_ppu_mpf_abnormal_int_st2[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPU_MPF_INT_ST3_MASK;
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST3",
-				&hclge_ppu_mpf_abnormal_int_st3[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_ppu_mpf_abnormal_int_st3[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log TM(Traffic Manager) errors */
 	desc_data = (__le32 *)&desc[6];
 	status = le32_to_cpu(*desc_data);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "TM_SCH_RINT",
-				&hclge_tm_sch_rint[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_tm_sch_rint[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log QCN(Quantized Congestion Control) errors */
 	desc_data = (__le32 *)&desc[7];
 	status = le32_to_cpu(*desc_data) & HCLGE_QCN_FIFO_INT_MASK;
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "QCN_FIFO_RINT",
-				&hclge_qcn_fifo_rint[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_qcn_fifo_rint[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(*(desc_data + 1)) & HCLGE_QCN_ECC_INT_MASK;
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "QCN_ECC_RINT",
-				&hclge_qcn_ecc_rint[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_qcn_ecc_rint[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log NCSI errors */
 	desc_data = (__le32 *)&desc[9];
 	status = le32_to_cpu(*desc_data) & HCLGE_NCSI_ECC_INT_MASK;
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "NCSI_ECC_INT_RPT",
-				&hclge_ncsi_err_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
-	}
+				&hclge_ncsi_err_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* clear all main PF RAS errors */
 	hclge_cmd_reuse_desc(&desc[0], false);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
 	if (ret)
 		dev_err(dev, "clear all mpf ras int cmd failed (%d)\n", ret);
@@ -960,8 +1285,6 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev,
 	/* query all PF RAS errors */
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_PF_RAS_INT,
 				   true);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
 	if (ret) {
 		dev_err(dev, "query all pf ras int cmd failed (%d)\n", ret);
@@ -970,37 +1293,41 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev,
 
 	/* log SSU(Storage Switch Unit) errors */
 	status = le32_to_cpu(desc[0].data[0]);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
-				&hclge_ssu_port_based_err_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-	}
+				&hclge_ssu_port_based_err_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(desc[0].data[1]);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "SSU_FIFO_OVERFLOW_INT",
-				&hclge_ssu_fifo_overflow_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-	}
+				&hclge_ssu_fifo_overflow_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	status = le32_to_cpu(desc[0].data[2]);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "SSU_ETS_TCG_INT",
-				&hclge_ssu_ets_tcg_int[0], status);
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-	}
+				&hclge_ssu_ets_tcg_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* log IGU(Ingress Unit) EGU(Egress Unit) TNL errors */
 	desc_data = (__le32 *)&desc[1];
 	status = le32_to_cpu(*desc_data) & HCLGE_IGU_EGU_TNL_INT_MASK;
 	if (status)
 		hclge_log_error(dev, "IGU_EGU_TNL_INT_STS",
-				&hclge_igu_egu_tnl_int[0], status);
+				&hclge_igu_egu_tnl_int[0], status,
+				&ae_dev->hw_err_reset_req);
+
+	/* log PPU(RCB) errors */
+	desc_data = (__le32 *)&desc[3];
+	status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_RAS_MASK;
+	if (status)
+		hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST0",
+				&hclge_ppu_pf_abnormal_int[0], status,
+				&ae_dev->hw_err_reset_req);
 
 	/* clear all PF RAS errors */
 	hclge_cmd_reuse_desc(&desc[0], false);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
 	if (ret)
 		dev_err(dev, "clear all pf ras int cmd failed (%d)\n", ret);
@@ -1010,24 +1337,16 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev,
 
 static int hclge_handle_all_ras_errors(struct hclge_dev *hdev)
 {
-	struct device *dev = &hdev->pdev->dev;
 	u32 mpf_bd_num, pf_bd_num, bd_num;
-	struct hclge_desc desc_bd;
 	struct hclge_desc *desc;
 	int ret;
 
 	/* query the number of registers in the RAS int status */
-	hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_RAS_INT_STS_BD_NUM,
-				   true);
-	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
-	if (ret) {
-		dev_err(dev, "fail(%d) to query ras int status bd num\n", ret);
+	ret = hclge_query_bd_num(hdev, true, &mpf_bd_num, &pf_bd_num);
+	if (ret)
 		return ret;
-	}
-	mpf_bd_num = le32_to_cpu(desc_bd.data[0]);
-	pf_bd_num = le32_to_cpu(desc_bd.data[1]);
-	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
 
+	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
 	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
 	if (!desc)
 		return -ENOMEM;
@@ -1047,6 +1366,66 @@ static int hclge_handle_all_ras_errors(struct hclge_dev *hdev)
 	return ret;
 }
 
+static int hclge_log_rocee_axi_error(struct hclge_dev *hdev)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[3];
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_ROCEE_AXI_RAS_INFO_CMD,
+				   true);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_QUERY_ROCEE_AXI_RAS_INFO_CMD,
+				   true);
+	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_QUERY_ROCEE_AXI_RAS_INFO_CMD,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 3);
+	if (ret) {
+		dev_err(dev, "failed(%d) to query ROCEE AXI error sts\n", ret);
+		return ret;
+	}
+
+	dev_info(dev, "AXI1: %08X %08X %08X %08X %08X %08X\n",
+		 le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]),
+		 le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]),
+		 le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5]));
+	dev_info(dev, "AXI2: %08X %08X %08X %08X %08X %08X\n",
+		 le32_to_cpu(desc[1].data[0]), le32_to_cpu(desc[1].data[1]),
+		 le32_to_cpu(desc[1].data[2]), le32_to_cpu(desc[1].data[3]),
+		 le32_to_cpu(desc[1].data[4]), le32_to_cpu(desc[1].data[5]));
+	dev_info(dev, "AXI3: %08X %08X %08X %08X\n",
+		 le32_to_cpu(desc[2].data[0]), le32_to_cpu(desc[2].data[1]),
+		 le32_to_cpu(desc[2].data[2]), le32_to_cpu(desc[2].data[3]));
+
+	return 0;
+}
+
+static int hclge_log_rocee_ecc_error(struct hclge_dev *hdev)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	int ret;
+
+	ret = hclge_cmd_query_error(hdev, &desc[0],
+				    HCLGE_QUERY_ROCEE_ECC_RAS_INFO_CMD,
+				    HCLGE_CMD_FLAG_NEXT, 0, 0);
+	if (ret) {
+		dev_err(dev, "failed(%d) to query ROCEE ECC error sts\n", ret);
+		return ret;
+	}
+
+	dev_info(dev, "ECC1: %08X %08X %08X %08X %08X %08X\n",
+		 le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]),
+		 le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]),
+		 le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5]));
+	dev_info(dev, "ECC2: %08X %08X %08X\n", le32_to_cpu(desc[1].data[0]),
+		 le32_to_cpu(desc[1].data[1]), le32_to_cpu(desc[1].data[2]));
+
+	return 0;
+}
+
 static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev)
 {
 	struct device *dev = &hdev->pdev->dev;
@@ -1054,8 +1433,7 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev)
 	int ret;
 
 	/* read overflow error status */
-	ret = hclge_cmd_query_error(hdev, &desc[0],
-				    HCLGE_ROCEE_PF_RAS_INT_CMD,
+	ret = hclge_cmd_query_error(hdev, &desc[0], HCLGE_ROCEE_PF_RAS_INT_CMD,
 				    0, 0, 0);
 	if (ret) {
 		dev_err(dev, "failed(%d) to query ROCEE OVF error sts\n", ret);
@@ -1094,10 +1472,10 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev)
 	return 0;
 }
 
-static int hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
+static enum hnae3_reset_type
+hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
 {
-	enum hnae3_reset_type reset_type = HNAE3_FUNC_RESET;
-	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
+	enum hnae3_reset_type reset_type = HNAE3_NONE_RESET;
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc[2];
 	unsigned int status;
@@ -1110,21 +1488,32 @@ static int hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(dev, "failed(%d) to query ROCEE RAS INT SRC\n", ret);
 		/* reset everything for now */
-		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-		return ret;
+		return HNAE3_GLOBAL_RESET;
 	}
 
 	status = le32_to_cpu(desc[0].data[0]);
 
-	if (status & HCLGE_ROCEE_RERR_INT_MASK)
-		dev_warn(dev, "ROCEE RAS AXI rresp error\n");
+	if (status & HCLGE_ROCEE_AXI_ERR_INT_MASK) {
+		if (status & HCLGE_ROCEE_RERR_INT_MASK)
+			dev_warn(dev, "ROCEE RAS AXI rresp error\n");
+
+		if (status & HCLGE_ROCEE_BERR_INT_MASK)
+			dev_warn(dev, "ROCEE RAS AXI bresp error\n");
 
-	if (status & HCLGE_ROCEE_BERR_INT_MASK)
-		dev_warn(dev, "ROCEE RAS AXI bresp error\n");
+		reset_type = HNAE3_FUNC_RESET;
+
+		ret = hclge_log_rocee_axi_error(hdev);
+		if (ret)
+			return HNAE3_GLOBAL_RESET;
+	}
 
 	if (status & HCLGE_ROCEE_ECC_INT_MASK) {
 		dev_warn(dev, "ROCEE RAS 2bit ECC error\n");
 		reset_type = HNAE3_GLOBAL_RESET;
+
+		ret = hclge_log_rocee_ecc_error(hdev);
+		if (ret)
+			return HNAE3_GLOBAL_RESET;
 	}
 
 	if (status & HCLGE_ROCEE_OVF_INT_MASK) {
@@ -1132,8 +1521,7 @@ static int hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
 		if (ret) {
 			dev_err(dev, "failed(%d) to process ovf error\n", ret);
 			/* reset everything for now */
-			HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
-			return ret;
+			return HNAE3_GLOBAL_RESET;
 		}
 	}
 
@@ -1143,15 +1531,13 @@ static int hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
 	if (ret) {
 		dev_err(dev, "failed(%d) to clear ROCEE RAS error\n", ret);
 		/* reset everything for now */
-		reset_type = HNAE3_GLOBAL_RESET;
+		return HNAE3_GLOBAL_RESET;
 	}
 
-	HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type);
-
-	return ret;
+	return reset_type;
 }
 
-static int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en)
+int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
@@ -1178,15 +1564,18 @@ static int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
-static int hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev)
+static void hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev)
 {
+	enum hnae3_reset_type reset_type = HNAE3_NONE_RESET;
 	struct hclge_dev *hdev = ae_dev->priv;
 
 	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
 	    hdev->pdev->revision < 0x21)
-		return HNAE3_NONE_RESET;
+		return;
 
-	return hclge_log_and_clear_rocee_ras_error(hdev);
+	reset_type = hclge_log_and_clear_rocee_ras_error(hdev);
+	if (reset_type != HNAE3_NONE_RESET)
+		set_bit(reset_type, &ae_dev->hw_err_reset_req);
 }
 
 static const struct hclge_hw_blk hw_blk[] = {
@@ -1221,10 +1610,9 @@ static const struct hclge_hw_blk hw_blk[] = {
 	{ /* sentinel */ }
 };
 
-int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
+int hclge_config_nic_hw_error(struct hclge_dev *hdev, bool state)
 {
 	const struct hclge_hw_blk *module = hw_blk;
-	struct device *dev = &hdev->pdev->dev;
 	int ret = 0;
 
 	while (module->name) {
@@ -1236,10 +1624,6 @@ int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
 		module++;
 	}
 
-	ret = hclge_config_rocee_ras_interrupt(hdev, state);
-	if (ret)
-		dev_err(dev, "fail(%d) to configure ROCEE err int\n", ret);
-
 	return ret;
 }
 
@@ -1249,160 +1633,303 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 	struct device *dev = &hdev->pdev->dev;
 	u32 status;
 
+	if (!test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state)) {
+		dev_err(dev,
+			"Can't recover - RAS error reported during dev init\n");
+		return PCI_ERS_RESULT_NONE;
+	}
+
 	status = hclge_read_dev(&hdev->hw, HCLGE_RAS_PF_OTHER_INT_STS_REG);
 
+	if (status & HCLGE_RAS_REG_NFE_MASK ||
+	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK)
+		ae_dev->hw_err_reset_req = 0;
+	else
+		goto out;
+
 	/* Handling Non-fatal HNS RAS errors */
 	if (status & HCLGE_RAS_REG_NFE_MASK) {
 		dev_warn(dev,
 			 "HNS Non-Fatal RAS error(status=0x%x) identified\n",
 			 status);
 		hclge_handle_all_ras_errors(hdev);
-	} else {
-		if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
-		    hdev->pdev->revision < 0x21)
-			return PCI_ERS_RESULT_RECOVERED;
 	}
 
-	if (status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
-		dev_warn(dev, "ROCEE uncorrected RAS error identified\n");
+	/* Handling Non-fatal Rocee RAS errors */
+	if (hdev->pdev->revision >= 0x21 &&
+	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
+		dev_warn(dev, "ROCEE Non-Fatal RAS error identified\n");
 		hclge_handle_rocee_ras_error(ae_dev);
 	}
 
-	if (status & HCLGE_RAS_REG_NFE_MASK ||
-	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK)
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+		goto out;
+
+	if (ae_dev->hw_err_reset_req)
 		return PCI_ERS_RESULT_NEED_RESET;
 
+out:
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
-			       unsigned long *reset_requests)
+static int hclge_clear_hw_msix_error(struct hclge_dev *hdev,
+				     struct hclge_desc *desc, bool is_mpf,
+				     u32 bd_num)
 {
-	struct device *dev = &hdev->pdev->dev;
-	u32 mpf_bd_num, pf_bd_num, bd_num;
-	struct hclge_desc desc_bd;
-	struct hclge_desc *desc;
-	__le32 *desc_data;
-	int ret = 0;
-	u32 status;
+	if (is_mpf)
+		desc[0].opcode =
+			cpu_to_le16(HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT);
+	else
+		desc[0].opcode = cpu_to_le16(HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT);
 
-	/* set default handling */
-	set_bit(HNAE3_FUNC_RESET, reset_requests);
+	desc[0].flag = cpu_to_le16(HCLGE_CMD_FLAG_NO_INTR | HCLGE_CMD_FLAG_IN);
 
-	/* query the number of bds for the MSIx int status */
-	hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_MSIX_INT_STS_BD_NUM,
-				   true);
-	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
+	return hclge_cmd_send(&hdev->hw, &desc[0], bd_num);
+}
+
+/* hclge_query_8bd_info: query information about over_8bd_nfe_err
+ * @hdev: pointer to struct hclge_dev
+ * @vf_id: Index of the virtual function with error
+ * @q_id: Physical index of the queue with error
+ *
+ * This function get specific index of queue and function which causes
+ * over_8bd_nfe_err by using command. If vf_id is 0, it means error is
+ * caused by PF instead of VF.
+ */
+static int hclge_query_over_8bd_err_info(struct hclge_dev *hdev, u16 *vf_id,
+					 u16 *q_id)
+{
+	struct hclge_query_ppu_pf_other_int_dfx_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PPU_PF_OTHER_INT_DFX, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		return ret;
+
+	req = (struct hclge_query_ppu_pf_other_int_dfx_cmd *)desc.data;
+	*vf_id = le16_to_cpu(req->over_8bd_no_fe_vf_id);
+	*q_id = le16_to_cpu(req->over_8bd_no_fe_qid);
+
+	return 0;
+}
+
+/* hclge_handle_over_8bd_err: handle MSI-X error named over_8bd_nfe_err
+ * @hdev: pointer to struct hclge_dev
+ * @reset_requests: reset level that we need to trigger later
+ *
+ * over_8bd_nfe_err is a special MSI-X because it may caused by a VF, in
+ * that case, we need to trigger VF reset. Otherwise, a PF reset is needed.
+ */
+static void hclge_handle_over_8bd_err(struct hclge_dev *hdev,
+				      unsigned long *reset_requests)
+{
+	struct device *dev = &hdev->pdev->dev;
+	u16 vf_id;
+	u16 q_id;
+	int ret;
+
+	ret = hclge_query_over_8bd_err_info(hdev, &vf_id, &q_id);
 	if (ret) {
-		dev_err(dev, "fail(%d) to query msix int status bd num\n",
+		dev_err(dev, "fail(%d) to query over_8bd_no_fe info\n",
 			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
-		return ret;
+		return;
 	}
 
-	mpf_bd_num = le32_to_cpu(desc_bd.data[0]);
-	pf_bd_num = le32_to_cpu(desc_bd.data[1]);
-	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
+	dev_warn(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vf_id(%d), queue_id(%d)\n",
+		 vf_id, q_id);
 
-	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
-	if (!desc)
-		goto out;
+	if (vf_id) {
+		if (vf_id >= hdev->num_alloc_vport) {
+			dev_err(dev, "invalid vf id(%d)\n", vf_id);
+			return;
+		}
+
+		/* If we need to trigger other reset whose level is higher
+		 * than HNAE3_VF_FUNC_RESET, no need to trigger a VF reset
+		 * here.
+		 */
+		if (*reset_requests != 0)
+			return;
+
+		ret = hclge_inform_reset_assert_to_vf(&hdev->vport[vf_id]);
+		if (ret)
+			dev_warn(dev, "inform reset to vf(%d) failed %d!\n",
+				 hdev->vport->vport_id, ret);
+	} else {
+		set_bit(HNAE3_FUNC_RESET, reset_requests);
+	}
+}
 
+/* hclge_handle_mpf_msix_error: handle all main PF MSI-X errors
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @mpf_bd_num: number of extended command structures
+ * @reset_requests: record of the reset level that we need
+ *
+ * This function handles all the main PF MSI-X errors in the hw register/s
+ * using command.
+ */
+static int hclge_handle_mpf_msix_error(struct hclge_dev *hdev,
+				       struct hclge_desc *desc,
+				       int mpf_bd_num,
+				       unsigned long *reset_requests)
+{
+	struct device *dev = &hdev->pdev->dev;
+	__le32 *desc_data;
+	u32 status;
+	int ret;
 	/* query all main PF MSIx errors */
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT,
 				   true);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], mpf_bd_num);
 	if (ret) {
-		dev_err(dev, "query all mpf msix int cmd failed (%d)\n",
-			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
-		goto msi_error;
+		dev_err(dev, "query all mpf msix int cmd failed (%d)\n", ret);
+		return ret;
 	}
 
 	/* log MAC errors */
 	desc_data = (__le32 *)&desc[1];
 	status = le32_to_cpu(*desc_data);
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "MAC_AFIFO_TNL_INT_R",
-				&hclge_mac_afifo_tnl_int[0], status);
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
-	}
+				&hclge_mac_afifo_tnl_int[0], status,
+				reset_requests);
 
-	/* log PPU(RCB) errors */
+	/* log PPU(RCB) MPF errors */
 	desc_data = (__le32 *)&desc[5];
 	status = le32_to_cpu(*(desc_data + 2)) &
 			HCLGE_PPU_MPF_INT_ST2_MSIX_MASK;
-	if (status) {
-		dev_warn(dev,
-			 "PPU_MPF_ABNORMAL_INT_ST2[28:29], err_status(0x%x)\n",
+	if (status)
+		dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST2 rx_q_search_miss found [dfx status=0x%x\n]",
 			 status);
-		set_bit(HNAE3_CORE_RESET, reset_requests);
-	}
 
 	/* clear all main PF MSIx errors */
-	hclge_cmd_reuse_desc(&desc[0], false);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	ret = hclge_clear_hw_msix_error(hdev, desc, true, mpf_bd_num);
+	if (ret)
+		dev_err(dev, "clear all mpf msix int cmd failed (%d)\n", ret);
 
-	ret = hclge_cmd_send(&hdev->hw, &desc[0], mpf_bd_num);
-	if (ret) {
-		dev_err(dev, "clear all mpf msix int cmd failed (%d)\n",
-			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
-		goto msi_error;
-	}
+	return ret;
+}
+
+/* hclge_handle_pf_msix_error: handle all PF MSI-X errors
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @mpf_bd_num: number of extended command structures
+ * @reset_requests: record of the reset level that we need
+ *
+ * This function handles all the PF MSI-X errors in the hw register/s using
+ * command.
+ */
+static int hclge_handle_pf_msix_error(struct hclge_dev *hdev,
+				      struct hclge_desc *desc,
+				      int pf_bd_num,
+				      unsigned long *reset_requests)
+{
+	struct device *dev = &hdev->pdev->dev;
+	__le32 *desc_data;
+	u32 status;
+	int ret;
 
 	/* query all PF MSIx errors */
-	memset(desc, 0, bd_num * sizeof(struct hclge_desc));
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT,
 				   true);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], pf_bd_num);
 	if (ret) {
-		dev_err(dev, "query all pf msix int cmd failed (%d)\n",
-			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
-		goto msi_error;
+		dev_err(dev, "query all pf msix int cmd failed (%d)\n", ret);
+		return ret;
 	}
 
 	/* log SSU PF errors */
 	status = le32_to_cpu(desc[0].data[0]) & HCLGE_SSU_PORT_INT_MSIX_MASK;
-	if (status) {
+	if (status)
 		hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
-				&hclge_ssu_port_based_pf_int[0], status);
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
-	}
+				&hclge_ssu_port_based_pf_int[0],
+				status, reset_requests);
 
 	/* read and log PPP PF errors */
 	desc_data = (__le32 *)&desc[2];
 	status = le32_to_cpu(*desc_data);
 	if (status)
 		hclge_log_error(dev, "PPP_PF_ABNORMAL_INT_ST0",
-				&hclge_ppp_pf_abnormal_int[0], status);
+				&hclge_ppp_pf_abnormal_int[0],
+				status, reset_requests);
 
-	/* PPU(RCB) PF errors */
+	/* log PPU(RCB) PF errors */
 	desc_data = (__le32 *)&desc[3];
 	status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_MSIX_MASK;
 	if (status)
 		hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST",
-				&hclge_ppu_pf_abnormal_int[0], status);
+				&hclge_ppu_pf_abnormal_int[0],
+				status, reset_requests);
+
+	status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_OVER_8BD_ERR_MASK;
+	if (status)
+		hclge_handle_over_8bd_err(hdev, reset_requests);
 
 	/* clear all PF MSIx errors */
-	hclge_cmd_reuse_desc(&desc[0], false);
-	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	ret = hclge_clear_hw_msix_error(hdev, desc, false, pf_bd_num);
+	if (ret)
+		dev_err(dev, "clear all pf msix int cmd failed (%d)\n", ret);
 
-	ret = hclge_cmd_send(&hdev->hw, &desc[0], pf_bd_num);
+	return ret;
+}
+
+static int hclge_handle_all_hw_msix_error(struct hclge_dev *hdev,
+					  unsigned long *reset_requests)
+{
+	struct hclge_mac_tnl_stats mac_tnl_stats;
+	struct device *dev = &hdev->pdev->dev;
+	u32 mpf_bd_num, pf_bd_num, bd_num;
+	struct hclge_desc *desc;
+	u32 status;
+	int ret;
+
+	/* query the number of bds for the MSIx int status */
+	ret = hclge_query_bd_num(hdev, false, &mpf_bd_num, &pf_bd_num);
+	if (ret)
+		goto out;
+
+	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
+	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = hclge_handle_mpf_msix_error(hdev, desc, mpf_bd_num,
+					  reset_requests);
+	if (ret)
+		goto msi_error;
+
+	memset(desc, 0, bd_num * sizeof(struct hclge_desc));
+	ret = hclge_handle_pf_msix_error(hdev, desc, pf_bd_num, reset_requests);
+	if (ret)
+		goto msi_error;
+
+	/* query and clear mac tnl interruptions */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_MAC_TNL_INT,
+				   true);
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 1);
 	if (ret) {
-		dev_err(dev, "clear all pf msix int cmd failed (%d)\n",
-			ret);
-		/* reset everything for now */
-		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		dev_err(dev, "query mac tnl int cmd failed (%d)\n", ret);
+		goto msi_error;
+	}
+
+	status = le32_to_cpu(desc->data[0]);
+	if (status) {
+		/* When mac tnl interrupt occurs, we record current time and
+		 * register status here in a fifo, then clear the status. So
+		 * that if link status changes suddenly at some time, we can
+		 * query them by debugfs.
+		 */
+		mac_tnl_stats.time = local_clock();
+		mac_tnl_stats.status = status;
+		kfifo_put(&hdev->mac_tnl_log, mac_tnl_stats);
+		ret = hclge_clear_mac_tnl_int(hdev);
+		if (ret)
+			dev_err(dev, "clear mac tnl int failed (%d)\n", ret);
 	}
 
 msi_error:
@@ -1410,3 +1937,70 @@ msi_error:
 out:
 	return ret;
 }
+
+int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
+			       unsigned long *reset_requests)
+{
+	struct device *dev = &hdev->pdev->dev;
+
+	if (!test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state)) {
+		dev_err(dev,
+			"Can't handle - MSIx error reported during dev init\n");
+		return 0;
+	}
+
+	return hclge_handle_all_hw_msix_error(hdev, reset_requests);
+}
+
+void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev)
+{
+#define HCLGE_DESC_NO_DATA_LEN 8
+
+	struct hclge_dev *hdev = ae_dev->priv;
+	struct device *dev = &hdev->pdev->dev;
+	u32 mpf_bd_num, pf_bd_num, bd_num;
+	struct hclge_desc *desc;
+	u32 status;
+	int ret;
+
+	ae_dev->hw_err_reset_req = 0;
+	status = hclge_read_dev(&hdev->hw, HCLGE_RAS_PF_OTHER_INT_STS_REG);
+
+	/* query the number of bds for the MSIx int status */
+	ret = hclge_query_bd_num(hdev, false, &mpf_bd_num, &pf_bd_num);
+	if (ret)
+		return;
+
+	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
+	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		return;
+
+	/* Clear HNS hw errors reported through msix  */
+	memset(&desc[0].data[0], 0xFF, mpf_bd_num * sizeof(struct hclge_desc) -
+	       HCLGE_DESC_NO_DATA_LEN);
+	ret = hclge_clear_hw_msix_error(hdev, desc, true, mpf_bd_num);
+	if (ret) {
+		dev_err(dev, "fail(%d) to clear mpf msix int during init\n",
+			ret);
+		goto msi_error;
+	}
+
+	memset(&desc[0].data[0], 0xFF, pf_bd_num * sizeof(struct hclge_desc) -
+	       HCLGE_DESC_NO_DATA_LEN);
+	ret = hclge_clear_hw_msix_error(hdev, desc, false, pf_bd_num);
+	if (ret) {
+		dev_err(dev, "fail(%d) to clear pf msix int during init\n",
+			ret);
+		goto msi_error;
+	}
+
+	/* Handle Non-fatal HNS RAS errors */
+	if (status & HCLGE_RAS_REG_NFE_MASK) {
+		dev_warn(dev, "HNS hw error(RAS) identified during init\n");
+		hclge_handle_all_ras_errors(hdev);
+	}
+
+msi_error:
+	kfree(desc);
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 51a7d4eb066a..7ea8bb28a0cb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -6,6 +6,11 @@
 
 #include "hclge_main.h"
 
+#define HCLGE_MPF_RAS_INT_MIN_BD_NUM	10
+#define HCLGE_PF_RAS_INT_MIN_BD_NUM	4
+#define HCLGE_MPF_MSIX_INT_MIN_BD_NUM	10
+#define HCLGE_PF_MSIX_INT_MIN_BD_NUM	4
+
 #define HCLGE_RAS_PF_OTHER_INT_STS_REG   0x20B00
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
 #define HCLGE_RAS_REG_ROCEE_ERR_MASK   0x3000000
@@ -45,8 +50,11 @@
 #define HCLGE_TM_QCN_MEM_ERR_INT_EN	0xFFFFFF
 #define HCLGE_NCSI_ERR_INT_EN	0x3
 #define HCLGE_NCSI_ERR_INT_TYPE	0x9
-#define HCLGE_MAC_COMMON_ERR_INT_EN		GENMASK(7, 0)
-#define HCLGE_MAC_COMMON_ERR_INT_EN_MASK	GENMASK(7, 0)
+#define HCLGE_MAC_COMMON_ERR_INT_EN		0x107FF
+#define HCLGE_MAC_COMMON_ERR_INT_EN_MASK	0x107FF
+#define HCLGE_MAC_TNL_INT_EN			GENMASK(9, 0)
+#define HCLGE_MAC_TNL_INT_EN_MASK		GENMASK(9, 0)
+#define HCLGE_MAC_TNL_INT_CLR			GENMASK(9, 0)
 #define HCLGE_PPU_MPF_ABNORMAL_INT0_EN		GENMASK(31, 0)
 #define HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK	GENMASK(31, 0)
 #define HCLGE_PPU_MPF_ABNORMAL_INT1_EN		GENMASK(31, 0)
@@ -78,8 +86,10 @@
 #define HCLGE_IGU_EGU_TNL_INT_MASK	GENMASK(5, 0)
 #define HCLGE_PPP_MPF_INT_ST3_MASK	GENMASK(5, 0)
 #define HCLGE_PPU_MPF_INT_ST3_MASK	GENMASK(7, 0)
-#define HCLGE_PPU_MPF_INT_ST2_MSIX_MASK	GENMASK(29, 28)
-#define HCLGE_PPU_PF_INT_MSIX_MASK	0x27
+#define HCLGE_PPU_MPF_INT_ST2_MSIX_MASK	BIT(29)
+#define HCLGE_PPU_PF_INT_RAS_MASK	0x18
+#define HCLGE_PPU_PF_INT_MSIX_MASK	0x26
+#define HCLGE_PPU_PF_OVER_8BD_ERR_MASK	0x01
 #define HCLGE_QCN_FIFO_INT_MASK		GENMASK(17, 0)
 #define HCLGE_QCN_ECC_INT_MASK		GENMASK(21, 0)
 #define HCLGE_NCSI_ECC_INT_MASK		GENMASK(1, 0)
@@ -90,6 +100,7 @@
 #define HCLGE_ROCEE_RAS_CE_INT_EN_MASK		0x1
 #define HCLGE_ROCEE_RERR_INT_MASK		BIT(0)
 #define HCLGE_ROCEE_BERR_INT_MASK		BIT(1)
+#define HCLGE_ROCEE_AXI_ERR_INT_MASK		GENMASK(1, 0)
 #define HCLGE_ROCEE_ECC_INT_MASK		BIT(2)
 #define HCLGE_ROCEE_OVF_INT_MASK		BIT(3)
 #define HCLGE_ROCEE_OVF_ERR_INT_MASK		0x10000
@@ -111,9 +122,13 @@ struct hclge_hw_blk {
 struct hclge_hw_error {
 	u32 int_msk;
 	const char *msg;
+	enum hnae3_reset_type reset_level;
 };
 
-int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
+int hclge_config_mac_tnl_int(struct hclge_dev *hdev, bool en);
+int hclge_config_nic_hw_error(struct hclge_dev *hdev, bool state);
+int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en);
+void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev);
 pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev);
 int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
 			       unsigned long *reset_requests);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index f7637c08bb3a..3fde5471e1c0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -12,6 +12,7 @@
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/if_vlan.h>
+#include <linux/crash_dump.h>
 #include <net/rtnetlink.h>
 #include "hclge_cmd.h"
 #include "hclge_dcb.h"
@@ -26,13 +27,26 @@
 #define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
 #define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f))
 
-#define HCLGE_BUF_SIZE_UNIT	256
+#define HCLGE_BUF_SIZE_UNIT	256U
+#define HCLGE_BUF_MUL_BY	2
+#define HCLGE_BUF_DIV_BY	2
+#define NEED_RESERVE_TC_NUM	2
+#define BUF_MAX_PERCENT		100
+#define BUF_RESERVE_PERCENT	90
+
+#define HCLGE_RESET_MAX_FAIL_CNT	5
 
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
+static void hclge_sync_vlan_filter(struct hclge_dev *hdev);
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
+static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle);
 static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
 			       u16 *allocated_size, bool is_alloc);
+static void hclge_rfs_filter_expire(struct hclge_dev *hdev);
+static void hclge_clear_arfs_rules(struct hnae3_handle *handle);
+static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
+						   unsigned long *addr);
 
 static struct hnae3_ae_algo ae_algo;
 
@@ -118,6 +132,12 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = {
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_mac_pause_num)},
 	{"mac_rx_mac_pause_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_mac_pause_num)},
+	{"mac_tx_control_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_ctrl_pkt_num)},
+	{"mac_rx_control_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_ctrl_pkt_num)},
+	{"mac_tx_pfc_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pause_pkt_num)},
 	{"mac_tx_pfc_pri0_pkt_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri0_pkt_num)},
 	{"mac_tx_pfc_pri1_pkt_num",
@@ -134,6 +154,8 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = {
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri6_pkt_num)},
 	{"mac_tx_pfc_pri7_pkt_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri7_pkt_num)},
+	{"mac_rx_pfc_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pause_pkt_num)},
 	{"mac_rx_pfc_pri0_pkt_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri0_pkt_num)},
 	{"mac_rx_pfc_pri1_pkt_num",
@@ -280,17 +302,24 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = {
 static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = {
 	{
 		.flags = HCLGE_MAC_MGR_MASK_VLAN_B,
-		.ethter_type = cpu_to_le16(HCLGE_MAC_ETHERTYPE_LLDP),
+		.ethter_type = cpu_to_le16(ETH_P_LLDP),
 		.mac_addr_hi32 = cpu_to_le32(htonl(0x0180C200)),
 		.mac_addr_lo16 = cpu_to_le16(htons(0x000E)),
 		.i_port_bitmap = 0x1,
 	},
 };
 
-static int hclge_mac_update_stats(struct hclge_dev *hdev)
+static const u8 hclge_hash_key[] = {
+	0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2,
+	0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0,
+	0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4,
+	0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C,
+	0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA
+};
+
+static int hclge_mac_update_stats_defective(struct hclge_dev *hdev)
 {
 #define HCLGE_MAC_CMD_NUM 21
-#define HCLGE_RTN_DATA_NUM 4
 
 	u64 *data = (u64 *)(&hdev->hw_stats.mac_stats);
 	struct hclge_desc desc[HCLGE_MAC_CMD_NUM];
@@ -308,22 +337,104 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev)
 	}
 
 	for (i = 0; i < HCLGE_MAC_CMD_NUM; i++) {
+		/* for special opcode 0032, only the first desc has the head */
 		if (unlikely(i == 0)) {
 			desc_data = (__le64 *)(&desc[i].data[0]);
-			n = HCLGE_RTN_DATA_NUM - 2;
+			n = HCLGE_RD_FIRST_STATS_NUM;
+		} else {
+			desc_data = (__le64 *)(&desc[i]);
+			n = HCLGE_RD_OTHER_STATS_NUM;
+		}
+
+		for (k = 0; k < n; k++) {
+			*data += le64_to_cpu(*desc_data);
+			data++;
+			desc_data++;
+		}
+	}
+
+	return 0;
+}
+
+static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num)
+{
+	u64 *data = (u64 *)(&hdev->hw_stats.mac_stats);
+	struct hclge_desc *desc;
+	__le64 *desc_data;
+	u16 i, k, n;
+	int ret;
+
+	desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, desc_num);
+	if (ret) {
+		kfree(desc);
+		return ret;
+	}
+
+	for (i = 0; i < desc_num; i++) {
+		/* for special opcode 0034, only the first desc has the head */
+		if (i == 0) {
+			desc_data = (__le64 *)(&desc[i].data[0]);
+			n = HCLGE_RD_FIRST_STATS_NUM;
 		} else {
 			desc_data = (__le64 *)(&desc[i]);
-			n = HCLGE_RTN_DATA_NUM;
+			n = HCLGE_RD_OTHER_STATS_NUM;
 		}
+
 		for (k = 0; k < n; k++) {
-			*data++ += le64_to_cpu(*desc_data);
+			*data += le64_to_cpu(*desc_data);
+			data++;
 			desc_data++;
 		}
 	}
 
+	kfree(desc);
+
+	return 0;
+}
+
+static int hclge_mac_query_reg_num(struct hclge_dev *hdev, u32 *desc_num)
+{
+	struct hclge_desc desc;
+	__le32 *desc_data;
+	u32 reg_num;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_MAC_REG_NUM, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		return ret;
+
+	desc_data = (__le32 *)(&desc.data[0]);
+	reg_num = le32_to_cpu(*desc_data);
+
+	*desc_num = 1 + ((reg_num - 3) >> 2) +
+		    (u32)(((reg_num - 3) & 0x3) ? 1 : 0);
+
 	return 0;
 }
 
+static int hclge_mac_update_stats(struct hclge_dev *hdev)
+{
+	u32 desc_num;
+	int ret;
+
+	ret = hclge_mac_query_reg_num(hdev, &desc_num);
+
+	/* The firmware supports the new statistics acquisition method */
+	if (!ret)
+		ret = hclge_mac_update_stats_complete(hdev, desc_num);
+	else if (ret == -EOPNOTSUPP)
+		ret = hclge_mac_update_stats_defective(hdev);
+	else
+		dev_err(&hdev->pdev->dev, "query mac reg num fail!\n");
+
+	return ret;
+}
+
 static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
@@ -338,8 +449,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 		queue = handle->kinfo.tqp[i];
 		tqp = container_of(queue, struct hclge_tqp, q);
 		/* command : HCLGE_OPC_QUERY_IGU_STAT */
-		hclge_cmd_setup_basic_desc(&desc[0],
-					   HCLGE_OPC_QUERY_RX_STATUS,
+		hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_RX_STATUS,
 					   true);
 
 		desc[0].data[0] = cpu_to_le32((tqp->index & 0x1ff));
@@ -347,7 +457,7 @@ static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
 				"Query tqp stat fail, status = %d,queue = %d\n",
-				ret,	i);
+				ret, i);
 			return ret;
 		}
 		tqp->tqp_stats.rcb_rx_ring_pktnum_rcd +=
@@ -401,6 +511,7 @@ static int hclge_tqps_get_sset_count(struct hnae3_handle *handle, int stringset)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 
+	/* each tqp has TX & RX two queues */
 	return kinfo->num_tqps * (2);
 }
 
@@ -429,7 +540,7 @@ static u8 *hclge_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
 	return buff;
 }
 
-static u64 *hclge_comm_get_stats(void *comm_stats,
+static u64 *hclge_comm_get_stats(const void *comm_stats,
 				 const struct hclge_comm_stats_str strs[],
 				 int size, u64 *data)
 {
@@ -453,34 +564,13 @@ static u8 *hclge_comm_get_strings(u32 stringset,
 		return buff;
 
 	for (i = 0; i < size; i++) {
-		snprintf(buff, ETH_GSTRING_LEN,
-			 strs[i].desc);
+		snprintf(buff, ETH_GSTRING_LEN, "%s", strs[i].desc);
 		buff = buff + ETH_GSTRING_LEN;
 	}
 
 	return (u8 *)buff;
 }
 
-static void hclge_update_netstat(struct hclge_hw_stats *hw_stats,
-				 struct net_device_stats *net_stats)
-{
-	net_stats->tx_dropped = 0;
-	net_stats->rx_errors = hw_stats->mac_stats.mac_rx_oversize_pkt_num;
-	net_stats->rx_errors += hw_stats->mac_stats.mac_rx_undersize_pkt_num;
-	net_stats->rx_errors += hw_stats->mac_stats.mac_rx_fcs_err_pkt_num;
-
-	net_stats->multicast = hw_stats->mac_stats.mac_tx_multi_pkt_num;
-	net_stats->multicast += hw_stats->mac_stats.mac_rx_multi_pkt_num;
-
-	net_stats->rx_crc_errors = hw_stats->mac_stats.mac_rx_fcs_err_pkt_num;
-	net_stats->rx_length_errors =
-		hw_stats->mac_stats.mac_rx_undersize_pkt_num;
-	net_stats->rx_length_errors +=
-		hw_stats->mac_stats.mac_rx_oversize_pkt_num;
-	net_stats->rx_over_errors =
-		hw_stats->mac_stats.mac_rx_oversize_pkt_num;
-}
-
 static void hclge_update_stats_for_all(struct hclge_dev *hdev)
 {
 	struct hnae3_handle *handle;
@@ -500,8 +590,6 @@ static void hclge_update_stats_for_all(struct hclge_dev *hdev)
 	if (status)
 		dev_err(&hdev->pdev->dev,
 			"Update MAC stats fail, status = %d.\n", status);
-
-	hclge_update_netstat(&hdev->hw_stats, &handle->kinfo.netdev->stats);
 }
 
 static void hclge_update_stats(struct hnae3_handle *handle,
@@ -509,7 +597,6 @@ static void hclge_update_stats(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_hw_stats *hw_stats = &hdev->hw_stats;
 	int status;
 
 	if (test_and_set_bit(HCLGE_STATE_STATISTICS_UPDATING, &hdev->state))
@@ -527,8 +614,6 @@ static void hclge_update_stats(struct hnae3_handle *handle,
 			"Update TQPS stats fail, status = %d.\n",
 			status);
 
-	hclge_update_netstat(hw_stats, net_stats);
-
 	clear_bit(HCLGE_STATE_STATISTICS_UPDATING, &hdev->state);
 }
 
@@ -570,8 +655,7 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset)
 	return count;
 }
 
-static void hclge_get_strings(struct hnae3_handle *handle,
-			      u32 stringset,
+static void hclge_get_strings(struct hnae3_handle *handle, u32 stringset,
 			      u8 *data)
 {
 	u8 *p = (char *)data;
@@ -579,21 +663,17 @@ static void hclge_get_strings(struct hnae3_handle *handle,
 
 	if (stringset == ETH_SS_STATS) {
 		size = ARRAY_SIZE(g_mac_stats_string);
-		p = hclge_comm_get_strings(stringset,
-					   g_mac_stats_string,
-					   size,
-					   p);
+		p = hclge_comm_get_strings(stringset, g_mac_stats_string,
+					   size, p);
 		p = hclge_tqps_get_strings(handle, p);
 	} else if (stringset == ETH_SS_TEST) {
 		if (handle->flags & HNAE3_SUPPORT_APP_LOOPBACK) {
-			memcpy(p,
-			       hns3_nic_test_strs[HNAE3_LOOP_APP],
+			memcpy(p, hns3_nic_test_strs[HNAE3_LOOP_APP],
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
 		if (handle->flags & HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK) {
-			memcpy(p,
-			       hns3_nic_test_strs[HNAE3_LOOP_SERIAL_SERDES],
+			memcpy(p, hns3_nic_test_strs[HNAE3_LOOP_SERIAL_SERDES],
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
@@ -604,8 +684,7 @@ static void hclge_get_strings(struct hnae3_handle *handle,
 			p += ETH_GSTRING_LEN;
 		}
 		if (handle->flags & HNAE3_SUPPORT_PHY_LOOPBACK) {
-			memcpy(p,
-			       hns3_nic_test_strs[HNAE3_LOOP_PHY],
+			memcpy(p, hns3_nic_test_strs[HNAE3_LOOP_PHY],
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
@@ -618,13 +697,21 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data)
 	struct hclge_dev *hdev = vport->back;
 	u64 *p;
 
-	p = hclge_comm_get_stats(&hdev->hw_stats.mac_stats,
-				 g_mac_stats_string,
-				 ARRAY_SIZE(g_mac_stats_string),
-				 data);
+	p = hclge_comm_get_stats(&hdev->hw_stats.mac_stats, g_mac_stats_string,
+				 ARRAY_SIZE(g_mac_stats_string), data);
 	p = hclge_tqps_get_stats(handle, p);
 }
 
+static void hclge_get_mac_pause_stat(struct hnae3_handle *handle, u64 *tx_cnt,
+				     u64 *rx_cnt)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	*tx_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num;
+	*rx_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num;
+}
+
 static int hclge_parse_func_status(struct hclge_dev *hdev,
 				   struct hclge_func_status_cmd *status)
 {
@@ -642,6 +729,8 @@ static int hclge_parse_func_status(struct hclge_dev *hdev,
 
 static int hclge_query_function_status(struct hclge_dev *hdev)
 {
+#define HCLGE_QUERY_MAX_CNT	5
+
 	struct hclge_func_status_cmd *req;
 	struct hclge_desc desc;
 	int timeout = 0;
@@ -654,9 +743,7 @@ static int hclge_query_function_status(struct hclge_dev *hdev)
 		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
-				"query function status failed %d.\n",
-				ret);
-
+				"query function status failed %d.\n", ret);
 			return ret;
 		}
 
@@ -664,7 +751,7 @@ static int hclge_query_function_status(struct hclge_dev *hdev)
 		if (req->pf_state)
 			break;
 		usleep_range(1000, 2000);
-	} while (timeout++ < 5);
+	} while (timeout++ < HCLGE_QUERY_MAX_CNT);
 
 	ret = hclge_parse_func_status(hdev, req);
 
@@ -716,7 +803,7 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		/* PF should have NIC vectors and Roce vectors,
 		 * NIC vectors are queued before Roce vectors.
 		 */
-		hdev->num_msi = hdev->num_roce_msi  +
+		hdev->num_msi = hdev->num_roce_msi +
 				hdev->roce_base_msix_offset;
 	} else {
 		hdev->num_msi =
@@ -761,51 +848,239 @@ static int hclge_parse_speed(int speed_cmd, int *speed)
 	return 0;
 }
 
-static void hclge_parse_fiber_link_mode(struct hclge_dev *hdev,
-					u8 speed_ability)
+static int hclge_check_port_speed(struct hnae3_handle *handle, u32 speed)
 {
-	unsigned long *supported = hdev->hw.mac.supported;
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	u32 speed_ability = hdev->hw.mac.speed_ability;
+	u32 speed_bit = 0;
 
-	if (speed_ability & HCLGE_SUPPORT_1G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
-			supported);
+	switch (speed) {
+	case HCLGE_MAC_SPEED_10M:
+		speed_bit = HCLGE_SUPPORT_10M_BIT;
+		break;
+	case HCLGE_MAC_SPEED_100M:
+		speed_bit = HCLGE_SUPPORT_100M_BIT;
+		break;
+	case HCLGE_MAC_SPEED_1G:
+		speed_bit = HCLGE_SUPPORT_1G_BIT;
+		break;
+	case HCLGE_MAC_SPEED_10G:
+		speed_bit = HCLGE_SUPPORT_10G_BIT;
+		break;
+	case HCLGE_MAC_SPEED_25G:
+		speed_bit = HCLGE_SUPPORT_25G_BIT;
+		break;
+	case HCLGE_MAC_SPEED_40G:
+		speed_bit = HCLGE_SUPPORT_40G_BIT;
+		break;
+	case HCLGE_MAC_SPEED_50G:
+		speed_bit = HCLGE_SUPPORT_50G_BIT;
+		break;
+	case HCLGE_MAC_SPEED_100G:
+		speed_bit = HCLGE_SUPPORT_100G_BIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (speed_bit & speed_ability)
+		return 0;
 
+	return -EINVAL;
+}
+
+static void hclge_convert_setting_sr(struct hclge_mac *mac, u8 speed_ability)
+{
 	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_25G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_40G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_50G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+				 mac->supported);
+}
 
+static void hclge_convert_setting_lr(struct hclge_mac *mac, u8 speed_ability)
+{
+	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
+				 mac->supported);
 	if (speed_ability & HCLGE_SUPPORT_25G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_50G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_40G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+				 mac->supported);
+}
 
+static void hclge_convert_setting_cr(struct hclge_mac *mac, u8 speed_ability)
+{
+	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_25G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_40G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+				 mac->supported);
 	if (speed_ability & HCLGE_SUPPORT_50G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+				 mac->supported);
+}
 
+static void hclge_convert_setting_kr(struct hclge_mac *mac, u8 speed_ability)
+{
+	if (speed_ability & HCLGE_SUPPORT_1G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_25G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_40G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+				 mac->supported);
+	if (speed_ability & HCLGE_SUPPORT_50G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+				 mac->supported);
 	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+				 mac->supported);
+}
+
+static void hclge_convert_setting_fec(struct hclge_mac *mac)
+{
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, mac->supported);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, mac->supported);
+
+	switch (mac->speed) {
+	case HCLGE_MAC_SPEED_10G:
+	case HCLGE_MAC_SPEED_40G:
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT,
+				 mac->supported);
+		mac->fec_ability =
+			BIT(HNAE3_FEC_BASER) | BIT(HNAE3_FEC_AUTO);
+		break;
+	case HCLGE_MAC_SPEED_25G:
+	case HCLGE_MAC_SPEED_50G:
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT,
+				 mac->supported);
+		mac->fec_ability =
+			BIT(HNAE3_FEC_BASER) | BIT(HNAE3_FEC_RS) |
+			BIT(HNAE3_FEC_AUTO);
+		break;
+	case HCLGE_MAC_SPEED_100G:
+		linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, mac->supported);
+		mac->fec_ability = BIT(HNAE3_FEC_RS) | BIT(HNAE3_FEC_AUTO);
+		break;
+	default:
+		mac->fec_ability = 0;
+		break;
+	}
+}
+
+static void hclge_parse_fiber_link_mode(struct hclge_dev *hdev,
+					u8 speed_ability)
+{
+	struct hclge_mac *mac = &hdev->hw.mac;
+
+	if (speed_ability & HCLGE_SUPPORT_1G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
+				 mac->supported);
+
+	hclge_convert_setting_sr(mac, speed_ability);
+	hclge_convert_setting_lr(mac, speed_ability);
+	hclge_convert_setting_cr(mac, speed_ability);
+	if (hdev->pdev->revision >= 0x21)
+		hclge_convert_setting_fec(mac);
 
-	set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported);
-	set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mac->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, mac->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, mac->supported);
 }
 
-static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability)
+static void hclge_parse_backplane_link_mode(struct hclge_dev *hdev,
+					    u8 speed_ability)
 {
-	u8 media_type = hdev->hw.mac.media_type;
+	struct hclge_mac *mac = &hdev->hw.mac;
 
-	if (media_type != HNAE3_MEDIA_TYPE_FIBER)
-		return;
+	hclge_convert_setting_kr(mac, speed_ability);
+	if (hdev->pdev->revision >= 0x21)
+		hclge_convert_setting_fec(mac);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Backplane_BIT, mac->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, mac->supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, mac->supported);
+}
+
+static void hclge_parse_copper_link_mode(struct hclge_dev *hdev,
+					 u8 speed_ability)
+{
+	unsigned long *supported = hdev->hw.mac.supported;
+
+	/* default to support all speed for GE port */
+	if (!speed_ability)
+		speed_ability = HCLGE_SUPPORT_GE;
 
-	hclge_parse_fiber_link_mode(hdev, speed_ability);
+	if (speed_ability & HCLGE_SUPPORT_1G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 supported);
+
+	if (speed_ability & HCLGE_SUPPORT_100M_BIT) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				 supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				 supported);
+	}
+
+	if (speed_ability & HCLGE_SUPPORT_10M_BIT) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, supported);
+	}
+
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, supported);
 }
 
+static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability)
+{
+	u8 media_type = hdev->hw.mac.media_type;
+
+	if (media_type == HNAE3_MEDIA_TYPE_FIBER)
+		hclge_parse_fiber_link_mode(hdev, speed_ability);
+	else if (media_type == HNAE3_MEDIA_TYPE_COPPER)
+		hclge_parse_copper_link_mode(hdev, speed_ability);
+	else if (media_type == HNAE3_MEDIA_TYPE_BACKPLANE)
+		hclge_parse_backplane_link_mode(hdev, speed_ability);
+}
 static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 {
 	struct hclge_cfg_param_cmd *req;
 	u64 mac_addr_tmp_high;
 	u64 mac_addr_tmp;
-	int i;
+	unsigned int i;
 
 	req = (struct hclge_cfg_param_cmd *)desc[0].data;
 
@@ -867,7 +1142,8 @@ static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg)
 {
 	struct hclge_desc desc[HCLGE_PF_CFG_DESC_NUM];
 	struct hclge_cfg_param_cmd *req;
-	int i, ret;
+	unsigned int i;
+	int ret;
 
 	for (i = 0; i < HCLGE_PF_CFG_DESC_NUM; i++) {
 		u32 offset = 0;
@@ -913,10 +1189,28 @@ static int hclge_get_cap(struct hclge_dev *hdev)
 	return ret;
 }
 
+static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev)
+{
+#define HCLGE_MIN_TX_DESC	64
+#define HCLGE_MIN_RX_DESC	64
+
+	if (!is_kdump_kernel())
+		return;
+
+	dev_info(&hdev->pdev->dev,
+		 "Running kdump kernel. Using minimal resources\n");
+
+	/* minimal queue pairs equals to the number of vports */
+	hdev->num_tqps = hdev->num_vmdq_vport + hdev->num_req_vfs + 1;
+	hdev->num_tx_desc = HCLGE_MIN_TX_DESC;
+	hdev->num_rx_desc = HCLGE_MIN_RX_DESC;
+}
+
 static int hclge_configure(struct hclge_dev *hdev)
 {
 	struct hclge_cfg cfg;
-	int ret, i;
+	unsigned int i;
+	int ret;
 
 	ret = hclge_get_cfg(hdev, &cfg);
 	if (ret) {
@@ -931,12 +1225,18 @@ static int hclge_configure(struct hclge_dev *hdev)
 	ether_addr_copy(hdev->hw.mac.mac_addr, cfg.mac_addr);
 	hdev->hw.mac.media_type = cfg.media_type;
 	hdev->hw.mac.phy_addr = cfg.phy_addr;
-	hdev->num_desc = cfg.tqp_desc_num;
+	hdev->num_tx_desc = cfg.tqp_desc_num;
+	hdev->num_rx_desc = cfg.tqp_desc_num;
 	hdev->tm_info.num_pg = 1;
 	hdev->tc_max = cfg.tc_num;
 	hdev->tm_info.hw_pfc_map = 0;
 	hdev->wanted_umv_size = cfg.umv_space;
 
+	if (hnae3_dev_fd_supported(hdev)) {
+		hdev->fd_en = true;
+		hdev->fd_active_type = HCLGE_FD_RULE_NONE;
+	}
+
 	ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed);
 	if (ret) {
 		dev_err(&hdev->pdev->dev, "Get wrong speed ret=%d.\n", ret);
@@ -968,11 +1268,13 @@ static int hclge_configure(struct hclge_dev *hdev)
 
 	hdev->tx_sch_mode = HCLGE_FLAG_TC_BASE_SCH_MODE;
 
+	hclge_init_kdump_kernel_config(hdev);
+
 	return ret;
 }
 
-static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min,
-			    int tso_mss_max)
+static int hclge_config_tso(struct hclge_dev *hdev, unsigned int tso_mss_min,
+			    unsigned int tso_mss_max)
 {
 	struct hclge_cfg_tso_status_cmd *req;
 	struct hclge_desc desc;
@@ -1035,7 +1337,8 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev)
 
 		tqp->q.ae_algo = &ae_algo;
 		tqp->q.buf_size = hdev->rx_buf_len;
-		tqp->q.desc_num = hdev->num_desc;
+		tqp->q.tx_desc_num = hdev->num_tx_desc;
+		tqp->q.rx_desc_num = hdev->num_rx_desc;
 		tqp->q.io_base = hdev->hw.io_base + HCLGE_TQP_REG_OFFSET +
 			i * HCLGE_TQP_REG_SIZE;
 
@@ -1057,8 +1360,9 @@ static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id,
 	req = (struct hclge_tqp_map_cmd *)desc.data;
 	req->tqp_id = cpu_to_le16(tqp_pid);
 	req->tqp_vf = func_id;
-	req->tqp_flag = !is_pf << HCLGE_TQP_MAP_TYPE_B |
-			1 << HCLGE_TQP_MAP_EN_B;
+	req->tqp_flag = 1U << HCLGE_TQP_MAP_EN_B;
+	if (!is_pf)
+		req->tqp_flag |= 1U << HCLGE_TQP_MAP_TYPE_B;
 	req->tqp_vid = cpu_to_le16(tqp_vid);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -1068,64 +1372,51 @@ static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id,
 	return ret;
 }
 
-static int  hclge_assign_tqp(struct hclge_vport *vport)
+static int  hclge_assign_tqp(struct hclge_vport *vport, u16 num_tqps)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, alloced;
 
 	for (i = 0, alloced = 0; i < hdev->num_tqps &&
-	     alloced < kinfo->num_tqps; i++) {
+	     alloced < num_tqps; i++) {
 		if (!hdev->htqp[i].alloced) {
 			hdev->htqp[i].q.handle = &vport->nic;
 			hdev->htqp[i].q.tqp_index = alloced;
-			hdev->htqp[i].q.desc_num = kinfo->num_desc;
+			hdev->htqp[i].q.tx_desc_num = kinfo->num_tx_desc;
+			hdev->htqp[i].q.rx_desc_num = kinfo->num_rx_desc;
 			kinfo->tqp[alloced] = &hdev->htqp[i].q;
 			hdev->htqp[i].alloced = true;
 			alloced++;
 		}
 	}
-	vport->alloc_tqps = kinfo->num_tqps;
+	vport->alloc_tqps = alloced;
+	kinfo->rss_size = min_t(u16, hdev->rss_size_max,
+				vport->alloc_tqps / hdev->tm_info.num_tc);
 
 	return 0;
 }
 
-static int hclge_knic_setup(struct hclge_vport *vport,
-			    u16 num_tqps, u16 num_desc)
+static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps,
+			    u16 num_tx_desc, u16 num_rx_desc)
+
 {
 	struct hnae3_handle *nic = &vport->nic;
 	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
 	struct hclge_dev *hdev = vport->back;
-	int i, ret;
+	int ret;
 
-	kinfo->num_desc = num_desc;
-	kinfo->rx_buf_len = hdev->rx_buf_len;
-	kinfo->num_tc = min_t(u16, num_tqps, hdev->tm_info.num_tc);
-	kinfo->rss_size
-		= min_t(u16, hdev->rss_size_max, num_tqps / kinfo->num_tc);
-	kinfo->num_tqps = kinfo->rss_size * kinfo->num_tc;
+	kinfo->num_tx_desc = num_tx_desc;
+	kinfo->num_rx_desc = num_rx_desc;
 
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
-		if (hdev->hw_tc_map & BIT(i)) {
-			kinfo->tc_info[i].enable = true;
-			kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size;
-			kinfo->tc_info[i].tqp_count = kinfo->rss_size;
-			kinfo->tc_info[i].tc = i;
-		} else {
-			/* Set to default queue if TC is disable */
-			kinfo->tc_info[i].enable = false;
-			kinfo->tc_info[i].tqp_offset = 0;
-			kinfo->tc_info[i].tqp_count = 1;
-			kinfo->tc_info[i].tc = 0;
-		}
-	}
+	kinfo->rx_buf_len = hdev->rx_buf_len;
 
-	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps,
+	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, num_tqps,
 				  sizeof(struct hnae3_queue *), GFP_KERNEL);
 	if (!kinfo->tqp)
 		return -ENOMEM;
 
-	ret = hclge_assign_tqp(vport);
+	ret = hclge_assign_tqp(vport, num_tqps);
 	if (ret)
 		dev_err(&hdev->pdev->dev, "fail to assign TQPs %d.\n", ret);
 
@@ -1140,7 +1431,7 @@ static int hclge_map_tqp_to_vport(struct hclge_dev *hdev,
 	u16 i;
 
 	kinfo = &nic->kinfo;
-	for (i = 0; i < kinfo->num_tqps; i++) {
+	for (i = 0; i < vport->alloc_tqps; i++) {
 		struct hclge_tqp *q =
 			container_of(kinfo->tqp[i], struct hclge_tqp, q);
 		bool is_pf;
@@ -1175,11 +1466,6 @@ static int hclge_map_tqp(struct hclge_dev *hdev)
 	return 0;
 }
 
-static void hclge_unic_setup(struct hclge_vport *vport, u16 num_tqps)
-{
-	/* this would be initialized later */
-}
-
 static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
 {
 	struct hnae3_handle *nic = &vport->nic;
@@ -1190,18 +1476,12 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
 	nic->ae_algo = &ae_algo;
 	nic->numa_node_mask = hdev->numa_node_mask;
 
-	if (hdev->ae_dev->dev_type == HNAE3_DEV_KNIC) {
-		ret = hclge_knic_setup(vport, num_tqps, hdev->num_desc);
-		if (ret) {
-			dev_err(&hdev->pdev->dev, "knic setup failed %d\n",
-				ret);
-			return ret;
-		}
-	} else {
-		hclge_unic_setup(vport, num_tqps);
-	}
+	ret = hclge_knic_setup(vport, num_tqps,
+			       hdev->num_tx_desc, hdev->num_rx_desc);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "knic setup failed %d\n", ret);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_alloc_vport(struct hclge_dev *hdev)
@@ -1241,6 +1521,11 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 		vport->back = hdev;
 		vport->vport_id = i;
 		vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+		vport->port_base_vlan_cfg.state = HNAE3_PORT_BASE_VLAN_DISABLE;
+		vport->rxvlan_cfg.rx_vlan_offload_en = true;
+		INIT_LIST_HEAD(&vport->vlan_list);
+		INIT_LIST_HEAD(&vport->uc_mac_list);
+		INIT_LIST_HEAD(&vport->mc_mac_list);
 
 		if (i == 0)
 			ret = hclge_vport_setup(vport, tqp_main_vport);
@@ -1273,7 +1558,7 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev,
 	req = (struct hclge_tx_buff_alloc_cmd *)desc.data;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
-	for (i = 0; i < HCLGE_TC_NUM; i++) {
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		u32 buf_size = buf_alloc->priv_buf[i].tx_buf_size;
 
 		req->tx_pkt_buff[i] =
@@ -1300,9 +1585,10 @@ static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
 	return ret;
 }
 
-static int hclge_get_tc_num(struct hclge_dev *hdev)
+static u32 hclge_get_tc_num(struct hclge_dev *hdev)
 {
-	int i, cnt = 0;
+	unsigned int i;
+	u32 cnt = 0;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
 		if (hdev->hw_tc_map & BIT(i))
@@ -1310,23 +1596,13 @@ static int hclge_get_tc_num(struct hclge_dev *hdev)
 	return cnt;
 }
 
-static int hclge_get_pfc_enalbe_num(struct hclge_dev *hdev)
-{
-	int i, cnt = 0;
-
-	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
-		if (hdev->hw_tc_map & BIT(i) &&
-		    hdev->tm_info.hw_pfc_map & BIT(i))
-			cnt++;
-	return cnt;
-}
-
 /* Get the number of pfc enabled TCs, which have private buffer */
 static int hclge_get_pfc_priv_num(struct hclge_dev *hdev,
 				  struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
-	int i, cnt = 0;
+	unsigned int i;
+	int cnt = 0;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		priv = &buf_alloc->priv_buf[i];
@@ -1343,7 +1619,8 @@ static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev,
 				     struct hclge_pkt_buf_alloc *buf_alloc)
 {
 	struct hclge_priv_buf *priv;
-	int i, cnt = 0;
+	unsigned int i;
+	int cnt = 0;
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		priv = &buf_alloc->priv_buf[i];
@@ -1384,25 +1661,22 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
 				struct hclge_pkt_buf_alloc *buf_alloc,
 				u32 rx_all)
 {
-	u32 shared_buf_min, shared_buf_tc, shared_std;
-	int tc_num, pfc_enable_num;
+	u32 shared_buf_min, shared_buf_tc, shared_std, hi_thrd, lo_thrd;
+	u32 tc_num = hclge_get_tc_num(hdev);
 	u32 shared_buf, aligned_mps;
 	u32 rx_priv;
 	int i;
 
-	tc_num = hclge_get_tc_num(hdev);
-	pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
 	aligned_mps = roundup(hdev->mps, HCLGE_BUF_SIZE_UNIT);
 
 	if (hnae3_dev_dcb_supported(hdev))
-		shared_buf_min = 2 * aligned_mps + hdev->dv_buf_size;
+		shared_buf_min = HCLGE_BUF_MUL_BY * aligned_mps +
+					hdev->dv_buf_size;
 	else
 		shared_buf_min = aligned_mps + HCLGE_NON_DCB_ADDITIONAL_BUF
 					+ hdev->dv_buf_size;
 
-	shared_buf_tc = pfc_enable_num * aligned_mps +
-			(tc_num - pfc_enable_num) * aligned_mps / 2 +
-			aligned_mps;
+	shared_buf_tc = tc_num * aligned_mps + aligned_mps;
 	shared_std = roundup(max_t(u32, shared_buf_min, shared_buf_tc),
 			     HCLGE_BUF_SIZE_UNIT);
 
@@ -1415,23 +1689,35 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
 	if (hnae3_dev_dcb_supported(hdev)) {
 		buf_alloc->s_buf.self.high = shared_buf - hdev->dv_buf_size;
 		buf_alloc->s_buf.self.low = buf_alloc->s_buf.self.high
-			- roundup(aligned_mps / 2, HCLGE_BUF_SIZE_UNIT);
+			- roundup(aligned_mps / HCLGE_BUF_DIV_BY,
+				  HCLGE_BUF_SIZE_UNIT);
 	} else {
 		buf_alloc->s_buf.self.high = aligned_mps +
 						HCLGE_NON_DCB_ADDITIONAL_BUF;
-		buf_alloc->s_buf.self.low =
-			roundup(aligned_mps / 2, HCLGE_BUF_SIZE_UNIT);
+		buf_alloc->s_buf.self.low = aligned_mps;
+	}
+
+	if (hnae3_dev_dcb_supported(hdev)) {
+		hi_thrd = shared_buf - hdev->dv_buf_size;
+
+		if (tc_num <= NEED_RESERVE_TC_NUM)
+			hi_thrd = hi_thrd * BUF_RESERVE_PERCENT
+					/ BUF_MAX_PERCENT;
+
+		if (tc_num)
+			hi_thrd = hi_thrd / tc_num;
+
+		hi_thrd = max_t(u32, hi_thrd, HCLGE_BUF_MUL_BY * aligned_mps);
+		hi_thrd = rounddown(hi_thrd, HCLGE_BUF_SIZE_UNIT);
+		lo_thrd = hi_thrd - aligned_mps / HCLGE_BUF_DIV_BY;
+	} else {
+		hi_thrd = aligned_mps + HCLGE_NON_DCB_ADDITIONAL_BUF;
+		lo_thrd = aligned_mps;
 	}
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		if ((hdev->hw_tc_map & BIT(i)) &&
-		    (hdev->tm_info.hw_pfc_map & BIT(i))) {
-			buf_alloc->s_buf.tc_thrd[i].low = aligned_mps;
-			buf_alloc->s_buf.tc_thrd[i].high = 2 * aligned_mps;
-		} else {
-			buf_alloc->s_buf.tc_thrd[i].low = 0;
-			buf_alloc->s_buf.tc_thrd[i].high = aligned_mps;
-		}
+		buf_alloc->s_buf.tc_thrd[i].low = lo_thrd;
+		buf_alloc->s_buf.tc_thrd[i].high = hi_thrd;
 	}
 
 	return true;
@@ -1448,13 +1734,14 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
-		if (total_size < hdev->tx_buf_size)
-			return -ENOMEM;
+		if (hdev->hw_tc_map & BIT(i)) {
+			if (total_size < hdev->tx_buf_size)
+				return -ENOMEM;
 
-		if (hdev->hw_tc_map & BIT(i))
 			priv->tx_buf_size = hdev->tx_buf_size;
-		else
+		} else {
 			priv->tx_buf_size = 0;
+		}
 
 		total_size -= priv->tx_buf_size;
 	}
@@ -1462,66 +1749,15 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
 	return 0;
 }
 
-/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
- * @hdev: pointer to struct hclge_dev
- * @buf_alloc: pointer to buffer calculation data
- * @return: 0: calculate sucessful, negative: fail
- */
-static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
-				struct hclge_pkt_buf_alloc *buf_alloc)
+static bool hclge_rx_buf_calc_all(struct hclge_dev *hdev, bool max,
+				  struct hclge_pkt_buf_alloc *buf_alloc)
 {
-	u32 rx_all = hdev->pkt_buf_size, aligned_mps;
-	int no_pfc_priv_num, pfc_priv_num;
-	struct hclge_priv_buf *priv;
-	int i;
+	u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc);
+	u32 aligned_mps = round_up(hdev->mps, HCLGE_BUF_SIZE_UNIT);
+	unsigned int i;
 
-	aligned_mps = round_up(hdev->mps, HCLGE_BUF_SIZE_UNIT);
-	rx_all -= hclge_get_tx_buff_alloced(buf_alloc);
-
-	/* When DCB is not supported, rx private
-	 * buffer is not allocated.
-	 */
-	if (!hnae3_dev_dcb_supported(hdev)) {
-		if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-			return -ENOMEM;
-
-		return 0;
-	}
-
-	/* step 1, try to alloc private buffer for all enabled tc */
-	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &buf_alloc->priv_buf[i];
-		if (hdev->hw_tc_map & BIT(i)) {
-			priv->enable = 1;
-			if (hdev->tm_info.hw_pfc_map & BIT(i)) {
-				priv->wl.low = aligned_mps;
-				priv->wl.high =
-					roundup(priv->wl.low + aligned_mps,
-						HCLGE_BUF_SIZE_UNIT);
-				priv->buf_size = priv->wl.high +
-					hdev->dv_buf_size;
-			} else {
-				priv->wl.low = 0;
-				priv->wl.high = 2 * aligned_mps;
-				priv->buf_size = priv->wl.high +
-						hdev->dv_buf_size;
-			}
-		} else {
-			priv->enable = 0;
-			priv->wl.low = 0;
-			priv->wl.high = 0;
-			priv->buf_size = 0;
-		}
-	}
-
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-		return 0;
-
-	/* step 2, try to decrease the buffer size of
-	 * no pfc TC's private buffer
-	 */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &buf_alloc->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
 		priv->enable = 0;
 		priv->wl.low = 0;
@@ -1534,31 +1770,35 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 		priv->enable = 1;
 
 		if (hdev->tm_info.hw_pfc_map & BIT(i)) {
-			priv->wl.low = 256;
-			priv->wl.high = priv->wl.low + aligned_mps;
-			priv->buf_size = priv->wl.high + hdev->dv_buf_size;
+			priv->wl.low = max ? aligned_mps : HCLGE_BUF_SIZE_UNIT;
+			priv->wl.high = roundup(priv->wl.low + aligned_mps,
+						HCLGE_BUF_SIZE_UNIT);
 		} else {
 			priv->wl.low = 0;
-			priv->wl.high = aligned_mps;
-			priv->buf_size = priv->wl.high + hdev->dv_buf_size;
+			priv->wl.high = max ? (aligned_mps * HCLGE_BUF_MUL_BY) :
+					aligned_mps;
 		}
+
+		priv->buf_size = priv->wl.high + hdev->dv_buf_size;
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-		return 0;
+	return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all);
+}
 
-	/* step 3, try to reduce the number of pfc disabled TCs,
-	 * which have private buffer
-	 */
-	/* get the total no pfc enable TC number, which have private buffer */
-	no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc);
+static bool hclge_drop_nopfc_buf_till_fit(struct hclge_dev *hdev,
+					  struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc);
+	int no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc);
+	int i;
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &buf_alloc->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
+		unsigned int mask = BIT((unsigned int)i);
 
-		if (hdev->hw_tc_map & BIT(i) &&
-		    !(hdev->tm_info.hw_pfc_map & BIT(i))) {
+		if (hdev->hw_tc_map & mask &&
+		    !(hdev->tm_info.hw_pfc_map & mask)) {
 			/* Clear the no pfc TC private buffer */
 			priv->wl.low = 0;
 			priv->wl.high = 0;
@@ -1572,20 +1812,23 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 			break;
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-		return 0;
+	return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all);
+}
 
-	/* step 4, try to reduce the number of pfc enabled TCs
-	 * which have private buffer.
-	 */
-	pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc);
+static bool hclge_drop_pfc_buf_till_fit(struct hclge_dev *hdev,
+					struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc);
+	int pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc);
+	int i;
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &buf_alloc->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
+		unsigned int mask = BIT((unsigned int)i);
 
-		if (hdev->hw_tc_map & BIT(i) &&
-		    hdev->tm_info.hw_pfc_map & BIT(i)) {
+		if (hdev->hw_tc_map & mask &&
+		    hdev->tm_info.hw_pfc_map & mask) {
 			/* Reduce the number of pfc TC with private buffer */
 			priv->wl.low = 0;
 			priv->enable = 0;
@@ -1598,7 +1841,92 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 		    pfc_priv_num == 0)
 			break;
 	}
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
+
+	return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all);
+}
+
+static int hclge_only_alloc_priv_buff(struct hclge_dev *hdev,
+				      struct hclge_pkt_buf_alloc *buf_alloc)
+{
+#define COMPENSATE_BUFFER	0x3C00
+#define COMPENSATE_HALF_MPS_NUM	5
+#define PRIV_WL_GAP		0x1800
+
+	u32 rx_priv = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc);
+	u32 tc_num = hclge_get_tc_num(hdev);
+	u32 half_mps = hdev->mps >> 1;
+	u32 min_rx_priv;
+	unsigned int i;
+
+	if (tc_num)
+		rx_priv = rx_priv / tc_num;
+
+	if (tc_num <= NEED_RESERVE_TC_NUM)
+		rx_priv = rx_priv * BUF_RESERVE_PERCENT / BUF_MAX_PERCENT;
+
+	min_rx_priv = hdev->dv_buf_size + COMPENSATE_BUFFER +
+			COMPENSATE_HALF_MPS_NUM * half_mps;
+	min_rx_priv = round_up(min_rx_priv, HCLGE_BUF_SIZE_UNIT);
+	rx_priv = round_down(rx_priv, HCLGE_BUF_SIZE_UNIT);
+
+	if (rx_priv < min_rx_priv)
+		return false;
+
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
+
+		priv->enable = 0;
+		priv->wl.low = 0;
+		priv->wl.high = 0;
+		priv->buf_size = 0;
+
+		if (!(hdev->hw_tc_map & BIT(i)))
+			continue;
+
+		priv->enable = 1;
+		priv->buf_size = rx_priv;
+		priv->wl.high = rx_priv - hdev->dv_buf_size;
+		priv->wl.low = priv->wl.high - PRIV_WL_GAP;
+	}
+
+	buf_alloc->s_buf.buf_size = 0;
+
+	return true;
+}
+
+/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
+ * @hdev: pointer to struct hclge_dev
+ * @buf_alloc: pointer to buffer calculation data
+ * @return: 0: calculate sucessful, negative: fail
+ */
+static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
+				struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	/* When DCB is not supported, rx private buffer is not allocated. */
+	if (!hnae3_dev_dcb_supported(hdev)) {
+		u32 rx_all = hdev->pkt_buf_size;
+
+		rx_all -= hclge_get_tx_buff_alloced(buf_alloc);
+		if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
+			return -ENOMEM;
+
+		return 0;
+	}
+
+	if (hclge_only_alloc_priv_buff(hdev, buf_alloc))
+		return 0;
+
+	if (hclge_rx_buf_calc_all(hdev, true, buf_alloc))
+		return 0;
+
+	/* try to decrease the buffer size */
+	if (hclge_rx_buf_calc_all(hdev, false, buf_alloc))
+		return 0;
+
+	if (hclge_drop_nopfc_buf_till_fit(hdev, buf_alloc))
+		return 0;
+
+	if (hclge_drop_pfc_buf_till_fit(hdev, buf_alloc))
 		return 0;
 
 	return -ENOMEM;
@@ -1885,7 +2213,6 @@ static int hclge_init_msi(struct hclge_dev *hdev)
 
 static u8 hclge_check_speed_dup(u8 duplex, int speed)
 {
-
 	if (!(speed == HCLGE_MAC_SPEED_10M || speed == HCLGE_MAC_SPEED_100M))
 		duplex = HCLGE_MAC_FULL;
 
@@ -1903,7 +2230,8 @@ static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed,
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false);
 
-	hnae3_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex);
+	if (duplex)
+		hnae3_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, 1);
 
 	switch (speed) {
 	case HCLGE_MAC_SPEED_10M:
@@ -1993,7 +2321,8 @@ static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false);
 
 	req = (struct hclge_config_auto_neg_cmd *)desc.data;
-	hnae3_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
+	if (enable)
+		hnae3_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, 1U);
 	req->cfg_an_cmd_flag = cpu_to_le32(flag);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2009,6 +2338,16 @@ static int hclge_set_autoneg(struct hnae3_handle *handle, bool enable)
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
+	if (!hdev->hw.mac.support_autoneg) {
+		if (enable) {
+			dev_err(&hdev->pdev->dev,
+				"autoneg is not supported by current port\n");
+			return -EOPNOTSUPP;
+		} else {
+			return 0;
+		}
+	}
+
 	return hclge_set_autoneg_en(hdev, enable);
 }
 
@@ -2024,6 +2363,89 @@ static int hclge_get_autoneg(struct hnae3_handle *handle)
 	return hdev->hw.mac.autoneg;
 }
 
+static int hclge_restart_autoneg(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	dev_dbg(&hdev->pdev->dev, "restart autoneg\n");
+
+	ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		return ret;
+	return hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+}
+
+static int hclge_halt_autoneg(struct hnae3_handle *handle, bool halt)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	if (hdev->hw.mac.support_autoneg && hdev->hw.mac.autoneg)
+		return hclge_set_autoneg_en(hdev, !halt);
+
+	return 0;
+}
+
+static int hclge_set_fec_hw(struct hclge_dev *hdev, u32 fec_mode)
+{
+	struct hclge_config_fec_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_FEC_MODE, false);
+
+	req = (struct hclge_config_fec_cmd *)desc.data;
+	if (fec_mode & BIT(HNAE3_FEC_AUTO))
+		hnae3_set_bit(req->fec_mode, HCLGE_MAC_CFG_FEC_AUTO_EN_B, 1);
+	if (fec_mode & BIT(HNAE3_FEC_RS))
+		hnae3_set_field(req->fec_mode, HCLGE_MAC_CFG_FEC_MODE_M,
+				HCLGE_MAC_CFG_FEC_MODE_S, HCLGE_MAC_FEC_RS);
+	if (fec_mode & BIT(HNAE3_FEC_BASER))
+		hnae3_set_field(req->fec_mode, HCLGE_MAC_CFG_FEC_MODE_M,
+				HCLGE_MAC_CFG_FEC_MODE_S, HCLGE_MAC_FEC_BASER);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "set fec mode failed %d.\n", ret);
+
+	return ret;
+}
+
+static int hclge_set_fec(struct hnae3_handle *handle, u32 fec_mode)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_mac *mac = &hdev->hw.mac;
+	int ret;
+
+	if (fec_mode && !(mac->fec_ability & fec_mode)) {
+		dev_err(&hdev->pdev->dev, "unsupported fec mode\n");
+		return -EINVAL;
+	}
+
+	ret = hclge_set_fec_hw(hdev, fec_mode);
+	if (ret)
+		return ret;
+
+	mac->user_fec_mode = fec_mode | BIT(HNAE3_FEC_USER_DEF);
+	return 0;
+}
+
+static void hclge_get_fec(struct hnae3_handle *handle, u8 *fec_ability,
+			  u8 *fec_mode)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_mac *mac = &hdev->hw.mac;
+
+	if (fec_ability)
+		*fec_ability = mac->fec_ability;
+	if (fec_mode)
+		*fec_mode = mac->fec_mode;
+}
+
 static int hclge_mac_init(struct hclge_dev *hdev)
 {
 	struct hclge_mac *mac = &hdev->hw.mac;
@@ -2039,8 +2461,26 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 		return ret;
 	}
 
+	if (hdev->hw.mac.support_autoneg) {
+		ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"Config mac autoneg fail ret=%d\n", ret);
+			return ret;
+		}
+	}
+
 	mac->link = 0;
 
+	if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) {
+		ret = hclge_set_fec_hw(hdev, mac->user_fec_mode);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"Fec mode init fail, ret = %d\n", ret);
+			return ret;
+		}
+	}
+
 	ret = hclge_set_mac_mtu(hdev, hdev->mps);
 	if (ret) {
 		dev_err(&hdev->pdev->dev, "set mtu failed ret=%d\n", ret);
@@ -2057,13 +2497,15 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 
 static void hclge_mbx_task_schedule(struct hclge_dev *hdev)
 {
-	if (!test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state))
+	if (!test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state) &&
+	    !test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state))
 		schedule_work(&hdev->mbx_service_task);
 }
 
 static void hclge_reset_task_schedule(struct hclge_dev *hdev)
 {
-	if (!test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state))
+	if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
+	    !test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state))
 		schedule_work(&hdev->rst_service_task);
 }
 
@@ -2098,7 +2540,7 @@ static int hclge_get_mac_link_status(struct hclge_dev *hdev)
 
 static int hclge_get_mac_phy_link(struct hclge_dev *hdev)
 {
-	int mac_state;
+	unsigned int mac_state;
 	int link_stat;
 
 	if (test_bit(HCLGE_STATE_DOWN, &hdev->state))
@@ -2122,7 +2564,9 @@ static int hclge_get_mac_phy_link(struct hclge_dev *hdev)
 
 static void hclge_update_link_status(struct hclge_dev *hdev)
 {
+	struct hnae3_client *rclient = hdev->roce_client;
 	struct hnae3_client *client = hdev->nic_client;
+	struct hnae3_handle *rhandle;
 	struct hnae3_handle *handle;
 	int state;
 	int i;
@@ -2134,19 +2578,48 @@ static void hclge_update_link_status(struct hclge_dev *hdev)
 		for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
 			handle = &hdev->vport[i].nic;
 			client->ops->link_status_change(handle, state);
+			hclge_config_mac_tnl_int(hdev, state);
+			rhandle = &hdev->vport[i].roce;
+			if (rclient && rclient->ops->link_status_change)
+				rclient->ops->link_status_change(rhandle,
+								 state);
 		}
 		hdev->hw.mac.link = state;
 	}
 }
 
+static void hclge_update_port_capability(struct hclge_mac *mac)
+{
+	/* update fec ability by speed */
+	hclge_convert_setting_fec(mac);
+
+	/* firmware can not identify back plane type, the media type
+	 * read from configuration can help deal it
+	 */
+	if (mac->media_type == HNAE3_MEDIA_TYPE_BACKPLANE &&
+	    mac->module_type == HNAE3_MODULE_TYPE_UNKNOWN)
+		mac->module_type = HNAE3_MODULE_TYPE_KR;
+	else if (mac->media_type == HNAE3_MEDIA_TYPE_COPPER)
+		mac->module_type = HNAE3_MODULE_TYPE_TP;
+
+	if (mac->support_autoneg == true) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mac->supported);
+		linkmode_copy(mac->advertising, mac->supported);
+	} else {
+		linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				   mac->supported);
+		linkmode_zero(mac->advertising);
+	}
+}
+
 static int hclge_get_sfp_speed(struct hclge_dev *hdev, u32 *speed)
 {
-	struct hclge_sfp_speed_cmd *resp = NULL;
+	struct hclge_sfp_info_cmd *resp;
 	struct hclge_desc desc;
 	int ret;
 
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SFP_GET_SPEED, true);
-	resp = (struct hclge_sfp_speed_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GET_SFP_INFO, true);
+	resp = (struct hclge_sfp_info_cmd *)desc.data;
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret == -EOPNOTSUPP) {
 		dev_warn(&hdev->pdev->dev,
@@ -2157,28 +2630,72 @@ static int hclge_get_sfp_speed(struct hclge_dev *hdev, u32 *speed)
 		return ret;
 	}
 
-	*speed = resp->sfp_speed;
+	*speed = le32_to_cpu(resp->speed);
 
 	return 0;
 }
 
-static int hclge_update_speed_duplex(struct hclge_dev *hdev)
+static int hclge_get_sfp_info(struct hclge_dev *hdev, struct hclge_mac *mac)
 {
-	struct hclge_mac mac = hdev->hw.mac;
-	int speed;
+	struct hclge_sfp_info_cmd *resp;
+	struct hclge_desc desc;
 	int ret;
 
-	/* get the speed from SFP cmd when phy
-	 * doesn't exit.
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GET_SFP_INFO, true);
+	resp = (struct hclge_sfp_info_cmd *)desc.data;
+
+	resp->query_type = QUERY_ACTIVE_SPEED;
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret == -EOPNOTSUPP) {
+		dev_warn(&hdev->pdev->dev,
+			 "IMP does not support get SFP info %d\n", ret);
+		return ret;
+	} else if (ret) {
+		dev_err(&hdev->pdev->dev, "get sfp info failed %d\n", ret);
+		return ret;
+	}
+
+	mac->speed = le32_to_cpu(resp->speed);
+	/* if resp->speed_ability is 0, it means it's an old version
+	 * firmware, do not update these params
 	 */
-	if (mac.phydev)
+	if (resp->speed_ability) {
+		mac->module_type = le32_to_cpu(resp->module_type);
+		mac->speed_ability = le32_to_cpu(resp->speed_ability);
+		mac->autoneg = resp->autoneg;
+		mac->support_autoneg = resp->autoneg_ability;
+		mac->speed_type = QUERY_ACTIVE_SPEED;
+		if (!resp->active_fec)
+			mac->fec_mode = 0;
+		else
+			mac->fec_mode = BIT(resp->active_fec);
+	} else {
+		mac->speed_type = QUERY_SFP_SPEED;
+	}
+
+	return 0;
+}
+
+static int hclge_update_port_info(struct hclge_dev *hdev)
+{
+	struct hclge_mac *mac = &hdev->hw.mac;
+	int speed = HCLGE_MAC_SPEED_UNKNOWN;
+	int ret;
+
+	/* get the port info from SFP cmd if not copper port */
+	if (mac->media_type == HNAE3_MEDIA_TYPE_COPPER)
 		return 0;
 
-	/* if IMP does not support get SFP/qSFP speed, return directly */
+	/* if IMP does not support get SFP/qSFP info, return directly */
 	if (!hdev->support_sfp_query)
 		return 0;
 
-	ret = hclge_get_sfp_speed(hdev, &speed);
+	if (hdev->pdev->revision >= 0x21)
+		ret = hclge_get_sfp_info(hdev, mac);
+	else
+		ret = hclge_get_sfp_speed(hdev, &speed);
+
 	if (ret == -EOPNOTSUPP) {
 		hdev->support_sfp_query = false;
 		return ret;
@@ -2186,19 +2703,20 @@ static int hclge_update_speed_duplex(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	if (speed == HCLGE_MAC_SPEED_UNKNOWN)
-		return 0; /* do nothing if no SFP */
-
-	/* must config full duplex for SFP */
-	return hclge_cfg_mac_speed_dup(hdev, speed, HCLGE_MAC_FULL);
-}
-
-static int hclge_update_speed_duplex_h(struct hnae3_handle *handle)
-{
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
+	if (hdev->pdev->revision >= 0x21) {
+		if (mac->speed_type == QUERY_ACTIVE_SPEED) {
+			hclge_update_port_capability(mac);
+			return 0;
+		}
+		return hclge_cfg_mac_speed_dup(hdev, mac->speed,
+					       HCLGE_MAC_FULL);
+	} else {
+		if (speed == HCLGE_MAC_SPEED_UNKNOWN)
+			return 0; /* do nothing if no SFP */
 
-	return hclge_update_speed_duplex(hdev);
+		/* must config full duplex for SFP */
+		return hclge_cfg_mac_speed_dup(hdev, speed, HCLGE_MAC_FULL);
+	}
 }
 
 static int hclge_get_status(struct hnae3_handle *handle)
@@ -2217,6 +2735,7 @@ static void hclge_service_timer(struct timer_list *t)
 
 	mod_timer(&hdev->service_timer, jiffies + HZ);
 	hdev->hw_stats.stats_timer++;
+	hdev->fd_arfs_expire_timer++;
 	hclge_task_schedule(hdev);
 }
 
@@ -2252,6 +2771,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
+		hdev->rst_stats.imp_rst_cnt++;
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
@@ -2260,20 +2780,17 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
-		return HCLGE_VECTOR0_EVENT_RST;
-	}
-
-	if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_src_reg) {
-		dev_info(&hdev->pdev->dev, "core reset interrupt\n");
-		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
-		set_bit(HNAE3_CORE_RESET, &hdev->reset_pending);
-		*clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
+		hdev->rst_stats.global_rst_cnt++;
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
 	/* check for vector0 msix event source */
-	if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK)
+	if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK) {
+		dev_info(&hdev->pdev->dev, "received event 0x%x\n",
+			 msix_src_reg);
+		*clearval = msix_src_reg;
 		return HCLGE_VECTOR0_EVENT_ERR;
+	}
 
 	/* check for vector0 mailbox(=CMDQ RX) event source */
 	if (BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
@@ -2282,6 +2799,12 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 		return HCLGE_VECTOR0_EVENT_MBX;
 	}
 
+	/* print other vector0 event source */
+	dev_info(&hdev->pdev->dev,
+		 "CMDQ INT status:0x%x, other INT status:0x%x\n",
+		 cmdq_src_reg, msix_src_reg);
+	*clearval = msix_src_reg;
+
 	return HCLGE_VECTOR0_EVENT_OTHER;
 }
 
@@ -2317,8 +2840,8 @@ static void hclge_enable_vector(struct hclge_misc_vector *vector, bool enable)
 static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 {
 	struct hclge_dev *hdev = data;
+	u32 clearval = 0;
 	u32 event_cause;
-	u32 clearval;
 
 	hclge_enable_vector(&hdev->misc_vector, false);
 	event_cause = hclge_check_event_cause(hdev, &clearval);
@@ -2360,7 +2883,8 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 	}
 
 	/* clear the source of interrupt if it is not cause by reset */
-	if (event_cause == HCLGE_VECTOR0_EVENT_MBX) {
+	if (!clearval ||
+	    event_cause == HCLGE_VECTOR0_EVENT_MBX) {
 		hclge_clear_event_cause(hdev, event_cause, clearval);
 		hclge_enable_vector(&hdev->misc_vector, true);
 	}
@@ -2418,12 +2942,15 @@ static void hclge_misc_irq_uninit(struct hclge_dev *hdev)
 	hclge_free_vector(hdev, 0);
 }
 
-static int hclge_notify_client(struct hclge_dev *hdev,
-			       enum hnae3_reset_notify_type type)
+int hclge_notify_client(struct hclge_dev *hdev,
+			enum hnae3_reset_notify_type type)
 {
 	struct hnae3_client *client = hdev->nic_client;
 	u16 i;
 
+	if (!test_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state) || !client)
+		return 0;
+
 	if (!client->ops->reset_notify)
 		return -EOPNOTSUPP;
 
@@ -2449,7 +2976,7 @@ static int hclge_notify_roce_client(struct hclge_dev *hdev,
 	int ret = 0;
 	u16 i;
 
-	if (!client)
+	if (!test_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state) || !client)
 		return 0;
 
 	if (!client->ops->reset_notify)
@@ -2486,10 +3013,6 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 		reg = HCLGE_GLOBAL_RESET_REG;
 		reg_bit = HCLGE_GLOBAL_RESET_BIT;
 		break;
-	case HNAE3_CORE_RESET:
-		reg = HCLGE_GLOBAL_RESET_REG;
-		reg_bit = HCLGE_CORE_RESET_BIT;
-		break;
 	case HNAE3_FUNC_RESET:
 		reg = HCLGE_FUN_RST_ING;
 		reg_bit = HCLGE_FUN_RST_ING_B;
@@ -2548,7 +3071,7 @@ static int hclge_set_vf_rst(struct hclge_dev *hdev, int func_id, bool reset)
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
-int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
+static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
 {
 	int i;
 
@@ -2565,7 +3088,7 @@ int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
 			return ret;
 		}
 
-		if (!reset)
+		if (!reset || !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
 			continue;
 
 		/* Inform VF to process the reset.
@@ -2602,9 +3125,18 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 
 static void hclge_do_reset(struct hclge_dev *hdev)
 {
+	struct hnae3_handle *handle = &hdev->vport[0].nic;
 	struct pci_dev *pdev = hdev->pdev;
 	u32 val;
 
+	if (hclge_get_hw_reset_stat(handle)) {
+		dev_info(&pdev->dev, "Hardware reset not finish\n");
+		dev_info(&pdev->dev, "func_rst_reg:0x%x, global_rst_reg:0x%x\n",
+			 hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING),
+			 hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG));
+		return;
+	}
+
 	switch (hdev->reset_type) {
 	case HNAE3_GLOBAL_RESET:
 		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
@@ -2612,12 +3144,6 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
 		dev_info(&pdev->dev, "Global Reset requested\n");
 		break;
-	case HNAE3_CORE_RESET:
-		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
-		hnae3_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
-		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
-		dev_info(&pdev->dev, "Core Reset requested\n");
-		break;
 	case HNAE3_FUNC_RESET:
 		dev_info(&pdev->dev, "PF Reset requested\n");
 		/* schedule again to check later */
@@ -2637,10 +3163,11 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 	}
 }
 
-static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
+static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 						   unsigned long *addr)
 {
 	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
+	struct hclge_dev *hdev = ae_dev->priv;
 
 	/* first, resolve any unknown reset type to the known type(s) */
 	if (test_bit(HNAE3_UNKNOWN_RESET, addr)) {
@@ -2664,16 +3191,10 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
 		rst_level = HNAE3_IMP_RESET;
 		clear_bit(HNAE3_IMP_RESET, addr);
 		clear_bit(HNAE3_GLOBAL_RESET, addr);
-		clear_bit(HNAE3_CORE_RESET, addr);
 		clear_bit(HNAE3_FUNC_RESET, addr);
 	} else if (test_bit(HNAE3_GLOBAL_RESET, addr)) {
 		rst_level = HNAE3_GLOBAL_RESET;
 		clear_bit(HNAE3_GLOBAL_RESET, addr);
-		clear_bit(HNAE3_CORE_RESET, addr);
-		clear_bit(HNAE3_FUNC_RESET, addr);
-	} else if (test_bit(HNAE3_CORE_RESET, addr)) {
-		rst_level = HNAE3_CORE_RESET;
-		clear_bit(HNAE3_CORE_RESET, addr);
 		clear_bit(HNAE3_FUNC_RESET, addr);
 	} else if (test_bit(HNAE3_FUNC_RESET, addr)) {
 		rst_level = HNAE3_FUNC_RESET;
@@ -2683,6 +3204,10 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
 		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
+	if (hdev->reset_type != HNAE3_NONE_RESET &&
+	    rst_level < hdev->reset_type)
+		return HNAE3_NONE_RESET;
+
 	return rst_level;
 }
 
@@ -2697,9 +3222,6 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 	case HNAE3_GLOBAL_RESET:
 		clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
 		break;
-	case HNAE3_CORE_RESET:
-		clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
-		break;
 	default:
 		break;
 	}
@@ -2730,6 +3252,8 @@ static int hclge_reset_prepare_down(struct hclge_dev *hdev)
 
 static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 {
+#define HCLGE_RESET_SYNC_TIME 100
+
 	u32 reg_val;
 	int ret = 0;
 
@@ -2738,7 +3262,7 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		/* There is no mechanism for PF to know if VF has stopped IO
 		 * for now, just wait 100 ms for VF to stop IO
 		 */
-		msleep(100);
+		msleep(HCLGE_RESET_SYNC_TIME);
 		ret = hclge_func_reset_cmd(hdev, 0);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -2752,14 +3276,16 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		 * after hclge_cmd_init is called.
 		 */
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		hdev->rst_stats.pf_rst_cnt++;
 		break;
 	case HNAE3_FLR_RESET:
 		/* There is no mechanism for PF to know if VF has stopped IO
 		 * for now, just wait 100 ms for VF to stop IO
 		 */
-		msleep(100);
+		msleep(HCLGE_RESET_SYNC_TIME);
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+		hdev->rst_stats.flr_rst_cnt++;
 		break;
 	case HNAE3_IMP_RESET:
 		reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG);
@@ -2770,6 +3296,10 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 		break;
 	}
 
+	/* inform hardware that preparatory work is done */
+	msleep(HCLGE_RESET_SYNC_TIME);
+	hclge_write_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG,
+			HCLGE_NIC_CMQ_ENABLE);
 	dev_info(&hdev->pdev->dev, "prepare wait ok\n");
 
 	return ret;
@@ -2778,7 +3308,6 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
 static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout)
 {
 #define MAX_RESET_FAIL_CNT 5
-#define RESET_UPGRADE_DELAY_SEC 10
 
 	if (hdev->reset_pending) {
 		dev_info(&hdev->pdev->dev, "Reset pending %lu\n",
@@ -2802,8 +3331,9 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout)
 
 		dev_info(&hdev->pdev->dev, "Upgrade reset level\n");
 		hclge_clear_reset_cause(hdev);
+		set_bit(HNAE3_GLOBAL_RESET, &hdev->default_reset_request);
 		mod_timer(&hdev->reset_timer,
-			  jiffies + RESET_UPGRADE_DELAY_SEC * HZ);
+			  jiffies + HCLGE_RESET_INTERVAL);
 
 		return false;
 	}
@@ -2830,6 +3360,25 @@ static int hclge_reset_prepare_up(struct hclge_dev *hdev)
 	return ret;
 }
 
+static int hclge_reset_stack(struct hclge_dev *hdev)
+{
+	int ret;
+
+	ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
+
+	ret = hclge_reset_ae_dev(hdev->ae_dev);
+	if (ret)
+		return ret;
+
+	ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		return ret;
+
+	return hclge_notify_client(hdev, HNAE3_RESTORE_CLIENT);
+}
+
 static void hclge_reset(struct hclge_dev *hdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
@@ -2840,7 +3389,7 @@ static void hclge_reset(struct hclge_dev *hdev)
 	 * know if device is undergoing reset
 	 */
 	ae_dev->reset_type = hdev->reset_type;
-	hdev->reset_count++;
+	hdev->rst_stats.reset_cnt++;
 	/* perform reset of the stack & ae device for a client */
 	ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
 	if (ret)
@@ -2866,20 +3415,15 @@ static void hclge_reset(struct hclge_dev *hdev)
 		goto err_reset;
 	}
 
+	hdev->rst_stats.hw_reset_done_cnt++;
+
 	ret = hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
 	if (ret)
 		goto err_reset;
 
 	rtnl_lock();
-	ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
-	if (ret)
-		goto err_reset_lock;
 
-	ret = hclge_reset_ae_dev(hdev->ae_dev);
-	if (ret)
-		goto err_reset_lock;
-
-	ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	ret = hclge_reset_stack(hdev);
 	if (ret)
 		goto err_reset_lock;
 
@@ -2889,23 +3433,32 @@ static void hclge_reset(struct hclge_dev *hdev)
 	if (ret)
 		goto err_reset_lock;
 
+	rtnl_unlock();
+
+	ret = hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+	/* ignore RoCE notify error if it fails HCLGE_RESET_MAX_FAIL_CNT - 1
+	 * times
+	 */
+	if (ret && hdev->reset_fail_cnt < HCLGE_RESET_MAX_FAIL_CNT - 1)
+		goto err_reset;
+
+	rtnl_lock();
+
 	ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
 	if (ret)
 		goto err_reset_lock;
 
 	rtnl_unlock();
 
-	ret = hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
-	if (ret)
-		goto err_reset;
-
 	ret = hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
 	if (ret)
 		goto err_reset;
 
 	hdev->last_reset_time = jiffies;
 	hdev->reset_fail_cnt = 0;
+	hdev->rst_stats.reset_done_cnt++;
 	ae_dev->reset_type = HNAE3_NONE_RESET;
+	del_timer(&hdev->reset_timer);
 
 	return;
 
@@ -2939,11 +3492,12 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 	if (!handle)
 		handle = &hdev->vport[0].nic;
 
-	if (time_before(jiffies, (hdev->last_reset_time + 3 * HZ)))
+	if (time_before(jiffies, (hdev->last_reset_time +
+				  HCLGE_RESET_INTERVAL)))
 		return;
 	else if (hdev->default_reset_request)
 		hdev->reset_level =
-			hclge_get_reset_level(hdev,
+			hclge_get_reset_level(ae_dev,
 					      &hdev->default_reset_request);
 	else if (time_after(jiffies, (hdev->last_reset_time + 4 * 5 * HZ)))
 		hdev->reset_level = HNAE3_FUNC_RESET;
@@ -2972,13 +3526,14 @@ static void hclge_reset_timer(struct timer_list *t)
 	struct hclge_dev *hdev = from_timer(hdev, t, reset_timer);
 
 	dev_info(&hdev->pdev->dev,
-		 "triggering global reset in reset timer\n");
-	set_bit(HNAE3_GLOBAL_RESET, &hdev->default_reset_request);
+		 "triggering reset in reset timer\n");
 	hclge_reset_event(hdev->pdev, NULL);
 }
 
 static void hclge_reset_subtask(struct hclge_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+
 	/* check if there is any ongoing reset in the hardware. This status can
 	 * be checked from reset_pending. If there is then, we need to wait for
 	 * hardware to complete reset.
@@ -2989,12 +3544,12 @@ static void hclge_reset_subtask(struct hclge_dev *hdev)
 	 *       now.
 	 */
 	hdev->last_reset_time = jiffies;
-	hdev->reset_type = hclge_get_reset_level(hdev, &hdev->reset_pending);
+	hdev->reset_type = hclge_get_reset_level(ae_dev, &hdev->reset_pending);
 	if (hdev->reset_type != HNAE3_NONE_RESET)
 		hclge_reset(hdev);
 
 	/* check if we got any *new* reset requests to be honored */
-	hdev->reset_type = hclge_get_reset_level(hdev, &hdev->reset_request);
+	hdev->reset_type = hclge_get_reset_level(ae_dev, &hdev->reset_request);
 	if (hdev->reset_type != HNAE3_NONE_RESET)
 		hclge_do_reset(hdev);
 
@@ -3058,9 +3613,14 @@ static void hclge_service_task(struct work_struct *work)
 		hdev->hw_stats.stats_timer = 0;
 	}
 
-	hclge_update_speed_duplex(hdev);
+	hclge_update_port_info(hdev);
 	hclge_update_link_status(hdev);
 	hclge_update_vport_alive(hdev);
+	hclge_sync_vlan_filter(hdev);
+	if (hdev->fd_arfs_expire_timer >= HCLGE_FD_ARFS_EXPIRE_TIMER_INTERVAL) {
+		hclge_rfs_filter_expire(hdev);
+		hdev->fd_arfs_expire_timer = 0;
+	}
 	hclge_service_complete(hdev);
 }
 
@@ -3154,29 +3714,28 @@ static int hclge_set_rss_algo_key(struct hclge_dev *hdev,
 				  const u8 hfunc, const u8 *key)
 {
 	struct hclge_rss_config_cmd *req;
+	unsigned int key_offset = 0;
 	struct hclge_desc desc;
-	int key_offset;
+	int key_counts;
 	int key_size;
 	int ret;
 
+	key_counts = HCLGE_RSS_KEY_SIZE;
 	req = (struct hclge_rss_config_cmd *)desc.data;
 
-	for (key_offset = 0; key_offset < 3; key_offset++) {
+	while (key_counts) {
 		hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_GENERIC_CONFIG,
 					   false);
 
 		req->hash_config |= (hfunc & HCLGE_RSS_HASH_ALGO_MASK);
 		req->hash_config |= (key_offset << HCLGE_RSS_HASH_KEY_OFFSET_B);
 
-		if (key_offset == 2)
-			key_size =
-			HCLGE_RSS_KEY_SIZE - HCLGE_RSS_HASH_KEY_NUM * 2;
-		else
-			key_size = HCLGE_RSS_HASH_KEY_NUM;
-
+		key_size = min(HCLGE_RSS_HASH_KEY_NUM, key_counts);
 		memcpy(req->hash_key,
 		       key + key_offset * HCLGE_RSS_HASH_KEY_NUM, key_size);
 
+		key_counts -= key_size;
+		key_offset++;
 		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -3535,13 +4094,14 @@ int hclge_rss_init_hw(struct hclge_dev *hdev)
 	struct hclge_vport *vport = hdev->vport;
 	u8 *rss_indir = vport[0].rss_indirection_tbl;
 	u16 rss_size = vport[0].alloc_rss_size;
+	u16 tc_offset[HCLGE_MAX_TC_NUM] = {0};
+	u16 tc_size[HCLGE_MAX_TC_NUM] = {0};
 	u8 *key = vport[0].rss_hash_key;
 	u8 hfunc = vport[0].rss_algo;
-	u16 tc_offset[HCLGE_MAX_TC_NUM];
 	u16 tc_valid[HCLGE_MAX_TC_NUM];
-	u16 tc_size[HCLGE_MAX_TC_NUM];
 	u16 roundup_size;
-	int i, ret;
+	unsigned int i;
+	int ret;
 
 	ret = hclge_set_rss_indir_table(hdev, rss_indir);
 	if (ret)
@@ -3597,8 +4157,11 @@ void hclge_rss_indir_init_cfg(struct hclge_dev *hdev)
 
 static void hclge_rss_init_cfg(struct hclge_dev *hdev)
 {
+	int i, rss_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
 	struct hclge_vport *vport = hdev->vport;
-	int i;
+
+	if (hdev->pdev->revision >= 0x21)
+		rss_algo = HCLGE_RSS_HASH_ALGO_SIMPLE;
 
 	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
 		vport[i].rss_tuple_sets.ipv4_tcp_en =
@@ -3618,9 +4181,10 @@ static void hclge_rss_init_cfg(struct hclge_dev *hdev)
 		vport[i].rss_tuple_sets.ipv6_fragment_en =
 			HCLGE_RSS_INPUT_TUPLE_OTHER;
 
-		vport[i].rss_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
+		vport[i].rss_algo = rss_algo;
 
-		netdev_rss_key_fill(vport[i].rss_hash_key, HCLGE_RSS_KEY_SIZE);
+		memcpy(vport[i].rss_hash_key, hclge_hash_key,
+		       HCLGE_RSS_KEY_SIZE);
 	}
 
 	hclge_rss_indir_init_cfg(hdev);
@@ -3692,8 +4256,7 @@ int hclge_bind_ring_with_vector(struct hclge_vport *vport,
 	return 0;
 }
 
-static int hclge_map_ring_to_vector(struct hnae3_handle *handle,
-				    int vector,
+static int hclge_map_ring_to_vector(struct hnae3_handle *handle, int vector,
 				    struct hnae3_ring_chain_node *ring_chain)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -3710,8 +4273,7 @@ static int hclge_map_ring_to_vector(struct hnae3_handle *handle,
 	return hclge_bind_ring_with_vector(vport, vector_id, true, ring_chain);
 }
 
-static int hclge_unmap_ring_frm_vector(struct hnae3_handle *handle,
-				       int vector,
+static int hclge_unmap_ring_frm_vector(struct hnae3_handle *handle, int vector,
 				       struct hnae3_ring_chain_node *ring_chain)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -3732,8 +4294,7 @@ static int hclge_unmap_ring_frm_vector(struct hnae3_handle *handle,
 	if (ret)
 		dev_err(&handle->pdev->dev,
 			"Unmap ring from vector fail. vectorid=%d, ret =%d\n",
-			vector_id,
-			ret);
+			vector_id, ret);
 
 	return ret;
 }
@@ -3788,8 +4349,16 @@ static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_promisc_param param;
+	bool en_bc_pmc = true;
+
+	/* For revision 0x20, if broadcast promisc enabled, vlan filter is
+	 * always bypassed. So broadcast promisc should be disabled until
+	 * user enable promisc mode
+	 */
+	if (handle->pdev->revision == 0x20)
+		en_bc_pmc = handle->netdev_flags & HNAE3_BPE ? true : false;
 
-	hclge_promisc_param_init(&param, en_uc_pmc, en_mc_pmc, true,
+	hclge_promisc_param_init(&param, en_uc_pmc, en_mc_pmc, en_bc_pmc,
 				 vport->vport_id);
 	return hclge_cmd_set_promisc_mode(hdev, &param);
 }
@@ -3898,7 +4467,6 @@ static int hclge_init_fd_config(struct hclge_dev *hdev)
 		return -EOPNOTSUPP;
 	}
 
-	hdev->fd_cfg.fd_en = true;
 	hdev->fd_cfg.proto_support =
 		TCP_V4_FLOW | UDP_V4_FLOW | SCTP_V4_FLOW | TCP_V6_FLOW |
 		UDP_V6_FLOW | SCTP_V6_FLOW | IPV4_USER_FLOW | IPV6_USER_FLOW;
@@ -4032,19 +4600,19 @@ static bool hclge_fd_convert_tuple(u32 tuple_bit, u8 *key_x, u8 *key_y,
 	case 0:
 		return false;
 	case BIT(INNER_DST_MAC):
-		for (i = 0; i < 6; i++) {
-			calc_x(key_x[5 - i], rule->tuples.dst_mac[i],
+		for (i = 0; i < ETH_ALEN; i++) {
+			calc_x(key_x[ETH_ALEN - 1 - i], rule->tuples.dst_mac[i],
 			       rule->tuples_mask.dst_mac[i]);
-			calc_y(key_y[5 - i], rule->tuples.dst_mac[i],
+			calc_y(key_y[ETH_ALEN - 1 - i], rule->tuples.dst_mac[i],
 			       rule->tuples_mask.dst_mac[i]);
 		}
 
 		return true;
 	case BIT(INNER_SRC_MAC):
-		for (i = 0; i < 6; i++) {
-			calc_x(key_x[5 - i], rule->tuples.src_mac[i],
+		for (i = 0; i < ETH_ALEN; i++) {
+			calc_x(key_x[ETH_ALEN - 1 - i], rule->tuples.src_mac[i],
 			       rule->tuples.src_mac[i]);
-			calc_y(key_y[5 - i], rule->tuples.src_mac[i],
+			calc_y(key_y[ETH_ALEN - 1 - i], rule->tuples.src_mac[i],
 			       rule->tuples.src_mac[i]);
 		}
 
@@ -4080,19 +4648,19 @@ static bool hclge_fd_convert_tuple(u32 tuple_bit, u8 *key_x, u8 *key_y,
 
 		return true;
 	case BIT(INNER_SRC_IP):
-		calc_x(tmp_x_l, rule->tuples.src_ip[3],
-		       rule->tuples_mask.src_ip[3]);
-		calc_y(tmp_y_l, rule->tuples.src_ip[3],
-		       rule->tuples_mask.src_ip[3]);
+		calc_x(tmp_x_l, rule->tuples.src_ip[IPV4_INDEX],
+		       rule->tuples_mask.src_ip[IPV4_INDEX]);
+		calc_y(tmp_y_l, rule->tuples.src_ip[IPV4_INDEX],
+		       rule->tuples_mask.src_ip[IPV4_INDEX]);
 		*(__le32 *)key_x = cpu_to_le32(tmp_x_l);
 		*(__le32 *)key_y = cpu_to_le32(tmp_y_l);
 
 		return true;
 	case BIT(INNER_DST_IP):
-		calc_x(tmp_x_l, rule->tuples.dst_ip[3],
-		       rule->tuples_mask.dst_ip[3]);
-		calc_y(tmp_y_l, rule->tuples.dst_ip[3],
-		       rule->tuples_mask.dst_ip[3]);
+		calc_x(tmp_x_l, rule->tuples.dst_ip[IPV4_INDEX],
+		       rule->tuples_mask.dst_ip[IPV4_INDEX]);
+		calc_y(tmp_y_l, rule->tuples.dst_ip[IPV4_INDEX],
+		       rule->tuples_mask.dst_ip[IPV4_INDEX]);
 		*(__le32 *)key_x = cpu_to_le32(tmp_x_l);
 		*(__le32 *)key_y = cpu_to_le32(tmp_y_l);
 
@@ -4146,7 +4714,7 @@ static void hclge_fd_convert_meta_data(struct hclge_fd_key_cfg *key_cfg,
 {
 	u32 tuple_bit, meta_data = 0, tmp_x, tmp_y, port_number;
 	u8 cur_pos = 0, tuple_size, shift_bits;
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < MAX_META_DATA; i++) {
 		tuple_size = meta_data_key_info[i].key_length;
@@ -4188,7 +4756,8 @@ static int hclge_config_key(struct hclge_dev *hdev, u8 stage,
 	struct hclge_fd_key_cfg *key_cfg = &hdev->fd_cfg.key_cfg[stage];
 	u8 key_x[MAX_KEY_BYTES], key_y[MAX_KEY_BYTES];
 	u8 *cur_key_x, *cur_key_y;
-	int i, ret, tuple_size;
+	unsigned int i;
+	int ret, tuple_size;
 	u8 meta_data_region;
 
 	memset(key_x, 0, sizeof(key_x));
@@ -4341,6 +4910,7 @@ static int hclge_fd_check_spec(struct hclge_dev *hdev,
 		*unused |= BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
 			BIT(INNER_IP_TOS);
 
+		/* check whether src/dst ip address used */
 		if (!tcp_ip6_spec->ip6src[0] && !tcp_ip6_spec->ip6src[1] &&
 		    !tcp_ip6_spec->ip6src[2] && !tcp_ip6_spec->ip6src[3])
 			*unused |= BIT(INNER_SRC_IP);
@@ -4365,6 +4935,7 @@ static int hclge_fd_check_spec(struct hclge_dev *hdev,
 			BIT(INNER_IP_TOS) | BIT(INNER_SRC_PORT) |
 			BIT(INNER_DST_PORT);
 
+		/* check whether src/dst ip address used */
 		if (!usr_ip6_spec->ip6src[0] && !usr_ip6_spec->ip6src[1] &&
 		    !usr_ip6_spec->ip6src[2] && !usr_ip6_spec->ip6src[3])
 			*unused |= BIT(INNER_SRC_IP);
@@ -4435,14 +5006,18 @@ static bool hclge_fd_rule_exist(struct hclge_dev *hdev, u16 location)
 	struct hclge_fd_rule *rule = NULL;
 	struct hlist_node *node2;
 
+	spin_lock_bh(&hdev->fd_rule_lock);
 	hlist_for_each_entry_safe(rule, node2, &hdev->fd_rule_list, rule_node) {
 		if (rule->location >= location)
 			break;
 	}
 
+	spin_unlock_bh(&hdev->fd_rule_lock);
+
 	return  rule && rule->location == location;
 }
 
+/* make sure being called after lock up with fd_rule_lock */
 static int hclge_fd_update_rule_list(struct hclge_dev *hdev,
 				     struct hclge_fd_rule *new_rule,
 				     u16 location,
@@ -4466,9 +5041,13 @@ static int hclge_fd_update_rule_list(struct hclge_dev *hdev,
 		kfree(rule);
 		hdev->hclge_fd_rule_num--;
 
-		if (!is_add)
-			return 0;
+		if (!is_add) {
+			if (!hdev->hclge_fd_rule_num)
+				hdev->fd_active_type = HCLGE_FD_RULE_NONE;
+			clear_bit(location, hdev->fd_bmap);
 
+			return 0;
+		}
 	} else if (!is_add) {
 		dev_err(&hdev->pdev->dev,
 			"delete fail, rule %d is inexistent\n",
@@ -4483,7 +5062,9 @@ static int hclge_fd_update_rule_list(struct hclge_dev *hdev,
 	else
 		hlist_add_head(&new_rule->rule_node, &hdev->fd_rule_list);
 
+	set_bit(location, hdev->fd_bmap);
 	hdev->hclge_fd_rule_num++;
+	hdev->fd_active_type = new_rule->rule_type;
 
 	return 0;
 }
@@ -4498,14 +5079,14 @@ static int hclge_fd_get_tuple(struct hclge_dev *hdev,
 	case SCTP_V4_FLOW:
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
-		rule->tuples.src_ip[3] =
+		rule->tuples.src_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->h_u.tcp_ip4_spec.ip4src);
-		rule->tuples_mask.src_ip[3] =
+		rule->tuples_mask.src_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->m_u.tcp_ip4_spec.ip4src);
 
-		rule->tuples.dst_ip[3] =
+		rule->tuples.dst_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->h_u.tcp_ip4_spec.ip4dst);
-		rule->tuples_mask.dst_ip[3] =
+		rule->tuples_mask.dst_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->m_u.tcp_ip4_spec.ip4dst);
 
 		rule->tuples.src_port = be16_to_cpu(fs->h_u.tcp_ip4_spec.psrc);
@@ -4524,14 +5105,14 @@ static int hclge_fd_get_tuple(struct hclge_dev *hdev,
 
 		break;
 	case IP_USER_FLOW:
-		rule->tuples.src_ip[3] =
+		rule->tuples.src_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->h_u.usr_ip4_spec.ip4src);
-		rule->tuples_mask.src_ip[3] =
+		rule->tuples_mask.src_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->m_u.usr_ip4_spec.ip4src);
 
-		rule->tuples.dst_ip[3] =
+		rule->tuples.dst_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->h_u.usr_ip4_spec.ip4dst);
-		rule->tuples_mask.dst_ip[3] =
+		rule->tuples_mask.dst_ip[IPV4_INDEX] =
 				be32_to_cpu(fs->m_u.usr_ip4_spec.ip4dst);
 
 		rule->tuples.ip_tos = fs->h_u.usr_ip4_spec.tos;
@@ -4548,14 +5129,14 @@ static int hclge_fd_get_tuple(struct hclge_dev *hdev,
 	case TCP_V6_FLOW:
 	case UDP_V6_FLOW:
 		be32_to_cpu_array(rule->tuples.src_ip,
-				  fs->h_u.tcp_ip6_spec.ip6src, 4);
+				  fs->h_u.tcp_ip6_spec.ip6src, IPV6_SIZE);
 		be32_to_cpu_array(rule->tuples_mask.src_ip,
-				  fs->m_u.tcp_ip6_spec.ip6src, 4);
+				  fs->m_u.tcp_ip6_spec.ip6src, IPV6_SIZE);
 
 		be32_to_cpu_array(rule->tuples.dst_ip,
-				  fs->h_u.tcp_ip6_spec.ip6dst, 4);
+				  fs->h_u.tcp_ip6_spec.ip6dst, IPV6_SIZE);
 		be32_to_cpu_array(rule->tuples_mask.dst_ip,
-				  fs->m_u.tcp_ip6_spec.ip6dst, 4);
+				  fs->m_u.tcp_ip6_spec.ip6dst, IPV6_SIZE);
 
 		rule->tuples.src_port = be16_to_cpu(fs->h_u.tcp_ip6_spec.psrc);
 		rule->tuples_mask.src_port =
@@ -4571,14 +5152,14 @@ static int hclge_fd_get_tuple(struct hclge_dev *hdev,
 		break;
 	case IPV6_USER_FLOW:
 		be32_to_cpu_array(rule->tuples.src_ip,
-				  fs->h_u.usr_ip6_spec.ip6src, 4);
+				  fs->h_u.usr_ip6_spec.ip6src, IPV6_SIZE);
 		be32_to_cpu_array(rule->tuples_mask.src_ip,
-				  fs->m_u.usr_ip6_spec.ip6src, 4);
+				  fs->m_u.usr_ip6_spec.ip6src, IPV6_SIZE);
 
 		be32_to_cpu_array(rule->tuples.dst_ip,
-				  fs->h_u.usr_ip6_spec.ip6dst, 4);
+				  fs->h_u.usr_ip6_spec.ip6dst, IPV6_SIZE);
 		be32_to_cpu_array(rule->tuples_mask.dst_ip,
-				  fs->m_u.usr_ip6_spec.ip6dst, 4);
+				  fs->m_u.usr_ip6_spec.ip6dst, IPV6_SIZE);
 
 		rule->tuples.ip_proto = fs->h_u.usr_ip6_spec.l4_proto;
 		rule->tuples_mask.ip_proto = fs->m_u.usr_ip6_spec.l4_proto;
@@ -4641,6 +5222,36 @@ static int hclge_fd_get_tuple(struct hclge_dev *hdev,
 	return 0;
 }
 
+/* make sure being called after lock up with fd_rule_lock */
+static int hclge_fd_config_rule(struct hclge_dev *hdev,
+				struct hclge_fd_rule *rule)
+{
+	int ret;
+
+	if (!rule) {
+		dev_err(&hdev->pdev->dev,
+			"The flow director rule is NULL\n");
+		return -EINVAL;
+	}
+
+	/* it will never fail here, so needn't to check return value */
+	hclge_fd_update_rule_list(hdev, rule, rule->location, true);
+
+	ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
+	if (ret)
+		goto clear_rule;
+
+	ret = hclge_config_key(hdev, HCLGE_FD_STAGE_1, rule);
+	if (ret)
+		goto clear_rule;
+
+	return 0;
+
+clear_rule:
+	hclge_fd_update_rule_list(hdev, rule, rule->location, false);
+	return ret;
+}
+
 static int hclge_add_fd_entry(struct hnae3_handle *handle,
 			      struct ethtool_rxnfc *cmd)
 {
@@ -4656,7 +5267,7 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 	if (!hnae3_dev_fd_supported(hdev))
 		return -EOPNOTSUPP;
 
-	if (!hdev->fd_cfg.fd_en) {
+	if (!hdev->fd_en) {
 		dev_warn(&hdev->pdev->dev,
 			 "Please enable flow director first\n");
 		return -EOPNOTSUPP;
@@ -4703,8 +5314,10 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 		return -ENOMEM;
 
 	ret = hclge_fd_get_tuple(hdev, fs, rule);
-	if (ret)
-		goto free_rule;
+	if (ret) {
+		kfree(rule);
+		return ret;
+	}
 
 	rule->flow_type = fs->flow_type;
 
@@ -4713,23 +5326,18 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 	rule->vf_id = dst_vport_id;
 	rule->queue_id = q_index;
 	rule->action = action;
+	rule->rule_type = HCLGE_FD_EP_ACTIVE;
 
-	ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
-	if (ret)
-		goto free_rule;
-
-	ret = hclge_config_key(hdev, HCLGE_FD_STAGE_1, rule);
-	if (ret)
-		goto free_rule;
+	/* to avoid rule conflict, when user configure rule by ethtool,
+	 * we need to clear all arfs rules
+	 */
+	hclge_clear_arfs_rules(handle);
 
-	ret = hclge_fd_update_rule_list(hdev, rule, fs->location, true);
-	if (ret)
-		goto free_rule;
+	spin_lock_bh(&hdev->fd_rule_lock);
+	ret = hclge_fd_config_rule(hdev, rule);
 
-	return ret;
+	spin_unlock_bh(&hdev->fd_rule_lock);
 
-free_rule:
-	kfree(rule);
 	return ret;
 }
 
@@ -4751,18 +5359,21 @@ static int hclge_del_fd_entry(struct hnae3_handle *handle,
 
 	if (!hclge_fd_rule_exist(hdev, fs->location)) {
 		dev_err(&hdev->pdev->dev,
-			"Delete fail, rule %d is inexistent\n",
-			fs->location);
+			"Delete fail, rule %d is inexistent\n", fs->location);
 		return -ENOENT;
 	}
 
-	ret = hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true,
-				   fs->location, NULL, false);
+	ret = hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, fs->location,
+				   NULL, false);
 	if (ret)
 		return ret;
 
-	return hclge_fd_update_rule_list(hdev, NULL, fs->location,
-					 false);
+	spin_lock_bh(&hdev->fd_rule_lock);
+	ret = hclge_fd_update_rule_list(hdev, NULL, fs->location, false);
+
+	spin_unlock_bh(&hdev->fd_rule_lock);
+
+	return ret;
 }
 
 static void hclge_del_all_fd_entries(struct hnae3_handle *handle,
@@ -4772,25 +5383,30 @@ static void hclge_del_all_fd_entries(struct hnae3_handle *handle,
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_fd_rule *rule;
 	struct hlist_node *node;
+	u16 location;
 
 	if (!hnae3_dev_fd_supported(hdev))
 		return;
 
+	spin_lock_bh(&hdev->fd_rule_lock);
+	for_each_set_bit(location, hdev->fd_bmap,
+			 hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1])
+		hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, location,
+				     NULL, false);
+
 	if (clear_list) {
 		hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list,
 					  rule_node) {
-			hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true,
-					     rule->location, NULL, false);
 			hlist_del(&rule->rule_node);
 			kfree(rule);
-			hdev->hclge_fd_rule_num--;
 		}
-	} else {
-		hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list,
-					  rule_node)
-			hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true,
-					     rule->location, NULL, false);
+		hdev->fd_active_type = HCLGE_FD_RULE_NONE;
+		hdev->hclge_fd_rule_num = 0;
+		bitmap_zero(hdev->fd_bmap,
+			    hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]);
 	}
+
+	spin_unlock_bh(&hdev->fd_rule_lock);
 }
 
 static int hclge_restore_fd_entries(struct hnae3_handle *handle)
@@ -4809,9 +5425,10 @@ static int hclge_restore_fd_entries(struct hnae3_handle *handle)
 		return 0;
 
 	/* if fd is disabled, should not restore it when reset */
-	if (!hdev->fd_cfg.fd_en)
+	if (!hdev->fd_en)
 		return 0;
 
+	spin_lock_bh(&hdev->fd_rule_lock);
 	hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) {
 		ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
 		if (!ret)
@@ -4821,11 +5438,18 @@ static int hclge_restore_fd_entries(struct hnae3_handle *handle)
 			dev_warn(&hdev->pdev->dev,
 				 "Restore rule %d failed, remove it\n",
 				 rule->location);
+			clear_bit(rule->location, hdev->fd_bmap);
 			hlist_del(&rule->rule_node);
 			kfree(rule);
 			hdev->hclge_fd_rule_num--;
 		}
 	}
+
+	if (hdev->hclge_fd_rule_num)
+		hdev->fd_active_type = HCLGE_FD_EP_ACTIVE;
+
+	spin_unlock_bh(&hdev->fd_rule_lock);
+
 	return 0;
 }
 
@@ -4858,13 +5482,18 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 
 	fs = (struct ethtool_rx_flow_spec *)&cmd->fs;
 
+	spin_lock_bh(&hdev->fd_rule_lock);
+
 	hlist_for_each_entry_safe(rule, node2, &hdev->fd_rule_list, rule_node) {
 		if (rule->location >= fs->location)
 			break;
 	}
 
-	if (!rule || fs->location != rule->location)
+	if (!rule || fs->location != rule->location) {
+		spin_unlock_bh(&hdev->fd_rule_lock);
+
 		return -ENOENT;
+	}
 
 	fs->flow_type = rule->flow_type;
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
@@ -4872,16 +5501,16 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 		fs->h_u.tcp_ip4_spec.ip4src =
-				cpu_to_be32(rule->tuples.src_ip[3]);
+				cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]);
 		fs->m_u.tcp_ip4_spec.ip4src =
-				rule->unused_tuple & BIT(INNER_SRC_IP) ?
-				0 : cpu_to_be32(rule->tuples_mask.src_ip[3]);
+			rule->unused_tuple & BIT(INNER_SRC_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]);
 
 		fs->h_u.tcp_ip4_spec.ip4dst =
-				cpu_to_be32(rule->tuples.dst_ip[3]);
+				cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]);
 		fs->m_u.tcp_ip4_spec.ip4dst =
-				rule->unused_tuple & BIT(INNER_DST_IP) ?
-				0 : cpu_to_be32(rule->tuples_mask.dst_ip[3]);
+			rule->unused_tuple & BIT(INNER_DST_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]);
 
 		fs->h_u.tcp_ip4_spec.psrc = cpu_to_be16(rule->tuples.src_port);
 		fs->m_u.tcp_ip4_spec.psrc =
@@ -4901,16 +5530,16 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 		break;
 	case IP_USER_FLOW:
 		fs->h_u.usr_ip4_spec.ip4src =
-				cpu_to_be32(rule->tuples.src_ip[3]);
+				cpu_to_be32(rule->tuples.src_ip[IPV4_INDEX]);
 		fs->m_u.tcp_ip4_spec.ip4src =
-				rule->unused_tuple & BIT(INNER_SRC_IP) ?
-				0 : cpu_to_be32(rule->tuples_mask.src_ip[3]);
+			rule->unused_tuple & BIT(INNER_SRC_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.src_ip[IPV4_INDEX]);
 
 		fs->h_u.usr_ip4_spec.ip4dst =
-				cpu_to_be32(rule->tuples.dst_ip[3]);
+				cpu_to_be32(rule->tuples.dst_ip[IPV4_INDEX]);
 		fs->m_u.usr_ip4_spec.ip4dst =
-				rule->unused_tuple & BIT(INNER_DST_IP) ?
-				0 : cpu_to_be32(rule->tuples_mask.dst_ip[3]);
+			rule->unused_tuple & BIT(INNER_DST_IP) ?
+			0 : cpu_to_be32(rule->tuples_mask.dst_ip[IPV4_INDEX]);
 
 		fs->h_u.usr_ip4_spec.tos = rule->tuples.ip_tos;
 		fs->m_u.usr_ip4_spec.tos =
@@ -4929,20 +5558,22 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 	case TCP_V6_FLOW:
 	case UDP_V6_FLOW:
 		cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6src,
-				  rule->tuples.src_ip, 4);
+				  rule->tuples.src_ip, IPV6_SIZE);
 		if (rule->unused_tuple & BIT(INNER_SRC_IP))
-			memset(fs->m_u.tcp_ip6_spec.ip6src, 0, sizeof(int) * 4);
+			memset(fs->m_u.tcp_ip6_spec.ip6src, 0,
+			       sizeof(int) * IPV6_SIZE);
 		else
 			cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6src,
-					  rule->tuples_mask.src_ip, 4);
+					  rule->tuples_mask.src_ip, IPV6_SIZE);
 
 		cpu_to_be32_array(fs->h_u.tcp_ip6_spec.ip6dst,
-				  rule->tuples.dst_ip, 4);
+				  rule->tuples.dst_ip, IPV6_SIZE);
 		if (rule->unused_tuple & BIT(INNER_DST_IP))
-			memset(fs->m_u.tcp_ip6_spec.ip6dst, 0, sizeof(int) * 4);
+			memset(fs->m_u.tcp_ip6_spec.ip6dst, 0,
+			       sizeof(int) * IPV6_SIZE);
 		else
 			cpu_to_be32_array(fs->m_u.tcp_ip6_spec.ip6dst,
-					  rule->tuples_mask.dst_ip, 4);
+					  rule->tuples_mask.dst_ip, IPV6_SIZE);
 
 		fs->h_u.tcp_ip6_spec.psrc = cpu_to_be16(rule->tuples.src_port);
 		fs->m_u.tcp_ip6_spec.psrc =
@@ -4957,20 +5588,22 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 		break;
 	case IPV6_USER_FLOW:
 		cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6src,
-				  rule->tuples.src_ip, 4);
+				  rule->tuples.src_ip, IPV6_SIZE);
 		if (rule->unused_tuple & BIT(INNER_SRC_IP))
-			memset(fs->m_u.usr_ip6_spec.ip6src, 0, sizeof(int) * 4);
+			memset(fs->m_u.usr_ip6_spec.ip6src, 0,
+			       sizeof(int) * IPV6_SIZE);
 		else
 			cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6src,
-					  rule->tuples_mask.src_ip, 4);
+					  rule->tuples_mask.src_ip, IPV6_SIZE);
 
 		cpu_to_be32_array(fs->h_u.usr_ip6_spec.ip6dst,
-				  rule->tuples.dst_ip, 4);
+				  rule->tuples.dst_ip, IPV6_SIZE);
 		if (rule->unused_tuple & BIT(INNER_DST_IP))
-			memset(fs->m_u.usr_ip6_spec.ip6dst, 0, sizeof(int) * 4);
+			memset(fs->m_u.usr_ip6_spec.ip6dst, 0,
+			       sizeof(int) * IPV6_SIZE);
 		else
 			cpu_to_be32_array(fs->m_u.usr_ip6_spec.ip6dst,
-					  rule->tuples_mask.dst_ip, 4);
+					  rule->tuples_mask.dst_ip, IPV6_SIZE);
 
 		fs->h_u.usr_ip6_spec.l4_proto = rule->tuples.ip_proto;
 		fs->m_u.usr_ip6_spec.l4_proto =
@@ -5003,6 +5636,7 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 
 		break;
 	default:
+		spin_unlock_bh(&hdev->fd_rule_lock);
 		return -EOPNOTSUPP;
 	}
 
@@ -5034,6 +5668,8 @@ static int hclge_get_fd_rule_info(struct hnae3_handle *handle,
 		fs->ring_cookie |= vf_id;
 	}
 
+	spin_unlock_bh(&hdev->fd_rule_lock);
+
 	return 0;
 }
 
@@ -5051,20 +5687,208 @@ static int hclge_get_all_rules(struct hnae3_handle *handle,
 
 	cmd->data = hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1];
 
+	spin_lock_bh(&hdev->fd_rule_lock);
 	hlist_for_each_entry_safe(rule, node2,
 				  &hdev->fd_rule_list, rule_node) {
-		if (cnt == cmd->rule_cnt)
+		if (cnt == cmd->rule_cnt) {
+			spin_unlock_bh(&hdev->fd_rule_lock);
 			return -EMSGSIZE;
+		}
 
 		rule_locs[cnt] = rule->location;
 		cnt++;
 	}
 
+	spin_unlock_bh(&hdev->fd_rule_lock);
+
 	cmd->rule_cnt = cnt;
 
 	return 0;
 }
 
+static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys,
+				     struct hclge_fd_rule_tuples *tuples)
+{
+	tuples->ether_proto = be16_to_cpu(fkeys->basic.n_proto);
+	tuples->ip_proto = fkeys->basic.ip_proto;
+	tuples->dst_port = be16_to_cpu(fkeys->ports.dst);
+
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		tuples->src_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.src);
+		tuples->dst_ip[3] = be32_to_cpu(fkeys->addrs.v4addrs.dst);
+	} else {
+		memcpy(tuples->src_ip,
+		       fkeys->addrs.v6addrs.src.in6_u.u6_addr32,
+		       sizeof(tuples->src_ip));
+		memcpy(tuples->dst_ip,
+		       fkeys->addrs.v6addrs.dst.in6_u.u6_addr32,
+		       sizeof(tuples->dst_ip));
+	}
+}
+
+/* traverse all rules, check whether an existed rule has the same tuples */
+static struct hclge_fd_rule *
+hclge_fd_search_flow_keys(struct hclge_dev *hdev,
+			  const struct hclge_fd_rule_tuples *tuples)
+{
+	struct hclge_fd_rule *rule = NULL;
+	struct hlist_node *node;
+
+	hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) {
+		if (!memcmp(tuples, &rule->tuples, sizeof(*tuples)))
+			return rule;
+	}
+
+	return NULL;
+}
+
+static void hclge_fd_build_arfs_rule(const struct hclge_fd_rule_tuples *tuples,
+				     struct hclge_fd_rule *rule)
+{
+	rule->unused_tuple = BIT(INNER_SRC_MAC) | BIT(INNER_DST_MAC) |
+			     BIT(INNER_VLAN_TAG_FST) | BIT(INNER_IP_TOS) |
+			     BIT(INNER_SRC_PORT);
+	rule->action = 0;
+	rule->vf_id = 0;
+	rule->rule_type = HCLGE_FD_ARFS_ACTIVE;
+	if (tuples->ether_proto == ETH_P_IP) {
+		if (tuples->ip_proto == IPPROTO_TCP)
+			rule->flow_type = TCP_V4_FLOW;
+		else
+			rule->flow_type = UDP_V4_FLOW;
+	} else {
+		if (tuples->ip_proto == IPPROTO_TCP)
+			rule->flow_type = TCP_V6_FLOW;
+		else
+			rule->flow_type = UDP_V6_FLOW;
+	}
+	memcpy(&rule->tuples, tuples, sizeof(rule->tuples));
+	memset(&rule->tuples_mask, 0xFF, sizeof(rule->tuples_mask));
+}
+
+static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id,
+				      u16 flow_id, struct flow_keys *fkeys)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_fd_rule_tuples new_tuples;
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_fd_rule *rule;
+	u16 tmp_queue_id;
+	u16 bit_id;
+	int ret;
+
+	if (!hnae3_dev_fd_supported(hdev))
+		return -EOPNOTSUPP;
+
+	memset(&new_tuples, 0, sizeof(new_tuples));
+	hclge_fd_get_flow_tuples(fkeys, &new_tuples);
+
+	spin_lock_bh(&hdev->fd_rule_lock);
+
+	/* when there is already fd rule existed add by user,
+	 * arfs should not work
+	 */
+	if (hdev->fd_active_type == HCLGE_FD_EP_ACTIVE) {
+		spin_unlock_bh(&hdev->fd_rule_lock);
+
+		return -EOPNOTSUPP;
+	}
+
+	/* check is there flow director filter existed for this flow,
+	 * if not, create a new filter for it;
+	 * if filter exist with different queue id, modify the filter;
+	 * if filter exist with same queue id, do nothing
+	 */
+	rule = hclge_fd_search_flow_keys(hdev, &new_tuples);
+	if (!rule) {
+		bit_id = find_first_zero_bit(hdev->fd_bmap, MAX_FD_FILTER_NUM);
+		if (bit_id >= hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) {
+			spin_unlock_bh(&hdev->fd_rule_lock);
+
+			return -ENOSPC;
+		}
+
+		rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+		if (!rule) {
+			spin_unlock_bh(&hdev->fd_rule_lock);
+
+			return -ENOMEM;
+		}
+
+		set_bit(bit_id, hdev->fd_bmap);
+		rule->location = bit_id;
+		rule->flow_id = flow_id;
+		rule->queue_id = queue_id;
+		hclge_fd_build_arfs_rule(&new_tuples, rule);
+		ret = hclge_fd_config_rule(hdev, rule);
+
+		spin_unlock_bh(&hdev->fd_rule_lock);
+
+		if (ret)
+			return ret;
+
+		return rule->location;
+	}
+
+	spin_unlock_bh(&hdev->fd_rule_lock);
+
+	if (rule->queue_id == queue_id)
+		return rule->location;
+
+	tmp_queue_id = rule->queue_id;
+	rule->queue_id = queue_id;
+	ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
+	if (ret) {
+		rule->queue_id = tmp_queue_id;
+		return ret;
+	}
+
+	return rule->location;
+}
+
+static void hclge_rfs_filter_expire(struct hclge_dev *hdev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct hnae3_handle *handle = &hdev->vport[0].nic;
+	struct hclge_fd_rule *rule;
+	struct hlist_node *node;
+	HLIST_HEAD(del_list);
+
+	spin_lock_bh(&hdev->fd_rule_lock);
+	if (hdev->fd_active_type != HCLGE_FD_ARFS_ACTIVE) {
+		spin_unlock_bh(&hdev->fd_rule_lock);
+		return;
+	}
+	hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) {
+		if (rps_may_expire_flow(handle->netdev, rule->queue_id,
+					rule->flow_id, rule->location)) {
+			hlist_del_init(&rule->rule_node);
+			hlist_add_head(&rule->rule_node, &del_list);
+			hdev->hclge_fd_rule_num--;
+			clear_bit(rule->location, hdev->fd_bmap);
+		}
+	}
+	spin_unlock_bh(&hdev->fd_rule_lock);
+
+	hlist_for_each_entry_safe(rule, node, &del_list, rule_node) {
+		hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true,
+				     rule->location, NULL, false);
+		kfree(rule);
+	}
+#endif
+}
+
+static void hclge_clear_arfs_rules(struct hnae3_handle *handle)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	if (hdev->fd_active_type == HCLGE_FD_ARFS_ACTIVE)
+		hclge_del_all_fd_entries(handle, true);
+#endif
+}
+
 static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -5087,17 +5911,19 @@ static unsigned long hclge_ae_dev_reset_cnt(struct hnae3_handle *handle)
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	return hdev->reset_count;
+	return hdev->rst_stats.hw_reset_done_cnt;
 }
 
 static void hclge_enable_fd(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
+	bool clear;
 
-	hdev->fd_cfg.fd_en = enable;
+	hdev->fd_en = enable;
+	clear = hdev->fd_active_type == HCLGE_FD_ARFS_ACTIVE ? true : false;
 	if (!enable)
-		hclge_del_all_fd_entries(handle, false);
+		hclge_del_all_fd_entries(handle, clear);
 	else
 		hclge_restore_fd_entries(handle);
 }
@@ -5111,20 +5937,20 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable)
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false);
-	hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
-	hnae3_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
-	hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
-	hnae3_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
-	hnae3_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
-	hnae3_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
+
+	if (enable) {
+		hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, 1U);
+		hnae3_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, 1U);
+	}
+
 	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -5174,8 +6000,15 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
 {
 #define HCLGE_SERDES_RETRY_MS	10
 #define HCLGE_SERDES_RETRY_NUM	100
+
+#define HCLGE_MAC_LINK_STATUS_MS   10
+#define HCLGE_MAC_LINK_STATUS_NUM  100
+#define HCLGE_MAC_LINK_STATUS_DOWN 0
+#define HCLGE_MAC_LINK_STATUS_UP   1
+
 	struct hclge_serdes_lb_cmd *req;
 	struct hclge_desc desc;
+	int mac_link_ret = 0;
 	int ret, i = 0;
 	u8 loop_mode_b;
 
@@ -5198,8 +6031,10 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
 	if (en) {
 		req->enable = loop_mode_b;
 		req->mask = loop_mode_b;
+		mac_link_ret = HCLGE_MAC_LINK_STATUS_UP;
 	} else {
 		req->mask = loop_mode_b;
+		mac_link_ret = HCLGE_MAC_LINK_STATUS_DOWN;
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -5231,10 +6066,22 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
 	}
 
 	hclge_cfg_mac_mode(hdev, en);
-	return 0;
+
+	i = 0;
+	do {
+		/* serdes Internal loopback, independent of the network cable.*/
+		msleep(HCLGE_MAC_LINK_STATUS_MS);
+		ret = hclge_get_mac_link_status(hdev);
+		if (ret == mac_link_ret)
+			return 0;
+	} while (++i < HCLGE_MAC_LINK_STATUS_NUM);
+
+	dev_err(&hdev->pdev->dev, "config mac mode timeout\n");
+
+	return -EBUSY;
 }
 
-static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id,
+static int hclge_tqp_enable(struct hclge_dev *hdev, unsigned int tqp_id,
 			    int stream_id, bool enable)
 {
 	struct hclge_desc desc;
@@ -5245,7 +6092,8 @@ static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id,
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false);
 	req->tqp_id = cpu_to_le16(tqp_id & HCLGE_RING_ID_MASK);
 	req->stream_id = cpu_to_le16(stream_id);
-	req->enable |= enable << HCLGE_TQP_ENABLE_B;
+	if (enable)
+		req->enable |= 1U << HCLGE_TQP_ENABLE_B;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
@@ -5258,6 +6106,7 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 			      enum hnae3_loop loop_mode, bool en)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hnae3_knic_private_info *kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, ret;
 
@@ -5276,7 +6125,11 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 		break;
 	}
 
-	for (i = 0; i < vport->alloc_tqps; i++) {
+	if (ret)
+		return ret;
+
+	kinfo = &vport->nic.kinfo;
+	for (i = 0; i < kinfo->num_tqps; i++) {
 		ret = hclge_tqp_enable(hdev, i, 0, en);
 		if (ret)
 			return ret;
@@ -5288,11 +6141,13 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 static void hclge_reset_tqp_stats(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hnae3_knic_private_info *kinfo;
 	struct hnae3_queue *queue;
 	struct hclge_tqp *tqp;
 	int i;
 
-	for (i = 0; i < vport->alloc_tqps; i++) {
+	kinfo = &vport->nic.kinfo;
+	for (i = 0; i < kinfo->num_tqps; i++) {
 		queue = handle->kinfo.tqp[i];
 		tqp = container_of(queue, struct hclge_tqp, q);
 		memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats));
@@ -5339,6 +6194,8 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 
+	hclge_clear_arfs_rules(handle);
+
 	/* If it is not PF reset, the firmware will disable the MAC,
 	 * so it only need to stop phy here.
 	 */
@@ -5404,11 +6261,11 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport,
 	if (op == HCLGE_MAC_VLAN_ADD) {
 		if ((!resp_code) || (resp_code == 1)) {
 			return_status = 0;
-		} else if (resp_code == 2) {
+		} else if (resp_code == HCLGE_ADD_UC_OVERFLOW) {
 			return_status = -ENOSPC;
 			dev_err(&hdev->pdev->dev,
 				"add mac addr failed for uc_overflow.\n");
-		} else if (resp_code == 3) {
+		} else if (resp_code == HCLGE_ADD_MC_OVERFLOW) {
 			return_status = -ENOSPC;
 			dev_err(&hdev->pdev->dev,
 				"add mac addr failed for mc_overflow.\n");
@@ -5453,13 +6310,15 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport,
 
 static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr)
 {
-	int word_num;
-	int bit_num;
+#define HCLGE_VF_NUM_IN_FIRST_DESC 192
+
+	unsigned int word_num;
+	unsigned int bit_num;
 
 	if (vfid > 255 || vfid < 0)
 		return -EIO;
 
-	if (vfid >= 0 && vfid <= 191) {
+	if (vfid >= 0 && vfid < HCLGE_VF_NUM_IN_FIRST_DESC) {
 		word_num = vfid / 32;
 		bit_num  = vfid % 32;
 		if (clr)
@@ -5467,7 +6326,7 @@ static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr)
 		else
 			desc[1].data[word_num] |= cpu_to_le32(1 << bit_num);
 	} else {
-		word_num = (vfid - 192) / 32;
+		word_num = (vfid - HCLGE_VF_NUM_IN_FIRST_DESC) / 32;
 		bit_num  = vfid % 32;
 		if (clr)
 			desc[2].data[word_num] &= cpu_to_le32(~(1 << bit_num));
@@ -5493,13 +6352,19 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc)
 }
 
 static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req,
-				   const u8 *addr)
+				   const u8 *addr, bool is_mc)
 {
 	const unsigned char *mac_addr = addr;
 	u32 high_val = mac_addr[2] << 16 | (mac_addr[3] << 24) |
 		       (mac_addr[0]) | (mac_addr[1] << 8);
 	u32 low_val  = mac_addr[4] | (mac_addr[5] << 8);
 
+	hnae3_set_bit(new_req->flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	if (is_mc) {
+		hnae3_set_bit(new_req->entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+		hnae3_set_bit(new_req->mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	}
+
 	new_req->mac_addr_hi32 = cpu_to_le32(high_val);
 	new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff);
 }
@@ -5644,6 +6509,10 @@ static int hclge_init_umv_space(struct hclge_dev *hdev)
 
 	mutex_init(&hdev->umv_mutex);
 	hdev->max_umv_size = allocated_size;
+	/* divide max_umv_size by (hdev->num_req_vfs + 2), in order to
+	 * preserve some unicast mac vlan table entries shared by pf
+	 * and its vfs.
+	 */
 	hdev->priv_umv_size = hdev->max_umv_size / (hdev->num_req_vfs + 2);
 	hdev->share_umv_size = hdev->priv_umv_size +
 			hdev->max_umv_size % (hdev->num_req_vfs + 2);
@@ -5676,7 +6545,9 @@ static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
 
 	req = (struct hclge_umv_spc_alc_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_ALLOCATE, false);
-	hnae3_set_bit(req->allocate, HCLGE_UMV_SPC_ALC_B, !is_alloc);
+	if (!is_alloc)
+		hnae3_set_bit(req->allocate, HCLGE_UMV_SPC_ALC_B, 1);
+
 	req->space_size = cpu_to_le32(space_size);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -5730,9 +6601,12 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free)
 	if (is_free) {
 		if (vport->used_umv_num > hdev->priv_umv_size)
 			hdev->share_umv_size++;
-		vport->used_umv_num--;
+
+		if (vport->used_umv_num > 0)
+			vport->used_umv_num--;
 	} else {
-		if (vport->used_umv_num >= hdev->priv_umv_size)
+		if (vport->used_umv_num >= hdev->priv_umv_size &&
+		    hdev->share_umv_size > 0)
 			hdev->share_umv_size--;
 		vport->used_umv_num++;
 	}
@@ -5762,22 +6636,20 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 	    is_multicast_ether_addr(addr)) {
 		dev_err(&hdev->pdev->dev,
 			"Set_uc mac err! invalid mac:%pM. is_zero:%d,is_br=%d,is_mul=%d\n",
-			 addr,
-			 is_zero_ether_addr(addr),
+			 addr, is_zero_ether_addr(addr),
 			 is_broadcast_ether_addr(addr),
 			 is_multicast_ether_addr(addr));
 		return -EINVAL;
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 
 	hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
 			HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
 
 	req.egress_port = cpu_to_le16(egress_port);
 
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, false);
 
 	/* Lookup the mac address in the mac_vlan table, and add
 	 * it if the entry is inexistent. Repeated unicast entry
@@ -5799,8 +6671,11 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 	}
 
 	/* check if we just hit the duplicate */
-	if (!ret)
-		ret = -EINVAL;
+	if (!ret) {
+		dev_warn(&hdev->pdev->dev, "VF %d mac(%pM) exists\n",
+			 vport->vport_id, addr);
+		return 0;
+	}
 
 	dev_err(&hdev->pdev->dev,
 		"PF failed to add unicast entry(%pM) in the MAC table\n",
@@ -5828,16 +6703,14 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport,
 	if (is_zero_ether_addr(addr) ||
 	    is_broadcast_ether_addr(addr) ||
 	    is_multicast_ether_addr(addr)) {
-		dev_dbg(&hdev->pdev->dev,
-			"Remove mac err! invalid mac:%pM.\n",
-			 addr);
+		dev_dbg(&hdev->pdev->dev, "Remove mac err! invalid mac:%pM.\n",
+			addr);
 		return -EINVAL;
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, false);
 	ret = hclge_remove_mac_vlan_tbl(vport, &req);
 	if (!ret)
 		hclge_update_umv_space(vport, true);
@@ -5869,24 +6742,19 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport,
 		return -EINVAL;
 	}
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, true);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
-	if (!status) {
-		/* This mac addr exist, update VFID for it */
-		hclge_update_desc_vfid(desc, vport->vport_id, false);
-		status = hclge_add_mac_vlan_tbl(vport, &req, desc);
-	} else {
+	if (status) {
 		/* This mac addr do not exist, add new entry for it */
 		memset(desc[0].data, 0, sizeof(desc[0].data));
 		memset(desc[1].data, 0, sizeof(desc[0].data));
 		memset(desc[2].data, 0, sizeof(desc[0].data));
-		hclge_update_desc_vfid(desc, vport->vport_id, false);
-		status = hclge_add_mac_vlan_tbl(vport, &req, desc);
 	}
+	status = hclge_update_desc_vfid(desc, vport->vport_id, false);
+	if (status)
+		return status;
+	status = hclge_add_mac_vlan_tbl(vport, &req, desc);
 
 	if (status == -ENOSPC)
 		dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n");
@@ -5919,15 +6787,14 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, true);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
 	if (!status) {
 		/* This mac addr exist, remove this handle's VFID for it */
-		hclge_update_desc_vfid(desc, vport->vport_id, true);
+		status = hclge_update_desc_vfid(desc, vport->vport_id, true);
+		if (status)
+			return status;
 
 		if (hclge_is_all_function_id_zero(desc))
 			/* All the vfid is zero, so need to delete this entry */
@@ -5949,6 +6816,103 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 	return status;
 }
 
+void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			       enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_vport_mac_addr_cfg *mac_cfg;
+	struct list_head *list;
+
+	if (!vport->vport_id)
+		return;
+
+	mac_cfg = kzalloc(sizeof(*mac_cfg), GFP_KERNEL);
+	if (!mac_cfg)
+		return;
+
+	mac_cfg->hd_tbl_status = true;
+	memcpy(mac_cfg->mac_addr, mac_addr, ETH_ALEN);
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+	       &vport->uc_mac_list : &vport->mc_mac_list;
+
+	list_add_tail(&mac_cfg->node, list);
+}
+
+void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			      bool is_write_tbl,
+			      enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp;
+	struct list_head *list;
+	bool uc_flag, mc_flag;
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+	       &vport->uc_mac_list : &vport->mc_mac_list;
+
+	uc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_UC;
+	mc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_MC;
+
+	list_for_each_entry_safe(mac_cfg, tmp, list, node) {
+		if (strncmp(mac_cfg->mac_addr, mac_addr, ETH_ALEN) == 0) {
+			if (uc_flag && mac_cfg->hd_tbl_status)
+				hclge_rm_uc_addr_common(vport, mac_addr);
+
+			if (mc_flag && mac_cfg->hd_tbl_status)
+				hclge_rm_mc_addr_common(vport, mac_addr);
+
+			list_del(&mac_cfg->node);
+			kfree(mac_cfg);
+			break;
+		}
+	}
+}
+
+void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
+				  enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp;
+	struct list_head *list;
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+	       &vport->uc_mac_list : &vport->mc_mac_list;
+
+	list_for_each_entry_safe(mac_cfg, tmp, list, node) {
+		if (mac_type == HCLGE_MAC_ADDR_UC && mac_cfg->hd_tbl_status)
+			hclge_rm_uc_addr_common(vport, mac_cfg->mac_addr);
+
+		if (mac_type == HCLGE_MAC_ADDR_MC && mac_cfg->hd_tbl_status)
+			hclge_rm_mc_addr_common(vport, mac_cfg->mac_addr);
+
+		mac_cfg->hd_tbl_status = false;
+		if (is_del_list) {
+			list_del(&mac_cfg->node);
+			kfree(mac_cfg);
+		}
+	}
+}
+
+void hclge_uninit_vport_mac_table(struct hclge_dev *hdev)
+{
+	struct hclge_vport_mac_addr_cfg *mac, *tmp;
+	struct hclge_vport *vport;
+	int i;
+
+	mutex_lock(&hdev->vport_cfg_mutex);
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		vport = &hdev->vport[i];
+		list_for_each_entry_safe(mac, tmp, &vport->uc_mac_list, node) {
+			list_del(&mac->node);
+			kfree(mac);
+		}
+
+		list_for_each_entry_safe(mac, tmp, &vport->mc_mac_list, node) {
+			list_del(&mac->node);
+			kfree(mac);
+		}
+	}
+	mutex_unlock(&hdev->vport_cfg_mutex);
+}
+
 static int hclge_get_mac_ethertype_cmd_status(struct hclge_dev *hdev,
 					      u16 cmdq_resp, u8 resp_code)
 {
@@ -6060,7 +7024,8 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p,
 		return -EINVAL;
 	}
 
-	if (!is_first && hclge_rm_uc_addr(handle, hdev->hw.mac.mac_addr))
+	if ((!is_first || is_kdump_kernel()) &&
+	    hclge_rm_uc_addr(handle, hdev->hw.mac.mac_addr))
 		dev_warn(&hdev->pdev->dev,
 			 "remove old uc mac address fail.\n");
 
@@ -6104,7 +7069,7 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr,
 }
 
 static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
-				      u8 fe_type, bool filter_en)
+				      u8 fe_type, bool filter_en, u8 vf_id)
 {
 	struct hclge_vlan_filter_ctrl_cmd *req;
 	struct hclge_desc desc;
@@ -6115,6 +7080,7 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 	req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data;
 	req->vlan_type = vlan_type;
 	req->vlan_fe = filter_en ? fe_type : 0;
+	req->vf_id = vf_id;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
@@ -6143,12 +7109,13 @@ static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
 
 	if (hdev->pdev->revision >= 0x21) {
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-					   HCLGE_FILTER_FE_EGRESS, enable);
+					   HCLGE_FILTER_FE_EGRESS, enable, 0);
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
-					   HCLGE_FILTER_FE_INGRESS, enable);
+					   HCLGE_FILTER_FE_INGRESS, enable, 0);
 	} else {
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-					   HCLGE_FILTER_FE_EGRESS_V1_B, enable);
+					   HCLGE_FILTER_FE_EGRESS_V1_B, enable,
+					   0);
 	}
 	if (enable)
 		handle->netdev_flags |= HNAE3_VLAN_FLTR;
@@ -6156,7 +7123,7 @@ static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
 		handle->netdev_flags &= ~HNAE3_VLAN_FLTR;
 }
 
-static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
+static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, u16 vfid,
 				    bool is_kill, u16 vlan, u8 qos,
 				    __be16 proto)
 {
@@ -6168,6 +7135,12 @@ static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
 	u8 vf_byte_off;
 	int ret;
 
+	/* if vf vlan table is full, firmware will close vf vlan filter, it
+	 * is unable and unnecessary to add new vlan id to vf vlan filter
+	 */
+	if (test_bit(vfid, hdev->vf_vlan_full) && !is_kill)
+		return 0;
+
 	hclge_cmd_setup_basic_desc(&desc[0],
 				   HCLGE_OPC_VLAN_FILTER_VF_CFG, false);
 	hclge_cmd_setup_basic_desc(&desc[1],
@@ -6203,6 +7176,7 @@ static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
 			return 0;
 
 		if (req0->resp_code == HCLGE_VF_VLAN_NO_ENTRY) {
+			set_bit(vfid, hdev->vf_vlan_full);
 			dev_warn(&hdev->pdev->dev,
 				 "vf vlan table is full, vf vlan filter is disabled\n");
 			return 0;
@@ -6216,12 +7190,13 @@ static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid,
 		if (!req0->resp_code)
 			return 0;
 
-		if (req0->resp_code == HCLGE_VF_VLAN_DEL_NO_FOUND) {
-			dev_warn(&hdev->pdev->dev,
-				 "vlan %d filter is not in vf vlan table\n",
-				 vlan);
+		/* vf vlan filter is disabled when vf vlan table is full,
+		 * then new vlan id will not be added into vf vlan table.
+		 * Just return 0 without warning, avoid massive verbose
+		 * print logs when unload.
+		 */
+		if (req0->resp_code == HCLGE_VF_VLAN_DEL_NO_FOUND)
 			return 0;
-		}
 
 		dev_err(&hdev->pdev->dev,
 			"Kill vf vlan filter fail, ret =%d.\n",
@@ -6308,30 +7283,6 @@ static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto,
 	return ret;
 }
 
-int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
-			  u16 vlan_id, bool is_kill)
-{
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
-
-	return hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id, vlan_id,
-					0, is_kill);
-}
-
-static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
-				    u16 vlan, u8 qos, __be16 proto)
-{
-	struct hclge_vport *vport = hclge_get_vport(handle);
-	struct hclge_dev *hdev = vport->back;
-
-	if ((vfid >= hdev->num_alloc_vfs) || (vlan > 4095) || (qos > 7))
-		return -EINVAL;
-	if (proto != htons(ETH_P_8021Q))
-		return -EPROTONOSUPPORT;
-
-	return hclge_set_vlan_filter_hw(hdev, proto, vfid, vlan, qos, false);
-}
-
 static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport)
 {
 	struct hclge_tx_vtag_cfg *vcfg = &vport->txvlan_cfg;
@@ -6405,6 +7356,52 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport)
 	return status;
 }
 
+static int hclge_vlan_offload_cfg(struct hclge_vport *vport,
+				  u16 port_base_vlan_state,
+				  u16 vlan_tag)
+{
+	int ret;
+
+	if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+		vport->txvlan_cfg.accept_tag1 = true;
+		vport->txvlan_cfg.insert_tag1_en = false;
+		vport->txvlan_cfg.default_tag1 = 0;
+	} else {
+		vport->txvlan_cfg.accept_tag1 = false;
+		vport->txvlan_cfg.insert_tag1_en = true;
+		vport->txvlan_cfg.default_tag1 = vlan_tag;
+	}
+
+	vport->txvlan_cfg.accept_untag1 = true;
+
+	/* accept_tag2 and accept_untag2 are not supported on
+	 * pdev revision(0x20), new revision support them,
+	 * this two fields can not be configured by user.
+	 */
+	vport->txvlan_cfg.accept_tag2 = true;
+	vport->txvlan_cfg.accept_untag2 = true;
+	vport->txvlan_cfg.insert_tag2_en = false;
+	vport->txvlan_cfg.default_tag2 = 0;
+
+	if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+		vport->rxvlan_cfg.strip_tag1_en = false;
+		vport->rxvlan_cfg.strip_tag2_en =
+				vport->rxvlan_cfg.rx_vlan_offload_en;
+	} else {
+		vport->rxvlan_cfg.strip_tag1_en =
+				vport->rxvlan_cfg.rx_vlan_offload_en;
+		vport->rxvlan_cfg.strip_tag2_en = true;
+	}
+	vport->rxvlan_cfg.vlan1_vlan_prionly = false;
+	vport->rxvlan_cfg.vlan2_vlan_prionly = false;
+
+	ret = hclge_set_vlan_tx_offload_cfg(vport);
+	if (ret)
+		return ret;
+
+	return hclge_set_vlan_rx_offload_cfg(vport);
+}
+
 static int hclge_set_vlan_protocol_type(struct hclge_dev *hdev)
 {
 	struct hclge_rx_vlan_type_cfg_cmd *rx_req;
@@ -6456,19 +7453,27 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 	int i;
 
 	if (hdev->pdev->revision >= 0x21) {
-		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-						 HCLGE_FILTER_FE_EGRESS, true);
-		if (ret)
-			return ret;
+		/* for revision 0x21, vf vlan filter is per function */
+		for (i = 0; i < hdev->num_alloc_vport; i++) {
+			vport = &hdev->vport[i];
+			ret = hclge_set_vlan_filter_ctrl(hdev,
+							 HCLGE_FILTER_TYPE_VF,
+							 HCLGE_FILTER_FE_EGRESS,
+							 true,
+							 vport->vport_id);
+			if (ret)
+				return ret;
+		}
 
 		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
-						 HCLGE_FILTER_FE_INGRESS, true);
+						 HCLGE_FILTER_FE_INGRESS, true,
+						 0);
 		if (ret)
 			return ret;
 	} else {
 		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
 						 HCLGE_FILTER_FE_EGRESS_V1_B,
-						 true);
+						 true, 0);
 		if (ret)
 			return ret;
 	}
@@ -6487,53 +7492,404 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 		return ret;
 
 	for (i = 0; i < hdev->num_alloc_vport; i++) {
-		vport = &hdev->vport[i];
-		vport->txvlan_cfg.accept_tag1 = true;
-		vport->txvlan_cfg.accept_untag1 = true;
+		u16 vlan_tag;
 
-		/* accept_tag2 and accept_untag2 are not supported on
-		 * pdev revision(0x20), new revision support them. The
-		 * value of this two fields will not return error when driver
-		 * send command to fireware in revision(0x20).
-		 * This two fields can not configured by user.
-		 */
-		vport->txvlan_cfg.accept_tag2 = true;
-		vport->txvlan_cfg.accept_untag2 = true;
-
-		vport->txvlan_cfg.insert_tag1_en = false;
-		vport->txvlan_cfg.insert_tag2_en = false;
-		vport->txvlan_cfg.default_tag1 = 0;
-		vport->txvlan_cfg.default_tag2 = 0;
+		vport = &hdev->vport[i];
+		vlan_tag = vport->port_base_vlan_cfg.vlan_info.vlan_tag;
 
-		ret = hclge_set_vlan_tx_offload_cfg(vport);
+		ret = hclge_vlan_offload_cfg(vport,
+					     vport->port_base_vlan_cfg.state,
+					     vlan_tag);
 		if (ret)
 			return ret;
+	}
 
-		vport->rxvlan_cfg.strip_tag1_en = false;
-		vport->rxvlan_cfg.strip_tag2_en = true;
-		vport->rxvlan_cfg.vlan1_vlan_prionly = false;
-		vport->rxvlan_cfg.vlan2_vlan_prionly = false;
+	return hclge_set_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
+}
 
-		ret = hclge_set_vlan_rx_offload_cfg(vport);
-		if (ret)
-			return ret;
+static void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
+				       bool writen_to_tbl)
+{
+	struct hclge_vport_vlan_cfg *vlan;
+
+	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		return;
+
+	vlan->hd_tbl_status = writen_to_tbl;
+	vlan->vlan_id = vlan_id;
+
+	list_add_tail(&vlan->node, &vport->vlan_list);
+}
+
+static int hclge_add_vport_all_vlan_table(struct hclge_vport *vport)
+{
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+		if (!vlan->hd_tbl_status) {
+			ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
+						       vport->vport_id,
+						       vlan->vlan_id, 0, false);
+			if (ret) {
+				dev_err(&hdev->pdev->dev,
+					"restore vport vlan list failed, ret=%d\n",
+					ret);
+				return ret;
+			}
+		}
+		vlan->hd_tbl_status = true;
 	}
 
-	return hclge_set_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
+	return 0;
+}
+
+static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
+				      bool is_write_tbl)
+{
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_dev *hdev = vport->back;
+
+	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+		if (vlan->vlan_id == vlan_id) {
+			if (is_write_tbl && vlan->hd_tbl_status)
+				hclge_set_vlan_filter_hw(hdev,
+							 htons(ETH_P_8021Q),
+							 vport->vport_id,
+							 vlan_id, 0,
+							 true);
+
+			list_del(&vlan->node);
+			kfree(vlan);
+			break;
+		}
+	}
+}
+
+void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list)
+{
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_dev *hdev = vport->back;
+
+	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+		if (vlan->hd_tbl_status)
+			hclge_set_vlan_filter_hw(hdev,
+						 htons(ETH_P_8021Q),
+						 vport->vport_id,
+						 vlan->vlan_id, 0,
+						 true);
+
+		vlan->hd_tbl_status = false;
+		if (is_del_list) {
+			list_del(&vlan->node);
+			kfree(vlan);
+		}
+	}
+}
+
+void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev)
+{
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_vport *vport;
+	int i;
+
+	mutex_lock(&hdev->vport_cfg_mutex);
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		vport = &hdev->vport[i];
+		list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+			list_del(&vlan->node);
+			kfree(vlan);
+		}
+	}
+	mutex_unlock(&hdev->vport_cfg_mutex);
+}
+
+static void hclge_restore_vlan_table(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_dev *hdev = vport->back;
+	u16 vlan_proto, qos;
+	u16 state, vlan_id;
+	int i;
+
+	mutex_lock(&hdev->vport_cfg_mutex);
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		vport = &hdev->vport[i];
+		vlan_proto = vport->port_base_vlan_cfg.vlan_info.vlan_proto;
+		vlan_id = vport->port_base_vlan_cfg.vlan_info.vlan_tag;
+		qos = vport->port_base_vlan_cfg.vlan_info.qos;
+		state = vport->port_base_vlan_cfg.state;
+
+		if (state != HNAE3_PORT_BASE_VLAN_DISABLE) {
+			hclge_set_vlan_filter_hw(hdev, htons(vlan_proto),
+						 vport->vport_id, vlan_id, qos,
+						 false);
+			continue;
+		}
+
+		list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+			if (vlan->hd_tbl_status)
+				hclge_set_vlan_filter_hw(hdev,
+							 htons(ETH_P_8021Q),
+							 vport->vport_id,
+							 vlan->vlan_id, 0,
+							 false);
+		}
+	}
+
+	mutex_unlock(&hdev->vport_cfg_mutex);
 }
 
 int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 
-	vport->rxvlan_cfg.strip_tag1_en = false;
-	vport->rxvlan_cfg.strip_tag2_en = enable;
+	if (vport->port_base_vlan_cfg.state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+		vport->rxvlan_cfg.strip_tag1_en = false;
+		vport->rxvlan_cfg.strip_tag2_en = enable;
+	} else {
+		vport->rxvlan_cfg.strip_tag1_en = enable;
+		vport->rxvlan_cfg.strip_tag2_en = true;
+	}
 	vport->rxvlan_cfg.vlan1_vlan_prionly = false;
 	vport->rxvlan_cfg.vlan2_vlan_prionly = false;
+	vport->rxvlan_cfg.rx_vlan_offload_en = enable;
 
 	return hclge_set_vlan_rx_offload_cfg(vport);
 }
 
+static int hclge_update_vlan_filter_entries(struct hclge_vport *vport,
+					    u16 port_base_vlan_state,
+					    struct hclge_vlan_info *new_info,
+					    struct hclge_vlan_info *old_info)
+{
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_ENABLE) {
+		hclge_rm_vport_all_vlan_table(vport, false);
+		return hclge_set_vlan_filter_hw(hdev,
+						 htons(new_info->vlan_proto),
+						 vport->vport_id,
+						 new_info->vlan_tag,
+						 new_info->qos, false);
+	}
+
+	ret = hclge_set_vlan_filter_hw(hdev, htons(old_info->vlan_proto),
+				       vport->vport_id, old_info->vlan_tag,
+				       old_info->qos, true);
+	if (ret)
+		return ret;
+
+	return hclge_add_vport_all_vlan_table(vport);
+}
+
+int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
+				    struct hclge_vlan_info *vlan_info)
+{
+	struct hnae3_handle *nic = &vport->nic;
+	struct hclge_vlan_info *old_vlan_info;
+	struct hclge_dev *hdev = vport->back;
+	int ret;
+
+	old_vlan_info = &vport->port_base_vlan_cfg.vlan_info;
+
+	ret = hclge_vlan_offload_cfg(vport, state, vlan_info->vlan_tag);
+	if (ret)
+		return ret;
+
+	if (state == HNAE3_PORT_BASE_VLAN_MODIFY) {
+		/* add new VLAN tag */
+		ret = hclge_set_vlan_filter_hw(hdev,
+					       htons(vlan_info->vlan_proto),
+					       vport->vport_id,
+					       vlan_info->vlan_tag,
+					       vlan_info->qos, false);
+		if (ret)
+			return ret;
+
+		/* remove old VLAN tag */
+		ret = hclge_set_vlan_filter_hw(hdev,
+					       htons(old_vlan_info->vlan_proto),
+					       vport->vport_id,
+					       old_vlan_info->vlan_tag,
+					       old_vlan_info->qos, true);
+		if (ret)
+			return ret;
+
+		goto update;
+	}
+
+	ret = hclge_update_vlan_filter_entries(vport, state, vlan_info,
+					       old_vlan_info);
+	if (ret)
+		return ret;
+
+	/* update state only when disable/enable port based VLAN */
+	vport->port_base_vlan_cfg.state = state;
+	if (state == HNAE3_PORT_BASE_VLAN_DISABLE)
+		nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE;
+	else
+		nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE;
+
+update:
+	vport->port_base_vlan_cfg.vlan_info.vlan_tag = vlan_info->vlan_tag;
+	vport->port_base_vlan_cfg.vlan_info.qos = vlan_info->qos;
+	vport->port_base_vlan_cfg.vlan_info.vlan_proto = vlan_info->vlan_proto;
+
+	return 0;
+}
+
+static u16 hclge_get_port_base_vlan_state(struct hclge_vport *vport,
+					  enum hnae3_port_base_vlan_state state,
+					  u16 vlan)
+{
+	if (state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+		if (!vlan)
+			return HNAE3_PORT_BASE_VLAN_NOCHANGE;
+		else
+			return HNAE3_PORT_BASE_VLAN_ENABLE;
+	} else {
+		if (!vlan)
+			return HNAE3_PORT_BASE_VLAN_DISABLE;
+		else if (vport->port_base_vlan_cfg.vlan_info.vlan_tag == vlan)
+			return HNAE3_PORT_BASE_VLAN_NOCHANGE;
+		else
+			return HNAE3_PORT_BASE_VLAN_MODIFY;
+	}
+}
+
+static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
+				    u16 vlan, u8 qos, __be16 proto)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	struct hclge_vlan_info vlan_info;
+	u16 state;
+	int ret;
+
+	if (hdev->pdev->revision == 0x20)
+		return -EOPNOTSUPP;
+
+	/* qos is a 3 bits value, so can not be bigger than 7 */
+	if (vfid >= hdev->num_alloc_vfs || vlan > VLAN_N_VID - 1 || qos > 7)
+		return -EINVAL;
+	if (proto != htons(ETH_P_8021Q))
+		return -EPROTONOSUPPORT;
+
+	vport = &hdev->vport[vfid];
+	state = hclge_get_port_base_vlan_state(vport,
+					       vport->port_base_vlan_cfg.state,
+					       vlan);
+	if (state == HNAE3_PORT_BASE_VLAN_NOCHANGE)
+		return 0;
+
+	vlan_info.vlan_tag = vlan;
+	vlan_info.qos = qos;
+	vlan_info.vlan_proto = ntohs(proto);
+
+	/* update port based VLAN for PF */
+	if (!vfid) {
+		hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+		ret = hclge_update_port_base_vlan_cfg(vport, state, &vlan_info);
+		hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+
+		return ret;
+	}
+
+	if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) {
+		return hclge_update_port_base_vlan_cfg(vport, state,
+						       &vlan_info);
+	} else {
+		ret = hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+							(u8)vfid, state,
+							vlan, qos,
+							ntohs(proto));
+		return ret;
+	}
+}
+
+int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
+			  u16 vlan_id, bool is_kill)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+	bool writen_to_tbl = false;
+	int ret = 0;
+
+	/* When device is resetting, firmware is unable to handle
+	 * mailbox. Just record the vlan id, and remove it after
+	 * reset finished.
+	 */
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && is_kill) {
+		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+		return -EBUSY;
+	}
+
+	/* When port base vlan enabled, we use port base vlan as the vlan
+	 * filter entry. In this case, we don't update vlan filter table
+	 * when user add new vlan or remove exist vlan, just update the vport
+	 * vlan list. The vlan id in vlan list will be writen in vlan filter
+	 * table until port base vlan disabled
+	 */
+	if (handle->port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) {
+		ret = hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id,
+					       vlan_id, 0, is_kill);
+		writen_to_tbl = true;
+	}
+
+	if (!ret) {
+		if (is_kill)
+			hclge_rm_vport_vlan_table(vport, vlan_id, false);
+		else
+			hclge_add_vport_vlan_table(vport, vlan_id,
+						   writen_to_tbl);
+	} else if (is_kill) {
+		/* When remove hw vlan filter failed, record the vlan id,
+		 * and try to remove it from hw later, to be consistence
+		 * with stack
+		 */
+		set_bit(vlan_id, vport->vlan_del_fail_bmap);
+	}
+	return ret;
+}
+
+static void hclge_sync_vlan_filter(struct hclge_dev *hdev)
+{
+#define HCLGE_MAX_SYNC_COUNT	60
+
+	int i, ret, sync_cnt = 0;
+	u16 vlan_id;
+
+	/* start from vport 1 for PF is always alive */
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+
+		vlan_id = find_first_bit(vport->vlan_del_fail_bmap,
+					 VLAN_N_VID);
+		while (vlan_id != VLAN_N_VID) {
+			ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q),
+						       vport->vport_id, vlan_id,
+						       0, true);
+			if (ret && ret != -EINVAL)
+				return;
+
+			clear_bit(vlan_id, vport->vlan_del_fail_bmap);
+			hclge_rm_vport_vlan_table(vport, vlan_id, false);
+
+			sync_cnt++;
+			if (sync_cnt >= HCLGE_MAX_SYNC_COUNT)
+				return;
+
+			vlan_id = find_first_bit(vport->vlan_del_fail_bmap,
+						 VLAN_N_VID);
+		}
+	}
+}
+
 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
 {
 	struct hclge_config_max_frm_size_cmd *req;
@@ -6558,7 +7914,7 @@ static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
 int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu)
 {
 	struct hclge_dev *hdev = vport->back;
-	int i, max_frm_size, ret = 0;
+	int i, max_frm_size, ret;
 
 	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
 	if (max_frm_size < HCLGE_MAC_MIN_FRAME ||
@@ -6618,7 +7974,8 @@ static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id,
 
 	req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
 	req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
-	hnae3_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
+	if (enable)
+		hnae3_set_bit(req->reset_req, HCLGE_TQP_RESET_B, 1U);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -6669,7 +8026,7 @@ int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
 	int reset_try_times = 0;
 	int reset_status;
 	u16 queue_gid;
-	int ret = 0;
+	int ret;
 
 	queue_gid = hclge_covert_handle_qid_global(handle, queue_id);
 
@@ -6686,7 +8043,6 @@ int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
 		return ret;
 	}
 
-	reset_try_times = 0;
 	while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) {
 		/* Wait for tqp hw reset */
 		msleep(20);
@@ -6725,7 +8081,6 @@ void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id)
 		return;
 	}
 
-	reset_try_times = 0;
 	while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) {
 		/* Wait for tqp hw reset */
 		msleep(20);
@@ -6795,7 +8150,7 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev)
 {
 	struct phy_device *phydev = hdev->hw.mac.phydev;
 	u16 remote_advertising = 0;
-	u16 local_advertising = 0;
+	u16 local_advertising;
 	u32 rx_pause, tx_pause;
 	u8 flowctl;
 
@@ -6828,8 +8183,9 @@ static void hclge_get_pauseparam(struct hnae3_handle *handle, u32 *auto_neg,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
+	struct phy_device *phydev = hdev->hw.mac.phydev;
 
-	*auto_neg = hclge_get_autoneg(handle);
+	*auto_neg = phydev ? hclge_get_autoneg(handle) : 0;
 
 	if (hdev->tm_info.fc_mode == HCLGE_FC_PFC) {
 		*rx_en = 0;
@@ -6860,11 +8216,13 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg,
 	struct phy_device *phydev = hdev->hw.mac.phydev;
 	u32 fc_autoneg;
 
-	fc_autoneg = hclge_get_autoneg(handle);
-	if (auto_neg != fc_autoneg) {
-		dev_info(&hdev->pdev->dev,
-			 "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
-		return -EOPNOTSUPP;
+	if (phydev) {
+		fc_autoneg = hclge_get_autoneg(handle);
+		if (auto_neg != fc_autoneg) {
+			dev_info(&hdev->pdev->dev,
+				 "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
+			return -EOPNOTSUPP;
+		}
 	}
 
 	if (hdev->tm_info.fc_mode == HCLGE_FC_PFC) {
@@ -6875,16 +8233,13 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg,
 
 	hclge_set_flowctrl_adv(hdev, rx_en, tx_en);
 
-	if (!fc_autoneg)
+	if (!auto_neg)
 		return hclge_cfg_pauseparam(hdev, rx_en, tx_en);
 
-	/* Only support flow control negotiation for netdev with
-	 * phy attached for now.
-	 */
-	if (!phydev)
-		return -EOPNOTSUPP;
+	if (phydev)
+		return phy_start_aneg(phydev);
 
-	return phy_start_aneg(phydev);
+	return -EOPNOTSUPP;
 }
 
 static void hclge_get_ksettings_an_result(struct hnae3_handle *handle,
@@ -6901,13 +8256,17 @@ static void hclge_get_ksettings_an_result(struct hnae3_handle *handle,
 		*auto_neg = hdev->hw.mac.autoneg;
 }
 
-static void hclge_get_media_type(struct hnae3_handle *handle, u8 *media_type)
+static void hclge_get_media_type(struct hnae3_handle *handle, u8 *media_type,
+				 u8 *module_type)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
 	if (media_type)
 		*media_type = hdev->hw.mac.media_type;
+
+	if (module_type)
+		*module_type = hdev->hw.mac.module_type;
 }
 
 static void hclge_get_mdix_mode(struct hnae3_handle *handle,
@@ -6916,7 +8275,8 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
-	int mdix_ctrl, mdix, retval, is_resolved;
+	int mdix_ctrl, mdix, is_resolved;
+	unsigned int retval;
 
 	if (!phydev) {
 		*tp_mdix_ctrl = ETH_TP_MDI_INVALID;
@@ -6959,14 +8319,126 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 		*tp_mdix = ETH_TP_MDI;
 }
 
-static int hclge_init_instance_hw(struct hclge_dev *hdev)
+static void hclge_info_show(struct hclge_dev *hdev)
+{
+	struct device *dev = &hdev->pdev->dev;
+
+	dev_info(dev, "PF info begin:\n");
+
+	dev_info(dev, "Task queue pairs numbers: %d\n", hdev->num_tqps);
+	dev_info(dev, "Desc num per TX queue: %d\n", hdev->num_tx_desc);
+	dev_info(dev, "Desc num per RX queue: %d\n", hdev->num_rx_desc);
+	dev_info(dev, "Numbers of vports: %d\n", hdev->num_alloc_vport);
+	dev_info(dev, "Numbers of vmdp vports: %d\n", hdev->num_vmdq_vport);
+	dev_info(dev, "Numbers of VF for this PF: %d\n", hdev->num_req_vfs);
+	dev_info(dev, "HW tc map: %d\n", hdev->hw_tc_map);
+	dev_info(dev, "Total buffer size for TX/RX: %d\n", hdev->pkt_buf_size);
+	dev_info(dev, "TX buffer size for each TC: %d\n", hdev->tx_buf_size);
+	dev_info(dev, "DV buffer size for each TC: %d\n", hdev->dv_buf_size);
+	dev_info(dev, "This is %s PF\n",
+		 hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main");
+	dev_info(dev, "DCB %s\n",
+		 hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable");
+	dev_info(dev, "MQPRIO %s\n",
+		 hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable");
+
+	dev_info(dev, "PF info end.\n");
+}
+
+static int hclge_init_nic_client_instance(struct hnae3_ae_dev *ae_dev,
+					  struct hclge_vport *vport)
 {
-	return hclge_mac_connect_phy(hdev);
+	struct hnae3_client *client = vport->nic.client;
+	struct hclge_dev *hdev = ae_dev->priv;
+	int rst_cnt;
+	int ret;
+
+	rst_cnt = hdev->rst_stats.reset_cnt;
+	ret = client->ops->init_instance(&vport->nic);
+	if (ret)
+		return ret;
+
+	set_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state);
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+	    rst_cnt != hdev->rst_stats.reset_cnt) {
+		ret = -EBUSY;
+		goto init_nic_err;
+	}
+
+	/* Enable nic hw error interrupts */
+	ret = hclge_config_nic_hw_error(hdev, true);
+	if (ret) {
+		dev_err(&ae_dev->pdev->dev,
+			"fail(%d) to enable hw error interrupts\n", ret);
+		goto init_nic_err;
+	}
+
+	hnae3_set_client_init_flag(client, ae_dev, 1);
+
+	if (netif_msg_drv(&hdev->vport->nic))
+		hclge_info_show(hdev);
+
+	return ret;
+
+init_nic_err:
+	clear_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state);
+	while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+		msleep(HCLGE_WAIT_RESET_DONE);
+
+	client->ops->uninit_instance(&vport->nic, 0);
+
+	return ret;
 }
 
-static void hclge_uninit_instance_hw(struct hclge_dev *hdev)
+static int hclge_init_roce_client_instance(struct hnae3_ae_dev *ae_dev,
+					   struct hclge_vport *vport)
 {
-	hclge_mac_disconnect_phy(hdev);
+	struct hnae3_client *client = vport->roce.client;
+	struct hclge_dev *hdev = ae_dev->priv;
+	int rst_cnt;
+	int ret;
+
+	if (!hnae3_dev_roce_supported(hdev) || !hdev->roce_client ||
+	    !hdev->nic_client)
+		return 0;
+
+	client = hdev->roce_client;
+	ret = hclge_init_roce_base_info(vport);
+	if (ret)
+		return ret;
+
+	rst_cnt = hdev->rst_stats.reset_cnt;
+	ret = client->ops->init_instance(&vport->roce);
+	if (ret)
+		return ret;
+
+	set_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state);
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+	    rst_cnt != hdev->rst_stats.reset_cnt) {
+		ret = -EBUSY;
+		goto init_roce_err;
+	}
+
+	/* Enable roce ras interrupts */
+	ret = hclge_config_rocee_ras_interrupt(hdev, true);
+	if (ret) {
+		dev_err(&ae_dev->pdev->dev,
+			"fail(%d) to enable roce ras interrupts\n", ret);
+		goto init_roce_err;
+	}
+
+	hnae3_set_client_init_flag(client, ae_dev, 1);
+
+	return 0;
+
+init_roce_err:
+	clear_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state);
+	while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+		msleep(HCLGE_WAIT_RESET_DONE);
+
+	hdev->roce_client->ops->uninit_instance(&vport->roce, 0);
+
+	return ret;
 }
 
 static int hclge_init_client_instance(struct hnae3_client *client,
@@ -6984,45 +8456,13 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 
 			hdev->nic_client = client;
 			vport->nic.client = client;
-			ret = client->ops->init_instance(&vport->nic);
+			ret = hclge_init_nic_client_instance(ae_dev, vport);
 			if (ret)
 				goto clear_nic;
 
-			ret = hclge_init_instance_hw(hdev);
-			if (ret) {
-			        client->ops->uninit_instance(&vport->nic,
-			                                     0);
-				goto clear_nic;
-			}
-
-			hnae3_set_client_init_flag(client, ae_dev, 1);
-
-			if (hdev->roce_client &&
-			    hnae3_dev_roce_supported(hdev)) {
-				struct hnae3_client *rc = hdev->roce_client;
-
-				ret = hclge_init_roce_base_info(vport);
-				if (ret)
-					goto clear_roce;
-
-				ret = rc->ops->init_instance(&vport->roce);
-				if (ret)
-					goto clear_roce;
-
-				hnae3_set_client_init_flag(hdev->roce_client,
-							   ae_dev, 1);
-			}
-
-			break;
-		case HNAE3_CLIENT_UNIC:
-			hdev->nic_client = client;
-			vport->nic.client = client;
-
-			ret = client->ops->init_instance(&vport->nic);
+			ret = hclge_init_roce_client_instance(ae_dev, vport);
 			if (ret)
-				goto clear_nic;
-
-			hnae3_set_client_init_flag(client, ae_dev, 1);
+				goto clear_roce;
 
 			break;
 		case HNAE3_CLIENT_ROCE:
@@ -7031,17 +8471,9 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 				vport->roce.client = client;
 			}
 
-			if (hdev->roce_client && hdev->nic_client) {
-				ret = hclge_init_roce_base_info(vport);
-				if (ret)
-					goto clear_roce;
-
-				ret = client->ops->init_instance(&vport->roce);
-				if (ret)
-					goto clear_roce;
-
-				hnae3_set_client_init_flag(client, ae_dev, 1);
-			}
+			ret = hclge_init_roce_client_instance(ae_dev, vport);
+			if (ret)
+				goto clear_roce;
 
 			break;
 		default:
@@ -7049,7 +8481,7 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 		}
 	}
 
-	return 0;
+	return ret;
 
 clear_nic:
 	hdev->nic_client = NULL;
@@ -7071,6 +8503,10 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
 		vport = &hdev->vport[i];
 		if (hdev->roce_client) {
+			clear_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state);
+			while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+				msleep(HCLGE_WAIT_RESET_DONE);
+
 			hdev->roce_client->ops->uninit_instance(&vport->roce,
 								0);
 			hdev->roce_client = NULL;
@@ -7079,7 +8515,10 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 		if (client->type == HNAE3_CLIENT_ROCE)
 			return;
 		if (hdev->nic_client && client->ops->uninit_instance) {
-			hclge_uninit_instance_hw(hdev);
+			clear_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state);
+			while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+				msleep(HCLGE_WAIT_RESET_DONE);
+
 			client->ops->uninit_instance(&vport->nic, 0);
 			hdev->nic_client = NULL;
 			vport->nic.client = NULL;
@@ -7161,6 +8600,7 @@ static void hclge_state_init(struct hclge_dev *hdev)
 static void hclge_state_uninit(struct hclge_dev *hdev)
 {
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
+	set_bit(HCLGE_STATE_REMOVING, &hdev->state);
 
 	if (hdev->service_timer.function)
 		del_timer_sync(&hdev->service_timer);
@@ -7202,6 +8642,23 @@ static void hclge_flr_done(struct hnae3_ae_dev *ae_dev)
 	set_bit(HNAE3_FLR_DONE, &hdev->flr_state);
 }
 
+static void hclge_clear_resetting_state(struct hclge_dev *hdev)
+{
+	u16 i;
+
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+		int ret;
+
+		 /* Send cmd to clear VF's FUNC_RST_ING */
+		ret = hclge_set_vf_rst(hdev, vport->vport_id, false);
+		if (ret)
+			dev_warn(&hdev->pdev->dev,
+				 "clear vf(%d) rst failed %d!\n",
+				 vport->vport_id, ret);
+	}
+}
+
 static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
@@ -7222,6 +8679,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hdev->mps = ETH_FRAME_LEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
 
 	mutex_init(&hdev->vport_lock);
+	mutex_init(&hdev->vport_cfg_mutex);
+	spin_lock_init(&hdev->fd_rule_lock);
 
 	ret = hclge_pci_init(hdev);
 	if (ret) {
@@ -7298,7 +8757,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	ret = hclge_init_umv_space(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "umv space init error, ret=%d.\n", ret);
-		goto err_msi_irq_uninit;
+		goto err_mdiobus_unreg;
 	}
 
 	ret = hclge_mac_init(hdev);
@@ -7349,12 +8808,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_mdiobus_unreg;
 	}
 
-	ret = hclge_hw_error_set_state(hdev, true);
-	if (ret) {
-		dev_err(&pdev->dev,
-			"fail(%d) to enable hw error interrupts\n", ret);
-		goto err_mdiobus_unreg;
-	}
+	INIT_KFIFO(hdev->mac_tnl_log);
 
 	hclge_dcb_ops_set(hdev);
 
@@ -7365,6 +8819,22 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	INIT_WORK(&hdev->mbx_service_task, hclge_mailbox_service_task);
 
 	hclge_clear_all_event_cause(hdev);
+	hclge_clear_resetting_state(hdev);
+
+	/* Log and clear the hw errors those already occurred */
+	hclge_handle_all_hns_hw_errors(ae_dev);
+
+	/* request delayed reset for the error recovery because an immediate
+	 * global reset on a PF affecting pending initialization of other PFs
+	 */
+	if (ae_dev->hw_err_reset_req) {
+		enum hnae3_reset_type reset_level;
+
+		reset_level = hclge_get_reset_level(ae_dev,
+						    &ae_dev->hw_err_reset_req);
+		hclge_set_def_reset_request(ae_dev, reset_level);
+		mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL);
+	}
 
 	/* Enable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, true);
@@ -7383,7 +8853,7 @@ err_msi_irq_uninit:
 err_msi_uninit:
 	pci_free_irq_vectors(pdev);
 err_cmd_uninit:
-	hclge_destroy_cmd_queue(&hdev->hw);
+	hclge_cmd_uninit(hdev);
 err_pci_uninit:
 	pcim_iounmap(pdev, hdev->hw.io_base);
 	pci_clear_master(pdev);
@@ -7404,7 +8874,7 @@ static void hclge_reset_vport_state(struct hclge_dev *hdev)
 	int i;
 
 	for (i = 0; i < hdev->num_alloc_vport; i++) {
-		hclge_vport_start(vport);
+		hclge_vport_stop(vport);
 		vport++;
 	}
 }
@@ -7419,6 +8889,7 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	hclge_stats_clear(hdev);
 	memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table));
+	memset(hdev->vf_vlan_full, 0, sizeof(hdev->vf_vlan_full));
 
 	ret = hclge_cmd_init(hdev);
 	if (ret) {
@@ -7456,7 +8927,7 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
-	ret = hclge_tm_init_hw(hdev);
+	ret = hclge_tm_init_hw(hdev, true);
 	if (ret) {
 		dev_err(&pdev->dev, "tm init hw fail, ret =%d\n", ret);
 		return ret;
@@ -7470,21 +8941,31 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	ret = hclge_init_fd_config(hdev);
 	if (ret) {
-		dev_err(&pdev->dev,
-			"fd table init fail, ret=%d\n", ret);
+		dev_err(&pdev->dev, "fd table init fail, ret=%d\n", ret);
 		return ret;
 	}
 
 	/* Re-enable the hw error interrupts because
-	 * the interrupts get disabled on core/global reset.
+	 * the interrupts get disabled on global reset.
 	 */
-	ret = hclge_hw_error_set_state(hdev, true);
+	ret = hclge_config_nic_hw_error(hdev, true);
 	if (ret) {
 		dev_err(&pdev->dev,
-			"fail(%d) to re-enable HNS hw error interrupts\n", ret);
+			"fail(%d) to re-enable NIC hw error interrupts\n",
+			ret);
 		return ret;
 	}
 
+	if (hdev->roce_client) {
+		ret = hclge_config_rocee_ras_interrupt(hdev, true);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"fail(%d) to re-enable roce ras interrupts\n",
+				ret);
+			return ret;
+		}
+	}
+
 	hclge_reset_vport_state(hdev);
 
 	dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n",
@@ -7509,11 +8990,18 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_enable_vector(&hdev->misc_vector, false);
 	synchronize_irq(hdev->misc_vector.vector_irq);
 
-	hclge_hw_error_set_state(hdev, false);
-	hclge_destroy_cmd_queue(&hdev->hw);
+	/* Disable all hw interrupts */
+	hclge_config_mac_tnl_int(hdev, false);
+	hclge_config_nic_hw_error(hdev, false);
+	hclge_config_rocee_ras_interrupt(hdev, false);
+
+	hclge_cmd_uninit(hdev);
 	hclge_misc_irq_uninit(hdev);
 	hclge_pci_uninit(hdev);
 	mutex_destroy(&hdev->vport_lock);
+	hclge_uninit_vport_mac_table(hdev);
+	hclge_uninit_vport_vlan_table(hdev);
+	mutex_destroy(&hdev->vport_cfg_mutex);
 	ae_dev->priv = NULL;
 }
 
@@ -7523,18 +9011,17 @@ static u32 hclge_get_max_channels(struct hnae3_handle *handle)
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	return min_t(u32, hdev->rss_size_max * kinfo->num_tc, hdev->num_tqps);
+	return min_t(u32, hdev->rss_size_max,
+		     vport->alloc_tqps / kinfo->num_tc);
 }
 
 static void hclge_get_channels(struct hnae3_handle *handle,
 			       struct ethtool_channels *ch)
 {
-	struct hclge_vport *vport = hclge_get_vport(handle);
-
 	ch->max_combined = hclge_get_max_channels(handle);
 	ch->other_count = 1;
 	ch->max_other = 1;
-	ch->combined_count = vport->alloc_tqps;
+	ch->combined_count = handle->kinfo.rss_size;
 }
 
 static void hclge_get_tqps_and_rss_info(struct hnae3_handle *handle,
@@ -7547,57 +9034,27 @@ static void hclge_get_tqps_and_rss_info(struct hnae3_handle *handle,
 	*max_rss_size = hdev->rss_size_max;
 }
 
-static void hclge_release_tqp(struct hclge_vport *vport)
-{
-	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
-	struct hclge_dev *hdev = vport->back;
-	int i;
-
-	for (i = 0; i < kinfo->num_tqps; i++) {
-		struct hclge_tqp *tqp =
-			container_of(kinfo->tqp[i], struct hclge_tqp, q);
-
-		tqp->q.handle = NULL;
-		tqp->q.tqp_index = 0;
-		tqp->alloced = false;
-	}
-
-	devm_kfree(&hdev->pdev->dev, kinfo->tqp);
-	kinfo->tqp = NULL;
-}
-
-static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
+static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num,
+			      bool rxfh_configured)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
+	u16 tc_offset[HCLGE_MAX_TC_NUM] = {0};
 	struct hclge_dev *hdev = vport->back;
+	u16 tc_size[HCLGE_MAX_TC_NUM] = {0};
 	int cur_rss_size = kinfo->rss_size;
 	int cur_tqps = kinfo->num_tqps;
-	u16 tc_offset[HCLGE_MAX_TC_NUM];
 	u16 tc_valid[HCLGE_MAX_TC_NUM];
-	u16 tc_size[HCLGE_MAX_TC_NUM];
 	u16 roundup_size;
 	u32 *rss_indir;
-	int ret, i;
-
-	/* Free old tqps, and reallocate with new tqp number when nic setup */
-	hclge_release_tqp(vport);
-
-	ret = hclge_knic_setup(vport, new_tqps_num, kinfo->num_desc);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "setup nic fail, ret =%d\n", ret);
-		return ret;
-	}
+	unsigned int i;
+	int ret;
 
-	ret = hclge_map_tqp_to_vport(hdev, vport);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "map vport tqp fail, ret =%d\n", ret);
-		return ret;
-	}
+	kinfo->req_rss_size = new_tqps_num;
 
-	ret = hclge_tm_schd_init(hdev);
+	ret = hclge_tm_vport_map_update(hdev);
 	if (ret) {
-		dev_err(&hdev->pdev->dev, "tm schd init fail, ret =%d\n", ret);
+		dev_err(&hdev->pdev->dev, "tm vport map fail, ret =%d\n", ret);
 		return ret;
 	}
 
@@ -7618,6 +9075,10 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 	if (ret)
 		return ret;
 
+	/* RSS indirection table has been configuared by user */
+	if (rxfh_configured)
+		goto out;
+
 	/* Reinitializes the rss indirect table according to the new RSS size */
 	rss_indir = kcalloc(HCLGE_RSS_IND_TBL_SIZE, sizeof(u32), GFP_KERNEL);
 	if (!rss_indir)
@@ -7633,6 +9094,7 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 
 	kfree(rss_indir);
 
+out:
 	if (!ret)
 		dev_info(&hdev->pdev->dev,
 			 "Channels changed, rss_size from %d to %d, tqps from %d to %d",
@@ -7671,10 +9133,12 @@ static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 				 void *data)
 {
 #define HCLGE_32_BIT_REG_RTN_DATANUM 8
+#define HCLGE_32_BIT_DESC_NODATA_LEN 2
 
 	struct hclge_desc *desc;
 	u32 *reg_val = data;
 	__le32 *desc_data;
+	int nodata_num;
 	int cmd_num;
 	int i, k, n;
 	int ret;
@@ -7682,7 +9146,9 @@ static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 	if (regs_num == 0)
 		return 0;
 
-	cmd_num = DIV_ROUND_UP(regs_num + 2, HCLGE_32_BIT_REG_RTN_DATANUM);
+	nodata_num = HCLGE_32_BIT_DESC_NODATA_LEN;
+	cmd_num = DIV_ROUND_UP(regs_num + nodata_num,
+			       HCLGE_32_BIT_REG_RTN_DATANUM);
 	desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL);
 	if (!desc)
 		return -ENOMEM;
@@ -7699,7 +9165,7 @@ static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 	for (i = 0; i < cmd_num; i++) {
 		if (i == 0) {
 			desc_data = (__le32 *)(&desc[i].data[0]);
-			n = HCLGE_32_BIT_REG_RTN_DATANUM - 2;
+			n = HCLGE_32_BIT_REG_RTN_DATANUM - nodata_num;
 		} else {
 			desc_data = (__le32 *)(&desc[i]);
 			n = HCLGE_32_BIT_REG_RTN_DATANUM;
@@ -7721,10 +9187,12 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 				 void *data)
 {
 #define HCLGE_64_BIT_REG_RTN_DATANUM 4
+#define HCLGE_64_BIT_DESC_NODATA_LEN 1
 
 	struct hclge_desc *desc;
 	u64 *reg_val = data;
 	__le64 *desc_data;
+	int nodata_len;
 	int cmd_num;
 	int i, k, n;
 	int ret;
@@ -7732,7 +9200,9 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 	if (regs_num == 0)
 		return 0;
 
-	cmd_num = DIV_ROUND_UP(regs_num + 1, HCLGE_64_BIT_REG_RTN_DATANUM);
+	nodata_len = HCLGE_64_BIT_DESC_NODATA_LEN;
+	cmd_num = DIV_ROUND_UP(regs_num + nodata_len,
+			       HCLGE_64_BIT_REG_RTN_DATANUM);
 	desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL);
 	if (!desc)
 		return -ENOMEM;
@@ -7749,7 +9219,7 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 	for (i = 0; i < cmd_num; i++) {
 		if (i == 0) {
 			desc_data = (__le64 *)(&desc[i].data[0]);
-			n = HCLGE_64_BIT_REG_RTN_DATANUM - 1;
+			n = HCLGE_64_BIT_REG_RTN_DATANUM - nodata_len;
 		} else {
 			desc_data = (__le64 *)(&desc[i]);
 			n = HCLGE_64_BIT_REG_RTN_DATANUM;
@@ -7927,7 +9397,7 @@ static void hclge_get_link_mode(struct hnae3_handle *handle,
 	}
 }
 
-static int hclge_gro_en(struct hnae3_handle *handle, int enable)
+static int hclge_gro_en(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
@@ -7954,9 +9424,11 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.client_stop = hclge_client_stop,
 	.get_status = hclge_get_status,
 	.get_ksettings_an_result = hclge_get_ksettings_an_result,
-	.update_speed_duplex_h = hclge_update_speed_duplex_h,
 	.cfg_mac_speed_dup_h = hclge_cfg_mac_speed_dup_h,
 	.get_media_type = hclge_get_media_type,
+	.check_port_speed = hclge_check_port_speed,
+	.get_fec = hclge_get_fec,
+	.set_fec = hclge_set_fec,
 	.get_rss_key_size = hclge_get_rss_key_size,
 	.get_rss_indir_size = hclge_get_rss_indir_size,
 	.get_rss = hclge_get_rss,
@@ -7973,11 +9445,14 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.rm_mc_addr = hclge_rm_mc_addr,
 	.set_autoneg = hclge_set_autoneg,
 	.get_autoneg = hclge_get_autoneg,
+	.restart_autoneg = hclge_restart_autoneg,
+	.halt_autoneg = hclge_halt_autoneg,
 	.get_pauseparam = hclge_get_pauseparam,
 	.set_pauseparam = hclge_set_pauseparam,
 	.set_mtu = hclge_set_mtu,
 	.reset_queue = hclge_reset_tqp,
 	.get_stats = hclge_get_stats,
+	.get_mac_pause_stats = hclge_get_mac_pause_stat,
 	.update_stats = hclge_update_stats,
 	.get_strings = hclge_get_strings,
 	.get_sset_count = hclge_get_sset_count,
@@ -7988,6 +9463,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_vf_vlan_filter = hclge_set_vf_vlan_filter,
 	.enable_hw_strip_rxvtag = hclge_en_hw_strip_rxvtag,
 	.reset_event = hclge_reset_event,
+	.get_reset_level = hclge_get_reset_level,
 	.set_default_reset_request = hclge_set_def_reset_request,
 	.get_tqps_and_rss_info = hclge_get_tqps_and_rss_info,
 	.set_channels = hclge_set_channels,
@@ -8004,6 +9480,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_fd_all_rules = hclge_get_all_rules,
 	.restore_fd_rules = hclge_restore_fd_entries,
 	.enable_fd = hclge_enable_fd,
+	.add_arfs_entry = hclge_add_fd_entry_by_arfs,
 	.dbg_run_cmd = hclge_dbg_run_cmd,
 	.handle_hw_ras_error = hclge_handle_hw_ras_error,
 	.get_hw_reset_stat = hclge_get_hw_reset_stat,
@@ -8012,6 +9489,9 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_gro_en = hclge_gro_en,
 	.get_global_queue_id = hclge_covert_handle_qid_global,
 	.set_timer_task = hclge_set_timer_task,
+	.mac_connect_phy = hclge_mac_connect_phy,
+	.mac_disconnect_phy = hclge_mac_disconnect_phy,
+	.restore_vlan_table = hclge_restore_vlan_table,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 6615b85a1c52..6a12285f4c76 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/phy.h>
 #include <linux/if_vlan.h>
+#include <linux/kfifo.h>
 
 #include "hclge_cmd.h"
 #include "hnae3.h"
@@ -16,6 +17,9 @@
 
 #define HCLGE_MAX_PF_NUM		8
 
+#define HCLGE_RD_FIRST_STATS_NUM        2
+#define HCLGE_RD_OTHER_STATS_NUM        4
+
 #define HCLGE_INVALID_VPORT 0xffff
 
 #define HCLGE_PF_CFG_BLOCK_SIZE		32
@@ -185,12 +189,20 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_SUPPORT_25G_BIT		BIT(2)
 #define HCLGE_SUPPORT_50G_BIT		BIT(3)
 #define HCLGE_SUPPORT_100G_BIT		BIT(4)
+/* to be compatible with exsit board */
+#define HCLGE_SUPPORT_40G_BIT		BIT(5)
+#define HCLGE_SUPPORT_100M_BIT		BIT(6)
+#define HCLGE_SUPPORT_10M_BIT		BIT(7)
+#define HCLGE_SUPPORT_GE \
+	(HCLGE_SUPPORT_1G_BIT | HCLGE_SUPPORT_100M_BIT | HCLGE_SUPPORT_10M_BIT)
 
 enum HCLGE_DEV_STATE {
 	HCLGE_STATE_REINITING,
 	HCLGE_STATE_DOWN,
 	HCLGE_STATE_DISABLED,
 	HCLGE_STATE_REMOVING,
+	HCLGE_STATE_NIC_REGISTERED,
+	HCLGE_STATE_ROCE_REGISTERED,
 	HCLGE_STATE_SERVICE_INITED,
 	HCLGE_STATE_SERVICE_SCHED,
 	HCLGE_STATE_RST_SERVICE_SCHED,
@@ -228,15 +240,25 @@ enum HCLGE_MAC_DUPLEX {
 	HCLGE_MAC_FULL
 };
 
+#define QUERY_SFP_SPEED		0
+#define QUERY_ACTIVE_SPEED	1
+
 struct hclge_mac {
 	u8 phy_addr;
 	u8 flag;
-	u8 media_type;
+	u8 media_type;	/* port media type, e.g. fibre/copper/backplane */
 	u8 mac_addr[ETH_ALEN];
 	u8 autoneg;
 	u8 duplex;
+	u8 support_autoneg;
+	u8 speed_type;	/* 0: sfp speed, 1: active speed */
 	u32 speed;
-	int link;	/* store the link status of mac & phy (if phy exit)*/
+	u32 speed_ability; /* speed ability supported by current media */
+	u32 module_type; /* sub media type, e.g. kr/cr/sr/lr */
+	u32 fec_mode; /* active fec mode */
+	u32 user_fec_mode;
+	u32 fec_ability;
+	int link;	/* store the link status of mac & phy (if phy exit) */
 	struct phy_device *phydev;
 	struct mii_bus *mdio_bus;
 	phy_interface_t phy_if;
@@ -322,6 +344,7 @@ struct hclge_tm_info {
 	struct hclge_tc_info tc_info[HNAE3_MAX_TC];
 	enum hclge_fc_mode fc_mode;
 	u8 hw_pfc_map; /* Allow for packet drop or not on this TC */
+	u8 pfc_en;	/* PFC enabled or not for user priority */
 };
 
 struct hclge_comm_stats_str {
@@ -415,6 +438,10 @@ struct hclge_mac_stats {
 	u64 mac_rx_fcs_err_pkt_num;
 	u64 mac_rx_send_app_good_pkt_num;
 	u64 mac_rx_send_app_bad_pkt_num;
+	u64 mac_tx_pfc_pause_pkt_num;
+	u64 mac_rx_pfc_pause_pkt_num;
+	u64 mac_tx_ctrl_pkt_num;
+	u64 mac_rx_ctrl_pkt_num;
 };
 
 #define HCLGE_STATS_TIMER_INTERVAL	(60 * 5)
@@ -447,6 +474,7 @@ enum HCLGE_FD_KEY_TYPE {
 enum HCLGE_FD_STAGE {
 	HCLGE_FD_STAGE_1,
 	HCLGE_FD_STAGE_2,
+	MAX_STAGE_NUM,
 };
 
 /* OUTER_XXX indicates tuples in tunnel header of tunnel packet
@@ -501,7 +529,7 @@ enum HCLGE_FD_META_DATA {
 
 struct key_info {
 	u8 key_type;
-	u8 key_length;
+	u8 key_length; /* use bit as unit */
 };
 
 static const struct key_info meta_data_key_info[] = {
@@ -553,6 +581,16 @@ static const struct key_info tuple_key_info[] = {
 #define MAX_KEY_BYTES	(MAX_KEY_DWORDS * 4)
 #define MAX_META_DATA_LENGTH	32
 
+/* assigned by firmware, the real filter number for each pf may be less */
+#define MAX_FD_FILTER_NUM	4096
+#define HCLGE_FD_ARFS_EXPIRE_TIMER_INTERVAL	5
+
+enum HCLGE_FD_ACTIVE_RULE_TYPE {
+	HCLGE_FD_RULE_NONE,
+	HCLGE_FD_ARFS_ACTIVE,
+	HCLGE_FD_EP_ACTIVE,
+};
+
 enum HCLGE_FD_PACKET_TYPE {
 	NIC_PACKET,
 	ROCE_PACKET,
@@ -575,19 +613,23 @@ struct hclge_fd_key_cfg {
 
 struct hclge_fd_cfg {
 	u8 fd_mode;
-	u8 fd_en;
-	u16 max_key_length;
+	u16 max_key_length; /* use bit as unit */
 	u32 proto_support;
-	u32 rule_num[2]; /* rule entry number */
-	u16 cnt_num[2]; /* rule hit counter number */
-	struct hclge_fd_key_cfg key_cfg[2];
+	u32 rule_num[MAX_STAGE_NUM]; /* rule entry number */
+	u16 cnt_num[MAX_STAGE_NUM]; /* rule hit counter number */
+	struct hclge_fd_key_cfg key_cfg[MAX_STAGE_NUM];
 };
 
+#define IPV4_INDEX	3
+#define IPV6_SIZE	4
 struct hclge_fd_rule_tuples {
-	u8 src_mac[6];
-	u8 dst_mac[6];
-	u32 src_ip[4];
-	u32 dst_ip[4];
+	u8 src_mac[ETH_ALEN];
+	u8 dst_mac[ETH_ALEN];
+	/* Be compatible for ip address of both ipv4 and ipv6.
+	 * For ipv4 address, we store it in src/dst_ip[3].
+	 */
+	u32 src_ip[IPV6_SIZE];
+	u32 dst_ip[IPV6_SIZE];
 	u16 src_port;
 	u16 dst_port;
 	u16 vlan_tag1;
@@ -606,6 +648,8 @@ struct hclge_fd_rule {
 	u16 vf_id;
 	u16 queue_id;
 	u16 location;
+	u16 flow_id;	/* only used for arfs */
+	enum HCLGE_FD_ACTIVE_RULE_TYPE rule_type;
 };
 
 struct hclge_fd_ad_data {
@@ -621,6 +665,54 @@ struct hclge_fd_ad_data {
 	u16 rule_id;
 };
 
+struct hclge_vport_mac_addr_cfg {
+	struct list_head node;
+	int hd_tbl_status;
+	u8 mac_addr[ETH_ALEN];
+};
+
+enum HCLGE_MAC_ADDR_TYPE {
+	HCLGE_MAC_ADDR_UC,
+	HCLGE_MAC_ADDR_MC
+};
+
+struct hclge_vport_vlan_cfg {
+	struct list_head node;
+	int hd_tbl_status;
+	u16 vlan_id;
+};
+
+struct hclge_rst_stats {
+	u32 reset_done_cnt;	/* the number of reset has completed */
+	u32 hw_reset_done_cnt;	/* the number of HW reset has completed */
+	u32 pf_rst_cnt;		/* the number of PF reset */
+	u32 flr_rst_cnt;	/* the number of FLR */
+	u32 core_rst_cnt;	/* the number of CORE reset */
+	u32 global_rst_cnt;	/* the number of GLOBAL */
+	u32 imp_rst_cnt;	/* the number of IMP reset */
+	u32 reset_cnt;		/* the number of reset */
+};
+
+/* time and register status when mac tunnel interruption occur */
+struct hclge_mac_tnl_stats {
+	u64 time;
+	u32 status;
+};
+
+#define HCLGE_RESET_INTERVAL	(10 * HZ)
+#define HCLGE_WAIT_RESET_DONE	100
+
+#pragma pack(1)
+struct hclge_vf_vlan_cfg {
+	u8 mbx_cmd;
+	u8 subcode;
+	u8 is_kill;
+	u16 vlan;
+	u16 proto;
+};
+
+#pragma pack()
+
 /* For each bit of TCAM entry, it uses a pair of 'x' and
  * 'y' to indicate which value to match, like below:
  * ----------------------------------
@@ -647,6 +739,7 @@ struct hclge_fd_ad_data {
 		(y) = (_k_ ^ ~_v_) & (_k_); \
 	} while (0)
 
+#define HCLGE_MAC_TNL_LOG_SIZE	8
 #define HCLGE_VPORT_NUM 256
 struct hclge_dev {
 	struct pci_dev *pdev;
@@ -663,7 +756,7 @@ struct hclge_dev {
 	unsigned long default_reset_request;
 	unsigned long reset_request;	/* reset has been requested */
 	unsigned long reset_pending;	/* client rst is pending to be served */
-	unsigned long reset_count;	/* the number of reset has been done */
+	struct hclge_rst_stats rst_stats;
 	u32 reset_fail_cnt;
 	u32 fw_version;
 	u16 num_vmdq_vport;		/* Num vmdq vport this PF has set up */
@@ -678,7 +771,8 @@ struct hclge_dev {
 	u16 num_alloc_vport;		/* Num vports this driver supports */
 	u32 numa_node_mask;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;		/* desc num of per tx queue */
+	u16 num_rx_desc;		/* desc num of per rx queue */
 	u8 hw_tc_map;
 	u8 tc_num_last_time;
 	enum hclge_fc_mode fc_mode_last_time;
@@ -746,10 +840,16 @@ struct hclge_dev {
 	struct hclge_vlan_type_cfg vlan_type_cfg;
 
 	unsigned long vlan_table[VLAN_N_VID][BITS_TO_LONGS(HCLGE_VPORT_NUM)];
+	unsigned long vf_vlan_full[BITS_TO_LONGS(HCLGE_VPORT_NUM)];
 
 	struct hclge_fd_cfg fd_cfg;
 	struct hlist_head fd_rule_list;
+	spinlock_t fd_rule_lock; /* protect fd_rule_list and fd_bmap */
 	u16 hclge_fd_rule_num;
+	u16 fd_arfs_expire_timer;
+	unsigned long fd_bmap[BITS_TO_LONGS(MAX_FD_FILTER_NUM)];
+	enum HCLGE_FD_ACTIVE_RULE_TYPE fd_active_type;
+	u8 fd_en;
 
 	u16 wanted_umv_size;
 	/* max available unicast mac vlan space */
@@ -759,6 +859,11 @@ struct hclge_dev {
 	/* unicast mac vlan space shared by PF and its VFs */
 	u16 share_umv_size;
 	struct mutex umv_mutex; /* protect share_umv_size */
+
+	struct mutex vport_cfg_mutex;   /* Protect stored vf table */
+
+	DECLARE_KFIFO(mac_tnl_log, struct hclge_mac_tnl_stats,
+		      HCLGE_MAC_TNL_LOG_SIZE);
 };
 
 /* VPort level vlan tag configuration for TX direction */
@@ -775,10 +880,11 @@ struct hclge_tx_vtag_cfg {
 
 /* VPort level vlan tag configuration for RX direction */
 struct hclge_rx_vtag_cfg {
-	bool strip_tag1_en;	/* Whether strip inner vlan tag */
-	bool strip_tag2_en;	/* Whether strip outer vlan tag */
-	bool vlan1_vlan_prionly;/* Inner VLAN Tag up to descriptor Enable */
-	bool vlan2_vlan_prionly;/* Outer VLAN Tag up to descriptor Enable */
+	u8 rx_vlan_offload_en;	/* Whether enable rx vlan offload */
+	u8 strip_tag1_en;	/* Whether strip inner vlan tag */
+	u8 strip_tag2_en;	/* Whether strip outer vlan tag */
+	u8 vlan1_vlan_prionly;	/* Inner VLAN Tag up to descriptor Enable */
+	u8 vlan2_vlan_prionly;	/* Outer VLAN Tag up to descriptor Enable */
 };
 
 struct hclge_rss_tuple_cfg {
@@ -797,6 +903,17 @@ enum HCLGE_VPORT_STATE {
 	HCLGE_VPORT_STATE_MAX
 };
 
+struct hclge_vlan_info {
+	u16 vlan_proto; /* so far support 802.1Q only */
+	u16 qos;
+	u16 vlan_tag;
+};
+
+struct hclge_port_base_vlan_config {
+	u16 state;
+	struct hclge_vlan_info vlan_info;
+};
+
 struct hclge_vport {
 	u16 alloc_tqps;	/* Allocated Tx/Rx queues */
 
@@ -810,15 +927,17 @@ struct hclge_vport {
 	u16 alloc_rss_size;
 
 	u16 qs_offset;
-	u16 bw_limit;		/* VSI BW Limit (0 = disabled) */
+	u32 bw_limit;		/* VSI BW Limit (0 = disabled) */
 	u8  dwrr;
 
+	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
+	struct hclge_port_base_vlan_config port_base_vlan_cfg;
 	struct hclge_tx_vtag_cfg  txvlan_cfg;
 	struct hclge_rx_vtag_cfg  rxvlan_cfg;
 
 	u16 used_umv_num;
 
-	int vport_id;
+	u16 vport_id;
 	struct hclge_dev *back;  /* Back reference to associated dev */
 	struct hnae3_handle nic;
 	struct hnae3_handle roce;
@@ -826,6 +945,10 @@ struct hclge_vport {
 	unsigned long state;
 	unsigned long last_active_jiffies;
 	u32 mps; /* Max packet size */
+
+	struct list_head uc_mac_list;   /* Store VF unicast table */
+	struct list_head mc_mac_list;   /* Store VF multicast table */
+	struct list_head vlan_list;     /* Store VF vlan table */
 };
 
 void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc,
@@ -876,6 +999,23 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
 int hclge_vport_start(struct hclge_vport *vport);
 void hclge_vport_stop(struct hclge_vport *vport);
 int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu);
-int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf);
+int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf);
 u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id);
+int hclge_notify_client(struct hclge_dev *hdev,
+			enum hnae3_reset_notify_type type);
+void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			       enum HCLGE_MAC_ADDR_TYPE mac_type);
+void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			      bool is_write_tbl,
+			      enum HCLGE_MAC_ADDR_TYPE mac_type);
+void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
+				  enum HCLGE_MAC_ADDR_TYPE mac_type);
+void hclge_uninit_vport_mac_table(struct hclge_dev *hdev);
+void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list);
+void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev);
+int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state,
+				    struct hclge_vlan_info *vlan_info);
+int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
+				      u16 state, u16 vlan_tag, u16 qos,
+				      u16 vlan_proto);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index a1de451a85df..a38ac7cfe16b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -29,6 +29,10 @@ static int hclge_gen_resp_to_vf(struct hclge_vport *vport,
 			"PF fail to gen resp to VF len %d exceeds max len %d\n",
 			resp_data_len,
 			HCLGE_MBX_MAX_RESP_DATA_SIZE);
+		/* If resp_data_len is too long, set the value to max length
+		 * and return the msg to VF
+		 */
+		resp_data_len = HCLGE_MBX_MAX_RESP_DATA_SIZE;
 	}
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_PF_TO_VF, false);
@@ -93,7 +97,7 @@ int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
 	else if (hdev->reset_type == HNAE3_FLR_RESET)
 		reset_type = HNAE3_VF_FULL_RESET;
 	else
-		return -EINVAL;
+		reset_type = HNAE3_VF_FUNC_RESET;
 
 	memcpy(&msg_data[0], &reset_type, sizeof(u16));
 
@@ -192,29 +196,25 @@ static int hclge_map_unmap_ring_to_vf_vector(struct hclge_vport *vport, bool en,
 		return ret;
 
 	ret = hclge_bind_ring_with_vector(vport, vector_id, en, &ring_chain);
-	if (ret)
-		return ret;
 
 	hclge_free_vector_ring_chain(&ring_chain);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_vf_promisc_mode(struct hclge_vport *vport,
 				     struct hclge_mbx_vf_to_pf_cmd *req)
 {
-	bool en_uc = req->msg[1] ? true : false;
-	bool en_mc = req->msg[2] ? true : false;
+	bool en_bc = req->msg[1] ? true : false;
 	struct hclge_promisc_param param;
 
-	/* always enable broadcast promisc bit */
-	hclge_promisc_param_init(&param, en_uc, en_mc, true, vport->vport_id);
+	/* vf is not allowed to enable unicast/multicast broadcast */
+	hclge_promisc_param_init(&param, false, false, en_bc, vport->vport_id);
 	return hclge_cmd_set_promisc_mode(vport->back, &param);
 }
 
 static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
-				    struct hclge_mbx_vf_to_pf_cmd *mbx_req,
-				    bool gen_resp)
+				    struct hclge_mbx_vf_to_pf_cmd *mbx_req)
 {
 	const u8 *mac_addr = (const u8 *)(&mbx_req->msg[2]);
 	struct hclge_dev *hdev = vport->back;
@@ -225,12 +225,24 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
 
 		hclge_rm_uc_addr_common(vport, old_addr);
 		status = hclge_add_uc_addr_common(vport, mac_addr);
-		if (status)
+		if (status) {
 			hclge_add_uc_addr_common(vport, old_addr);
+		} else {
+			hclge_rm_vport_mac_table(vport, mac_addr,
+						 false, HCLGE_MAC_ADDR_UC);
+			hclge_add_vport_mac_table(vport, mac_addr,
+						  HCLGE_MAC_ADDR_UC);
+		}
 	} else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_UC_ADD) {
 		status = hclge_add_uc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_add_vport_mac_table(vport, mac_addr,
+						  HCLGE_MAC_ADDR_UC);
 	} else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_UC_REMOVE) {
 		status = hclge_rm_uc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_rm_vport_mac_table(vport, mac_addr,
+						 false, HCLGE_MAC_ADDR_UC);
 	} else {
 		dev_err(&hdev->pdev->dev,
 			"failed to set unicast mac addr, unknown subcode %d\n",
@@ -238,7 +250,7 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
 		return -EIO;
 	}
 
-	if (gen_resp)
+	if (mbx_req->mbx_need_resp & HCLGE_MBX_NEED_RESP_BIT)
 		hclge_gen_resp_to_vf(vport, mbx_req, status, NULL, 0);
 
 	return 0;
@@ -256,8 +268,14 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport,
 
 	if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_ADD) {
 		status = hclge_add_mc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_add_vport_mac_table(vport, mac_addr,
+						  HCLGE_MAC_ADDR_MC);
 	} else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_REMOVE) {
 		status = hclge_rm_mc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_rm_vport_mac_table(vport, mac_addr,
+						 false, HCLGE_MAC_ADDR_MC);
 	} else {
 		dev_err(&hdev->pdev->dev,
 			"failed to set mcast mac addr, unknown subcode %d\n",
@@ -272,32 +290,61 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport,
 	return 0;
 }
 
+int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid,
+				      u16 state, u16 vlan_tag, u16 qos,
+				      u16 vlan_proto)
+{
+#define MSG_DATA_SIZE	8
+
+	u8 msg_data[MSG_DATA_SIZE];
+
+	memcpy(&msg_data[0], &state, sizeof(u16));
+	memcpy(&msg_data[2], &vlan_proto, sizeof(u16));
+	memcpy(&msg_data[4], &qos, sizeof(u16));
+	memcpy(&msg_data[6], &vlan_tag, sizeof(u16));
+
+	return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
+				  HLCGE_MBX_PUSH_VLAN_INFO, vfid);
+}
+
 static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport,
-				 struct hclge_mbx_vf_to_pf_cmd *mbx_req,
-				 bool gen_resp)
+				 struct hclge_mbx_vf_to_pf_cmd *mbx_req)
 {
+	struct hclge_vf_vlan_cfg *msg_cmd;
 	int status = 0;
 
-	if (mbx_req->msg[1] == HCLGE_MBX_VLAN_FILTER) {
+	msg_cmd = (struct hclge_vf_vlan_cfg *)mbx_req->msg;
+	if (msg_cmd->subcode == HCLGE_MBX_VLAN_FILTER) {
 		struct hnae3_handle *handle = &vport->nic;
 		u16 vlan, proto;
 		bool is_kill;
 
-		is_kill = !!mbx_req->msg[2];
-		memcpy(&vlan, &mbx_req->msg[3], sizeof(vlan));
-		memcpy(&proto, &mbx_req->msg[5], sizeof(proto));
+		is_kill = !!msg_cmd->is_kill;
+		vlan =  msg_cmd->vlan;
+		proto =  msg_cmd->proto;
 		status = hclge_set_vlan_filter(handle, cpu_to_be16(proto),
 					       vlan, is_kill);
-	} else if (mbx_req->msg[1] == HCLGE_MBX_VLAN_RX_OFF_CFG) {
+	} else if (msg_cmd->subcode == HCLGE_MBX_VLAN_RX_OFF_CFG) {
 		struct hnae3_handle *handle = &vport->nic;
-		bool en = mbx_req->msg[2] ? true : false;
+		bool en = msg_cmd->is_kill ? true : false;
 
 		status = hclge_en_hw_strip_rxvtag(handle, en);
+	} else if (mbx_req->msg[1] == HCLGE_MBX_PORT_BASE_VLAN_CFG) {
+		struct hclge_vlan_info *vlan_info;
+		u16 *state;
+
+		state = (u16 *)&mbx_req->msg[2];
+		vlan_info = (struct hclge_vlan_info *)&mbx_req->msg[4];
+		status = hclge_update_port_base_vlan_cfg(vport, *state,
+							 vlan_info);
+	} else if (mbx_req->msg[1] == HCLGE_MBX_GET_PORT_BASE_VLAN_STATE) {
+		u8 state;
+
+		state = vport->port_base_vlan_cfg.state;
+		status = hclge_gen_resp_to_vf(vport, mbx_req, 0, &state,
+					      sizeof(u8));
 	}
 
-	if (gen_resp)
-		status = hclge_gen_resp_to_vf(vport, mbx_req, status, NULL, 0);
-
 	return status;
 }
 
@@ -320,11 +367,16 @@ static int hclge_get_vf_tcinfo(struct hclge_vport *vport,
 			       struct hclge_mbx_vf_to_pf_cmd *mbx_req,
 			       bool gen_resp)
 {
-	struct hclge_dev *hdev = vport->back;
+	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
+	u8 vf_tc_map = 0;
+	unsigned int i;
 	int ret;
 
-	ret = hclge_gen_resp_to_vf(vport, mbx_req, 0, &hdev->hw_tc_map,
-				   sizeof(u8));
+	for (i = 0; i < kinfo->num_tc; i++)
+		vf_tc_map |= BIT(i);
+
+	ret = hclge_gen_resp_to_vf(vport, mbx_req, 0, &vf_tc_map,
+				   sizeof(vf_tc_map));
 
 	return ret;
 }
@@ -333,20 +385,46 @@ static int hclge_get_vf_queue_info(struct hclge_vport *vport,
 				   struct hclge_mbx_vf_to_pf_cmd *mbx_req,
 				   bool gen_resp)
 {
-#define HCLGE_TQPS_RSS_INFO_LEN		8
+#define HCLGE_TQPS_RSS_INFO_LEN		6
 	u8 resp_data[HCLGE_TQPS_RSS_INFO_LEN];
 	struct hclge_dev *hdev = vport->back;
 
 	/* get the queue related info */
 	memcpy(&resp_data[0], &vport->alloc_tqps, sizeof(u16));
 	memcpy(&resp_data[2], &vport->nic.kinfo.rss_size, sizeof(u16));
-	memcpy(&resp_data[4], &hdev->num_desc, sizeof(u16));
-	memcpy(&resp_data[6], &hdev->rx_buf_len, sizeof(u16));
+	memcpy(&resp_data[4], &hdev->rx_buf_len, sizeof(u16));
 
 	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data,
 				    HCLGE_TQPS_RSS_INFO_LEN);
 }
 
+static int hclge_get_vf_queue_depth(struct hclge_vport *vport,
+				    struct hclge_mbx_vf_to_pf_cmd *mbx_req,
+				    bool gen_resp)
+{
+#define HCLGE_TQPS_DEPTH_INFO_LEN	4
+	u8 resp_data[HCLGE_TQPS_DEPTH_INFO_LEN];
+	struct hclge_dev *hdev = vport->back;
+
+	/* get the queue depth info */
+	memcpy(&resp_data[0], &hdev->num_tx_desc, sizeof(u16));
+	memcpy(&resp_data[2], &hdev->num_rx_desc, sizeof(u16));
+	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data,
+				    HCLGE_TQPS_DEPTH_INFO_LEN);
+}
+
+static int hclge_get_vf_media_type(struct hclge_vport *vport,
+				   struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	struct hclge_dev *hdev = vport->back;
+	u8 resp_data[2];
+
+	resp_data[0] = hdev->hw.mac.media_type;
+	resp_data[1] = hdev->hw.mac.module_type;
+	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data,
+				    sizeof(resp_data));
+}
+
 static int hclge_get_link_info(struct hclge_vport *vport,
 			       struct hclge_mbx_vf_to_pf_cmd *mbx_req)
 {
@@ -369,6 +447,29 @@ static int hclge_get_link_info(struct hclge_vport *vport,
 				  HCLGE_MBX_LINK_STAT_CHANGE, dest_vfid);
 }
 
+static void hclge_get_link_mode(struct hclge_vport *vport,
+				struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+#define HCLGE_SUPPORTED   1
+	struct hclge_dev *hdev = vport->back;
+	unsigned long advertising;
+	unsigned long supported;
+	unsigned long send_data;
+	u8 msg_data[10];
+	u8 dest_vfid;
+
+	advertising = hdev->hw.mac.advertising[0];
+	supported = hdev->hw.mac.supported[0];
+	dest_vfid = mbx_req->mbx_src_vfid;
+	msg_data[0] = mbx_req->msg[2];
+
+	send_data = msg_data[0] == HCLGE_SUPPORTED ? supported : advertising;
+
+	memcpy(&msg_data[2], &send_data, sizeof(unsigned long));
+	hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
+			   HCLGE_MBX_LINK_STAT_MODE, dest_vfid);
+}
+
 static void hclge_mbx_reset_vf_queue(struct hclge_vport *vport,
 				     struct hclge_mbx_vf_to_pf_cmd *mbx_req)
 {
@@ -426,6 +527,24 @@ static int hclge_get_queue_id_in_pf(struct hclge_vport *vport,
 	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data, 2);
 }
 
+static int hclge_get_rss_key(struct hclge_vport *vport,
+			     struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+#define HCLGE_RSS_MBX_RESP_LEN	8
+	u8 resp_data[HCLGE_RSS_MBX_RESP_LEN];
+	struct hclge_dev *hdev = vport->back;
+	u8 index;
+
+	index = mbx_req->msg[2];
+
+	memcpy(&resp_data[0],
+	       &hdev->vport[0].rss_hash_key[index * HCLGE_RSS_MBX_RESP_LEN],
+	       HCLGE_RSS_MBX_RESP_LEN);
+
+	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data,
+				    HCLGE_RSS_MBX_RESP_LEN);
+}
+
 static bool hclge_cmd_crq_empty(struct hclge_hw *hw)
 {
 	u32 tail = hclge_read_dev(hw, HCLGE_NIC_CRQ_TAIL_REG);
@@ -439,7 +558,8 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 	struct hclge_mbx_vf_to_pf_cmd *req;
 	struct hclge_vport *vport;
 	struct hclge_desc *desc;
-	int ret, flag;
+	unsigned int flag;
+	int ret;
 
 	/* handle all the mailbox requests in the queue */
 	while (!hclge_cmd_crq_empty(&hdev->hw)) {
@@ -483,7 +603,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					ret);
 			break;
 		case HCLGE_MBX_SET_UNICAST:
-			ret = hclge_set_vf_uc_mac_addr(vport, req, true);
+			ret = hclge_set_vf_uc_mac_addr(vport, req);
 			if (ret)
 				dev_err(&hdev->pdev->dev,
 					"PF fail(%d) to set VF UC MAC Addr\n",
@@ -497,7 +617,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					ret);
 			break;
 		case HCLGE_MBX_SET_VLAN:
-			ret = hclge_set_vf_vlan_cfg(vport, req, false);
+			ret = hclge_set_vf_vlan_cfg(vport, req);
 			if (ret)
 				dev_err(&hdev->pdev->dev,
 					"PF failed(%d) to config VF's VLAN\n",
@@ -517,6 +637,14 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					"PF failed(%d) to get Q info for VF\n",
 					ret);
 			break;
+		case HCLGE_MBX_GET_QDEPTH:
+			ret = hclge_get_vf_queue_depth(vport, req, true);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF failed(%d) to get Q depth for VF\n",
+					ret);
+			break;
+
 		case HCLGE_MBX_GET_TCINFO:
 			ret = hclge_get_vf_tcinfo(vport, req, true);
 			if (ret)
@@ -553,6 +681,32 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					"PF failed(%d) to get qid for VF\n",
 					ret);
 			break;
+		case HCLGE_MBX_GET_RSS_KEY:
+			ret = hclge_get_rss_key(vport, req);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF fail(%d) to get rss key for VF\n",
+					ret);
+			break;
+		case HCLGE_MBX_GET_LINK_MODE:
+			hclge_get_link_mode(vport, req);
+			break;
+		case HCLGE_MBX_GET_VF_FLR_STATUS:
+			mutex_lock(&hdev->vport_cfg_mutex);
+			hclge_rm_vport_all_mac_table(vport, true,
+						     HCLGE_MAC_ADDR_UC);
+			hclge_rm_vport_all_mac_table(vport, true,
+						     HCLGE_MAC_ADDR_MC);
+			hclge_rm_vport_all_vlan_table(vport, true);
+			mutex_unlock(&hdev->vport_cfg_mutex);
+			break;
+		case HCLGE_MBX_GET_MEDIA_TYPE:
+			ret = hclge_get_vf_media_type(vport, req);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF fail(%d) to media type for VF\n",
+					ret);
+			break;
 		default:
 			dev_err(&hdev->pdev->dev,
 				"un-supported mailbox message, code = %d\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index dabb8437f8dc..abb1b438564e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -3,17 +3,12 @@
 
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
+#include <linux/marvell_phy.h>
 
 #include "hclge_cmd.h"
 #include "hclge_main.h"
 #include "hclge_mdio.h"
 
-#define HCLGE_PHY_SUPPORTED_FEATURES	(SUPPORTED_Autoneg | \
-					 SUPPORTED_TP | \
-					 PHY_10BT_FEATURES | \
-					 PHY_100BT_FEATURES | \
-					 SUPPORTED_1000baseT_Full)
-
 enum hclge_mdio_c22_op_seq {
 	HCLGE_MDIO_C22_WRITE = 1,
 	HCLGE_MDIO_C22_READ = 2
@@ -60,9 +55,9 @@ static int hclge_mdio_write(struct mii_bus *bus, int phyid, int regnum,
 	mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
 
 	hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
-			HCLGE_MDIO_PHYID_S, phyid);
+			HCLGE_MDIO_PHYID_S, (u32)phyid);
 	hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
-			HCLGE_MDIO_PHYREG_S, regnum);
+			HCLGE_MDIO_PHYREG_S, (u32)regnum);
 
 	hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
 	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
@@ -98,9 +93,9 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum)
 	mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
 
 	hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
-			HCLGE_MDIO_PHYID_S, phyid);
+			HCLGE_MDIO_PHYID_S, (u32)phyid);
 	hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
-			HCLGE_MDIO_PHYREG_S, regnum);
+			HCLGE_MDIO_PHYREG_S, (u32)regnum);
 
 	hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
 	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
@@ -127,12 +122,18 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum)
 
 int hclge_mac_mdio_config(struct hclge_dev *hdev)
 {
+#define PHY_INEXISTENT	255
+
 	struct hclge_mac *mac = &hdev->hw.mac;
 	struct phy_device *phydev;
 	struct mii_bus *mdio_bus;
 	int ret;
 
-	if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) {
+	if (hdev->hw.mac.phy_addr == PHY_INEXISTENT) {
+		dev_info(&hdev->pdev->dev,
+			 "no phy device is connected to mdio bus\n");
+		return 0;
+	} else if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) {
 		dev_err(&hdev->pdev->dev, "phy_addr(%d) is too large.\n",
 			hdev->hw.mac.phy_addr);
 		return -EINVAL;
@@ -195,8 +196,10 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
 		netdev_err(netdev, "failed to configure flow control.\n");
 }
 
-int hclge_mac_connect_phy(struct hclge_dev *hdev)
+int hclge_mac_connect_phy(struct hnae3_handle *handle)
 {
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
 	struct net_device *netdev = hdev->vport[0].nic.netdev;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
@@ -207,6 +210,8 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev)
 
 	linkmode_clear_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported);
 
+	phydev->dev_flags |= MARVELL_PHY_LED0_LINK_LED1_ACTIVE;
+
 	ret = phy_connect_direct(netdev, phydev,
 				 hclge_mac_adjust_link,
 				 PHY_INTERFACE_MODE_SGMII);
@@ -215,22 +220,24 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, mask);
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       mask);
-	linkmode_set_bit_array(phy_gbit_features_array,
-			       ARRAY_SIZE(phy_gbit_features_array),
-			       mask);
+	linkmode_copy(mask, hdev->hw.mac.supported);
 	linkmode_and(phydev->supported, phydev->supported, mask);
-	phy_support_asym_pause(phydev);
+	linkmode_copy(phydev->advertising, phydev->supported);
+
+	/* supported flag is Pause and Asym Pause, but default advertising
+	 * should be rx on, tx on, so need clear Asym Pause in advertising
+	 * flag
+	 */
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			   phydev->advertising);
 
 	return 0;
 }
 
-void hclge_mac_disconnect_phy(struct hclge_dev *hdev)
+void hclge_mac_disconnect_phy(struct hnae3_handle *handle)
 {
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
 
 	if (!phydev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index 5fbf7dddb5d9..ef095d9c566f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -5,8 +5,8 @@
 #define __HCLGE_MDIO_H
 
 int hclge_mac_mdio_config(struct hclge_dev *hdev);
-int hclge_mac_connect_phy(struct hclge_dev *hdev);
-void hclge_mac_disconnect_phy(struct hclge_dev *hdev);
+int hclge_mac_connect_phy(struct hnae3_handle *handle);
+void hclge_mac_disconnect_phy(struct hnae3_handle *handle);
 void hclge_mac_start_phy(struct hclge_dev *hdev);
 void hclge_mac_stop_phy(struct hclge_dev *hdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 00458da67503..3f41fa2bc414 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -43,18 +43,23 @@ enum hclge_shaper_level {
 static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
 				  u8 *ir_b, u8 *ir_u, u8 *ir_s)
 {
+#define DIVISOR_CLK		(1000 * 8)
+#define DIVISOR_IR_B_126	(126 * DIVISOR_CLK)
+
 	const u16 tick_array[HCLGE_SHAPER_LVL_CNT] = {
 		6 * 256,        /* Prioriy level */
 		6 * 32,         /* Prioriy group level */
 		6 * 8,          /* Port level */
 		6 * 256         /* Qset level */
 	};
-	u8 ir_u_calc = 0, ir_s_calc = 0;
+	u8 ir_u_calc = 0;
+	u8 ir_s_calc = 0;
 	u32 ir_calc;
 	u32 tick;
 
 	/* Calc tick */
-	if (shaper_level >= HCLGE_SHAPER_LVL_CNT)
+	if (shaper_level >= HCLGE_SHAPER_LVL_CNT ||
+	    ir > HCLGE_ETHER_MAX_RATE)
 		return -EINVAL;
 
 	tick = tick_array[shaper_level];
@@ -66,7 +71,7 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
 	 * ir_calc = ---------------- * 1000
 	 *		tick * 1
 	 */
-	ir_calc = (1008000 + (tick >> 1) - 1) / tick;
+	ir_calc = (DIVISOR_IR_B_126 + (tick >> 1) - 1) / tick;
 
 	if (ir_calc == ir) {
 		*ir_b = 126;
@@ -78,27 +83,28 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
 		/* Increasing the denominator to select ir_s value */
 		while (ir_calc > ir) {
 			ir_s_calc++;
-			ir_calc = 1008000 / (tick * (1 << ir_s_calc));
+			ir_calc = DIVISOR_IR_B_126 / (tick * (1 << ir_s_calc));
 		}
 
 		if (ir_calc == ir)
 			*ir_b = 126;
 		else
-			*ir_b = (ir * tick * (1 << ir_s_calc) + 4000) / 8000;
+			*ir_b = (ir * tick * (1 << ir_s_calc) +
+				 (DIVISOR_CLK >> 1)) / DIVISOR_CLK;
 	} else {
 		/* Increasing the numerator to select ir_u value */
 		u32 numerator;
 
 		while (ir_calc < ir) {
 			ir_u_calc++;
-			numerator = 1008000 * (1 << ir_u_calc);
+			numerator = DIVISOR_IR_B_126 * (1 << ir_u_calc);
 			ir_calc = (numerator + (tick >> 1)) / tick;
 		}
 
 		if (ir_calc == ir) {
 			*ir_b = 126;
 		} else {
-			u32 denominator = (8000 * (1 << --ir_u_calc));
+			u32 denominator = (DIVISOR_CLK * (1 << --ir_u_calc));
 			*ir_b = (ir * tick + (denominator >> 1)) / denominator;
 		}
 	}
@@ -119,14 +125,13 @@ static int hclge_pfc_stats_get(struct hclge_dev *hdev,
 	      opcode == HCLGE_OPC_QUERY_PFC_TX_PKT_CNT))
 		return -EINVAL;
 
-	for (i = 0; i < HCLGE_TM_PFC_PKT_GET_CMD_NUM; i++) {
+	for (i = 0; i < HCLGE_TM_PFC_PKT_GET_CMD_NUM - 1; i++) {
 		hclge_cmd_setup_basic_desc(&desc[i], opcode, true);
-		if (i != (HCLGE_TM_PFC_PKT_GET_CMD_NUM - 1))
-			desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
-		else
-			desc[i].flag &= ~cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+		desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 	}
 
+	hclge_cmd_setup_basic_desc(&desc[i], opcode, true);
+
 	ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_TM_PFC_PKT_GET_CMD_NUM);
 	if (ret)
 		return ret;
@@ -219,8 +224,7 @@ int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr)
 	trans_gap = pause_param->pause_trans_gap;
 	trans_time = le16_to_cpu(pause_param->pause_trans_time);
 
-	return hclge_pause_param_cfg(hdev, mac_addr, trans_gap,
-					 trans_time);
+	return hclge_pause_param_cfg(hdev, mac_addr, trans_gap, trans_time);
 }
 
 static int hclge_fill_pri_array(struct hclge_dev *hdev, u8 *pri, u8 pri_id)
@@ -361,29 +365,36 @@ static int hclge_tm_qs_weight_cfg(struct hclge_dev *hdev, u16 qs_id,
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
+static u32 hclge_tm_get_shapping_para(u8 ir_b, u8 ir_u, u8 ir_s,
+				      u8 bs_b, u8 bs_s)
+{
+	u32 shapping_para = 0;
+
+	hclge_tm_set_field(shapping_para, IR_B, ir_b);
+	hclge_tm_set_field(shapping_para, IR_U, ir_u);
+	hclge_tm_set_field(shapping_para, IR_S, ir_s);
+	hclge_tm_set_field(shapping_para, BS_B, bs_b);
+	hclge_tm_set_field(shapping_para, BS_S, bs_s);
+
+	return shapping_para;
+}
+
 static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev,
 				    enum hclge_shap_bucket bucket, u8 pg_id,
-				    u8 ir_b, u8 ir_u, u8 ir_s, u8 bs_b, u8 bs_s)
+				    u32 shapping_para)
 {
 	struct hclge_pg_shapping_cmd *shap_cfg_cmd;
 	enum hclge_opcode_type opcode;
 	struct hclge_desc desc;
-	u32 shapping_para = 0;
 
 	opcode = bucket ? HCLGE_OPC_TM_PG_P_SHAPPING :
-		HCLGE_OPC_TM_PG_C_SHAPPING;
+		 HCLGE_OPC_TM_PG_C_SHAPPING;
 	hclge_cmd_setup_basic_desc(&desc, opcode, false);
 
 	shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
 
 	shap_cfg_cmd->pg_id = pg_id;
 
-	hclge_tm_set_field(shapping_para, IR_B, ir_b);
-	hclge_tm_set_field(shapping_para, IR_U, ir_u);
-	hclge_tm_set_field(shapping_para, IR_S, ir_s);
-	hclge_tm_set_field(shapping_para, BS_B, bs_b);
-	hclge_tm_set_field(shapping_para, BS_S, bs_s);
-
 	shap_cfg_cmd->pg_shapping_para = cpu_to_le32(shapping_para);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -397,7 +408,7 @@ static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
 	u8 ir_u, ir_b, ir_s;
 	int ret;
 
-	ret = hclge_shaper_para_calc(HCLGE_ETHER_MAX_RATE,
+	ret = hclge_shaper_para_calc(hdev->hw.mac.speed,
 				     HCLGE_SHAPER_LVL_PORT,
 				     &ir_b, &ir_u, &ir_s);
 	if (ret)
@@ -406,11 +417,9 @@ static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, false);
 	shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
 
-	hclge_tm_set_field(shapping_para, IR_B, ir_b);
-	hclge_tm_set_field(shapping_para, IR_U, ir_u);
-	hclge_tm_set_field(shapping_para, IR_S, ir_s);
-	hclge_tm_set_field(shapping_para, BS_B, HCLGE_SHAPER_BS_U_DEF);
-	hclge_tm_set_field(shapping_para, BS_S, HCLGE_SHAPER_BS_S_DEF);
+	shapping_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+						   HCLGE_SHAPER_BS_U_DEF,
+						   HCLGE_SHAPER_BS_S_DEF);
 
 	shap_cfg_cmd->port_shapping_para = cpu_to_le32(shapping_para);
 
@@ -419,16 +428,14 @@ static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev)
 
 static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev,
 				     enum hclge_shap_bucket bucket, u8 pri_id,
-				     u8 ir_b, u8 ir_u, u8 ir_s,
-				     u8 bs_b, u8 bs_s)
+				     u32 shapping_para)
 {
 	struct hclge_pri_shapping_cmd *shap_cfg_cmd;
 	enum hclge_opcode_type opcode;
 	struct hclge_desc desc;
-	u32 shapping_para = 0;
 
 	opcode = bucket ? HCLGE_OPC_TM_PRI_P_SHAPPING :
-		HCLGE_OPC_TM_PRI_C_SHAPPING;
+		 HCLGE_OPC_TM_PRI_C_SHAPPING;
 
 	hclge_cmd_setup_basic_desc(&desc, opcode, false);
 
@@ -436,12 +443,6 @@ static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev,
 
 	shap_cfg_cmd->pri_id = pri_id;
 
-	hclge_tm_set_field(shapping_para, IR_B, ir_b);
-	hclge_tm_set_field(shapping_para, IR_U, ir_u);
-	hclge_tm_set_field(shapping_para, IR_S, ir_s);
-	hclge_tm_set_field(shapping_para, BS_B, bs_b);
-	hclge_tm_set_field(shapping_para, BS_S, bs_s);
-
 	shap_cfg_cmd->pri_shapping_para = cpu_to_le32(shapping_para);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -517,20 +518,41 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
+	u16 max_rss_size;
 	u8 i;
 
-	vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit;
-	kinfo->num_tc =
-		min_t(u16, kinfo->num_tqps, hdev->tm_info.num_tc);
-	kinfo->rss_size
-		= min_t(u16, hdev->rss_size_max,
-			kinfo->num_tqps / kinfo->num_tc);
-	vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id;
+	/* TC configuration is shared by PF/VF in one port, only allow
+	 * one tc for VF for simplicity. VF's vport_id is non zero.
+	 */
+	kinfo->num_tc = vport->vport_id ? 1 :
+			min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc);
+	vport->qs_offset = (vport->vport_id ? hdev->tm_info.num_tc : 0) +
+				(vport->vport_id ? (vport->vport_id - 1) : 0);
+
+	max_rss_size = min_t(u16, hdev->rss_size_max,
+			     vport->alloc_tqps / kinfo->num_tc);
+
+	/* Set to user value, no larger than max_rss_size. */
+	if (kinfo->req_rss_size != kinfo->rss_size && kinfo->req_rss_size &&
+	    kinfo->req_rss_size <= max_rss_size) {
+		dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n",
+			 kinfo->rss_size, kinfo->req_rss_size);
+		kinfo->rss_size = kinfo->req_rss_size;
+	} else if (kinfo->rss_size > max_rss_size ||
+		   (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) {
+		/* Set to the maximum specification value (max_rss_size). */
+		dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n",
+			 kinfo->rss_size, max_rss_size);
+		kinfo->rss_size = max_rss_size;
+	}
+
+	kinfo->num_tqps = kinfo->num_tc * kinfo->rss_size;
 	vport->dwrr = 100;  /* 100 percent as init */
 	vport->alloc_rss_size = kinfo->rss_size;
+	vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit;
 
-	for (i = 0; i < kinfo->num_tc; i++) {
-		if (hdev->hw_tc_map & BIT(i)) {
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		if (hdev->hw_tc_map & BIT(i) && i < kinfo->num_tc) {
 			kinfo->tc_info[i].enable = true;
 			kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size;
 			kinfo->tc_info[i].tqp_count = kinfo->rss_size;
@@ -576,8 +598,10 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev)
 		hdev->tm_info.prio_tc[i] =
 			(i >= hdev->tm_info.num_tc) ? 0 : i;
 
-	/* DCB is enabled if we have more than 1 TC */
-	if (hdev->tm_info.num_tc > 1)
+	/* DCB is enabled if we have more than 1 TC or pfc_en is
+	 * non-zero.
+	 */
+	if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en)
 		hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
 	else
 		hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
@@ -585,12 +609,14 @@ static void hclge_tm_tc_info_init(struct hclge_dev *hdev)
 
 static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
 {
+#define BW_PERCENT	100
+
 	u8 i;
 
 	for (i = 0; i < hdev->tm_info.num_pg; i++) {
 		int k;
 
-		hdev->tm_info.pg_dwrr[i] = i ? 0 : 100;
+		hdev->tm_info.pg_dwrr[i] = i ? 0 : BW_PERCENT;
 
 		hdev->tm_info.pg_info[i].pg_id = i;
 		hdev->tm_info.pg_info[i].pg_sch_mode = HCLGE_SCH_MODE_DWRR;
@@ -602,7 +628,7 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
 
 		hdev->tm_info.pg_info[i].tc_bit_map = hdev->hw_tc_map;
 		for (k = 0; k < hdev->tm_info.num_tc; k++)
-			hdev->tm_info.pg_info[i].tc_dwrr[k] = 100;
+			hdev->tm_info.pg_info[i].tc_dwrr[k] = BW_PERCENT;
 	}
 }
 
@@ -663,6 +689,7 @@ static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev)
 static int hclge_tm_pg_shaper_cfg(struct hclge_dev *hdev)
 {
 	u8 ir_u, ir_b, ir_s;
+	u32 shaper_para;
 	int ret;
 	u32 i;
 
@@ -680,18 +707,21 @@ static int hclge_tm_pg_shaper_cfg(struct hclge_dev *hdev)
 		if (ret)
 			return ret;
 
+		shaper_para = hclge_tm_get_shapping_para(0, 0, 0,
+							 HCLGE_SHAPER_BS_U_DEF,
+							 HCLGE_SHAPER_BS_S_DEF);
 		ret = hclge_tm_pg_shapping_cfg(hdev,
 					       HCLGE_TM_SHAP_C_BUCKET, i,
-					       0, 0, 0, HCLGE_SHAPER_BS_U_DEF,
-					       HCLGE_SHAPER_BS_S_DEF);
+					       shaper_para);
 		if (ret)
 			return ret;
 
+		shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+							 HCLGE_SHAPER_BS_U_DEF,
+							 HCLGE_SHAPER_BS_S_DEF);
 		ret = hclge_tm_pg_shapping_cfg(hdev,
 					       HCLGE_TM_SHAP_P_BUCKET, i,
-					       ir_b, ir_u, ir_s,
-					       HCLGE_SHAPER_BS_U_DEF,
-					       HCLGE_SHAPER_BS_S_DEF);
+					       shaper_para);
 		if (ret)
 			return ret;
 	}
@@ -711,8 +741,7 @@ static int hclge_tm_pg_dwrr_cfg(struct hclge_dev *hdev)
 	/* pg to prio */
 	for (i = 0; i < hdev->tm_info.num_pg; i++) {
 		/* Cfg dwrr */
-		ret = hclge_tm_pg_weight_cfg(hdev, i,
-					     hdev->tm_info.pg_dwrr[i]);
+		ret = hclge_tm_pg_weight_cfg(hdev, i, hdev->tm_info.pg_dwrr[i]);
 		if (ret)
 			return ret;
 	}
@@ -753,13 +782,17 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev)
 
 	if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
 		/* Cfg qs -> pri mapping, one by one mapping */
-		for (k = 0; k < hdev->num_alloc_vport; k++)
-			for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		for (k = 0; k < hdev->num_alloc_vport; k++) {
+			struct hnae3_knic_private_info *kinfo =
+				&vport[k].nic.kinfo;
+
+			for (i = 0; i < kinfo->num_tc; i++) {
 				ret = hclge_tm_qs_to_pri_map_cfg(
 					hdev, vport[k].qs_offset + i, i);
 				if (ret)
 					return ret;
 			}
+		}
 	} else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) {
 		/* Cfg qs -> pri mapping,  qs = tc, pri = vf, 8 qs -> 1 pri */
 		for (k = 0; k < hdev->num_alloc_vport; k++)
@@ -788,6 +821,7 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev)
 static int hclge_tm_pri_tc_base_shaper_cfg(struct hclge_dev *hdev)
 {
 	u8 ir_u, ir_b, ir_s;
+	u32 shaper_para;
 	int ret;
 	u32 i;
 
@@ -799,17 +833,19 @@ static int hclge_tm_pri_tc_base_shaper_cfg(struct hclge_dev *hdev)
 		if (ret)
 			return ret;
 
-		ret = hclge_tm_pri_shapping_cfg(
-			hdev, HCLGE_TM_SHAP_C_BUCKET, i,
-			0, 0, 0, HCLGE_SHAPER_BS_U_DEF,
-			HCLGE_SHAPER_BS_S_DEF);
+		shaper_para = hclge_tm_get_shapping_para(0, 0, 0,
+							 HCLGE_SHAPER_BS_U_DEF,
+							 HCLGE_SHAPER_BS_S_DEF);
+		ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_C_BUCKET, i,
+						shaper_para);
 		if (ret)
 			return ret;
 
-		ret = hclge_tm_pri_shapping_cfg(
-			hdev, HCLGE_TM_SHAP_P_BUCKET, i,
-			ir_b, ir_u, ir_s, HCLGE_SHAPER_BS_U_DEF,
-			HCLGE_SHAPER_BS_S_DEF);
+		shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+							 HCLGE_SHAPER_BS_U_DEF,
+							 HCLGE_SHAPER_BS_S_DEF);
+		ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET, i,
+						shaper_para);
 		if (ret)
 			return ret;
 	}
@@ -821,6 +857,7 @@ static int hclge_tm_pri_vnet_base_shaper_pri_cfg(struct hclge_vport *vport)
 {
 	struct hclge_dev *hdev = vport->back;
 	u8 ir_u, ir_b, ir_s;
+	u32 shaper_para;
 	int ret;
 
 	ret = hclge_shaper_para_calc(vport->bw_limit, HCLGE_SHAPER_LVL_VF,
@@ -828,18 +865,19 @@ static int hclge_tm_pri_vnet_base_shaper_pri_cfg(struct hclge_vport *vport)
 	if (ret)
 		return ret;
 
+	shaper_para = hclge_tm_get_shapping_para(0, 0, 0,
+						 HCLGE_SHAPER_BS_U_DEF,
+						 HCLGE_SHAPER_BS_S_DEF);
 	ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_C_BUCKET,
-					vport->vport_id,
-					0, 0, 0, HCLGE_SHAPER_BS_U_DEF,
-					HCLGE_SHAPER_BS_S_DEF);
+					vport->vport_id, shaper_para);
 	if (ret)
 		return ret;
 
+	shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s,
+						 HCLGE_SHAPER_BS_U_DEF,
+						 HCLGE_SHAPER_BS_S_DEF);
 	ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET,
-					vport->vport_id,
-					ir_b, ir_u, ir_s,
-					HCLGE_SHAPER_BS_U_DEF,
-					HCLGE_SHAPER_BS_S_DEF);
+					vport->vport_id, shaper_para);
 	if (ret)
 		return ret;
 
@@ -934,6 +972,36 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
+static int hclge_tm_ets_tc_dwrr_cfg(struct hclge_dev *hdev)
+{
+#define DEFAULT_TC_WEIGHT	1
+#define DEFAULT_TC_OFFSET	14
+
+	struct hclge_ets_tc_weight_cmd *ets_weight;
+	struct hclge_desc desc;
+	unsigned int i;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, false);
+	ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		struct hclge_pg_info *pg_info;
+
+		ets_weight->tc_weight[i] = DEFAULT_TC_WEIGHT;
+
+		if (!(hdev->hw_tc_map & BIT(i)))
+			continue;
+
+		pg_info =
+			&hdev->tm_info.pg_info[hdev->tm_info.tc_info[i].pgid];
+		ets_weight->tc_weight[i] = pg_info->tc_dwrr[i];
+	}
+
+	ets_weight->weight_offset = DEFAULT_TC_OFFSET;
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
 static int hclge_tm_pri_vnet_base_dwrr_pri_cfg(struct hclge_vport *vport)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
@@ -983,6 +1051,19 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
 		ret = hclge_tm_pri_tc_base_dwrr_cfg(hdev);
 		if (ret)
 			return ret;
+
+		if (!hnae3_dev_dcb_supported(hdev))
+			return 0;
+
+		ret = hclge_tm_ets_tc_dwrr_cfg(hdev);
+		if (ret == -EOPNOTSUPP) {
+			dev_warn(&hdev->pdev->dev,
+				 "fw %08x does't support ets tc weight cmd\n",
+				 hdev->fw_version);
+			ret = 0;
+		}
+
+		return ret;
 	} else {
 		ret = hclge_tm_pri_vnet_base_dwrr_cfg(hdev);
 		if (ret)
@@ -992,7 +1073,7 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-int hclge_tm_map_cfg(struct hclge_dev *hdev)
+static int hclge_tm_map_cfg(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -1058,6 +1139,9 @@ static int hclge_tm_schd_mode_vnet_base_cfg(struct hclge_vport *vport)
 	int ret;
 	u8 i;
 
+	if (vport->vport_id >= HNAE3_MAX_TC)
+		return -EINVAL;
+
 	ret = hclge_tm_pri_schd_mode_cfg(hdev, vport->vport_id);
 	if (ret)
 		return ret;
@@ -1107,7 +1191,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
+static int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -1118,7 +1202,7 @@ int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
 	return hclge_tm_lvl34_schd_mode_cfg(hdev);
 }
 
-static int hclge_tm_schd_setup_hw(struct hclge_dev *hdev)
+int hclge_tm_schd_setup_hw(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -1146,8 +1230,8 @@ static int hclge_pause_param_setup_hw(struct hclge_dev *hdev)
 	struct hclge_mac *mac = &hdev->hw.mac;
 
 	return hclge_pause_param_cfg(hdev, mac->mac_addr,
-					 HCLGE_DEFAULT_PAUSE_TRANS_GAP,
-					 HCLGE_DEFAULT_PAUSE_TRANS_TIME);
+				     HCLGE_DEFAULT_PAUSE_TRANS_GAP,
+				     HCLGE_DEFAULT_PAUSE_TRANS_TIME);
 }
 
 static int hclge_pfc_setup_hw(struct hclge_dev *hdev)
@@ -1159,7 +1243,7 @@ static int hclge_pfc_setup_hw(struct hclge_dev *hdev)
 				HCLGE_RX_MAC_PAUSE_EN_MSK;
 
 	return hclge_pfc_pause_en_cfg(hdev, enable_bitmap,
-				      hdev->tm_info.hw_pfc_map);
+				      hdev->tm_info.pfc_en);
 }
 
 /* Each Tc has a 1024 queue sets to backpress, it divides to
@@ -1228,10 +1312,23 @@ static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
 	return hclge_mac_pause_en_cfg(hdev, tx_en, rx_en);
 }
 
-int hclge_pause_setup_hw(struct hclge_dev *hdev)
+static int hclge_tm_bp_setup(struct hclge_dev *hdev)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		ret = hclge_bp_setup_hw(hdev, i);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+int hclge_pause_setup_hw(struct hclge_dev *hdev, bool init)
 {
 	int ret;
-	u8 i;
 
 	ret = hclge_pause_param_setup_hw(hdev);
 	if (ret)
@@ -1245,18 +1342,20 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev)
 	if (!hnae3_dev_dcb_supported(hdev))
 		return 0;
 
-	/* When MAC is GE Mode, hdev does not support pfc setting */
+	/* GE MAC does not support PFC, when driver is initializing and MAC
+	 * is in GE Mode, ignore the error here, otherwise initialization
+	 * will fail.
+	 */
 	ret = hclge_pfc_setup_hw(hdev);
-	if (ret)
-		dev_warn(&hdev->pdev->dev, "set pfc pause failed:%d\n", ret);
-
-	for (i = 0; i < hdev->tm_info.num_tc; i++) {
-		ret = hclge_bp_setup_hw(hdev, i);
-		if (ret)
-			return ret;
+	if (init && ret == -EOPNOTSUPP)
+		dev_warn(&hdev->pdev->dev, "GE MAC does not support pfc\n");
+	else if (ret) {
+		dev_err(&hdev->pdev->dev, "config pfc failed! ret = %d\n",
+			ret);
+		return ret;
 	}
 
-	return 0;
+	return hclge_tm_bp_setup(hdev);
 }
 
 void hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
@@ -1277,7 +1376,8 @@ void hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
 
 void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
 {
-	u8 i, bit_map = 0;
+	u8 bit_map = 0;
+	u8 i;
 
 	hdev->tm_info.num_tc = num_tc;
 
@@ -1294,7 +1394,20 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
 	hclge_tm_schd_info_init(hdev);
 }
 
-int hclge_tm_init_hw(struct hclge_dev *hdev)
+void hclge_tm_pfc_info_update(struct hclge_dev *hdev)
+{
+	/* DCB is enabled if we have more than 1 TC or pfc_en is
+	 * non-zero.
+	 */
+	if (hdev->tm_info.num_tc > 1 || hdev->tm_info.pfc_en)
+		hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
+	else
+		hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+
+	hclge_pfc_info_init(hdev);
+}
+
+int hclge_tm_init_hw(struct hclge_dev *hdev, bool init)
 {
 	int ret;
 
@@ -1306,7 +1419,7 @@ int hclge_tm_init_hw(struct hclge_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclge_pause_setup_hw(hdev);
+	ret = hclge_pause_setup_hw(hdev, init);
 	if (ret)
 		return ret;
 
@@ -1325,5 +1438,22 @@ int hclge_tm_schd_init(struct hclge_dev *hdev)
 	if (ret)
 		return ret;
 
-	return hclge_tm_init_hw(hdev);
+	return hclge_tm_init_hw(hdev, true);
+}
+
+int hclge_tm_vport_map_update(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	int ret;
+
+	hclge_tm_vport_tc_info_update(vport);
+
+	ret = hclge_vport_q_to_qs_map(hdev, vport);
+	if (ret)
+		return ret;
+
+	if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE))
+		return 0;
+
+	return hclge_tm_bp_setup(hdev);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index b6496a439304..818610988d34 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -12,7 +12,7 @@
 
 #define HCLGE_TM_PORT_BASE_MODE_MSK	BIT(0)
 
-#define HCLGE_DEFAULT_PAUSE_TRANS_GAP	0xFF
+#define HCLGE_DEFAULT_PAUSE_TRANS_GAP	0x7F
 #define HCLGE_DEFAULT_PAUSE_TRANS_TIME	0xFFFF
 
 /* SP or DWRR */
@@ -142,13 +142,14 @@ struct hclge_port_shapping_cmd {
 				       (HCLGE_TM_SHAP_##string##_LSH))
 
 int hclge_tm_schd_init(struct hclge_dev *hdev);
-int hclge_pause_setup_hw(struct hclge_dev *hdev);
-int hclge_tm_schd_mode_hw(struct hclge_dev *hdev);
+int hclge_tm_vport_map_update(struct hclge_dev *hdev);
+int hclge_pause_setup_hw(struct hclge_dev *hdev, bool init);
+int hclge_tm_schd_setup_hw(struct hclge_dev *hdev);
 void hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
 void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
+void hclge_tm_pfc_info_update(struct hclge_dev *hdev);
 int hclge_tm_dwrr_cfg(struct hclge_dev *hdev);
-int hclge_tm_map_cfg(struct hclge_dev *hdev);
-int hclge_tm_init_hw(struct hclge_dev *hdev);
+int hclge_tm_init_hw(struct hclge_dev *hdev, bool init);
 int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx);
 int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr);
 int hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
index fb93bbd35845..53804d95ea90 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the HISILICON network device drivers.
 #
 
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 
 obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
-hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
\ No newline at end of file
+hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index 4e78e8812a04..652b796044e3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -27,26 +27,39 @@ static int hclgevf_ring_space(struct hclgevf_cmq_ring *ring)
 	return ring->desc_num - used - 1;
 }
 
+static int hclgevf_is_valid_csq_clean_head(struct hclgevf_cmq_ring *ring,
+					   int head)
+{
+	int ntu = ring->next_to_use;
+	int ntc = ring->next_to_clean;
+
+	if (ntu > ntc)
+		return head >= ntc && head <= ntu;
+
+	return head >= ntc || head <= ntu;
+}
+
 static int hclgevf_cmd_csq_clean(struct hclgevf_hw *hw)
 {
+	struct hclgevf_dev *hdev = container_of(hw, struct hclgevf_dev, hw);
 	struct hclgevf_cmq_ring *csq = &hw->cmq.csq;
-	u16 ntc = csq->next_to_clean;
-	struct hclgevf_desc *desc;
 	int clean = 0;
 	u32 head;
 
-	desc = &csq->desc[ntc];
 	head = hclgevf_read_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG);
-	while (head != ntc) {
-		memset(desc, 0, sizeof(*desc));
-		ntc++;
-		if (ntc == csq->desc_num)
-			ntc = 0;
-		desc = &csq->desc[ntc];
-		clean++;
+	rmb(); /* Make sure head is ready before touch any data */
+
+	if (!hclgevf_is_valid_csq_clean_head(csq, head)) {
+		dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head,
+			 csq->next_to_use, csq->next_to_clean);
+		dev_warn(&hdev->pdev->dev,
+			 "Disabling any further commands to IMP firmware\n");
+		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+		return -EIO;
 	}
-	csq->next_to_clean = ntc;
 
+	clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num;
+	csq->next_to_clean = head;
 	return clean;
 }
 
@@ -85,7 +98,6 @@ static void hclgevf_cmd_config_regs(struct hclgevf_cmq_ring *ring)
 		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val);
 
 		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
-		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
 		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val);
 
 		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
@@ -97,7 +109,6 @@ static void hclgevf_cmd_config_regs(struct hclgevf_cmq_ring *ring)
 		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, reg_val);
 
 		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
-		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
 		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val);
 
 		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
@@ -166,6 +177,38 @@ void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
 		desc->flag &= cpu_to_le16(~HCLGEVF_CMD_FLAG_WR);
 }
 
+static int hclgevf_cmd_convert_err_code(u16 desc_ret)
+{
+	switch (desc_ret) {
+	case HCLGEVF_CMD_EXEC_SUCCESS:
+		return 0;
+	case HCLGEVF_CMD_NO_AUTH:
+		return -EPERM;
+	case HCLGEVF_CMD_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case HCLGEVF_CMD_QUEUE_FULL:
+		return -EXFULL;
+	case HCLGEVF_CMD_NEXT_ERR:
+		return -ENOSR;
+	case HCLGEVF_CMD_UNEXE_ERR:
+		return -ENOTBLK;
+	case HCLGEVF_CMD_PARA_ERR:
+		return -EINVAL;
+	case HCLGEVF_CMD_RESULT_ERR:
+		return -ERANGE;
+	case HCLGEVF_CMD_TIMEOUT:
+		return -ETIME;
+	case HCLGEVF_CMD_HILINK_ERR:
+		return -ENOLINK;
+	case HCLGEVF_CMD_QUEUE_ILLEGAL:
+		return -ENXIO;
+	case HCLGEVF_CMD_INVALID:
+		return -EBADR;
+	default:
+		return -EIO;
+	}
+}
+
 /* hclgevf_cmd_send - send command to command queue
  * @hw: pointer to the hw struct
  * @desc: prefilled descriptor for describing the command
@@ -177,6 +220,7 @@ void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
 int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num)
 {
 	struct hclgevf_dev *hdev = (struct hclgevf_dev *)hw->hdev;
+	struct hclgevf_cmq_ring *csq = &hw->cmq.csq;
 	struct hclgevf_desc *desc_to_use;
 	bool complete = false;
 	u32 timeout = 0;
@@ -188,8 +232,17 @@ int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num)
 
 	spin_lock_bh(&hw->cmq.csq.lock);
 
-	if (num > hclgevf_ring_space(&hw->cmq.csq) ||
-	    test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
+	if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
+		spin_unlock_bh(&hw->cmq.csq.lock);
+		return -EBUSY;
+	}
+
+	if (num > hclgevf_ring_space(&hw->cmq.csq)) {
+		/* If CMDQ ring is full, SW HEAD and HW HEAD may be different,
+		 * need update the SW HEAD pointer csq->next_to_clean
+		 */
+		csq->next_to_clean = hclgevf_read_dev(hw,
+						      HCLGEVF_NIC_CSQ_HEAD_REG);
 		spin_unlock_bh(&hw->cmq.csq.lock);
 		return -EBUSY;
 	}
@@ -238,11 +291,7 @@ int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num)
 			else
 				retval = le16_to_cpu(desc[0].retval);
 
-			if ((enum hclgevf_cmd_return_status)retval ==
-			    HCLGEVF_CMD_EXEC_SUCCESS)
-				status = 0;
-			else
-				status = -EIO;
+			status = hclgevf_cmd_convert_err_code(retval);
 			hw->cmq.last_status = (enum hclgevf_cmd_status)retval;
 			ntc++;
 			handle++;
@@ -252,14 +301,13 @@ int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num)
 	}
 
 	if (!complete)
-		status = -EAGAIN;
+		status = -EBADE;
 
 	/* Clean the command send queue */
 	handle = hclgevf_cmd_csq_clean(hw);
-	if (handle != num) {
+	if (handle != num)
 		dev_warn(&hdev->pdev->dev,
 			 "cleaned %d, need to clean %d\n", handle, num);
-	}
 
 	spin_unlock_bh(&hw->cmq.csq.lock);
 
@@ -321,13 +369,13 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 	int ret;
 
 	spin_lock_bh(&hdev->hw.cmq.csq.lock);
-	spin_lock_bh(&hdev->hw.cmq.crq.lock);
+	spin_lock(&hdev->hw.cmq.crq.lock);
 
 	/* initialize the pointers of async rx queue of mailbox */
 	hdev->arq.hdev = hdev;
 	hdev->arq.head = 0;
 	hdev->arq.tail = 0;
-	hdev->arq.count = 0;
+	atomic_set(&hdev->arq.count, 0);
 	hdev->hw.cmq.csq.next_to_clean = 0;
 	hdev->hw.cmq.csq.next_to_use = 0;
 	hdev->hw.cmq.crq.next_to_clean = 0;
@@ -335,7 +383,7 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 
 	hclgevf_cmd_init_regs(&hdev->hw);
 
-	spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+	spin_unlock(&hdev->hw.cmq.crq.lock);
 	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 
 	clear_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
@@ -344,8 +392,8 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 	 * reset may happen when lower level reset is being processed.
 	 */
 	if (hclgevf_is_reset_pending(hdev)) {
-		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto err_cmd_init;
 	}
 
 	/* get firmware version */
@@ -353,17 +401,42 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to query firmware version\n", ret);
-		return ret;
+		goto err_cmd_init;
 	}
 	hdev->fw_version = version;
 
 	dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
 
 	return 0;
+
+err_cmd_init:
+	set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+
+	return ret;
+}
+
+static void hclgevf_cmd_uninit_regs(struct hclgevf_hw *hw)
+{
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
 }
 
 void hclgevf_cmd_uninit(struct hclgevf_dev *hdev)
 {
+	spin_lock_bh(&hdev->hw.cmq.csq.lock);
+	spin_lock(&hdev->hw.cmq.crq.lock);
+	clear_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+	hclgevf_cmd_uninit_regs(&hdev->hw);
+	spin_unlock(&hdev->hw.cmq.crq.lock);
+	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 	hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
 	hclgevf_free_cmd_desc(&hdev->hw.cmq.crq);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 47030b42341f..127a434a56f3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -46,9 +46,17 @@ struct hclgevf_cmq_ring {
 
 enum hclgevf_cmd_return_status {
 	HCLGEVF_CMD_EXEC_SUCCESS	= 0,
-	HCLGEVF_CMD_NO_AUTH	= 1,
-	HCLGEVF_CMD_NOT_EXEC	= 2,
-	HCLGEVF_CMD_QUEUE_FULL	= 3,
+	HCLGEVF_CMD_NO_AUTH		= 1,
+	HCLGEVF_CMD_NOT_SUPPORTED	= 2,
+	HCLGEVF_CMD_QUEUE_FULL		= 3,
+	HCLGEVF_CMD_NEXT_ERR		= 4,
+	HCLGEVF_CMD_UNEXE_ERR		= 5,
+	HCLGEVF_CMD_PARA_ERR		= 6,
+	HCLGEVF_CMD_RESULT_ERR		= 7,
+	HCLGEVF_CMD_TIMEOUT		= 8,
+	HCLGEVF_CMD_HILINK_ERR		= 9,
+	HCLGEVF_CMD_QUEUE_ILLEGAL	= 10,
+	HCLGEVF_CMD_INVALID		= 11,
 };
 
 enum hclgevf_cmd_status {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 82103d5fa815..a13a0e101c3b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -11,6 +11,8 @@
 
 #define HCLGEVF_NAME	"hclgevf"
 
+#define HCLGEVF_RESET_MAX_FAIL_CNT	5
+
 static int hclgevf_reset_hdev(struct hclgevf_dev *hdev);
 static struct hnae3_ae_algo ae_algovf;
 
@@ -21,6 +23,14 @@ static const struct pci_device_id ae_algovf_pci_tbl[] = {
 	{0, }
 };
 
+static const u8 hclgevf_hash_key[] = {
+	0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2,
+	0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0,
+	0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4,
+	0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C,
+	0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA
+};
+
 MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl);
 
 static const u32 cmdq_reg_addr_list[] = {HCLGEVF_CMDQ_TX_ADDR_L_REG,
@@ -75,10 +85,14 @@ static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG,
 					     HCLGEVF_TQP_INTR_GL2_REG,
 					     HCLGEVF_TQP_INTR_RL_REG};
 
-static inline struct hclgevf_dev *hclgevf_ae_get_hdev(
-	struct hnae3_handle *handle)
+static struct hclgevf_dev *hclgevf_ae_get_hdev(struct hnae3_handle *handle)
 {
-	return container_of(handle, struct hclgevf_dev, nic);
+	if (!handle->client)
+		return container_of(handle, struct hclgevf_dev, nic);
+	else if (handle->client->type == HNAE3_CLIENT_ROCE)
+		return container_of(handle, struct hclgevf_dev, roce);
+	else
+		return container_of(handle, struct hclgevf_dev, nic);
 }
 
 static int hclgevf_tqps_update_stats(struct hnae3_handle *handle)
@@ -219,7 +233,7 @@ static int hclgevf_get_tc_info(struct hclgevf_dev *hdev)
 	int status;
 
 	status = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_TCINFO, 0, NULL, 0,
-				      true, &resp_msg, sizeof(u8));
+				      true, &resp_msg, sizeof(resp_msg));
 	if (status) {
 		dev_err(&hdev->pdev->dev,
 			"VF request to get TC info from PF failed %d",
@@ -232,9 +246,30 @@ static int hclgevf_get_tc_info(struct hclgevf_dev *hdev)
 	return 0;
 }
 
+static int hclgevf_get_port_base_vlan_filter_state(struct hclgevf_dev *hdev)
+{
+	struct hnae3_handle *nic = &hdev->nic;
+	u8 resp_msg;
+	int ret;
+
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+				   HCLGE_MBX_GET_PORT_BASE_VLAN_STATE,
+				   NULL, 0, true, &resp_msg, sizeof(u8));
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"VF request to get port based vlan state failed %d",
+			ret);
+		return ret;
+	}
+
+	nic->port_base_vlan_state = resp_msg;
+
+	return 0;
+}
+
 static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
 {
-#define HCLGEVF_TQPS_RSS_INFO_LEN	8
+#define HCLGEVF_TQPS_RSS_INFO_LEN	6
 	u8 resp_msg[HCLGEVF_TQPS_RSS_INFO_LEN];
 	int status;
 
@@ -250,8 +285,29 @@ static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
 
 	memcpy(&hdev->num_tqps, &resp_msg[0], sizeof(u16));
 	memcpy(&hdev->rss_size_max, &resp_msg[2], sizeof(u16));
-	memcpy(&hdev->num_desc, &resp_msg[4], sizeof(u16));
-	memcpy(&hdev->rx_buf_len, &resp_msg[6], sizeof(u16));
+	memcpy(&hdev->rx_buf_len, &resp_msg[4], sizeof(u16));
+
+	return 0;
+}
+
+static int hclgevf_get_queue_depth(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_TQPS_DEPTH_INFO_LEN	4
+	u8 resp_msg[HCLGEVF_TQPS_DEPTH_INFO_LEN];
+	int ret;
+
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_QDEPTH, 0, NULL, 0,
+				   true, resp_msg,
+				   HCLGEVF_TQPS_DEPTH_INFO_LEN);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"VF request to get tqp depth info from PF failed %d",
+			ret);
+		return ret;
+	}
+
+	memcpy(&hdev->num_tx_desc, &resp_msg[0], sizeof(u16));
+	memcpy(&hdev->num_rx_desc, &resp_msg[2], sizeof(u16));
 
 	return 0;
 }
@@ -266,13 +322,34 @@ static u16 hclgevf_get_qid_global(struct hnae3_handle *handle, u16 queue_id)
 	memcpy(&msg_data[0], &queue_id, sizeof(queue_id));
 
 	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_QID_IN_PF, 0, msg_data,
-				   2, true, resp_data, 2);
+				   sizeof(msg_data), true, resp_data,
+				   sizeof(resp_data));
 	if (!ret)
 		qid_in_pf = *(u16 *)resp_data;
 
 	return qid_in_pf;
 }
 
+static int hclgevf_get_pf_media_type(struct hclgevf_dev *hdev)
+{
+	u8 resp_msg[2];
+	int ret;
+
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_MEDIA_TYPE, 0, NULL, 0,
+				   true, resp_msg, sizeof(resp_msg));
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"VF request to get the pf port media type failed %d",
+			ret);
+		return ret;
+	}
+
+	hdev->hw.mac.media_type = resp_msg[0];
+	hdev->hw.mac.module_type = resp_msg[1];
+
+	return 0;
+}
+
 static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 {
 	struct hclgevf_tqp *tqp;
@@ -291,7 +368,8 @@ static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 
 		tqp->q.ae_algo = &ae_algovf;
 		tqp->q.buf_size = hdev->rx_buf_len;
-		tqp->q.desc_num = hdev->num_desc;
+		tqp->q.tx_desc_num = hdev->num_tx_desc;
+		tqp->q.rx_desc_num = hdev->num_rx_desc;
 		tqp->q.io_base = hdev->hw.io_base + HCLGEVF_TQP_REG_OFFSET +
 			i * HCLGEVF_TQP_REG_SIZE;
 
@@ -306,11 +384,12 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev)
 	struct hnae3_handle *nic = &hdev->nic;
 	struct hnae3_knic_private_info *kinfo;
 	u16 new_tqps = hdev->num_tqps;
-	int i;
+	unsigned int i;
 
 	kinfo = &nic->kinfo;
 	kinfo->num_tc = 0;
-	kinfo->num_desc = hdev->num_desc;
+	kinfo->num_tx_desc = hdev->num_tx_desc;
+	kinfo->num_rx_desc = hdev->num_rx_desc;
 	kinfo->rx_buf_len = hdev->rx_buf_len;
 	for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++)
 		if (hdev->hw_tc_map & BIT(i))
@@ -341,7 +420,7 @@ static void hclgevf_request_link_info(struct hclgevf_dev *hdev)
 	u8 resp_msg;
 
 	status = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_LINK_STATUS, 0, NULL,
-				      0, false, &resp_msg, sizeof(u8));
+				      0, false, &resp_msg, sizeof(resp_msg));
 	if (status)
 		dev_err(&hdev->pdev->dev,
 			"VF failed to fetch link status(%d) from PF", status);
@@ -349,20 +428,42 @@ static void hclgevf_request_link_info(struct hclgevf_dev *hdev)
 
 void hclgevf_update_link_status(struct hclgevf_dev *hdev, int link_state)
 {
+	struct hnae3_handle *rhandle = &hdev->roce;
 	struct hnae3_handle *handle = &hdev->nic;
+	struct hnae3_client *rclient;
 	struct hnae3_client *client;
 
 	client = handle->client;
+	rclient = hdev->roce_client;
 
 	link_state =
 		test_bit(HCLGEVF_STATE_DOWN, &hdev->state) ? 0 : link_state;
 
 	if (link_state != hdev->hw.mac.link) {
 		client->ops->link_status_change(handle, !!link_state);
+		if (rclient && rclient->ops->link_status_change)
+			rclient->ops->link_status_change(rhandle, !!link_state);
 		hdev->hw.mac.link = link_state;
 	}
 }
 
+static void hclgevf_update_link_mode(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_ADVERTISING 0
+#define HCLGEVF_SUPPORTED   1
+	u8 send_msg;
+	u8 resp_msg;
+
+	send_msg = HCLGEVF_ADVERTISING;
+	hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_LINK_MODE, 0,
+			     &send_msg, sizeof(send_msg), false,
+			     &resp_msg, sizeof(resp_msg));
+	send_msg = HCLGEVF_SUPPORTED;
+	hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_LINK_MODE, 0,
+			     &send_msg, sizeof(send_msg), false,
+			     &resp_msg, sizeof(resp_msg));
+}
+
 static int hclgevf_set_handle_info(struct hclgevf_dev *hdev)
 {
 	struct hnae3_handle *nic = &hdev->nic;
@@ -373,12 +474,6 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev)
 	nic->numa_node_mask = hdev->numa_node_mask;
 	nic->flags |= HNAE3_SUPPORT_VF;
 
-	if (hdev->ae_dev->dev_type != HNAE3_DEV_KNIC) {
-		dev_err(&hdev->pdev->dev, "unsupported device type %d\n",
-			hdev->ae_dev->dev_type);
-		return -EINVAL;
-	}
-
 	ret = hclgevf_knic_setup(hdev);
 	if (ret)
 		dev_err(&hdev->pdev->dev, "VF knic setup failed %d\n",
@@ -447,14 +542,16 @@ static int hclgevf_set_rss_algo_key(struct hclgevf_dev *hdev,
 				    const u8 hfunc, const u8 *key)
 {
 	struct hclgevf_rss_config_cmd *req;
+	unsigned int key_offset = 0;
 	struct hclgevf_desc desc;
-	int key_offset;
+	int key_counts;
 	int key_size;
 	int ret;
 
+	key_counts = HCLGEVF_RSS_KEY_SIZE;
 	req = (struct hclgevf_rss_config_cmd *)desc.data;
 
-	for (key_offset = 0; key_offset < 3; key_offset++) {
+	while (key_counts) {
 		hclgevf_cmd_setup_basic_desc(&desc,
 					     HCLGEVF_OPC_RSS_GENERIC_CONFIG,
 					     false);
@@ -463,15 +560,12 @@ static int hclgevf_set_rss_algo_key(struct hclgevf_dev *hdev,
 		req->hash_config |=
 			(key_offset << HCLGEVF_RSS_HASH_KEY_OFFSET_B);
 
-		if (key_offset == 2)
-			key_size =
-			HCLGEVF_RSS_KEY_SIZE - HCLGEVF_RSS_HASH_KEY_NUM * 2;
-		else
-			key_size = HCLGEVF_RSS_HASH_KEY_NUM;
-
+		key_size = min(HCLGEVF_RSS_HASH_KEY_NUM, key_counts);
 		memcpy(req->hash_key,
 		       key + key_offset * HCLGEVF_RSS_HASH_KEY_NUM, key_size);
 
+		key_counts -= key_size;
+		key_offset++;
 		ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
 		if (ret) {
 			dev_err(&hdev->pdev->dev,
@@ -534,7 +628,7 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 	struct hclgevf_desc desc;
 	u16 roundup_size;
 	int status;
-	int i;
+	unsigned int i;
 
 	req = (struct hclgevf_rss_tc_mode_cmd *)desc.data;
 
@@ -564,12 +658,50 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 	return status;
 }
 
+/* for revision 0x20, vf shared the same rss config with pf */
+static int hclgevf_get_rss_hash_key(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_RSS_MBX_RESP_LEN	8
+
+	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
+	u8 resp_msg[HCLGEVF_RSS_MBX_RESP_LEN];
+	u16 msg_num, hash_key_index;
+	u8 index;
+	int ret;
+
+	msg_num = (HCLGEVF_RSS_KEY_SIZE + HCLGEVF_RSS_MBX_RESP_LEN - 1) /
+			HCLGEVF_RSS_MBX_RESP_LEN;
+	for (index = 0; index < msg_num; index++) {
+		ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_RSS_KEY, 0,
+					   &index, sizeof(index),
+					   true, resp_msg,
+					   HCLGEVF_RSS_MBX_RESP_LEN);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"VF get rss hash key from PF failed, ret=%d",
+				ret);
+			return ret;
+		}
+
+		hash_key_index = HCLGEVF_RSS_MBX_RESP_LEN * index;
+		if (index == msg_num - 1)
+			memcpy(&rss_cfg->rss_hash_key[hash_key_index],
+			       &resp_msg[0],
+			       HCLGEVF_RSS_KEY_SIZE - hash_key_index);
+		else
+			memcpy(&rss_cfg->rss_hash_key[hash_key_index],
+			       &resp_msg[0], HCLGEVF_RSS_MBX_RESP_LEN);
+	}
+
+	return 0;
+}
+
 static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key,
 			   u8 *hfunc)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
-	int i;
+	int i, ret;
 
 	if (handle->pdev->revision >= 0x21) {
 		/* Get hash algorithm */
@@ -591,6 +723,16 @@ static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key,
 		if (key)
 			memcpy(key, rss_cfg->rss_hash_key,
 			       HCLGEVF_RSS_KEY_SIZE);
+	} else {
+		if (hfunc)
+			*hfunc = ETH_RSS_HASH_TOP;
+		if (key) {
+			ret = hclgevf_get_rss_hash_key(hdev);
+			if (ret)
+				return ret;
+			memcpy(key, rss_cfg->rss_hash_key,
+			       HCLGEVF_RSS_KEY_SIZE);
+		}
 	}
 
 	if (indir)
@@ -852,6 +994,8 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
 	u8 type;
 
 	req = (struct hclge_mbx_vf_to_pf_cmd *)desc.data;
+	type = en ? HCLGE_MBX_MAP_RING_TO_VECTOR :
+		HCLGE_MBX_UNMAP_RING_TO_VECTOR;
 
 	for (node = ring_chain; node; node = node->next) {
 		int idx_offset = HCLGE_MBX_RING_MAP_BASIC_MSG_NUM +
@@ -861,9 +1005,6 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
 			hclgevf_cmd_setup_basic_desc(&desc,
 						     HCLGEVF_OPC_MBX_VF_TO_PF,
 						     false);
-			type = en ?
-				HCLGE_MBX_MAP_RING_TO_VECTOR :
-				HCLGE_MBX_UNMAP_RING_TO_VECTOR;
 			req->msg[0] = type;
 			req->msg[1] = vector_id;
 		}
@@ -964,36 +1105,32 @@ static int hclgevf_put_vector(struct hnae3_handle *handle, int vector)
 }
 
 static int hclgevf_cmd_set_promisc_mode(struct hclgevf_dev *hdev,
-					bool en_uc_pmc, bool en_mc_pmc)
+					bool en_bc_pmc)
 {
 	struct hclge_mbx_vf_to_pf_cmd *req;
 	struct hclgevf_desc desc;
-	int status;
+	int ret;
 
 	req = (struct hclge_mbx_vf_to_pf_cmd *)desc.data;
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_VF_TO_PF, false);
 	req->msg[0] = HCLGE_MBX_SET_PROMISC_MODE;
-	req->msg[1] = en_uc_pmc ? 1 : 0;
-	req->msg[2] = en_mc_pmc ? 1 : 0;
+	req->msg[1] = en_bc_pmc ? 1 : 0;
 
-	status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
-	if (status)
+	ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
 		dev_err(&hdev->pdev->dev,
-			"Set promisc mode fail, status is %d.\n", status);
+			"Set promisc mode fail, status is %d.\n", ret);
 
-	return status;
+	return ret;
 }
 
-static int hclgevf_set_promisc_mode(struct hnae3_handle *handle,
-				    bool en_uc_pmc, bool en_mc_pmc)
+static int hclgevf_set_promisc_mode(struct hclgevf_dev *hdev, bool en_bc_pmc)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-
-	return hclgevf_cmd_set_promisc_mode(hdev, en_uc_pmc, en_mc_pmc);
+	return hclgevf_cmd_set_promisc_mode(hdev, en_bc_pmc);
 }
 
-static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id,
+static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, unsigned int tqp_id,
 			      int stream_id, bool enable)
 {
 	struct hclgevf_cfg_com_tqp_queue_cmd *req;
@@ -1006,7 +1143,8 @@ static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id,
 				     false);
 	req->tqp_id = cpu_to_le16(tqp_id & HCLGEVF_RING_ID_MASK);
 	req->stream_id = cpu_to_le16(stream_id);
-	req->enable |= enable << HCLGEVF_TQP_ENABLE_B;
+	if (enable)
+		req->enable |= 1U << HCLGEVF_TQP_ENABLE_B;
 
 	status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
 	if (status)
@@ -1052,7 +1190,7 @@ static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p,
 			HCLGE_MBX_MAC_VLAN_UC_MODIFY;
 
 	status = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_UNICAST,
-				      subcode, msg_data, ETH_ALEN * 2,
+				      subcode, msg_data, sizeof(msg_data),
 				      true, NULL, 0);
 	if (!status)
 		ether_addr_copy(hdev->hw.mac.mac_addr, new_mac_addr);
@@ -1107,19 +1245,61 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle,
 #define HCLGEVF_VLAN_MBX_MSG_LEN 5
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	u8 msg_data[HCLGEVF_VLAN_MBX_MSG_LEN];
+	int ret;
 
-	if (vlan_id > 4095)
+	if (vlan_id > HCLGEVF_MAX_VLAN_ID)
 		return -EINVAL;
 
 	if (proto != htons(ETH_P_8021Q))
 		return -EPROTONOSUPPORT;
 
+	/* When device is resetting, firmware is unable to handle
+	 * mailbox. Just record the vlan id, and remove it after
+	 * reset finished.
+	 */
+	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state) && is_kill) {
+		set_bit(vlan_id, hdev->vlan_del_fail_bmap);
+		return -EBUSY;
+	}
+
 	msg_data[0] = is_kill;
 	memcpy(&msg_data[1], &vlan_id, sizeof(vlan_id));
 	memcpy(&msg_data[3], &proto, sizeof(proto));
-	return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
-				    HCLGE_MBX_VLAN_FILTER, msg_data,
-				    HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0);
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+				   HCLGE_MBX_VLAN_FILTER, msg_data,
+				   HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0);
+
+	/* When remove hw vlan filter failed, record the vlan id,
+	 * and try to remove it from hw later, to be consistence
+	 * with stack.
+	 */
+	if (is_kill && ret)
+		set_bit(vlan_id, hdev->vlan_del_fail_bmap);
+
+	return ret;
+}
+
+static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_MAX_SYNC_COUNT	60
+	struct hnae3_handle *handle = &hdev->nic;
+	int ret, sync_cnt = 0;
+	u16 vlan_id;
+
+	vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
+	while (vlan_id != VLAN_N_VID) {
+		ret = hclgevf_set_vlan_filter(handle, htons(ETH_P_8021Q),
+					      vlan_id, true);
+		if (ret)
+			return;
+
+		clear_bit(vlan_id, hdev->vlan_del_fail_bmap);
+		sync_cnt++;
+		if (sync_cnt >= HCLGEVF_MAX_SYNC_COUNT)
+			return;
+
+		vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID);
+	}
 }
 
 static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
@@ -1139,7 +1319,7 @@ static int hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
 	u8 msg_data[2];
 	int ret;
 
-	memcpy(&msg_data[0], &queue_id, sizeof(queue_id));
+	memcpy(msg_data, &queue_id, sizeof(queue_id));
 
 	/* disable vf queue before send queue reset msg to PF */
 	ret = hclgevf_tqp_enable(hdev, queue_id, 0, false);
@@ -1147,7 +1327,7 @@ static int hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
 		return ret;
 
 	return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_QUEUE_RESET, 0, msg_data,
-				    2, true, NULL, 0);
+				    sizeof(msg_data), true, NULL, 0);
 }
 
 static int hclgevf_set_mtu(struct hnae3_handle *handle, int new_mtu)
@@ -1165,6 +1345,10 @@ static int hclgevf_notify_client(struct hclgevf_dev *hdev,
 	struct hnae3_handle *handle = &hdev->nic;
 	int ret;
 
+	if (!test_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state) ||
+	    !client)
+		return 0;
+
 	if (!client->ops->reset_notify)
 		return -EOPNOTSUPP;
 
@@ -1264,33 +1448,58 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	if (ret)
 		return ret;
 
-	return 0;
+	return hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT);
 }
 
 static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev)
 {
+#define HCLGEVF_RESET_SYNC_TIME 100
+
 	int ret = 0;
 
 	switch (hdev->reset_type) {
 	case HNAE3_VF_FUNC_RESET:
 		ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_RESET, 0, NULL,
 					   0, true, NULL, sizeof(u8));
+		hdev->rst_stats.vf_func_rst_cnt++;
 		break;
 	case HNAE3_FLR_RESET:
 		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+		hdev->rst_stats.flr_rst_cnt++;
 		break;
 	default:
 		break;
 	}
 
 	set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
-
+	/* inform hardware that preparatory work is done */
+	msleep(HCLGEVF_RESET_SYNC_TIME);
+	hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG,
+			  HCLGEVF_NIC_CMQ_ENABLE);
 	dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done, ret:%d\n",
 		 hdev->reset_type, ret);
 
 	return ret;
 }
 
+static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev)
+{
+	hdev->rst_stats.rst_fail_cnt++;
+	dev_err(&hdev->pdev->dev, "failed to reset VF(%d)\n",
+		hdev->rst_stats.rst_fail_cnt);
+
+	if (hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT)
+		set_bit(hdev->reset_type, &hdev->reset_pending);
+
+	if (hclgevf_is_reset_pending(hdev)) {
+		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
+		hclgevf_reset_task_schedule(hdev);
+	} else {
+		hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG,
+				  HCLGEVF_NIC_CMQ_ENABLE);
+	}
+}
+
 static int hclgevf_reset(struct hclgevf_dev *hdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
@@ -1300,7 +1509,7 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 	 * know if device is undergoing reset
 	 */
 	ae_dev->reset_type = hdev->reset_type;
-	hdev->reset_count++;
+	hdev->rst_stats.rst_cnt++;
 	rtnl_lock();
 
 	/* bring down the nic to stop any ongoing TX/RX */
@@ -1326,6 +1535,8 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 		goto err_reset;
 	}
 
+	hdev->rst_stats.hw_rst_done_cnt++;
+
 	rtnl_lock();
 
 	/* now, re-initialize the nic client and ae device*/
@@ -1344,17 +1555,14 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 
 	hdev->last_reset_time = jiffies;
 	ae_dev->reset_type = HNAE3_NONE_RESET;
+	hdev->rst_stats.rst_done_cnt++;
+	hdev->rst_stats.rst_fail_cnt = 0;
 
 	return ret;
 err_reset_lock:
 	rtnl_unlock();
 err_reset:
-	/* When VF reset failed, only the higher level reset asserted by PF
-	 * can restore it, so re-initialize the command queue to receive
-	 * this higher reset event.
-	 */
-	hclgevf_cmd_init(hdev);
-	dev_err(&hdev->pdev->dev, "failed to reset VF\n");
+	hclgevf_reset_err_handle(hdev);
 
 	return ret;
 }
@@ -1465,7 +1673,7 @@ static void hclgevf_get_misc_vector(struct hclgevf_dev *hdev)
 void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev)
 {
 	if (!test_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state) &&
-	    !test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) {
+	    !test_bit(HCLGEVF_STATE_REMOVING, &hdev->state)) {
 		set_bit(HCLGEVF_STATE_RST_SERVICE_SCHED, &hdev->state);
 		schedule_work(&hdev->rst_service_task);
 	}
@@ -1501,8 +1709,10 @@ static void hclgevf_service_timer(struct timer_list *t)
 {
 	struct hclgevf_dev *hdev = from_timer(hdev, t, service_timer);
 
-	mod_timer(&hdev->service_timer, jiffies + 5 * HZ);
+	mod_timer(&hdev->service_timer, jiffies +
+		  HCLGEVF_GENERAL_TASK_INTERVAL * HZ);
 
+	hdev->stats_timer++;
 	hclgevf_task_schedule(hdev);
 }
 
@@ -1520,9 +1730,9 @@ static void hclgevf_reset_service_task(struct work_struct *work)
 	if (test_and_clear_bit(HCLGEVF_RESET_PENDING,
 			       &hdev->reset_state)) {
 		/* PF has initmated that it is about to reset the hardware.
-		 * We now have to poll & check if harware has actually completed
-		 * the reset sequence. On hardware reset completion, VF needs to
-		 * reset the client and ae device.
+		 * We now have to poll & check if hardware has actually
+		 * completed the reset sequence. On hardware reset completion,
+		 * VF needs to reset the client and ae device.
 		 */
 		hdev->reset_attempts = 0;
 
@@ -1538,7 +1748,7 @@ static void hclgevf_reset_service_task(struct work_struct *work)
 	} else if (test_and_clear_bit(HCLGEVF_RESET_REQUESTED,
 				      &hdev->reset_state)) {
 		/* we could be here when either of below happens:
-		 * 1. reset was initiated due to watchdog timeout due to
+		 * 1. reset was initiated due to watchdog timeout caused by
 		 *    a. IMP was earlier reset and our TX got choked down and
 		 *       which resulted in watchdog reacting and inducing VF
 		 *       reset. This also means our cmdq would be unreliable.
@@ -1600,7 +1810,8 @@ static void hclgevf_keep_alive_timer(struct timer_list *t)
 	struct hclgevf_dev *hdev = from_timer(hdev, t, keep_alive_timer);
 
 	schedule_work(&hdev->keep_alive_task);
-	mod_timer(&hdev->keep_alive_timer, jiffies + 2 * HZ);
+	mod_timer(&hdev->keep_alive_timer, jiffies +
+		  HCLGEVF_KEEP_ALIVE_TASK_INTERVAL * HZ);
 }
 
 static void hclgevf_keep_alive_task(struct work_struct *work)
@@ -1610,8 +1821,12 @@ static void hclgevf_keep_alive_task(struct work_struct *work)
 	int ret;
 
 	hdev = container_of(work, struct hclgevf_dev, keep_alive_task);
+
+	if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state))
+		return;
+
 	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_KEEP_ALIVE, 0, NULL,
-				   0, false, &respmsg, sizeof(u8));
+				   0, false, &respmsg, sizeof(respmsg));
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"VF sends keep alive cmd failed(=%d)\n", ret);
@@ -1619,15 +1834,26 @@ static void hclgevf_keep_alive_task(struct work_struct *work)
 
 static void hclgevf_service_task(struct work_struct *work)
 {
+	struct hnae3_handle *handle;
 	struct hclgevf_dev *hdev;
 
 	hdev = container_of(work, struct hclgevf_dev, service_task);
+	handle = &hdev->nic;
+
+	if (hdev->stats_timer >= HCLGEVF_STATS_TIMER_INTERVAL) {
+		hclgevf_tqps_update_stats(handle);
+		hdev->stats_timer = 0;
+	}
 
 	/* request the link status from the PF. PF would be able to tell VF
 	 * about such updates in future so we might remove this later
 	 */
 	hclgevf_request_link_info(hdev);
 
+	hclgevf_update_link_mode(hdev);
+
+	hclgevf_sync_vlan_filter(hdev);
+
 	hclgevf_deferred_task_schedule(hdev);
 
 	clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state);
@@ -1656,6 +1882,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
 		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
 		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B);
 		*clearval = cmdq_src_reg;
+		hdev->rst_stats.vf_rst_cnt++;
 		return HCLGEVF_VECTOR0_EVENT_RST;
 	}
 
@@ -1708,12 +1935,25 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
 {
 	int ret;
 
-	hdev->hw.mac.media_type = HNAE3_MEDIA_TYPE_NONE;
+	/* get current port based vlan state from PF */
+	ret = hclgevf_get_port_base_vlan_filter_state(hdev);
+	if (ret)
+		return ret;
 
 	/* get queue configuration from PF */
 	ret = hclgevf_get_queue_info(hdev);
 	if (ret)
 		return ret;
+
+	/* get queue depth info from PF */
+	ret = hclgevf_get_queue_depth(hdev);
+	if (ret)
+		return ret;
+
+	ret = hclgevf_get_pf_media_type(hdev);
+	if (ret)
+		return ret;
+
 	/* get tc configuration from PF */
 	return hclgevf_get_tc_info(hdev);
 }
@@ -1788,9 +2028,9 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 	rss_cfg->rss_size = hdev->rss_size_max;
 
 	if (hdev->pdev->revision >= 0x21) {
-		rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_TOEPLITZ;
-		netdev_rss_key_fill(rss_cfg->rss_hash_key,
-				    HCLGEVF_RSS_KEY_SIZE);
+		rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_SIMPLE;
+		memcpy(rss_cfg->rss_hash_key, hclgevf_hash_key,
+		       HCLGEVF_RSS_KEY_SIZE);
 
 		ret = hclgevf_set_rss_algo_key(hdev, rss_cfg->hash_algo,
 					       rss_cfg->rss_hash_key);
@@ -1820,7 +2060,7 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 
 	}
 
-	/* Initialize RSS indirect table for each vport */
+	/* Initialize RSS indirect table */
 	for (i = 0; i < HCLGEVF_RSS_IND_TBL_SIZE; i++)
 		rss_cfg->rss_indirection_tbl[i] = i % hdev->rss_size_max;
 
@@ -1833,9 +2073,6 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 
 static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
 {
-	/* other vlan config(like, VLAN TX/RX offload) would also be added
-	 * here later
-	 */
 	return hclgevf_set_vlan_filter(&hdev->nic, htons(ETH_P_8021Q), 0,
 				       false);
 }
@@ -1857,11 +2094,12 @@ static int hclgevf_ae_start(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 
-	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
 
 	hclgevf_request_link_info(hdev);
 
+	hclgevf_update_link_mode(hdev);
+
 	clear_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 
 	return 0;
@@ -1874,10 +2112,11 @@ static void hclgevf_ae_stop(struct hnae3_handle *handle)
 
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 
-	for (i = 0; i < handle->kinfo.num_tqps; i++)
-		hclgevf_reset_tqp(handle, i);
+	if (hdev->reset_type != HNAE3_VF_RESET)
+		for (i = 0; i < handle->kinfo.num_tqps; i++)
+			if (hclgevf_reset_tqp(handle, i))
+				break;
 
-	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
 	hclgevf_update_link_status(hdev, 0);
 }
@@ -1895,9 +2134,16 @@ static int hclgevf_set_alive(struct hnae3_handle *handle, bool alive)
 static int hclgevf_client_start(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
+
+	ret = hclgevf_set_alive(handle, true);
+	if (ret)
+		return ret;
 
-	mod_timer(&hdev->keep_alive_timer, jiffies + 2 * HZ);
-	return hclgevf_set_alive(handle, true);
+	mod_timer(&hdev->keep_alive_timer, jiffies +
+		  HCLGEVF_KEEP_ALIVE_TASK_INTERVAL * HZ);
+
+	return 0;
 }
 
 static void hclgevf_client_stop(struct hnae3_handle *handle)
@@ -1938,7 +2184,12 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev)
 static void hclgevf_state_uninit(struct hclgevf_dev *hdev)
 {
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
+	set_bit(HCLGEVF_STATE_REMOVING, &hdev->state);
 
+	if (hdev->keep_alive_timer.function)
+		del_timer_sync(&hdev->keep_alive_timer);
+	if (hdev->keep_alive_task.func)
+		cancel_work_sync(&hdev->keep_alive_task);
 	if (hdev->service_timer.function)
 		del_timer_sync(&hdev->service_timer);
 	if (hdev->service_task.func)
@@ -2043,6 +2294,65 @@ static void hclgevf_misc_irq_uninit(struct hclgevf_dev *hdev)
 	hclgevf_free_vector(hdev, 0);
 }
 
+static void hclgevf_info_show(struct hclgevf_dev *hdev)
+{
+	struct device *dev = &hdev->pdev->dev;
+
+	dev_info(dev, "VF info begin:\n");
+
+	dev_info(dev, "Task queue pairs numbers: %d\n", hdev->num_tqps);
+	dev_info(dev, "Desc num per TX queue: %d\n", hdev->num_tx_desc);
+	dev_info(dev, "Desc num per RX queue: %d\n", hdev->num_rx_desc);
+	dev_info(dev, "Numbers of vports: %d\n", hdev->num_alloc_vport);
+	dev_info(dev, "HW tc map: %d\n", hdev->hw_tc_map);
+	dev_info(dev, "PF media type of this VF: %d\n",
+		 hdev->hw.mac.media_type);
+
+	dev_info(dev, "VF info end.\n");
+}
+
+static int hclgevf_init_nic_client_instance(struct hnae3_ae_dev *ae_dev,
+					    struct hnae3_client *client)
+{
+	struct hclgevf_dev *hdev = ae_dev->priv;
+	int ret;
+
+	ret = client->ops->init_instance(&hdev->nic);
+	if (ret)
+		return ret;
+
+	set_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state);
+	hnae3_set_client_init_flag(client, ae_dev, 1);
+
+	if (netif_msg_drv(&hdev->nic))
+		hclgevf_info_show(hdev);
+
+	return 0;
+}
+
+static int hclgevf_init_roce_client_instance(struct hnae3_ae_dev *ae_dev,
+					     struct hnae3_client *client)
+{
+	struct hclgevf_dev *hdev = ae_dev->priv;
+	int ret;
+
+	if (!hnae3_dev_roce_supported(hdev) || !hdev->roce_client ||
+	    !hdev->nic_client)
+		return 0;
+
+	ret = hclgevf_init_roce_base_info(hdev);
+	if (ret)
+		return ret;
+
+	ret = client->ops->init_instance(&hdev->roce);
+	if (ret)
+		return ret;
+
+	hnae3_set_client_init_flag(client, ae_dev, 1);
+
+	return 0;
+}
+
 static int hclgevf_init_client_instance(struct hnae3_client *client,
 					struct hnae3_ae_dev *ae_dev)
 {
@@ -2054,35 +2364,15 @@ static int hclgevf_init_client_instance(struct hnae3_client *client,
 		hdev->nic_client = client;
 		hdev->nic.client = client;
 
-		ret = client->ops->init_instance(&hdev->nic);
+		ret = hclgevf_init_nic_client_instance(ae_dev, client);
 		if (ret)
 			goto clear_nic;
 
-		hnae3_set_client_init_flag(client, ae_dev, 1);
-
-		if (hdev->roce_client && hnae3_dev_roce_supported(hdev)) {
-			struct hnae3_client *rc = hdev->roce_client;
-
-			ret = hclgevf_init_roce_base_info(hdev);
-			if (ret)
-				goto clear_roce;
-			ret = rc->ops->init_instance(&hdev->roce);
-			if (ret)
-				goto clear_roce;
-
-			hnae3_set_client_init_flag(hdev->roce_client, ae_dev,
-						   1);
-		}
-		break;
-	case HNAE3_CLIENT_UNIC:
-		hdev->nic_client = client;
-		hdev->nic.client = client;
-
-		ret = client->ops->init_instance(&hdev->nic);
+		ret = hclgevf_init_roce_client_instance(ae_dev,
+							hdev->roce_client);
 		if (ret)
-			goto clear_nic;
+			goto clear_roce;
 
-		hnae3_set_client_init_flag(client, ae_dev, 1);
 		break;
 	case HNAE3_CLIENT_ROCE:
 		if (hnae3_dev_roce_supported(hdev)) {
@@ -2090,17 +2380,10 @@ static int hclgevf_init_client_instance(struct hnae3_client *client,
 			hdev->roce.client = client;
 		}
 
-		if (hdev->roce_client && hdev->nic_client) {
-			ret = hclgevf_init_roce_base_info(hdev);
-			if (ret)
-				goto clear_roce;
-
-			ret = client->ops->init_instance(&hdev->roce);
-			if (ret)
-				goto clear_roce;
-		}
+		ret = hclgevf_init_roce_client_instance(ae_dev, client);
+		if (ret)
+			goto clear_roce;
 
-		hnae3_set_client_init_flag(client, ae_dev, 1);
 		break;
 	default:
 		return -EINVAL;
@@ -2133,6 +2416,8 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client,
 	/* un-init nic/unic, if this was not called by roce client */
 	if (client->ops->uninit_instance && hdev->nic_client &&
 	    client->type != HNAE3_CLIENT_ROCE) {
+		clear_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state);
+
 		client->ops->uninit_instance(&hdev->nic, 0);
 		hdev->nic_client = NULL;
 		hdev->nic.client = NULL;
@@ -2303,6 +2588,12 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 		return ret;
 	}
 
+	if (pdev->revision >= 0x21) {
+		ret = hclgevf_set_promisc_mode(hdev, true);
+		if (ret)
+			return ret;
+	}
+
 	dev_info(&hdev->pdev->dev, "Reset done\n");
 
 	return 0;
@@ -2377,6 +2668,17 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 	if (ret)
 		goto err_config;
 
+	/* vf is not allowed to enable unicast/multicast promisc mode.
+	 * For revision 0x20, default to disable broadcast promisc mode,
+	 * firmware makes sure broadcast packets can be accepted.
+	 * For revision 0x21, default to enable broadcast promisc mode.
+	 */
+	if (pdev->revision >= 0x21) {
+		ret = hclgevf_set_promisc_mode(hdev, true);
+		if (ret)
+			goto err_config;
+	}
+
 	/* Initialize RSS for this VF */
 	ret = hclgevf_rss_init_hw(hdev);
 	if (ret) {
@@ -2461,7 +2763,8 @@ static u32 hclgevf_get_max_channels(struct hclgevf_dev *hdev)
 	struct hnae3_handle *nic = &hdev->nic;
 	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
 
-	return min_t(u32, hdev->rss_size_max * kinfo->num_tc, hdev->num_tqps);
+	return min_t(u32, hdev->rss_size_max,
+		     hdev->num_tqps / kinfo->num_tc);
 }
 
 /**
@@ -2482,7 +2785,7 @@ static void hclgevf_get_channels(struct hnae3_handle *handle,
 	ch->max_combined = hclgevf_get_max_channels(hdev);
 	ch->other_count = 0;
 	ch->max_other = 0;
-	ch->combined_count = hdev->num_tqps;
+	ch->combined_count = handle->kinfo.rss_size;
 }
 
 static void hclgevf_get_tqps_and_rss_info(struct hnae3_handle *handle,
@@ -2522,19 +2825,23 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed,
 	hdev->hw.mac.duplex = duplex;
 }
 
-static int hclgevf_gro_en(struct hnae3_handle *handle, int enable)
+static int hclgevf_gro_en(struct hnae3_handle *handle, bool enable)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 
 	return hclgevf_config_gro(hdev, enable);
 }
 
-static void hclgevf_get_media_type(struct hnae3_handle *handle,
-				  u8 *media_type)
+static void hclgevf_get_media_type(struct hnae3_handle *handle, u8 *media_type,
+				   u8 *module_type)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
 	if (media_type)
 		*media_type = hdev->hw.mac.media_type;
+
+	if (module_type)
+		*module_type = hdev->hw.mac.module_type;
 }
 
 static bool hclgevf_get_hw_reset_stat(struct hnae3_handle *handle)
@@ -2555,7 +2862,17 @@ static unsigned long hclgevf_ae_dev_reset_cnt(struct hnae3_handle *handle)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 
-	return hdev->reset_count;
+	return hdev->rst_stats.hw_rst_done_cnt;
+}
+
+static void hclgevf_get_link_mode(struct hnae3_handle *handle,
+				  unsigned long *supported,
+				  unsigned long *advertising)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	*supported = hdev->hw.mac.supported;
+	*advertising = hdev->hw.mac.advertising;
 }
 
 #define MAX_SEPARATE_NUM	4
@@ -2624,6 +2941,31 @@ static void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
 	}
 }
 
+void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state,
+					u8 *port_base_vlan_info, u8 data_size)
+{
+	struct hnae3_handle *nic = &hdev->nic;
+
+	rtnl_lock();
+	hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	rtnl_unlock();
+
+	/* send msg to PF and wait update port based vlan info */
+	hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN,
+			     HCLGE_MBX_PORT_BASE_VLAN_CFG,
+			     port_base_vlan_info, data_size,
+			     false, NULL, 0);
+
+	if (state == HNAE3_PORT_BASE_VLAN_DISABLE)
+		nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE;
+	else
+		nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE;
+
+	rtnl_lock();
+	hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
+	rtnl_unlock();
+}
+
 static const struct hnae3_ae_ops hclgevf_ops = {
 	.init_ae_dev = hclgevf_init_ae_dev,
 	.uninit_ae_dev = hclgevf_uninit_ae_dev,
@@ -2640,7 +2982,6 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.get_vector = hclgevf_get_vector,
 	.put_vector = hclgevf_put_vector,
 	.reset_queue = hclgevf_reset_tqp,
-	.set_promisc_mode = hclgevf_set_promisc_mode,
 	.get_mac_addr = hclgevf_get_mac_addr,
 	.set_mac_addr = hclgevf_set_mac_addr,
 	.add_uc_addr = hclgevf_add_uc_addr,
@@ -2677,6 +3018,7 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.set_mtu = hclgevf_set_mtu,
 	.get_global_queue_id = hclgevf_get_qid_global,
 	.set_timer_task = hclgevf_set_timer_task,
+	.get_link_mode = hclgevf_get_link_mode,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 787bc06944e5..5a9e30998a8f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -4,6 +4,7 @@
 #ifndef __HCLGEVF_MAIN_H
 #define __HCLGEVF_MAIN_H
 #include <linux/fs.h>
+#include <linux/if_vlan.h>
 #include <linux/types.h>
 #include "hclge_mbx.h"
 #include "hclgevf_cmd.h"
@@ -12,9 +13,12 @@
 #define HCLGEVF_MOD_VERSION "1.0"
 #define HCLGEVF_DRIVER_NAME "hclgevf"
 
+#define HCLGEVF_MAX_VLAN_ID	4095
 #define HCLGEVF_MISC_VECTOR_NUM		0
 
 #define HCLGEVF_INVALID_VPORT		0xffff
+#define HCLGEVF_GENERAL_TASK_INTERVAL	  5
+#define HCLGEVF_KEEP_ALIVE_TASK_INTERVAL  2
 
 /* This number in actual depends upon the total number of VFs
  * created by physical function. But the maximum number of
@@ -116,6 +120,8 @@
 #define HCLGEVF_S_IP_BIT		BIT(3)
 #define HCLGEVF_V_TAG_BIT		BIT(4)
 
+#define HCLGEVF_STATS_TIMER_INTERVAL	(36)
+
 enum hclgevf_evt_cause {
 	HCLGEVF_VECTOR0_EVENT_RST,
 	HCLGEVF_VECTOR0_EVENT_MBX,
@@ -128,6 +134,8 @@ enum hclgevf_states {
 	HCLGEVF_STATE_DOWN,
 	HCLGEVF_STATE_DISABLED,
 	HCLGEVF_STATE_IRQ_INITED,
+	HCLGEVF_STATE_REMOVING,
+	HCLGEVF_STATE_NIC_REGISTERED,
 	/* task states */
 	HCLGEVF_STATE_SERVICE_SCHED,
 	HCLGEVF_STATE_RST_SERVICE_SCHED,
@@ -141,10 +149,13 @@ enum hclgevf_states {
 
 struct hclgevf_mac {
 	u8 media_type;
+	u8 module_type;
 	u8 mac_addr[ETH_ALEN];
 	int link;
 	u8 duplex;
 	u32 speed;
+	u64 supported;
+	u64 advertising;
 };
 
 struct hclgevf_hw {
@@ -208,6 +219,16 @@ struct hclgevf_misc_vector {
 	int vector_irq;
 };
 
+struct hclgevf_rst_stats {
+	u32 rst_cnt;			/* the number of reset */
+	u32 vf_func_rst_cnt;		/* the number of VF function reset */
+	u32 flr_rst_cnt;		/* the number of FLR */
+	u32 vf_rst_cnt;			/* the number of VF reset */
+	u32 rst_done_cnt;		/* the number of reset completed */
+	u32 hw_rst_done_cnt;		/* the number of HW reset completed */
+	u32 rst_fail_cnt;		/* the number of VF reset fail */
+};
+
 struct hclgevf_dev {
 	struct pci_dev *pdev;
 	struct hnae3_ae_dev *ae_dev;
@@ -225,7 +246,7 @@ struct hclgevf_dev {
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
 	unsigned long reset_state;	/* requested, pending */
-	unsigned long reset_count;	/* the number of reset has been done */
+	struct hclgevf_rst_stats rst_stats;
 	u32 reset_attempts;
 
 	u32 fw_version;
@@ -237,7 +258,8 @@ struct hclgevf_dev {
 	u16 num_alloc_vport;	/* num vports this driver supports */
 	u32 numa_node_mask;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;	/* desc num of per tx queue */
+	u16 num_rx_desc;	/* desc num of per rx queue */
 	u8 hw_tc_map;
 
 	u16 num_msi;
@@ -250,6 +272,8 @@ struct hclgevf_dev {
 	u16 *vector_status;
 	int *vector_irq;
 
+	unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)];
+
 	bool mbx_event_pending;
 	struct hclgevf_mbx_resp_status mbx_resp; /* mailbox response */
 	struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */
@@ -269,6 +293,7 @@ struct hclgevf_dev {
 	struct hnae3_client *nic_client;
 	struct hnae3_client *roce_client;
 	u32 flag;
+	u32 stats_timer;
 };
 
 static inline bool hclgevf_is_reset_pending(struct hclgevf_dev *hdev)
@@ -287,4 +312,6 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed,
 				 u8 duplex);
 void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev);
 void hclgevf_mbx_task_schedule(struct hclgevf_dev *hdev);
+void hclgevf_update_port_base_vlan_info(struct hclgevf_dev *hdev, u16 state,
+					u8 *port_base_vlan_info, u8 data_size);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index 84653f58b2d1..f60b80bd605e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -49,8 +49,8 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 
 	if (i >= HCLGEVF_MAX_TRY_TIMES) {
 		dev_err(&hdev->pdev->dev,
-			"VF could not get mbx resp(=%d) from PF in %d tries\n",
-			hdev->mbx_resp.received_resp, i);
+			"VF could not get mbx(%d,%d) resp(=%d) from PF in %d tries\n",
+			code0, code1, hdev->mbx_resp.received_resp, i);
 		return -EIO;
 	}
 
@@ -68,8 +68,11 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 
 	if (!(r_code0 == code0 && r_code1 == code1 && !mbx_resp->resp_status)) {
 		dev_err(&hdev->pdev->dev,
-			"VF could not match resp code(code0=%d,code1=%d), %d",
+			"VF could not match resp code(code0=%d,code1=%d), %d\n",
 			code0, code1, mbx_resp->resp_status);
+		dev_err(&hdev->pdev->dev,
+			"VF could not match resp r_code(r_code0=%d,r_code1=%d)\n",
+			r_code0, r_code1);
 		return -EIO;
 	}
 
@@ -95,9 +98,12 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, u16 code, u16 subcode,
 	}
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_VF_TO_PF, false);
+	req->mbx_need_resp |= need_resp ? HCLGE_MBX_NEED_RESP_BIT :
+					  ~HCLGE_MBX_NEED_RESP_BIT;
 	req->msg[0] = code;
 	req->msg[1] = subcode;
-	memcpy(&req->msg[2], msg_data, msg_len);
+	if (msg_data)
+		memcpy(&req->msg[2], msg_data, msg_len);
 
 	/* synchronous send */
 	if (need_resp) {
@@ -197,6 +203,8 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 			break;
 		case HCLGE_MBX_LINK_STAT_CHANGE:
 		case HCLGE_MBX_ASSERTING_RESET:
+		case HCLGE_MBX_LINK_STAT_MODE:
+		case HLCGE_MBX_PUSH_VLAN_INFO:
 			/* set this mbx event as pending. This is required as we
 			 * might loose interrupt event when mbx task is busy
 			 * handling. This shall be cleared when mbx task just
@@ -207,7 +215,8 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 			/* we will drop the async msg if we find ARQ as full
 			 * and continue with next message
 			 */
-			if (hdev->arq.count >= HCLGE_MBX_MAX_ARQ_MSG_NUM) {
+			if (atomic_read(&hdev->arq.count) >=
+			    HCLGE_MBX_MAX_ARQ_MSG_NUM) {
 				dev_warn(&hdev->pdev->dev,
 					 "Async Q full, dropping msg(%d)\n",
 					 req->msg[1]);
@@ -219,7 +228,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 			memcpy(&msg_q[0], req->msg,
 			       HCLGE_MBX_MAX_ARQ_MSG_SIZE * sizeof(u16));
 			hclge_mbx_tail_ptr_move_arq(hdev->arq);
-			hdev->arq.count++;
+			atomic_inc(&hdev->arq.count);
 
 			hclgevf_mbx_task_schedule(hdev);
 
@@ -242,11 +251,12 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 {
 	enum hnae3_reset_type reset_type;
-	u16 link_status;
-	u16 *msg_q;
+	u16 link_status, state;
+	u16 *msg_q, *vlan_info;
 	u8 duplex;
 	u32 speed;
 	u32 tail;
+	u8 idx;
 
 	/* we can safely clear it now as we are at start of the async message
 	 * processing
@@ -276,6 +286,15 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 			hclgevf_update_speed_duplex(hdev, speed, duplex);
 
 			break;
+		case HCLGE_MBX_LINK_STAT_MODE:
+			idx = (u8)le16_to_cpu(msg_q[1]);
+			if (idx)
+				memcpy(&hdev->hw.mac.supported, &msg_q[2],
+				       sizeof(unsigned long));
+			else
+				memcpy(&hdev->hw.mac.advertising, &msg_q[2],
+				       sizeof(unsigned long));
+			break;
 		case HCLGE_MBX_ASSERTING_RESET:
 			/* PF has asserted reset hence VF should go in pending
 			 * state and poll for the hardware reset status till it
@@ -288,6 +307,12 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 			hclgevf_reset_task_schedule(hdev);
 
 			break;
+		case HLCGE_MBX_PUSH_VLAN_INFO:
+			state = le16_to_cpu(msg_q[1]);
+			vlan_info = &msg_q[1];
+			hclgevf_update_port_base_vlan_info(hdev, state,
+							   (u8 *)vlan_info, 8);
+			break;
 		default:
 			dev_err(&hdev->pdev->dev,
 				"fetched unsupported(%d) message from arq\n",
@@ -296,7 +321,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 		}
 
 		hclge_mbx_head_ptr_move_arq(hdev->arq);
-		hdev->arq.count--;
+		atomic_dec(&hdev->arq.count);
 		msg_q = hdev->arq.msg_q[hdev->arq.head];
 	}
 }
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index baf5cc251f32..3e863a71c513 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -1,10 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (c) 2014-2015 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/acpi.h>
@@ -39,7 +35,7 @@ struct hns_mdio_sc_reg {
 };
 
 struct hns_mdio_device {
-	void *vbase;		/* mdio reg base address */
+	u8 __iomem *vbase;		/* mdio reg base address */
 	struct regmap *subctrl_vbase;
 	struct hns_mdio_sc_reg sc_reg;
 };
@@ -96,21 +92,17 @@ enum mdio_c45_op_seq {
 #define MDIO_SC_CLK_ST		0x531C
 #define MDIO_SC_RESET_ST	0x5A1C
 
-static void mdio_write_reg(void *base, u32 reg, u32 value)
+static void mdio_write_reg(u8 __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = (u8 __iomem *)base;
-
-	writel_relaxed(value, reg_addr + reg);
+	writel_relaxed(value, base + reg);
 }
 
 #define MDIO_WRITE_REG(a, reg, value) \
 	mdio_write_reg((a)->vbase, (reg), (value))
 
-static u32 mdio_read_reg(void *base, u32 reg)
+static u32 mdio_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = (u8 __iomem *)base;
-
-	return readl_relaxed(reg_addr + reg);
+	return readl_relaxed(base + reg);
 }
 
 #define mdio_set_field(origin, mask, shift, val) \
@@ -121,7 +113,7 @@ static u32 mdio_read_reg(void *base, u32 reg)
 
 #define mdio_get_field(origin, mask, shift) (((origin) >> (shift)) & (mask))
 
-static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift,
+static void mdio_set_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift,
 			       u32 val)
 {
 	u32 origin = mdio_read_reg(base, reg);
@@ -133,7 +125,7 @@ static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift,
 #define MDIO_SET_REG_FIELD(dev, reg, mask, shift, val) \
 	mdio_set_reg_field((dev)->vbase, (reg), (mask), (shift), (val))
 
-static u32 mdio_get_reg_field(void *base, u32 reg, u32 mask, u32 shift)
+static u32 mdio_get_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift)
 {
 	u32 origin;
 
@@ -425,7 +417,6 @@ static int hns_mdio_probe(struct platform_device *pdev)
 {
 	struct hns_mdio_device *mdio_dev;
 	struct mii_bus *new_bus;
-	struct resource *res;
 	int ret = -ENODEV;
 
 	if (!pdev) {
@@ -450,8 +441,7 @@ static int hns_mdio_probe(struct platform_device *pdev)
 	new_bus->priv = mdio_dev;
 	new_bus->parent = &pdev->dev;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mdio_dev->vbase = devm_ioremap_resource(&pdev->dev, res);
+	mdio_dev->vbase = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(mdio_dev->vbase)) {
 		ret = PTR_ERR(mdio_dev->vbase);
 		return ret;
diff --git a/drivers/net/ethernet/hp/Kconfig b/drivers/net/ethernet/hp/Kconfig
index d4df78c2abce..fb395cfe6b92 100644
--- a/drivers/net/ethernet/hp/Kconfig
+++ b/drivers/net/ethernet/hp/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # HP network device configuration
 #
diff --git a/drivers/net/ethernet/hp/Makefile b/drivers/net/ethernet/hp/Makefile
index 20b6918b52bd..5ed723bb11e2 100644
--- a/drivers/net/ethernet/hp/Makefile
+++ b/drivers/net/ethernet/hp/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the HP network device drivers.
 #
diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c
index 9b5a68b65432..6ec78f5c602f 100644
--- a/drivers/net/ethernet/hp/hp100.c
+++ b/drivers/net/ethernet/hp/hp100.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
 ** hp100.c
 ** HP CASCADE Architecture Driver for 100VG-AnyLan Network Adapters
@@ -31,19 +32,6 @@
 **       -  some updates for EISA version of card
 **
 **
-**   This code is free software; you can redistribute it and/or modify
-**   it under the terms of the GNU General Public License as published by
-**   the Free Software Foundation; either version 2 of the License, or
-**   (at your option) any later version.
-**
-**   This code is distributed in the hope that it will be useful,
-**   but WITHOUT ANY WARRANTY; without even the implied warranty of
-**   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-**   GNU General Public License for more details.
-**
-**   You should have received a copy of the GNU General Public License
-**   along with this program; if not, write to the Free Software
-**   Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 **
 ** 1.57c -> 1.58
 **   - used indent to change coding-style
diff --git a/drivers/net/ethernet/hp/hp100.h b/drivers/net/ethernet/hp/hp100.h
index b60e96fe38b4..7239b94c9de5 100644
--- a/drivers/net/ethernet/hp/hp100.h
+++ b/drivers/net/ethernet/hp/hp100.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * hp100.h: Hewlett Packard HP10/100VG ANY LAN ethernet driver for Linux.
  *
@@ -7,11 +8,6 @@
  *           Siegfried Loeffler <floeff@tunix.mathematik.uni-stuttgart.de>
  *
  * This driver is based on the 'hpfepkt' crynwr packet driver.
- *
- * This source/code is public free; you can distribute it and/or modify
- * it under terms of the GNU General Public License (published by the
- * Free Software Foundation) either version two of this License, or any
- * later version.
  */
 
 /****************************************************************************
diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig
index c1a95ae4058b..bdcbface62d7 100644
--- a/drivers/net/ethernet/huawei/Kconfig
+++ b/drivers/net/ethernet/huawei/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Huawei driver configuration
 #
diff --git a/drivers/net/ethernet/huawei/Makefile b/drivers/net/ethernet/huawei/Makefile
index 5c37cc8fc1bc..2549ad5afe6d 100644
--- a/drivers/net/ethernet/huawei/Makefile
+++ b/drivers/net/ethernet/huawei/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Huawei device drivers.
 #
diff --git a/drivers/net/ethernet/huawei/hinic/Kconfig b/drivers/net/ethernet/huawei/hinic/Kconfig
index e4e8b24c1a5d..cabc2f72d9d7 100644
--- a/drivers/net/ethernet/huawei/hinic/Kconfig
+++ b/drivers/net/ethernet/huawei/hinic/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Huawei driver configuration
 #
diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile
index 289ce88bb2d0..fe88ab88cacc 100644
--- a/drivers/net/ethernet/huawei/hinic/Makefile
+++ b/drivers/net/ethernet/huawei/hinic/Makefile
@@ -1,6 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_HINIC) += hinic.o
 
 hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \
 	   hinic_hw_io.o hinic_hw_qp.o hinic_hw_cmdq.o hinic_hw_wq.o \
 	   hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o \
-	   hinic_common.o
+	   hinic_common.o hinic_ethtool.o
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_common.c b/drivers/net/ethernet/huawei/hinic/hinic_common.c
index 02c74fd8380e..8e9b4a6c88c2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_common.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_common.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_common.h b/drivers/net/ethernet/huawei/hinic/hinic_common.h
index 2c06b76e94a1..a0de9d9644c6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_common.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_common.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_COMMON_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
index 5186cc9023aa..a209b14160cc 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_DEV_H
@@ -31,6 +22,7 @@
 enum hinic_flags {
 	HINIC_LINK_UP = BIT(0),
 	HINIC_INTF_UP = BIT(1),
+	HINIC_RSS_ENABLE = BIT(2),
 };
 
 struct hinic_rx_mode_work {
@@ -38,6 +30,23 @@ struct hinic_rx_mode_work {
 	u32                     rx_mode;
 };
 
+struct hinic_rss_type {
+	u8 tcp_ipv6_ext;
+	u8 ipv6_ext;
+	u8 tcp_ipv6;
+	u8 ipv6;
+	u8 tcp_ipv4;
+	u8 ipv4;
+	u8 udp_ipv6;
+	u8 udp_ipv4;
+};
+
+enum hinic_rss_hash_type {
+	HINIC_RSS_HASH_ENGINE_TYPE_XOR,
+	HINIC_RSS_HASH_ENGINE_TYPE_TOEP,
+	HINIC_RSS_HASH_ENGINE_TYPE_MAX,
+};
+
 struct hinic_dev {
 	struct net_device               *netdev;
 	struct hinic_hwdev              *hwdev;
@@ -45,6 +54,8 @@ struct hinic_dev {
 	u32                             msg_enable;
 	unsigned int                    tx_weight;
 	unsigned int                    rx_weight;
+	u16				num_qps;
+	u16				max_qps;
 
 	unsigned int                    flags;
 
@@ -59,6 +70,14 @@ struct hinic_dev {
 
 	struct hinic_txq_stats          tx_stats;
 	struct hinic_rxq_stats          rx_stats;
+
+	u8				rss_tmpl_idx;
+	u8				rss_hash_engine;
+	u16				num_rss;
+	u16				rss_limit;
+	struct hinic_rss_type		rss_type;
+	u8				*rss_hkey_user;
+	s32				*rss_indir_user;
 };
 
 #endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
new file mode 100644
index 000000000000..60ec48fe4144
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -0,0 +1,762 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Huawei HiNIC PCI Express Linux driver
+ * Copyright(c) 2017 Huawei Technologies Co., Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/ethtool.h>
+#include <linux/vmalloc.h>
+
+#include "hinic_hw_qp.h"
+#include "hinic_hw_dev.h"
+#include "hinic_port.h"
+#include "hinic_tx.h"
+#include "hinic_rx.h"
+#include "hinic_dev.h"
+
+static void set_link_speed(struct ethtool_link_ksettings *link_ksettings,
+			   enum hinic_speed speed)
+{
+	switch (speed) {
+	case HINIC_SPEED_10MB_LINK:
+		link_ksettings->base.speed = SPEED_10;
+		break;
+
+	case HINIC_SPEED_100MB_LINK:
+		link_ksettings->base.speed = SPEED_100;
+		break;
+
+	case HINIC_SPEED_1000MB_LINK:
+		link_ksettings->base.speed = SPEED_1000;
+		break;
+
+	case HINIC_SPEED_10GB_LINK:
+		link_ksettings->base.speed = SPEED_10000;
+		break;
+
+	case HINIC_SPEED_25GB_LINK:
+		link_ksettings->base.speed = SPEED_25000;
+		break;
+
+	case HINIC_SPEED_40GB_LINK:
+		link_ksettings->base.speed = SPEED_40000;
+		break;
+
+	case HINIC_SPEED_100GB_LINK:
+		link_ksettings->base.speed = SPEED_100000;
+		break;
+
+	default:
+		link_ksettings->base.speed = SPEED_UNKNOWN;
+		break;
+	}
+}
+
+static int hinic_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings
+				    *link_ksettings)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	enum hinic_port_link_state link_state;
+	struct hinic_port_cap port_cap;
+	int err;
+
+	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
+	ethtool_link_ksettings_add_link_mode(link_ksettings, supported,
+					     Autoneg);
+
+	link_ksettings->base.speed = SPEED_UNKNOWN;
+	link_ksettings->base.autoneg = AUTONEG_DISABLE;
+	link_ksettings->base.duplex = DUPLEX_UNKNOWN;
+
+	err = hinic_port_get_cap(nic_dev, &port_cap);
+	if (err)
+		return err;
+
+	err = hinic_port_link_state(nic_dev, &link_state);
+	if (err)
+		return err;
+
+	if (link_state != HINIC_LINK_STATE_UP)
+		return err;
+
+	set_link_speed(link_ksettings, port_cap.speed);
+
+	if (!!(port_cap.autoneg_cap & HINIC_AUTONEG_SUPPORTED))
+		ethtool_link_ksettings_add_link_mode(link_ksettings,
+						     advertising, Autoneg);
+
+	if (port_cap.autoneg_state == HINIC_AUTONEG_ACTIVE)
+		link_ksettings->base.autoneg = AUTONEG_ENABLE;
+
+	link_ksettings->base.duplex = (port_cap.duplex == HINIC_DUPLEX_FULL) ?
+					   DUPLEX_FULL : DUPLEX_HALF;
+	return 0;
+}
+
+static void hinic_get_drvinfo(struct net_device *netdev,
+			      struct ethtool_drvinfo *info)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	u8 mgmt_ver[HINIC_MGMT_VERSION_MAX_LEN] = {0};
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	int err;
+
+	strlcpy(info->driver, HINIC_DRV_NAME, sizeof(info->driver));
+	strlcpy(info->bus_info, pci_name(hwif->pdev), sizeof(info->bus_info));
+
+	err = hinic_get_mgmt_version(nic_dev, mgmt_ver);
+	if (err)
+		return;
+
+	snprintf(info->fw_version, sizeof(info->fw_version), "%s", mgmt_ver);
+}
+
+static void hinic_get_ringparam(struct net_device *netdev,
+				struct ethtool_ringparam *ring)
+{
+	ring->rx_max_pending = HINIC_RQ_DEPTH;
+	ring->tx_max_pending = HINIC_SQ_DEPTH;
+	ring->rx_pending = HINIC_RQ_DEPTH;
+	ring->tx_pending = HINIC_SQ_DEPTH;
+}
+
+static void hinic_get_channels(struct net_device *netdev,
+			       struct ethtool_channels *channels)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+
+	channels->max_rx = hwdev->nic_cap.max_qps;
+	channels->max_tx = hwdev->nic_cap.max_qps;
+	channels->max_other = 0;
+	channels->max_combined = 0;
+	channels->rx_count = hinic_hwdev_num_qps(hwdev);
+	channels->tx_count = hinic_hwdev_num_qps(hwdev);
+	channels->other_count = 0;
+	channels->combined_count = 0;
+}
+
+static int hinic_get_rss_hash_opts(struct hinic_dev *nic_dev,
+				   struct ethtool_rxnfc *cmd)
+{
+	struct hinic_rss_type rss_type = { 0 };
+	int err;
+
+	cmd->data = 0;
+
+	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
+		return 0;
+
+	err = hinic_get_rss_type(nic_dev, nic_dev->rss_tmpl_idx,
+				 &rss_type);
+	if (err)
+		return err;
+
+	cmd->data = RXH_IP_SRC | RXH_IP_DST;
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+		if (rss_type.tcp_ipv4)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	case TCP_V6_FLOW:
+		if (rss_type.tcp_ipv6)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	case UDP_V4_FLOW:
+		if (rss_type.udp_ipv4)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	case UDP_V6_FLOW:
+		if (rss_type.udp_ipv6)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		break;
+	default:
+		cmd->data = 0;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int set_l4_rss_hash_ops(struct ethtool_rxnfc *cmd,
+			       struct hinic_rss_type *rss_type)
+{
+	u8 rss_l4_en = 0;
+
+	switch (cmd->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+	case 0:
+		rss_l4_en = 0;
+		break;
+	case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+		rss_l4_en = 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+		rss_type->tcp_ipv4 = rss_l4_en;
+		break;
+	case TCP_V6_FLOW:
+		rss_type->tcp_ipv6 = rss_l4_en;
+		break;
+	case UDP_V4_FLOW:
+		rss_type->udp_ipv4 = rss_l4_en;
+		break;
+	case UDP_V6_FLOW:
+		rss_type->udp_ipv6 = rss_l4_en;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hinic_set_rss_hash_opts(struct hinic_dev *nic_dev,
+				   struct ethtool_rxnfc *cmd)
+{
+	struct hinic_rss_type *rss_type = &nic_dev->rss_type;
+	int err;
+
+	if (!(nic_dev->flags & HINIC_RSS_ENABLE)) {
+		cmd->data = 0;
+		return -EOPNOTSUPP;
+	}
+
+	/* RSS does not support anything other than hashing
+	 * to queues on src and dst IPs and ports
+	 */
+	if (cmd->data & ~(RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 |
+		RXH_L4_B_2_3))
+		return -EINVAL;
+
+	/* We need at least the IP SRC and DEST fields for hashing */
+	if (!(cmd->data & RXH_IP_SRC) || !(cmd->data & RXH_IP_DST))
+		return -EINVAL;
+
+	err = hinic_get_rss_type(nic_dev,
+				 nic_dev->rss_tmpl_idx, rss_type);
+	if (err)
+		return -EFAULT;
+
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V4_FLOW:
+	case UDP_V6_FLOW:
+		err = set_l4_rss_hash_ops(cmd, rss_type);
+		if (err)
+			return err;
+		break;
+	case IPV4_FLOW:
+		rss_type->ipv4 = 1;
+		break;
+	case IPV6_FLOW:
+		rss_type->ipv6 = 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	err = hinic_set_rss_type(nic_dev, nic_dev->rss_tmpl_idx,
+				 *rss_type);
+	if (err)
+		return -EFAULT;
+
+	return 0;
+}
+
+static int __set_rss_rxfh(struct net_device *netdev,
+			  const u32 *indir, const u8 *key)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	int err;
+
+	if (indir) {
+		if (!nic_dev->rss_indir_user) {
+			nic_dev->rss_indir_user =
+				kzalloc(sizeof(u32) * HINIC_RSS_INDIR_SIZE,
+					GFP_KERNEL);
+			if (!nic_dev->rss_indir_user)
+				return -ENOMEM;
+		}
+
+		memcpy(nic_dev->rss_indir_user, indir,
+		       sizeof(u32) * HINIC_RSS_INDIR_SIZE);
+
+		err = hinic_rss_set_indir_tbl(nic_dev,
+					      nic_dev->rss_tmpl_idx, indir);
+		if (err)
+			return -EFAULT;
+	}
+
+	if (key) {
+		if (!nic_dev->rss_hkey_user) {
+			nic_dev->rss_hkey_user =
+				kzalloc(HINIC_RSS_KEY_SIZE * 2, GFP_KERNEL);
+
+			if (!nic_dev->rss_hkey_user)
+				return -ENOMEM;
+		}
+
+		memcpy(nic_dev->rss_hkey_user, key, HINIC_RSS_KEY_SIZE);
+
+		err = hinic_rss_set_template_tbl(nic_dev,
+						 nic_dev->rss_tmpl_idx, key);
+		if (err)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int hinic_get_rxnfc(struct net_device *netdev,
+			   struct ethtool_rxnfc *cmd, u32 *rule_locs)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	int err = 0;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = nic_dev->num_qps;
+		break;
+	case ETHTOOL_GRXFH:
+		err = hinic_get_rss_hash_opts(nic_dev, cmd);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int hinic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	int err = 0;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		err = hinic_set_rss_hash_opts(nic_dev, cmd);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int hinic_get_rxfh(struct net_device *netdev,
+			  u32 *indir, u8 *key, u8 *hfunc)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	u8 hash_engine_type = 0;
+	int err = 0;
+
+	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
+		return -EOPNOTSUPP;
+
+	if (hfunc) {
+		err = hinic_rss_get_hash_engine(nic_dev,
+						nic_dev->rss_tmpl_idx,
+						&hash_engine_type);
+		if (err)
+			return -EFAULT;
+
+		*hfunc = hash_engine_type ? ETH_RSS_HASH_TOP : ETH_RSS_HASH_XOR;
+	}
+
+	if (indir) {
+		err = hinic_rss_get_indir_tbl(nic_dev,
+					      nic_dev->rss_tmpl_idx, indir);
+		if (err)
+			return -EFAULT;
+	}
+
+	if (key)
+		err = hinic_rss_get_template_tbl(nic_dev,
+						 nic_dev->rss_tmpl_idx, key);
+
+	return err;
+}
+
+static int hinic_set_rxfh(struct net_device *netdev, const u32 *indir,
+			  const u8 *key, const u8 hfunc)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	int err = 0;
+
+	if (!(nic_dev->flags & HINIC_RSS_ENABLE))
+		return -EOPNOTSUPP;
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE) {
+		if (hfunc != ETH_RSS_HASH_TOP && hfunc != ETH_RSS_HASH_XOR)
+			return -EOPNOTSUPP;
+
+		nic_dev->rss_hash_engine = (hfunc == ETH_RSS_HASH_XOR) ?
+			HINIC_RSS_HASH_ENGINE_TYPE_XOR :
+			HINIC_RSS_HASH_ENGINE_TYPE_TOEP;
+		err = hinic_rss_set_hash_engine
+			(nic_dev, nic_dev->rss_tmpl_idx,
+			nic_dev->rss_hash_engine);
+		if (err)
+			return -EFAULT;
+	}
+
+	err = __set_rss_rxfh(netdev, indir, key);
+
+	return err;
+}
+
+static u32 hinic_get_rxfh_key_size(struct net_device *netdev)
+{
+	return HINIC_RSS_KEY_SIZE;
+}
+
+static u32 hinic_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return HINIC_RSS_INDIR_SIZE;
+}
+
+#define ARRAY_LEN(arr) ((int)((int)sizeof(arr) / (int)sizeof(arr[0])))
+
+#define HINIC_FUNC_STAT(_stat_item) {	\
+	.name = #_stat_item, \
+	.size = FIELD_SIZEOF(struct hinic_vport_stats, _stat_item), \
+	.offset = offsetof(struct hinic_vport_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_function_stats[] = {
+	HINIC_FUNC_STAT(tx_unicast_pkts_vport),
+	HINIC_FUNC_STAT(tx_unicast_bytes_vport),
+	HINIC_FUNC_STAT(tx_multicast_pkts_vport),
+	HINIC_FUNC_STAT(tx_multicast_bytes_vport),
+	HINIC_FUNC_STAT(tx_broadcast_pkts_vport),
+	HINIC_FUNC_STAT(tx_broadcast_bytes_vport),
+
+	HINIC_FUNC_STAT(rx_unicast_pkts_vport),
+	HINIC_FUNC_STAT(rx_unicast_bytes_vport),
+	HINIC_FUNC_STAT(rx_multicast_pkts_vport),
+	HINIC_FUNC_STAT(rx_multicast_bytes_vport),
+	HINIC_FUNC_STAT(rx_broadcast_pkts_vport),
+	HINIC_FUNC_STAT(rx_broadcast_bytes_vport),
+
+	HINIC_FUNC_STAT(tx_discard_vport),
+	HINIC_FUNC_STAT(rx_discard_vport),
+	HINIC_FUNC_STAT(tx_err_vport),
+	HINIC_FUNC_STAT(rx_err_vport),
+};
+
+#define HINIC_PORT_STAT(_stat_item) { \
+	.name = #_stat_item, \
+	.size = FIELD_SIZEOF(struct hinic_phy_port_stats, _stat_item), \
+	.offset = offsetof(struct hinic_phy_port_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_port_stats[] = {
+	HINIC_PORT_STAT(mac_rx_total_pkt_num),
+	HINIC_PORT_STAT(mac_rx_total_oct_num),
+	HINIC_PORT_STAT(mac_rx_bad_pkt_num),
+	HINIC_PORT_STAT(mac_rx_bad_oct_num),
+	HINIC_PORT_STAT(mac_rx_good_pkt_num),
+	HINIC_PORT_STAT(mac_rx_good_oct_num),
+	HINIC_PORT_STAT(mac_rx_uni_pkt_num),
+	HINIC_PORT_STAT(mac_rx_multi_pkt_num),
+	HINIC_PORT_STAT(mac_rx_broad_pkt_num),
+	HINIC_PORT_STAT(mac_tx_total_pkt_num),
+	HINIC_PORT_STAT(mac_tx_total_oct_num),
+	HINIC_PORT_STAT(mac_tx_bad_pkt_num),
+	HINIC_PORT_STAT(mac_tx_bad_oct_num),
+	HINIC_PORT_STAT(mac_tx_good_pkt_num),
+	HINIC_PORT_STAT(mac_tx_good_oct_num),
+	HINIC_PORT_STAT(mac_tx_uni_pkt_num),
+	HINIC_PORT_STAT(mac_tx_multi_pkt_num),
+	HINIC_PORT_STAT(mac_tx_broad_pkt_num),
+	HINIC_PORT_STAT(mac_rx_fragment_pkt_num),
+	HINIC_PORT_STAT(mac_rx_undersize_pkt_num),
+	HINIC_PORT_STAT(mac_rx_undermin_pkt_num),
+	HINIC_PORT_STAT(mac_rx_64_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_65_127_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_128_255_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_256_511_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_512_1023_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_1024_1518_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_1519_2047_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_2048_4095_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_4096_8191_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_8192_9216_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_9217_12287_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_12288_16383_oct_pkt_num),
+	HINIC_PORT_STAT(mac_rx_1519_max_good_pkt_num),
+	HINIC_PORT_STAT(mac_rx_1519_max_bad_pkt_num),
+	HINIC_PORT_STAT(mac_rx_oversize_pkt_num),
+	HINIC_PORT_STAT(mac_rx_jabber_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pause_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri0_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri1_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri2_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri3_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri4_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri5_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri6_pkt_num),
+	HINIC_PORT_STAT(mac_rx_pfc_pri7_pkt_num),
+	HINIC_PORT_STAT(mac_rx_control_pkt_num),
+	HINIC_PORT_STAT(mac_rx_sym_err_pkt_num),
+	HINIC_PORT_STAT(mac_rx_fcs_err_pkt_num),
+	HINIC_PORT_STAT(mac_rx_send_app_good_pkt_num),
+	HINIC_PORT_STAT(mac_rx_send_app_bad_pkt_num),
+	HINIC_PORT_STAT(mac_tx_fragment_pkt_num),
+	HINIC_PORT_STAT(mac_tx_undersize_pkt_num),
+	HINIC_PORT_STAT(mac_tx_undermin_pkt_num),
+	HINIC_PORT_STAT(mac_tx_64_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_65_127_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_128_255_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_256_511_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_512_1023_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_1024_1518_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_1519_2047_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_2048_4095_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_4096_8191_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_8192_9216_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_9217_12287_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_12288_16383_oct_pkt_num),
+	HINIC_PORT_STAT(mac_tx_1519_max_good_pkt_num),
+	HINIC_PORT_STAT(mac_tx_1519_max_bad_pkt_num),
+	HINIC_PORT_STAT(mac_tx_oversize_pkt_num),
+	HINIC_PORT_STAT(mac_tx_jabber_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pause_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri0_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri1_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri2_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri3_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri4_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri5_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri6_pkt_num),
+	HINIC_PORT_STAT(mac_tx_pfc_pri7_pkt_num),
+	HINIC_PORT_STAT(mac_tx_control_pkt_num),
+	HINIC_PORT_STAT(mac_tx_err_all_pkt_num),
+	HINIC_PORT_STAT(mac_tx_from_app_good_pkt_num),
+	HINIC_PORT_STAT(mac_tx_from_app_bad_pkt_num),
+};
+
+#define HINIC_TXQ_STAT(_stat_item) { \
+	.name = "txq%d_"#_stat_item, \
+	.size = FIELD_SIZEOF(struct hinic_txq_stats, _stat_item), \
+	.offset = offsetof(struct hinic_txq_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_tx_queue_stats[] = {
+	HINIC_TXQ_STAT(pkts),
+	HINIC_TXQ_STAT(bytes),
+	HINIC_TXQ_STAT(tx_busy),
+	HINIC_TXQ_STAT(tx_wake),
+	HINIC_TXQ_STAT(tx_dropped),
+	HINIC_TXQ_STAT(big_frags_pkts),
+};
+
+#define HINIC_RXQ_STAT(_stat_item) { \
+	.name = "rxq%d_"#_stat_item, \
+	.size = FIELD_SIZEOF(struct hinic_rxq_stats, _stat_item), \
+	.offset = offsetof(struct hinic_rxq_stats, _stat_item) \
+}
+
+static struct hinic_stats hinic_rx_queue_stats[] = {
+	HINIC_RXQ_STAT(pkts),
+	HINIC_RXQ_STAT(bytes),
+	HINIC_RXQ_STAT(errors),
+	HINIC_RXQ_STAT(csum_errors),
+	HINIC_RXQ_STAT(other_errors),
+};
+
+static void get_drv_queue_stats(struct hinic_dev *nic_dev, u64 *data)
+{
+	struct hinic_txq_stats txq_stats;
+	struct hinic_rxq_stats rxq_stats;
+	u16 i = 0, j = 0, qid = 0;
+	char *p;
+
+	for (qid = 0; qid < nic_dev->num_qps; qid++) {
+		if (!nic_dev->txqs)
+			break;
+
+		hinic_txq_get_stats(&nic_dev->txqs[qid], &txq_stats);
+		for (j = 0; j < ARRAY_LEN(hinic_tx_queue_stats); j++, i++) {
+			p = (char *)&txq_stats +
+				hinic_tx_queue_stats[j].offset;
+			data[i] = (hinic_tx_queue_stats[j].size ==
+					sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+		}
+	}
+
+	for (qid = 0; qid < nic_dev->num_qps; qid++) {
+		if (!nic_dev->rxqs)
+			break;
+
+		hinic_rxq_get_stats(&nic_dev->rxqs[qid], &rxq_stats);
+		for (j = 0; j < ARRAY_LEN(hinic_rx_queue_stats); j++, i++) {
+			p = (char *)&rxq_stats +
+				hinic_rx_queue_stats[j].offset;
+			data[i] = (hinic_rx_queue_stats[j].size ==
+					sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+		}
+	}
+}
+
+static void hinic_get_ethtool_stats(struct net_device *netdev,
+				    struct ethtool_stats *stats, u64 *data)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic_vport_stats vport_stats = {0};
+	struct hinic_phy_port_stats *port_stats;
+	u16 i = 0, j = 0;
+	char *p;
+	int err;
+
+	err = hinic_get_vport_stats(nic_dev, &vport_stats);
+	if (err)
+		netif_err(nic_dev, drv, netdev,
+			  "Failed to get vport stats from firmware\n");
+
+	for (j = 0; j < ARRAY_LEN(hinic_function_stats); j++, i++) {
+		p = (char *)&vport_stats + hinic_function_stats[j].offset;
+		data[i] = (hinic_function_stats[j].size ==
+				sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+	}
+
+	port_stats = kzalloc(sizeof(*port_stats), GFP_KERNEL);
+	if (!port_stats) {
+		memset(&data[i], 0,
+		       ARRAY_LEN(hinic_port_stats) * sizeof(*data));
+		i += ARRAY_LEN(hinic_port_stats);
+		goto get_drv_stats;
+	}
+
+	err = hinic_get_phy_port_stats(nic_dev, port_stats);
+	if (err)
+		netif_err(nic_dev, drv, netdev,
+			  "Failed to get port stats from firmware\n");
+
+	for (j = 0; j < ARRAY_LEN(hinic_port_stats); j++, i++) {
+		p = (char *)port_stats + hinic_port_stats[j].offset;
+		data[i] = (hinic_port_stats[j].size ==
+				sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+	}
+
+	kfree(port_stats);
+
+get_drv_stats:
+	get_drv_queue_stats(nic_dev, data + i);
+}
+
+static int hinic_get_sset_count(struct net_device *netdev, int sset)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	int count, q_num;
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		q_num = nic_dev->num_qps;
+		count = ARRAY_LEN(hinic_function_stats) +
+			(ARRAY_LEN(hinic_tx_queue_stats) +
+			ARRAY_LEN(hinic_rx_queue_stats)) * q_num;
+
+		count += ARRAY_LEN(hinic_port_stats);
+
+		return count;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void hinic_get_strings(struct net_device *netdev,
+			      u32 stringset, u8 *data)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+	char *p = (char *)data;
+	u16 i, j;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_LEN(hinic_function_stats); i++) {
+			memcpy(p, hinic_function_stats[i].name,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
+		for (i = 0; i < ARRAY_LEN(hinic_port_stats); i++) {
+			memcpy(p, hinic_port_stats[i].name,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
+		for (i = 0; i < nic_dev->num_qps; i++) {
+			for (j = 0; j < ARRAY_LEN(hinic_tx_queue_stats); j++) {
+				sprintf(p, hinic_tx_queue_stats[j].name, i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
+		for (i = 0; i < nic_dev->num_qps; i++) {
+			for (j = 0; j < ARRAY_LEN(hinic_rx_queue_stats); j++) {
+				sprintf(p, hinic_rx_queue_stats[j].name, i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
+		return;
+	default:
+		return;
+	}
+}
+
+static const struct ethtool_ops hinic_ethtool_ops = {
+	.get_link_ksettings = hinic_get_link_ksettings,
+	.get_drvinfo = hinic_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+	.get_ringparam = hinic_get_ringparam,
+	.get_channels = hinic_get_channels,
+	.get_rxnfc = hinic_get_rxnfc,
+	.set_rxnfc = hinic_set_rxnfc,
+	.get_rxfh_key_size = hinic_get_rxfh_key_size,
+	.get_rxfh_indir_size = hinic_get_rxfh_indir_size,
+	.get_rxfh = hinic_get_rxfh,
+	.set_rxfh = hinic_set_rxfh,
+	.get_sset_count = hinic_get_sset_count,
+	.get_ethtool_stats = hinic_get_ethtool_stats,
+	.get_strings = hinic_get_strings,
+};
+
+void hinic_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &hinic_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
index b4fefb4c3064..583fd24c29cf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
index 31b94d5d47f7..0ba00fd828df 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_API_CMD_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index 4d09ea786b35..eb53c15b13f3 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
index 23f8d39eab68..7a434b653faa 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_CMDQ_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
index f39b184f674d..cdec1d0a3962 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_CSR_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 6b19607a4caa..6f2cf569a283 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
@@ -98,9 +89,6 @@ static int get_capability(struct hinic_hwdev *hwdev,
 	if (nic_cap->num_qps > HINIC_Q_CTXT_MAX)
 		nic_cap->num_qps = HINIC_Q_CTXT_MAX;
 
-	/* num_qps must be power of 2 */
-	nic_cap->num_qps = BIT(fls(nic_cap->num_qps) - 1);
-
 	nic_cap->max_qps = dev_cap->max_sqs + 1;
 	if (nic_cap->max_qps != (dev_cap->max_rqs + 1))
 		return -EFAULT;
@@ -313,6 +301,8 @@ static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth,
 	hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT;
 	hw_ioctxt.cmdq_depth = 0;
 
+	hw_ioctxt.lro_en = 1;
+
 	hw_ioctxt.rq_depth  = ilog2(rq_depth);
 
 	hw_ioctxt.rx_buf_sz_idx = HINIC_RX_BUF_SZ_IDX;
@@ -881,6 +871,13 @@ void hinic_free_hwdev(struct hinic_hwdev *hwdev)
 	hinic_free_hwif(hwdev->hwif);
 }
 
+int hinic_hwdev_max_num_qps(struct hinic_hwdev *hwdev)
+{
+	struct hinic_cap *nic_cap = &hwdev->nic_cap;
+
+	return nic_cap->max_qps;
+}
+
 /**
  * hinic_hwdev_num_qps - return the number QPs available for use
  * @hwdev: the NIC HW device
@@ -1008,3 +1005,16 @@ int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq,
 				 &hw_ci, sizeof(hw_ci), NULL,
 				 NULL, HINIC_MGMT_MSG_SYNC);
 }
+
+/**
+ * hinic_hwdev_set_msix_state- set msix state
+ * @hwdev: the NIC HW device
+ * @msix_index: IRQ corresponding index number
+ * @flag: msix state
+ *
+ **/
+void hinic_hwdev_set_msix_state(struct hinic_hwdev *hwdev, u16 msix_index,
+				enum hinic_msix_state flag)
+{
+	hinic_set_msix_state(hwdev->hwif, msix_index, flag);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index d1a7d2522d82..b069045de416 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_DEV_H
@@ -50,21 +41,73 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_GET_LINK_STATE   = 24,
 
+	HINIC_PORT_CMD_SET_LRO		= 25,
+
 	HINIC_PORT_CMD_SET_RX_CSUM	= 26,
 
+	HINIC_PORT_CMD_SET_RX_VLAN_OFFLOAD = 27,
+
+	HINIC_PORT_CMD_GET_PORT_STATISTICS = 28,
+
+	HINIC_PORT_CMD_CLEAR_PORT_STATISTICS = 29,
+
+	HINIC_PORT_CMD_GET_VPORT_STAT	= 30,
+
+	HINIC_PORT_CMD_CLEAN_VPORT_STAT	= 31,
+
+	HINIC_PORT_CMD_GET_RSS_TEMPLATE_INDIR_TBL = 37,
+
 	HINIC_PORT_CMD_SET_PORT_STATE   = 41,
 
+	HINIC_PORT_CMD_SET_RSS_TEMPLATE_TBL = 43,
+
+	HINIC_PORT_CMD_GET_RSS_TEMPLATE_TBL = 44,
+
+	HINIC_PORT_CMD_SET_RSS_HASH_ENGINE = 45,
+
+	HINIC_PORT_CMD_GET_RSS_HASH_ENGINE = 46,
+
+	HINIC_PORT_CMD_GET_RSS_CTX_TBL  = 47,
+
+	HINIC_PORT_CMD_SET_RSS_CTX_TBL  = 48,
+
+	HINIC_PORT_CMD_RSS_TEMP_MGR	= 49,
+
+	HINIC_PORT_CMD_RSS_CFG		= 66,
+
 	HINIC_PORT_CMD_FWCTXT_INIT      = 69,
 
+	HINIC_PORT_CMD_GET_MGMT_VERSION = 88,
+
 	HINIC_PORT_CMD_SET_FUNC_STATE   = 93,
 
 	HINIC_PORT_CMD_GET_GLOBAL_QPN   = 102,
 
 	HINIC_PORT_CMD_SET_TSO          = 112,
 
+	HINIC_PORT_CMD_SET_RQ_IQ_MAP	= 115,
+
 	HINIC_PORT_CMD_GET_CAP          = 170,
+
+	HINIC_PORT_CMD_SET_LRO_TIMER	= 244,
 };
 
+enum hinic_ucode_cmd {
+	HINIC_UCODE_CMD_MODIFY_QUEUE_CONTEXT    = 0,
+	HINIC_UCODE_CMD_CLEAN_QUEUE_CONTEXT,
+	HINIC_UCODE_CMD_ARM_SQ,
+	HINIC_UCODE_CMD_ARM_RQ,
+	HINIC_UCODE_CMD_SET_RSS_INDIR_TABLE,
+	HINIC_UCODE_CMD_SET_RSS_CONTEXT_TABLE,
+	HINIC_UCODE_CMD_GET_RSS_INDIR_TABLE,
+	HINIC_UCODE_CMD_GET_RSS_CONTEXT_TABLE,
+	HINIC_UCODE_CMD_SET_IQ_ENABLE,
+	HINIC_UCODE_CMD_SET_RQ_FLUSH            = 10
+};
+
+#define NIC_RSS_CMD_TEMP_ALLOC  0x01
+#define NIC_RSS_CMD_TEMP_FREE   0x02
+
 enum hinic_mgmt_msg_cmd {
 	HINIC_MGMT_MSG_CMD_BASE         = 160,
 
@@ -106,7 +149,7 @@ struct hinic_cmd_hw_ioctxt {
 	u8      set_cmdq_depth;
 	u8      cmdq_depth;
 
-	u8      rsvd2;
+	u8      lro_en;
 	u8      rsvd3;
 	u8      rsvd4;
 	u8      rsvd5;
@@ -224,6 +267,8 @@ struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev);
 
 void hinic_free_hwdev(struct hinic_hwdev *hwdev);
 
+int hinic_hwdev_max_num_qps(struct hinic_hwdev *hwdev);
+
 int hinic_hwdev_num_qps(struct hinic_hwdev *hwdev);
 
 struct hinic_sq *hinic_hwdev_get_sq(struct hinic_hwdev *hwdev, int i);
@@ -240,4 +285,7 @@ int hinic_hwdev_msix_set(struct hinic_hwdev *hwdev, u16 msix_index,
 int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq,
 			       u8 pending_limit, u8 coalesc_timer);
 
+void hinic_hwdev_set_msix_state(struct hinic_hwdev *hwdev, u16 msix_index,
+				enum hinic_msix_state flag);
+
 #endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index 683e67515016..79243b626ddb 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
index ecb9c2bc6dc8..d35f2068ee0c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_EQS_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index 823a17061a97..07bbfbf68577 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/pci.h>
@@ -168,6 +159,22 @@ void hinic_db_state_set(struct hinic_hwif *hwif,
 	hinic_hwif_write_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR, attr4);
 }
 
+void hinic_set_msix_state(struct hinic_hwif *hwif, u16 msix_idx,
+			  enum hinic_msix_state flag)
+{
+	u32 offset = msix_idx * HINIC_PCI_MSIX_ENTRY_SIZE +
+			HINIC_PCI_MSIX_ENTRY_VECTOR_CTRL;
+	u32 mask_bits;
+
+	mask_bits = readl(hwif->intr_regs_base + offset);
+	mask_bits &= ~HINIC_PCI_MSIX_ENTRY_CTRL_MASKBIT;
+
+	if (flag)
+		mask_bits |= HINIC_PCI_MSIX_ENTRY_CTRL_MASKBIT;
+
+	writel(mask_bits, hwif->intr_regs_base + offset);
+}
+
 /**
  * hwif_ready - test if the HW is ready for use
  * @hwif: the HW interface of a pci function device
@@ -321,6 +328,13 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev)
 		return -ENOMEM;
 	}
 
+	hwif->intr_regs_base = pci_ioremap_bar(pdev, HINIC_PCI_INTR_REGS_BAR);
+	if (!hwif->intr_regs_base) {
+		dev_err(&pdev->dev, "Failed to map configuration regs\n");
+		err = -ENOMEM;
+		goto err_map_intr_bar;
+	}
+
 	err = hwif_ready(hwif);
 	if (err) {
 		dev_err(&pdev->dev, "HW interface is not ready\n");
@@ -337,7 +351,11 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev)
 	return 0;
 
 err_hwif_ready:
+	iounmap(hwif->intr_regs_base);
+
+err_map_intr_bar:
 	iounmap(hwif->cfg_regs_bar);
+
 	return err;
 }
 
@@ -347,5 +365,6 @@ err_hwif_ready:
  **/
 void hinic_free_hwif(struct hinic_hwif *hwif)
 {
+	iounmap(hwif->intr_regs_base);
 	iounmap(hwif->cfg_regs_bar);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 5b4760c0e9f5..517794509eb2 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_IF_H
@@ -152,6 +143,7 @@
 #define HINIC_IS_PPF(hwif)              (HINIC_FUNC_TYPE(hwif) == HINIC_PPF)
 
 #define HINIC_PCI_CFG_REGS_BAR          0
+#define HINIC_PCI_INTR_REGS_BAR         2
 #define HINIC_PCI_DB_BAR                4
 
 #define HINIC_PCIE_ST_DISABLE           0
@@ -164,6 +156,10 @@
 #define HINIC_EQ_MSIX_LLI_CREDIT_LIMIT_DEFAULT  0       /* Disabled */
 #define HINIC_EQ_MSIX_RESEND_TIMER_DEFAULT      7       /* max */
 
+#define HINIC_PCI_MSIX_ENTRY_SIZE               16
+#define HINIC_PCI_MSIX_ENTRY_VECTOR_CTRL        12
+#define HINIC_PCI_MSIX_ENTRY_CTRL_MASKBIT       1
+
 enum hinic_pcie_nosnoop {
 	HINIC_PCIE_SNOOP        = 0,
 	HINIC_PCIE_NO_SNOOP     = 1,
@@ -207,6 +203,11 @@ enum hinic_db_state {
 	HINIC_DB_DISABLE = 1,
 };
 
+enum hinic_msix_state {
+	HINIC_MSIX_ENABLE,
+	HINIC_MSIX_DISABLE,
+};
+
 struct hinic_func_attr {
 	u16                     func_idx;
 	u8                      pf_idx;
@@ -226,6 +227,7 @@ struct hinic_func_attr {
 struct hinic_hwif {
 	struct pci_dev          *pdev;
 	void __iomem            *cfg_regs_bar;
+	void __iomem		*intr_regs_base;
 
 	struct hinic_func_attr  attr;
 };
@@ -251,6 +253,9 @@ int hinic_msix_attr_get(struct hinic_hwif *hwif, u16 msix_index,
 			u8 *lli_timer, u8 *lli_credit_limit,
 			u8 *resend_timer);
 
+void hinic_set_msix_state(struct hinic_hwif *hwif, u16 msix_idx,
+			  enum hinic_msix_state flag);
+
 int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index);
 
 void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
index a322a22d9357..d66f86fa3f46 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
@@ -45,6 +36,7 @@
 
 enum io_cmd {
 	IO_CMD_MODIFY_QUEUE_CTXT = 0,
+	IO_CMD_CLEAN_QUEUE_CTXT,
 };
 
 static void init_db_area_idx(struct hinic_free_db_area *free_db_area)
@@ -210,6 +202,59 @@ static int write_qp_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn,
 		write_rq_ctxts(func_to_io, base_qpn, num_qps));
 }
 
+static int hinic_clean_queue_offload_ctxt(struct hinic_func_to_io *func_to_io,
+					  enum hinic_qp_ctxt_type ctxt_type)
+{
+	struct hinic_hwif *hwif = func_to_io->hwif;
+	struct hinic_clean_queue_ctxt *ctxt_block;
+	struct pci_dev *pdev = hwif->pdev;
+	struct hinic_cmdq_buf cmdq_buf;
+	u64 out_param = 0;
+	int err;
+
+	err = hinic_alloc_cmdq_buf(&func_to_io->cmdqs, &cmdq_buf);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to allocate cmdq buf\n");
+		return err;
+	}
+
+	ctxt_block = cmdq_buf.buf;
+	ctxt_block->cmdq_hdr.num_queues = func_to_io->max_qps;
+	ctxt_block->cmdq_hdr.queue_type = ctxt_type;
+	ctxt_block->cmdq_hdr.addr_offset = 0;
+
+	/* TSO/LRO ctxt size: 0x0:0B; 0x1:160B; 0x2:200B; 0x3:240B */
+	ctxt_block->ctxt_size = 0x3;
+
+	hinic_cpu_to_be32(ctxt_block, sizeof(*ctxt_block));
+
+	cmdq_buf.size = sizeof(*ctxt_block);
+
+	err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC,
+				     IO_CMD_CLEAN_QUEUE_CTXT,
+				     &cmdq_buf, &out_param);
+
+	if (err || out_param) {
+		dev_err(&pdev->dev, "Failed to clean offload ctxts, err: %d, out_param: 0x%llx\n",
+			err, out_param);
+
+		err = -EFAULT;
+	}
+
+	hinic_free_cmdq_buf(&func_to_io->cmdqs, &cmdq_buf);
+
+	return err;
+}
+
+static int hinic_clean_qp_offload_ctxt(struct hinic_func_to_io *func_to_io)
+{
+	/* clean LRO/TSO context space */
+	return (hinic_clean_queue_offload_ctxt(func_to_io,
+					       HINIC_QP_CTXT_TYPE_SQ) ||
+		hinic_clean_queue_offload_ctxt(func_to_io,
+					       HINIC_QP_CTXT_TYPE_RQ));
+}
+
 /**
  * init_qp - Initialize a Queue Pair
  * @func_to_io: func to io channel that holds the IO components
@@ -381,6 +426,12 @@ int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
 		goto err_write_qp_ctxts;
 	}
 
+	err = hinic_clean_qp_offload_ctxt(func_to_io);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to clean QP contexts space\n");
+		goto err_write_qp_ctxts;
+	}
+
 	return 0;
 
 err_write_qp_ctxts:
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
index adb64179d47d..cac2b722e7dc 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_IO_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
index 278dc13f3dae..c1a6be6bf6a8 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
index 320711e8dee6..182fba17b643 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_MGMT_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index d62cf509646a..be364b7a7019 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index 038522e202b6..f4a339b10b10 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_QP_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h
index 376abf00762b..00900a6640ad 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_QP_CTXT_H
@@ -201,6 +192,11 @@ struct hinic_rq_ctxt {
 	u32     wq_block_lo_pfn;
 };
 
+struct hinic_clean_queue_ctxt {
+	struct hinic_qp_ctxt_header	cmdq_hdr;
+	u32				ctxt_size;
+};
+
 struct hinic_sq_ctxt_block {
 	struct hinic_qp_ctxt_header hdr;
 	struct hinic_sq_ctxt sq_ctxt[HINIC_Q_CTXT_MAX];
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
index cb66e7024659..03363216ff59 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
index 0a936cd6709b..811eef744140 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_WQ_H
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
index 138941527872..f4b6d2c1061f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_HW_WQE_H
@@ -219,6 +210,57 @@
 #define HINIC_MSS_DEFAULT		        0x3E00
 #define HINIC_MSS_MIN		                0x50
 
+#define RQ_CQE_STATUS_NUM_LRO_SHIFT		16
+#define RQ_CQE_STATUS_NUM_LRO_MASK		0xFFU
+
+#define RQ_CQE_STATUS_GET(val, member)		(((val) >> \
+			RQ_CQE_STATUS_##member##_SHIFT) & \
+			RQ_CQE_STATUS_##member##_MASK)
+
+#define HINIC_GET_RX_NUM_LRO(status)	\
+		RQ_CQE_STATUS_GET(status, NUM_LRO)
+
+#define RQ_CQE_OFFOLAD_TYPE_PKT_TYPE_SHIFT		0
+#define RQ_CQE_OFFOLAD_TYPE_PKT_TYPE_MASK		0xFFFU
+#define RQ_CQE_OFFOLAD_TYPE_VLAN_EN_SHIFT		21
+#define RQ_CQE_OFFOLAD_TYPE_VLAN_EN_MASK		0x1U
+
+#define RQ_CQE_OFFOLAD_TYPE_GET(val, member)		(((val) >> \
+				RQ_CQE_OFFOLAD_TYPE_##member##_SHIFT) & \
+				RQ_CQE_OFFOLAD_TYPE_##member##_MASK)
+
+#define HINIC_GET_RX_PKT_TYPE(offload_type)	\
+			RQ_CQE_OFFOLAD_TYPE_GET(offload_type, PKT_TYPE)
+
+#define HINIC_GET_RX_VLAN_OFFLOAD_EN(offload_type)	\
+			RQ_CQE_OFFOLAD_TYPE_GET(offload_type, VLAN_EN)
+
+#define RQ_CQE_SGE_VLAN_MASK				0xFFFFU
+#define RQ_CQE_SGE_VLAN_SHIFT				0
+
+#define RQ_CQE_SGE_GET(val, member)			(((val) >> \
+					RQ_CQE_SGE_##member##_SHIFT) & \
+					RQ_CQE_SGE_##member##_MASK)
+
+#define HINIC_GET_RX_VLAN_TAG(vlan_len)	\
+		RQ_CQE_SGE_GET(vlan_len, VLAN)
+
+#define HINIC_RSS_TYPE_VALID_SHIFT			23
+#define HINIC_RSS_TYPE_TCP_IPV6_EXT_SHIFT		24
+#define HINIC_RSS_TYPE_IPV6_EXT_SHIFT			25
+#define HINIC_RSS_TYPE_TCP_IPV6_SHIFT			26
+#define HINIC_RSS_TYPE_IPV6_SHIFT			27
+#define HINIC_RSS_TYPE_TCP_IPV4_SHIFT			28
+#define HINIC_RSS_TYPE_IPV4_SHIFT			29
+#define HINIC_RSS_TYPE_UDP_IPV6_SHIFT			30
+#define HINIC_RSS_TYPE_UDP_IPV4_SHIFT			31
+
+#define HINIC_RSS_TYPE_SET(val, member)                        \
+		(((u32)(val) & 0x1) << HINIC_RSS_TYPE_##member##_SHIFT)
+
+#define HINIC_RSS_TYPE_GET(val, member)                        \
+		(((u32)(val) >> HINIC_RSS_TYPE_##member##_SHIFT) & 0x1)
+
 enum hinic_l4offload_type {
 	HINIC_L4_OFF_DISABLE            = 0,
 	HINIC_TCP_OFFLOAD_ENABLE        = 1,
@@ -372,7 +414,7 @@ struct hinic_rq_cqe {
 	u32     status;
 	u32     len;
 
-	u32     rsvd2;
+	u32     offload_type;
 	u32     rsvd3;
 	u32     rsvd4;
 	u32     rsvd5;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index da323b9e1f62..2411ad270c98 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
@@ -51,9 +42,10 @@ static unsigned int rx_weight = 64;
 module_param(rx_weight, uint, 0644);
 MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
 
-#define HINIC_DEV_ID_QUAD_PORT_25GE     0x1822
-#define HINIC_DEV_ID_DUAL_PORT_25GE     0x0200
-#define HINIC_DEV_ID_DUAL_PORT_100GE    0x0201
+#define HINIC_DEV_ID_QUAD_PORT_25GE         0x1822
+#define HINIC_DEV_ID_DUAL_PORT_100GE        0x0200
+#define HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ   0x0205
+#define HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ    0x0210
 
 #define HINIC_WQ_NAME                   "hinic_dev"
 
@@ -61,6 +53,10 @@ MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
 					 NETIF_MSG_IFUP |                  \
 					 NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR)
 
+#define HINIC_LRO_MAX_WQE_NUM_DEFAULT	8
+
+#define HINIC_LRO_RX_TIMER_DEFAULT	16
+
 #define VLAN_BITMAP_SIZE(nic_dev)       (ALIGN(VLAN_N_VID, 8) / 8)
 
 #define work_to_rx_mode_work(work)      \
@@ -71,137 +67,9 @@ MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
 
 static int change_mac_addr(struct net_device *netdev, const u8 *addr);
 
-static void set_link_speed(struct ethtool_link_ksettings *link_ksettings,
-			   enum hinic_speed speed)
-{
-	switch (speed) {
-	case HINIC_SPEED_10MB_LINK:
-		link_ksettings->base.speed = SPEED_10;
-		break;
-
-	case HINIC_SPEED_100MB_LINK:
-		link_ksettings->base.speed = SPEED_100;
-		break;
-
-	case HINIC_SPEED_1000MB_LINK:
-		link_ksettings->base.speed = SPEED_1000;
-		break;
-
-	case HINIC_SPEED_10GB_LINK:
-		link_ksettings->base.speed = SPEED_10000;
-		break;
-
-	case HINIC_SPEED_25GB_LINK:
-		link_ksettings->base.speed = SPEED_25000;
-		break;
-
-	case HINIC_SPEED_40GB_LINK:
-		link_ksettings->base.speed = SPEED_40000;
-		break;
-
-	case HINIC_SPEED_100GB_LINK:
-		link_ksettings->base.speed = SPEED_100000;
-		break;
-
-	default:
-		link_ksettings->base.speed = SPEED_UNKNOWN;
-		break;
-	}
-}
-
-static int hinic_get_link_ksettings(struct net_device *netdev,
-				    struct ethtool_link_ksettings
-				    *link_ksettings)
-{
-	struct hinic_dev *nic_dev = netdev_priv(netdev);
-	enum hinic_port_link_state link_state;
-	struct hinic_port_cap port_cap;
-	int err;
-
-	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
-	ethtool_link_ksettings_add_link_mode(link_ksettings, supported,
-					     Autoneg);
-
-	link_ksettings->base.speed   = SPEED_UNKNOWN;
-	link_ksettings->base.autoneg = AUTONEG_DISABLE;
-	link_ksettings->base.duplex  = DUPLEX_UNKNOWN;
-
-	err = hinic_port_get_cap(nic_dev, &port_cap);
-	if (err) {
-		netif_err(nic_dev, drv, netdev,
-			  "Failed to get port capabilities\n");
-		return err;
-	}
-
-	err = hinic_port_link_state(nic_dev, &link_state);
-	if (err) {
-		netif_err(nic_dev, drv, netdev,
-			  "Failed to get port link state\n");
-		return err;
-	}
-
-	if (link_state != HINIC_LINK_STATE_UP) {
-		netif_info(nic_dev, drv, netdev, "No link\n");
-		return err;
-	}
-
-	set_link_speed(link_ksettings, port_cap.speed);
-
-	if (!!(port_cap.autoneg_cap & HINIC_AUTONEG_SUPPORTED))
-		ethtool_link_ksettings_add_link_mode(link_ksettings,
-						     advertising, Autoneg);
-
-	if (port_cap.autoneg_state == HINIC_AUTONEG_ACTIVE)
-		link_ksettings->base.autoneg = AUTONEG_ENABLE;
-
-	link_ksettings->base.duplex = (port_cap.duplex == HINIC_DUPLEX_FULL) ?
-				       DUPLEX_FULL : DUPLEX_HALF;
-	return 0;
-}
-
-static void hinic_get_drvinfo(struct net_device *netdev,
-			      struct ethtool_drvinfo *info)
-{
-	struct hinic_dev *nic_dev = netdev_priv(netdev);
-	struct hinic_hwdev *hwdev = nic_dev->hwdev;
-	struct hinic_hwif *hwif = hwdev->hwif;
-
-	strlcpy(info->driver, HINIC_DRV_NAME, sizeof(info->driver));
-	strlcpy(info->bus_info, pci_name(hwif->pdev), sizeof(info->bus_info));
-}
-
-static void hinic_get_ringparam(struct net_device *netdev,
-				struct ethtool_ringparam *ring)
-{
-	ring->rx_max_pending = HINIC_RQ_DEPTH;
-	ring->tx_max_pending = HINIC_SQ_DEPTH;
-	ring->rx_pending = HINIC_RQ_DEPTH;
-	ring->tx_pending = HINIC_SQ_DEPTH;
-}
-
-static void hinic_get_channels(struct net_device *netdev,
-			       struct ethtool_channels *channels)
-{
-	struct hinic_dev *nic_dev = netdev_priv(netdev);
-	struct hinic_hwdev *hwdev = nic_dev->hwdev;
-
-	channels->max_rx = hwdev->nic_cap.max_qps;
-	channels->max_tx = hwdev->nic_cap.max_qps;
-	channels->max_other    = 0;
-	channels->max_combined = 0;
-	channels->rx_count = hinic_hwdev_num_qps(hwdev);
-	channels->tx_count = hinic_hwdev_num_qps(hwdev);
-	channels->other_count    = 0;
-	channels->combined_count = 0;
-}
-
-static const struct ethtool_ops hinic_ethtool_ops = {
-	.get_link_ksettings = hinic_get_link_ksettings,
-	.get_drvinfo = hinic_get_drvinfo,
-	.get_link = ethtool_op_get_link,
-	.get_ringparam = hinic_get_ringparam,
-	.get_channels = hinic_get_channels,
-};
+static int set_features(struct hinic_dev *nic_dev,
+			netdev_features_t pre_features,
+			netdev_features_t features, bool force_change);
 
 static void update_rx_stats(struct hinic_dev *nic_dev, struct hinic_rxq *rxq)
 {
@@ -215,6 +83,9 @@ static void update_rx_stats(struct hinic_dev *nic_dev, struct hinic_rxq *rxq)
 	u64_stats_update_begin(&nic_rx_stats->syncp);
 	nic_rx_stats->bytes += rx_stats.bytes;
 	nic_rx_stats->pkts  += rx_stats.pkts;
+	nic_rx_stats->errors += rx_stats.errors;
+	nic_rx_stats->csum_errors += rx_stats.csum_errors;
+	nic_rx_stats->other_errors += rx_stats.other_errors;
 	u64_stats_update_end(&nic_rx_stats->syncp);
 
 	hinic_rxq_clean_stats(rxq);
@@ -235,6 +106,7 @@ static void update_tx_stats(struct hinic_dev *nic_dev, struct hinic_txq *txq)
 	nic_tx_stats->tx_busy += tx_stats.tx_busy;
 	nic_tx_stats->tx_wake += tx_stats.tx_wake;
 	nic_tx_stats->tx_dropped += tx_stats.tx_dropped;
+	nic_tx_stats->big_frags_pkts += tx_stats.big_frags_pkts;
 	u64_stats_update_end(&nic_tx_stats->syncp);
 
 	hinic_txq_clean_stats(txq);
@@ -371,11 +243,135 @@ static void free_rxqs(struct hinic_dev *nic_dev)
 	nic_dev->rxqs = NULL;
 }
 
+static int hinic_configure_max_qnum(struct hinic_dev *nic_dev)
+{
+	int err;
+
+	err = hinic_set_max_qnum(nic_dev, nic_dev->hwdev->nic_cap.max_qps);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int hinic_rss_init(struct hinic_dev *nic_dev)
+{
+	u8 default_rss_key[HINIC_RSS_KEY_SIZE];
+	u8 tmpl_idx = nic_dev->rss_tmpl_idx;
+	u32 *indir_tbl;
+	int err, i;
+
+	indir_tbl = kcalloc(HINIC_RSS_INDIR_SIZE, sizeof(u32), GFP_KERNEL);
+	if (!indir_tbl)
+		return -ENOMEM;
+
+	netdev_rss_key_fill(default_rss_key, sizeof(default_rss_key));
+	for (i = 0; i < HINIC_RSS_INDIR_SIZE; i++)
+		indir_tbl[i] = ethtool_rxfh_indir_default(i, nic_dev->num_rss);
+
+	err = hinic_rss_set_template_tbl(nic_dev, tmpl_idx, default_rss_key);
+	if (err)
+		goto out;
+
+	err = hinic_rss_set_indir_tbl(nic_dev, tmpl_idx, indir_tbl);
+	if (err)
+		goto out;
+
+	err = hinic_set_rss_type(nic_dev, tmpl_idx, nic_dev->rss_type);
+	if (err)
+		goto out;
+
+	err = hinic_rss_set_hash_engine(nic_dev, tmpl_idx,
+					nic_dev->rss_hash_engine);
+	if (err)
+		goto out;
+
+	err = hinic_rss_cfg(nic_dev, 1, tmpl_idx);
+	if (err)
+		goto out;
+
+out:
+	kfree(indir_tbl);
+	return err;
+}
+
+static void hinic_rss_deinit(struct hinic_dev *nic_dev)
+{
+	hinic_rss_cfg(nic_dev, 0, nic_dev->rss_tmpl_idx);
+}
+
+static void hinic_init_rss_parameters(struct hinic_dev *nic_dev)
+{
+	nic_dev->rss_hash_engine = HINIC_RSS_HASH_ENGINE_TYPE_XOR;
+	nic_dev->rss_type.tcp_ipv6_ext = 1;
+	nic_dev->rss_type.ipv6_ext = 1;
+	nic_dev->rss_type.tcp_ipv6 = 1;
+	nic_dev->rss_type.ipv6 = 1;
+	nic_dev->rss_type.tcp_ipv4 = 1;
+	nic_dev->rss_type.ipv4 = 1;
+	nic_dev->rss_type.udp_ipv6 = 1;
+	nic_dev->rss_type.udp_ipv4 = 1;
+}
+
+static void hinic_enable_rss(struct hinic_dev *nic_dev)
+{
+	struct net_device *netdev = nic_dev->netdev;
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	int i, node, err = 0;
+	u16 num_cpus = 0;
+
+	nic_dev->max_qps = hinic_hwdev_max_num_qps(hwdev);
+	if (nic_dev->max_qps <= 1) {
+		nic_dev->flags &= ~HINIC_RSS_ENABLE;
+		nic_dev->rss_limit = nic_dev->max_qps;
+		nic_dev->num_qps = nic_dev->max_qps;
+		nic_dev->num_rss = nic_dev->max_qps;
+
+		return;
+	}
+
+	err = hinic_rss_template_alloc(nic_dev, &nic_dev->rss_tmpl_idx);
+	if (err) {
+		netif_err(nic_dev, drv, netdev,
+			  "Failed to alloc tmpl_idx for rss, can't enable rss for this function\n");
+		nic_dev->flags &= ~HINIC_RSS_ENABLE;
+		nic_dev->max_qps = 1;
+		nic_dev->rss_limit = nic_dev->max_qps;
+		nic_dev->num_qps = nic_dev->max_qps;
+		nic_dev->num_rss = nic_dev->max_qps;
+
+		return;
+	}
+
+	nic_dev->flags |= HINIC_RSS_ENABLE;
+
+	for (i = 0; i < num_online_cpus(); i++) {
+		node = cpu_to_node(i);
+		if (node == dev_to_node(&pdev->dev))
+			num_cpus++;
+	}
+
+	if (!num_cpus)
+		num_cpus = num_online_cpus();
+
+	nic_dev->num_qps = min_t(u16, nic_dev->max_qps, num_cpus);
+
+	nic_dev->rss_limit = nic_dev->num_qps;
+	nic_dev->num_rss = nic_dev->num_qps;
+
+	hinic_init_rss_parameters(nic_dev);
+	err = hinic_rss_init(nic_dev);
+	if (err)
+		netif_err(nic_dev, drv, netdev, "Failed to init rss\n");
+}
+
 static int hinic_open(struct net_device *netdev)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
 	enum hinic_port_link_state link_state;
-	int err, ret, num_qps;
+	int err, ret;
 
 	if (!(nic_dev->flags & HINIC_INTF_UP)) {
 		err = hinic_hwdev_ifup(nic_dev->hwdev);
@@ -400,9 +396,17 @@ static int hinic_open(struct net_device *netdev)
 		goto err_create_rxqs;
 	}
 
-	num_qps = hinic_hwdev_num_qps(nic_dev->hwdev);
-	netif_set_real_num_tx_queues(netdev, num_qps);
-	netif_set_real_num_rx_queues(netdev, num_qps);
+	hinic_enable_rss(nic_dev);
+
+	err = hinic_configure_max_qnum(nic_dev);
+	if (err) {
+		netif_err(nic_dev, drv, nic_dev->netdev,
+			  "Failed to configure the maximum number of queues\n");
+		goto err_port_state;
+	}
+
+	netif_set_real_num_tx_queues(netdev, nic_dev->num_qps);
+	netif_set_real_num_rx_queues(netdev, nic_dev->num_qps);
 
 	err = hinic_port_set_state(nic_dev, HINIC_PORT_ENABLE);
 	if (err) {
@@ -458,9 +462,12 @@ err_func_port_state:
 	if (ret)
 		netif_warn(nic_dev, drv, netdev,
 			   "Failed to revert port state\n");
-
 err_port_state:
 	free_rxqs(nic_dev);
+	if (nic_dev->flags & HINIC_RSS_ENABLE) {
+		hinic_rss_deinit(nic_dev);
+		hinic_rss_template_free(nic_dev, nic_dev->rss_tmpl_idx);
+	}
 
 err_create_rxqs:
 	free_txqs(nic_dev);
@@ -504,6 +511,11 @@ static int hinic_close(struct net_device *netdev)
 		return err;
 	}
 
+	if (nic_dev->flags & HINIC_RSS_ENABLE) {
+		hinic_rss_deinit(nic_dev);
+		hinic_rss_template_free(nic_dev, nic_dev->rss_tmpl_idx);
+	}
+
 	free_rxqs(nic_dev);
 	free_txqs(nic_dev);
 
@@ -723,7 +735,6 @@ static void set_rx_mode(struct work_struct *work)
 {
 	struct hinic_rx_mode_work *rx_mode_work = work_to_rx_mode_work(work);
 	struct hinic_dev *nic_dev = rx_mode_work_to_nic_dev(rx_mode_work);
-	struct netdev_hw_addr *ha;
 
 	netif_info(nic_dev, drv, nic_dev->netdev, "set rx mode work\n");
 
@@ -731,9 +742,6 @@ static void set_rx_mode(struct work_struct *work)
 
 	__dev_uc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
 	__dev_mc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
-
-	netdev_for_each_mc_addr(ha, nic_dev->netdev)
-		add_mac_addr(nic_dev->netdev, ha->addr);
 }
 
 static void hinic_set_rx_mode(struct net_device *netdev)
@@ -784,12 +792,36 @@ static void hinic_get_stats64(struct net_device *netdev,
 
 	stats->rx_bytes   = nic_rx_stats->bytes;
 	stats->rx_packets = nic_rx_stats->pkts;
+	stats->rx_errors  = nic_rx_stats->errors;
 
 	stats->tx_bytes   = nic_tx_stats->bytes;
 	stats->tx_packets = nic_tx_stats->pkts;
 	stats->tx_errors  = nic_tx_stats->tx_dropped;
 }
 
+static int hinic_set_features(struct net_device *netdev,
+			      netdev_features_t features)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+
+	return set_features(nic_dev, nic_dev->netdev->features,
+			    features, false);
+}
+
+static netdev_features_t hinic_fix_features(struct net_device *netdev,
+					    netdev_features_t features)
+{
+	struct hinic_dev *nic_dev = netdev_priv(netdev);
+
+	/* If Rx checksum is disabled, then LRO should also be disabled */
+	if (!(features & NETIF_F_RXCSUM)) {
+		netif_info(nic_dev, drv, netdev, "disabling LRO as RXCSUM is off\n");
+		features &= ~NETIF_F_LRO;
+	}
+
+	return features;
+}
+
 static const struct net_device_ops hinic_netdev_ops = {
 	.ndo_open = hinic_open,
 	.ndo_stop = hinic_close,
@@ -802,13 +834,16 @@ static const struct net_device_ops hinic_netdev_ops = {
 	.ndo_start_xmit = hinic_xmit_frame,
 	.ndo_tx_timeout = hinic_tx_timeout,
 	.ndo_get_stats64 = hinic_get_stats64,
+	.ndo_fix_features = hinic_fix_features,
+	.ndo_set_features = hinic_set_features,
 };
 
 static void netdev_features_init(struct net_device *netdev)
 {
 	netdev->hw_features = NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_IP_CSUM |
 			      NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
-			      NETIF_F_RXCSUM;
+			      NETIF_F_RXCSUM | NETIF_F_LRO |
+			      NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 
 	netdev->vlan_features = netdev->hw_features;
 
@@ -881,6 +916,18 @@ static int set_features(struct hinic_dev *nic_dev,
 	if (changed & NETIF_F_RXCSUM)
 		err = hinic_set_rx_csum_offload(nic_dev, csum_en);
 
+	if (changed & NETIF_F_LRO) {
+		err = hinic_set_rx_lro_state(nic_dev,
+					     !!(features & NETIF_F_LRO),
+					     HINIC_LRO_RX_TIMER_DEFAULT,
+					     HINIC_LRO_MAX_WQE_NUM_DEFAULT);
+	}
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
+		err = hinic_set_rx_vlan_offload(nic_dev,
+						!!(features &
+						   NETIF_F_HW_VLAN_CTAG_RX));
+
 	return err;
 }
 
@@ -920,8 +967,8 @@ static int nic_dev_init(struct pci_dev *pdev)
 		goto err_alloc_etherdev;
 	}
 
+	hinic_set_ethtool_ops(netdev);
 	netdev->netdev_ops = &hinic_netdev_ops;
-	netdev->ethtool_ops = &hinic_ethtool_ops;
 	netdev->max_mtu = ETH_MAX_MTU;
 
 	nic_dev = netdev_priv(netdev);
@@ -1113,8 +1160,9 @@ static void hinic_shutdown(struct pci_dev *pdev)
 
 static const struct pci_device_id hinic_pci_table[] = {
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE), 0},
-	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_25GE), 0},
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE), 0},
+	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ), 0},
+	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ), 0},
 	{ 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, hinic_pci_table);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 122c93597268..1e389a004e50 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/types.h>
@@ -439,3 +430,641 @@ int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en)
 
 	return 0;
 }
+
+int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_vlan_cfg vlan_cfg;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u16 out_size;
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+	vlan_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	vlan_cfg.vlan_rx_offload = en;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RX_VLAN_OFFLOAD,
+				 &vlan_cfg, sizeof(vlan_cfg),
+				 &vlan_cfg, &out_size);
+	if (err || !out_size || vlan_cfg.status) {
+		dev_err(&pdev->dev,
+			"Failed to set rx vlan offload, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, vlan_cfg.status, out_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	struct hinic_rq_num rq_num = { 0 };
+	u16 out_size = sizeof(rq_num);
+	int err;
+
+	rq_num.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rq_num.num_rqs = num_rqs;
+	rq_num.rq_depth = ilog2(HINIC_SQ_DEPTH);
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RQ_IQ_MAP,
+				 &rq_num, sizeof(rq_num),
+				 &rq_num, &out_size);
+	if (err || !out_size || rq_num.status) {
+		dev_err(&pdev->dev,
+			"Failed to rxq number, ret = %d\n",
+			rq_num.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hinic_set_rx_lro(struct hinic_dev *nic_dev, u8 ipv4_en, u8 ipv6_en,
+			    u8 max_wqe_num)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct hinic_lro_config lro_cfg = { 0 };
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size = sizeof(lro_cfg);
+	int err;
+
+	lro_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	lro_cfg.lro_ipv4_en = ipv4_en;
+	lro_cfg.lro_ipv6_en = ipv6_en;
+	lro_cfg.lro_max_wqe_num = max_wqe_num;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_LRO,
+				 &lro_cfg, sizeof(lro_cfg),
+				 &lro_cfg, &out_size);
+	if (err || !out_size || lro_cfg.status) {
+		dev_err(&pdev->dev,
+			"Failed to set lro offload, ret = %d\n",
+			lro_cfg.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hinic_set_rx_lro_timer(struct hinic_dev *nic_dev, u32 timer_value)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_lro_timer lro_timer = { 0 };
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size = sizeof(lro_timer);
+	int err;
+
+	lro_timer.status = 0;
+	lro_timer.type = 0;
+	lro_timer.enable = 1;
+	lro_timer.timer = timer_value;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_LRO_TIMER,
+				 &lro_timer, sizeof(lro_timer),
+				 &lro_timer, &out_size);
+	if (lro_timer.status == 0xFF) {
+		/* For this case, we think status (0xFF) is OK */
+		lro_timer.status = 0;
+		dev_dbg(&pdev->dev,
+			"Set lro timer not supported by the current FW version, it will be 1ms default\n");
+	}
+
+	if (err || !out_size || lro_timer.status) {
+		dev_err(&pdev->dev,
+			"Failed to set lro timer, ret = %d\n",
+			lro_timer.status);
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic_set_rx_lro_state(struct hinic_dev *nic_dev, u8 lro_en,
+			   u32 lro_timer, u32 wqe_num)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	u8 ipv4_en;
+	u8 ipv6_en;
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	ipv4_en = lro_en ? 1 : 0;
+	ipv6_en = lro_en ? 1 : 0;
+
+	err = hinic_set_rx_lro(nic_dev, ipv4_en, ipv6_en, (u8)wqe_num);
+	if (err)
+		return err;
+
+	err = hinic_set_rx_lro_timer(nic_dev, lro_timer);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int hinic_rss_set_indir_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
+			    const u32 *indir_table)
+{
+	struct hinic_rss_indirect_tbl *indir_tbl;
+	struct hinic_func_to_io *func_to_io;
+	struct hinic_cmdq_buf cmd_buf;
+	struct hinic_hwdev *hwdev;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u32 indir_size;
+	u64 out_param;
+	int err, i;
+	u32 *temp;
+
+	hwdev = nic_dev->hwdev;
+	func_to_io = &hwdev->func_to_io;
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+
+	err = hinic_alloc_cmdq_buf(&func_to_io->cmdqs, &cmd_buf);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to allocate cmdq buf\n");
+		return err;
+	}
+
+	cmd_buf.size = sizeof(*indir_tbl);
+
+	indir_tbl = cmd_buf.buf;
+	indir_tbl->group_index = cpu_to_be32(tmpl_idx);
+
+	for (i = 0; i < HINIC_RSS_INDIR_SIZE; i++) {
+		indir_tbl->entry[i] = indir_table[i];
+
+		if (0x3 == (i & 0x3)) {
+			temp = (u32 *)&indir_tbl->entry[i - 3];
+			*temp = cpu_to_be32(*temp);
+		}
+	}
+
+	/* cfg the rss indirect table by command queue */
+	indir_size = HINIC_RSS_INDIR_SIZE / 2;
+	indir_tbl->offset = 0;
+	indir_tbl->size = cpu_to_be32(indir_size);
+
+	err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC,
+				     HINIC_UCODE_CMD_SET_RSS_INDIR_TABLE,
+				     &cmd_buf, &out_param);
+	if (err || out_param != 0) {
+		dev_err(&pdev->dev, "Failed to set rss indir table\n");
+		err = -EFAULT;
+		goto free_buf;
+	}
+
+	indir_tbl->offset = cpu_to_be32(indir_size);
+	indir_tbl->size = cpu_to_be32(indir_size);
+	memcpy(&indir_tbl->entry[0], &indir_tbl->entry[indir_size], indir_size);
+
+	err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC,
+				     HINIC_UCODE_CMD_SET_RSS_INDIR_TABLE,
+				     &cmd_buf, &out_param);
+	if (err || out_param != 0) {
+		dev_err(&pdev->dev, "Failed to set rss indir table\n");
+		err = -EFAULT;
+	}
+
+free_buf:
+	hinic_free_cmdq_buf(&func_to_io->cmdqs, &cmd_buf);
+
+	return err;
+}
+
+int hinic_rss_get_indir_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
+			    u32 *indir_table)
+{
+	struct hinic_rss_indir_table rss_cfg = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size = sizeof(rss_cfg);
+	int err = 0, i;
+
+	rss_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rss_cfg.template_id = tmpl_idx;
+
+	err = hinic_port_msg_cmd(hwdev,
+				 HINIC_PORT_CMD_GET_RSS_TEMPLATE_INDIR_TBL,
+				 &rss_cfg, sizeof(rss_cfg), &rss_cfg,
+				 &out_size);
+	if (err || !out_size || rss_cfg.status) {
+		dev_err(&pdev->dev, "Failed to get indir table, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, rss_cfg.status, out_size);
+		return -EINVAL;
+	}
+
+	hinic_be32_to_cpu(rss_cfg.indir, HINIC_RSS_INDIR_SIZE);
+	for (i = 0; i < HINIC_RSS_INDIR_SIZE; i++)
+		indir_table[i] = rss_cfg.indir[i];
+
+	return 0;
+}
+
+int hinic_set_rss_type(struct hinic_dev *nic_dev, u32 tmpl_idx,
+		       struct hinic_rss_type rss_type)
+{
+	struct hinic_rss_context_tbl *ctx_tbl;
+	struct hinic_func_to_io *func_to_io;
+	struct hinic_cmdq_buf cmd_buf;
+	struct hinic_hwdev *hwdev;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u64 out_param;
+	u32 ctx = 0;
+	int err;
+
+	hwdev = nic_dev->hwdev;
+	func_to_io = &hwdev->func_to_io;
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+
+	err = hinic_alloc_cmdq_buf(&func_to_io->cmdqs, &cmd_buf);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to allocate cmd buf\n");
+		return -ENOMEM;
+	}
+
+	ctx |=  HINIC_RSS_TYPE_SET(1, VALID) |
+		HINIC_RSS_TYPE_SET(rss_type.ipv4, IPV4) |
+		HINIC_RSS_TYPE_SET(rss_type.ipv6, IPV6) |
+		HINIC_RSS_TYPE_SET(rss_type.ipv6_ext, IPV6_EXT) |
+		HINIC_RSS_TYPE_SET(rss_type.tcp_ipv4, TCP_IPV4) |
+		HINIC_RSS_TYPE_SET(rss_type.tcp_ipv6, TCP_IPV6) |
+		HINIC_RSS_TYPE_SET(rss_type.tcp_ipv6_ext, TCP_IPV6_EXT) |
+		HINIC_RSS_TYPE_SET(rss_type.udp_ipv4, UDP_IPV4) |
+		HINIC_RSS_TYPE_SET(rss_type.udp_ipv6, UDP_IPV6);
+
+	cmd_buf.size = sizeof(struct hinic_rss_context_tbl);
+
+	ctx_tbl = (struct hinic_rss_context_tbl *)cmd_buf.buf;
+	ctx_tbl->group_index = cpu_to_be32(tmpl_idx);
+	ctx_tbl->offset = 0;
+	ctx_tbl->size = sizeof(u32);
+	ctx_tbl->size = cpu_to_be32(ctx_tbl->size);
+	ctx_tbl->rsvd = 0;
+	ctx_tbl->ctx = cpu_to_be32(ctx);
+
+	/* cfg the rss context table by command queue */
+	err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC,
+				     HINIC_UCODE_CMD_SET_RSS_CONTEXT_TABLE,
+				     &cmd_buf, &out_param);
+
+	hinic_free_cmdq_buf(&func_to_io->cmdqs, &cmd_buf);
+
+	if (err || out_param != 0) {
+		dev_err(&pdev->dev, "Failed to set rss context table, err: %d\n",
+			err);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic_get_rss_type(struct hinic_dev *nic_dev, u32 tmpl_idx,
+		       struct hinic_rss_type *rss_type)
+{
+	struct hinic_rss_context_table ctx_tbl = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u16 out_size = sizeof(ctx_tbl);
+	int err;
+
+	if (!hwdev || !rss_type)
+		return -EINVAL;
+
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+
+	ctx_tbl.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	ctx_tbl.template_id = tmpl_idx;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_RSS_CTX_TBL,
+				 &ctx_tbl, sizeof(ctx_tbl),
+				 &ctx_tbl, &out_size);
+	if (err || !out_size || ctx_tbl.status) {
+		dev_err(&pdev->dev, "Failed to get hash type, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, ctx_tbl.status, out_size);
+		return -EINVAL;
+	}
+
+	rss_type->ipv4          = HINIC_RSS_TYPE_GET(ctx_tbl.context, IPV4);
+	rss_type->ipv6          = HINIC_RSS_TYPE_GET(ctx_tbl.context, IPV6);
+	rss_type->ipv6_ext      = HINIC_RSS_TYPE_GET(ctx_tbl.context, IPV6_EXT);
+	rss_type->tcp_ipv4      = HINIC_RSS_TYPE_GET(ctx_tbl.context, TCP_IPV4);
+	rss_type->tcp_ipv6      = HINIC_RSS_TYPE_GET(ctx_tbl.context, TCP_IPV6);
+	rss_type->tcp_ipv6_ext  = HINIC_RSS_TYPE_GET(ctx_tbl.context,
+						     TCP_IPV6_EXT);
+	rss_type->udp_ipv4      = HINIC_RSS_TYPE_GET(ctx_tbl.context, UDP_IPV4);
+	rss_type->udp_ipv6      = HINIC_RSS_TYPE_GET(ctx_tbl.context, UDP_IPV6);
+
+	return 0;
+}
+
+int hinic_rss_set_template_tbl(struct hinic_dev *nic_dev, u32 template_id,
+			       const u8 *temp)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct hinic_rss_key rss_key = { 0 };
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size;
+	int err;
+
+	rss_key.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rss_key.template_id = template_id;
+	memcpy(rss_key.key, temp, HINIC_RSS_KEY_SIZE);
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RSS_TEMPLATE_TBL,
+				 &rss_key, sizeof(rss_key),
+				 &rss_key, &out_size);
+	if (err || !out_size || rss_key.status) {
+		dev_err(&pdev->dev,
+			"Failed to set rss hash key, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, rss_key.status, out_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic_rss_get_template_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
+			       u8 *temp)
+{
+	struct hinic_rss_template_key temp_key = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u16 out_size = sizeof(temp_key);
+	int err;
+
+	if (!hwdev || !temp)
+		return -EINVAL;
+
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+
+	temp_key.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	temp_key.template_id = tmpl_idx;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_RSS_TEMPLATE_TBL,
+				 &temp_key, sizeof(temp_key),
+				 &temp_key, &out_size);
+	if (err || !out_size || temp_key.status) {
+		dev_err(&pdev->dev, "Failed to set hash key, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, temp_key.status, out_size);
+		return -EINVAL;
+	}
+
+	memcpy(temp, temp_key.key, HINIC_RSS_KEY_SIZE);
+
+	return 0;
+}
+
+int hinic_rss_set_hash_engine(struct hinic_dev *nic_dev, u8 template_id,
+			      u8 type)
+{
+	struct hinic_rss_engine_type rss_engine = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size;
+	int err;
+
+	rss_engine.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rss_engine.hash_engine = type;
+	rss_engine.template_id = template_id;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RSS_HASH_ENGINE,
+				 &rss_engine, sizeof(rss_engine),
+				 &rss_engine, &out_size);
+	if (err || !out_size || rss_engine.status) {
+		dev_err(&pdev->dev,
+			"Failed to set hash engine, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, rss_engine.status, out_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic_rss_get_hash_engine(struct hinic_dev *nic_dev, u8 tmpl_idx, u8 *type)
+{
+	struct hinic_rss_engine_type hash_type = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u16 out_size = sizeof(hash_type);
+	int err;
+
+	if (!hwdev || !type)
+		return -EINVAL;
+
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+
+	hash_type.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	hash_type.template_id = tmpl_idx;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_RSS_HASH_ENGINE,
+				 &hash_type, sizeof(hash_type),
+				 &hash_type, &out_size);
+	if (err || !out_size || hash_type.status) {
+		dev_err(&pdev->dev, "Failed to get hash engine, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, hash_type.status, out_size);
+		return -EINVAL;
+	}
+
+	*type = hash_type.hash_engine;
+	return 0;
+}
+
+int hinic_rss_cfg(struct hinic_dev *nic_dev, u8 rss_en, u8 template_id)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_rss_config rss_cfg = { 0 };
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size;
+	int err;
+
+	rss_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rss_cfg.rss_en = rss_en;
+	rss_cfg.template_id = template_id;
+	rss_cfg.rq_priority_number = 0;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_RSS_CFG,
+				 &rss_cfg, sizeof(rss_cfg),
+				 &rss_cfg, &out_size);
+	if (err || !out_size || rss_cfg.status) {
+		dev_err(&pdev->dev,
+			"Failed to set rss cfg, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, rss_cfg.status, out_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic_rss_template_alloc(struct hinic_dev *nic_dev, u8 *tmpl_idx)
+{
+	struct hinic_rss_template_mgmt template_mgmt = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size;
+	int err;
+
+	template_mgmt.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	template_mgmt.cmd = NIC_RSS_CMD_TEMP_ALLOC;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_RSS_TEMP_MGR,
+				 &template_mgmt, sizeof(template_mgmt),
+				 &template_mgmt, &out_size);
+	if (err || !out_size || template_mgmt.status) {
+		dev_err(&pdev->dev, "Failed to alloc rss template, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, template_mgmt.status, out_size);
+		return -EINVAL;
+	}
+
+	*tmpl_idx = template_mgmt.template_id;
+
+	return 0;
+}
+
+int hinic_rss_template_free(struct hinic_dev *nic_dev, u8 tmpl_idx)
+{
+	struct hinic_rss_template_mgmt template_mgmt = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct pci_dev *pdev = hwif->pdev;
+	u16 out_size;
+	int err;
+
+	template_mgmt.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	template_mgmt.template_id = tmpl_idx;
+	template_mgmt.cmd = NIC_RSS_CMD_TEMP_FREE;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_RSS_TEMP_MGR,
+				 &template_mgmt, sizeof(template_mgmt),
+				 &template_mgmt, &out_size);
+	if (err || !out_size || template_mgmt.status) {
+		dev_err(&pdev->dev, "Failed to free rss template, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, template_mgmt.status, out_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic_get_vport_stats(struct hinic_dev *nic_dev,
+			  struct hinic_vport_stats *stats)
+{
+	struct hinic_cmd_vport_stats vport_stats = { 0 };
+	struct hinic_port_stats_info stats_info = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	u16 out_size = sizeof(vport_stats);
+	struct pci_dev *pdev = hwif->pdev;
+	int err;
+
+	stats_info.stats_version = HINIC_PORT_STATS_VERSION;
+	stats_info.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	stats_info.stats_size = sizeof(vport_stats);
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_VPORT_STAT,
+				 &stats_info, sizeof(stats_info),
+				 &vport_stats, &out_size);
+	if (err || !out_size || vport_stats.status) {
+		dev_err(&pdev->dev,
+			"Failed to get function statistics, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, vport_stats.status, out_size);
+		return -EFAULT;
+	}
+
+	memcpy(stats, &vport_stats.stats, sizeof(*stats));
+	return 0;
+}
+
+int hinic_get_phy_port_stats(struct hinic_dev *nic_dev,
+			     struct hinic_phy_port_stats *stats)
+{
+	struct hinic_port_stats_info stats_info = { 0 };
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif = hwdev->hwif;
+	struct hinic_port_stats *port_stats;
+	u16 out_size = sizeof(*port_stats);
+	struct pci_dev *pdev = hwif->pdev;
+	int err;
+
+	port_stats = kzalloc(sizeof(*port_stats), GFP_KERNEL);
+	if (!port_stats)
+		return -ENOMEM;
+
+	stats_info.stats_version = HINIC_PORT_STATS_VERSION;
+	stats_info.stats_size = sizeof(*port_stats);
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_PORT_STATISTICS,
+				 &stats_info, sizeof(stats_info),
+				 port_stats, &out_size);
+	if (err || !out_size || port_stats->status) {
+		dev_err(&pdev->dev,
+			"Failed to get port statistics, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, port_stats->status, out_size);
+		err = -EINVAL;
+		goto out;
+	}
+
+	memcpy(stats, &port_stats->stats, sizeof(*stats));
+
+out:
+	kfree(port_stats);
+
+	return err;
+}
+
+int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver)
+{
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_version_info up_ver = {0};
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u16 out_size;
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_MGMT_VERSION,
+				 &up_ver, sizeof(up_ver), &up_ver,
+				 &out_size);
+	if (err || !out_size || up_ver.status) {
+		dev_err(&pdev->dev,
+			"Failed to get mgmt version, err: %d, status: 0x%x, out size: 0x%x\n",
+			err, up_ver.status, out_size);
+		return -EINVAL;
+	}
+
+	snprintf(mgmt_ver, HINIC_MGMT_VERSION_MAX_LEN, "%s", up_ver.ver);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index 02d896eed455..44772fd47fc1 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_PORT_H
@@ -22,6 +13,22 @@
 
 #include "hinic_dev.h"
 
+#define HINIC_RSS_KEY_SIZE	40
+#define HINIC_RSS_INDIR_SIZE	256
+#define HINIC_PORT_STATS_VERSION	0
+#define HINIC_FW_VERSION_NAME	16
+#define HINIC_COMPILE_TIME_LEN	20
+#define HINIC_MGMT_VERSION_MAX_LEN	32
+
+struct hinic_version_info {
+	u8 status;
+	u8 version;
+	u8 rsvd[6];
+
+	u8 ver[HINIC_FW_VERSION_NAME];
+	u8 time[HINIC_COMPILE_TIME_LEN];
+};
+
 enum hinic_rx_mode {
 	HINIC_RX_MODE_UC        = BIT(0),
 	HINIC_RX_MODE_MC        = BIT(1),
@@ -192,6 +199,313 @@ struct hinic_checksum_offload {
 	u16	rsvd1;
 	u32	rx_csum_offload;
 };
+
+struct hinic_rq_num {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1[33];
+	u32	num_rqs;
+	u32	rq_depth;
+};
+
+struct hinic_lro_config {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u8	lro_ipv4_en;
+	u8	lro_ipv6_en;
+	u8	lro_max_wqe_num;
+	u8	resv2[13];
+};
+
+struct hinic_lro_timer {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u8	type;   /* 0: set timer value, 1: get timer value */
+	u8	enable; /* when set lro time, enable should be 1 */
+	u16	rsvd1;
+	u32	timer;
+};
+
+struct hinic_vlan_cfg {
+	u8      status;
+	u8      version;
+	u8      rsvd0[6];
+
+	u16     func_id;
+	u8      vlan_rx_offload;
+	u8      rsvd1[5];
+};
+
+struct hinic_rss_template_mgmt {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u8	cmd;
+	u8	template_id;
+	u8	rsvd1[4];
+};
+
+struct hinic_rss_template_key {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u8	template_id;
+	u8	rsvd1;
+	u8	key[HINIC_RSS_KEY_SIZE];
+};
+
+struct hinic_rss_context_tbl {
+	u32 group_index;
+	u32 offset;
+	u32 size;
+	u32 rsvd;
+	u32 ctx;
+};
+
+struct hinic_rss_context_table {
+	u8      status;
+	u8      version;
+	u8      rsvd0[6];
+
+	u16     func_id;
+	u8      template_id;
+	u8      rsvd1;
+	u32     context;
+};
+
+struct hinic_rss_indirect_tbl {
+	u32 group_index;
+	u32 offset;
+	u32 size;
+	u32 rsvd;
+	u8 entry[HINIC_RSS_INDIR_SIZE];
+};
+
+struct hinic_rss_indir_table {
+	u8      status;
+	u8      version;
+	u8      rsvd0[6];
+
+	u16     func_id;
+	u8      template_id;
+	u8      rsvd1;
+	u8      indir[HINIC_RSS_INDIR_SIZE];
+};
+
+struct hinic_rss_key {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u8	template_id;
+	u8	rsvd1;
+	u8	key[HINIC_RSS_KEY_SIZE];
+};
+
+struct hinic_rss_engine_type {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u8	template_id;
+	u8	hash_engine;
+	u8	rsvd1[4];
+};
+
+struct hinic_rss_config {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u8	rss_en;
+	u8	template_id;
+	u8	rq_priority_number;
+	u8	rsvd1[11];
+};
+
+struct hinic_stats {
+	char name[ETH_GSTRING_LEN];
+	u32 size;
+	int offset;
+};
+
+struct hinic_vport_stats {
+	u64 tx_unicast_pkts_vport;
+	u64 tx_unicast_bytes_vport;
+	u64 tx_multicast_pkts_vport;
+	u64 tx_multicast_bytes_vport;
+	u64 tx_broadcast_pkts_vport;
+	u64 tx_broadcast_bytes_vport;
+
+	u64 rx_unicast_pkts_vport;
+	u64 rx_unicast_bytes_vport;
+	u64 rx_multicast_pkts_vport;
+	u64 rx_multicast_bytes_vport;
+	u64 rx_broadcast_pkts_vport;
+	u64 rx_broadcast_bytes_vport;
+
+	u64 tx_discard_vport;
+	u64 rx_discard_vport;
+	u64 tx_err_vport;
+	u64 rx_err_vport;
+};
+
+struct hinic_phy_port_stats {
+	u64 mac_rx_total_pkt_num;
+	u64 mac_rx_total_oct_num;
+	u64 mac_rx_bad_pkt_num;
+	u64 mac_rx_bad_oct_num;
+	u64 mac_rx_good_pkt_num;
+	u64 mac_rx_good_oct_num;
+	u64 mac_rx_uni_pkt_num;
+	u64 mac_rx_multi_pkt_num;
+	u64 mac_rx_broad_pkt_num;
+
+	u64 mac_tx_total_pkt_num;
+	u64 mac_tx_total_oct_num;
+	u64 mac_tx_bad_pkt_num;
+	u64 mac_tx_bad_oct_num;
+	u64 mac_tx_good_pkt_num;
+	u64 mac_tx_good_oct_num;
+	u64 mac_tx_uni_pkt_num;
+	u64 mac_tx_multi_pkt_num;
+	u64 mac_tx_broad_pkt_num;
+
+	u64 mac_rx_fragment_pkt_num;
+	u64 mac_rx_undersize_pkt_num;
+	u64 mac_rx_undermin_pkt_num;
+	u64 mac_rx_64_oct_pkt_num;
+	u64 mac_rx_65_127_oct_pkt_num;
+	u64 mac_rx_128_255_oct_pkt_num;
+	u64 mac_rx_256_511_oct_pkt_num;
+	u64 mac_rx_512_1023_oct_pkt_num;
+	u64 mac_rx_1024_1518_oct_pkt_num;
+	u64 mac_rx_1519_2047_oct_pkt_num;
+	u64 mac_rx_2048_4095_oct_pkt_num;
+	u64 mac_rx_4096_8191_oct_pkt_num;
+	u64 mac_rx_8192_9216_oct_pkt_num;
+	u64 mac_rx_9217_12287_oct_pkt_num;
+	u64 mac_rx_12288_16383_oct_pkt_num;
+	u64 mac_rx_1519_max_bad_pkt_num;
+	u64 mac_rx_1519_max_good_pkt_num;
+	u64 mac_rx_oversize_pkt_num;
+	u64 mac_rx_jabber_pkt_num;
+
+	u64 mac_rx_pause_num;
+	u64 mac_rx_pfc_pkt_num;
+	u64 mac_rx_pfc_pri0_pkt_num;
+	u64 mac_rx_pfc_pri1_pkt_num;
+	u64 mac_rx_pfc_pri2_pkt_num;
+	u64 mac_rx_pfc_pri3_pkt_num;
+	u64 mac_rx_pfc_pri4_pkt_num;
+	u64 mac_rx_pfc_pri5_pkt_num;
+	u64 mac_rx_pfc_pri6_pkt_num;
+	u64 mac_rx_pfc_pri7_pkt_num;
+	u64 mac_rx_control_pkt_num;
+	u64 mac_rx_y1731_pkt_num;
+	u64 mac_rx_sym_err_pkt_num;
+	u64 mac_rx_fcs_err_pkt_num;
+	u64 mac_rx_send_app_good_pkt_num;
+	u64 mac_rx_send_app_bad_pkt_num;
+
+	u64 mac_tx_fragment_pkt_num;
+	u64 mac_tx_undersize_pkt_num;
+	u64 mac_tx_undermin_pkt_num;
+	u64 mac_tx_64_oct_pkt_num;
+	u64 mac_tx_65_127_oct_pkt_num;
+	u64 mac_tx_128_255_oct_pkt_num;
+	u64 mac_tx_256_511_oct_pkt_num;
+	u64 mac_tx_512_1023_oct_pkt_num;
+	u64 mac_tx_1024_1518_oct_pkt_num;
+	u64 mac_tx_1519_2047_oct_pkt_num;
+	u64 mac_tx_2048_4095_oct_pkt_num;
+	u64 mac_tx_4096_8191_oct_pkt_num;
+	u64 mac_tx_8192_9216_oct_pkt_num;
+	u64 mac_tx_9217_12287_oct_pkt_num;
+	u64 mac_tx_12288_16383_oct_pkt_num;
+	u64 mac_tx_1519_max_bad_pkt_num;
+	u64 mac_tx_1519_max_good_pkt_num;
+	u64 mac_tx_oversize_pkt_num;
+	u64 mac_tx_jabber_pkt_num;
+
+	u64 mac_tx_pause_num;
+	u64 mac_tx_pfc_pkt_num;
+	u64 mac_tx_pfc_pri0_pkt_num;
+	u64 mac_tx_pfc_pri1_pkt_num;
+	u64 mac_tx_pfc_pri2_pkt_num;
+	u64 mac_tx_pfc_pri3_pkt_num;
+	u64 mac_tx_pfc_pri4_pkt_num;
+	u64 mac_tx_pfc_pri5_pkt_num;
+	u64 mac_tx_pfc_pri6_pkt_num;
+	u64 mac_tx_pfc_pri7_pkt_num;
+	u64 mac_tx_control_pkt_num;
+	u64 mac_tx_y1731_pkt_num;
+	u64 mac_tx_1588_pkt_num;
+	u64 mac_tx_err_all_pkt_num;
+	u64 mac_tx_from_app_good_pkt_num;
+	u64 mac_tx_from_app_bad_pkt_num;
+
+	u64 mac_rx_higig2_ext_pkt_num;
+	u64 mac_rx_higig2_message_pkt_num;
+	u64 mac_rx_higig2_error_pkt_num;
+	u64 mac_rx_higig2_cpu_ctrl_pkt_num;
+	u64 mac_rx_higig2_unicast_pkt_num;
+	u64 mac_rx_higig2_broadcast_pkt_num;
+	u64 mac_rx_higig2_l2_multicast_pkt_num;
+	u64 mac_rx_higig2_l3_multicast_pkt_num;
+
+	u64 mac_tx_higig2_message_pkt_num;
+	u64 mac_tx_higig2_ext_pkt_num;
+	u64 mac_tx_higig2_cpu_ctrl_pkt_num;
+	u64 mac_tx_higig2_unicast_pkt_num;
+	u64 mac_tx_higig2_broadcast_pkt_num;
+	u64 mac_tx_higig2_l2_multicast_pkt_num;
+	u64 mac_tx_higig2_l3_multicast_pkt_num;
+};
+
+struct hinic_port_stats_info {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u32	stats_version;
+	u32	stats_size;
+};
+
+struct hinic_port_stats {
+	u8 status;
+	u8 version;
+	u8 rsvd[6];
+
+	struct hinic_phy_port_stats stats;
+};
+
+struct hinic_cmd_vport_stats {
+	u8 status;
+	u8 version;
+	u8 rsvd0[6];
+
+	struct hinic_vport_stats stats;
+};
+
 int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		       u16 vlan_id);
 
@@ -220,7 +534,55 @@ int hinic_port_set_func_state(struct hinic_dev *nic_dev,
 int hinic_port_get_cap(struct hinic_dev *nic_dev,
 		       struct hinic_port_cap *port_cap);
 
+int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs);
+
 int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state);
 
 int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en);
+
+int hinic_set_rx_lro_state(struct hinic_dev *nic_dev, u8 lro_en,
+			   u32 lro_timer, u32 wqe_num);
+
+int hinic_set_rss_type(struct hinic_dev *nic_dev, u32 tmpl_idx,
+		       struct hinic_rss_type rss_type);
+
+int hinic_rss_set_indir_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
+			    const u32 *indir_table);
+
+int hinic_rss_set_template_tbl(struct hinic_dev *nic_dev, u32 template_id,
+			       const u8 *temp);
+
+int hinic_rss_set_hash_engine(struct hinic_dev *nic_dev, u8 template_id,
+			      u8 type);
+
+int hinic_rss_cfg(struct hinic_dev *nic_dev, u8 rss_en, u8 template_id);
+
+int hinic_rss_template_alloc(struct hinic_dev *nic_dev, u8 *tmpl_idx);
+
+int hinic_rss_template_free(struct hinic_dev *nic_dev, u8 tmpl_idx);
+
+void hinic_set_ethtool_ops(struct net_device *netdev);
+
+int hinic_get_rss_type(struct hinic_dev *nic_dev, u32 tmpl_idx,
+		       struct hinic_rss_type *rss_type);
+
+int hinic_rss_get_indir_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
+			    u32 *indir_table);
+
+int hinic_rss_get_template_tbl(struct hinic_dev *nic_dev, u32 tmpl_idx,
+			       u8 *temp);
+
+int hinic_rss_get_hash_engine(struct hinic_dev *nic_dev, u8 tmpl_idx,
+			      u8 *type);
+
+int hinic_get_phy_port_stats(struct hinic_dev *nic_dev,
+			     struct hinic_phy_port_stats *stats);
+
+int hinic_get_vport_stats(struct hinic_dev *nic_dev,
+			  struct hinic_vport_stats *stats);
+
+int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en);
+
+int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver);
+
 #endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 0098b206e7e9..56ea6d692f1c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
@@ -27,6 +18,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/prefetch.h>
 #include <linux/cpumask.h>
+#include <linux/if_vlan.h>
 #include <asm/barrier.h>
 
 #include "hinic_common.h"
@@ -45,6 +37,15 @@
 #define RX_IRQ_NO_RESEND_TIMER          0
 #define HINIC_RX_BUFFER_WRITE           16
 
+#define HINIC_RX_IPV6_PKT		7
+#define LRO_PKT_HDR_LEN_IPV4		66
+#define LRO_PKT_HDR_LEN_IPV6		86
+#define LRO_REPLENISH_THLD		256
+
+#define LRO_PKT_HDR_LEN(cqe)		\
+	(HINIC_GET_RX_PKT_TYPE(be32_to_cpu((cqe)->offload_type)) == \
+	 HINIC_RX_IPV6_PKT ? LRO_PKT_HDR_LEN_IPV6 : LRO_PKT_HDR_LEN_IPV4)
+
 /**
  * hinic_rxq_clean_stats - Clean the statistics of specific queue
  * @rxq: Logical Rx Queue
@@ -56,6 +57,9 @@ void hinic_rxq_clean_stats(struct hinic_rxq *rxq)
 	u64_stats_update_begin(&rxq_stats->syncp);
 	rxq_stats->pkts  = 0;
 	rxq_stats->bytes = 0;
+	rxq_stats->errors = 0;
+	rxq_stats->csum_errors = 0;
+	rxq_stats->other_errors = 0;
 	u64_stats_update_end(&rxq_stats->syncp);
 }
 
@@ -74,6 +78,10 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats)
 		start = u64_stats_fetch_begin(&rxq_stats->syncp);
 		stats->pkts = rxq_stats->pkts;
 		stats->bytes = rxq_stats->bytes;
+		stats->errors = rxq_stats->csum_errors +
+				rxq_stats->other_errors;
+		stats->csum_errors = rxq_stats->csum_errors;
+		stats->other_errors = rxq_stats->other_errors;
 	} while (u64_stats_fetch_retry(&rxq_stats->syncp, start));
 	u64_stats_update_end(&stats->syncp);
 }
@@ -90,27 +98,25 @@ static void rxq_stats_init(struct hinic_rxq *rxq)
 	hinic_rxq_clean_stats(rxq);
 }
 
-static void rx_csum(struct hinic_rxq *rxq, u16 cons_idx,
+static void rx_csum(struct hinic_rxq *rxq, u32 status,
 		    struct sk_buff *skb)
 {
 	struct net_device *netdev = rxq->netdev;
-	struct hinic_rq_cqe *cqe;
-	struct hinic_rq *rq;
 	u32 csum_err;
-	u32 status;
 
-	rq = rxq->rq;
-	cqe = rq->cqe[cons_idx];
-	status = be32_to_cpu(cqe->status);
 	csum_err = HINIC_RQ_CQE_STATUS_GET(status, CSUM_ERR);
 
 	if (!(netdev->features & NETIF_F_RXCSUM))
 		return;
 
-	if (!csum_err)
+	if (!csum_err) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
-	else
+	} else {
+		if (!(csum_err & (HINIC_RX_CSUM_HW_CHECK_NONE |
+			HINIC_RX_CSUM_IPSU_OTHER_ERR)))
+			rxq->rxq_stats.csum_errors++;
 		skb->ip_summed = CHECKSUM_NONE;
+	}
 }
 /**
  * rx_alloc_skb - allocate skb and map it to dma address
@@ -320,13 +326,21 @@ static int rx_recv_jumbo_pkt(struct hinic_rxq *rxq, struct sk_buff *head_skb,
 static int rxq_recv(struct hinic_rxq *rxq, int budget)
 {
 	struct hinic_qp *qp = container_of(rxq->rq, struct hinic_qp, rq);
+	struct net_device *netdev = rxq->netdev;
 	u64 pkt_len = 0, rx_bytes = 0;
+	struct hinic_rq *rq = rxq->rq;
 	struct hinic_rq_wqe *rq_wqe;
 	unsigned int free_wqebbs;
+	struct hinic_rq_cqe *cqe;
 	int num_wqes, pkts = 0;
 	struct hinic_sge sge;
+	unsigned int status;
 	struct sk_buff *skb;
-	u16 ci;
+	u32 offload_type;
+	u16 ci, num_lro;
+	u16 num_wqe = 0;
+	u32 vlan_len;
+	u16 vid;
 
 	while (pkts < budget) {
 		num_wqes = 0;
@@ -336,11 +350,13 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 		if (!rq_wqe)
 			break;
 
+		cqe = rq->cqe[ci];
+		status =  be32_to_cpu(cqe->status);
 		hinic_rq_get_sge(rxq->rq, rq_wqe, ci, &sge);
 
 		rx_unmap_skb(rxq, hinic_sge_to_dma(&sge));
 
-		rx_csum(rxq, ci, skb);
+		rx_csum(rxq, status, skb);
 
 		prefetch(skb->data);
 
@@ -354,9 +370,17 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 						     HINIC_RX_BUF_SZ, ci);
 		}
 
-		hinic_rq_put_wqe(rxq->rq, ci,
+		hinic_rq_put_wqe(rq, ci,
 				 (num_wqes + 1) * HINIC_RQ_WQE_SIZE);
 
+		offload_type = be32_to_cpu(cqe->offload_type);
+		vlan_len = be32_to_cpu(cqe->len);
+		if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+		    HINIC_GET_RX_VLAN_OFFLOAD_EN(offload_type)) {
+			vid = HINIC_GET_RX_VLAN_TAG(vlan_len);
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+		}
+
 		skb_record_rx_queue(skb, qp->q_id);
 		skb->protocol = eth_type_trans(skb, rxq->netdev);
 
@@ -364,6 +388,21 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 
 		pkts++;
 		rx_bytes += pkt_len;
+
+		num_lro = HINIC_GET_RX_NUM_LRO(status);
+		if (num_lro) {
+			rx_bytes += ((num_lro - 1) *
+				     LRO_PKT_HDR_LEN(cqe));
+
+			num_wqe +=
+			(u16)(pkt_len >> rxq->rx_buff_shift) +
+			((pkt_len & (rxq->buf_len - 1)) ? 1 : 0);
+		}
+
+		cqe->status = 0;
+
+		if (num_wqe >= LRO_REPLENISH_THLD)
+			break;
 	}
 
 	free_wqebbs = hinic_get_rq_free_wqebbs(rxq->rq);
@@ -381,6 +420,7 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 static int rx_poll(struct napi_struct *napi, int budget)
 {
 	struct hinic_rxq *rxq = container_of(napi, struct hinic_rxq, napi);
+	struct hinic_dev *nic_dev = netdev_priv(rxq->netdev);
 	struct hinic_rq *rq = rxq->rq;
 	int pkts;
 
@@ -389,7 +429,10 @@ static int rx_poll(struct napi_struct *napi, int budget)
 		return budget;
 
 	napi_complete(napi);
-	enable_irq(rq->irq);
+	hinic_hwdev_set_msix_state(nic_dev->hwdev,
+				   rq->msix_entry,
+				   HINIC_MSIX_ENABLE);
+
 	return pkts;
 }
 
@@ -414,7 +457,10 @@ static irqreturn_t rx_irq(int irq, void *data)
 	struct hinic_dev *nic_dev;
 
 	/* Disable the interrupt until napi will be completed */
-	disable_irq_nosync(rq->irq);
+	nic_dev = netdev_priv(rxq->netdev);
+	hinic_hwdev_set_msix_state(nic_dev->hwdev,
+				   rq->msix_entry,
+				   HINIC_MSIX_DISABLE);
 
 	nic_dev = netdev_priv(rxq->netdev);
 	hinic_hwdev_msix_cnt_set(nic_dev->hwdev, rq->msix_entry);
@@ -471,20 +517,20 @@ int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq,
 		   struct net_device *netdev)
 {
 	struct hinic_qp *qp = container_of(rq, struct hinic_qp, rq);
-	int err, pkts, irqname_len;
+	int err, pkts;
 
 	rxq->netdev = netdev;
 	rxq->rq = rq;
+	rxq->buf_len = HINIC_RX_BUF_SZ;
+	rxq->rx_buff_shift = ilog2(HINIC_RX_BUF_SZ);
 
 	rxq_stats_init(rxq);
 
-	irqname_len = snprintf(NULL, 0, "hinic_rxq%d", qp->q_id) + 1;
-	rxq->irq_name = devm_kzalloc(&netdev->dev, irqname_len, GFP_KERNEL);
+	rxq->irq_name = devm_kasprintf(&netdev->dev, GFP_KERNEL,
+				       "hinic_rxq%d", qp->q_id);
 	if (!rxq->irq_name)
 		return -ENOMEM;
 
-	sprintf(rxq->irq_name, "hinic_rxq%d", qp->q_id);
-
 	pkts = rx_alloc_pkts(rxq);
 	if (!pkts) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.h b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
index f8ed3fa6c8ee..507dcbae9085 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_RX_H
@@ -30,7 +21,10 @@
 struct hinic_rxq_stats {
 	u64                     pkts;
 	u64                     bytes;
-
+	u64			errors;
+	u64			csum_errors;
+	u64			other_errors;
+	u64			alloc_skb_err;
 	struct u64_stats_sync   syncp;
 };
 
@@ -41,6 +35,8 @@ struct hinic_rxq {
 	struct hinic_rxq_stats  rxq_stats;
 
 	char                    *irq_name;
+	u16			buf_len;
+	u32			rx_buff_shift;
 
 	struct napi_struct      napi;
 };
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 11e73e67358d..9c78251f9c39 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #include <linux/kernel.h>
@@ -92,6 +83,7 @@ void hinic_txq_clean_stats(struct hinic_txq *txq)
 	txq_stats->tx_busy = 0;
 	txq_stats->tx_wake = 0;
 	txq_stats->tx_dropped = 0;
+	txq_stats->big_frags_pkts = 0;
 	u64_stats_update_end(&txq_stats->syncp);
 }
 
@@ -113,6 +105,7 @@ void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats)
 		stats->tx_busy = txq_stats->tx_busy;
 		stats->tx_wake = txq_stats->tx_wake;
 		stats->tx_dropped = txq_stats->tx_dropped;
+		stats->big_frags_pkts = txq_stats->big_frags_pkts;
 	} while (u64_stats_fetch_retry(&txq_stats->syncp, start));
 	u64_stats_update_end(&stats->syncp);
 }
@@ -414,10 +407,20 @@ static int offload_csum(struct hinic_sq_task *task, u32 *queue_info,
 	return 1;
 }
 
+static void offload_vlan(struct hinic_sq_task *task, u32 *queue_info,
+			 u16 vlan_tag, u16 vlan_pri)
+{
+	task->pkt_info0 |= HINIC_SQ_TASK_INFO0_SET(vlan_tag, VLAN_TAG) |
+				HINIC_SQ_TASK_INFO0_SET(1U, VLAN_OFFLOAD);
+
+	*queue_info |= HINIC_SQ_CTRL_SET(vlan_pri, QUEUE_INFO_PRI);
+}
+
 static int hinic_tx_offload(struct sk_buff *skb, struct hinic_sq_task *task,
 			    u32 *queue_info)
 {
 	enum hinic_offload_type offload = 0;
+	u16 vlan_tag;
 	int enabled;
 
 	enabled = offload_tso(task, queue_info, skb);
@@ -431,6 +434,13 @@ static int hinic_tx_offload(struct sk_buff *skb, struct hinic_sq_task *task,
 		return -EPROTONOSUPPORT;
 	}
 
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		vlan_tag = skb_vlan_tag_get(skb);
+		offload_vlan(task, queue_info, vlan_tag,
+			     vlan_tag >> VLAN_PRIO_SHIFT);
+		offload |= TX_OFFLOAD_VLAN;
+	}
+
 	if (offload)
 		hinic_task_set_l2hdr(task, skb_network_offset(skb));
 
@@ -473,6 +483,12 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	nr_sges = skb_shinfo(skb)->nr_frags + 1;
+	if (nr_sges > 17) {
+		u64_stats_update_begin(&txq->txq_stats.syncp);
+		txq->txq_stats.big_frags_pkts++;
+		u64_stats_update_end(&txq->txq_stats.syncp);
+	}
+
 	if (nr_sges > txq->max_sges) {
 		netdev_err(netdev, "Too many Tx sges\n");
 		goto skb_error;
@@ -518,7 +534,7 @@ process_sq_wqe:
 
 flush_skbs:
 	netdev_txq = netdev_get_tx_queue(netdev, q_id);
-	if ((!skb->xmit_more) || (netif_xmit_stopped(netdev_txq)))
+	if ((!netdev_xmit_more()) || (netif_xmit_stopped(netdev_txq)))
 		hinic_sq_write_db(txq->sq, prod_idx, wqe_size, 0);
 
 	return err;
@@ -655,7 +671,9 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 
 	if (pkts < budget) {
 		napi_complete(napi);
-		enable_irq(sq->irq);
+		hinic_hwdev_set_msix_state(nic_dev->hwdev,
+					   sq->msix_entry,
+					   HINIC_MSIX_ENABLE);
 		return pkts;
 	}
 
@@ -682,7 +700,9 @@ static irqreturn_t tx_irq(int irq, void *data)
 	nic_dev = netdev_priv(txq->netdev);
 
 	/* Disable the interrupt until napi will be completed */
-	disable_irq_nosync(txq->sq->irq);
+	hinic_hwdev_set_msix_state(nic_dev->hwdev,
+				   txq->sq->msix_entry,
+				   HINIC_MSIX_DISABLE);
 
 	hinic_hwdev_msix_cnt_set(nic_dev->hwdev, txq->sq->msix_entry);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.h b/drivers/net/ethernet/huawei/hinic/hinic_tx.h
index 1fa55dce5aa7..f158b7db7fb8 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Huawei HiNIC PCI Express Linux driver
  * Copyright(c) 2017 Huawei Technologies Co., Ltd
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
  */
 
 #ifndef HINIC_TX_H
@@ -30,6 +21,7 @@ struct hinic_txq_stats {
 	u64     tx_busy;
 	u64     tx_wake;
 	u64     tx_dropped;
+	u64	big_frags_pkts;
 
 	struct u64_stats_sync   syncp;
 };
diff --git a/drivers/net/ethernet/i825xx/Kconfig b/drivers/net/ethernet/i825xx/Kconfig
index e8d61f670479..33faff985438 100644
--- a/drivers/net/ethernet/i825xx/Kconfig
+++ b/drivers/net/ethernet/i825xx/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Intel 82596/82593/82596 network device configuration
 #
diff --git a/drivers/net/ethernet/i825xx/ether1.c b/drivers/net/ethernet/i825xx/ether1.c
index 35f6291a3672..bb3b8adbe4f0 100644
--- a/drivers/net/ethernet/i825xx/ether1.c
+++ b/drivers/net/ethernet/i825xx/ether1.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/drivers/acorn/net/ether1.c
  *
  *  Copyright (C) 1996-2000 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  Acorn ether1 driver (82586 chip) for Acorn machines
  *
  * We basically keep two queues in the cards memory - one for transmit
diff --git a/drivers/net/ethernet/i825xx/ether1.h b/drivers/net/ethernet/i825xx/ether1.h
index 3a5830ab3dc7..3926e042fe2e 100644
--- a/drivers/net/ethernet/i825xx/ether1.h
+++ b/drivers/net/ethernet/i825xx/ether1.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/drivers/acorn/net/ether1.h
  *
  *  Copyright (C) 1996 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  Network driver for Acorn Ether1 cards.
  */
 
diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c
index b69c622ba8b2..211c5f74b4c8 100644
--- a/drivers/net/ethernet/i825xx/lasi_82596.c
+++ b/drivers/net/ethernet/i825xx/lasi_82596.c
@@ -105,7 +105,7 @@
 #define DMA_WBACK_INV(ndev, addr, len) \
 	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_BIDIRECTIONAL); } while (0)
 
-#define SYSBUS      0x0000006c;
+#define SYSBUS      0x0000006c
 
 /* big endian CPU, 82596 "big" endian mode */
 #define SWAP32(x)   (((u32)(x)<<16) | ((((u32)(x)))>>16))
@@ -141,7 +141,8 @@ static void mpu_port(struct net_device *dev, int c, dma_addr_t x)
 	}
 
 	gsc_writel(a, dev->base_addr + PA_CPU_PORT_L_ACCESS);
-	udelay(1);
+	if (!running_on_qemu)
+		udelay(1);
 	gsc_writel(b, dev->base_addr + PA_CPU_PORT_L_ACCESS);
 }
 
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index 2f7ae118217f..1274ad24d6af 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -1194,7 +1194,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id)
 				dma_unmap_single(dev->dev.parent,
 						 tx_cmd->dma_addr,
 						 skb->len, DMA_TO_DEVICE);
-				dev_kfree_skb_irq(skb);
+				dev_consume_skb_irq(skb);
 
 				tx_cmd->cmd.command = 0; /* Mark free */
 				break;
diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c
index b2c04a789744..6eb6c2ff7f09 100644
--- a/drivers/net/ethernet/i825xx/sni_82596.c
+++ b/drivers/net/ethernet/i825xx/sni_82596.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * sni_82596.c -- driver for intel 82596 ethernet controller, as
  *  		  used in older SNI RM machines
diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig
index 37dceabf8861..a95d941360f8 100644
--- a/drivers/net/ethernet/ibm/Kconfig
+++ b/drivers/net/ethernet/ibm/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # IBM device configuration.
 #
diff --git a/drivers/net/ethernet/ibm/Makefile b/drivers/net/ethernet/ibm/Makefile
index 447865c8b632..1d17d0c33d4d 100644
--- a/drivers/net/ethernet/ibm/Makefile
+++ b/drivers/net/ethernet/ibm/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for th IBM network device drivers.
 #
diff --git a/drivers/net/ethernet/ibm/ehea/Makefile b/drivers/net/ethernet/ibm/ehea/Makefile
index cd473e295242..9e1e5c7aafe2 100644
--- a/drivers/net/ethernet/ibm/ehea/Makefile
+++ b/drivers/net/ethernet/ibm/ehea/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the eHEA ethernet device driver for IBM eServer System p
 #
diff --git a/drivers/net/ethernet/ibm/ehea/ehea.h b/drivers/net/ethernet/ibm/ehea/ehea.h
index 6be7b9839f35..b140835d4c23 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea.h
+++ b/drivers/net/ethernet/ibm/ehea/ehea.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea.h
  *
@@ -9,21 +10,6 @@
  *       Christoph Raisch <raisch@de.ibm.com>
  *       Jan-Bernd Themann <themann@de.ibm.com>
  *       Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __EHEA_H__
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c b/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
index 4f58d338d739..6cb86032ce46 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
  *
@@ -9,21 +10,6 @@
  *       Christoph Raisch <raisch@de.ibm.com>
  *       Jan-Bernd Themann <themann@de.ibm.com>
  *       Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_hw.h b/drivers/net/ethernet/ibm/ehea/ehea_hw.h
index 180d4128a711..590933a45d65 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_hw.h
+++ b/drivers/net/ethernet/ibm/ehea/ehea_hw.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea_hw.h
  *
@@ -9,21 +10,6 @@
  *       Christoph Raisch <raisch@de.ibm.com>
  *       Jan-Bernd Themann <themann@de.ibm.com>
  *       Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __EHEA_HW_H__
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 3baabdc89726..4138a8480347 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea_main.c
  *
@@ -9,21 +10,6 @@
  *	 Christoph Raisch <raisch@de.ibm.com>
  *	 Jan-Bernd Themann <themann@de.ibm.com>
  *	 Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -1463,7 +1449,7 @@ static int ehea_init_port_res(struct ehea_port *port, struct ehea_port_res *pr,
 
 	memset(pr, 0, sizeof(struct ehea_port_res));
 
-	pr->tx_bytes = rx_bytes;
+	pr->tx_bytes = tx_bytes;
 	pr->tx_packets = tx_packets;
 	pr->rx_bytes = rx_bytes;
 	pr->rx_packets = rx_packets;
@@ -3160,6 +3146,7 @@ static ssize_t ehea_probe_port(struct device *dev,
 
 	if (ehea_add_adapter_mr(adapter)) {
 		pr_err("creating MR failed\n");
+		of_node_put(eth_dn);
 		return -EIO;
 	}
 
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_phyp.c b/drivers/net/ethernet/ibm/ehea/ehea_phyp.c
index d3a130ccdcc8..e63716e139f5 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_phyp.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_phyp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea_phyp.c
  *
@@ -9,21 +10,6 @@
  *	 Christoph Raisch <raisch@de.ibm.com>
  *	 Jan-Bernd Themann <themann@de.ibm.com>
  *	 Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_phyp.h b/drivers/net/ethernet/ibm/ehea/ehea_phyp.h
index 99b6c2a38dbf..e8b56c103410 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_phyp.h
+++ b/drivers/net/ethernet/ibm/ehea/ehea_phyp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea_phyp.h
  *
@@ -9,21 +10,6 @@
  *       Christoph Raisch <raisch@de.ibm.com>
  *       Jan-Bernd Themann <themann@de.ibm.com>
  *       Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __EHEA_PHYP_H__
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
index 5e4e37132bf2..6e70658d50c4 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
  *
@@ -9,21 +10,6 @@
  *       Christoph Raisch <raisch@de.ibm.com>
  *       Jan-Bernd Themann <themann@de.ibm.com>
  *       Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -123,8 +109,7 @@ struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter,
 			       int nr_of_cqe, u64 eq_handle, u32 cq_token)
 {
 	struct ehea_cq *cq;
-	struct h_epa epa;
-	u64 *cq_handle_ref, hret, rpage;
+	u64 hret, rpage;
 	u32 counter;
 	int ret;
 	void *vpage;
@@ -139,8 +124,6 @@ struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter,
 
 	cq->adapter = adapter;
 
-	cq_handle_ref = &cq->fw_handle;
-
 	hret = ehea_h_alloc_resource_cq(adapter->handle, &cq->attr,
 					&cq->fw_handle, &cq->epas);
 	if (hret != H_SUCCESS) {
@@ -188,7 +171,6 @@ struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter,
 	}
 
 	hw_qeit_reset(&cq->hw_queue);
-	epa = cq->epas.kernel;
 	ehea_reset_cq_ep(cq);
 	ehea_reset_cq_n1(cq);
 
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.h b/drivers/net/ethernet/ibm/ehea/ehea_qmr.h
index 8e4a70c20ab7..7c7cccd820f7 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.h
+++ b/drivers/net/ethernet/ibm/ehea/ehea_qmr.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/drivers/net/ethernet/ibm/ehea/ehea_qmr.h
  *
@@ -9,21 +10,6 @@
  *       Christoph Raisch <raisch@de.ibm.com>
  *       Jan-Bernd Themann <themann@de.ibm.com>
  *       Thomas Klein <tklein@de.ibm.com>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __EHEA_QMR_H__
diff --git a/drivers/net/ethernet/ibm/emac/Kconfig b/drivers/net/ethernet/ibm/emac/Kconfig
index 90d49191beb3..c8e5de5987ac 100644
--- a/drivers/net/ethernet/ibm/emac/Kconfig
+++ b/drivers/net/ethernet/ibm/emac/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config IBM_EMAC
 	tristate "IBM EMAC Ethernet support"
 	depends on PPC_DCR
@@ -28,18 +29,6 @@ config IBM_EMAC_RX_COPY_THRESHOLD
 	depends on IBM_EMAC
 	default "256"
 
-config IBM_EMAC_RX_SKB_HEADROOM
-	int "Additional RX skb headroom (bytes)"
-	depends on IBM_EMAC
-	default "0"
-	help
-	  Additional receive skb headroom. Note, that driver
-	  will always reserve at least 2 bytes to make IP header
-	  aligned, so usually there is no need to add any additional
-	  headroom.
-
-	  If unsure, set to 0.
-
 config IBM_EMAC_DEBUG
 	bool "Debugging"
 	depends on IBM_EMAC
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 209255495bc9..395dde444483 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/ibm/emac/core.c
  *
@@ -16,12 +17,6 @@
  *	(c) 2003 Benjamin Herrenschmidt <benh@kernel.crashing.org>
  *      Armin Kuster <akuster@mvista.com>
  * 	Johnnie Peters <jpeters@mvista.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 #include <linux/module.h>
@@ -1071,7 +1066,9 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 
 	/* Second pass, allocate new skbs */
 	for (i = 0; i < NUM_RX_BUFF; ++i) {
-		struct sk_buff *skb = alloc_skb(rx_skb_size, GFP_ATOMIC);
+		struct sk_buff *skb;
+
+		skb = netdev_alloc_skb_ip_align(dev->ndev, rx_skb_size);
 		if (!skb) {
 			ret = -ENOMEM;
 			goto oom;
@@ -1080,10 +1077,10 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 		BUG_ON(!dev->rx_skb[i]);
 		dev_kfree_skb(dev->rx_skb[i]);
 
-		skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2);
 		dev->rx_desc[i].data_ptr =
-		    dma_map_single(&dev->ofdev->dev, skb->data - 2, rx_sync_size,
-				   DMA_FROM_DEVICE) + 2;
+		    dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+				   rx_sync_size, DMA_FROM_DEVICE)
+				   + NET_IP_ALIGN;
 		dev->rx_skb[i] = skb;
 	}
  skip:
@@ -1174,20 +1171,18 @@ static void emac_clean_rx_ring(struct emac_instance *dev)
 	}
 }
 
-static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot,
-				    gfp_t flags)
+static int
+__emac_prepare_rx_skb(struct sk_buff *skb, struct emac_instance *dev, int slot)
 {
-	struct sk_buff *skb = alloc_skb(dev->rx_skb_size, flags);
 	if (unlikely(!skb))
 		return -ENOMEM;
 
 	dev->rx_skb[slot] = skb;
 	dev->rx_desc[slot].data_len = 0;
 
-	skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2);
 	dev->rx_desc[slot].data_ptr =
-	    dma_map_single(&dev->ofdev->dev, skb->data - 2, dev->rx_sync_size,
-			   DMA_FROM_DEVICE) + 2;
+	    dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+			   dev->rx_sync_size, DMA_FROM_DEVICE) + NET_IP_ALIGN;
 	wmb();
 	dev->rx_desc[slot].ctrl = MAL_RX_CTRL_EMPTY |
 	    (slot == (NUM_RX_BUFF - 1) ? MAL_RX_CTRL_WRAP : 0);
@@ -1195,6 +1190,27 @@ static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot,
 	return 0;
 }
 
+static int
+emac_alloc_rx_skb(struct emac_instance *dev, int slot)
+{
+	struct sk_buff *skb;
+
+	skb = __netdev_alloc_skb_ip_align(dev->ndev, dev->rx_skb_size,
+					  GFP_KERNEL);
+
+	return __emac_prepare_rx_skb(skb, dev, slot);
+}
+
+static int
+emac_alloc_rx_skb_napi(struct emac_instance *dev, int slot)
+{
+	struct sk_buff *skb;
+
+	skb = napi_alloc_skb(&dev->mal->napi, dev->rx_skb_size);
+
+	return __emac_prepare_rx_skb(skb, dev, slot);
+}
+
 static void emac_print_link_status(struct emac_instance *dev)
 {
 	if (netif_carrier_ok(dev->ndev))
@@ -1225,7 +1241,7 @@ static int emac_open(struct net_device *ndev)
 
 	/* Allocate RX ring */
 	for (i = 0; i < NUM_RX_BUFF; ++i)
-		if (emac_alloc_rx_skb(dev, i, GFP_KERNEL)) {
+		if (emac_alloc_rx_skb(dev, i)) {
 			printk(KERN_ERR "%s: failed to allocate RX ring\n",
 			       ndev->name);
 			goto oom;
@@ -1660,8 +1676,9 @@ static inline void emac_recycle_rx_skb(struct emac_instance *dev, int slot,
 	DBG2(dev, "recycle %d %d" NL, slot, len);
 
 	if (len)
-		dma_map_single(&dev->ofdev->dev, skb->data - 2,
-			       EMAC_DMA_ALIGN(len + 2), DMA_FROM_DEVICE);
+		dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+			       SKB_DATA_ALIGN(len + NET_IP_ALIGN),
+			       DMA_FROM_DEVICE);
 
 	dev->rx_desc[slot].data_len = 0;
 	wmb();
@@ -1713,7 +1730,7 @@ static inline int emac_rx_sg_append(struct emac_instance *dev, int slot)
 		int len = dev->rx_desc[slot].data_len;
 		int tot_len = dev->rx_sg_skb->len + len;
 
-		if (unlikely(tot_len + 2 > dev->rx_skb_size)) {
+		if (unlikely(tot_len + NET_IP_ALIGN > dev->rx_skb_size)) {
 			++dev->estats.rx_dropped_mtu;
 			dev_kfree_skb(dev->rx_sg_skb);
 			dev->rx_sg_skb = NULL;
@@ -1769,16 +1786,18 @@ static int emac_poll_rx(void *param, int budget)
 		}
 
 		if (len && len < EMAC_RX_COPY_THRESH) {
-			struct sk_buff *copy_skb =
-			    alloc_skb(len + EMAC_RX_SKB_HEADROOM + 2, GFP_ATOMIC);
+			struct sk_buff *copy_skb;
+
+			copy_skb = napi_alloc_skb(&dev->mal->napi, len);
 			if (unlikely(!copy_skb))
 				goto oom;
 
-			skb_reserve(copy_skb, EMAC_RX_SKB_HEADROOM + 2);
-			memcpy(copy_skb->data - 2, skb->data - 2, len + 2);
+			memcpy(copy_skb->data - NET_IP_ALIGN,
+			       skb->data - NET_IP_ALIGN,
+			       len + NET_IP_ALIGN);
 			emac_recycle_rx_skb(dev, slot, len);
 			skb = copy_skb;
-		} else if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC)))
+		} else if (unlikely(emac_alloc_rx_skb_napi(dev, slot)))
 			goto oom;
 
 		skb_put(skb, len);
@@ -1799,7 +1818,7 @@ static int emac_poll_rx(void *param, int budget)
 	sg:
 		if (ctrl & MAL_RX_CTRL_FIRST) {
 			BUG_ON(dev->rx_sg_skb);
-			if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC))) {
+			if (unlikely(emac_alloc_rx_skb_napi(dev, slot))) {
 				DBG(dev, "rx OOM %d" NL, slot);
 				++dev->estats.rx_dropped_oom;
 				emac_recycle_rx_skb(dev, slot, 0);
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 84caa4a3fc52..e9cda024cbf6 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/core.h
  *
@@ -15,12 +16,6 @@
  *      Armin Kuster <akuster@mvista.com>
  * 	Johnnie Peters <jpeters@mvista.com>
  *      Copyright 2000, 2001 MontaVista Softare Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 #ifndef __IBM_NEWEMAC_CORE_H
 #define __IBM_NEWEMAC_CORE_H
@@ -68,22 +63,18 @@ static inline int emac_rx_size(int mtu)
 		return mal_rx_size(ETH_DATA_LEN + EMAC_MTU_OVERHEAD);
 }
 
-#define EMAC_DMA_ALIGN(x)		ALIGN((x), dma_get_cache_alignment())
-
-#define EMAC_RX_SKB_HEADROOM		\
-	EMAC_DMA_ALIGN(CONFIG_IBM_EMAC_RX_SKB_HEADROOM)
-
 /* Size of RX skb for the given MTU */
 static inline int emac_rx_skb_size(int mtu)
 {
 	int size = max(mtu + EMAC_MTU_OVERHEAD, emac_rx_size(mtu));
-	return EMAC_DMA_ALIGN(size + 2) + EMAC_RX_SKB_HEADROOM;
+
+	return SKB_DATA_ALIGN(size + NET_IP_ALIGN) + NET_SKB_PAD;
 }
 
 /* RX DMA sync size */
 static inline int emac_rx_sync_size(int mtu)
 {
-	return EMAC_DMA_ALIGN(emac_rx_size(mtu) + 2);
+	return SKB_DATA_ALIGN(emac_rx_size(mtu) + NET_IP_ALIGN);
 }
 
 /* Driver statistcs is split into two parts to make it more cache friendly:
diff --git a/drivers/net/ethernet/ibm/emac/debug.h b/drivers/net/ethernet/ibm/emac/debug.h
index 9d06d3be3161..c09a46a329d9 100644
--- a/drivers/net/ethernet/ibm/emac/debug.h
+++ b/drivers/net/ethernet/ibm/emac/debug.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/debug.h
  *
@@ -10,12 +11,6 @@
  *
  * Copyright (c) 2004, 2005 Zultys Technologies
  * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 #ifndef __IBM_NEWEMAC_DEBUG_H
 #define __IBM_NEWEMAC_DEBUG_H
diff --git a/drivers/net/ethernet/ibm/emac/emac.h b/drivers/net/ethernet/ibm/emac/emac.h
index 0d2de6f67676..aa9f651288d5 100644
--- a/drivers/net/ethernet/ibm/emac/emac.h
+++ b/drivers/net/ethernet/ibm/emac/emac.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/emac.h
  *
@@ -15,12 +16,6 @@
  *      Matt Porter <mporter@kernel.crashing.org>
  *      Armin Kuster <akuster@mvista.com>
  * 	Copyright 2002-2004 MontaVista Software Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 #ifndef __IBM_NEWEMAC_H
 #define __IBM_NEWEMAC_H
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index 787d5aca5278..075c07303f16 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/ibm/emac/mal.c
  *
@@ -17,12 +18,6 @@
  *
  *      Armin Kuster <akuster@mvista.com>
  *      Copyright 2002 MontaVista Softare Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/ibm/emac/mal.h b/drivers/net/ethernet/ibm/emac/mal.h
index e4c20f0024f6..d212373a72e7 100644
--- a/drivers/net/ethernet/ibm/emac/mal.h
+++ b/drivers/net/ethernet/ibm/emac/mal.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/mal.h
  *
@@ -14,12 +15,6 @@
  * Based on original work by
  *      Armin Kuster <akuster@mvista.com>
  *      Copyright 2002 MontaVista Softare Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 #ifndef __IBM_NEWEMAC_MAL_H
 #define __IBM_NEWEMAC_MAL_H
diff --git a/drivers/net/ethernet/ibm/emac/phy.c b/drivers/net/ethernet/ibm/emac/phy.c
index aa070c063e48..1e798cc9b6b8 100644
--- a/drivers/net/ethernet/ibm/emac/phy.c
+++ b/drivers/net/ethernet/ibm/emac/phy.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * drivers/net/ethernet/ibm/emac/phy.c
  *
diff --git a/drivers/net/ethernet/ibm/emac/phy.h b/drivers/net/ethernet/ibm/emac/phy.h
index d7e41ec37467..2184e8373ee5 100644
--- a/drivers/net/ethernet/ibm/emac/phy.h
+++ b/drivers/net/ethernet/ibm/emac/phy.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/phy.h
  *
@@ -13,11 +14,6 @@
  *
  * Minor additions by Eugene Surovegin <ebs@ebshome.net>, 2004
  *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  * This file basically duplicates sungem_phy.{c,h} with different PHYs
  * supported. I'm looking into merging that in a single mii layer more
  * flexible than mii.c
diff --git a/drivers/net/ethernet/ibm/emac/rgmii.c b/drivers/net/ethernet/ibm/emac/rgmii.c
index 00f5999de3cf..242ef976fd15 100644
--- a/drivers/net/ethernet/ibm/emac/rgmii.c
+++ b/drivers/net/ethernet/ibm/emac/rgmii.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/ibm/emac/rgmii.c
  *
@@ -14,12 +15,6 @@
  * Based on original work by
  * 	Matt Porter <mporter@kernel.crashing.org>
  * 	Copyright 2004 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 #include <linux/slab.h>
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/ibm/emac/rgmii.h b/drivers/net/ethernet/ibm/emac/rgmii.h
index d4f1374d1900..8e4e36eed172 100644
--- a/drivers/net/ethernet/ibm/emac/rgmii.h
+++ b/drivers/net/ethernet/ibm/emac/rgmii.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/rgmii.h
  *
@@ -16,11 +17,6 @@
  *
  * Copyright (c) 2004, 2005 Zultys Technologies.
  * Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __IBM_NEWEMAC_RGMII_H
diff --git a/drivers/net/ethernet/ibm/emac/tah.c b/drivers/net/ethernet/ibm/emac/tah.c
index 9912456dca48..008bbdaf1204 100644
--- a/drivers/net/ethernet/ibm/emac/tah.c
+++ b/drivers/net/ethernet/ibm/emac/tah.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/ibm/emac/tah.c
  *
@@ -12,11 +13,6 @@
  * Matt Porter <mporter@kernel.crashing.org>
  *
  * Copyright (c) 2005 Eugene Surovegin <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 #include <linux/of_address.h>
 #include <asm/io.h>
diff --git a/drivers/net/ethernet/ibm/emac/tah.h b/drivers/net/ethernet/ibm/emac/tah.h
index 4d5f336f07b3..86c2b6b9d460 100644
--- a/drivers/net/ethernet/ibm/emac/tah.h
+++ b/drivers/net/ethernet/ibm/emac/tah.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/tah.h
  *
@@ -12,11 +13,6 @@
  * Matt Porter <mporter@kernel.crashing.org>
  *
  * Copyright (c) 2005 Eugene Surovegin <ebs@ebshome.net>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __IBM_NEWEMAC_TAH_H
diff --git a/drivers/net/ethernet/ibm/emac/zmii.c b/drivers/net/ethernet/ibm/emac/zmii.c
index fdcc734541fe..b9e821de2ac6 100644
--- a/drivers/net/ethernet/ibm/emac/zmii.c
+++ b/drivers/net/ethernet/ibm/emac/zmii.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/ibm/emac/zmii.c
  *
@@ -14,12 +15,6 @@
  * Based on original work by
  *      Armin Kuster <akuster@mvista.com>
  * 	Copyright 2001 MontaVista Softare Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 #include <linux/slab.h>
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/ibm/emac/zmii.h b/drivers/net/ethernet/ibm/emac/zmii.h
index 0959c55b1459..41d46e9b87ba 100644
--- a/drivers/net/ethernet/ibm/emac/zmii.h
+++ b/drivers/net/ethernet/ibm/emac/zmii.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/ibm/emac/zmii.h
  *
@@ -14,12 +15,6 @@
  * Based on original work by
  *      Armin Kuster <akuster@mvista.com>
  * 	Copyright 2001 MontaVista Softare Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
  */
 #ifndef __IBM_NEWEMAC_ZMII_H
 #define __IBM_NEWEMAC_ZMII_H
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index dd71d5db7274..d654c234aaf7 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * IBM Power Virtual Ethernet Device Driver
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * Copyright (C) IBM Corporation, 2003, 2010
  *
  * Authors: Dave Larson <larson1@us.ibm.com>
@@ -93,7 +81,7 @@ struct ibmveth_stat {
 #define IBMVETH_STAT_OFF(stat) offsetof(struct ibmveth_adapter, stat)
 #define IBMVETH_GET_STAT(a, off) *((u64 *)(((unsigned long)(a)) + off))
 
-struct ibmveth_stat ibmveth_stats[] = {
+static struct ibmveth_stat ibmveth_stats[] = {
 	{ "replenish_task_cycles", IBMVETH_STAT_OFF(replenish_task_cycles) },
 	{ "replenish_no_mem", IBMVETH_STAT_OFF(replenish_no_mem) },
 	{ "replenish_add_buff_failure",
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 01c587fc02c7..4e9bf3421f4f 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -1,19 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * IBM Power Virtual Ethernet Device Driver
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * Copyright (C) IBM Corporation, 2003, 2010
  *
  * Authors: Dave Larson <larson1@us.ibm.com>
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5ecbb1adcf3b..3da680073265 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**************************************************************************/
 /*                                                                        */
 /*  IBM System i and System p Virtual NIC Device Driver                   */
@@ -6,18 +7,6 @@
 /*  Thomas Falcon (tlfalcon@linux.vnet.ibm.com)                           */
 /*  John Allen (jallen@linux.vnet.ibm.com)                                */
 /*                                                                        */
-/*  This program is free software; you can redistribute it and/or modify  */
-/*  it under the terms of the GNU General Public License as published by  */
-/*  the Free Software Foundation; either version 2 of the License, or     */
-/*  (at your option) any later version.                                   */
-/*                                                                        */
-/*  This program is distributed in the hope that it will be useful,       */
-/*  but WITHOUT ANY WARRANTY; without even the implied warranty of        */
-/*  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the         */
-/*  GNU General Public License for more details.                          */
-/*                                                                        */
-/*  You should have received a copy of the GNU General Public License     */
-/*  along with this program.                                              */
 /*                                                                        */
 /* This module contains the implementation of a virtual ethernet device   */
 /* for use with IBM i/p Series LPAR Linux. It utilizes the logical LAN    */
@@ -118,8 +107,9 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
 static int ibmvnic_init(struct ibmvnic_adapter *);
 static int ibmvnic_reset_init(struct ibmvnic_adapter *);
 static void release_crq_queue(struct ibmvnic_adapter *);
-static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p);
+static int __ibmvnic_set_mac(struct net_device *, u8 *);
 static int init_crq_queue(struct ibmvnic_adapter *adapter);
+static int send_query_phys_parms(struct ibmvnic_adapter *adapter);
 
 struct ibmvnic_stat {
 	char name[ETH_GSTRING_LEN];
@@ -438,9 +428,10 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter)
 		if (rx_pool->buff_size != be64_to_cpu(size_array[i])) {
 			free_long_term_buff(adapter, &rx_pool->long_term_buff);
 			rx_pool->buff_size = be64_to_cpu(size_array[i]);
-			alloc_long_term_buff(adapter, &rx_pool->long_term_buff,
-					     rx_pool->size *
-					     rx_pool->buff_size);
+			rc = alloc_long_term_buff(adapter,
+						  &rx_pool->long_term_buff,
+						  rx_pool->size *
+						  rx_pool->buff_size);
 		} else {
 			rc = reset_long_term_buff(adapter,
 						  &rx_pool->long_term_buff);
@@ -706,9 +697,9 @@ static int init_tx_pools(struct net_device *netdev)
 			return rc;
 		}
 
-		init_one_tx_pool(netdev, &adapter->tso_pool[i],
-				 IBMVNIC_TSO_BUFS,
-				 IBMVNIC_TSO_BUF_SZ);
+		rc = init_one_tx_pool(netdev, &adapter->tso_pool[i],
+				      IBMVNIC_TSO_BUFS,
+				      IBMVNIC_TSO_BUF_SZ);
 		if (rc) {
 			release_tx_pools(adapter);
 			return rc;
@@ -848,11 +839,7 @@ static int ibmvnic_login(struct net_device *netdev)
 		}
 	} while (retry);
 
-	/* handle pending MAC address changes after successful login */
-	if (adapter->mac_change_pending) {
-		__ibmvnic_set_mac(netdev, &adapter->desired.mac);
-		adapter->mac_change_pending = false;
-	}
+	__ibmvnic_set_mac(netdev, adapter->mac_addr);
 
 	return 0;
 }
@@ -1114,7 +1101,6 @@ static int ibmvnic_open(struct net_device *netdev)
 	}
 
 	rc = __ibmvnic_open(netdev);
-	netif_carrier_on(netdev);
 
 	return rc;
 }
@@ -1685,28 +1671,40 @@ static void ibmvnic_set_multi(struct net_device *netdev)
 	}
 }
 
-static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p)
+static int __ibmvnic_set_mac(struct net_device *netdev, u8 *dev_addr)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
-	struct sockaddr *addr = p;
 	union ibmvnic_crq crq;
 	int rc;
 
-	if (!is_valid_ether_addr(addr->sa_data))
-		return -EADDRNOTAVAIL;
+	if (!is_valid_ether_addr(dev_addr)) {
+		rc = -EADDRNOTAVAIL;
+		goto err;
+	}
 
 	memset(&crq, 0, sizeof(crq));
 	crq.change_mac_addr.first = IBMVNIC_CRQ_CMD;
 	crq.change_mac_addr.cmd = CHANGE_MAC_ADDR;
-	ether_addr_copy(&crq.change_mac_addr.mac_addr[0], addr->sa_data);
+	ether_addr_copy(&crq.change_mac_addr.mac_addr[0], dev_addr);
 
 	init_completion(&adapter->fw_done);
 	rc = ibmvnic_send_crq(adapter, &crq);
-	if (rc)
-		return rc;
+	if (rc) {
+		rc = -EIO;
+		goto err;
+	}
+
 	wait_for_completion(&adapter->fw_done);
 	/* netdev->dev_addr is changed in handle_change_mac_rsp function */
-	return adapter->fw_done_rc ? -EIO : 0;
+	if (adapter->fw_done_rc) {
+		rc = -EIO;
+		goto err;
+	}
+
+	return 0;
+err:
+	ether_addr_copy(adapter->mac_addr, netdev->dev_addr);
+	return rc;
 }
 
 static int ibmvnic_set_mac(struct net_device *netdev, void *p)
@@ -1715,13 +1713,10 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p)
 	struct sockaddr *addr = p;
 	int rc;
 
-	if (adapter->state == VNIC_PROBED) {
-		memcpy(&adapter->desired.mac, addr, sizeof(struct sockaddr));
-		adapter->mac_change_pending = true;
-		return 0;
-	}
-
-	rc = __ibmvnic_set_mac(netdev, addr);
+	rc = 0;
+	ether_addr_copy(adapter->mac_addr, addr->sa_data);
+	if (adapter->state != VNIC_PROBED)
+		rc = __ibmvnic_set_mac(netdev, addr->sa_data);
 
 	return rc;
 }
@@ -1751,7 +1746,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 
 	ibmvnic_cleanup(netdev);
 
-	if (adapter->reset_reason != VNIC_RESET_MOBILITY &&
+	if (reset_state == VNIC_OPEN &&
+	    adapter->reset_reason != VNIC_RESET_MOBILITY &&
 	    adapter->reset_reason != VNIC_RESET_FAILOVER) {
 		rc = __ibmvnic_close(netdev);
 		if (rc)
@@ -1850,6 +1846,9 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 		return 0;
 	}
 
+	/* refresh device's multicast list */
+	ibmvnic_set_multi(netdev);
+
 	/* kick napi */
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_schedule(&adapter->napi[i]);
@@ -1858,8 +1857,6 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	    adapter->reset_reason != VNIC_RESET_CHANGE_PARAM)
 		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev);
 
-	netif_carrier_on(netdev);
-
 	return 0;
 }
 
@@ -1885,6 +1882,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	 */
 	adapter->state = VNIC_PROBED;
 
+	reinit_completion(&adapter->init_done);
 	rc = init_crq_queue(adapter);
 	if (rc) {
 		netdev_err(adapter->netdev,
@@ -1928,8 +1926,6 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 		return 0;
 	}
 
-	netif_carrier_on(netdev);
-
 	return 0;
 }
 
@@ -1967,13 +1963,11 @@ static void __ibmvnic_reset(struct work_struct *work)
 {
 	struct ibmvnic_rwi *rwi;
 	struct ibmvnic_adapter *adapter;
-	struct net_device *netdev;
 	bool we_lock_rtnl = false;
 	u32 reset_state;
 	int rc = 0;
 
 	adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset);
-	netdev = adapter->netdev;
 
 	/* netif_set_real_num_xx_queues needs to take rtnl lock here
 	 * unless wait_for_reset is set, in which case the rtnl lock
@@ -2278,23 +2272,20 @@ static const struct net_device_ops ibmvnic_netdev_ops = {
 static int ibmvnic_get_link_ksettings(struct net_device *netdev,
 				      struct ethtool_link_ksettings *cmd)
 {
-	u32 supported, advertising;
+	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+	int rc;
 
-	supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg |
-			  SUPPORTED_FIBRE);
-	advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg |
-			    ADVERTISED_FIBRE);
-	cmd->base.speed = SPEED_1000;
-	cmd->base.duplex = DUPLEX_FULL;
+	rc = send_query_phys_parms(adapter);
+	if (rc) {
+		adapter->speed = SPEED_UNKNOWN;
+		adapter->duplex = DUPLEX_UNKNOWN;
+	}
+	cmd->base.speed = adapter->speed;
+	cmd->base.duplex = adapter->duplex;
 	cmd->base.port = PORT_FIBRE;
 	cmd->base.phy_address = 0;
 	cmd->base.autoneg = AUTONEG_ENABLE;
 
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
-
 	return 0;
 }
 
@@ -2922,8 +2913,10 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
 			goto req_tx_irq_failed;
 		}
 
+		snprintf(scrq->name, sizeof(scrq->name), "ibmvnic-%x-tx%d",
+			 adapter->vdev->unit_address, i);
 		rc = request_irq(scrq->irq, ibmvnic_interrupt_tx,
-				 0, "ibmvnic_tx", scrq);
+				 0, scrq->name, scrq);
 
 		if (rc) {
 			dev_err(dev, "Couldn't register tx irq 0x%x. rc=%d\n",
@@ -2943,8 +2936,10 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter)
 			dev_err(dev, "Error mapping irq\n");
 			goto req_rx_irq_failed;
 		}
+		snprintf(scrq->name, sizeof(scrq->name), "ibmvnic-%x-rx%d",
+			 adapter->vdev->unit_address, i);
 		rc = request_irq(scrq->irq, ibmvnic_interrupt_rx,
-				 0, "ibmvnic_rx", scrq);
+				 0, scrq->name, scrq);
 		if (rc) {
 			dev_err(dev, "Couldn't register rx irq 0x%x. rc=%d\n",
 				scrq->irq, rc);
@@ -3761,6 +3756,7 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
+	netdev_features_t old_hw_features = 0;
 	union ibmvnic_crq crq;
 	int i;
 
@@ -3836,24 +3832,41 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
 	adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
 
-	adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO;
+	if (adapter->state != VNIC_PROBING) {
+		old_hw_features = adapter->netdev->hw_features;
+		adapter->netdev->hw_features = 0;
+	}
+
+	adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO;
 
 	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
-		adapter->netdev->features |= NETIF_F_IP_CSUM;
+		adapter->netdev->hw_features |= NETIF_F_IP_CSUM;
 
 	if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
-		adapter->netdev->features |= NETIF_F_IPV6_CSUM;
+		adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM;
 
 	if ((adapter->netdev->features &
 	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
-		adapter->netdev->features |= NETIF_F_RXCSUM;
+		adapter->netdev->hw_features |= NETIF_F_RXCSUM;
 
 	if (buf->large_tx_ipv4)
-		adapter->netdev->features |= NETIF_F_TSO;
+		adapter->netdev->hw_features |= NETIF_F_TSO;
 	if (buf->large_tx_ipv6)
-		adapter->netdev->features |= NETIF_F_TSO6;
+		adapter->netdev->hw_features |= NETIF_F_TSO6;
+
+	if (adapter->state == VNIC_PROBING) {
+		adapter->netdev->features |= adapter->netdev->hw_features;
+	} else if (old_hw_features != adapter->netdev->hw_features) {
+		netdev_features_t tmp = 0;
 
-	adapter->netdev->hw_features |= adapter->netdev->features;
+		/* disable features no longer supported */
+		adapter->netdev->features &= adapter->netdev->hw_features;
+		/* turn on features now supported if previously enabled */
+		tmp = (old_hw_features ^ adapter->netdev->hw_features) &
+			adapter->netdev->hw_features;
+		adapter->netdev->features |=
+				tmp & adapter->netdev->wanted_features;
+	}
 
 	memset(&crq, 0, sizeof(crq));
 	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
@@ -3918,8 +3931,8 @@ static int handle_change_mac_rsp(union ibmvnic_crq *crq,
 		dev_err(dev, "Error %ld in CHANGE_MAC_ADDR_RSP\n", rc);
 		goto out;
 	}
-	memcpy(netdev->dev_addr, &crq->change_mac_addr_rsp.mac_addr[0],
-	       ETH_ALEN);
+	ether_addr_copy(netdev->dev_addr,
+			&crq->change_mac_addr_rsp.mac_addr[0]);
 out:
 	complete(&adapter->fw_done);
 	return rc;
@@ -4278,6 +4291,73 @@ out:
 	}
 }
 
+static int send_query_phys_parms(struct ibmvnic_adapter *adapter)
+{
+	union ibmvnic_crq crq;
+	int rc;
+
+	memset(&crq, 0, sizeof(crq));
+	crq.query_phys_parms.first = IBMVNIC_CRQ_CMD;
+	crq.query_phys_parms.cmd = QUERY_PHYS_PARMS;
+	init_completion(&adapter->fw_done);
+	rc = ibmvnic_send_crq(adapter, &crq);
+	if (rc)
+		return rc;
+	wait_for_completion(&adapter->fw_done);
+	return adapter->fw_done_rc ? -EIO : 0;
+}
+
+static int handle_query_phys_parms_rsp(union ibmvnic_crq *crq,
+				       struct ibmvnic_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	int rc;
+
+	rc = crq->query_phys_parms_rsp.rc.code;
+	if (rc) {
+		netdev_err(netdev, "Error %d in QUERY_PHYS_PARMS\n", rc);
+		return rc;
+	}
+	switch (cpu_to_be32(crq->query_phys_parms_rsp.speed)) {
+	case IBMVNIC_10MBPS:
+		adapter->speed = SPEED_10;
+		break;
+	case IBMVNIC_100MBPS:
+		adapter->speed = SPEED_100;
+		break;
+	case IBMVNIC_1GBPS:
+		adapter->speed = SPEED_1000;
+		break;
+	case IBMVNIC_10GBP:
+		adapter->speed = SPEED_10000;
+		break;
+	case IBMVNIC_25GBPS:
+		adapter->speed = SPEED_25000;
+		break;
+	case IBMVNIC_40GBPS:
+		adapter->speed = SPEED_40000;
+		break;
+	case IBMVNIC_50GBPS:
+		adapter->speed = SPEED_50000;
+		break;
+	case IBMVNIC_100GBPS:
+		adapter->speed = SPEED_100000;
+		break;
+	default:
+		netdev_warn(netdev, "Unknown speed 0x%08x\n",
+			    cpu_to_be32(crq->query_phys_parms_rsp.speed));
+		adapter->speed = SPEED_UNKNOWN;
+	}
+	if (crq->query_phys_parms_rsp.flags1 & IBMVNIC_FULL_DUPLEX)
+		adapter->duplex = DUPLEX_FULL;
+	else if (crq->query_phys_parms_rsp.flags1 & IBMVNIC_HALF_DUPLEX)
+		adapter->duplex = DUPLEX_HALF;
+	else
+		adapter->duplex = DUPLEX_UNKNOWN;
+
+	return rc;
+}
+
 static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 			       struct ibmvnic_adapter *adapter)
 {
@@ -4389,6 +4469,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		    crq->link_state_indication.phys_link_state;
 		adapter->logical_link_state =
 		    crq->link_state_indication.logical_link_state;
+		if (adapter->phys_link_state && adapter->logical_link_state)
+			netif_carrier_on(netdev);
+		else
+			netif_carrier_off(netdev);
 		break;
 	case CHANGE_MAC_ADDR_RSP:
 		netdev_dbg(netdev, "Got MAC address change Response\n");
@@ -4426,6 +4510,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 	case GET_VPD_RSP:
 		handle_vpd_rsp(crq, adapter);
 		break;
+	case QUERY_PHYS_PARMS_RSP:
+		adapter->fw_done_rc = handle_query_phys_parms_rsp(crq, adapter);
+		complete(&adapter->fw_done);
+		break;
 	default:
 		netdev_err(netdev, "Got an invalid cmd type 0x%02x\n",
 			   gen_crq->cmd);
@@ -4581,8 +4669,9 @@ static int init_crq_queue(struct ibmvnic_adapter *adapter)
 		     (unsigned long)adapter);
 
 	netdev_dbg(adapter->netdev, "registering irq 0x%x\n", vdev->irq);
-	rc = request_irq(vdev->irq, ibmvnic_interrupt, 0, IBMVNIC_NAME,
-			 adapter);
+	snprintf(crq->name, sizeof(crq->name), "ibmvnic-%x",
+		 adapter->vdev->unit_address);
+	rc = request_irq(vdev->irq, ibmvnic_interrupt, 0, crq->name, adapter);
 	if (rc) {
 		dev_err(dev, "Couldn't register irq 0x%x. rc=%d\n",
 			vdev->irq, rc);
@@ -4625,7 +4714,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter)
 	old_num_rx_queues = adapter->req_rx_queues;
 	old_num_tx_queues = adapter->req_tx_queues;
 
-	init_completion(&adapter->init_done);
+	reinit_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4680,7 +4769,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 
 	adapter->from_passive_init = false;
 
-	init_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4759,10 +4847,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
 	INIT_LIST_HEAD(&adapter->rwi_list);
 	spin_lock_init(&adapter->rwi_lock);
+	init_completion(&adapter->init_done);
 	adapter->resetting = false;
 
-	adapter->mac_change_pending = false;
-
 	do {
 		rc = init_crq_queue(adapter);
 		if (rc) {
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index f2018dbebfa5..70bd286f8932 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /**************************************************************************/
 /*                                                                        */
 /*  IBM System i and System p Virtual NIC Device Driver                   */
@@ -6,18 +7,6 @@
 /*  Thomas Falcon (tlfalcon@linux.vnet.ibm.com)                           */
 /*  John Allen (jallen@linux.vnet.ibm.com)                                */
 /*                                                                        */
-/*  This program is free software; you can redistribute it and/or modify  */
-/*  it under the terms of the GNU General Public License as published by  */
-/*  the Free Software Foundation; either version 2 of the License, or     */
-/*  (at your option) any later version.                                   */
-/*                                                                        */
-/*  This program is distributed in the hope that it will be useful,       */
-/*  but WITHOUT ANY WARRANTY; without even the implied warranty of        */
-/*  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the         */
-/*  GNU General Public License for more details.                          */
-/*                                                                        */
-/*  You should have received a copy of the GNU General Public License     */
-/*  along with this program.                                              */
 /*                                                                        */
 /* This module contains the implementation of a virtual ethernet device   */
 /* for use with IBM i/pSeries LPAR Linux.  It utilizes the logical LAN    */
@@ -377,11 +366,16 @@ struct ibmvnic_phys_parms {
 	u8 flags2;
 #define IBMVNIC_LOGICAL_LNK_ACTIVE 0x80
 	__be32 speed;
-#define IBMVNIC_AUTONEG		0x80
-#define IBMVNIC_10MBPS		0x40
-#define IBMVNIC_100MBPS		0x20
-#define IBMVNIC_1GBPS		0x10
-#define IBMVNIC_10GBPS		0x08
+#define IBMVNIC_AUTONEG		0x80000000
+#define IBMVNIC_10MBPS		0x40000000
+#define IBMVNIC_100MBPS		0x20000000
+#define IBMVNIC_1GBPS		0x10000000
+#define IBMVNIC_10GBP		0x08000000
+#define IBMVNIC_40GBPS		0x04000000
+#define IBMVNIC_100GBPS		0x02000000
+#define IBMVNIC_25GBPS		0x01000000
+#define IBMVNIC_50GBPS		0x00800000
+#define IBMVNIC_200GBPS		0x00400000
 	__be32 mtu;
 	struct ibmvnic_rc rc;
 } __packed __aligned(8);
@@ -850,6 +844,7 @@ struct ibmvnic_crq_queue {
 	dma_addr_t msg_token;
 	spinlock_t lock;
 	bool active;
+	char name[32];
 };
 
 union sub_crq {
@@ -876,6 +871,7 @@ struct ibmvnic_sub_crq_queue {
 	struct sk_buff *rx_skb_top;
 	struct ibmvnic_adapter *adapter;
 	atomic_t used;
+	char name[32];
 };
 
 struct ibmvnic_long_term_buff {
@@ -962,7 +958,6 @@ struct ibmvnic_tunables {
 	u64 rx_entries;
 	u64 tx_entries;
 	u64 mtu;
-	struct sockaddr mac;
 };
 
 struct ibmvnic_adapter {
@@ -999,6 +994,9 @@ struct ibmvnic_adapter {
 	int phys_link_state;
 	int logical_link_state;
 
+	u32 speed;
+	u8 duplex;
+
 	/* login data */
 	struct ibmvnic_login_buffer *login_buf;
 	dma_addr_t login_buf_token;
@@ -1081,7 +1079,6 @@ struct ibmvnic_adapter {
 	bool resetting;
 	bool napi_enabled, from_passive_init;
 
-	bool mac_change_pending;
 	bool failover_pending;
 	bool force_reset_recovery;
 
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index a1246e89aad4..154e2e818ec6 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Intel network device configuration
 #
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 0fd268070fb4..a65d5a9ba7db 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -2797,7 +2797,7 @@ static int e100_set_features(struct net_device *netdev,
 
 	netdev->features = features;
 	e100_exec_cb(nic, NULL, e100_configure);
-	return 0;
+	return 1;
 }
 
 static const struct net_device_ops e100_netdev_ops = {
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 8fe9af0e2ab7..f703fa58458e 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -820,7 +820,7 @@ static int e1000_set_features(struct net_device *netdev,
 	else
 		e1000_reset(adapter);
 
-	return 0;
+	return 1;
 }
 
 static const struct net_device_ops e1000_netdev_ops = {
@@ -3019,7 +3019,7 @@ static void e1000_tx_queue(struct e1000_adapter *adapter,
 	 * applicable for weak-ordered memory model archs,
 	 * such as IA-64).
 	 */
-	wmb();
+	dma_wmb();
 
 	tx_ring->next_to_use = i;
 }
@@ -3267,14 +3267,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		/* Make sure there is space in the ring for the next send. */
 		e1000_maybe_stop_tx(netdev, tx_ring, desc_needed);
 
-		if (!skb->xmit_more ||
+		if (!netdev_xmit_more() ||
 		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
 			writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt);
-			/* we need this if more than one processor can write to
-			 * our tail at a time, it synchronizes IO on IA64/Altix
-			 * systems
-			 */
-			mmiowb();
 		}
 	} else {
 		dev_kfree_skb_any(skb);
@@ -4545,7 +4540,7 @@ e1000_alloc_jumbo_rx_buffers(struct e1000_adapter *adapter,
 		 * applicable for weak-ordered memory model archs,
 		 * such as IA-64).
 		 */
-		wmb();
+		dma_wmb();
 		writel(i, adapter->hw.hw_addr + rx_ring->rdt);
 	}
 }
@@ -4660,7 +4655,7 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 		 * applicable for weak-ordered memory model archs,
 		 * such as IA-64).
 		 */
-		wmb();
+		dma_wmb();
 		writel(i, hw->hw_addr + rx_ring->rdt);
 	}
 }
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 257bd59bc9c6..4b103cca8a39 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -680,7 +680,7 @@ static s32 e1000_reset_hw_80003es2lan(struct e1000_hw *hw)
 	ew32(TCTL, E1000_TCTL_PSP);
 	e1e_flush();
 
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	ctrl = er32(CTRL);
 
@@ -696,11 +696,16 @@ static s32 e1000_reset_hw_80003es2lan(struct e1000_hw *hw)
 	ret_val =
 	    e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
 					    &kum_reg_data);
-	if (ret_val)
-		return ret_val;
-	kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
-	e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
-					 kum_reg_data);
+	if (!ret_val) {
+		kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
+		ret_val = e1000_write_kmrn_reg_80003es2lan(hw,
+						 E1000_KMRNCTRLSTA_INBAND_PARAM,
+						 kum_reg_data);
+		if (ret_val)
+			e_dbg("Error disabling far-end loopback\n");
+	} else {
+		e_dbg("Error disabling far-end loopback\n");
+	}
 
 	ret_val = e1000e_get_auto_rd_done(hw);
 	if (ret_val)
@@ -754,11 +759,19 @@ static s32 e1000_init_hw_80003es2lan(struct e1000_hw *hw)
 		return ret_val;
 
 	/* Disable IBIST slave mode (far-end loopback) */
-	e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
-					&kum_reg_data);
-	kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
-	e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
-					 kum_reg_data);
+	ret_val =
+	    e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
+					    &kum_reg_data);
+	if (!ret_val) {
+		kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
+		ret_val = e1000_write_kmrn_reg_80003es2lan(hw,
+						 E1000_KMRNCTRLSTA_INBAND_PARAM,
+						 kum_reg_data);
+		if (ret_val)
+			e_dbg("Error disabling far-end loopback\n");
+	} else {
+		e_dbg("Error disabling far-end loopback\n");
+	}
 
 	/* Set the transmit descriptor write-back policy */
 	reg_data = er32(TXDCTL(0));
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index b9309302c29e..2c1bab377b2a 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -959,7 +959,7 @@ static s32 e1000_reset_hw_82571(struct e1000_hw *hw)
 	ew32(TCTL, tctl);
 	e1e_flush();
 
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	/* Must acquire the MDIO ownership before MAC reset.
 	 * Ownership defaults to firmware after a reset.
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index fd550dee4982..63c3c79380a1 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -222,6 +222,9 @@
 #define E1000_STATUS_PHYRA      0x00000400      /* PHY Reset Asserted */
 #define E1000_STATUS_GIO_MASTER_ENABLE	0x00080000	/* Master Req status */
 
+/* PCIm function state */
+#define E1000_STATUS_PCIM_STATE	0x40000000
+
 #define HALF_DUPLEX 1
 #define FULL_DUPLEX 2
 
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index be13227f1697..34cd67951aec 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -186,12 +186,13 @@ struct e1000_phy_regs {
 
 /* board specific private data structure */
 struct e1000_adapter {
-	struct timer_list watchdog_timer;
 	struct timer_list phy_info_timer;
 	struct timer_list blink_timer;
 
 	struct work_struct reset_task;
-	struct work_struct watchdog_task;
+	struct delayed_work watchdog_task;
+
+	struct workqueue_struct *e1000_workqueue;
 
 	const struct e1000_info *ei;
 
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 02ebf208f48b..08342698386d 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -1014,7 +1014,7 @@ static int e1000_intr_test(struct e1000_adapter *adapter, u64 *data)
 	/* Disable all the interrupts */
 	ew32(IMC, 0xFFFFFFFF);
 	e1e_flush();
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	/* Test each interrupt */
 	for (i = 0; i < 10; i++) {
@@ -1046,7 +1046,7 @@ static int e1000_intr_test(struct e1000_adapter *adapter, u64 *data)
 			ew32(IMC, mask);
 			ew32(ICS, mask);
 			e1e_flush();
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 
 			if (adapter->test_icr & mask) {
 				*data = 3;
@@ -1064,7 +1064,7 @@ static int e1000_intr_test(struct e1000_adapter *adapter, u64 *data)
 		ew32(IMS, mask);
 		ew32(ICS, mask);
 		e1e_flush();
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 
 		if (!(adapter->test_icr & mask)) {
 			*data = 4;
@@ -1082,7 +1082,7 @@ static int e1000_intr_test(struct e1000_adapter *adapter, u64 *data)
 			ew32(IMC, ~mask & 0x00007FFF);
 			ew32(ICS, ~mask & 0x00007FFF);
 			e1e_flush();
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 
 			if (adapter->test_icr) {
 				*data = 5;
@@ -1094,7 +1094,7 @@ static int e1000_intr_test(struct e1000_adapter *adapter, u64 *data)
 	/* Disable all the interrupts */
 	ew32(IMC, 0xFFFFFFFF);
 	e1e_flush();
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	/* Unhook test interrupt handler */
 	free_irq(irq, netdev);
@@ -1470,7 +1470,7 @@ static int e1000_set_82571_fiber_loopback(struct e1000_adapter *adapter)
 	 */
 	ew32(SCTL, E1000_SCTL_ENABLE_SERDES_LOOPBACK);
 	e1e_flush();
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	return 0;
 }
@@ -1584,7 +1584,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter)
 		    hw->phy.media_type == e1000_media_type_internal_serdes) {
 			ew32(SCTL, E1000_SCTL_DISABLE_SERDES_LOOPBACK);
 			e1e_flush();
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 			break;
 		}
 		/* Fall Through */
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index cdae0efde8e6..395b05701480 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -271,7 +271,7 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw)
 		u16 count = 20;
 
 		do {
-			usleep_range(5000, 10000);
+			usleep_range(5000, 6000);
 		} while (!(er32(CTRL_EXT) & E1000_CTRL_EXT_LPCD) && count--);
 
 		msleep(30);
@@ -405,7 +405,7 @@ out:
 	/* Ungate automatic PHY configuration on non-managed 82579 */
 	if ((hw->mac.type == e1000_pch2lan) &&
 	    !(fwsm & E1000_ICH_FWSM_FW_VALID)) {
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 		e1000_gate_hw_phy_config_ich8lan(hw, false);
 	}
 
@@ -531,7 +531,7 @@ static s32 e1000_init_phy_params_ich8lan(struct e1000_hw *hw)
 	phy->id = 0;
 	while ((e1000_phy_unknown == e1000e_get_phy_type_from_id(phy->id)) &&
 	       (i++ < 100)) {
-		usleep_range(1000, 2000);
+		usleep_range(1000, 1100);
 		ret_val = e1000e_get_phy_id(hw);
 		if (ret_val)
 			return ret_val;
@@ -1244,7 +1244,7 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force)
 				goto out;
 			}
 
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 		}
 		e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
 
@@ -1999,7 +1999,7 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw)
 
 	while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) &&
 	       (i++ < 30))
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 	return blocked ? E1000_BLK_PHY_RESET : 0;
 }
 
@@ -2818,7 +2818,7 @@ static s32 e1000_post_phy_reset_ich8lan(struct e1000_hw *hw)
 		return 0;
 
 	/* Allow time for h/w to get to quiescent state after reset */
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	/* Perform any necessary post-reset workarounds */
 	switch (hw->mac.type) {
@@ -2854,7 +2854,7 @@ static s32 e1000_post_phy_reset_ich8lan(struct e1000_hw *hw)
 	if (hw->mac.type == e1000_pch2lan) {
 		/* Ungate automatic PHY configuration on non-managed 82579 */
 		if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) {
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 			e1000_gate_hw_phy_config_ich8lan(hw, false);
 		}
 
@@ -3875,7 +3875,7 @@ release:
 	 */
 	if (!ret_val) {
 		nvm->ops.reload(hw);
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 	}
 
 out:
@@ -4026,7 +4026,7 @@ release:
 	 */
 	if (!ret_val) {
 		nvm->ops.reload(hw);
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 	}
 
 out:
@@ -4650,7 +4650,7 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
 	ew32(TCTL, E1000_TCTL_PSP);
 	e1e_flush();
 
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	/* Workaround for ICH8 bit corruption issue in FIFO memory */
 	if (hw->mac.type == e1000_ich8lan) {
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index 4abd55d646c5..e531976f8a67 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -797,7 +797,7 @@ static s32 e1000_poll_fiber_serdes_link_generic(struct e1000_hw *hw)
 	 * milliseconds even if the other end is doing it in SW).
 	 */
 	for (i = 0; i < FIBER_LINK_UP_LIMIT; i++) {
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 		status = er32(STATUS);
 		if (status & E1000_STATUS_LU)
 			break;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 189f231075c2..e4baa13b3cda 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1780,7 +1780,8 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data)
 		}
 		/* guard against interrupt when we're going down */
 		if (!test_bit(__E1000_DOWN, &adapter->state))
-			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+			queue_delayed_work(adapter->e1000_workqueue,
+					   &adapter->watchdog_task, 1);
 	}
 
 	/* Reset on uncorrectable ECC error */
@@ -1860,7 +1861,8 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data)
 		}
 		/* guard against interrupt when we're going down */
 		if (!test_bit(__E1000_DOWN, &adapter->state))
-			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+			queue_delayed_work(adapter->e1000_workqueue,
+					   &adapter->watchdog_task, 1);
 	}
 
 	/* Reset on uncorrectable ECC error */
@@ -1905,7 +1907,8 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data)
 		hw->mac.get_link_status = true;
 		/* guard against interrupt when we're going down */
 		if (!test_bit(__E1000_DOWN, &adapter->state))
-			mod_timer(&adapter->watchdog_timer, jiffies + 1);
+			queue_delayed_work(adapter->e1000_workqueue,
+					   &adapter->watchdog_task, 1);
 	}
 
 	if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -2106,7 +2109,7 @@ static int e1000_request_msix(struct e1000_adapter *adapter)
 	if (strlen(netdev->name) < (IFNAMSIZ - 5))
 		snprintf(adapter->rx_ring->name,
 			 sizeof(adapter->rx_ring->name) - 1,
-			 "%s-rx-0", netdev->name);
+			 "%.14s-rx-0", netdev->name);
 	else
 		memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ);
 	err = request_irq(adapter->msix_entries[vector].vector,
@@ -2122,7 +2125,7 @@ static int e1000_request_msix(struct e1000_adapter *adapter)
 	if (strlen(netdev->name) < (IFNAMSIZ - 5))
 		snprintf(adapter->tx_ring->name,
 			 sizeof(adapter->tx_ring->name) - 1,
-			 "%s-tx-0", netdev->name);
+			 "%.14s-tx-0", netdev->name);
 	else
 		memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ);
 	err = request_irq(adapter->msix_entries[vector].vector,
@@ -3208,7 +3211,7 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 	if (!(adapter->flags2 & FLAG2_NO_DISABLE_RX))
 		ew32(RCTL, rctl & ~E1000_RCTL_EN);
 	e1e_flush();
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	if (adapter->flags2 & FLAG2_DMA_BURST) {
 		/* set the writeback threshold (only takes effect if the RDTR
@@ -3816,7 +3819,6 @@ static void e1000_flush_tx_ring(struct e1000_adapter *adapter)
 	if (tx_ring->next_to_use == tx_ring->count)
 		tx_ring->next_to_use = 0;
 	ew32(TDT(0), tx_ring->next_to_use);
-	mmiowb();
 	usleep_range(200, 250);
 }
 
@@ -4047,12 +4049,12 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	case e1000_pch_lpt:
 	case e1000_pch_spt:
 	case e1000_pch_cnp:
-		fc->refresh_time = 0x0400;
+		fc->refresh_time = 0xFFFF;
+		fc->pause_time = 0xFFFF;
 
 		if (adapter->netdev->mtu <= ETH_DATA_LEN) {
 			fc->high_water = 0x05C20;
 			fc->low_water = 0x05048;
-			fc->pause_time = 0x0650;
 			break;
 		}
 
@@ -4209,7 +4211,7 @@ void e1000e_up(struct e1000_adapter *adapter)
 		e1000_configure_msix(adapter);
 	e1000_irq_enable(adapter);
 
-	netif_start_queue(adapter->netdev);
+	/* Tx queue started by watchdog timer when link is up */
 
 	e1000e_trigger_lsc(adapter);
 }
@@ -4273,13 +4275,12 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
 
 	/* flush both disables and wait for them to finish */
 	e1e_flush();
-	usleep_range(10000, 20000);
+	usleep_range(10000, 11000);
 
 	e1000_irq_disable(adapter);
 
 	napi_synchronize(&adapter->napi);
 
-	del_timer_sync(&adapter->watchdog_timer);
 	del_timer_sync(&adapter->phy_info_timer);
 
 	spin_lock(&adapter->stats64_lock);
@@ -4311,7 +4312,7 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter)
 {
 	might_sleep();
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
-		usleep_range(1000, 2000);
+		usleep_range(1000, 1100);
 	e1000e_down(adapter, true);
 	e1000e_up(adapter);
 	clear_bit(__E1000_RESETTING, &adapter->state);
@@ -4607,6 +4608,7 @@ int e1000e_open(struct net_device *netdev)
 	pm_runtime_get_sync(&pdev->dev);
 
 	netif_carrier_off(netdev);
+	netif_stop_queue(netdev);
 
 	/* allocate transmit descriptors */
 	err = e1000e_setup_tx_resources(adapter->tx_ring);
@@ -4667,7 +4669,6 @@ int e1000e_open(struct net_device *netdev)
 	e1000_irq_enable(adapter);
 
 	adapter->tx_hang_recheck = false;
-	netif_start_queue(netdev);
 
 	hw->mac.get_link_status = true;
 	pm_runtime_put(&pdev->dev);
@@ -4708,7 +4709,7 @@ int e1000e_close(struct net_device *netdev)
 	int count = E1000_CHECK_RESET_COUNT;
 
 	while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 
 	WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 
@@ -5151,31 +5152,18 @@ static void e1000e_check_82574_phy_workaround(struct e1000_adapter *adapter)
 	}
 }
 
-/**
- * e1000_watchdog - Timer Call-back
- * @data: pointer to adapter cast into an unsigned long
- **/
-static void e1000_watchdog(struct timer_list *t)
-{
-	struct e1000_adapter *adapter = from_timer(adapter, t, watchdog_timer);
-
-	/* Do the rest outside of interrupt context */
-	schedule_work(&adapter->watchdog_task);
-
-	/* TODO: make this use queue_delayed_work() */
-}
-
 static void e1000_watchdog_task(struct work_struct *work)
 {
 	struct e1000_adapter *adapter = container_of(work,
 						     struct e1000_adapter,
-						     watchdog_task);
+						     watchdog_task.work);
 	struct net_device *netdev = adapter->netdev;
 	struct e1000_mac_info *mac = &adapter->hw.mac;
 	struct e1000_phy_info *phy = &adapter->hw.phy;
 	struct e1000_ring *tx_ring = adapter->tx_ring;
+	u32 dmoff_exit_timeout = 100, tries = 0;
 	struct e1000_hw *hw = &adapter->hw;
-	u32 link, tctl;
+	u32 link, tctl, pcim_state;
 
 	if (test_bit(__E1000_DOWN, &adapter->state))
 		return;
@@ -5200,6 +5188,21 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* Cancel scheduled suspend requests. */
 			pm_runtime_resume(netdev->dev.parent);
 
+			/* Checking if MAC is in DMoff state*/
+			pcim_state = er32(STATUS);
+			while (pcim_state & E1000_STATUS_PCIM_STATE) {
+				if (tries++ == dmoff_exit_timeout) {
+					e_dbg("Error in exiting dmoff\n");
+					break;
+				}
+				usleep_range(10000, 20000);
+				pcim_state = er32(STATUS);
+
+				/* Checking if MAC exited DMoff state */
+				if (!(pcim_state & E1000_STATUS_PCIM_STATE))
+					e1000_phy_hw_reset(&adapter->hw);
+			}
+
 			/* update snapshot of PHY registers on LSC */
 			e1000_phy_read_status(adapter);
 			mac->ops.get_link_up_info(&adapter->hw,
@@ -5289,6 +5292,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			if (phy->ops.cfg_on_link_up)
 				phy->ops.cfg_on_link_up(hw);
 
+			netif_wake_queue(netdev);
 			netif_carrier_on(netdev);
 
 			if (!test_bit(__E1000_DOWN, &adapter->state))
@@ -5302,6 +5306,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* Link status message must follow this format */
 			pr_info("%s NIC Link is Down\n", adapter->netdev->name);
 			netif_carrier_off(netdev);
+			netif_stop_queue(netdev);
 			if (!test_bit(__E1000_DOWN, &adapter->state))
 				mod_timer(&adapter->phy_info_timer,
 					  round_jiffies(jiffies + 2 * HZ));
@@ -5399,8 +5404,9 @@ link_up:
 
 	/* Reset the timer */
 	if (!test_bit(__E1000_DOWN, &adapter->state))
-		mod_timer(&adapter->watchdog_timer,
-			  round_jiffies(jiffies + 2 * HZ));
+		queue_delayed_work(adapter->e1000_workqueue,
+				   &adapter->watchdog_task,
+				   round_jiffies(2 * HZ));
 }
 
 #define E1000_TX_FLAGS_CSUM		0x00000001
@@ -5900,19 +5906,13 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				     DIV_ROUND_UP(PAGE_SIZE,
 						  adapter->tx_fifo_limit) + 2));
 
-		if (!skb->xmit_more ||
+		if (!netdev_xmit_more() ||
 		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
 			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
 				e1000e_update_tdt_wa(tx_ring,
 						     tx_ring->next_to_use);
 			else
 				writel(tx_ring->next_to_use, tx_ring->tail);
-
-			/* we need this if more than one processor can write
-			 * to our tail at a time, it synchronizes IO on
-			 *IA64/Altix systems
-			 */
-			mmiowb();
 		}
 	} else {
 		dev_kfree_skb_any(skb);
@@ -6026,7 +6026,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	}
 
 	while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
-		usleep_range(1000, 2000);
+		usleep_range(1000, 1100);
 	/* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */
 	adapter->max_frame_size = max_frame;
 	e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu);
@@ -6306,7 +6306,7 @@ static int e1000e_pm_freeze(struct device *dev)
 		int count = E1000_CHECK_RESET_COUNT;
 
 		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 
 		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 
@@ -6721,7 +6721,7 @@ static int e1000e_pm_runtime_suspend(struct device *dev)
 		int count = E1000_CHECK_RESET_COUNT;
 
 		while (test_bit(__E1000_RESETTING, &adapter->state) && count--)
-			usleep_range(10000, 20000);
+			usleep_range(10000, 11000);
 
 		WARN_ON(test_bit(__E1000_RESETTING, &adapter->state));
 
@@ -7006,7 +7006,7 @@ static int e1000_set_features(struct net_device *netdev,
 	else
 		e1000e_reset(adapter);
 
-	return 0;
+	return 1;
 }
 
 static const struct net_device_ops e1000e_netdev_ops = {
@@ -7261,11 +7261,21 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_eeprom;
 	}
 
-	timer_setup(&adapter->watchdog_timer, e1000_watchdog, 0);
+	adapter->e1000_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+						   e1000e_driver_name);
+
+	if (!adapter->e1000_workqueue) {
+		err = -ENOMEM;
+		goto err_workqueue;
+	}
+
+	INIT_DELAYED_WORK(&adapter->watchdog_task, e1000_watchdog_task);
+	queue_delayed_work(adapter->e1000_workqueue, &adapter->watchdog_task,
+			   0);
+
 	timer_setup(&adapter->phy_info_timer, e1000_update_phy_info, 0);
 
 	INIT_WORK(&adapter->reset_task, e1000_reset_task);
-	INIT_WORK(&adapter->watchdog_task, e1000_watchdog_task);
 	INIT_WORK(&adapter->downshift_task, e1000e_downshift_workaround);
 	INIT_WORK(&adapter->update_phy_task, e1000e_update_phy_task);
 	INIT_WORK(&adapter->print_hang_task, e1000_print_hw_hang);
@@ -7351,12 +7361,17 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	e1000_print_device_info(adapter);
 
-	if (pci_dev_run_wake(pdev))
+	dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP);
+
+	if (pci_dev_run_wake(pdev) && hw->mac.type < e1000_pch_cnp)
 		pm_runtime_put_noidle(&pdev->dev);
 
 	return 0;
 
 err_register:
+	flush_workqueue(adapter->e1000_workqueue);
+	destroy_workqueue(adapter->e1000_workqueue);
+err_workqueue:
 	if (!(adapter->flags & FLAG_HAS_AMT))
 		e1000e_release_hw_control(adapter);
 err_eeprom:
@@ -7403,15 +7418,17 @@ static void e1000_remove(struct pci_dev *pdev)
 	 */
 	if (!down)
 		set_bit(__E1000_DOWN, &adapter->state);
-	del_timer_sync(&adapter->watchdog_timer);
 	del_timer_sync(&adapter->phy_info_timer);
 
 	cancel_work_sync(&adapter->reset_task);
-	cancel_work_sync(&adapter->watchdog_task);
 	cancel_work_sync(&adapter->downshift_task);
 	cancel_work_sync(&adapter->update_phy_task);
 	cancel_work_sync(&adapter->print_hang_task);
 
+	cancel_delayed_work(&adapter->watchdog_task);
+	flush_workqueue(adapter->e1000_workqueue);
+	destroy_workqueue(adapter->e1000_workqueue);
+
 	if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) {
 		cancel_work_sync(&adapter->tx_hwtstamp_work);
 		if (adapter->tx_hwtstamp_skb) {
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c
index 937f9af22d26..e609f4df86f4 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.c
+++ b/drivers/net/ethernet/intel/e1000e/nvm.c
@@ -392,7 +392,7 @@ s32 e1000e_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data)
 				break;
 			}
 		}
-		usleep_range(10000, 20000);
+		usleep_range(10000, 11000);
 		nvm->ops.release(hw);
 	}
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
index 5d4f1761dc0c..8de77155f2e7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -321,8 +321,6 @@ static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask);
 	err_mask |= PCI_ERR_UNC_COMP_ABORT;
 	pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask);
-
-	mmiowb();
 }
 
 int fm10k_iov_resume(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 6fd15a734324..90270b4a1682 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -41,6 +41,8 @@ static int __init fm10k_init_module(void)
 	/* create driver workqueue */
 	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
 					  fm10k_driver_name);
+	if (!fm10k_workqueue)
+		return -ENOMEM;
 
 	fm10k_dbg_init();
 
@@ -278,7 +280,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
 	/* we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN);
+	pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
@@ -1035,13 +1037,8 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 	fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
@@ -1603,14 +1600,12 @@ static int fm10k_alloc_q_vector(struct fm10k_intfc *interface,
 {
 	struct fm10k_q_vector *q_vector;
 	struct fm10k_ring *ring;
-	int ring_count, size;
+	int ring_count;
 
 	ring_count = txr_count + rxr_count;
-	size = sizeof(struct fm10k_q_vector) +
-	       (sizeof(struct fm10k_ring) * ring_count);
 
 	/* allocate q_vector and rings */
-	q_vector = kzalloc(size, GFP_KERNEL);
+	q_vector = kzalloc(struct_size(q_vector, ring, ring_count), GFP_KERNEL);
 	if (!q_vector)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 8f0a99b6a537..cb4d02629b86 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1148,7 +1148,7 @@ static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw,
  *  @results: Pointer array to message, results[0] is pointer to message
  *  @mbx: Pointer to mailbox information structure
  *
- *  This function is a default handler for MSI-X requests from the VF.  The
+ *  This function is a default handler for MSI-X requests from the VF. The
  *  assumption is that in this case it is acceptable to just directly
  *  hand off the message from the VF to the underlying shared code.
  **/
diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile
index 50590e8d1fd1..2f21b3e89fd0 100644
--- a/drivers/net/ethernet/intel/i40e/Makefile
+++ b/drivers/net/ethernet/intel/i40e/Makefile
@@ -21,6 +21,7 @@ i40e-objs := i40e_main.o \
 	i40e_diag.o	\
 	i40e_txrx.o	\
 	i40e_ptp.o	\
+	i40e_ddp.o \
 	i40e_client.o   \
 	i40e_virtchnl_pf.o \
 	i40e_xsk.o
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 8de9085bba9e..84bd06901014 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -27,6 +27,7 @@
 #include <net/ip6_checksum.h>
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
+#include <linux/if_macvlan.h>
 #include <linux/if_bridge.h>
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
@@ -34,6 +35,7 @@
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/xdp_sock.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
 #include "i40e_client.h"
@@ -148,6 +150,7 @@ enum i40e_state_t {
 	__I40E_CLIENT_L2_CHANGE,
 	__I40E_CLIENT_RESET,
 	__I40E_VIRTCHNL_OP_PENDING,
+	__I40E_RECOVERY_MODE,
 	/* This must be last as it determines the size of the BITMAP */
 	__I40E_STATE_SIZE__,
 };
@@ -293,8 +296,6 @@ struct i40e_cloud_filter {
 	u8 tunnel_type;
 };
 
-#define I40E_ETH_P_LLDP			0x88cc
-
 #define I40E_DCB_PRIO_TYPE_STRICT	0
 #define I40E_DCB_PRIO_TYPE_ETS		1
 #define I40E_DCB_STRICT_PRIO_CREDITS	127
@@ -320,6 +321,29 @@ struct i40e_udp_port_config {
 	u8 filter_index;
 };
 
+#define I40_DDP_FLASH_REGION 100
+#define I40E_PROFILE_INFO_SIZE 48
+#define I40E_MAX_PROFILE_NUM 16
+#define I40E_PROFILE_LIST_SIZE \
+	(I40E_PROFILE_INFO_SIZE * I40E_MAX_PROFILE_NUM + 4)
+#define I40E_DDP_PROFILE_PATH "intel/i40e/ddp/"
+#define I40E_DDP_PROFILE_NAME_MAX 64
+
+int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
+		  bool is_add);
+int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash);
+
+struct i40e_ddp_profile_list {
+	u32 p_count;
+	struct i40e_profile_info p_info[0];
+};
+
+struct i40e_ddp_old_profile_list {
+	struct list_head list;
+	size_t old_ddp_size;
+	u8 old_ddp_buf[0];
+};
+
 /* macros related to FLX_PIT */
 #define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \
 				    I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \
@@ -389,6 +413,11 @@ struct i40e_flex_pit {
 	u8 pit_index;
 };
 
+struct i40e_fwd_adapter {
+	struct net_device *netdev;
+	int bit_no;
+};
+
 struct i40e_channel {
 	struct list_head list;
 	bool initialized;
@@ -403,11 +432,25 @@ struct i40e_channel {
 	struct i40e_aqc_vsi_properties_data info;
 
 	u64 max_tx_rate;
+	struct i40e_fwd_adapter *fwd;
 
 	/* track this channel belongs to which VSI */
 	struct i40e_vsi *parent_vsi;
 };
 
+static inline bool i40e_is_channel_macvlan(struct i40e_channel *ch)
+{
+	return !!ch->fwd;
+}
+
+static inline u8 *i40e_channel_mac(struct i40e_channel *ch)
+{
+	if (i40e_is_channel_macvlan(ch))
+		return ch->fwd->netdev->dev_addr;
+	else
+		return NULL;
+}
+
 /* struct that defines the Ethernet device */
 struct i40e_pf {
 	struct pci_dev *pdev;
@@ -523,6 +566,8 @@ struct i40e_pf {
 #define I40E_FLAG_FD_SB_INACTIVE		BIT(22)
 #define I40E_FLAG_FD_SB_TO_CLOUD_FILTER		BIT(23)
 #define I40E_FLAG_DISABLE_FW_LLDP		BIT(24)
+#define I40E_FLAG_RS_FEC			BIT(25)
+#define I40E_FLAG_BASE_R_FEC			BIT(26)
 
 	struct i40e_client_instance *cinst;
 	bool stat_offsets_loaded;
@@ -586,6 +631,8 @@ struct i40e_pf {
 	struct sk_buff *ptp_tx_skb;
 	unsigned long ptp_tx_start;
 	struct hwtstamp_config tstamp_config;
+	struct timespec64 ptp_prev_hw_time;
+	ktime_t ptp_reset_start;
 	struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */
 	u32 ptp_adj_mult;
 	u32 tx_hwtstamp_timeouts;
@@ -607,6 +654,8 @@ struct i40e_pf {
 	u16 override_q_count;
 	u16 last_sw_conf_flags;
 	u16 last_sw_conf_valid_flags;
+	/* List to keep previous DDP profiles to be rolled back in the future */
+	struct list_head ddp_old_prof;
 };
 
 /**
@@ -746,7 +795,8 @@ struct i40e_vsi {
 	u16 alloc_queue_pairs;	/* Allocated Tx/Rx queues */
 	u16 req_queue_pairs;	/* User requested queue pairs */
 	u16 num_queue_pairs;	/* Used tx and rx pairs */
-	u16 num_desc;
+	u16 num_tx_desc;
+	u16 num_rx_desc;
 	enum i40e_vsi_type type;  /* VSI type, e.g., LAN, FCoE, etc */
 	s16 vf_id;		/* Virtual function ID for SRIOV VSIs */
 
@@ -783,15 +833,19 @@ struct i40e_vsi {
 	struct list_head ch_list;
 	u16 tc_seid_map[I40E_MAX_TRAFFIC_CLASS];
 
+	/* macvlan fields */
+#define I40E_MAX_MACVLANS		128 /* Max HW vectors - 1 on FVL */
+#define I40E_MIN_MACVLAN_VECTORS	2   /* Min vectors to enable macvlans */
+	DECLARE_BITMAP(fwd_bitmask, I40E_MAX_MACVLANS);
+	struct list_head macvlan_list;
+	int macvlan_cnt;
+
 	void *priv;	/* client driver data reference. */
 
 	/* VSI specific handlers */
 	irqreturn_t (*irq_handler)(int irq, void *data);
 
-	/* AF_XDP zero-copy */
-	struct xdp_umem **xsk_umems;
-	u16 num_xsk_umems_used;
-	u16 num_xsk_umems;
+	unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */
 } ____cacheline_internodealigned_in_smp;
 
 struct i40e_netdev_priv {
@@ -1083,6 +1137,8 @@ void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index);
 void i40e_ptp_set_increment(struct i40e_pf *pf);
 int i40e_ptp_set_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
 int i40e_ptp_get_ts_config(struct i40e_pf *pf, struct ifreq *ifr);
+void i40e_ptp_save_hw_time(struct i40e_pf *pf);
+void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
 void i40e_ptp_init(struct i40e_pf *pf);
 void i40e_ptp_stop(struct i40e_pf *pf);
 int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
@@ -1091,25 +1147,13 @@ i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf);
 i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf);
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
 
+void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags);
+
 static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
 {
 	return !!vsi->xdp_prog;
 }
 
-static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
-{
-	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
-	int qid = ring->queue_index;
-
-	if (ring_is_xdp(ring))
-		qid -= ring->vsi->alloc_queue_pairs;
-
-	if (!ring->vsi->xsk_umems || !ring->vsi->xsk_umems[qid] || !xdp_on)
-		return NULL;
-
-	return ring->vsi->xsk_umems[qid];
-}
-
 int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch);
 int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate);
 int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 7ab61f6ebb5f..814acbe79ffd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -608,6 +608,11 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw)
 	     hw->aq.api_min_ver >= 7))
 		hw->flags |= I40E_HW_FLAG_802_1AD_CAPABLE;
 
+	if (hw->aq.api_maj_ver > 1 ||
+	    (hw->aq.api_maj_ver == 1 &&
+	     hw->aq.api_min_ver >= 8))
+		hw->flags |= I40E_HW_FLAG_FW_LLDP_PERSISTENT;
+
 	if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
 		ret_code = I40E_ERR_FIRMWARE_API_VERSION;
 		goto init_adminq_free_arq;
@@ -670,7 +675,7 @@ static u16 i40e_clean_asq(struct i40e_hw *hw)
 	desc = I40E_ADMINQ_DESC(*asq, ntc);
 	details = I40E_ADMINQ_DETAILS(*asq, ntc);
 	while (rd32(hw, hw->aq.asq.head) != ntc) {
-		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+		i40e_debug(hw, I40E_DEBUG_AQ_COMMAND,
 			   "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
 
 		if (details->callback) {
@@ -749,7 +754,7 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 	if (val >= hw->aq.num_asq_entries) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
 			   "AQTX: head overrun at %d\n", val);
-		status = I40E_ERR_QUEUE_EMPTY;
+		status = I40E_ERR_ADMIN_QUEUE_FULL;
 		goto asq_send_command_error;
 	}
 
@@ -830,7 +835,7 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 	}
 
 	/* bump the tail */
-	i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n");
+	i40e_debug(hw, I40E_DEBUG_AQ_COMMAND, "AQTX: desc and buffer:\n");
 	i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc_on_ring,
 		      buff, buff_size);
 	(hw->aq.asq.next_to_use)++;
@@ -881,7 +886,7 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
 	}
 
-	i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+	i40e_debug(hw, I40E_DEBUG_AQ_COMMAND,
 		   "AQTX: desc and buffer writeback:\n");
 	i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size);
 
@@ -990,7 +995,7 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
 		memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
 		       e->msg_len);
 
-	i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n");
+	i40e_debug(hw, I40E_DEBUG_AQ_COMMAND, "AQRX: desc and buffer:\n");
 	i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf,
 		      hw->aq.arq_buf_size);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 11506102471c..6536023fa074 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -11,8 +11,8 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR	0x0001
-#define I40E_FW_API_VERSION_MINOR_X722	0x0006
-#define I40E_FW_API_VERSION_MINOR_X710	0x0007
+#define I40E_FW_API_VERSION_MINOR_X722	0x0008
+#define I40E_FW_API_VERSION_MINOR_X710	0x0008
 
 #define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
 					I40E_FW_API_VERSION_MINOR_X710 : \
@@ -261,6 +261,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_get_cee_dcb_cfg	= 0x0A07,
 	i40e_aqc_opc_lldp_set_local_mib	= 0x0A08,
 	i40e_aqc_opc_lldp_stop_start_spec_agent	= 0x0A09,
+	i40e_aqc_opc_lldp_restore		= 0x0A0A,
 
 	/* Tunnel commands */
 	i40e_aqc_opc_add_udp_tunnel	= 0x0B00,
@@ -1887,6 +1888,8 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_25GBASE_LR		= 0x22,
 	I40E_PHY_TYPE_25GBASE_AOC		= 0x23,
 	I40E_PHY_TYPE_25GBASE_ACC		= 0x24,
+	I40E_PHY_TYPE_2_5GBASE_T		= 0x30,
+	I40E_PHY_TYPE_5GBASE_T			= 0x31,
 	I40E_PHY_TYPE_MAX,
 	I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP	= 0xFD,
 	I40E_PHY_TYPE_EMPTY			= 0xFE,
@@ -1928,19 +1931,25 @@ enum i40e_aq_phy_type {
 				BIT_ULL(I40E_PHY_TYPE_25GBASE_SR) | \
 				BIT_ULL(I40E_PHY_TYPE_25GBASE_LR) | \
 				BIT_ULL(I40E_PHY_TYPE_25GBASE_AOC) | \
-				BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC))
+				BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC) | \
+				BIT_ULL(I40E_PHY_TYPE_2_5GBASE_T) | \
+				BIT_ULL(I40E_PHY_TYPE_5GBASE_T))
 
+#define I40E_LINK_SPEED_2_5GB_SHIFT	0x0
 #define I40E_LINK_SPEED_100MB_SHIFT	0x1
 #define I40E_LINK_SPEED_1000MB_SHIFT	0x2
 #define I40E_LINK_SPEED_10GB_SHIFT	0x3
 #define I40E_LINK_SPEED_40GB_SHIFT	0x4
 #define I40E_LINK_SPEED_20GB_SHIFT	0x5
 #define I40E_LINK_SPEED_25GB_SHIFT	0x6
+#define I40E_LINK_SPEED_5GB_SHIFT	0x7
 
 enum i40e_aq_link_speed {
 	I40E_LINK_SPEED_UNKNOWN	= 0,
 	I40E_LINK_SPEED_100MB	= BIT(I40E_LINK_SPEED_100MB_SHIFT),
 	I40E_LINK_SPEED_1GB	= BIT(I40E_LINK_SPEED_1000MB_SHIFT),
+	I40E_LINK_SPEED_2_5GB	= (1 << I40E_LINK_SPEED_2_5GB_SHIFT),
+	I40E_LINK_SPEED_5GB	= (1 << I40E_LINK_SPEED_5GB_SHIFT),
 	I40E_LINK_SPEED_10GB	= BIT(I40E_LINK_SPEED_10GB_SHIFT),
 	I40E_LINK_SPEED_40GB	= BIT(I40E_LINK_SPEED_40GB_SHIFT),
 	I40E_LINK_SPEED_20GB	= BIT(I40E_LINK_SPEED_20GB_SHIFT),
@@ -1986,6 +1995,8 @@ struct i40e_aq_get_phy_abilities_resp {
 #define I40E_AQ_PHY_TYPE_EXT_25G_LR	0x08
 #define I40E_AQ_PHY_TYPE_EXT_25G_AOC	0x10
 #define I40E_AQ_PHY_TYPE_EXT_25G_ACC	0x20
+#define I40E_AQ_PHY_TYPE_EXT_2_5GBASE_T	0x40
+#define I40E_AQ_PHY_TYPE_EXT_5GBASE_T	0x80
 	u8	fec_cfg_curr_mod_ext_info;
 #define I40E_AQ_ENABLE_FEC_KR		0x01
 #define I40E_AQ_ENABLE_FEC_RS		0x02
@@ -2498,18 +2509,19 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_tlv);
 /* Stop LLDP (direct 0x0A05) */
 struct i40e_aqc_lldp_stop {
 	u8	command;
-#define I40E_AQ_LLDP_AGENT_STOP		0x0
-#define I40E_AQ_LLDP_AGENT_SHUTDOWN	0x1
+#define I40E_AQ_LLDP_AGENT_STOP			0x0
+#define I40E_AQ_LLDP_AGENT_SHUTDOWN		0x1
+#define I40E_AQ_LLDP_AGENT_STOP_PERSIST		0x2
 	u8	reserved[15];
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop);
 
 /* Start LLDP (direct 0x0A06) */
-
 struct i40e_aqc_lldp_start {
 	u8	command;
-#define I40E_AQ_LLDP_AGENT_START	0x1
+#define I40E_AQ_LLDP_AGENT_START		0x1
+#define I40E_AQ_LLDP_AGENT_START_PERSIST	0x2
 	u8	reserved[15];
 };
 
@@ -2633,6 +2645,16 @@ struct i40e_aqc_lldp_stop_start_specific_agent {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop_start_specific_agent);
 
+/* Restore LLDP Agent factory settings (direct 0x0A0A) */
+struct i40e_aqc_lldp_restore {
+	u8	command;
+#define I40E_AQ_LLDP_AGENT_RESTORE_NOT		0x0
+#define I40E_AQ_LLDP_AGENT_RESTORE		0x1
+	u8	reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_restore);
+
 /* Add Udp Tunnel command and completion (direct 0x0B00) */
 struct i40e_aqc_add_udp_tunnel {
 	__le16	udp_port;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 5f3b8b9ff511..e81530ca08d0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -578,11 +578,9 @@ static int i40e_client_setup_qvlist(struct i40e_info *ldev,
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_qv_info *qv_info;
 	u32 v_idx, i, reg_idx, reg;
-	u32 size;
 
-	size = sizeof(struct i40e_qvlist_info) +
-	       (sizeof(struct i40e_qv_info) * (qvlist_info->num_vectors - 1));
-	ldev->qvlist_info = kzalloc(size, GFP_KERNEL);
+	ldev->qvlist_info = kzalloc(struct_size(ldev->qvlist_info, qv_info,
+				    qvlist_info->num_vectors - 1), GFP_KERNEL);
 	if (!ldev->qvlist_info)
 		return -ENOMEM;
 	ldev->qvlist_info->num_vectors = qvlist_info->num_vectors;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 97a9b1fb4763..906cf68d3453 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -28,10 +28,14 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw)
 		case I40E_DEV_ID_QSFP_C:
 		case I40E_DEV_ID_10G_BASE_T:
 		case I40E_DEV_ID_10G_BASE_T4:
+		case I40E_DEV_ID_10G_B:
+		case I40E_DEV_ID_10G_SFP:
 		case I40E_DEV_ID_20G_KR2:
 		case I40E_DEV_ID_20G_KR2_A:
 		case I40E_DEV_ID_25G_B:
 		case I40E_DEV_ID_25G_SFP28:
+		case I40E_DEV_ID_X710_N3000:
+		case I40E_DEV_ID_XXV710_N3000:
 			hw->mac.type = I40E_MAC_XL710;
 			break;
 		case I40E_DEV_ID_KX_X722:
@@ -277,47 +281,49 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 		   void *buffer, u16 buf_len)
 {
 	struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
+	u32 effective_mask = hw->debug_mask & mask;
+	char prefix[27];
 	u16 len;
 	u8 *buf = (u8 *)buffer;
 
-	if ((!(mask & hw->debug_mask)) || (desc == NULL))
+	if (!effective_mask || !desc)
 		return;
 
 	len = le16_to_cpu(aq_desc->datalen);
 
-	i40e_debug(hw, mask,
+	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
 		   "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
 		   le16_to_cpu(aq_desc->opcode),
 		   le16_to_cpu(aq_desc->flags),
 		   le16_to_cpu(aq_desc->datalen),
 		   le16_to_cpu(aq_desc->retval));
-	i40e_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n",
+	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
+		   "\tcookie (h,l) 0x%08X 0x%08X\n",
 		   le32_to_cpu(aq_desc->cookie_high),
 		   le32_to_cpu(aq_desc->cookie_low));
-	i40e_debug(hw, mask, "\tparam (0,1)  0x%08X 0x%08X\n",
+	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
+		   "\tparam (0,1)  0x%08X 0x%08X\n",
 		   le32_to_cpu(aq_desc->params.internal.param0),
 		   le32_to_cpu(aq_desc->params.internal.param1));
-	i40e_debug(hw, mask, "\taddr (h,l)   0x%08X 0x%08X\n",
+	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
+		   "\taddr (h,l)   0x%08X 0x%08X\n",
 		   le32_to_cpu(aq_desc->params.external.addr_high),
 		   le32_to_cpu(aq_desc->params.external.addr_low));
 
-	if ((buffer != NULL) && (aq_desc->datalen != 0)) {
+	if (buffer && buf_len != 0 && len != 0 &&
+	    (effective_mask & I40E_DEBUG_AQ_DESC_BUFFER)) {
 		i40e_debug(hw, mask, "AQ CMD Buffer:\n");
 		if (buf_len < len)
 			len = buf_len;
-		/* write the full 16-byte chunks */
-		if (hw->debug_mask & mask) {
-			char prefix[27];
-
-			snprintf(prefix, sizeof(prefix),
-				 "i40e %02x:%02x.%x: \t0x",
-				 hw->bus.bus_id,
-				 hw->bus.device,
-				 hw->bus.func);
-
-			print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET,
-				       16, 1, buf, len, false);
-		}
+
+		snprintf(prefix, sizeof(prefix),
+			 "i40e %02x:%02x.%x: \t0x",
+			 hw->bus.bus_id,
+			 hw->bus.device,
+			 hw->bus.func);
+
+		print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET,
+			       16, 1, buf, len, false);
 	}
 }
 
@@ -1149,6 +1155,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw)
 		break;
 	case I40E_PHY_TYPE_100BASE_TX:
 	case I40E_PHY_TYPE_1000BASE_T:
+	case I40E_PHY_TYPE_2_5GBASE_T:
+	case I40E_PHY_TYPE_5GBASE_T:
 	case I40E_PHY_TYPE_10GBASE_T:
 		media = I40E_MEDIA_TYPE_BASET;
 		break;
@@ -1466,7 +1474,6 @@ static u32 i40e_led_is_mine(struct i40e_hw *hw, int idx)
  **/
 u32 i40e_led_get(struct i40e_hw *hw)
 {
-	u32 current_mode = 0;
 	u32 mode = 0;
 	int i;
 
@@ -1479,21 +1486,6 @@ u32 i40e_led_get(struct i40e_hw *hw)
 		if (!gpio_val)
 			continue;
 
-		/* ignore gpio LED src mode entries related to the activity
-		 * LEDs
-		 */
-		current_mode = ((gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK)
-				>> I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT);
-		switch (current_mode) {
-		case I40E_COMBINED_ACTIVITY:
-		case I40E_FILTER_ACTIVITY:
-		case I40E_MAC_ACTIVITY:
-		case I40E_LINK_ACTIVITY:
-			continue;
-		default:
-			break;
-		}
-
 		mode = (gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK) >>
 			I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT;
 		break;
@@ -1513,7 +1505,6 @@ u32 i40e_led_get(struct i40e_hw *hw)
  **/
 void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink)
 {
-	u32 current_mode = 0;
 	int i;
 
 	if (mode & 0xfffffff0)
@@ -1527,22 +1518,6 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink)
 
 		if (!gpio_val)
 			continue;
-
-		/* ignore gpio LED src mode entries related to the activity
-		 * LEDs
-		 */
-		current_mode = ((gpio_val & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK)
-				>> I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT);
-		switch (current_mode) {
-		case I40E_COMBINED_ACTIVITY:
-		case I40E_FILTER_ACTIVITY:
-		case I40E_MAC_ACTIVITY:
-		case I40E_LINK_ACTIVITY:
-			continue;
-		default:
-			break;
-		}
-
 		gpio_val &= ~I40E_GLGEN_GPIO_CTL_LED_MODE_MASK;
 		/* this & is a bit of paranoia, but serves as a range check */
 		gpio_val |= ((mode << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT) &
@@ -1886,8 +1861,7 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
 	     hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE)
 		hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU;
 
-	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
-	    hw->aq.api_min_ver >= 7) {
+	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
 		__le32 tmp;
 
 		memcpy(&tmp, resp->link_type, sizeof(tmp));
@@ -3657,14 +3631,54 @@ i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 }
 
 /**
+ * i40e_aq_restore_lldp
+ * @hw: pointer to the hw struct
+ * @setting: pointer to factory setting variable or NULL
+ * @restore: True if factory settings should be restored
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Restore LLDP Agent factory settings if @restore set to True. In other case
+ * only returns factory setting in AQ response.
+ **/
+enum i40e_status_code
+i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
+		     struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_lldp_restore *cmd =
+		(struct i40e_aqc_lldp_restore *)&desc.params.raw;
+	i40e_status status;
+
+	if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)) {
+		i40e_debug(hw, I40E_DEBUG_ALL,
+			   "Restore LLDP not supported by current FW version.\n");
+		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+	}
+
+	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_restore);
+
+	if (restore)
+		cmd->command |= I40E_AQ_LLDP_AGENT_RESTORE;
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	if (setting)
+		*setting = cmd->command & 1;
+
+	return status;
+}
+
+/**
  * i40e_aq_stop_lldp
  * @hw: pointer to the hw struct
  * @shutdown_agent: True if LLDP Agent needs to be Shutdown
+ * @persist: True if stop of LLDP should be persistent across power cycles
  * @cmd_details: pointer to command details structure or NULL
  *
  * Stop or Shutdown the embedded LLDP Agent
  **/
 i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
+				bool persist,
 				struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aq_desc desc;
@@ -3677,6 +3691,14 @@ i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 	if (shutdown_agent)
 		cmd->command |= I40E_AQ_LLDP_AGENT_SHUTDOWN;
 
+	if (persist) {
+		if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)
+			cmd->command |= I40E_AQ_LLDP_AGENT_STOP_PERSIST;
+		else
+			i40e_debug(hw, I40E_DEBUG_ALL,
+				   "Persistent Stop LLDP not supported by current FW version.\n");
+	}
+
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
 
 	return status;
@@ -3686,13 +3708,14 @@ i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
  * i40e_aq_start_lldp
  * @hw: pointer to the hw struct
  * @buff: buffer for result
+ * @persist: True if start of LLDP should be persistent across power cycles
  * @buff_size: buffer size
  * @cmd_details: pointer to command details structure or NULL
  *
  * Start the embedded LLDP Agent on all ports.
  **/
-i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
-				struct i40e_asq_cmd_details *cmd_details)
+i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, bool persist,
+			       struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aq_desc desc;
 	struct i40e_aqc_lldp_start *cmd =
@@ -3702,6 +3725,15 @@ i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_start);
 
 	cmd->command = I40E_AQ_LLDP_AGENT_START;
+
+	if (persist) {
+		if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)
+			cmd->command |= I40E_AQ_LLDP_AGENT_START_PERSIST;
+		else
+			i40e_debug(hw, I40E_DEBUG_ALL,
+				   "Persistent Start LLDP not supported by current FW version.\n");
+	}
+
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
 
 	return status;
@@ -4873,6 +4905,7 @@ i40e_status i40e_read_phy_register(struct i40e_hw *hw,
 		break;
 	case I40E_DEV_ID_10G_BASE_T:
 	case I40E_DEV_ID_10G_BASE_T4:
+	case I40E_DEV_ID_10G_BASE_T_BC:
 	case I40E_DEV_ID_10G_BASE_T_X722:
 	case I40E_DEV_ID_25G_B:
 	case I40E_DEV_ID_25G_SFP28:
@@ -5448,6 +5481,163 @@ i40e_find_segment_in_package(u32 segment_type,
 	return NULL;
 }
 
+/* Get section table in profile */
+#define I40E_SECTION_TABLE(profile, sec_tbl)				\
+	do {								\
+		struct i40e_profile_segment *p = (profile);		\
+		u32 count;						\
+		u32 *nvm;						\
+		count = p->device_table_count;				\
+		nvm = (u32 *)&p->device_table[count];			\
+		sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; \
+	} while (0)
+
+/* Get section header in profile */
+#define I40E_SECTION_HEADER(profile, offset)				\
+	(struct i40e_profile_section_header *)((u8 *)(profile) + (offset))
+
+/**
+ * i40e_find_section_in_profile
+ * @section_type: the section type to search for (i.e., SECTION_TYPE_NOTE)
+ * @profile: pointer to the i40e segment header to be searched
+ *
+ * This function searches i40e segment for a particular section type. On
+ * success it returns a pointer to the section header, otherwise it will
+ * return NULL.
+ **/
+struct i40e_profile_section_header *
+i40e_find_section_in_profile(u32 section_type,
+			     struct i40e_profile_segment *profile)
+{
+	struct i40e_profile_section_header *sec;
+	struct i40e_section_table *sec_tbl;
+	u32 sec_off;
+	u32 i;
+
+	if (profile->header.type != SEGMENT_TYPE_I40E)
+		return NULL;
+
+	I40E_SECTION_TABLE(profile, sec_tbl);
+
+	for (i = 0; i < sec_tbl->section_count; i++) {
+		sec_off = sec_tbl->section_offset[i];
+		sec = I40E_SECTION_HEADER(profile, sec_off);
+		if (sec->section.type == section_type)
+			return sec;
+	}
+
+	return NULL;
+}
+
+/**
+ * i40e_ddp_exec_aq_section - Execute generic AQ for DDP
+ * @hw: pointer to the hw struct
+ * @aq: command buffer containing all data to execute AQ
+ **/
+static enum
+i40e_status_code i40e_ddp_exec_aq_section(struct i40e_hw *hw,
+					  struct i40e_profile_aq_section *aq)
+{
+	i40e_status status;
+	struct i40e_aq_desc desc;
+	u8 *msg = NULL;
+	u16 msglen;
+
+	i40e_fill_default_direct_cmd_desc(&desc, aq->opcode);
+	desc.flags |= cpu_to_le16(aq->flags);
+	memcpy(desc.params.raw, aq->param, sizeof(desc.params.raw));
+
+	msglen = aq->datalen;
+	if (msglen) {
+		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
+						I40E_AQ_FLAG_RD));
+		if (msglen > I40E_AQ_LARGE_BUF)
+			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.datalen = cpu_to_le16(msglen);
+		msg = &aq->data[0];
+	}
+
+	status = i40e_asq_send_command(hw, &desc, msg, msglen, NULL);
+
+	if (status) {
+		i40e_debug(hw, I40E_DEBUG_PACKAGE,
+			   "unable to exec DDP AQ opcode %u, error %d\n",
+			   aq->opcode, status);
+		return status;
+	}
+
+	/* copy returned desc to aq_buf */
+	memcpy(aq->param, desc.params.raw, sizeof(desc.params.raw));
+
+	return 0;
+}
+
+/**
+ * i40e_validate_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be validated
+ * @track_id: package tracking id
+ * @rollback: flag if the profile is for rollback.
+ *
+ * Validates supported devices and profile's sections.
+ */
+static enum i40e_status_code
+i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+		      u32 track_id, bool rollback)
+{
+	struct i40e_profile_section_header *sec = NULL;
+	i40e_status status = 0;
+	struct i40e_section_table *sec_tbl;
+	u32 vendor_dev_id;
+	u32 dev_cnt;
+	u32 sec_off;
+	u32 i;
+
+	if (track_id == I40E_DDP_TRACKID_INVALID) {
+		i40e_debug(hw, I40E_DEBUG_PACKAGE, "Invalid track_id\n");
+		return I40E_NOT_SUPPORTED;
+	}
+
+	dev_cnt = profile->device_table_count;
+	for (i = 0; i < dev_cnt; i++) {
+		vendor_dev_id = profile->device_table[i].vendor_dev_id;
+		if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL &&
+		    hw->device_id == (vendor_dev_id & 0xFFFF))
+			break;
+	}
+	if (dev_cnt && i == dev_cnt) {
+		i40e_debug(hw, I40E_DEBUG_PACKAGE,
+			   "Device doesn't support DDP\n");
+		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+	}
+
+	I40E_SECTION_TABLE(profile, sec_tbl);
+
+	/* Validate sections types */
+	for (i = 0; i < sec_tbl->section_count; i++) {
+		sec_off = sec_tbl->section_offset[i];
+		sec = I40E_SECTION_HEADER(profile, sec_off);
+		if (rollback) {
+			if (sec->section.type == SECTION_TYPE_MMIO ||
+			    sec->section.type == SECTION_TYPE_AQ ||
+			    sec->section.type == SECTION_TYPE_RB_AQ) {
+				i40e_debug(hw, I40E_DEBUG_PACKAGE,
+					   "Not a roll-back package\n");
+				return I40E_NOT_SUPPORTED;
+			}
+		} else {
+			if (sec->section.type == SECTION_TYPE_RB_AQ ||
+			    sec->section.type == SECTION_TYPE_RB_MMIO) {
+				i40e_debug(hw, I40E_DEBUG_PACKAGE,
+					   "Not an original package\n");
+				return I40E_NOT_SUPPORTED;
+			}
+		}
+	}
+
+	return status;
+}
+
 /**
  * i40e_write_profile
  * @hw: pointer to the hardware structure
@@ -5463,47 +5653,99 @@ i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
 	i40e_status status = 0;
 	struct i40e_section_table *sec_tbl;
 	struct i40e_profile_section_header *sec = NULL;
-	u32 dev_cnt;
-	u32 vendor_dev_id;
-	u32 *nvm;
+	struct i40e_profile_aq_section *ddp_aq;
 	u32 section_size = 0;
 	u32 offset = 0, info = 0;
+	u32 sec_off;
 	u32 i;
 
-	dev_cnt = profile->device_table_count;
+	status = i40e_validate_profile(hw, profile, track_id, false);
+	if (status)
+		return status;
 
-	for (i = 0; i < dev_cnt; i++) {
-		vendor_dev_id = profile->device_table[i].vendor_dev_id;
-		if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL)
-			if (hw->device_id == (vendor_dev_id & 0xFFFF))
+	I40E_SECTION_TABLE(profile, sec_tbl);
+
+	for (i = 0; i < sec_tbl->section_count; i++) {
+		sec_off = sec_tbl->section_offset[i];
+		sec = I40E_SECTION_HEADER(profile, sec_off);
+		/* Process generic admin command */
+		if (sec->section.type == SECTION_TYPE_AQ) {
+			ddp_aq = (struct i40e_profile_aq_section *)&sec[1];
+			status = i40e_ddp_exec_aq_section(hw, ddp_aq);
+			if (status) {
+				i40e_debug(hw, I40E_DEBUG_PACKAGE,
+					   "Failed to execute aq: section %d, opcode %u\n",
+					   i, ddp_aq->opcode);
 				break;
+			}
+			sec->section.type = SECTION_TYPE_RB_AQ;
+		}
+
+		/* Skip any non-mmio sections */
+		if (sec->section.type != SECTION_TYPE_MMIO)
+			continue;
+
+		section_size = sec->section.size +
+			sizeof(struct i40e_profile_section_header);
+
+		/* Write MMIO section */
+		status = i40e_aq_write_ddp(hw, (void *)sec, (u16)section_size,
+					   track_id, &offset, &info, NULL);
+		if (status) {
+			i40e_debug(hw, I40E_DEBUG_PACKAGE,
+				   "Failed to write profile: section %d, offset %d, info %d\n",
+				   i, offset, info);
+			break;
+		}
 	}
-	if (i == dev_cnt) {
-		i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support DDP");
-		return I40E_ERR_DEVICE_NOT_SUPPORTED;
-	}
+	return status;
+}
 
-	nvm = (u32 *)&profile->device_table[dev_cnt];
-	sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1];
+/**
+ * i40e_rollback_profile
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package to be removed
+ * @track_id: package tracking id
+ *
+ * Rolls back previously loaded package.
+ */
+enum i40e_status_code
+i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+		      u32 track_id)
+{
+	struct i40e_profile_section_header *sec = NULL;
+	i40e_status status = 0;
+	struct i40e_section_table *sec_tbl;
+	u32 offset = 0, info = 0;
+	u32 section_size = 0;
+	u32 sec_off;
+	int i;
 
-	for (i = 0; i < sec_tbl->section_count; i++) {
-		sec = (struct i40e_profile_section_header *)((u8 *)profile +
-					     sec_tbl->section_offset[i]);
+	status = i40e_validate_profile(hw, profile, track_id, true);
+	if (status)
+		return status;
 
-		/* Skip 'AQ', 'note' and 'name' sections */
-		if (sec->section.type != SECTION_TYPE_MMIO)
+	I40E_SECTION_TABLE(profile, sec_tbl);
+
+	/* For rollback write sections in reverse */
+	for (i = sec_tbl->section_count - 1; i >= 0; i--) {
+		sec_off = sec_tbl->section_offset[i];
+		sec = I40E_SECTION_HEADER(profile, sec_off);
+
+		/* Skip any non-rollback sections */
+		if (sec->section.type != SECTION_TYPE_RB_MMIO)
 			continue;
 
 		section_size = sec->section.size +
 			sizeof(struct i40e_profile_section_header);
 
-		/* Write profile */
+		/* Write roll-back MMIO section */
 		status = i40e_aq_write_ddp(hw, (void *)sec, (u16)section_size,
 					   track_id, &offset, &info, NULL);
 		if (status) {
 			i40e_debug(hw, I40E_DEBUG_PACKAGE,
-				   "Failed to write profile: offset %d, info %d",
-				   offset, info);
+				   "Failed to write profile: section %d, offset %d, info %d\n",
+				   i, offset, info);
 			break;
 		}
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 56bff8faf371..292eeb3def10 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -863,22 +863,23 @@ out:
 /**
  * i40e_init_dcb
  * @hw: pointer to the hw struct
+ * @enable_mib_change: enable mib change event
  *
  * Update DCB configuration from the Firmware
  **/
-i40e_status i40e_init_dcb(struct i40e_hw *hw)
+i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change)
 {
 	i40e_status ret = 0;
 	struct i40e_lldp_variables lldp_cfg;
 	u8 adminstatus = 0;
 
 	if (!hw->func_caps.dcb)
-		return ret;
+		return I40E_NOT_SUPPORTED;
 
 	/* Read LLDP NVM area */
 	ret = i40e_read_lldp_cfg(hw, &lldp_cfg);
 	if (ret)
-		return ret;
+		return I40E_ERR_NOT_READY;
 
 	/* Get the LLDP AdminStatus for the current port */
 	adminstatus = lldp_cfg.adminstatus >> (hw->port * 4);
@@ -887,7 +888,7 @@ i40e_status i40e_init_dcb(struct i40e_hw *hw)
 	/* LLDP agent disabled */
 	if (!adminstatus) {
 		hw->dcbx_status = I40E_DCBX_STATUS_DISABLED;
-		return ret;
+		return I40E_ERR_NOT_READY;
 	}
 
 	/* Get DCBX status */
@@ -896,26 +897,19 @@ i40e_status i40e_init_dcb(struct i40e_hw *hw)
 		return ret;
 
 	/* Check the DCBX Status */
-	switch (hw->dcbx_status) {
-	case I40E_DCBX_STATUS_DONE:
-	case I40E_DCBX_STATUS_IN_PROGRESS:
+	if (hw->dcbx_status == I40E_DCBX_STATUS_DONE ||
+	    hw->dcbx_status == I40E_DCBX_STATUS_IN_PROGRESS) {
 		/* Get current DCBX configuration */
 		ret = i40e_get_dcb_config(hw);
 		if (ret)
 			return ret;
-		break;
-	case I40E_DCBX_STATUS_DISABLED:
-		return ret;
-	case I40E_DCBX_STATUS_NOT_STARTED:
-	case I40E_DCBX_STATUS_MULTIPLE_PEERS:
-	default:
-		break;
+	} else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) {
+		return I40E_ERR_NOT_READY;
 	}
 
 	/* Configure the LLDP MIB change event */
-	ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
-	if (ret)
-		return ret;
+	if (enable_mib_change)
+		ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
index 2b748a60a843..ddb48ae7cce4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h
@@ -124,5 +124,5 @@ i40e_status i40e_aq_get_dcb_config(struct i40e_hw *hw, u8 mib_type,
 					     u8 bridgetype,
 					     struct i40e_dcbx_config *dcbcfg);
 i40e_status i40e_get_dcb_config(struct i40e_hw *hw);
-i40e_status i40e_init_dcb(struct i40e_hw *hw);
+i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change);
 #endif /* _I40E_DCB_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
new file mode 100644
index 000000000000..5e08f100c413
--- /dev/null
+++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c
@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#include "i40e.h"
+
+#include <linux/firmware.h>
+
+/**
+ * i40e_ddp_profiles_eq - checks if DDP profiles are the equivalent
+ * @a: new profile info
+ * @b: old profile info
+ *
+ * checks if DDP profiles are the equivalent.
+ * Returns true if profiles are the same.
+ **/
+static bool i40e_ddp_profiles_eq(struct i40e_profile_info *a,
+				 struct i40e_profile_info *b)
+{
+	return a->track_id == b->track_id &&
+		!memcmp(&a->version, &b->version, sizeof(a->version)) &&
+		!memcmp(&a->name, &b->name, I40E_DDP_NAME_SIZE);
+}
+
+/**
+ * i40e_ddp_does_profile_exist - checks if DDP profile loaded already
+ * @hw: HW data structure
+ * @pinfo: DDP profile information structure
+ *
+ * checks if DDP profile loaded already.
+ * Returns >0 if the profile exists.
+ * Returns  0 if the profile is absent.
+ * Returns <0 if error.
+ **/
+static int i40e_ddp_does_profile_exist(struct i40e_hw *hw,
+				       struct i40e_profile_info *pinfo)
+{
+	struct i40e_ddp_profile_list *profile_list;
+	u8 buff[I40E_PROFILE_LIST_SIZE];
+	i40e_status status;
+	int i;
+
+	status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0,
+				      NULL);
+	if (status)
+		return -1;
+
+	profile_list = (struct i40e_ddp_profile_list *)buff;
+	for (i = 0; i < profile_list->p_count; i++) {
+		if (i40e_ddp_profiles_eq(pinfo, &profile_list->p_info[i]))
+			return 1;
+	}
+	return 0;
+}
+
+/**
+ * i40e_ddp_profiles_overlap - checks if DDP profiles overlap.
+ * @new: new profile info
+ * @old: old profile info
+ *
+ * checks if DDP profiles overlap.
+ * Returns true if profiles are overlap.
+ **/
+static bool i40e_ddp_profiles_overlap(struct i40e_profile_info *new,
+				      struct i40e_profile_info *old)
+{
+	unsigned int group_id_old = (u8)((old->track_id & 0x00FF0000) >> 16);
+	unsigned int group_id_new = (u8)((new->track_id & 0x00FF0000) >> 16);
+
+	/* 0x00 group must be only the first */
+	if (group_id_new == 0)
+		return true;
+	/* 0xFF group is compatible with anything else */
+	if (group_id_new == 0xFF || group_id_old == 0xFF)
+		return false;
+	/* otherwise only profiles from the same group are compatible*/
+	return group_id_old != group_id_new;
+}
+
+/**
+ * i40e_ddp_does_profiles_ - checks if DDP overlaps with existing one.
+ * @hw: HW data structure
+ * @pinfo: DDP profile information structure
+ *
+ * checks if DDP profile overlaps with existing one.
+ * Returns >0 if the profile overlaps.
+ * Returns  0 if the profile is ok.
+ * Returns <0 if error.
+ **/
+static int i40e_ddp_does_profile_overlap(struct i40e_hw *hw,
+					 struct i40e_profile_info *pinfo)
+{
+	struct i40e_ddp_profile_list *profile_list;
+	u8 buff[I40E_PROFILE_LIST_SIZE];
+	i40e_status status;
+	int i;
+
+	status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0,
+				      NULL);
+	if (status)
+		return -EIO;
+
+	profile_list = (struct i40e_ddp_profile_list *)buff;
+	for (i = 0; i < profile_list->p_count; i++) {
+		if (i40e_ddp_profiles_overlap(pinfo,
+					      &profile_list->p_info[i]))
+			return 1;
+	}
+	return 0;
+}
+
+/**
+ * i40e_add_pinfo
+ * @hw: pointer to the hardware structure
+ * @profile: pointer to the profile segment of the package
+ * @profile_info_sec: buffer for information section
+ * @track_id: package tracking id
+ *
+ * Register a profile to the list of loaded profiles.
+ */
+static enum i40e_status_code
+i40e_add_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+	       u8 *profile_info_sec, u32 track_id)
+{
+	struct i40e_profile_section_header *sec;
+	struct i40e_profile_info *pinfo;
+	i40e_status status;
+	u32 offset = 0, info = 0;
+
+	sec = (struct i40e_profile_section_header *)profile_info_sec;
+	sec->tbl_size = 1;
+	sec->data_end = sizeof(struct i40e_profile_section_header) +
+			sizeof(struct i40e_profile_info);
+	sec->section.type = SECTION_TYPE_INFO;
+	sec->section.offset = sizeof(struct i40e_profile_section_header);
+	sec->section.size = sizeof(struct i40e_profile_info);
+	pinfo = (struct i40e_profile_info *)(profile_info_sec +
+					     sec->section.offset);
+	pinfo->track_id = track_id;
+	pinfo->version = profile->version;
+	pinfo->op = I40E_DDP_ADD_TRACKID;
+
+	/* Clear reserved field */
+	memset(pinfo->reserved, 0, sizeof(pinfo->reserved));
+	memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
+
+	status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
+				   track_id, &offset, &info, NULL);
+	return status;
+}
+
+/**
+ * i40e_del_pinfo - delete DDP profile info from NIC
+ * @hw: HW data structure
+ * @profile: DDP profile segment to be deleted
+ * @profile_info_sec: DDP profile section header
+ * @track_id: track ID of the profile for deletion
+ *
+ * Removes DDP profile from the NIC.
+ **/
+static enum i40e_status_code
+i40e_del_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile,
+	       u8 *profile_info_sec, u32 track_id)
+{
+	struct i40e_profile_section_header *sec;
+	struct i40e_profile_info *pinfo;
+	i40e_status status;
+	u32 offset = 0, info = 0;
+
+	sec = (struct i40e_profile_section_header *)profile_info_sec;
+	sec->tbl_size = 1;
+	sec->data_end = sizeof(struct i40e_profile_section_header) +
+			sizeof(struct i40e_profile_info);
+	sec->section.type = SECTION_TYPE_INFO;
+	sec->section.offset = sizeof(struct i40e_profile_section_header);
+	sec->section.size = sizeof(struct i40e_profile_info);
+	pinfo = (struct i40e_profile_info *)(profile_info_sec +
+					     sec->section.offset);
+	pinfo->track_id = track_id;
+	pinfo->version = profile->version;
+	pinfo->op = I40E_DDP_REMOVE_TRACKID;
+
+	/* Clear reserved field */
+	memset(pinfo->reserved, 0, sizeof(pinfo->reserved));
+	memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE);
+
+	status = i40e_aq_write_ddp(hw, (void *)sec, sec->data_end,
+				   track_id, &offset, &info, NULL);
+	return status;
+}
+
+/**
+ * i40e_ddp_is_pkg_hdr_valid - performs basic pkg header integrity checks
+ * @netdev: net device structure (for logging purposes)
+ * @pkg_hdr: pointer to package header
+ * @size_huge: size of the whole DDP profile package in size_t
+ *
+ * Checks correctness of pkg header: Version, size too big/small, and
+ * all segment offsets alignment and boundaries. This function lets
+ * reject non DDP profile file to be loaded by administrator mistake.
+ **/
+static bool i40e_ddp_is_pkg_hdr_valid(struct net_device *netdev,
+				      struct i40e_package_header *pkg_hdr,
+				      size_t size_huge)
+{
+	u32 size = 0xFFFFFFFFU & size_huge;
+	u32 pkg_hdr_size;
+	u32 segment;
+
+	if (!pkg_hdr)
+		return false;
+
+	if (pkg_hdr->version.major > 0) {
+		struct i40e_ddp_version ver = pkg_hdr->version;
+
+		netdev_err(netdev, "Unsupported DDP profile version %u.%u.%u.%u",
+			   ver.major, ver.minor, ver.update, ver.draft);
+		return false;
+	}
+	if (size_huge > size) {
+		netdev_err(netdev, "Invalid DDP profile - size is bigger than 4G");
+		return false;
+	}
+	if (size < (sizeof(struct i40e_package_header) +
+		sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
+		netdev_err(netdev, "Invalid DDP profile - size is too small.");
+		return false;
+	}
+
+	pkg_hdr_size = sizeof(u32) * (pkg_hdr->segment_count + 2U);
+	if (size < pkg_hdr_size) {
+		netdev_err(netdev, "Invalid DDP profile - too many segments");
+		return false;
+	}
+	for (segment = 0; segment < pkg_hdr->segment_count; ++segment) {
+		u32 offset = pkg_hdr->segment_offset[segment];
+
+		if (0xFU & offset) {
+			netdev_err(netdev,
+				   "Invalid DDP profile %u segment alignment",
+				   segment);
+			return false;
+		}
+		if (pkg_hdr_size > offset || offset >= size) {
+			netdev_err(netdev,
+				   "Invalid DDP profile %u segment offset",
+				   segment);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/**
+ * i40e_ddp_load - performs DDP loading
+ * @netdev: net device structure
+ * @data: buffer containing recipe file
+ * @size: size of the buffer
+ * @is_add: true when loading profile, false when rolling back the previous one
+ *
+ * Checks correctness and loads DDP profile to the NIC. The function is
+ * also used for rolling back previously loaded profile.
+ **/
+int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size,
+		  bool is_add)
+{
+	u8 profile_info_sec[sizeof(struct i40e_profile_section_header) +
+			    sizeof(struct i40e_profile_info)];
+	struct i40e_metadata_segment *metadata_hdr;
+	struct i40e_profile_segment *profile_hdr;
+	struct i40e_profile_info pinfo;
+	struct i40e_package_header *pkg_hdr;
+	i40e_status status;
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
+	u32 track_id;
+	int istatus;
+
+	pkg_hdr = (struct i40e_package_header *)data;
+	if (!i40e_ddp_is_pkg_hdr_valid(netdev, pkg_hdr, size))
+		return -EINVAL;
+
+	if (size < (sizeof(struct i40e_package_header) +
+		    sizeof(struct i40e_metadata_segment) + sizeof(u32) * 2)) {
+		netdev_err(netdev, "Invalid DDP recipe size.");
+		return -EINVAL;
+	}
+
+	/* Find beginning of segment data in buffer */
+	metadata_hdr = (struct i40e_metadata_segment *)
+		i40e_find_segment_in_package(SEGMENT_TYPE_METADATA, pkg_hdr);
+	if (!metadata_hdr) {
+		netdev_err(netdev, "Failed to find metadata segment in DDP recipe.");
+		return -EINVAL;
+	}
+
+	track_id = metadata_hdr->track_id;
+	profile_hdr = (struct i40e_profile_segment *)
+		i40e_find_segment_in_package(SEGMENT_TYPE_I40E, pkg_hdr);
+	if (!profile_hdr) {
+		netdev_err(netdev, "Failed to find profile segment in DDP recipe.");
+		return -EINVAL;
+	}
+
+	pinfo.track_id = track_id;
+	pinfo.version = profile_hdr->version;
+	if (is_add)
+		pinfo.op = I40E_DDP_ADD_TRACKID;
+	else
+		pinfo.op = I40E_DDP_REMOVE_TRACKID;
+
+	memcpy(pinfo.name, profile_hdr->name, I40E_DDP_NAME_SIZE);
+
+	/* Check if profile data already exists*/
+	istatus = i40e_ddp_does_profile_exist(&pf->hw, &pinfo);
+	if (istatus < 0) {
+		netdev_err(netdev, "Failed to fetch loaded profiles.");
+		return istatus;
+	}
+	if (is_add) {
+		if (istatus > 0) {
+			netdev_err(netdev, "DDP profile already loaded.");
+			return -EINVAL;
+		}
+		istatus = i40e_ddp_does_profile_overlap(&pf->hw, &pinfo);
+		if (istatus < 0) {
+			netdev_err(netdev, "Failed to fetch loaded profiles.");
+			return istatus;
+		}
+		if (istatus > 0) {
+			netdev_err(netdev, "DDP profile overlaps with existing one.");
+			return -EINVAL;
+		}
+	} else {
+		if (istatus == 0) {
+			netdev_err(netdev,
+				   "DDP profile for deletion does not exist.");
+			return -EINVAL;
+		}
+	}
+
+	/* Load profile data */
+	if (is_add) {
+		status = i40e_write_profile(&pf->hw, profile_hdr, track_id);
+		if (status) {
+			if (status == I40E_ERR_DEVICE_NOT_SUPPORTED) {
+				netdev_err(netdev,
+					   "Profile is not supported by the device.");
+				return -EPERM;
+			}
+			netdev_err(netdev, "Failed to write DDP profile.");
+			return -EIO;
+		}
+	} else {
+		status = i40e_rollback_profile(&pf->hw, profile_hdr, track_id);
+		if (status) {
+			netdev_err(netdev, "Failed to remove DDP profile.");
+			return -EIO;
+		}
+	}
+
+	/* Add/remove profile to/from profile list in FW */
+	if (is_add) {
+		status = i40e_add_pinfo(&pf->hw, profile_hdr, profile_info_sec,
+					track_id);
+		if (status) {
+			netdev_err(netdev, "Failed to add DDP profile info.");
+			return -EIO;
+		}
+	} else {
+		status = i40e_del_pinfo(&pf->hw, profile_hdr, profile_info_sec,
+					track_id);
+		if (status) {
+			netdev_err(netdev, "Failed to restore DDP profile info.");
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_ddp_restore - restore previously loaded profile and remove from list
+ * @pf: PF data struct
+ *
+ * Restores previously loaded profile stored on the list in driver memory.
+ * After rolling back removes entry from the list.
+ **/
+static int i40e_ddp_restore(struct i40e_pf *pf)
+{
+	struct i40e_ddp_old_profile_list *entry;
+	struct net_device *netdev = pf->vsi[pf->lan_vsi]->netdev;
+	int status = 0;
+
+	if (!list_empty(&pf->ddp_old_prof)) {
+		entry = list_first_entry(&pf->ddp_old_prof,
+					 struct i40e_ddp_old_profile_list,
+					 list);
+		status = i40e_ddp_load(netdev, entry->old_ddp_buf,
+				       entry->old_ddp_size, false);
+		list_del(&entry->list);
+		kfree(entry);
+	}
+	return status;
+}
+
+/**
+ * i40e_ddp_flash - callback function for ethtool flash feature
+ * @netdev: net device structure
+ * @flash: kernel flash structure
+ *
+ * Ethtool callback function used for loading and unloading DDP profiles.
+ **/
+int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash)
+{
+	const struct firmware *ddp_config;
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
+	int status = 0;
+
+	/* Check for valid region first */
+	if (flash->region != I40_DDP_FLASH_REGION) {
+		netdev_err(netdev, "Requested firmware region is not recognized by this driver.");
+		return -EINVAL;
+	}
+	if (pf->hw.bus.func != 0) {
+		netdev_err(netdev, "Any DDP operation is allowed only on Phy0 NIC interface");
+		return -EINVAL;
+	}
+
+	/* If the user supplied "-" instead of file name rollback previously
+	 * stored profile.
+	 */
+	if (strncmp(flash->data, "-", 2) != 0) {
+		struct i40e_ddp_old_profile_list *list_entry;
+		char profile_name[sizeof(I40E_DDP_PROFILE_PATH)
+				  + I40E_DDP_PROFILE_NAME_MAX];
+
+		profile_name[sizeof(profile_name) - 1] = 0;
+		strncpy(profile_name, I40E_DDP_PROFILE_PATH,
+			sizeof(profile_name) - 1);
+		strncat(profile_name, flash->data, I40E_DDP_PROFILE_NAME_MAX);
+		/* Load DDP recipe. */
+		status = request_firmware(&ddp_config, profile_name,
+					  &netdev->dev);
+		if (status) {
+			netdev_err(netdev, "DDP recipe file request failed.");
+			return status;
+		}
+
+		status = i40e_ddp_load(netdev, ddp_config->data,
+				       ddp_config->size, true);
+
+		if (!status) {
+			list_entry =
+			  kzalloc(sizeof(struct i40e_ddp_old_profile_list) +
+				  ddp_config->size, GFP_KERNEL);
+			if (!list_entry) {
+				netdev_info(netdev, "Failed to allocate memory for previous DDP profile data.");
+				netdev_info(netdev, "New profile loaded but roll-back will be impossible.");
+			} else {
+				memcpy(list_entry->old_ddp_buf,
+				       ddp_config->data, ddp_config->size);
+				list_entry->old_ddp_size = ddp_config->size;
+				list_add(&list_entry->list, &pf->ddp_old_prof);
+			}
+		}
+
+		release_firmware(ddp_config);
+	} else {
+		if (!list_empty(&pf->ddp_old_prof)) {
+			status = i40e_ddp_restore(pf);
+		} else {
+			netdev_warn(netdev, "There is no DDP profile to restore.");
+			status = -ENOENT;
+		}
+	}
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index a20d1cf058ad..55d20acfcf70 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -333,8 +333,9 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid)
 		 "    seid = %d, id = %d, uplink_seid = %d\n",
 		 vsi->seid, vsi->id, vsi->uplink_seid);
 	dev_info(&pf->pdev->dev,
-		 "    base_queue = %d, num_queue_pairs = %d, num_desc = %d\n",
-		 vsi->base_queue, vsi->num_queue_pairs, vsi->num_desc);
+		 "    base_queue = %d, num_queue_pairs = %d, num_tx_desc = %d, num_rx_desc = %d\n",
+		 vsi->base_queue, vsi->num_queue_pairs, vsi->num_tx_desc,
+		 vsi->num_rx_desc);
 	dev_info(&pf->pdev->dev, "    type = %i\n", vsi->type);
 	if (vsi->type == I40E_VSI_SRIOV)
 		dev_info(&pf->pdev->dev, "    VF ID = %i\n", vsi->vf_id);
@@ -1321,7 +1322,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		if (strncmp(&cmd_buf[5], "stop", 4) == 0) {
 			int ret;
 
-			ret = i40e_aq_stop_lldp(&pf->hw, false, NULL);
+			ret = i40e_aq_stop_lldp(&pf->hw, false, false, NULL);
 			if (ret) {
 				dev_info(&pf->pdev->dev,
 					 "Stop LLDP AQ command failed =0x%x\n",
@@ -1330,7 +1331,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			}
 			ret = i40e_aq_add_rem_control_packet_filter(&pf->hw,
 						pf->hw.mac.addr,
-						I40E_ETH_P_LLDP, 0,
+						ETH_P_LLDP, 0,
 						pf->vsi[pf->lan_vsi]->seid,
 						0, true, NULL, NULL);
 			if (ret) {
@@ -1348,7 +1349,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 
 			ret = i40e_aq_add_rem_control_packet_filter(&pf->hw,
 						pf->hw.mac.addr,
-						I40E_ETH_P_LLDP, 0,
+						ETH_P_LLDP, 0,
 						pf->vsi[pf->lan_vsi]->seid,
 						0, false, NULL, NULL);
 			if (ret) {
@@ -1358,7 +1359,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 				/* Continue and start FW LLDP anyways */
 			}
 
-			ret = i40e_aq_start_lldp(&pf->hw, NULL);
+			ret = i40e_aq_start_lldp(&pf->hw, false, NULL);
 			if (ret) {
 				dev_info(&pf->pdev->dev,
 					 "Start LLDP AQ command failed =0x%x\n",
@@ -1642,30 +1643,7 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 		count = buf_tmp - i40e_dbg_netdev_ops_buf + 1;
 	}
 
-	if (strncmp(i40e_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) {
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid);
-		if (cnt != 1) {
-			dev_info(&pf->pdev->dev, "tx_timeout <vsi_seid>\n");
-			goto netdev_ops_write_done;
-		}
-		vsi = i40e_dbg_find_vsi(pf, vsi_seid);
-		if (!vsi) {
-			dev_info(&pf->pdev->dev,
-				 "tx_timeout: VSI %d not found\n", vsi_seid);
-		} else if (!vsi->netdev) {
-			dev_info(&pf->pdev->dev, "tx_timeout: no netdev for VSI %d\n",
-				 vsi_seid);
-		} else if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
-			dev_info(&pf->pdev->dev, "tx_timeout: VSI %d not UP\n",
-				 vsi_seid);
-		} else if (rtnl_trylock()) {
-			vsi->netdev->netdev_ops->ndo_tx_timeout(vsi->netdev);
-			rtnl_unlock();
-			dev_info(&pf->pdev->dev, "tx_timeout called\n");
-		} else {
-			dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
-		}
-	} else if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
+	if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
 		int mtu;
 
 		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i %i",
@@ -1733,7 +1711,6 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 		dev_info(&pf->pdev->dev, "unknown command '%s'\n",
 			 i40e_dbg_netdev_ops_buf);
 		dev_info(&pf->pdev->dev, "available commands\n");
-		dev_info(&pf->pdev->dev, "  tx_timeout <vsi_seid>\n");
 		dev_info(&pf->pdev->dev, "  change_mtu <vsi_seid> <mtu>\n");
 		dev_info(&pf->pdev->dev, "  set_rx_mode <vsi_seid>\n");
 		dev_info(&pf->pdev->dev, "  napi <vsi_seid>\n");
diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h
index 334b05ff685a..bac4da031f9b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_devids.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h
@@ -5,6 +5,8 @@
 #define _I40E_DEVIDS_H_
 
 /* Device IDs */
+#define I40E_DEV_ID_X710_N3000		0x0CF8
+#define I40E_DEV_ID_XXV710_N3000	0x0D58
 #define I40E_DEV_ID_SFP_XL710		0x1572
 #define I40E_DEV_ID_QEMU		0x1574
 #define I40E_DEV_ID_KX_B		0x1580
@@ -18,6 +20,9 @@
 #define I40E_DEV_ID_10G_BASE_T4		0x1589
 #define I40E_DEV_ID_25G_B		0x158A
 #define I40E_DEV_ID_25G_SFP28		0x158B
+#define I40E_DEV_ID_10G_BASE_T_BC	0x15FF
+#define I40E_DEV_ID_10G_B		0x104F
+#define I40E_DEV_ID_10G_SFP		0x104E
 #define I40E_DEV_ID_KX_X722		0x37CE
 #define I40E_DEV_ID_QSFP_X722		0x37CF
 #define I40E_DEV_ID_SFP_X722		0x37D0
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index a6bc7847346b..527eb52c5401 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -438,6 +438,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 	I40E_PRIV_FLAG("disable-source-pruning",
 		       I40E_FLAG_SOURCE_PRUNING_DISABLED, 0),
 	I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_DISABLE_FW_LLDP, 0),
+	I40E_PRIV_FLAG("rs-fec", I40E_FLAG_RS_FEC, 0),
+	I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0),
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
@@ -506,6 +508,20 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     10000baseT_Full);
 	}
+	if (phy_types & I40E_CAP_PHY_TYPE_2_5GBASE_T) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     2500baseT_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_2_5GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     2500baseT_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_5GBASE_T) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     5000baseT_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_5GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     5000baseT_Full);
+	}
 	if (phy_types & I40E_CAP_PHY_TYPE_XLAUI ||
 	    phy_types & I40E_CAP_PHY_TYPE_XLPPI ||
 	    phy_types & I40E_CAP_PHY_TYPE_40GBASE_AOC)
@@ -533,17 +549,23 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     1000baseT_Full);
 	}
-	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4)
+	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_SR4) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseSR4_Full);
-	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4)
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseSR4_Full);
+	}
+	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_LR4) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseLR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseLR4_Full);
+	}
 	if (phy_types & I40E_CAP_PHY_TYPE_40GBASE_KR4) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
-						     40000baseLR4_Full);
+						     40000baseKR4_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
-						     40000baseLR4_Full);
+						     40000baseKR4_Full);
 	}
 	if (phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
@@ -606,6 +628,24 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     25000baseCR_Full);
 	}
+	if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_AOC ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_ACC) {
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) {
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     FEC_NONE);
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     FEC_RS);
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     FEC_BASER);
+		}
+	}
 	/* need to add new 10G PHY types */
 	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU) {
@@ -648,13 +688,15 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
 	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
 	    phy_types & I40E_CAP_PHY_TYPE_20GBASE_KR2 ||
-	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_SR ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_LR ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4 ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
+	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_T ||
+	    phy_types & I40E_CAP_PHY_TYPE_5GBASE_T ||
+	    phy_types & I40E_CAP_PHY_TYPE_2_5GBASE_T ||
 	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL ||
 	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_T ||
 	    phy_types & I40E_CAP_PHY_TYPE_1000BASE_SX ||
@@ -700,14 +742,20 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	case I40E_PHY_TYPE_40GBASE_AOC:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseCR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseCR4_Full);
 		break;
 	case I40E_PHY_TYPE_40GBASE_SR4:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseSR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseSR4_Full);
 		break;
 	case I40E_PHY_TYPE_40GBASE_LR4:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseLR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     40000baseLR4_Full);
 		break;
 	case I40E_PHY_TYPE_25GBASE_SR:
 	case I40E_PHY_TYPE_25GBASE_LR:
@@ -721,6 +769,13 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     25000baseSR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseSR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseSR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -751,12 +806,18 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 							     10000baseT_Full);
 		break;
 	case I40E_PHY_TYPE_10GBASE_T:
+	case I40E_PHY_TYPE_5GBASE_T:
+	case I40E_PHY_TYPE_2_5GBASE_T:
 	case I40E_PHY_TYPE_1000BASE_T:
 	case I40E_PHY_TYPE_100BASE_TX:
 		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseT_Full);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     5000baseT_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     2500baseT_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     1000baseT_Full);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     100baseT_Full);
@@ -764,6 +825,12 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     10000baseT_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_5GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     5000baseT_Full);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_2_5GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     2500baseT_Full);
 		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     1000baseT_Full);
@@ -825,6 +892,9 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     40000baseKR4_Full);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     20000baseKR2_Full);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
@@ -838,6 +908,10 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     40000baseKR4_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     20000baseKR2_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -855,6 +929,13 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     25000baseCR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseCR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		break;
 	case I40E_PHY_TYPE_25GBASE_AOC:
 	case I40E_PHY_TYPE_25GBASE_ACC:
@@ -862,9 +943,15 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseCR_Full);
-
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseCR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseCR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -899,6 +986,12 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 	case I40E_LINK_SPEED_10GB:
 		ks->base.speed = SPEED_10000;
 		break;
+	case I40E_LINK_SPEED_5GB:
+		ks->base.speed = SPEED_5000;
+		break;
+	case I40E_LINK_SPEED_2_5GB:
+		ks->base.speed = SPEED_2500;
+		break;
 	case I40E_LINK_SPEED_1GB:
 		ks->base.speed = SPEED_1000;
 		break;
@@ -986,6 +1079,7 @@ static int i40e_get_link_ksettings(struct net_device *netdev,
 		break;
 	case I40E_MEDIA_TYPE_FIBER:
 		ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FIBRE);
 		ks->base.port = PORT_FIBRE;
 		break;
 	case I40E_MEDIA_TYPE_UNKNOWN:
@@ -1184,6 +1278,12 @@ static int i40e_set_link_ksettings(struct net_device *netdev,
 						  10000baseLR_Full))
 		config.link_speed |= I40E_LINK_SPEED_10GB;
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  2500baseT_Full))
+		config.link_speed |= I40E_LINK_SPEED_2_5GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  5000baseT_Full))
+		config.link_speed |= I40E_LINK_SPEED_5GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  20000baseKR2_Full))
 		config.link_speed |= I40E_LINK_SPEED_20GB;
 	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
@@ -1261,6 +1361,154 @@ done:
 	return err;
 }
 
+static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_aq_get_phy_abilities_resp abilities;
+	struct i40e_pf *pf = np->vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	i40e_status status = 0;
+	u32 flags = 0;
+	int err = 0;
+
+	flags = READ_ONCE(pf->flags);
+	i40e_set_fec_in_flags(fec_cfg, &flags);
+
+	/* Get the current phy config */
+	memset(&abilities, 0, sizeof(abilities));
+	status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
+					      NULL);
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
+
+	if (abilities.fec_cfg_curr_mod_ext_info != fec_cfg) {
+		struct i40e_aq_set_phy_config config;
+
+		memset(&config, 0, sizeof(config));
+		config.phy_type = abilities.phy_type;
+		config.abilities = abilities.abilities;
+		config.phy_type_ext = abilities.phy_type_ext;
+		config.link_speed = abilities.link_speed;
+		config.eee_capability = abilities.eee_capability;
+		config.eeer = abilities.eeer_val;
+		config.low_power_ctrl = abilities.d3_lpan;
+		config.fec_config = fec_cfg & I40E_AQ_PHY_FEC_CONFIG_MASK;
+		status = i40e_aq_set_phy_config(hw, &config, NULL);
+		if (status) {
+			netdev_info(netdev,
+				    "Set phy config failed, err %s aq_err %s\n",
+				    i40e_stat_str(hw, status),
+				    i40e_aq_str(hw, hw->aq.asq_last_status));
+			err = -EAGAIN;
+			goto done;
+		}
+		pf->flags = flags;
+		status = i40e_update_link_info(hw);
+		if (status)
+			/* debug level message only due to relation to the link
+			 * itself rather than to the FEC settings
+			 * (e.g. no physical connection etc.)
+			 */
+			netdev_dbg(netdev,
+				   "Updating link info failed with err %s aq_err %s\n",
+				   i40e_stat_str(hw, status),
+				   i40e_aq_str(hw, hw->aq.asq_last_status));
+	}
+
+done:
+	return err;
+}
+
+static int i40e_get_fec_param(struct net_device *netdev,
+			      struct ethtool_fecparam *fecparam)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_aq_get_phy_abilities_resp abilities;
+	struct i40e_pf *pf = np->vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	i40e_status status = 0;
+	int err = 0;
+
+	/* Get the current phy config */
+	memset(&abilities, 0, sizeof(abilities));
+	status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
+					      NULL);
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
+
+	fecparam->fec = 0;
+	if (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_AUTO)
+		fecparam->fec |= ETHTOOL_FEC_AUTO;
+	if ((abilities.fec_cfg_curr_mod_ext_info &
+	     I40E_AQ_SET_FEC_REQUEST_RS) ||
+	    (abilities.fec_cfg_curr_mod_ext_info &
+	     I40E_AQ_SET_FEC_ABILITY_RS))
+		fecparam->fec |= ETHTOOL_FEC_RS;
+	if ((abilities.fec_cfg_curr_mod_ext_info &
+	     I40E_AQ_SET_FEC_REQUEST_KR) ||
+	    (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_ABILITY_KR))
+		fecparam->fec |= ETHTOOL_FEC_BASER;
+	if (abilities.fec_cfg_curr_mod_ext_info == 0)
+		fecparam->fec |= ETHTOOL_FEC_OFF;
+
+	if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA)
+		fecparam->active_fec = ETHTOOL_FEC_BASER;
+	else if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_RS_ENA)
+		fecparam->active_fec = ETHTOOL_FEC_RS;
+	else
+		fecparam->active_fec = ETHTOOL_FEC_OFF;
+done:
+	return err;
+}
+
+static int i40e_set_fec_param(struct net_device *netdev,
+			      struct ethtool_fecparam *fecparam)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_pf *pf = np->vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	u8 fec_cfg = 0;
+	int err = 0;
+
+	if (hw->device_id != I40E_DEV_ID_25G_SFP28 &&
+	    hw->device_id != I40E_DEV_ID_25G_B) {
+		err = -EPERM;
+		goto done;
+	}
+
+	switch (fecparam->fec) {
+	case ETHTOOL_FEC_AUTO:
+		fec_cfg = I40E_AQ_SET_FEC_AUTO;
+		break;
+	case ETHTOOL_FEC_RS:
+		fec_cfg = (I40E_AQ_SET_FEC_REQUEST_RS |
+			     I40E_AQ_SET_FEC_ABILITY_RS);
+		break;
+	case ETHTOOL_FEC_BASER:
+		fec_cfg = (I40E_AQ_SET_FEC_REQUEST_KR |
+			     I40E_AQ_SET_FEC_ABILITY_KR);
+		break;
+	case ETHTOOL_FEC_OFF:
+	case ETHTOOL_FEC_NONE:
+		fec_cfg = 0;
+		break;
+	default:
+		dev_warn(&pf->pdev->dev, "Unsupported FEC mode: %d",
+			 fecparam->fec);
+		err = -EINVAL;
+		goto done;
+	}
+
+	err = i40e_set_fec_cfg(netdev, fec_cfg);
+
+done:
+	return err;
+}
+
 static int i40e_nway_reset(struct net_device *netdev)
 {
 	/* restart autonegotiation */
@@ -1376,7 +1624,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	else if (!pause->rx_pause && !pause->tx_pause)
 		hw->fc.requested_mode = I40E_FC_NONE;
 	else
-		 return -EINVAL;
+		return -EINVAL;
 
 	/* Tell the OS link is going down, the link will go back up when fw
 	 * says it is ready asynchronously
@@ -1734,6 +1982,8 @@ static int i40e_set_ringparam(struct net_device *netdev,
 			if (i40e_enabled_xdp_vsi(vsi))
 				vsi->xdp_rings[i]->count = new_tx_count;
 		}
+		vsi->num_tx_desc = new_tx_count;
+		vsi->num_rx_desc = new_rx_count;
 		goto done;
 	}
 
@@ -1870,6 +2120,8 @@ rx_unwind:
 		rx_rings = NULL;
 	}
 
+	vsi->num_tx_desc = new_tx_count;
+	vsi->num_rx_desc = new_rx_count;
 	i40e_up(vsi);
 
 free_tx:
@@ -2175,7 +2427,7 @@ static int i40e_get_ts_info(struct net_device *dev,
 	return 0;
 }
 
-static int i40e_link_test(struct net_device *netdev, u64 *data)
+static u64 i40e_link_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2198,7 +2450,7 @@ static int i40e_link_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
-static int i40e_reg_test(struct net_device *netdev, u64 *data)
+static u64 i40e_reg_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2209,7 +2461,7 @@ static int i40e_reg_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
-static int i40e_eeprom_test(struct net_device *netdev, u64 *data)
+static u64 i40e_eeprom_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2223,7 +2475,7 @@ static int i40e_eeprom_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
-static int i40e_intr_test(struct net_device *netdev, u64 *data)
+static u64 i40e_intr_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2378,8 +2630,7 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		return -EOPNOTSUPP;
 
 	/* only magic packet is supported */
-	if (wol->wolopts && (wol->wolopts != WAKE_MAGIC)
-			  | (wol->wolopts != WAKE_FILTER))
+	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EOPNOTSUPP;
 
 	/* is this a new value? */
@@ -2440,10 +2691,10 @@ static int i40e_set_phys_id(struct net_device *netdev,
 	default:
 		break;
 	}
-		if (ret)
-			return -ENOENT;
-		else
-			return 0;
+	if (ret)
+		return -ENOENT;
+	else
+		return 0;
 }
 
 /* NOTE: i40e hardware uses a conversion factor of 2 for Interrupt
@@ -4605,9 +4856,12 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
+	u64 orig_flags, new_flags, changed_flags;
+	enum i40e_admin_queue_err adq_err;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
-	u64 orig_flags, new_flags, changed_flags;
+	bool is_reset_needed;
+	i40e_status status;
 	u32 i, j;
 
 	orig_flags = READ_ONCE(pf->flags);
@@ -4651,6 +4905,10 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 flags_complete:
 	changed_flags = orig_flags ^ new_flags;
 
+	is_reset_needed = !!(changed_flags & (I40E_FLAG_VEB_STATS_ENABLED |
+		I40E_FLAG_LEGACY_RX | I40E_FLAG_SOURCE_PRUNING_DISABLED |
+		I40E_FLAG_DISABLE_FW_LLDP));
+
 	/* Before we finalize any flag changes, we need to perform some
 	 * checks to ensure that the changes are supported and safe.
 	 */
@@ -4676,12 +4934,14 @@ flags_complete:
 		}
 	}
 
-	/* Now that we've checked to ensure that the new flags are valid, load
-	 * them into place. Since we only modify flags either (a) during
-	 * initialization or (b) while holding the RTNL lock, we don't need
-	 * anything fancy here.
-	 */
-	pf->flags = new_flags;
+	if (((changed_flags & I40E_FLAG_RS_FEC) ||
+	     (changed_flags & I40E_FLAG_BASE_R_FEC)) &&
+	    pf->hw.device_id != I40E_DEV_ID_25G_SFP28 &&
+	    pf->hw.device_id != I40E_DEV_ID_25G_B) {
+		dev_warn(&pf->pdev->dev,
+			 "Device does not support changing FEC configuration\n");
+		return -EOPNOTSUPP;
+	}
 
 	/* Process any additional changes needed as a result of flag changes.
 	 * The changed_flags value reflects the list of bits that were
@@ -4690,7 +4950,7 @@ flags_complete:
 
 	/* Flush current ATR settings if ATR was disabled */
 	if ((changed_flags & I40E_FLAG_FD_ATR_ENABLED) &&
-	    !(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) {
+	    !(new_flags & I40E_FLAG_FD_ATR_ENABLED)) {
 		set_bit(__I40E_FD_ATR_AUTO_DISABLED, pf->state);
 		set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state);
 	}
@@ -4699,7 +4959,7 @@ flags_complete:
 		u16 sw_flags = 0, valid_flags = 0;
 		int ret;
 
-		if (!(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
+		if (!(new_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT))
 			sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		ret = i40e_aq_set_switch_config(&pf->hw, sw_flags, valid_flags,
@@ -4714,17 +4974,35 @@ flags_complete:
 		}
 	}
 
-	if ((changed_flags & pf->flags &
+	if ((changed_flags & I40E_FLAG_RS_FEC) ||
+	    (changed_flags & I40E_FLAG_BASE_R_FEC)) {
+		u8 fec_cfg = 0;
+
+		if (new_flags & I40E_FLAG_RS_FEC &&
+		    new_flags & I40E_FLAG_BASE_R_FEC) {
+			fec_cfg = I40E_AQ_SET_FEC_AUTO;
+		} else if (new_flags & I40E_FLAG_RS_FEC) {
+			fec_cfg = (I40E_AQ_SET_FEC_REQUEST_RS |
+				   I40E_AQ_SET_FEC_ABILITY_RS);
+		} else if (new_flags & I40E_FLAG_BASE_R_FEC) {
+			fec_cfg = (I40E_AQ_SET_FEC_REQUEST_KR |
+				   I40E_AQ_SET_FEC_ABILITY_KR);
+		}
+		if (i40e_set_fec_cfg(dev, fec_cfg))
+			dev_warn(&pf->pdev->dev, "Cannot change FEC config\n");
+	}
+
+	if ((changed_flags & new_flags &
 	     I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) &&
-	    (pf->flags & I40E_FLAG_MFP_ENABLED))
+	    (new_flags & I40E_FLAG_MFP_ENABLED))
 		dev_warn(&pf->pdev->dev,
 			 "Turning on link-down-on-close flag may affect other partitions\n");
 
 	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
-		if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) {
+		if (new_flags & I40E_FLAG_DISABLE_FW_LLDP) {
 			struct i40e_dcbx_config *dcbcfg;
 
-			i40e_aq_stop_lldp(&pf->hw, true, NULL);
+			i40e_aq_stop_lldp(&pf->hw, true, false, NULL);
 			i40e_aq_set_dcb_parameters(&pf->hw, true, NULL);
 			/* reset local_dcbx_config to default */
 			dcbcfg = &pf->hw.local_dcbx_config;
@@ -4739,17 +5017,43 @@ flags_complete:
 			dcbcfg->pfc.willing = 1;
 			dcbcfg->pfc.pfccap = I40E_MAX_TRAFFIC_CLASS;
 		} else {
-			i40e_aq_start_lldp(&pf->hw, NULL);
+			status = i40e_aq_start_lldp(&pf->hw, false, NULL);
+			if (status) {
+				adq_err = pf->hw.aq.asq_last_status;
+				switch (adq_err) {
+				case I40E_AQ_RC_EEXIST:
+					dev_warn(&pf->pdev->dev,
+						 "FW LLDP agent is already running\n");
+					is_reset_needed = false;
+					break;
+				case I40E_AQ_RC_EPERM:
+					dev_warn(&pf->pdev->dev,
+						 "Device configuration forbids SW from starting the LLDP agent.\n");
+					return -EINVAL;
+				default:
+					dev_warn(&pf->pdev->dev,
+						 "Starting FW LLDP agent failed: error: %s, %s\n",
+						 i40e_stat_str(&pf->hw,
+							       status),
+						 i40e_aq_str(&pf->hw,
+							     adq_err));
+					return -EINVAL;
+				}
+			}
 		}
 	}
 
+	/* Now that we've checked to ensure that the new flags are valid, load
+	 * them into place. Since we only modify flags either (a) during
+	 * initialization or (b) while holding the RTNL lock, we don't need
+	 * anything fancy here.
+	 */
+	pf->flags = new_flags;
+
 	/* Issue reset to cause things to take effect, as additional bits
 	 * are added we will need to create a mask of bits requiring reset
 	 */
-	if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED |
-			     I40E_FLAG_LEGACY_RX |
-			     I40E_FLAG_SOURCE_PRUNING_DISABLED |
-			     I40E_FLAG_DISABLE_FW_LLDP))
+	if (is_reset_needed)
 		i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true);
 
 	return 0;
@@ -4907,6 +5211,22 @@ static int i40e_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
+static int i40e_get_eee(struct net_device *netdev, struct ethtool_eee *edata)
+{
+	return -EOPNOTSUPP;
+}
+
+static int i40e_set_eee(struct net_device *netdev, struct ethtool_eee *edata)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct ethtool_ops i40e_ethtool_recovery_mode_ops = {
+	.set_eeprom		= i40e_set_eeprom,
+	.get_eeprom_len		= i40e_get_eeprom_len,
+	.get_eeprom		= i40e_get_eeprom,
+};
+
 static const struct ethtool_ops i40e_ethtool_ops = {
 	.get_drvinfo		= i40e_get_drvinfo,
 	.get_regs_len		= i40e_get_regs_len,
@@ -4928,6 +5248,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.set_rxnfc		= i40e_set_rxnfc,
 	.self_test		= i40e_diag_test,
 	.get_strings		= i40e_get_strings,
+	.get_eee		= i40e_get_eee,
+	.set_eee		= i40e_set_eee,
 	.set_phys_id		= i40e_set_phys_id,
 	.get_sset_count		= i40e_get_sset_count,
 	.get_ethtool_stats	= i40e_get_ethtool_stats,
@@ -4948,9 +5270,18 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.set_per_queue_coalesce	= i40e_set_per_queue_coalesce,
 	.get_link_ksettings	= i40e_get_link_ksettings,
 	.set_link_ksettings	= i40e_set_link_ksettings,
+	.get_fecparam = i40e_get_fec_param,
+	.set_fecparam = i40e_set_fec_param,
+	.flash_device = i40e_ddp_flash,
 };
 
 void i40e_set_ethtool_ops(struct net_device *netdev)
 {
-	netdev->ethtool_ops = &i40e_ethtool_ops;
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_pf		*pf = np->vsi->back;
+
+	if (!test_bit(__I40E_RECOVERY_MODE, pf->state))
+		netdev->ethtool_ops = &i40e_ethtool_ops;
+	else
+		netdev->ethtool_ops = &i40e_ethtool_recovery_mode_ops;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index f52e2c46e6a7..9ebbe3da61bb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -26,13 +26,13 @@ static const char i40e_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 2
-#define DRV_VERSION_MINOR 7
-#define DRV_VERSION_BUILD 6
+#define DRV_VERSION_MINOR 8
+#define DRV_VERSION_BUILD 20
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
 const char i40e_driver_version_str[] = DRV_VERSION;
-static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporation.";
+static const char i40e_copyright[] = "Copyright (c) 2013 - 2019 Intel Corporation.";
 
 /* a bit of forward declarations */
 static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi);
@@ -46,6 +46,10 @@ static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
 static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
 static int i40e_reset(struct i40e_pf *pf);
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf);
+static int i40e_restore_interrupt_scheme(struct i40e_pf *pf);
+static bool i40e_check_recovery_mode(struct i40e_pf *pf);
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw);
 static void i40e_fdir_sb_setup(struct i40e_pf *pf);
 static int i40e_veb_get_bw_info(struct i40e_veb *veb);
 static int i40e_get_capabilities(struct i40e_pf *pf,
@@ -69,6 +73,8 @@ static const struct pci_device_id i40e_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_SFP), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_B), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
@@ -77,6 +83,8 @@ static const struct pci_device_id i40e_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_X710_N3000), 0},
+	{PCI_VDEVICE(INTEL, I40E_DEV_ID_XXV710_N3000), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_B), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_SFP28), 0},
 	/* required last entry */
@@ -278,8 +286,9 @@ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id)
  **/
 void i40e_service_event_schedule(struct i40e_pf *pf)
 {
-	if (!test_bit(__I40E_DOWN, pf->state) &&
-	    !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+	if ((!test_bit(__I40E_DOWN, pf->state) &&
+	     !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) ||
+	      test_bit(__I40E_RECOVERY_MODE, pf->state))
 		queue_work(i40e_wq, &pf->service_task);
 }
 
@@ -627,9 +636,6 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi)
 	i40e_stat_update32(hw, I40E_GLV_RUPP(stat_idx),
 			   vsi->stat_offsets_loaded,
 			   &oes->rx_unknown_protocol, &es->rx_unknown_protocol);
-	i40e_stat_update32(hw, I40E_GLV_TEPC(stat_idx),
-			   vsi->stat_offsets_loaded,
-			   &oes->tx_errors, &es->tx_errors);
 
 	i40e_stat_update48(hw, I40E_GLV_GORCH(stat_idx),
 			   I40E_GLV_GORCL(stat_idx),
@@ -2107,11 +2113,22 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 	fcnt = i40e_update_filter_state(num_add, list, add_head);
 
 	if (fcnt != num_add) {
-		set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
-		dev_warn(&vsi->back->pdev->dev,
-			 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
-			 i40e_aq_str(hw, aq_err),
-			 vsi_name);
+		if (vsi->type == I40E_VSI_MAIN) {
+			set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
+			dev_warn(&vsi->back->pdev->dev,
+				 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
+				 i40e_aq_str(hw, aq_err), vsi_name);
+		} else if (vsi->type == I40E_VSI_SRIOV ||
+			   vsi->type == I40E_VSI_VMDQ1 ||
+			   vsi->type == I40E_VSI_VMDQ2) {
+			dev_warn(&vsi->back->pdev->dev,
+				 "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n",
+				 i40e_aq_str(hw, aq_err), vsi_name, vsi_name);
+		} else {
+			dev_warn(&vsi->back->pdev->dev,
+				 "Error %s adding RX filters on %s, incorrect VSI type: %i.\n",
+				 i40e_aq_str(hw, aq_err), vsi_name, vsi->type);
+		}
 	}
 }
 
@@ -2654,6 +2671,10 @@ void i40e_vlan_stripping_enable(struct i40e_vsi *vsi)
 	struct i40e_vsi_context ctxt;
 	i40e_status ret;
 
+	/* Don't modify stripping options if a port VLAN is active */
+	if (vsi->info.pvid)
+		return;
+
 	if ((vsi->info.valid_sections &
 	     cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
 	    ((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_MODE_MASK) == 0))
@@ -2684,6 +2705,10 @@ void i40e_vlan_stripping_disable(struct i40e_vsi *vsi)
 	struct i40e_vsi_context ctxt;
 	i40e_status ret;
 
+	/* Don't modify stripping options if a port VLAN is active */
+	if (vsi->info.pvid)
+		return;
+
 	if ((vsi->info.valid_sections &
 	     cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID)) &&
 	    ((vsi->info.port_vlan_flags & I40E_AQ_VSI_PVLAN_EMOD_MASK) ==
@@ -2949,9 +2974,9 @@ int i40e_vsi_add_pvid(struct i40e_vsi *vsi, u16 vid)
  **/
 void i40e_vsi_remove_pvid(struct i40e_vsi *vsi)
 {
-	i40e_vlan_stripping_disable(vsi);
-
 	vsi->info.pvid = 0;
+
+	i40e_vlan_stripping_disable(vsi);
 }
 
 /**
@@ -3064,6 +3089,26 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 }
 
 /**
+ * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled
+ * @ring: The Tx or Rx ring
+ *
+ * Returns the UMEM or NULL.
+ **/
+static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
+{
+	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
+	int qid = ring->queue_index;
+
+	if (ring_is_xdp(ring))
+		qid -= ring->vsi->alloc_queue_pairs;
+
+	if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
+		return NULL;
+
+	return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
+}
+
+/**
  * i40e_configure_tx_ring - Configure a transmit ring context and rest
  * @ring: The Tx ring to configure
  *
@@ -3289,8 +3334,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	     i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
 	     !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
 	if (!ok) {
+		/* Log this in case the user has forgotten to give the kernel
+		 * any buffers, even later in the application.
+		 */
 		dev_info(&vsi->back->pdev->dev,
-			 "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
+			 "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n",
 			 ring->xsk_umem ? "UMEM enabled " : "",
 			 ring->queue_index, pf_q);
 	}
@@ -3610,7 +3658,7 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
 		      (I40E_QUEUE_TYPE_TX
 		       << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
 
-	       wr32(hw, I40E_QINT_TQCTL(nextqp), val);
+		wr32(hw, I40E_QINT_TQCTL(nextqp), val);
 	}
 
 	val = I40E_QINT_TQCTL_CAUSE_ENA_MASK		      |
@@ -3977,7 +4025,8 @@ static irqreturn_t i40e_intr(int irq, void *data)
 enable_intr:
 	/* re-enable interrupt causes */
 	wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
-	if (!test_bit(__I40E_DOWN, pf->state)) {
+	if (!test_bit(__I40E_DOWN, pf->state) ||
+	    test_bit(__I40E_RECOVERY_MODE, pf->state)) {
 		i40e_service_event_schedule(pf);
 		i40e_irq_dynamic_enable_icr0(pf);
 	}
@@ -5812,8 +5861,10 @@ static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid,
 		return -ENOENT;
 	}
 
-	/* Success, update channel */
-	ch->enabled_tc = enabled_tc;
+	/* Success, update channel, set enabled_tc only if the channel
+	 * is not a macvlan
+	 */
+	ch->enabled_tc = !i40e_is_channel_macvlan(ch) && enabled_tc;
 	ch->seid = ctxt.seid;
 	ch->vsi_number = ctxt.vsi_number;
 	ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx);
@@ -6361,6 +6412,50 @@ static int i40e_resume_port_tx(struct i40e_pf *pf)
 }
 
 /**
+ * i40e_update_dcb_config
+ * @hw: pointer to the HW struct
+ * @enable_mib_change: enable MIB change event
+ *
+ * Update DCB configuration from the firmware
+ **/
+static enum i40e_status_code
+i40e_update_dcb_config(struct i40e_hw *hw, bool enable_mib_change)
+{
+	struct i40e_lldp_variables lldp_cfg;
+	i40e_status ret;
+
+	if (!hw->func_caps.dcb)
+		return I40E_NOT_SUPPORTED;
+
+	/* Read LLDP NVM area */
+	ret = i40e_read_lldp_cfg(hw, &lldp_cfg);
+	if (ret)
+		return I40E_ERR_NOT_READY;
+
+	/* Get DCBX status */
+	ret = i40e_get_dcbx_status(hw, &hw->dcbx_status);
+	if (ret)
+		return ret;
+
+	/* Check the DCBX Status */
+	if (hw->dcbx_status == I40E_DCBX_STATUS_DONE ||
+	    hw->dcbx_status == I40E_DCBX_STATUS_IN_PROGRESS) {
+		/* Get current DCBX configuration */
+		ret = i40e_get_dcb_config(hw);
+		if (ret)
+			return ret;
+	} else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) {
+		return I40E_ERR_NOT_READY;
+	}
+
+	/* Configure the LLDP MIB change event */
+	if (enable_mib_change)
+		ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL);
+
+	return ret;
+}
+
+/**
  * i40e_init_pf_dcb - Initialize DCB configuration
  * @pf: PF being configured
  *
@@ -6376,11 +6471,13 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 	 * Also do not enable DCBx if FW LLDP agent is disabled
 	 */
 	if ((pf->hw_features & I40E_HW_NO_DCB_SUPPORT) ||
-	    (pf->flags & I40E_FLAG_DISABLE_FW_LLDP))
+	    (pf->flags & I40E_FLAG_DISABLE_FW_LLDP)) {
+		dev_info(&pf->pdev->dev, "DCB is not supported or FW LLDP is disabled\n");
+		err = I40E_NOT_SUPPORTED;
 		goto out;
+	}
 
-	/* Get the initial DCB configuration */
-	err = i40e_init_dcb(hw);
+	err = i40e_update_dcb_config(hw, true);
 	if (!err) {
 		/* Device/Function is not DCBX capable */
 		if ((!hw->func_caps.dcb) ||
@@ -6470,6 +6567,12 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 	case I40E_LINK_SPEED_10GB:
 		speed = "10 G";
 		break;
+	case I40E_LINK_SPEED_5GB:
+		speed = "5 G";
+		break;
+	case I40E_LINK_SPEED_2_5GB:
+		speed = "2.5 G";
+		break;
 	case I40E_LINK_SPEED_1GB:
 		speed = "1000 M";
 		break;
@@ -6725,8 +6828,13 @@ void i40e_down(struct i40e_vsi *vsi)
 
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
 		i40e_clean_tx_ring(vsi->tx_rings[i]);
-		if (i40e_enabled_xdp_vsi(vsi))
+		if (i40e_enabled_xdp_vsi(vsi)) {
+			/* Make sure that in-progress ndo_xdp_xmit
+			 * calls are completed.
+			 */
+			synchronize_rcu();
 			i40e_clean_tx_ring(vsi->xdp_rings[i]);
+		}
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
 
@@ -6806,6 +6914,489 @@ static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_del_macvlan_filter
+ * @hw: pointer to the HW structure
+ * @seid: seid of the channel VSI
+ * @macaddr: the mac address to apply as a filter
+ * @aq_err: store the admin Q error
+ *
+ * This function deletes a mac filter on the channel VSI which serves as the
+ * macvlan. Returns 0 on success.
+ **/
+static i40e_status i40e_del_macvlan_filter(struct i40e_hw *hw, u16 seid,
+					   const u8 *macaddr, int *aq_err)
+{
+	struct i40e_aqc_remove_macvlan_element_data element;
+	i40e_status status;
+
+	memset(&element, 0, sizeof(element));
+	ether_addr_copy(element.mac_addr, macaddr);
+	element.vlan_tag = 0;
+	element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
+	status = i40e_aq_remove_macvlan(hw, seid, &element, 1, NULL);
+	*aq_err = hw->aq.asq_last_status;
+
+	return status;
+}
+
+/**
+ * i40e_add_macvlan_filter
+ * @hw: pointer to the HW structure
+ * @seid: seid of the channel VSI
+ * @macaddr: the mac address to apply as a filter
+ * @aq_err: store the admin Q error
+ *
+ * This function adds a mac filter on the channel VSI which serves as the
+ * macvlan. Returns 0 on success.
+ **/
+static i40e_status i40e_add_macvlan_filter(struct i40e_hw *hw, u16 seid,
+					   const u8 *macaddr, int *aq_err)
+{
+	struct i40e_aqc_add_macvlan_element_data element;
+	i40e_status status;
+	u16 cmd_flags = 0;
+
+	ether_addr_copy(element.mac_addr, macaddr);
+	element.vlan_tag = 0;
+	element.queue_number = 0;
+	element.match_method = I40E_AQC_MM_ERR_NO_RES;
+	cmd_flags |= I40E_AQC_MACVLAN_ADD_PERFECT_MATCH;
+	element.flags = cpu_to_le16(cmd_flags);
+	status = i40e_aq_add_macvlan(hw, seid, &element, 1, NULL);
+	*aq_err = hw->aq.asq_last_status;
+
+	return status;
+}
+
+/**
+ * i40e_reset_ch_rings - Reset the queue contexts in a channel
+ * @vsi: the VSI we want to access
+ * @ch: the channel we want to access
+ */
+static void i40e_reset_ch_rings(struct i40e_vsi *vsi, struct i40e_channel *ch)
+{
+	struct i40e_ring *tx_ring, *rx_ring;
+	u16 pf_q;
+	int i;
+
+	for (i = 0; i < ch->num_queue_pairs; i++) {
+		pf_q = ch->base_queue + i;
+		tx_ring = vsi->tx_rings[pf_q];
+		tx_ring->ch = NULL;
+		rx_ring = vsi->rx_rings[pf_q];
+		rx_ring->ch = NULL;
+	}
+}
+
+/**
+ * i40e_free_macvlan_channels
+ * @vsi: the VSI we want to access
+ *
+ * This function frees the Qs of the channel VSI from
+ * the stack and also deletes the channel VSIs which
+ * serve as macvlans.
+ */
+static void i40e_free_macvlan_channels(struct i40e_vsi *vsi)
+{
+	struct i40e_channel *ch, *ch_tmp;
+	int ret;
+
+	if (list_empty(&vsi->macvlan_list))
+		return;
+
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+		struct i40e_vsi *parent_vsi;
+
+		if (i40e_is_channel_macvlan(ch)) {
+			i40e_reset_ch_rings(vsi, ch);
+			clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+			netdev_unbind_sb_channel(vsi->netdev, ch->fwd->netdev);
+			netdev_set_sb_channel(ch->fwd->netdev, 0);
+			kfree(ch->fwd);
+			ch->fwd = NULL;
+		}
+
+		list_del(&ch->list);
+		parent_vsi = ch->parent_vsi;
+		if (!parent_vsi || !ch->initialized) {
+			kfree(ch);
+			continue;
+		}
+
+		/* remove the VSI */
+		ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid,
+					     NULL);
+		if (ret)
+			dev_err(&vsi->back->pdev->dev,
+				"unable to remove channel (%d) for parent VSI(%d)\n",
+				ch->seid, parent_vsi->seid);
+		kfree(ch);
+	}
+	vsi->macvlan_cnt = 0;
+}
+
+/**
+ * i40e_fwd_ring_up - bring the macvlan device up
+ * @vsi: the VSI we want to access
+ * @vdev: macvlan netdevice
+ * @fwd: the private fwd structure
+ */
+static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev,
+			    struct i40e_fwd_adapter *fwd)
+{
+	int ret = 0, num_tc = 1,  i, aq_err;
+	struct i40e_channel *ch, *ch_tmp;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+
+	if (list_empty(&vsi->macvlan_list))
+		return -EINVAL;
+
+	/* Go through the list and find an available channel */
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+		if (!i40e_is_channel_macvlan(ch)) {
+			ch->fwd = fwd;
+			/* record configuration for macvlan interface in vdev */
+			for (i = 0; i < num_tc; i++)
+				netdev_bind_sb_channel_queue(vsi->netdev, vdev,
+							     i,
+							     ch->num_queue_pairs,
+							     ch->base_queue);
+			for (i = 0; i < ch->num_queue_pairs; i++) {
+				struct i40e_ring *tx_ring, *rx_ring;
+				u16 pf_q;
+
+				pf_q = ch->base_queue + i;
+
+				/* Get to TX ring ptr */
+				tx_ring = vsi->tx_rings[pf_q];
+				tx_ring->ch = ch;
+
+				/* Get the RX ring ptr */
+				rx_ring = vsi->rx_rings[pf_q];
+				rx_ring->ch = ch;
+			}
+			break;
+		}
+	}
+
+	/* Guarantee all rings are updated before we update the
+	 * MAC address filter.
+	 */
+	wmb();
+
+	/* Add a mac filter */
+	ret = i40e_add_macvlan_filter(hw, ch->seid, vdev->dev_addr, &aq_err);
+	if (ret) {
+		/* if we cannot add the MAC rule then disable the offload */
+		macvlan_release_l2fw_offload(vdev);
+		for (i = 0; i < ch->num_queue_pairs; i++) {
+			struct i40e_ring *rx_ring;
+			u16 pf_q;
+
+			pf_q = ch->base_queue + i;
+			rx_ring = vsi->rx_rings[pf_q];
+			rx_ring->netdev = NULL;
+		}
+		dev_info(&pf->pdev->dev,
+			 "Error adding mac filter on macvlan err %s, aq_err %s\n",
+			  i40e_stat_str(hw, ret),
+			  i40e_aq_str(hw, aq_err));
+		netdev_err(vdev, "L2fwd offload disabled to L2 filter error\n");
+	}
+
+	return ret;
+}
+
+/**
+ * i40e_setup_macvlans - create the channels which will be macvlans
+ * @vsi: the VSI we want to access
+ * @macvlan_cnt: no. of macvlans to be setup
+ * @qcnt: no. of Qs per macvlan
+ * @vdev: macvlan netdevice
+ */
+static int i40e_setup_macvlans(struct i40e_vsi *vsi, u16 macvlan_cnt, u16 qcnt,
+			       struct net_device *vdev)
+{
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	struct i40e_vsi_context ctxt;
+	u16 sections, qmap, num_qps;
+	struct i40e_channel *ch;
+	int i, pow, ret = 0;
+	u8 offset = 0;
+
+	if (vsi->type != I40E_VSI_MAIN || !macvlan_cnt)
+		return -EINVAL;
+
+	num_qps = vsi->num_queue_pairs - (macvlan_cnt * qcnt);
+
+	/* find the next higher power-of-2 of num queue pairs */
+	pow = fls(roundup_pow_of_two(num_qps) - 1);
+
+	qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) |
+		(pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT);
+
+	/* Setup context bits for the main VSI */
+	sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
+	sections |= I40E_AQ_VSI_PROP_SCHED_VALID;
+	memset(&ctxt, 0, sizeof(ctxt));
+	ctxt.seid = vsi->seid;
+	ctxt.pf_num = vsi->back->hw.pf_id;
+	ctxt.vf_num = 0;
+	ctxt.uplink_seid = vsi->uplink_seid;
+	ctxt.info = vsi->info;
+	ctxt.info.tc_mapping[0] = cpu_to_le16(qmap);
+	ctxt.info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG);
+	ctxt.info.queue_mapping[0] = cpu_to_le16(vsi->base_queue);
+	ctxt.info.valid_sections |= cpu_to_le16(sections);
+
+	/* Reconfigure RSS for main VSI with new max queue count */
+	vsi->rss_size = max_t(u16, num_qps, qcnt);
+	ret = i40e_vsi_config_rss(vsi);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "Failed to reconfig RSS for num_queues (%u)\n",
+			 vsi->rss_size);
+		return ret;
+	}
+	vsi->reconfig_rss = true;
+	dev_dbg(&vsi->back->pdev->dev,
+		"Reconfigured RSS with num_queues (%u)\n", vsi->rss_size);
+	vsi->next_base_queue = num_qps;
+	vsi->cnt_q_avail = vsi->num_queue_pairs - num_qps;
+
+	/* Update the VSI after updating the VSI queue-mapping
+	 * information
+	 */
+	ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "Update vsi tc config failed, err %s aq_err %s\n",
+			 i40e_stat_str(hw, ret),
+			 i40e_aq_str(hw, hw->aq.asq_last_status));
+		return ret;
+	}
+	/* update the local VSI info with updated queue map */
+	i40e_vsi_update_queue_map(vsi, &ctxt);
+	vsi->info.valid_sections = 0;
+
+	/* Create channels for macvlans */
+	INIT_LIST_HEAD(&vsi->macvlan_list);
+	for (i = 0; i < macvlan_cnt; i++) {
+		ch = kzalloc(sizeof(*ch), GFP_KERNEL);
+		if (!ch) {
+			ret = -ENOMEM;
+			goto err_free;
+		}
+		INIT_LIST_HEAD(&ch->list);
+		ch->num_queue_pairs = qcnt;
+		if (!i40e_setup_channel(pf, vsi, ch)) {
+			ret = -EINVAL;
+			goto err_free;
+		}
+		ch->parent_vsi = vsi;
+		vsi->cnt_q_avail -= ch->num_queue_pairs;
+		vsi->macvlan_cnt++;
+		list_add_tail(&ch->list, &vsi->macvlan_list);
+	}
+
+	return ret;
+
+err_free:
+	dev_info(&pf->pdev->dev, "Failed to setup macvlans\n");
+	i40e_free_macvlan_channels(vsi);
+
+	return ret;
+}
+
+/**
+ * i40e_fwd_add - configure macvlans
+ * @netdev: net device to configure
+ * @vdev: macvlan netdevice
+ **/
+static void *i40e_fwd_add(struct net_device *netdev, struct net_device *vdev)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	u16 q_per_macvlan = 0, macvlan_cnt = 0, vectors;
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_fwd_adapter *fwd;
+	int avail_macvlan, ret;
+
+	if ((pf->flags & I40E_FLAG_DCB_ENABLED)) {
+		netdev_info(netdev, "Macvlans are not supported when DCB is enabled\n");
+		return ERR_PTR(-EINVAL);
+	}
+	if ((pf->flags & I40E_FLAG_TC_MQPRIO)) {
+		netdev_info(netdev, "Macvlans are not supported when HW TC offload is on\n");
+		return ERR_PTR(-EINVAL);
+	}
+	if (pf->num_lan_msix < I40E_MIN_MACVLAN_VECTORS) {
+		netdev_info(netdev, "Not enough vectors available to support macvlans\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* The macvlan device has to be a single Q device so that the
+	 * tc_to_txq field can be reused to pick the tx queue.
+	 */
+	if (netif_is_multiqueue(vdev))
+		return ERR_PTR(-ERANGE);
+
+	if (!vsi->macvlan_cnt) {
+		/* reserve bit 0 for the pf device */
+		set_bit(0, vsi->fwd_bitmask);
+
+		/* Try to reserve as many queues as possible for macvlans. First
+		 * reserve 3/4th of max vectors, then half, then quarter and
+		 * calculate Qs per macvlan as you go
+		 */
+		vectors = pf->num_lan_msix;
+		if (vectors <= I40E_MAX_MACVLANS && vectors > 64) {
+			/* allocate 4 Qs per macvlan and 32 Qs to the PF*/
+			q_per_macvlan = 4;
+			macvlan_cnt = (vectors - 32) / 4;
+		} else if (vectors <= 64 && vectors > 32) {
+			/* allocate 2 Qs per macvlan and 16 Qs to the PF*/
+			q_per_macvlan = 2;
+			macvlan_cnt = (vectors - 16) / 2;
+		} else if (vectors <= 32 && vectors > 16) {
+			/* allocate 1 Q per macvlan and 16 Qs to the PF*/
+			q_per_macvlan = 1;
+			macvlan_cnt = vectors - 16;
+		} else if (vectors <= 16 && vectors > 8) {
+			/* allocate 1 Q per macvlan and 8 Qs to the PF */
+			q_per_macvlan = 1;
+			macvlan_cnt = vectors - 8;
+		} else {
+			/* allocate 1 Q per macvlan and 1 Q to the PF */
+			q_per_macvlan = 1;
+			macvlan_cnt = vectors - 1;
+		}
+
+		if (macvlan_cnt == 0)
+			return ERR_PTR(-EBUSY);
+
+		/* Quiesce VSI queues */
+		i40e_quiesce_vsi(vsi);
+
+		/* sets up the macvlans but does not "enable" them */
+		ret = i40e_setup_macvlans(vsi, macvlan_cnt, q_per_macvlan,
+					  vdev);
+		if (ret)
+			return ERR_PTR(ret);
+
+		/* Unquiesce VSI */
+		i40e_unquiesce_vsi(vsi);
+	}
+	avail_macvlan = find_first_zero_bit(vsi->fwd_bitmask,
+					    vsi->macvlan_cnt);
+	if (avail_macvlan >= I40E_MAX_MACVLANS)
+		return ERR_PTR(-EBUSY);
+
+	/* create the fwd struct */
+	fwd = kzalloc(sizeof(*fwd), GFP_KERNEL);
+	if (!fwd)
+		return ERR_PTR(-ENOMEM);
+
+	set_bit(avail_macvlan, vsi->fwd_bitmask);
+	fwd->bit_no = avail_macvlan;
+	netdev_set_sb_channel(vdev, avail_macvlan);
+	fwd->netdev = vdev;
+
+	if (!netif_running(netdev))
+		return fwd;
+
+	/* Set fwd ring up */
+	ret = i40e_fwd_ring_up(vsi, vdev, fwd);
+	if (ret) {
+		/* unbind the queues and drop the subordinate channel config */
+		netdev_unbind_sb_channel(netdev, vdev);
+		netdev_set_sb_channel(vdev, 0);
+
+		kfree(fwd);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return fwd;
+}
+
+/**
+ * i40e_del_all_macvlans - Delete all the mac filters on the channels
+ * @vsi: the VSI we want to access
+ */
+static void i40e_del_all_macvlans(struct i40e_vsi *vsi)
+{
+	struct i40e_channel *ch, *ch_tmp;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	int aq_err, ret = 0;
+
+	if (list_empty(&vsi->macvlan_list))
+		return;
+
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+		if (i40e_is_channel_macvlan(ch)) {
+			ret = i40e_del_macvlan_filter(hw, ch->seid,
+						      i40e_channel_mac(ch),
+						      &aq_err);
+			if (!ret) {
+				/* Reset queue contexts */
+				i40e_reset_ch_rings(vsi, ch);
+				clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+				netdev_unbind_sb_channel(vsi->netdev,
+							 ch->fwd->netdev);
+				netdev_set_sb_channel(ch->fwd->netdev, 0);
+				kfree(ch->fwd);
+				ch->fwd = NULL;
+			}
+		}
+	}
+}
+
+/**
+ * i40e_fwd_del - delete macvlan interfaces
+ * @netdev: net device to configure
+ * @vdev: macvlan netdevice
+ */
+static void i40e_fwd_del(struct net_device *netdev, void *vdev)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_fwd_adapter *fwd = vdev;
+	struct i40e_channel *ch, *ch_tmp;
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	int aq_err, ret = 0;
+
+	/* Find the channel associated with the macvlan and del mac filter */
+	list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+		if (i40e_is_channel_macvlan(ch) &&
+		    ether_addr_equal(i40e_channel_mac(ch),
+				     fwd->netdev->dev_addr)) {
+			ret = i40e_del_macvlan_filter(hw, ch->seid,
+						      i40e_channel_mac(ch),
+						      &aq_err);
+			if (!ret) {
+				/* Reset queue contexts */
+				i40e_reset_ch_rings(vsi, ch);
+				clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+				netdev_unbind_sb_channel(netdev, fwd->netdev);
+				netdev_set_sb_channel(fwd->netdev, 0);
+				kfree(ch->fwd);
+				ch->fwd = NULL;
+			} else {
+				dev_info(&pf->pdev->dev,
+					 "Error deleting mac filter on macvlan err %s, aq_err %s\n",
+					  i40e_stat_str(hw, ret),
+					  i40e_aq_str(hw, aq_err));
+			}
+			break;
+		}
+	}
+}
+
+/**
  * i40e_setup_tc - configure multiple traffic classes
  * @netdev: net device to configure
  * @type_data: tc offload data
@@ -6818,10 +7409,12 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data)
 	struct i40e_pf *pf = vsi->back;
 	u8 enabled_tc = 0, num_tc, hw;
 	bool need_reset = false;
+	int old_queue_pairs;
 	int ret = -EINVAL;
 	u16 mode;
 	int i;
 
+	old_queue_pairs = vsi->num_queue_pairs;
 	num_tc = mqprio_qopt->qopt.num_tc;
 	hw = mqprio_qopt->qopt.hw;
 	mode = mqprio_qopt->mode;
@@ -6898,6 +7491,10 @@ config_tc:
 			    vsi->seid);
 		need_reset = true;
 		goto exit;
+	} else {
+		dev_info(&vsi->back->pdev->dev,
+			 "Setup channel (id:%u) utilizing num_queues %d\n",
+			 vsi->seid, vsi->tc_config.tc_info[0].qcount);
 	}
 
 	if (pf->flags & I40E_FLAG_TC_MQPRIO) {
@@ -6922,6 +7519,7 @@ config_tc:
 		}
 		ret = i40e_configure_queue_channels(vsi);
 		if (ret) {
+			vsi->num_queue_pairs = old_queue_pairs;
 			netdev_info(netdev,
 				    "Failed configuring queue channels\n");
 			need_reset = true;
@@ -7161,19 +7759,21 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
 /**
  * i40e_parse_cls_flower - Parse tc flower filters provided by kernel
  * @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  * @filter: Pointer to cloud filter structure
  *
  **/
 static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
-				 struct tc_cls_flower_offload *f,
+				 struct flow_cls_offload *f,
 				 struct i40e_cloud_filter *filter)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0;
 	struct i40e_pf *pf = vsi->back;
 	u8 field_flags = 0;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -7183,143 +7783,109 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
 		dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n",
-			f->dissector->used_keys);
+			dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->key);
-
-		struct flow_dissector_key_keyid *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
 
-		if (mask->keyid != 0)
+		flow_rule_match_enc_keyid(rule, &match);
+		if (match.mask->keyid != 0)
 			field_flags |= I40E_CLOUD_FIELD_TEN_ID;
 
-		filter->tenant_id = be32_to_cpu(key->keyid);
+		filter->tenant_id = be32_to_cpu(match.key->keyid);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
-
-		n_proto_key = ntohs(key->n_proto);
-		n_proto_mask = ntohs(mask->n_proto);
+		flow_rule_match_basic(rule, &match);
+		n_proto_key = ntohs(match.key->n_proto);
+		n_proto_mask = ntohs(match.mask->n_proto);
 
 		if (n_proto_key == ETH_P_ALL) {
 			n_proto_key = 0;
 			n_proto_mask = 0;
 		}
 		filter->n_proto = n_proto_key & n_proto_mask;
-		filter->ip_proto = key->ip_proto;
+		filter->ip_proto = match.key->ip_proto;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
+		flow_rule_match_eth_addrs(rule, &match);
 
 		/* use is_broadcast and is_zero to check for all 0xf or 0 */
-		if (!is_zero_ether_addr(mask->dst)) {
-			if (is_broadcast_ether_addr(mask->dst)) {
+		if (!is_zero_ether_addr(match.mask->dst)) {
+			if (is_broadcast_ether_addr(match.mask->dst)) {
 				field_flags |= I40E_CLOUD_FIELD_OMAC;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n",
-					mask->dst);
+					match.mask->dst);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (!is_zero_ether_addr(mask->src)) {
-			if (is_broadcast_ether_addr(mask->src)) {
+		if (!is_zero_ether_addr(match.mask->src)) {
+			if (is_broadcast_ether_addr(match.mask->src)) {
 				field_flags |= I40E_CLOUD_FIELD_IMAC;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n",
-					mask->src);
+					match.mask->src);
 				return I40E_ERR_CONFIG;
 			}
 		}
-		ether_addr_copy(filter->dst_mac, key->dst);
-		ether_addr_copy(filter->src_mac, key->src);
+		ether_addr_copy(filter->dst_mac, match.key->dst);
+		ether_addr_copy(filter->src_mac, match.key->src);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
-		if (mask->vlan_id) {
-			if (mask->vlan_id == VLAN_VID_MASK) {
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_id) {
+			if (match.mask->vlan_id == VLAN_VID_MASK) {
 				field_flags |= I40E_CLOUD_FIELD_IVLAN;
 
 			} else {
 				dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n",
-					mask->vlan_id);
+					match.mask->vlan_id);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		filter->vlan_id = cpu_to_be16(key->vlan_id);
+		filter->vlan_id = cpu_to_be16(match.key->vlan_id);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->mask);
-
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be32(0xffffffff)) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_ipv4_addrs(rule, &match);
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be32(0xffffffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n",
-					&mask->dst);
+					&match.mask->dst);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (mask->src) {
-			if (mask->src == cpu_to_be32(0xffffffff)) {
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be32(0xffffffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n",
-					&mask->src);
+					&match.mask->src);
 				return I40E_ERR_CONFIG;
 			}
 		}
@@ -7328,70 +7894,60 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n");
 			return I40E_ERR_CONFIG;
 		}
-		filter->dst_ipv4 = key->dst;
-		filter->src_ipv4 = key->src;
+		filter->dst_ipv4 = match.key->dst;
+		filter->src_ipv4 = match.key->src;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->mask);
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
 
 		/* src and dest IPV6 address should not be LOOPBACK
 		 * (0:0:0:0:0:0:0:1), which can be represented as ::1
 		 */
-		if (ipv6_addr_loopback(&key->dst) ||
-		    ipv6_addr_loopback(&key->src)) {
+		if (ipv6_addr_loopback(&match.key->dst) ||
+		    ipv6_addr_loopback(&match.key->src)) {
 			dev_err(&pf->pdev->dev,
 				"Bad ipv6, addr is LOOPBACK\n");
 			return I40E_ERR_CONFIG;
 		}
-		if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
+		if (!ipv6_addr_any(&match.mask->dst) ||
+		    !ipv6_addr_any(&match.mask->src))
 			field_flags |= I40E_CLOUD_FIELD_IIP;
 
-		memcpy(&filter->src_ipv6, &key->src.s6_addr32,
+		memcpy(&filter->src_ipv6, &match.key->src.s6_addr32,
 		       sizeof(filter->src_ipv6));
-		memcpy(&filter->dst_ipv6, &key->dst.s6_addr32,
+		memcpy(&filter->dst_ipv6, &match.key->dst.s6_addr32,
 		       sizeof(filter->dst_ipv6));
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
-		if (mask->src) {
-			if (mask->src == cpu_to_be16(0xffff)) {
+		flow_rule_match_ports(rule, &match);
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be16(0xffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n",
-					be16_to_cpu(mask->src));
+					be16_to_cpu(match.mask->src));
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be16(0xffff)) {
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be16(0xffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n",
-					be16_to_cpu(mask->dst));
+					be16_to_cpu(match.mask->dst));
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		filter->dst_port = key->dst;
-		filter->src_port = key->src;
+		filter->dst_port = match.key->dst;
+		filter->src_port = match.key->src;
 
 		switch (filter->ip_proto) {
 		case IPPROTO_TCP:
@@ -7445,11 +8001,11 @@ static int i40e_handle_tclass(struct i40e_vsi *vsi, u32 tc,
 /**
  * i40e_configure_clsflower - Configure tc flower filters
  * @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  *
  **/
 static int i40e_configure_clsflower(struct i40e_vsi *vsi,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid);
 	struct i40e_cloud_filter *filter = NULL;
@@ -7541,11 +8097,11 @@ static struct i40e_cloud_filter *i40e_find_cloud_filter(struct i40e_vsi *vsi,
 /**
  * i40e_delete_clsflower - Remove tc flower filters
  * @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  *
  **/
 static int i40e_delete_clsflower(struct i40e_vsi *vsi,
-				 struct tc_cls_flower_offload *cls_flower)
+				 struct flow_cls_offload *cls_flower)
 {
 	struct i40e_cloud_filter *filter = NULL;
 	struct i40e_pf *pf = vsi->back;
@@ -7588,16 +8144,16 @@ static int i40e_delete_clsflower(struct i40e_vsi *vsi,
  * @type_data: offload data
  **/
 static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	struct i40e_vsi *vsi = np->vsi;
 
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return i40e_configure_clsflower(vsi, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return i40e_delete_clsflower(vsi, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return -EOPNOTSUPP;
 	default:
 		return -EOPNOTSUPP;
@@ -7621,34 +8177,21 @@ static int i40e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int i40e_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct i40e_netdev_priv *np = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
-					     np, np, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(i40e_block_cb_list);
 
 static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 			   void *type_data)
 {
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+
 	switch (type) {
 	case TC_SETUP_QDISC_MQPRIO:
 		return i40e_setup_tc(netdev, type_data);
 	case TC_SETUP_BLOCK:
-		return i40e_setup_tc_block(netdev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &i40e_block_cb_list,
+						  i40e_setup_tc_block_cb,
+						  np, np, true);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -8131,8 +8674,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 		i40e_service_event_schedule(pf);
 	} else {
 		i40e_pf_unquiesce_all_vsi(pf);
-	set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
-	set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
+		set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
+		set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
 	}
 
 exit:
@@ -8546,7 +9089,7 @@ static void i40e_link_event(struct i40e_pf *pf)
 	/* Notify the base of the switch tree connected to
 	 * the link.  Floating VEBs are not notified.
 	 */
-	if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+	if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
 		i40e_veb_link_event(pf->veb[pf->lan_veb], new_link);
 	else
 		i40e_vsi_link_event(vsi, new_link);
@@ -9304,6 +9847,11 @@ static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired)
 			dev_warn(&pf->pdev->dev,
 				 "shutdown_lan_hmc failed: %d\n", ret);
 	}
+
+	/* Save the current PTP time so that we can restore the time after the
+	 * reset completes.
+	 */
+	i40e_ptp_save_hw_time(pf);
 }
 
 /**
@@ -9396,6 +9944,7 @@ static int i40e_reset(struct i40e_pf *pf)
  **/
 static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 {
+	int old_recovery_mode_bit = test_bit(__I40E_RECOVERY_MODE, pf->state);
 	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
 	struct i40e_hw *hw = &pf->hw;
 	u8 set_fc_aq_fail = 0;
@@ -9403,7 +9952,14 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	u32 val;
 	int v;
 
-	if (test_bit(__I40E_DOWN, pf->state))
+	if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
+	    i40e_check_recovery_mode(pf)) {
+		i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev);
+	}
+
+	if (test_bit(__I40E_DOWN, pf->state) &&
+	    !test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+	    !old_recovery_mode_bit)
 		goto clear_recovery;
 	dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
 
@@ -9432,6 +9988,44 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state))
 		i40e_verify_eeprom(pf);
 
+	/* if we are going out of or into recovery mode we have to act
+	 * accordingly with regard to resources initialization
+	 * and deinitialization
+	 */
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state) ||
+	    old_recovery_mode_bit) {
+		if (i40e_get_capabilities(pf,
+					  i40e_aqc_opc_list_func_capabilities))
+			goto end_unlock;
+
+		if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+			/* we're staying in recovery mode so we'll reinitialize
+			 * misc vector here
+			 */
+			if (i40e_setup_misc_vector_for_recovery_mode(pf))
+				goto end_unlock;
+		} else {
+			if (!lock_acquired)
+				rtnl_lock();
+			/* we're going out of recovery mode so we'll free
+			 * the IRQ allocated specifically for recovery mode
+			 * and restore the interrupt scheme
+			 */
+			free_irq(pf->pdev->irq, pf);
+			i40e_clear_interrupt_scheme(pf);
+			if (i40e_restore_interrupt_scheme(pf))
+				goto end_unlock;
+		}
+
+		/* tell the firmware that we're starting */
+		i40e_send_version(pf);
+
+		/* bail out in case recovery mode was detected, as there is
+		 * no need for further configuration.
+		 */
+		goto end_unlock;
+	}
+
 	i40e_clear_pxe_mode(hw);
 	ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
 	if (ret)
@@ -9683,7 +10277,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
 	bool mdd_detected = false;
-	bool pf_mdd_detected = false;
 	struct i40e_vf *vf;
 	u32 reg;
 	int i;
@@ -9729,19 +10322,12 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 		reg = rd32(hw, I40E_PF_MDET_TX);
 		if (reg & I40E_PF_MDET_TX_VALID_MASK) {
 			wr32(hw, I40E_PF_MDET_TX, 0xFFFF);
-			dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
-			pf_mdd_detected = true;
+			dev_dbg(&pf->pdev->dev, "TX driver issue detected on PF\n");
 		}
 		reg = rd32(hw, I40E_PF_MDET_RX);
 		if (reg & I40E_PF_MDET_RX_VALID_MASK) {
 			wr32(hw, I40E_PF_MDET_RX, 0xFFFF);
-			dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n");
-			pf_mdd_detected = true;
-		}
-		/* Queue belongs to the PF, initiate a reset */
-		if (pf_mdd_detected) {
-			set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
-			i40e_service_event_schedule(pf);
+			dev_dbg(&pf->pdev->dev, "RX driver issue detected on PF\n");
 		}
 	}
 
@@ -9754,6 +10340,9 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 			vf->num_mdd_events++;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
+			dev_info(&pf->pdev->dev,
+				 "Use PF Control I/F to re-enable the VF\n");
+			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
 		}
 
 		reg = rd32(hw, I40E_VP_MDET_RX(i));
@@ -9762,11 +10351,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 			vf->num_mdd_events++;
 			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
 				 i);
-		}
-
-		if (vf->num_mdd_events > I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED) {
-			dev_info(&pf->pdev->dev,
-				 "Too many MDD events on VF %d, disabled\n", i);
 			dev_info(&pf->pdev->dev,
 				 "Use PF Control I/F to re-enable the VF\n");
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
@@ -9893,31 +10477,38 @@ static void i40e_service_task(struct work_struct *work)
 	unsigned long start_time = jiffies;
 
 	/* don't bother with service tasks if a reset is in progress */
-	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+	if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+	    test_bit(__I40E_SUSPENDED, pf->state))
 		return;
 
 	if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
 		return;
 
-	i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
-	i40e_sync_filters_subtask(pf);
-	i40e_reset_subtask(pf);
-	i40e_handle_mdd_event(pf);
-	i40e_vc_process_vflr_event(pf);
-	i40e_watchdog_subtask(pf);
-	i40e_fdir_reinit_subtask(pf);
-	if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
-		/* Client subtask will reopen next time through. */
-		i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+	if (!test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+		i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
+		i40e_sync_filters_subtask(pf);
+		i40e_reset_subtask(pf);
+		i40e_handle_mdd_event(pf);
+		i40e_vc_process_vflr_event(pf);
+		i40e_watchdog_subtask(pf);
+		i40e_fdir_reinit_subtask(pf);
+		if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
+			/* Client subtask will reopen next time through. */
+			i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi],
+							   true);
+		} else {
+			i40e_client_subtask(pf);
+			if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
+					       pf->state))
+				i40e_notify_client_of_l2_param_changes(
+								pf->vsi[pf->lan_vsi]);
+		}
+		i40e_sync_filters_subtask(pf);
+		i40e_sync_udp_filters_subtask(pf);
 	} else {
-		i40e_client_subtask(pf);
-		if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
-				       pf->state))
-			i40e_notify_client_of_l2_param_changes(
-							pf->vsi[pf->lan_vsi]);
-	}
-	i40e_sync_filters_subtask(pf);
-	i40e_sync_udp_filters_subtask(pf);
+		i40e_reset_subtask(pf);
+	}
+
 	i40e_clean_adminq_subtask(pf);
 
 	/* flush memory to make sure state is correct before next watchdog */
@@ -9959,8 +10550,12 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 	switch (vsi->type) {
 	case I40E_VSI_MAIN:
 		vsi->alloc_queue_pairs = pf->num_lan_qps;
-		vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
-				      I40E_REQ_DESCRIPTOR_MULTIPLE);
+		if (!vsi->num_tx_desc)
+			vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+						 I40E_REQ_DESCRIPTOR_MULTIPLE);
+		if (!vsi->num_rx_desc)
+			vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+						 I40E_REQ_DESCRIPTOR_MULTIPLE);
 		if (pf->flags & I40E_FLAG_MSIX_ENABLED)
 			vsi->num_q_vectors = pf->num_lan_msix;
 		else
@@ -9970,22 +10565,32 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi)
 
 	case I40E_VSI_FDIR:
 		vsi->alloc_queue_pairs = 1;
-		vsi->num_desc = ALIGN(I40E_FDIR_RING_COUNT,
-				      I40E_REQ_DESCRIPTOR_MULTIPLE);
+		vsi->num_tx_desc = ALIGN(I40E_FDIR_RING_COUNT,
+					 I40E_REQ_DESCRIPTOR_MULTIPLE);
+		vsi->num_rx_desc = ALIGN(I40E_FDIR_RING_COUNT,
+					 I40E_REQ_DESCRIPTOR_MULTIPLE);
 		vsi->num_q_vectors = pf->num_fdsb_msix;
 		break;
 
 	case I40E_VSI_VMDQ2:
 		vsi->alloc_queue_pairs = pf->num_vmdq_qps;
-		vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
-				      I40E_REQ_DESCRIPTOR_MULTIPLE);
+		if (!vsi->num_tx_desc)
+			vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+						 I40E_REQ_DESCRIPTOR_MULTIPLE);
+		if (!vsi->num_rx_desc)
+			vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+						 I40E_REQ_DESCRIPTOR_MULTIPLE);
 		vsi->num_q_vectors = pf->num_vmdq_msix;
 		break;
 
 	case I40E_VSI_SRIOV:
 		vsi->alloc_queue_pairs = pf->num_vf_qps;
-		vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
-				      I40E_REQ_DESCRIPTOR_MULTIPLE);
+		if (!vsi->num_tx_desc)
+			vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+						 I40E_REQ_DESCRIPTOR_MULTIPLE);
+		if (!vsi->num_rx_desc)
+			vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+						 I40E_REQ_DESCRIPTOR_MULTIPLE);
 		break;
 
 	default:
@@ -10098,6 +10703,12 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	hash_init(vsi->mac_filter_hash);
 	vsi->irqs_ready = false;
 
+	if (type == I40E_VSI_MAIN) {
+		vsi->af_xdp_zc_qps = bitmap_zalloc(pf->num_lan_qps, GFP_KERNEL);
+		if (!vsi->af_xdp_zc_qps)
+			goto err_rings;
+	}
+
 	ret = i40e_set_num_rings_in_vsi(vsi);
 	if (ret)
 		goto err_rings;
@@ -10116,6 +10727,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	goto unlock_pf;
 
 err_rings:
+	bitmap_free(vsi->af_xdp_zc_qps);
 	pf->next_vsi = i - 1;
 	kfree(vsi);
 unlock_pf:
@@ -10196,6 +10808,7 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi)
 	i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
 	i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
 
+	bitmap_free(vsi->af_xdp_zc_qps);
 	i40e_vsi_free_arrays(vsi, true);
 	i40e_clear_rss_config_user(vsi);
 
@@ -10253,7 +10866,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		ring->vsi = vsi;
 		ring->netdev = vsi->netdev;
 		ring->dev = &pf->pdev->dev;
-		ring->count = vsi->num_desc;
+		ring->count = vsi->num_tx_desc;
 		ring->size = 0;
 		ring->dcb_tc = 0;
 		if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
@@ -10270,7 +10883,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi)
 		ring->vsi = vsi;
 		ring->netdev = NULL;
 		ring->dev = &pf->pdev->dev;
-		ring->count = vsi->num_desc;
+		ring->count = vsi->num_tx_desc;
 		ring->size = 0;
 		ring->dcb_tc = 0;
 		if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
@@ -10286,7 +10899,7 @@ setup_rx:
 		ring->vsi = vsi;
 		ring->netdev = vsi->netdev;
 		ring->dev = &pf->pdev->dev;
-		ring->count = vsi->num_desc;
+		ring->count = vsi->num_rx_desc;
 		ring->size = 0;
 		ring->dcb_tc = 0;
 		ring->itr_setting = pf->rx_itr_default;
@@ -10732,6 +11345,48 @@ err_unwind:
 }
 
 /**
+ * i40e_setup_misc_vector_for_recovery_mode - Setup the misc vector to handle
+ * non queue events in recovery mode
+ * @pf: board private structure
+ *
+ * This sets up the handler for MSIX 0 or MSI/legacy, which is used to manage
+ * the non-queue interrupts, e.g. AdminQ and errors in recovery mode.
+ * This is handled differently than in recovery mode since no Tx/Rx resources
+ * are being allocated.
+ **/
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf)
+{
+	int err;
+
+	if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+		err = i40e_setup_misc_vector(pf);
+
+		if (err) {
+			dev_info(&pf->pdev->dev,
+				 "MSI-X misc vector request failed, error %d\n",
+				 err);
+			return err;
+		}
+	} else {
+		u32 flags = pf->flags & I40E_FLAG_MSI_ENABLED ? 0 : IRQF_SHARED;
+
+		err = request_irq(pf->pdev->irq, i40e_intr, flags,
+				  pf->int_name, pf);
+
+		if (err) {
+			dev_info(&pf->pdev->dev,
+				 "MSI/legacy misc vector request failed, error %d\n",
+				 err);
+			return err;
+		}
+		i40e_enable_misc_int_causes(pf);
+		i40e_irq_dynamic_enable_icr0(pf);
+	}
+
+	return 0;
+}
+
+/**
  * i40e_setup_misc_vector - Setup the misc vector to handle non queue events
  * @pf: board private structure
  *
@@ -11042,6 +11697,7 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 	if (!(pf->flags & I40E_FLAG_RSS_ENABLED))
 		return 0;
 
+	queue_count = min_t(int, queue_count, num_online_cpus());
 	new_rss_size = min_t(int, queue_count, pf->rss_size_max);
 
 	if (queue_count != vsi->num_queue_pairs) {
@@ -11481,6 +12137,9 @@ static int i40e_set_features(struct net_device *netdev,
 		return -EINVAL;
 	}
 
+	if (!(features & NETIF_F_HW_L2FW_DOFFLOAD) && vsi->macvlan_cnt)
+		i40e_del_all_macvlans(vsi);
+
 	need_reset = i40e_set_ntuple(pf, features);
 
 	if (need_reset)
@@ -11644,7 +12303,8 @@ static int i40e_get_phys_port_id(struct net_device *netdev,
 static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			    struct net_device *dev,
 			    const unsigned char *addr, u16 vid,
-			    u16 flags)
+			    u16 flags,
+			    struct netlink_ext_ack *extack)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -11895,6 +12555,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	/* Kick start the NAPI context if there is an AF_XDP socket open
+	 * on that queue id. This so that receiving will start.
+	 */
+	if (need_reset && prog)
+		for (i = 0; i < vsi->num_queue_pairs; i++)
+			if (vsi->xdp_rings[i]->xsk_umem)
+				(void)i40e_xsk_async_xmit(vsi->netdev, i);
+
 	return 0;
 }
 
@@ -11955,8 +12623,13 @@ static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair)
 static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair)
 {
 	i40e_clean_tx_ring(vsi->tx_rings[queue_pair]);
-	if (i40e_enabled_xdp_vsi(vsi))
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		/* Make sure that in-progress ndo_xdp_xmit calls are
+		 * completed.
+		 */
+		synchronize_rcu();
 		i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]);
+	}
 	i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
 }
 
@@ -12168,9 +12841,6 @@ static int i40e_xdp(struct net_device *dev,
 	case XDP_QUERY_PROG:
 		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
 		return 0;
-	case XDP_QUERY_XSK_UMEM:
-		return i40e_xsk_umem_query(vsi, &xdp->xsk.umem,
-					   xdp->xsk.queue_id);
 	case XDP_SETUP_XSK_UMEM:
 		return i40e_xsk_umem_setup(vsi, xdp->xsk.umem,
 					   xdp->xsk.queue_id);
@@ -12214,6 +12884,8 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_bpf		= i40e_xdp,
 	.ndo_xdp_xmit		= i40e_xdp_xmit,
 	.ndo_xsk_async_xmit	= i40e_xsk_async_xmit,
+	.ndo_dfwd_add_station	= i40e_fwd_add,
+	.ndo_dfwd_del_station	= i40e_fwd_del,
 };
 
 /**
@@ -12273,6 +12945,9 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	/* record features VLANs can make use of */
 	netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
 
+	/* enable macvlan offloads */
+	netdev->hw_features |= NETIF_F_HW_L2FW_DOFFLOAD;
+
 	hw_features = hw_enc_features		|
 		      NETIF_F_HW_VLAN_CTAG_TX	|
 		      NETIF_F_HW_VLAN_CTAG_RX;
@@ -12385,7 +13060,7 @@ int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi)
 	struct i40e_pf *pf = vsi->back;
 
 	/* Uplink is not a bridge so default to VEB */
-	if (vsi->veb_idx == I40E_NO_VEB)
+	if (vsi->veb_idx >= I40E_MAX_VEB)
 		return 1;
 
 	veb = pf->veb[vsi->veb_idx];
@@ -13443,7 +14118,7 @@ static void i40e_setup_pf_switch_element(struct i40e_pf *pf,
 		/* Main VEB? */
 		if (uplink_seid != pf->mac_seid)
 			break;
-		if (pf->lan_veb == I40E_NO_VEB) {
+		if (pf->lan_veb >= I40E_MAX_VEB) {
 			int v;
 
 			/* find existing or else empty VEB */
@@ -13453,13 +14128,15 @@ static void i40e_setup_pf_switch_element(struct i40e_pf *pf,
 					break;
 				}
 			}
-			if (pf->lan_veb == I40E_NO_VEB) {
+			if (pf->lan_veb >= I40E_MAX_VEB) {
 				v = i40e_veb_mem_alloc(pf);
 				if (v < 0)
 					break;
 				pf->lan_veb = v;
 			}
 		}
+		if (pf->lan_veb >= I40E_MAX_VEB)
+			break;
 
 		pf->veb[pf->lan_veb]->seid = seid;
 		pf->veb[pf->lan_veb]->uplink_seid = pf->mac_seid;
@@ -13613,7 +14290,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
 		/* Set up the PF VSI associated with the PF's main VSI
 		 * that is already in the HW switch
 		 */
-		if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+		if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
 			uplink_seid = pf->veb[pf->lan_veb]->seid;
 		else
 			uplink_seid = pf->mac_seid;
@@ -13859,6 +14536,148 @@ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
 }
 
 /**
+ * i40e_set_fec_in_flags - helper function for setting FEC options in flags
+ * @fec_cfg: FEC option to set in flags
+ * @flags: ptr to flags in which we set FEC option
+ **/
+void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags)
+{
+	if (fec_cfg & I40E_AQ_SET_FEC_AUTO)
+		*flags |= I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC;
+	if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_RS) ||
+	    (fec_cfg & I40E_AQ_SET_FEC_ABILITY_RS)) {
+		*flags |= I40E_FLAG_RS_FEC;
+		*flags &= ~I40E_FLAG_BASE_R_FEC;
+	}
+	if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_KR) ||
+	    (fec_cfg & I40E_AQ_SET_FEC_ABILITY_KR)) {
+		*flags |= I40E_FLAG_BASE_R_FEC;
+		*flags &= ~I40E_FLAG_RS_FEC;
+	}
+	if (fec_cfg == 0)
+		*flags &= ~(I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC);
+}
+
+/**
+ * i40e_check_recovery_mode - check if we are running transition firmware
+ * @pf: board private structure
+ *
+ * Check registers indicating the firmware runs in recovery mode. Sets the
+ * appropriate driver state.
+ *
+ * Returns true if the recovery mode was detected, false otherwise
+ **/
+static bool i40e_check_recovery_mode(struct i40e_pf *pf)
+{
+	u32 val = rd32(&pf->hw, I40E_GL_FWSTS);
+
+	if (val & I40E_GL_FWSTS_FWS1B_MASK) {
+		dev_notice(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n");
+		dev_notice(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
+		set_bit(__I40E_RECOVERY_MODE, pf->state);
+
+		return true;
+	}
+	if (test_and_clear_bit(__I40E_RECOVERY_MODE, pf->state))
+		dev_info(&pf->pdev->dev, "Reinitializing in normal mode with full functionality.\n");
+
+	return false;
+}
+
+/**
+ * i40e_init_recovery_mode - initialize subsystems needed in recovery mode
+ * @pf: board private structure
+ * @hw: ptr to the hardware info
+ *
+ * This function does a minimal setup of all subsystems needed for running
+ * recovery mode.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw)
+{
+	struct i40e_vsi *vsi;
+	int err;
+	int v_idx;
+
+	pci_save_state(pf->pdev);
+
+	/* set up periodic task facility */
+	timer_setup(&pf->service_timer, i40e_service_timer, 0);
+	pf->service_timer_period = HZ;
+
+	INIT_WORK(&pf->service_task, i40e_service_task);
+	clear_bit(__I40E_SERVICE_SCHED, pf->state);
+
+	err = i40e_init_interrupt_scheme(pf);
+	if (err)
+		goto err_switch_setup;
+
+	/* The number of VSIs reported by the FW is the minimum guaranteed
+	 * to us; HW supports far more and we share the remaining pool with
+	 * the other PFs. We allocate space for more than the guarantee with
+	 * the understanding that we might not get them all later.
+	 */
+	if (pf->hw.func_caps.num_vsis < I40E_MIN_VSI_ALLOC)
+		pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
+	else
+		pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+
+	/* Set up the vsi struct and our local tracking of the MAIN PF vsi. */
+	pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
+			  GFP_KERNEL);
+	if (!pf->vsi) {
+		err = -ENOMEM;
+		goto err_switch_setup;
+	}
+
+	/* We allocate one VSI which is needed as absolute minimum
+	 * in order to register the netdev
+	 */
+	v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN);
+	if (v_idx < 0)
+		goto err_switch_setup;
+	pf->lan_vsi = v_idx;
+	vsi = pf->vsi[v_idx];
+	if (!vsi)
+		goto err_switch_setup;
+	vsi->alloc_queue_pairs = 1;
+	err = i40e_config_netdev(vsi);
+	if (err)
+		goto err_switch_setup;
+	err = register_netdev(vsi->netdev);
+	if (err)
+		goto err_switch_setup;
+	vsi->netdev_registered = true;
+	i40e_dbg_pf_init(pf);
+
+	err = i40e_setup_misc_vector_for_recovery_mode(pf);
+	if (err)
+		goto err_switch_setup;
+
+	/* tell the firmware that we're starting */
+	i40e_send_version(pf);
+
+	/* since everything's happy, start the service_task timer */
+	mod_timer(&pf->service_timer,
+		  round_jiffies(jiffies + pf->service_timer_period));
+
+	return 0;
+
+err_switch_setup:
+	i40e_reset_interrupt_capability(pf);
+	del_timer_sync(&pf->service_timer);
+	i40e_shutdown_adminq(hw);
+	iounmap(hw->hw_addr);
+	pci_disable_pcie_error_reporting(pf->pdev);
+	pci_release_mem_regions(pf->pdev);
+	pci_disable_device(pf->pdev);
+	kfree(pf);
+
+	return err;
+}
+
+/**
  * i40e_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in i40e_pci_tbl
@@ -13927,7 +14746,17 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pf->ioremap_len = min_t(int, pci_resource_len(pdev, 0),
 				I40E_MAX_CSR_SPACE);
-
+	/* We believe that the highest register to read is
+	 * I40E_GLGEN_STAT_CLEAR, so we check if the BAR size
+	 * is not less than that before mapping to prevent a
+	 * kernel panic.
+	 */
+	if (pf->ioremap_len < I40E_GLGEN_STAT_CLEAR) {
+		dev_err(&pdev->dev, "Cannot map registers, bar size 0x%X too small, aborting\n",
+			pf->ioremap_len);
+		err = -ENOMEM;
+		goto err_ioremap;
+	}
 	hw->hw_addr = ioremap(pci_resource_start(pdev, 0), pf->ioremap_len);
 	if (!hw->hw_addr) {
 		err = -EIO;
@@ -13955,6 +14784,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_LIST_HEAD(&pf->l3_flex_pit_list);
 	INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+	INIT_LIST_HEAD(&pf->ddp_old_prof);
 
 	/* set up the locks for the AQ, do this only once in probe
 	 * and destroy them only once in remove
@@ -13982,13 +14812,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* Reset here to make sure all is clean and to define PF 'n' */
 	i40e_clear_hw(hw);
-	err = i40e_pf_reset(hw);
-	if (err) {
-		dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
-		goto err_pf_reset;
+	if (!i40e_check_recovery_mode(pf)) {
+		err = i40e_pf_reset(hw);
+		if (err) {
+			dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
+			goto err_pf_reset;
+		}
+		pf->pfr_count++;
 	}
-	pf->pfr_count++;
-
 	hw->aq.num_arq_entries = I40E_AQ_LEN;
 	hw->aq.num_asq_entries = I40E_AQ_LEN;
 	hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE;
@@ -14013,7 +14844,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err) {
 		if (err == I40E_ERR_FIRMWARE_API_VERSION)
 			dev_info(&pdev->dev,
-				 "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+				 "The driver for the device stopped because the NVM image v%u.%u is newer than expected v%u.%u. You must install the most recent version of the network driver.\n",
+				 hw->aq.api_maj_ver,
+				 hw->aq.api_min_ver,
+				 I40E_FW_API_VERSION_MAJOR,
+				 I40E_FW_MINOR_VERSION(hw));
 		else
 			dev_info(&pdev->dev,
 				 "The driver for the device stopped because the device firmware failed to init. Try updating your NVM image.\n");
@@ -14022,19 +14857,28 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	i40e_get_oem_version(hw);
 
-	/* provide nvm, fw, api versions */
-	dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n",
+	/* provide nvm, fw, api versions, vendor:device id, subsys vendor:device id */
+	dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s [%04x:%04x] [%04x:%04x]\n",
 		 hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build,
 		 hw->aq.api_maj_ver, hw->aq.api_min_ver,
-		 i40e_nvm_version_str(hw));
+		 i40e_nvm_version_str(hw), hw->vendor_id, hw->device_id,
+		 hw->subsystem_vendor_id, hw->subsystem_device_id);
 
 	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
 	    hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
 		dev_info(&pdev->dev,
-			 "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+			 "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n",
+			 hw->aq.api_maj_ver,
+			 hw->aq.api_min_ver,
+			 I40E_FW_API_VERSION_MAJOR,
+			 I40E_FW_MINOR_VERSION(hw));
 	else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
 		dev_info(&pdev->dev,
-			 "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+			 "The driver for the device detected an older version of the NVM image v%u.%u than expected v%u.%u. Please update the NVM image.\n",
+			 hw->aq.api_maj_ver,
+			 hw->aq.api_min_ver,
+			 I40E_FW_API_VERSION_MAJOR,
+			 I40E_FW_MINOR_VERSION(hw));
 
 	i40e_verify_eeprom(pf);
 
@@ -14043,6 +14887,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n");
 
 	i40e_clear_pxe_mode(hw);
+
 	err = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
 	if (err)
 		goto err_adminq_setup;
@@ -14053,6 +14898,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_sw_init;
 	}
 
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state))
+		return i40e_init_recovery_mode(pf, hw);
+
 	err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
 				hw->func_caps.num_rx_qp, 0, 0);
 	if (err) {
@@ -14073,7 +14921,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	if (pf->hw_features & I40E_HW_STOP_FW_LLDP) {
 		dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n");
-		i40e_aq_stop_lldp(hw, true, NULL);
+		i40e_aq_stop_lldp(hw, true, false, NULL);
 	}
 
 	/* allow a platform config to override the HW addr */
@@ -14093,6 +14941,11 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_drvdata(pdev, pf);
 	pci_save_state(pdev);
 
+	dev_info(&pdev->dev,
+		 (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) ?
+			"FW LLDP is disabled\n" :
+			"FW LLDP is enabled\n");
+
 	/* Enable FW to write default DCB config on link-up */
 	i40e_aq_set_dcb_parameters(hw, true, NULL);
 
@@ -14349,6 +15202,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 	pf->hw.phy.link_info.requested_speeds = abilities.link_speed;
 
+	/* set the FEC config due to the board capabilities */
+	i40e_set_fec_in_flags(abilities.fec_cfg_curr_mod_ext_info, &pf->flags);
+
 	/* get the supported phy types from the fw */
 	err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL);
 	if (err)
@@ -14435,6 +15291,19 @@ static void i40e_remove(struct pci_dev *pdev)
 	if (pf->service_task.func)
 		cancel_work_sync(&pf->service_task);
 
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+		struct i40e_vsi *vsi = pf->vsi[0];
+
+		/* We know that we have allocated only one vsi for this PF,
+		 * it was just for registering netdevice, so the interface
+		 * could be visible in the 'ifconfig' output
+		 */
+		unregister_netdev(vsi->netdev);
+		free_netdev(vsi->netdev);
+
+		goto unmap;
+	}
+
 	/* Client close must be called explicitly here because the timer
 	 * has been stopped.
 	 */
@@ -14484,6 +15353,12 @@ static void i40e_remove(struct pci_dev *pdev)
 				 ret_code);
 	}
 
+unmap:
+	/* Free MSI/legacy interrupt 0 when in recovery mode. */
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+	    !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+		free_irq(pf->pdev->irq, pf);
+
 	/* shutdown the adminq */
 	i40e_shutdown_adminq(hw);
 
@@ -14496,7 +15371,8 @@ static void i40e_remove(struct pci_dev *pdev)
 	i40e_clear_interrupt_scheme(pf);
 	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i]) {
-			i40e_vsi_clear_rings(pf->vsi[i]);
+			if (!test_bit(__I40E_RECOVERY_MODE, pf->state))
+				i40e_vsi_clear_rings(pf->vsi[i]);
 			i40e_vsi_clear(pf->vsi[i]);
 			pf->vsi[i] = NULL;
 		}
@@ -14704,6 +15580,11 @@ static void i40e_shutdown(struct pci_dev *pdev)
 	wr32(hw, I40E_PFPM_WUFC,
 	     (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
 
+	/* Free MSI/legacy interrupt 0 when in recovery mode. */
+	if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+	    !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+		free_irq(pf->pdev->irq, pf);
+
 	/* Since we're going to destroy queues during the
 	 * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
 	 * whole section
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 0299e5bbb902..c508b75c3c09 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -578,11 +578,10 @@ i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw)
 	__le16 le_sum;
 
 	ret_code = i40e_calc_nvm_checksum(hw, &checksum);
-	if (!ret_code) {
-		le_sum = cpu_to_le16(checksum);
+	le_sum = cpu_to_le16(checksum);
+	if (!ret_code)
 		ret_code = i40e_write_nvm_aq(hw, 0x00, I40E_SR_SW_CHECKSUM_WORD,
 					     1, &le_sum, true);
-	}
 
 	return ret_code;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index e08d754824b1..eac88bcc6c06 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -203,14 +203,18 @@ i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 				bool enable_update,
 				struct i40e_asq_cmd_details *cmd_details);
+enum i40e_status_code
+i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore,
+		     struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
+			      bool persist,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_set_dcb_parameters(struct i40e_hw *hw,
 				       bool dcb_enable,
 				       struct i40e_asq_cmd_details
 				       *cmd_details);
-i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
-				struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, bool persist,
+			       struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
 				       void *buff, u16 buff_size,
 				       struct i40e_asq_cmd_details *cmd_details);
@@ -346,6 +350,10 @@ i40e_virtchnl_link_speed(enum i40e_aq_link_speed link_speed)
 		return VIRTCHNL_LINK_SPEED_100MB;
 	case I40E_LINK_SPEED_1GB:
 		return VIRTCHNL_LINK_SPEED_1GB;
+	case I40E_LINK_SPEED_2_5GB:
+		return VIRTCHNL_LINK_SPEED_2_5GB;
+	case I40E_LINK_SPEED_5GB:
+		return VIRTCHNL_LINK_SPEED_5GB;
 	case I40E_LINK_SPEED_10GB:
 		return VIRTCHNL_LINK_SPEED_10GB;
 	case I40E_LINK_SPEED_40GB:
@@ -429,10 +437,16 @@ i40e_status i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff,
 struct i40e_generic_seg_header *
 i40e_find_segment_in_package(u32 segment_type,
 			     struct i40e_package_header *pkg_header);
+struct i40e_profile_section_header *
+i40e_find_section_in_profile(u32 section_type,
+			     struct i40e_profile_segment *profile);
 enum i40e_status_code
 i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
 		   u32 track_id);
 enum i40e_status_code
+i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg,
+		      u32 track_id);
+enum i40e_status_code
 i40e_add_pinfo_to_list(struct i40e_hw *hw,
 		       struct i40e_profile_segment *profile,
 		       u8 *profile_info_sec, u32 track_id);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 5fb4353c742b..11394a52e21c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -140,18 +140,18 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
  * @ptp: The PTP clock structure
  * @delta: Offset in nanoseconds to adjust the PHC time by
  *
- * Adjust the frequency of the PHC by the indicated parts per billion from the
- * base frequency.
+ * Adjust the current clock time by a delta specified in nanoseconds.
  **/
 static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
-	struct timespec64 now;
+	struct timespec64 now, then;
 
+	then = ns_to_timespec64(delta);
 	mutex_lock(&pf->tmreg_lock);
 
 	i40e_ptp_read(pf, &now, NULL);
-	timespec64_add_ns(&now, delta);
+	now = timespec64_add(now, then);
 	i40e_ptp_write(pf, (const struct timespec64 *)&now);
 
 	mutex_unlock(&pf->tmreg_lock);
@@ -724,16 +724,68 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf)
 	pf->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	pf->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
 
+	/* Set the previous "reset" time to the current Kernel clock time */
+	pf->ptp_prev_hw_time = ktime_to_timespec64(ktime_get_real());
+	pf->ptp_reset_start = ktime_get();
+
 	return 0;
 }
 
 /**
+ * i40e_ptp_save_hw_time - Save the current PTP time as ptp_prev_hw_time
+ * @pf: Board private structure
+ *
+ * Read the current PTP time and save it into pf->ptp_prev_hw_time. This should
+ * be called at the end of preparing to reset, just before hardware reset
+ * occurs, in order to preserve the PTP time as close as possible across
+ * resets.
+ */
+void i40e_ptp_save_hw_time(struct i40e_pf *pf)
+{
+	/* don't try to access the PTP clock if it's not enabled */
+	if (!(pf->flags & I40E_FLAG_PTP))
+		return;
+
+	i40e_ptp_gettimex(&pf->ptp_caps, &pf->ptp_prev_hw_time, NULL);
+	/* Get a monotonic starting time for this reset */
+	pf->ptp_reset_start = ktime_get();
+}
+
+/**
+ * i40e_ptp_restore_hw_time - Restore the ptp_prev_hw_time + delta to PTP regs
+ * @pf: Board private structure
+ *
+ * Restore the PTP hardware clock registers. We previously cached the PTP
+ * hardware time as pf->ptp_prev_hw_time. To be as accurate as possible,
+ * update this value based on the time delta since the time was saved, using
+ * CLOCK_MONOTONIC (via ktime_get()) to calculate the time difference.
+ *
+ * This ensures that the hardware clock is restored to nearly what it should
+ * have been if a reset had not occurred.
+ */
+void i40e_ptp_restore_hw_time(struct i40e_pf *pf)
+{
+	ktime_t delta = ktime_sub(ktime_get(), pf->ptp_reset_start);
+
+	/* Update the previous HW time with the ktime delta */
+	timespec64_add_ns(&pf->ptp_prev_hw_time, ktime_to_ns(delta));
+
+	/* Restore the hardware clock registers */
+	i40e_ptp_settime(&pf->ptp_caps, &pf->ptp_prev_hw_time);
+}
+
+/**
  * i40e_ptp_init - Initialize the 1588 support after device probe or reset
  * @pf: Board private structure
  *
  * This function sets device up for 1588 support. The first time it is run, it
  * will create a PHC clock device. It does not create a clock device if one
  * already exists. It also reconfigures the device after a reset.
+ *
+ * The first time a clock is created, i40e_ptp_create_clock will set
+ * pf->ptp_prev_hw_time to the current system time. During resets, it is
+ * expected that this timespec will be set to the last known PTP clock time,
+ * in order to preserve the clock time as close as possible across a reset.
  **/
 void i40e_ptp_init(struct i40e_pf *pf)
 {
@@ -765,7 +817,6 @@ void i40e_ptp_init(struct i40e_pf *pf)
 		dev_err(&pf->pdev->dev, "%s: ptp_clock_register failed\n",
 			__func__);
 	} else if (pf->ptp_clock) {
-		struct timespec64 ts;
 		u32 regval;
 
 		if (pf->hw.debug_mask & I40E_DEBUG_LAN)
@@ -786,9 +837,8 @@ void i40e_ptp_init(struct i40e_pf *pf)
 		/* reset timestamping mode */
 		i40e_ptp_set_timestamp_mode(pf, &pf->tstamp_config);
 
-		/* Set the clock value. */
-		ts = ktime_to_timespec64(ktime_get_real());
-		i40e_ptp_settime(&pf->ptp_caps, &ts);
+		/* Restore the clock time based on last known value */
+		i40e_ptp_restore_hw_time(pf);
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index a7e14e98889f..2a2fe3ec7926 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -774,7 +774,7 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi)
 static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 			      struct i40e_ring *tx_ring, int napi_budget)
 {
-	u16 i = tx_ring->next_to_clean;
+	int i = tx_ring->next_to_clean;
 	struct i40e_tx_buffer *tx_buf;
 	struct i40e_tx_desc *tx_head;
 	struct i40e_tx_desc *tx_desc;
@@ -2035,7 +2035,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > I40E_RX_HDR_SIZE)
-		headlen = eth_get_headlen(xdp->data, I40E_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, xdp->data,
+					  I40E_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), xdp->data,
@@ -3469,13 +3470,8 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
@@ -3709,6 +3705,7 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	unsigned int queue_index = smp_processor_id();
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 	struct i40e_ring *xdp_ring;
 	int drops = 0;
 	int i;
@@ -3716,7 +3713,8 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
 
-	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
+	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return -ENXIO;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 2781ab91ca82..8f43aa47c263 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -252,6 +252,12 @@ struct i40e_phy_info {
 					     I40E_PHY_TYPE_OFFSET)
 #define I40E_CAP_PHY_TYPE_25GBASE_ACC BIT_ULL(I40E_PHY_TYPE_25GBASE_ACC + \
 					     I40E_PHY_TYPE_OFFSET)
+/* Offset for 2.5G/5G PHY Types value to bit number conversion */
+#define I40E_PHY_TYPE_OFFSET2 (-10)
+#define I40E_CAP_PHY_TYPE_2_5GBASE_T BIT_ULL(I40E_PHY_TYPE_2_5GBASE_T + \
+					     I40E_PHY_TYPE_OFFSET2)
+#define I40E_CAP_PHY_TYPE_5GBASE_T BIT_ULL(I40E_PHY_TYPE_5GBASE_T + \
+					     I40E_PHY_TYPE_OFFSET2)
 #define I40E_HW_CAP_MAX_GPIO			30
 /* Capabilities of a PF or a VF or the whole device */
 struct i40e_hw_capabilities {
@@ -616,6 +622,7 @@ struct i40e_hw {
 #define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE  BIT_ULL(2)
 #define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3)
 #define I40E_HW_FLAG_FW_LLDP_STOPPABLE      BIT_ULL(4)
+#define I40E_HW_FLAG_FW_LLDP_PERSISTENT     BIT_ULL(5)
 	u64 flags;
 
 	/* Used in set switch config AQ command */
@@ -1527,6 +1534,8 @@ struct i40e_generic_seg_header {
 struct i40e_metadata_segment {
 	struct i40e_generic_seg_header header;
 	struct i40e_ddp_version version;
+#define I40E_DDP_TRACKID_RDONLY		0
+#define I40E_DDP_TRACKID_INVALID	0xFFFFFFFF
 	u32 track_id;
 	char name[I40E_DDP_NAME_SIZE];
 };
@@ -1555,15 +1564,36 @@ struct i40e_profile_section_header {
 	struct {
 #define SECTION_TYPE_INFO	0x00000010
 #define SECTION_TYPE_MMIO	0x00000800
+#define SECTION_TYPE_RB_MMIO	0x00001800
 #define SECTION_TYPE_AQ		0x00000801
+#define SECTION_TYPE_RB_AQ	0x00001801
 #define SECTION_TYPE_NOTE	0x80000000
 #define SECTION_TYPE_NAME	0x80000001
+#define SECTION_TYPE_PROTO	0x80000002
+#define SECTION_TYPE_PCTYPE	0x80000003
+#define SECTION_TYPE_PTYPE	0x80000004
 		u32 type;
 		u32 offset;
 		u32 size;
 	} section;
 };
 
+struct i40e_profile_tlv_section_record {
+	u8 rtype;
+	u8 type;
+	u16 len;
+	u8 data[12];
+};
+
+/* Generic AQ section in proflie */
+struct i40e_profile_aq_section {
+	u16 opcode;
+	u16 flags;
+	u8  param[16];
+	u16 datalen;
+	u8  data[1];
+};
+
 struct i40e_profile_info {
 	u32 track_id;
 	struct i40e_ddp_version version;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 2ac23ebfbf31..02b09a8ad54c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -181,7 +181,7 @@ static inline bool i40e_vc_isvalid_vsi_id(struct i40e_vf *vf, u16 vsi_id)
  * check for the valid queue id
  **/
 static inline bool i40e_vc_isvalid_queue_id(struct i40e_vf *vf, u16 vsi_id,
-					    u8 qid)
+					    u16 qid)
 {
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = i40e_find_vsi_from_id(pf, vsi_id);
@@ -196,7 +196,7 @@ static inline bool i40e_vc_isvalid_queue_id(struct i40e_vf *vf, u16 vsi_id,
  *
  * check for the valid vector id
  **/
-static inline bool i40e_vc_isvalid_vector_id(struct i40e_vf *vf, u8 vector_id)
+static inline bool i40e_vc_isvalid_vector_id(struct i40e_vf *vf, u32 vector_id)
 {
 	struct i40e_pf *pf = vf->pf;
 
@@ -440,15 +440,28 @@ static int i40e_config_iwarp_qvlist(struct i40e_vf *vf,
 	struct virtchnl_iwarp_qv_info *qv_info;
 	u32 v_idx, i, reg_idx, reg;
 	u32 next_q_idx, next_q_type;
-	u32 msix_vf, size;
+	u32 msix_vf;
+	int ret = 0;
 
-	size = sizeof(struct virtchnl_iwarp_qvlist_info) +
-	       (sizeof(struct virtchnl_iwarp_qv_info) *
-						(qvlist_info->num_vectors - 1));
-	vf->qvlist_info = kzalloc(size, GFP_KERNEL);
-	if (!vf->qvlist_info)
-		return -ENOMEM;
+	msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
+
+	if (qvlist_info->num_vectors > msix_vf) {
+		dev_warn(&pf->pdev->dev,
+			 "Incorrect number of iwarp vectors %u. Maximum %u allowed.\n",
+			 qvlist_info->num_vectors,
+			 msix_vf);
+		ret = -EINVAL;
+		goto err_out;
+	}
 
+	kfree(vf->qvlist_info);
+	vf->qvlist_info = kzalloc(struct_size(vf->qvlist_info, qv_info,
+					      qvlist_info->num_vectors - 1),
+				  GFP_KERNEL);
+	if (!vf->qvlist_info) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
 	vf->qvlist_info->num_vectors = qvlist_info->num_vectors;
 
 	msix_vf = pf->hw.func_caps.num_msix_vectors_vf;
@@ -456,11 +469,14 @@ static int i40e_config_iwarp_qvlist(struct i40e_vf *vf,
 		qv_info = &qvlist_info->qv_info[i];
 		if (!qv_info)
 			continue;
-		v_idx = qv_info->v_idx;
 
 		/* Validate vector id belongs to this vf */
-		if (!i40e_vc_isvalid_vector_id(vf, v_idx))
-			goto err;
+		if (!i40e_vc_isvalid_vector_id(vf, qv_info->v_idx)) {
+			ret = -EINVAL;
+			goto err_free;
+		}
+
+		v_idx = qv_info->v_idx;
 
 		vf->qvlist_info->qv_info[i] = *qv_info;
 
@@ -502,10 +518,11 @@ static int i40e_config_iwarp_qvlist(struct i40e_vf *vf,
 	}
 
 	return 0;
-err:
+err_free:
 	kfree(vf->qvlist_info);
 	vf->qvlist_info = NULL;
-	return -EINVAL;
+err_out:
+	return ret;
 }
 
 /**
@@ -1112,15 +1129,6 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf,
 	if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi)
 		return I40E_ERR_PARAM;
 
-	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) &&
-	    (allmulti || alluni)) {
-		dev_err(&pf->pdev->dev,
-			"Unprivileged VF %d is attempting to configure promiscuous mode\n",
-			vf->vf_id);
-		/* Lie to the VF on purpose. */
-		return 0;
-	}
-
 	if (vf->port_vlan_id) {
 		aq_ret = i40e_aq_set_vsi_mc_promisc_on_vlan(hw, vsi->seid,
 							    allmulti,
@@ -1837,7 +1845,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	struct i40e_vsi *vsi;
 	int num_vsis = 1;
-	int len = 0;
+	size_t len = 0;
 	int ret;
 
 	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
@@ -1845,9 +1853,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	len = (sizeof(struct virtchnl_vf_resource) +
-	       sizeof(struct virtchnl_vsi_resource) * num_vsis);
-
+	len = struct_size(vfres, vsi_res, num_vsis);
 	vfres = kzalloc(len, GFP_KERNEL);
 	if (!vfres) {
 		aq_ret = I40E_ERR_NO_MEMORY;
@@ -1997,8 +2003,31 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
 	bool allmulti = false;
 	bool alluni = false;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
-		return I40E_ERR_PARAM;
+	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+		aq_ret = I40E_ERR_PARAM;
+		goto err_out;
+	}
+	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) {
+		dev_err(&pf->pdev->dev,
+			"Unprivileged VF %d is attempting to configure promiscuous mode\n",
+			vf->vf_id);
+
+		/* Lie to the VF on purpose, because this is an error we can
+		 * ignore. Unprivileged VF is not a virtual channel error.
+		 */
+		aq_ret = 0;
+		goto err_out;
+	}
+
+	if (info->flags > I40E_MAX_VF_PROMISC_FLAGS) {
+		aq_ret = I40E_ERR_PARAM;
+		goto err_out;
+	}
+
+	if (!i40e_vc_isvalid_vsi_id(vf, info->vsi_id)) {
+		aq_ret = I40E_ERR_PARAM;
+		goto err_out;
+	}
 
 	/* Multicast promiscuous handling*/
 	if (info->flags & FLAG_VF_MULTICAST_PROMISC)
@@ -2032,7 +2061,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
 			clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states);
 		}
 	}
-
+err_out:
 	/* send the response to the VF */
 	return i40e_vc_send_resp_to_vf(vf,
 				       VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE,
@@ -2054,25 +2083,46 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 	struct virtchnl_queue_pair_info *qpi;
 	struct i40e_pf *pf = vf->pf;
 	u16 vsi_id, vsi_queue_id = 0;
+	u16 num_qps_all = 0;
 	i40e_status aq_ret = 0;
 	int i, j = 0, idx = 0;
 
-	vsi_id = qci->vsi_id;
-
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
 
-	if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+	if (!i40e_vc_isvalid_vsi_id(vf, qci->vsi_id)) {
+		aq_ret = I40E_ERR_PARAM;
+		goto error_param;
+	}
+
+	if (qci->num_queue_pairs > I40E_MAX_VF_QUEUES) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
 
+	if (vf->adq_enabled) {
+		for (i = 0; i < I40E_MAX_VF_VSI; i++)
+			num_qps_all += vf->ch[i].num_qps;
+		if (num_qps_all != qci->num_queue_pairs) {
+			aq_ret = I40E_ERR_PARAM;
+			goto error_param;
+		}
+	}
+
+	vsi_id = qci->vsi_id;
+
 	for (i = 0; i < qci->num_queue_pairs; i++) {
 		qpi = &qci->qpair[i];
 
 		if (!vf->adq_enabled) {
+			if (!i40e_vc_isvalid_queue_id(vf, vsi_id,
+						      qpi->txq.queue_id)) {
+				aq_ret = I40E_ERR_PARAM;
+				goto error_param;
+			}
+
 			vsi_queue_id = qpi->txq.queue_id;
 
 			if (qpi->txq.vsi_id != qci->vsi_id ||
@@ -2083,9 +2133,12 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 			}
 		}
 
-		if (!i40e_vc_isvalid_queue_id(vf, vsi_id, vsi_queue_id)) {
-			aq_ret = I40E_ERR_PARAM;
-			goto error_param;
+		if (vf->adq_enabled) {
+			if (idx >= ARRAY_SIZE(vf->ch)) {
+				aq_ret = I40E_ERR_NO_AVAILABLE_VSI;
+				goto error_param;
+			}
+			vsi_id = vf->ch[idx].vsi_id;
 		}
 
 		if (i40e_config_vsi_rx_queue(vf, vsi_id, vsi_queue_id,
@@ -2102,6 +2155,10 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		 * to its appropriate VSIs based on TC mapping
 		 **/
 		if (vf->adq_enabled) {
+			if (idx >= ARRAY_SIZE(vf->ch)) {
+				aq_ret = I40E_ERR_NO_AVAILABLE_VSI;
+				goto error_param;
+			}
 			if (j == (vf->ch[idx].num_qps - 1)) {
 				idx++;
 				j = 0; /* resetting the queue count */
@@ -2110,7 +2167,6 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 				j++;
 				vsi_queue_id++;
 			}
-			vsi_id = vf->ch[idx].vsi_id;
 		}
 	}
 	/* set vsi num_queue_pairs in use to num configured by VF */
@@ -2169,7 +2225,7 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg)
 	struct virtchnl_irq_map_info *irqmap_info =
 	    (struct virtchnl_irq_map_info *)msg;
 	struct virtchnl_vector_map *map;
-	u16 vsi_id, vector_id;
+	u16 vsi_id;
 	i40e_status aq_ret = 0;
 	int i;
 
@@ -2178,16 +2234,21 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
+	if (irqmap_info->num_vectors >
+	    vf->pf->hw.func_caps.num_msix_vectors_vf) {
+		aq_ret = I40E_ERR_PARAM;
+		goto error_param;
+	}
+
 	for (i = 0; i < irqmap_info->num_vectors; i++) {
 		map = &irqmap_info->vecmap[i];
-		vector_id = map->vector_id;
-		vsi_id = map->vsi_id;
 		/* validate msg params */
-		if (!i40e_vc_isvalid_vector_id(vf, vector_id) ||
-		    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+		if (!i40e_vc_isvalid_vector_id(vf, map->vector_id) ||
+		    !i40e_vc_isvalid_vsi_id(vf, map->vsi_id)) {
 			aq_ret = I40E_ERR_PARAM;
 			goto error_param;
 		}
+		vsi_id = map->vsi_id;
 
 		if (i40e_validate_queue_map(vf, vsi_id, map->rxq_map)) {
 			aq_ret = I40E_ERR_PARAM;
@@ -2264,7 +2325,6 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
 	struct virtchnl_queue_select *vqs =
 	    (struct virtchnl_queue_select *)msg;
 	struct i40e_pf *pf = vf->pf;
-	u16 vsi_id = vqs->vsi_id;
 	i40e_status aq_ret = 0;
 	int i;
 
@@ -2273,7 +2333,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if (!i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+	if (!i40e_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2335,7 +2395,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if ((0 == vqs->rx_queues) && (0 == vqs->tx_queues)) {
+	if ((vqs->rx_queues == 0 && vqs->tx_queues == 0) ||
+	    vqs->rx_queues > I40E_MAX_VF_QUEUES ||
+	    vqs->tx_queues > I40E_MAX_VF_QUEUES) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2371,18 +2433,14 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg)
 {
 	struct virtchnl_vf_res_request *vfres =
 		(struct virtchnl_vf_res_request *)msg;
-	int req_pairs = vfres->num_queue_pairs;
-	int cur_pairs = vf->num_queue_pairs;
+	u16 req_pairs = vfres->num_queue_pairs;
+	u8 cur_pairs = vf->num_queue_pairs;
 	struct i40e_pf *pf = vf->pf;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
 		return -EINVAL;
 
-	if (req_pairs <= 0) {
-		dev_err(&pf->pdev->dev,
-			"VF %d tried to request %d queues.  Ignoring.\n",
-			vf->vf_id, req_pairs);
-	} else if (req_pairs > I40E_MAX_VF_QUEUES) {
+	if (req_pairs > I40E_MAX_VF_QUEUES) {
 		dev_err(&pf->pdev->dev,
 			"VF %d tried to request more than %d queues.\n",
 			vf->vf_id,
@@ -2449,9 +2507,11 @@ error_param:
 				      (u8 *)&stats, sizeof(stats));
 }
 
-/* If the VF is not trusted restrict the number of MAC/VLAN it can program */
-#define I40E_VC_MAX_MAC_ADDR_PER_VF 12
-#define I40E_VC_MAX_VLAN_PER_VF 8
+/* If the VF is not trusted restrict the number of MAC/VLAN it can program
+ * MAC filters: 16 for multicast, 1 for MAC, 1 for broadcast
+ */
+#define I40E_VC_MAX_MAC_ADDR_PER_VF (16 + 1 + 1)
+#define I40E_VC_MAX_VLAN_PER_VF 16
 
 /**
  * i40e_check_vf_permission
@@ -2529,12 +2589,11 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 	    (struct virtchnl_ether_addr_list *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
-	u16 vsi_id = al->vsi_id;
 	i40e_status ret = 0;
 	int i;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
-	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+	    !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
 		ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2599,12 +2658,11 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 	    (struct virtchnl_ether_addr_list *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
-	u16 vsi_id = al->vsi_id;
 	i40e_status ret = 0;
 	int i;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
-	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+	    !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
 		ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2668,7 +2726,6 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg)
 	    (struct virtchnl_vlan_filter_list *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
-	u16 vsi_id = vfl->vsi_id;
 	i40e_status aq_ret = 0;
 	int i;
 
@@ -2679,7 +2736,7 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg)
 		goto error_param;
 	}
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
-	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+	    !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2740,12 +2797,11 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg)
 	    (struct virtchnl_vlan_filter_list *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
-	u16 vsi_id = vfl->vsi_id;
 	i40e_status aq_ret = 0;
 	int i;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
-	    !i40e_vc_isvalid_vsi_id(vf, vsi_id)) {
+	    !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2759,7 +2815,8 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg)
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (vsi->info.pvid) {
-		aq_ret = I40E_ERR_PARAM;
+		if (vfl->num_elements > 1 || vfl->vlan_id[0])
+			aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
 
@@ -2861,11 +2918,10 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg)
 		(struct virtchnl_rss_key *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
-	u16 vsi_id = vrk->vsi_id;
 	i40e_status aq_ret = 0;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
-	    !i40e_vc_isvalid_vsi_id(vf, vsi_id) ||
+	    !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) ||
 	    (vrk->key_len != I40E_HKEY_ARRAY_SIZE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
@@ -2892,16 +2948,22 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg)
 		(struct virtchnl_rss_lut *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_vsi *vsi = NULL;
-	u16 vsi_id = vrl->vsi_id;
 	i40e_status aq_ret = 0;
+	u16 i;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
-	    !i40e_vc_isvalid_vsi_id(vf, vsi_id) ||
+	    !i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) ||
 	    (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
 
+	for (i = 0; i < vrl->lut_entries; i++)
+		if (vrl->lut[i] >= vf->num_queue_pairs) {
+			aq_ret = I40E_ERR_PARAM;
+			goto err;
+		}
+
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	aq_ret = i40e_config_rss(vsi, NULL, vrl->lut, I40E_VF_HLUT_ARRAY_SIZE);
 	/* send the response to the VF */
@@ -2982,14 +3044,15 @@ err:
  **/
 static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
 {
-	struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
 	i40e_status aq_ret = 0;
+	struct i40e_vsi *vsi;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
 
+	vsi = vf->pf->vsi[vf->lan_vsi_idx];
 	i40e_vlan_stripping_enable(vsi);
 
 	/* send the response to the VF */
@@ -3007,14 +3070,15 @@ err:
  **/
 static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
 {
-	struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx];
 	i40e_status aq_ret = 0;
+	struct i40e_vsi *vsi;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
 
+	vsi = vf->pf->vsi[vf->lan_vsi_idx];
 	i40e_vlan_stripping_disable(vsi);
 
 	/* send the response to the VF */
@@ -3121,7 +3185,7 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf,
 	}
 
 	if (mask.dst_port & data.dst_port) {
-		if (!data.dst_port || be16_to_cpu(data.dst_port) > 0xFFFF) {
+		if (!data.dst_port) {
 			dev_info(&pf->pdev->dev, "VF %d: Invalid Dest port\n",
 				 vf->vf_id);
 			goto err;
@@ -3129,7 +3193,7 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf,
 	}
 
 	if (mask.src_port & data.src_port) {
-		if (!data.src_port || be16_to_cpu(data.src_port) > 0xFFFF) {
+		if (!data.src_port) {
 			dev_info(&pf->pdev->dev, "VF %d: Invalid Source port\n",
 				 vf->vf_id);
 			goto err;
@@ -3369,7 +3433,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
-		goto err;
+		goto err_out;
 	}
 
 	if (!vf->adq_enabled) {
@@ -3377,15 +3441,15 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 			 "VF %d: ADq is not enabled, can't apply cloud filter\n",
 			 vf->vf_id);
 		aq_ret = I40E_ERR_PARAM;
-		goto err;
+		goto err_out;
 	}
 
 	if (i40e_validate_cloud_filter(vf, vcf)) {
 		dev_info(&pf->pdev->dev,
 			 "VF %d: Invalid input/s, can't apply cloud filter\n",
 			 vf->vf_id);
-			aq_ret = I40E_ERR_PARAM;
-			goto err;
+		aq_ret = I40E_ERR_PARAM;
+		goto err_out;
 	}
 
 	cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL);
@@ -3446,13 +3510,17 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 			"VF %d: Failed to add cloud filter, err %s aq_err %s\n",
 			vf->vf_id, i40e_stat_str(&pf->hw, ret),
 			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
-		goto err;
+		goto err_free;
 	}
 
 	INIT_HLIST_NODE(&cfilter->cloud_node);
 	hlist_add_head(&cfilter->cloud_node, &vf->cloud_filter_list);
+	/* release the pointer passing it to the collection */
+	cfilter = NULL;
 	vf->num_cloud_filters++;
-err:
+err_free:
+	kfree(cfilter);
+err_out:
 	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_CLOUD_FILTER,
 				       aq_ret);
 }
@@ -3468,8 +3536,9 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 		(struct virtchnl_tc_info *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_link_status *ls = &pf->hw.phy.link_info;
-	int i, adq_request_qps = 0, speed = 0;
+	int i, adq_request_qps = 0;
 	i40e_status aq_ret = 0;
+	u64 speed = 0;
 
 	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
 		aq_ret = I40E_ERR_PARAM;
@@ -3495,8 +3564,8 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 	/* max number of traffic classes for VF currently capped at 4 */
 	if (!tci->num_tc || tci->num_tc > I40E_MAX_VF_VSI) {
 		dev_err(&pf->pdev->dev,
-			"VF %d trying to set %u TCs, valid range 1-4 TCs per VF\n",
-			vf->vf_id, tci->num_tc);
+			"VF %d trying to set %u TCs, valid range 1-%u TCs per VF\n",
+			vf->vf_id, tci->num_tc, I40E_MAX_VF_VSI);
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3506,8 +3575,9 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 		if (!tci->list[i].count ||
 		    tci->list[i].count > I40E_DEFAULT_QUEUES_PER_VF) {
 			dev_err(&pf->pdev->dev,
-				"VF %d: TC %d trying to set %u queues, valid range 1-4 queues per TC\n",
-				vf->vf_id, i, tci->list[i].count);
+				"VF %d: TC %d trying to set %u queues, valid range 1-%u queues per TC\n",
+				vf->vf_id, i, tci->list[i].count,
+				I40E_DEFAULT_QUEUES_PER_VF);
 			aq_ret = I40E_ERR_PARAM;
 			goto err;
 		}
@@ -3656,7 +3726,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 	int ret;
 
 	pf->vf_aq_requests++;
-	if (local_vf_id >= pf->num_alloc_vfs)
+	if (local_vf_id < 0 || local_vf_id >= pf->num_alloc_vfs)
 		return -EINVAL;
 	vf = &(pf->vf[local_vf_id]);
 
@@ -3667,19 +3737,6 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 	/* perform basic checks on the msg */
 	ret = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen);
 
-	/* perform additional checks specific to this driver */
-	if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_KEY) {
-		struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg;
-
-		if (vrk->key_len != I40E_HKEY_ARRAY_SIZE)
-			ret = -EINVAL;
-	} else if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_LUT) {
-		struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg;
-
-		if (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)
-			ret = -EINVAL;
-	}
-
 	if (ret) {
 		i40e_vc_send_resp_to_vf(vf, v_opcode, I40E_ERR_PARAM);
 		dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d\n",
@@ -3880,6 +3937,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	int bkt;
 	u8 i;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	ret = i40e_validate_vf(pf, vf_id);
 	if (ret)
@@ -3904,11 +3966,6 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		goto error_param;
 	}
 
-	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
-		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
-		return -EAGAIN;
-	}
-
 	if (is_multicast_ether_addr(mac)) {
 		dev_err(&pf->pdev->dev,
 			"Invalid Ethernet address %pM for VF %d\n", mac, vf_id);
@@ -4004,6 +4061,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 {
 	u16 vlanprio = vlan_id | (qos << I40E_VLAN_PRIORITY_SHIFT);
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	bool allmulti = false, alluni = false;
 	struct i40e_pf *pf = np->vsi->back;
 	struct i40e_vsi *vsi;
 	struct i40e_vf *vf;
@@ -4088,6 +4146,15 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	}
 
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
+
+	/* disable promisc modes in case they were enabled */
+	ret = i40e_config_vf_promiscuous_mode(vf, vf->lan_vsi_id,
+					      allmulti, alluni);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Unable to config VF promiscuous mode\n");
+		goto error_pvid;
+	}
+
 	if (vlan_id || qos)
 		ret = i40e_vsi_add_pvid(vsi, vlanprio);
 	else
@@ -4114,6 +4181,12 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);
 
+	if (test_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states))
+		alluni = true;
+
+	if (test_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states))
+		allmulti = true;
+
 	/* Schedule the worker thread to take care of applying changes */
 	i40e_service_event_schedule(vsi->back);
 
@@ -4126,6 +4199,13 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	 * default LAN MAC address.
 	 */
 	vf->port_vlan_id = le16_to_cpu(vsi->info.pvid);
+
+	ret = i40e_config_vf_promiscuous_mode(vf, vsi->id, allmulti, alluni);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Unable to config vf promiscuous mode\n");
+		goto error_pvid;
+	}
+
 	ret = 0;
 
 error_pvid:
@@ -4216,10 +4296,8 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 	vf = &pf->vf[vf_id];
 	/* first vsi is always the LAN vsi */
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
-		dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n",
-			vf_id);
-		ret = -EAGAIN;
+	if (!vsi) {
+		ret = -ENOENT;
 		goto error_param;
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index f9621026beef..f65cc0c16550 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -17,6 +17,8 @@
 #define I40E_VLAN_MASK			0xFFF
 #define I40E_PRIORITY_MASK		0xE000
 
+#define I40E_MAX_VF_PROMISC_FLAGS	3
+
 /* Various queue ctrls */
 enum i40e_queue_ctrl {
 	I40E_QUEUE_CTRL_UNKNOWN = 0,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 870cf654e436..32bad014d76c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -10,69 +10,6 @@
 #include "i40e_xsk.h"
 
 /**
- * i40e_alloc_xsk_umems - Allocate an array to store per ring UMEMs
- * @vsi: Current VSI
- *
- * Returns 0 on success, <0 on failure
- **/
-static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi)
-{
-	if (vsi->xsk_umems)
-		return 0;
-
-	vsi->num_xsk_umems_used = 0;
-	vsi->num_xsk_umems = vsi->alloc_queue_pairs;
-	vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems),
-				 GFP_KERNEL);
-	if (!vsi->xsk_umems) {
-		vsi->num_xsk_umems = 0;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-/**
- * i40e_add_xsk_umem - Store a UMEM for a certain ring/qid
- * @vsi: Current VSI
- * @umem: UMEM to store
- * @qid: Ring/qid to associate with the UMEM
- *
- * Returns 0 on success, <0 on failure
- **/
-static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem,
-			     u16 qid)
-{
-	int err;
-
-	err = i40e_alloc_xsk_umems(vsi);
-	if (err)
-		return err;
-
-	vsi->xsk_umems[qid] = umem;
-	vsi->num_xsk_umems_used++;
-
-	return 0;
-}
-
-/**
- * i40e_remove_xsk_umem - Remove a UMEM for a certain ring/qid
- * @vsi: Current VSI
- * @qid: Ring/qid associated with the UMEM
- **/
-static void i40e_remove_xsk_umem(struct i40e_vsi *vsi, u16 qid)
-{
-	vsi->xsk_umems[qid] = NULL;
-	vsi->num_xsk_umems_used--;
-
-	if (vsi->num_xsk_umems == 0) {
-		kfree(vsi->xsk_umems);
-		vsi->xsk_umems = NULL;
-		vsi->num_xsk_umems = 0;
-	}
-}
-
-/**
  * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
  * @vsi: Current VSI
  * @umem: UMEM to DMA map
@@ -140,6 +77,7 @@ static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
 static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 				u16 qid)
 {
+	struct net_device *netdev = vsi->netdev;
 	struct xdp_umem_fq_reuse *reuseq;
 	bool if_running;
 	int err;
@@ -150,12 +88,9 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	if (qid >= vsi->num_queue_pairs)
 		return -EINVAL;
 
-	if (vsi->xsk_umems) {
-		if (qid >= vsi->num_xsk_umems)
-			return -EINVAL;
-		if (vsi->xsk_umems[qid])
-			return -EBUSY;
-	}
+	if (qid >= netdev->real_num_rx_queues ||
+	    qid >= netdev->real_num_tx_queues)
+		return -EINVAL;
 
 	reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
 	if (!reuseq)
@@ -167,22 +102,23 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	if (err)
 		return err;
 
+	set_bit(qid, vsi->af_xdp_zc_qps);
+
 	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
 
 	if (if_running) {
 		err = i40e_queue_pair_disable(vsi, qid);
 		if (err)
 			return err;
-	}
 
-	err = i40e_add_xsk_umem(vsi, umem, qid);
-	if (err)
-		return err;
-
-	if (if_running) {
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
+
+		/* Kick start the NAPI context so that receiving will start */
+		err = i40e_xsk_async_xmit(vsi->netdev, qid);
+		if (err)
+			return err;
 	}
 
 	return 0;
@@ -197,11 +133,13 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
  **/
 static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 {
+	struct net_device *netdev = vsi->netdev;
+	struct xdp_umem *umem;
 	bool if_running;
 	int err;
 
-	if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems ||
-	    !vsi->xsk_umems[qid])
+	umem = xdp_get_umem_from_qid(netdev, qid);
+	if (!umem)
 		return -EINVAL;
 
 	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
@@ -212,8 +150,8 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 			return err;
 	}
 
-	i40e_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]);
-	i40e_remove_xsk_umem(vsi, qid);
+	clear_bit(qid, vsi->af_xdp_zc_qps);
+	i40e_xsk_umem_dma_unmap(vsi, umem);
 
 	if (if_running) {
 		err = i40e_queue_pair_enable(vsi, qid);
@@ -225,36 +163,6 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 }
 
 /**
- * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM
- * @vsi: Current VSI
- * @umem: UMEM associated to the ring, if any
- * @qid: Rx ring to associate UMEM to
- *
- * This function will store, if any, the UMEM associated to certain ring.
- *
- * Returns 0 on success, <0 on failure
- **/
-int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
-			u16 qid)
-{
-	if (vsi->type != I40E_VSI_MAIN)
-		return -EINVAL;
-
-	if (qid >= vsi->num_queue_pairs)
-		return -EINVAL;
-
-	if (vsi->xsk_umems) {
-		if (qid >= vsi->num_xsk_umems)
-			return -EINVAL;
-		*umem = vsi->xsk_umems[qid];
-		return 0;
-	}
-
-	*umem = NULL;
-	return 0;
-}
-
-/**
  * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid
  * @vsi: Current VSI
  * @umem: UMEM to enable/associate to a ring, or NULL to disable
@@ -307,6 +215,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
 	case XDP_ABORTED:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		/* fallthrough -- handle aborts by dropping packet */
@@ -732,8 +641,8 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 	struct i40e_tx_desc *tx_desc = NULL;
 	struct i40e_tx_buffer *tx_bi;
 	bool work_done = true;
+	struct xdp_desc desc;
 	dma_addr_t dma;
-	u32 len;
 
 	while (budget-- > 0) {
 		if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) {
@@ -742,21 +651,23 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 			break;
 		}
 
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len))
+		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
 			break;
 
-		dma_sync_single_for_device(xdp_ring->dev, dma, len,
+		dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
+
+		dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
 					   DMA_BIDIRECTIONAL);
 
 		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
-		tx_bi->bytecount = len;
+		tx_bi->bytecount = desc.len;
 
 		tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use);
 		tx_desc->buffer_addr = cpu_to_le64(dma);
 		tx_desc->cmd_type_offset_bsz =
 			build_ctob(I40E_TX_DESC_CMD_ICRC
 				   | I40E_TX_DESC_CMD_EOP,
-				   0, len, 0);
+				   0, desc.len, 0);
 
 		xdp_ring->next_to_use++;
 		if (xdp_ring->next_to_use == xdp_ring->count)
@@ -945,13 +856,11 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
  **/
 bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
 {
+	struct net_device *netdev = vsi->netdev;
 	int i;
 
-	if (!vsi->xsk_umems)
-		return false;
-
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		if (vsi->xsk_umems[i])
+		if (xdp_get_umem_from_qid(netdev, i))
 			return true;
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index 9038c5d5cf08..8cc0a2e7d9a2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -10,8 +10,6 @@ struct zero_copy_allocator;
 
 int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
 int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
-int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
-			u16 qid);
 int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
 			u16 qid);
 void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile
index 9cbb5743ed12..c997063ed728 100644
--- a/drivers/net/ethernet/intel/iavf/Makefile
+++ b/drivers/net/ethernet/intel/iavf/Makefile
@@ -12,4 +12,4 @@ subdir-ccflags-y += -I$(src)
 obj-$(CONFIG_IAVF) += iavf.o
 
 iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o \
-	     iavf_txrx.o iavf_common.o i40e_adminq.o iavf_client.o
+	     iavf_txrx.o iavf_common.o iavf_adminq.o iavf_client.o
diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h
deleted file mode 100644
index af4f94a6541e..000000000000
--- a/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h
+++ /dev/null
@@ -1,530 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2013 - 2018 Intel Corporation. */
-
-#ifndef _I40E_ADMINQ_CMD_H_
-#define _I40E_ADMINQ_CMD_H_
-
-/* This header file defines the i40e Admin Queue commands and is shared between
- * i40e Firmware and Software.  Do not change the names in this file to IAVF
- * because this file should be diff-able against the i40e version, even
- * though many parts have been removed in this VF version.
- *
- * This file needs to comply with the Linux Kernel coding style.
- */
-
-#define I40E_FW_API_VERSION_MAJOR	0x0001
-#define I40E_FW_API_VERSION_MINOR_X722	0x0005
-#define I40E_FW_API_VERSION_MINOR_X710	0x0007
-
-#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
-					I40E_FW_API_VERSION_MINOR_X710 : \
-					I40E_FW_API_VERSION_MINOR_X722)
-
-/* API version 1.7 implements additional link and PHY-specific APIs  */
-#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
-
-struct i40e_aq_desc {
-	__le16 flags;
-	__le16 opcode;
-	__le16 datalen;
-	__le16 retval;
-	__le32 cookie_high;
-	__le32 cookie_low;
-	union {
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 param2;
-			__le32 param3;
-		} internal;
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 addr_high;
-			__le32 addr_low;
-		} external;
-		u8 raw[16];
-	} params;
-};
-
-/* Flags sub-structure
- * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
- * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
- */
-
-/* command flags and offsets*/
-#define I40E_AQ_FLAG_DD_SHIFT	0
-#define I40E_AQ_FLAG_CMP_SHIFT	1
-#define I40E_AQ_FLAG_ERR_SHIFT	2
-#define I40E_AQ_FLAG_VFE_SHIFT	3
-#define I40E_AQ_FLAG_LB_SHIFT	9
-#define I40E_AQ_FLAG_RD_SHIFT	10
-#define I40E_AQ_FLAG_VFC_SHIFT	11
-#define I40E_AQ_FLAG_BUF_SHIFT	12
-#define I40E_AQ_FLAG_SI_SHIFT	13
-#define I40E_AQ_FLAG_EI_SHIFT	14
-#define I40E_AQ_FLAG_FE_SHIFT	15
-
-#define I40E_AQ_FLAG_DD		BIT(I40E_AQ_FLAG_DD_SHIFT)  /* 0x1    */
-#define I40E_AQ_FLAG_CMP	BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2    */
-#define I40E_AQ_FLAG_ERR	BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4    */
-#define I40E_AQ_FLAG_VFE	BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8    */
-#define I40E_AQ_FLAG_LB		BIT(I40E_AQ_FLAG_LB_SHIFT)  /* 0x200  */
-#define I40E_AQ_FLAG_RD		BIT(I40E_AQ_FLAG_RD_SHIFT)  /* 0x400  */
-#define I40E_AQ_FLAG_VFC	BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800  */
-#define I40E_AQ_FLAG_BUF	BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
-#define I40E_AQ_FLAG_SI		BIT(I40E_AQ_FLAG_SI_SHIFT)  /* 0x2000 */
-#define I40E_AQ_FLAG_EI		BIT(I40E_AQ_FLAG_EI_SHIFT)  /* 0x4000 */
-#define I40E_AQ_FLAG_FE		BIT(I40E_AQ_FLAG_FE_SHIFT)  /* 0x8000 */
-
-/* error codes */
-enum i40e_admin_queue_err {
-	I40E_AQ_RC_OK		= 0,  /* success */
-	I40E_AQ_RC_EPERM	= 1,  /* Operation not permitted */
-	I40E_AQ_RC_ENOENT	= 2,  /* No such element */
-	I40E_AQ_RC_ESRCH	= 3,  /* Bad opcode */
-	I40E_AQ_RC_EINTR	= 4,  /* operation interrupted */
-	I40E_AQ_RC_EIO		= 5,  /* I/O error */
-	I40E_AQ_RC_ENXIO	= 6,  /* No such resource */
-	I40E_AQ_RC_E2BIG	= 7,  /* Arg too long */
-	I40E_AQ_RC_EAGAIN	= 8,  /* Try again */
-	I40E_AQ_RC_ENOMEM	= 9,  /* Out of memory */
-	I40E_AQ_RC_EACCES	= 10, /* Permission denied */
-	I40E_AQ_RC_EFAULT	= 11, /* Bad address */
-	I40E_AQ_RC_EBUSY	= 12, /* Device or resource busy */
-	I40E_AQ_RC_EEXIST	= 13, /* object already exists */
-	I40E_AQ_RC_EINVAL	= 14, /* Invalid argument */
-	I40E_AQ_RC_ENOTTY	= 15, /* Not a typewriter */
-	I40E_AQ_RC_ENOSPC	= 16, /* No space left or alloc failure */
-	I40E_AQ_RC_ENOSYS	= 17, /* Function not implemented */
-	I40E_AQ_RC_ERANGE	= 18, /* Parameter out of range */
-	I40E_AQ_RC_EFLUSHED	= 19, /* Cmd flushed due to prev cmd error */
-	I40E_AQ_RC_BAD_ADDR	= 20, /* Descriptor contains a bad pointer */
-	I40E_AQ_RC_EMODE	= 21, /* Op not allowed in current dev mode */
-	I40E_AQ_RC_EFBIG	= 22, /* File too large */
-};
-
-/* Admin Queue command opcodes */
-enum i40e_admin_queue_opc {
-	/* aq commands */
-	i40e_aqc_opc_get_version	= 0x0001,
-	i40e_aqc_opc_driver_version	= 0x0002,
-	i40e_aqc_opc_queue_shutdown	= 0x0003,
-	i40e_aqc_opc_set_pf_context	= 0x0004,
-
-	/* resource ownership */
-	i40e_aqc_opc_request_resource	= 0x0008,
-	i40e_aqc_opc_release_resource	= 0x0009,
-
-	i40e_aqc_opc_list_func_capabilities	= 0x000A,
-	i40e_aqc_opc_list_dev_capabilities	= 0x000B,
-
-	/* Proxy commands */
-	i40e_aqc_opc_set_proxy_config		= 0x0104,
-	i40e_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
-
-	/* LAA */
-	i40e_aqc_opc_mac_address_read	= 0x0107,
-	i40e_aqc_opc_mac_address_write	= 0x0108,
-
-	/* PXE */
-	i40e_aqc_opc_clear_pxe_mode	= 0x0110,
-
-	/* WoL commands */
-	i40e_aqc_opc_set_wol_filter	= 0x0120,
-	i40e_aqc_opc_get_wake_reason	= 0x0121,
-
-	/* internal switch commands */
-	i40e_aqc_opc_get_switch_config		= 0x0200,
-	i40e_aqc_opc_add_statistics		= 0x0201,
-	i40e_aqc_opc_remove_statistics		= 0x0202,
-	i40e_aqc_opc_set_port_parameters	= 0x0203,
-	i40e_aqc_opc_get_switch_resource_alloc	= 0x0204,
-	i40e_aqc_opc_set_switch_config		= 0x0205,
-	i40e_aqc_opc_rx_ctl_reg_read		= 0x0206,
-	i40e_aqc_opc_rx_ctl_reg_write		= 0x0207,
-
-	i40e_aqc_opc_add_vsi			= 0x0210,
-	i40e_aqc_opc_update_vsi_parameters	= 0x0211,
-	i40e_aqc_opc_get_vsi_parameters		= 0x0212,
-
-	i40e_aqc_opc_add_pv			= 0x0220,
-	i40e_aqc_opc_update_pv_parameters	= 0x0221,
-	i40e_aqc_opc_get_pv_parameters		= 0x0222,
-
-	i40e_aqc_opc_add_veb			= 0x0230,
-	i40e_aqc_opc_update_veb_parameters	= 0x0231,
-	i40e_aqc_opc_get_veb_parameters		= 0x0232,
-
-	i40e_aqc_opc_delete_element		= 0x0243,
-
-	i40e_aqc_opc_add_macvlan		= 0x0250,
-	i40e_aqc_opc_remove_macvlan		= 0x0251,
-	i40e_aqc_opc_add_vlan			= 0x0252,
-	i40e_aqc_opc_remove_vlan		= 0x0253,
-	i40e_aqc_opc_set_vsi_promiscuous_modes	= 0x0254,
-	i40e_aqc_opc_add_tag			= 0x0255,
-	i40e_aqc_opc_remove_tag			= 0x0256,
-	i40e_aqc_opc_add_multicast_etag		= 0x0257,
-	i40e_aqc_opc_remove_multicast_etag	= 0x0258,
-	i40e_aqc_opc_update_tag			= 0x0259,
-	i40e_aqc_opc_add_control_packet_filter	= 0x025A,
-	i40e_aqc_opc_remove_control_packet_filter	= 0x025B,
-	i40e_aqc_opc_add_cloud_filters		= 0x025C,
-	i40e_aqc_opc_remove_cloud_filters	= 0x025D,
-	i40e_aqc_opc_clear_wol_switch_filters	= 0x025E,
-
-	i40e_aqc_opc_add_mirror_rule	= 0x0260,
-	i40e_aqc_opc_delete_mirror_rule	= 0x0261,
-
-	/* Dynamic Device Personalization */
-	i40e_aqc_opc_write_personalization_profile	= 0x0270,
-	i40e_aqc_opc_get_personalization_profile_list	= 0x0271,
-
-	/* DCB commands */
-	i40e_aqc_opc_dcb_ignore_pfc	= 0x0301,
-	i40e_aqc_opc_dcb_updated	= 0x0302,
-	i40e_aqc_opc_set_dcb_parameters = 0x0303,
-
-	/* TX scheduler */
-	i40e_aqc_opc_configure_vsi_bw_limit		= 0x0400,
-	i40e_aqc_opc_configure_vsi_ets_sla_bw_limit	= 0x0406,
-	i40e_aqc_opc_configure_vsi_tc_bw		= 0x0407,
-	i40e_aqc_opc_query_vsi_bw_config		= 0x0408,
-	i40e_aqc_opc_query_vsi_ets_sla_config		= 0x040A,
-	i40e_aqc_opc_configure_switching_comp_bw_limit	= 0x0410,
-
-	i40e_aqc_opc_enable_switching_comp_ets			= 0x0413,
-	i40e_aqc_opc_modify_switching_comp_ets			= 0x0414,
-	i40e_aqc_opc_disable_switching_comp_ets			= 0x0415,
-	i40e_aqc_opc_configure_switching_comp_ets_bw_limit	= 0x0416,
-	i40e_aqc_opc_configure_switching_comp_bw_config		= 0x0417,
-	i40e_aqc_opc_query_switching_comp_ets_config		= 0x0418,
-	i40e_aqc_opc_query_port_ets_config			= 0x0419,
-	i40e_aqc_opc_query_switching_comp_bw_config		= 0x041A,
-	i40e_aqc_opc_suspend_port_tx				= 0x041B,
-	i40e_aqc_opc_resume_port_tx				= 0x041C,
-	i40e_aqc_opc_configure_partition_bw			= 0x041D,
-	/* hmc */
-	i40e_aqc_opc_query_hmc_resource_profile	= 0x0500,
-	i40e_aqc_opc_set_hmc_resource_profile	= 0x0501,
-
-	/* phy commands*/
-	i40e_aqc_opc_get_phy_abilities		= 0x0600,
-	i40e_aqc_opc_set_phy_config		= 0x0601,
-	i40e_aqc_opc_set_mac_config		= 0x0603,
-	i40e_aqc_opc_set_link_restart_an	= 0x0605,
-	i40e_aqc_opc_get_link_status		= 0x0607,
-	i40e_aqc_opc_set_phy_int_mask		= 0x0613,
-	i40e_aqc_opc_get_local_advt_reg		= 0x0614,
-	i40e_aqc_opc_set_local_advt_reg		= 0x0615,
-	i40e_aqc_opc_get_partner_advt		= 0x0616,
-	i40e_aqc_opc_set_lb_modes		= 0x0618,
-	i40e_aqc_opc_get_phy_wol_caps		= 0x0621,
-	i40e_aqc_opc_set_phy_debug		= 0x0622,
-	i40e_aqc_opc_upload_ext_phy_fm		= 0x0625,
-	i40e_aqc_opc_run_phy_activity		= 0x0626,
-	i40e_aqc_opc_set_phy_register		= 0x0628,
-	i40e_aqc_opc_get_phy_register		= 0x0629,
-
-	/* NVM commands */
-	i40e_aqc_opc_nvm_read			= 0x0701,
-	i40e_aqc_opc_nvm_erase			= 0x0702,
-	i40e_aqc_opc_nvm_update			= 0x0703,
-	i40e_aqc_opc_nvm_config_read		= 0x0704,
-	i40e_aqc_opc_nvm_config_write		= 0x0705,
-	i40e_aqc_opc_oem_post_update		= 0x0720,
-	i40e_aqc_opc_thermal_sensor		= 0x0721,
-
-	/* virtualization commands */
-	i40e_aqc_opc_send_msg_to_pf		= 0x0801,
-	i40e_aqc_opc_send_msg_to_vf		= 0x0802,
-	i40e_aqc_opc_send_msg_to_peer		= 0x0803,
-
-	/* alternate structure */
-	i40e_aqc_opc_alternate_write		= 0x0900,
-	i40e_aqc_opc_alternate_write_indirect	= 0x0901,
-	i40e_aqc_opc_alternate_read		= 0x0902,
-	i40e_aqc_opc_alternate_read_indirect	= 0x0903,
-	i40e_aqc_opc_alternate_write_done	= 0x0904,
-	i40e_aqc_opc_alternate_set_mode		= 0x0905,
-	i40e_aqc_opc_alternate_clear_port	= 0x0906,
-
-	/* LLDP commands */
-	i40e_aqc_opc_lldp_get_mib	= 0x0A00,
-	i40e_aqc_opc_lldp_update_mib	= 0x0A01,
-	i40e_aqc_opc_lldp_add_tlv	= 0x0A02,
-	i40e_aqc_opc_lldp_update_tlv	= 0x0A03,
-	i40e_aqc_opc_lldp_delete_tlv	= 0x0A04,
-	i40e_aqc_opc_lldp_stop		= 0x0A05,
-	i40e_aqc_opc_lldp_start		= 0x0A06,
-
-	/* Tunnel commands */
-	i40e_aqc_opc_add_udp_tunnel	= 0x0B00,
-	i40e_aqc_opc_del_udp_tunnel	= 0x0B01,
-	i40e_aqc_opc_set_rss_key	= 0x0B02,
-	i40e_aqc_opc_set_rss_lut	= 0x0B03,
-	i40e_aqc_opc_get_rss_key	= 0x0B04,
-	i40e_aqc_opc_get_rss_lut	= 0x0B05,
-
-	/* Async Events */
-	i40e_aqc_opc_event_lan_overflow		= 0x1001,
-
-	/* OEM commands */
-	i40e_aqc_opc_oem_parameter_change	= 0xFE00,
-	i40e_aqc_opc_oem_device_status_change	= 0xFE01,
-	i40e_aqc_opc_oem_ocsd_initialize	= 0xFE02,
-	i40e_aqc_opc_oem_ocbb_initialize	= 0xFE03,
-
-	/* debug commands */
-	i40e_aqc_opc_debug_read_reg		= 0xFF03,
-	i40e_aqc_opc_debug_write_reg		= 0xFF04,
-	i40e_aqc_opc_debug_modify_reg		= 0xFF07,
-	i40e_aqc_opc_debug_dump_internals	= 0xFF08,
-};
-
-/* command structures and indirect data structures */
-
-/* Structure naming conventions:
- * - no suffix for direct command descriptor structures
- * - _data for indirect sent data
- * - _resp for indirect return data (data which is both will use _data)
- * - _completion for direct return data
- * - _element_ for repeated elements (may also be _data or _resp)
- *
- * Command structures are expected to overlay the params.raw member of the basic
- * descriptor, and as such cannot exceed 16 bytes in length.
- */
-
-/* This macro is used to generate a compilation error if a structure
- * is not exactly the correct length. It gives a divide by zero error if the
- * structure is not of the correct size, otherwise it creates an enum that is
- * never used.
- */
-#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \
-	{ i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) }
-
-/* This macro is used extensively to ensure that command structures are 16
- * bytes in length as they have to map to the raw array of that size.
- */
-#define I40E_CHECK_CMD_LENGTH(X)	I40E_CHECK_STRUCT_LEN(16, X)
-
-/* Queue Shutdown (direct 0x0003) */
-struct i40e_aqc_queue_shutdown {
-	__le32	driver_unloading;
-#define I40E_AQ_DRIVER_UNLOADING	0x1
-	u8	reserved[12];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown);
-
-struct i40e_aqc_vsi_properties_data {
-	/* first 96 byte are written by SW */
-	__le16	valid_sections;
-#define I40E_AQ_VSI_PROP_SWITCH_VALID		0x0001
-#define I40E_AQ_VSI_PROP_SECURITY_VALID		0x0002
-#define I40E_AQ_VSI_PROP_VLAN_VALID		0x0004
-#define I40E_AQ_VSI_PROP_CAS_PV_VALID		0x0008
-#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID	0x0010
-#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID	0x0020
-#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID	0x0040
-#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID	0x0080
-#define I40E_AQ_VSI_PROP_OUTER_UP_VALID		0x0100
-#define I40E_AQ_VSI_PROP_SCHED_VALID		0x0200
-	/* switch section */
-	__le16	switch_id; /* 12bit id combined with flags below */
-#define I40E_AQ_VSI_SW_ID_SHIFT		0x0000
-#define I40E_AQ_VSI_SW_ID_MASK		(0xFFF << I40E_AQ_VSI_SW_ID_SHIFT)
-#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG	0x1000
-#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB	0x2000
-#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB	0x4000
-	u8	sw_reserved[2];
-	/* security section */
-	u8	sec_flags;
-#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD	0x01
-#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK	0x02
-#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK	0x04
-	u8	sec_reserved;
-	/* VLAN section */
-	__le16	pvid; /* VLANS include priority bits */
-	__le16	fcoe_pvid;
-	u8	port_vlan_flags;
-#define I40E_AQ_VSI_PVLAN_MODE_SHIFT	0x00
-#define I40E_AQ_VSI_PVLAN_MODE_MASK	(0x03 << \
-					 I40E_AQ_VSI_PVLAN_MODE_SHIFT)
-#define I40E_AQ_VSI_PVLAN_MODE_TAGGED	0x01
-#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED	0x02
-#define I40E_AQ_VSI_PVLAN_MODE_ALL	0x03
-#define I40E_AQ_VSI_PVLAN_INSERT_PVID	0x04
-#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT	0x03
-#define I40E_AQ_VSI_PVLAN_EMOD_MASK	(0x3 << \
-					 I40E_AQ_VSI_PVLAN_EMOD_SHIFT)
-#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH	0x0
-#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP	0x08
-#define I40E_AQ_VSI_PVLAN_EMOD_STR	0x10
-#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING	0x18
-	u8	pvlan_reserved[3];
-	/* ingress egress up sections */
-	__le32	ingress_table; /* bitmap, 3 bits per up */
-#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT	0
-#define I40E_AQ_VSI_UP_TABLE_UP0_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP0_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT	3
-#define I40E_AQ_VSI_UP_TABLE_UP1_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP1_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT	6
-#define I40E_AQ_VSI_UP_TABLE_UP2_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP2_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT	9
-#define I40E_AQ_VSI_UP_TABLE_UP3_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP3_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT	12
-#define I40E_AQ_VSI_UP_TABLE_UP4_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP4_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT	15
-#define I40E_AQ_VSI_UP_TABLE_UP5_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP5_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT	18
-#define I40E_AQ_VSI_UP_TABLE_UP6_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP6_SHIFT)
-#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT	21
-#define I40E_AQ_VSI_UP_TABLE_UP7_MASK	(0x7 << \
-					 I40E_AQ_VSI_UP_TABLE_UP7_SHIFT)
-	__le32	egress_table;   /* same defines as for ingress table */
-	/* cascaded PV section */
-	__le16	cas_pv_tag;
-	u8	cas_pv_flags;
-#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT		0x00
-#define I40E_AQ_VSI_CAS_PV_TAGX_MASK		(0x03 << \
-						 I40E_AQ_VSI_CAS_PV_TAGX_SHIFT)
-#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE		0x00
-#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE		0x01
-#define I40E_AQ_VSI_CAS_PV_TAGX_COPY		0x02
-#define I40E_AQ_VSI_CAS_PV_INSERT_TAG		0x10
-#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE		0x20
-#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG	0x40
-	u8	cas_pv_reserved;
-	/* queue mapping section */
-	__le16	mapping_flags;
-#define I40E_AQ_VSI_QUE_MAP_CONTIG	0x0
-#define I40E_AQ_VSI_QUE_MAP_NONCONTIG	0x1
-	__le16	queue_mapping[16];
-#define I40E_AQ_VSI_QUEUE_SHIFT		0x0
-#define I40E_AQ_VSI_QUEUE_MASK		(0x7FF << I40E_AQ_VSI_QUEUE_SHIFT)
-	__le16	tc_mapping[8];
-#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT	0
-#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK	(0x1FF << \
-					 I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT)
-#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT	9
-#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK	(0x7 << \
-					 I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT)
-	/* queueing option section */
-	u8	queueing_opt_flags;
-#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA	0x04
-#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA	0x08
-#define I40E_AQ_VSI_QUE_OPT_TCP_ENA	0x10
-#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA	0x20
-#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF	0x00
-#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI	0x40
-	u8	queueing_opt_reserved[3];
-	/* scheduler section */
-	u8	up_enable_bits;
-	u8	sched_reserved;
-	/* outer up section */
-	__le32	outer_up_table; /* same structure and defines as ingress tbl */
-	u8	cmd_reserved[8];
-	/* last 32 bytes are written by FW */
-	__le16	qs_handle[8];
-#define I40E_AQ_VSI_QS_HANDLE_INVALID	0xFFFF
-	__le16	stat_counter_idx;
-	__le16	sched_id;
-	u8	resp_reserved[12];
-};
-
-I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data);
-
-/* Get VEB Parameters (direct 0x0232)
- * uses i40e_aqc_switch_seid for the descriptor
- */
-struct i40e_aqc_get_veb_parameters_completion {
-	__le16	seid;
-	__le16	switch_id;
-	__le16	veb_flags; /* only the first/last flags from 0x0230 is valid */
-	__le16	statistic_index;
-	__le16	vebs_used;
-	__le16	vebs_free;
-	u8	reserved[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion);
-
-#define I40E_LINK_SPEED_100MB_SHIFT	0x1
-#define I40E_LINK_SPEED_1000MB_SHIFT	0x2
-#define I40E_LINK_SPEED_10GB_SHIFT	0x3
-#define I40E_LINK_SPEED_40GB_SHIFT	0x4
-#define I40E_LINK_SPEED_20GB_SHIFT	0x5
-#define I40E_LINK_SPEED_25GB_SHIFT	0x6
-
-enum i40e_aq_link_speed {
-	I40E_LINK_SPEED_UNKNOWN	= 0,
-	I40E_LINK_SPEED_100MB	= BIT(I40E_LINK_SPEED_100MB_SHIFT),
-	I40E_LINK_SPEED_1GB	= BIT(I40E_LINK_SPEED_1000MB_SHIFT),
-	I40E_LINK_SPEED_10GB	= BIT(I40E_LINK_SPEED_10GB_SHIFT),
-	I40E_LINK_SPEED_40GB	= BIT(I40E_LINK_SPEED_40GB_SHIFT),
-	I40E_LINK_SPEED_20GB	= BIT(I40E_LINK_SPEED_20GB_SHIFT),
-	I40E_LINK_SPEED_25GB	= BIT(I40E_LINK_SPEED_25GB_SHIFT),
-};
-
-/* Send to PF command (indirect 0x0801) id is only used by PF
- * Send to VF command (indirect 0x0802) id is only used by PF
- * Send to Peer PF command (indirect 0x0803)
- */
-struct i40e_aqc_pf_vf_message {
-	__le32	id;
-	u8	reserved[4];
-	__le32	addr_high;
-	__le32	addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message);
-
-struct i40e_aqc_get_set_rss_key {
-#define I40E_AQC_SET_RSS_KEY_VSI_VALID		BIT(15)
-#define I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT	0
-#define I40E_AQC_SET_RSS_KEY_VSI_ID_MASK	(0x3FF << \
-					I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT)
-	__le16	vsi_id;
-	u8	reserved[6];
-	__le32	addr_high;
-	__le32	addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_key);
-
-struct i40e_aqc_get_set_rss_key_data {
-	u8 standard_rss_key[0x28];
-	u8 extended_hash_key[0xc];
-};
-
-I40E_CHECK_STRUCT_LEN(0x34, i40e_aqc_get_set_rss_key_data);
-
-struct  i40e_aqc_get_set_rss_lut {
-#define I40E_AQC_SET_RSS_LUT_VSI_VALID		BIT(15)
-#define I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT	0
-#define I40E_AQC_SET_RSS_LUT_VSI_ID_MASK	(0x3FF << \
-					I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT)
-	__le16	vsi_id;
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT	0
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \
-				BIT(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT)
-
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI	0
-#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF	1
-	__le16	flags;
-	u8	reserved[4];
-	__le32	addr_high;
-	__le32	addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_lut);
-#endif /* _I40E_ADMINQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 272d76b733aa..9fc635d816d2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -109,7 +109,7 @@ struct iavf_q_vector {
 
 /* Helper macros to switch between ints/sec and what the register uses.
  * And yes, it's the same math going both ways.  The lowest value
- * supported by all of the i40e hardware is 8.
+ * supported by all of the iavf hardware is 8.
  */
 #define EITR_INTS_PER_SEC_TO_REG(_eitr) \
 	((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8)
@@ -171,6 +171,7 @@ enum iavf_state_t {
 	__IAVF_INIT_GET_RESOURCES,	/* aq msg sent, awaiting reply */
 	__IAVF_INIT_SW,		/* got resources, setting up structs */
 	__IAVF_RESETTING,		/* in reset */
+	__IAVF_COMM_FAILED,		/* communication with PF failed */
 	/* Below here, watchdog is running */
 	__IAVF_DOWN,			/* ready, can be opened */
 	__IAVF_DOWN_PENDING,		/* descending, waiting for watchdog */
@@ -216,7 +217,6 @@ struct iavf_cloud_filter {
 
 /* board specific private data structure */
 struct iavf_adapter {
-	struct timer_list watchdog_timer;
 	struct work_struct reset_task;
 	struct work_struct adminq_task;
 	struct delayed_work client_task;
@@ -244,7 +244,7 @@ struct iavf_adapter {
 	int num_iwarp_msix;
 	int iwarp_base_vector;
 	u32 client_pending;
-	struct i40e_client_instance *cinst;
+	struct iavf_client_instance *cinst;
 	struct msix_entry *msix_entries;
 
 	u32 flags;
@@ -303,7 +303,7 @@ struct iavf_adapter {
 	enum iavf_state_t state;
 	unsigned long crit_section;
 
-	struct work_struct watchdog_task;
+	struct delayed_work watchdog_task;
 	bool netdev_registered;
 	bool link_up;
 	enum virtchnl_link_speed link_speed;
@@ -351,7 +351,7 @@ struct iavf_adapter {
 /* Ethtool Private Flags */
 
 /* lan device, used by client interface */
-struct i40e_device {
+struct iavf_device {
 	struct list_head list;
 	struct iavf_adapter *vf;
 };
@@ -359,6 +359,7 @@ struct i40e_device {
 /* needed by iavf_ethtool.c */
 extern char iavf_driver_name[];
 extern const char iavf_driver_version[];
+extern struct workqueue_struct *iavf_wq;
 
 int iavf_up(struct iavf_adapter *adapter);
 void iavf_down(struct iavf_adapter *adapter);
@@ -402,7 +403,7 @@ void iavf_enable_vlan_stripping(struct iavf_adapter *adapter);
 void iavf_disable_vlan_stripping(struct iavf_adapter *adapter);
 void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			      enum virtchnl_ops v_opcode,
-			      iavf_status v_retval, u8 *msg, u16 msglen);
+			      enum iavf_status v_retval, u8 *msg, u16 msglen);
 int iavf_config_rss(struct iavf_adapter *adapter);
 int iavf_lan_add_device(struct iavf_adapter *adapter);
 int iavf_lan_del_device(struct iavf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq.c b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
index fca1ecfd9f71..9fa3fa99b4c2 100644
--- a/drivers/net/ethernet/intel/iavf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.c
@@ -4,16 +4,16 @@
 #include "iavf_status.h"
 #include "iavf_type.h"
 #include "iavf_register.h"
-#include "i40e_adminq.h"
+#include "iavf_adminq.h"
 #include "iavf_prototype.h"
 
 /**
- *  i40e_adminq_init_regs - Initialize AdminQ registers
+ *  iavf_adminq_init_regs - Initialize AdminQ registers
  *  @hw: pointer to the hardware structure
  *
  *  This assumes the alloc_asq and alloc_arq functions have already been called
  **/
-static void i40e_adminq_init_regs(struct iavf_hw *hw)
+static void iavf_adminq_init_regs(struct iavf_hw *hw)
 {
 	/* set head and tail registers in our local struct */
 	hw->aq.asq.tail = IAVF_VF_ATQT1;
@@ -29,24 +29,24 @@ static void i40e_adminq_init_regs(struct iavf_hw *hw)
 }
 
 /**
- *  i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings
+ *  iavf_alloc_adminq_asq_ring - Allocate Admin Queue send rings
  *  @hw: pointer to the hardware structure
  **/
-static iavf_status i40e_alloc_adminq_asq_ring(struct iavf_hw *hw)
+static enum iavf_status iavf_alloc_adminq_asq_ring(struct iavf_hw *hw)
 {
-	iavf_status ret_code;
+	enum iavf_status ret_code;
 
 	ret_code = iavf_allocate_dma_mem(hw, &hw->aq.asq.desc_buf,
-					 i40e_mem_atq_ring,
+					 iavf_mem_atq_ring,
 					 (hw->aq.num_asq_entries *
-					 sizeof(struct i40e_aq_desc)),
+					 sizeof(struct iavf_aq_desc)),
 					 IAVF_ADMINQ_DESC_ALIGNMENT);
 	if (ret_code)
 		return ret_code;
 
 	ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf,
 					  (hw->aq.num_asq_entries *
-					  sizeof(struct i40e_asq_cmd_details)));
+					  sizeof(struct iavf_asq_cmd_details)));
 	if (ret_code) {
 		iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf);
 		return ret_code;
@@ -56,55 +56,55 @@ static iavf_status i40e_alloc_adminq_asq_ring(struct iavf_hw *hw)
 }
 
 /**
- *  i40e_alloc_adminq_arq_ring - Allocate Admin Queue receive rings
+ *  iavf_alloc_adminq_arq_ring - Allocate Admin Queue receive rings
  *  @hw: pointer to the hardware structure
  **/
-static iavf_status i40e_alloc_adminq_arq_ring(struct iavf_hw *hw)
+static enum iavf_status iavf_alloc_adminq_arq_ring(struct iavf_hw *hw)
 {
-	iavf_status ret_code;
+	enum iavf_status ret_code;
 
 	ret_code = iavf_allocate_dma_mem(hw, &hw->aq.arq.desc_buf,
-					 i40e_mem_arq_ring,
+					 iavf_mem_arq_ring,
 					 (hw->aq.num_arq_entries *
-					 sizeof(struct i40e_aq_desc)),
+					 sizeof(struct iavf_aq_desc)),
 					 IAVF_ADMINQ_DESC_ALIGNMENT);
 
 	return ret_code;
 }
 
 /**
- *  i40e_free_adminq_asq - Free Admin Queue send rings
+ *  iavf_free_adminq_asq - Free Admin Queue send rings
  *  @hw: pointer to the hardware structure
  *
  *  This assumes the posted send buffers have already been cleaned
  *  and de-allocated
  **/
-static void i40e_free_adminq_asq(struct iavf_hw *hw)
+static void iavf_free_adminq_asq(struct iavf_hw *hw)
 {
 	iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf);
 }
 
 /**
- *  i40e_free_adminq_arq - Free Admin Queue receive rings
+ *  iavf_free_adminq_arq - Free Admin Queue receive rings
  *  @hw: pointer to the hardware structure
  *
  *  This assumes the posted receive buffers have already been cleaned
  *  and de-allocated
  **/
-static void i40e_free_adminq_arq(struct iavf_hw *hw)
+static void iavf_free_adminq_arq(struct iavf_hw *hw)
 {
 	iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf);
 }
 
 /**
- *  i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue
+ *  iavf_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue
  *  @hw: pointer to the hardware structure
  **/
-static iavf_status i40e_alloc_arq_bufs(struct iavf_hw *hw)
+static enum iavf_status iavf_alloc_arq_bufs(struct iavf_hw *hw)
 {
-	struct i40e_aq_desc *desc;
+	struct iavf_aq_desc *desc;
 	struct iavf_dma_mem *bi;
-	iavf_status ret_code;
+	enum iavf_status ret_code;
 	int i;
 
 	/* We'll be allocating the buffer info memory first, then we can
@@ -123,7 +123,7 @@ static iavf_status i40e_alloc_arq_bufs(struct iavf_hw *hw)
 	for (i = 0; i < hw->aq.num_arq_entries; i++) {
 		bi = &hw->aq.arq.r.arq_bi[i];
 		ret_code = iavf_allocate_dma_mem(hw, bi,
-						 i40e_mem_arq_buf,
+						 iavf_mem_arq_buf,
 						 hw->aq.arq_buf_size,
 						 IAVF_ADMINQ_DESC_ALIGNMENT);
 		if (ret_code)
@@ -132,9 +132,9 @@ static iavf_status i40e_alloc_arq_bufs(struct iavf_hw *hw)
 		/* now configure the descriptors for use */
 		desc = IAVF_ADMINQ_DESC(hw->aq.arq, i);
 
-		desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
-		if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
-			desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+		desc->flags = cpu_to_le16(IAVF_AQ_FLAG_BUF);
+		if (hw->aq.arq_buf_size > IAVF_AQ_LARGE_BUF)
+			desc->flags |= cpu_to_le16(IAVF_AQ_FLAG_LB);
 		desc->opcode = 0;
 		/* This is in accordance with Admin queue design, there is no
 		 * register for buffer size configuration
@@ -165,13 +165,13 @@ unwind_alloc_arq_bufs:
 }
 
 /**
- *  i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue
+ *  iavf_alloc_asq_bufs - Allocate empty buffer structs for the send queue
  *  @hw: pointer to the hardware structure
  **/
-static iavf_status i40e_alloc_asq_bufs(struct iavf_hw *hw)
+static enum iavf_status iavf_alloc_asq_bufs(struct iavf_hw *hw)
 {
 	struct iavf_dma_mem *bi;
-	iavf_status ret_code;
+	enum iavf_status ret_code;
 	int i;
 
 	/* No mapped memory needed yet, just the buffer info structures */
@@ -186,7 +186,7 @@ static iavf_status i40e_alloc_asq_bufs(struct iavf_hw *hw)
 	for (i = 0; i < hw->aq.num_asq_entries; i++) {
 		bi = &hw->aq.asq.r.asq_bi[i];
 		ret_code = iavf_allocate_dma_mem(hw, bi,
-						 i40e_mem_asq_buf,
+						 iavf_mem_asq_buf,
 						 hw->aq.asq_buf_size,
 						 IAVF_ADMINQ_DESC_ALIGNMENT);
 		if (ret_code)
@@ -206,10 +206,10 @@ unwind_alloc_asq_bufs:
 }
 
 /**
- *  i40e_free_arq_bufs - Free receive queue buffer info elements
+ *  iavf_free_arq_bufs - Free receive queue buffer info elements
  *  @hw: pointer to the hardware structure
  **/
-static void i40e_free_arq_bufs(struct iavf_hw *hw)
+static void iavf_free_arq_bufs(struct iavf_hw *hw)
 {
 	int i;
 
@@ -225,10 +225,10 @@ static void i40e_free_arq_bufs(struct iavf_hw *hw)
 }
 
 /**
- *  i40e_free_asq_bufs - Free send queue buffer info elements
+ *  iavf_free_asq_bufs - Free send queue buffer info elements
  *  @hw: pointer to the hardware structure
  **/
-static void i40e_free_asq_bufs(struct iavf_hw *hw)
+static void iavf_free_asq_bufs(struct iavf_hw *hw)
 {
 	int i;
 
@@ -248,14 +248,14 @@ static void i40e_free_asq_bufs(struct iavf_hw *hw)
 }
 
 /**
- *  i40e_config_asq_regs - configure ASQ registers
+ *  iavf_config_asq_regs - configure ASQ registers
  *  @hw: pointer to the hardware structure
  *
  *  Configure base address and length registers for the transmit queue
  **/
-static iavf_status i40e_config_asq_regs(struct iavf_hw *hw)
+static enum iavf_status iavf_config_asq_regs(struct iavf_hw *hw)
 {
-	iavf_status ret_code = 0;
+	enum iavf_status ret_code = 0;
 	u32 reg = 0;
 
 	/* Clear Head and Tail */
@@ -271,20 +271,20 @@ static iavf_status i40e_config_asq_regs(struct iavf_hw *hw)
 	/* Check one register to verify that config was applied */
 	reg = rd32(hw, hw->aq.asq.bal);
 	if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
-		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+		ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
 
 	return ret_code;
 }
 
 /**
- *  i40e_config_arq_regs - ARQ register configuration
+ *  iavf_config_arq_regs - ARQ register configuration
  *  @hw: pointer to the hardware structure
  *
  * Configure base address and length registers for the receive (event queue)
  **/
-static iavf_status i40e_config_arq_regs(struct iavf_hw *hw)
+static enum iavf_status iavf_config_arq_regs(struct iavf_hw *hw)
 {
-	iavf_status ret_code = 0;
+	enum iavf_status ret_code = 0;
 	u32 reg = 0;
 
 	/* Clear Head and Tail */
@@ -303,13 +303,13 @@ static iavf_status i40e_config_arq_regs(struct iavf_hw *hw)
 	/* Check one register to verify that config was applied */
 	reg = rd32(hw, hw->aq.arq.bal);
 	if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
-		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+		ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
 
 	return ret_code;
 }
 
 /**
- *  i40e_init_asq - main initialization routine for ASQ
+ *  iavf_init_asq - main initialization routine for ASQ
  *  @hw: pointer to the hardware structure
  *
  *  This is the main initialization routine for the Admin Send Queue
@@ -321,20 +321,20 @@ static iavf_status i40e_config_arq_regs(struct iavf_hw *hw)
  *  Do *NOT* hold the lock when calling this as the memory allocation routines
  *  called are not going to be atomic context safe
  **/
-static iavf_status i40e_init_asq(struct iavf_hw *hw)
+static enum iavf_status iavf_init_asq(struct iavf_hw *hw)
 {
-	iavf_status ret_code = 0;
+	enum iavf_status ret_code = 0;
 
 	if (hw->aq.asq.count > 0) {
 		/* queue already initialized */
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = IAVF_ERR_NOT_READY;
 		goto init_adminq_exit;
 	}
 
 	/* verify input for valid configuration */
 	if ((hw->aq.num_asq_entries == 0) ||
 	    (hw->aq.asq_buf_size == 0)) {
-		ret_code = I40E_ERR_CONFIG;
+		ret_code = IAVF_ERR_CONFIG;
 		goto init_adminq_exit;
 	}
 
@@ -342,17 +342,17 @@ static iavf_status i40e_init_asq(struct iavf_hw *hw)
 	hw->aq.asq.next_to_clean = 0;
 
 	/* allocate the ring memory */
-	ret_code = i40e_alloc_adminq_asq_ring(hw);
+	ret_code = iavf_alloc_adminq_asq_ring(hw);
 	if (ret_code)
 		goto init_adminq_exit;
 
 	/* allocate buffers in the rings */
-	ret_code = i40e_alloc_asq_bufs(hw);
+	ret_code = iavf_alloc_asq_bufs(hw);
 	if (ret_code)
 		goto init_adminq_free_rings;
 
 	/* initialize base registers */
-	ret_code = i40e_config_asq_regs(hw);
+	ret_code = iavf_config_asq_regs(hw);
 	if (ret_code)
 		goto init_adminq_free_rings;
 
@@ -361,14 +361,14 @@ static iavf_status i40e_init_asq(struct iavf_hw *hw)
 	goto init_adminq_exit;
 
 init_adminq_free_rings:
-	i40e_free_adminq_asq(hw);
+	iavf_free_adminq_asq(hw);
 
 init_adminq_exit:
 	return ret_code;
 }
 
 /**
- *  i40e_init_arq - initialize ARQ
+ *  iavf_init_arq - initialize ARQ
  *  @hw: pointer to the hardware structure
  *
  *  The main initialization routine for the Admin Receive (Event) Queue.
@@ -380,20 +380,20 @@ init_adminq_exit:
  *  Do *NOT* hold the lock when calling this as the memory allocation routines
  *  called are not going to be atomic context safe
  **/
-static iavf_status i40e_init_arq(struct iavf_hw *hw)
+static enum iavf_status iavf_init_arq(struct iavf_hw *hw)
 {
-	iavf_status ret_code = 0;
+	enum iavf_status ret_code = 0;
 
 	if (hw->aq.arq.count > 0) {
 		/* queue already initialized */
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = IAVF_ERR_NOT_READY;
 		goto init_adminq_exit;
 	}
 
 	/* verify input for valid configuration */
 	if ((hw->aq.num_arq_entries == 0) ||
 	    (hw->aq.arq_buf_size == 0)) {
-		ret_code = I40E_ERR_CONFIG;
+		ret_code = IAVF_ERR_CONFIG;
 		goto init_adminq_exit;
 	}
 
@@ -401,17 +401,17 @@ static iavf_status i40e_init_arq(struct iavf_hw *hw)
 	hw->aq.arq.next_to_clean = 0;
 
 	/* allocate the ring memory */
-	ret_code = i40e_alloc_adminq_arq_ring(hw);
+	ret_code = iavf_alloc_adminq_arq_ring(hw);
 	if (ret_code)
 		goto init_adminq_exit;
 
 	/* allocate buffers in the rings */
-	ret_code = i40e_alloc_arq_bufs(hw);
+	ret_code = iavf_alloc_arq_bufs(hw);
 	if (ret_code)
 		goto init_adminq_free_rings;
 
 	/* initialize base registers */
-	ret_code = i40e_config_arq_regs(hw);
+	ret_code = iavf_config_arq_regs(hw);
 	if (ret_code)
 		goto init_adminq_free_rings;
 
@@ -420,26 +420,26 @@ static iavf_status i40e_init_arq(struct iavf_hw *hw)
 	goto init_adminq_exit;
 
 init_adminq_free_rings:
-	i40e_free_adminq_arq(hw);
+	iavf_free_adminq_arq(hw);
 
 init_adminq_exit:
 	return ret_code;
 }
 
 /**
- *  i40e_shutdown_asq - shutdown the ASQ
+ *  iavf_shutdown_asq - shutdown the ASQ
  *  @hw: pointer to the hardware structure
  *
  *  The main shutdown routine for the Admin Send Queue
  **/
-static iavf_status i40e_shutdown_asq(struct iavf_hw *hw)
+static enum iavf_status iavf_shutdown_asq(struct iavf_hw *hw)
 {
-	iavf_status ret_code = 0;
+	enum iavf_status ret_code = 0;
 
 	mutex_lock(&hw->aq.asq_mutex);
 
 	if (hw->aq.asq.count == 0) {
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = IAVF_ERR_NOT_READY;
 		goto shutdown_asq_out;
 	}
 
@@ -453,7 +453,7 @@ static iavf_status i40e_shutdown_asq(struct iavf_hw *hw)
 	hw->aq.asq.count = 0; /* to indicate uninitialized queue */
 
 	/* free ring buffers */
-	i40e_free_asq_bufs(hw);
+	iavf_free_asq_bufs(hw);
 
 shutdown_asq_out:
 	mutex_unlock(&hw->aq.asq_mutex);
@@ -461,19 +461,19 @@ shutdown_asq_out:
 }
 
 /**
- *  i40e_shutdown_arq - shutdown ARQ
+ *  iavf_shutdown_arq - shutdown ARQ
  *  @hw: pointer to the hardware structure
  *
  *  The main shutdown routine for the Admin Receive Queue
  **/
-static iavf_status i40e_shutdown_arq(struct iavf_hw *hw)
+static enum iavf_status iavf_shutdown_arq(struct iavf_hw *hw)
 {
-	iavf_status ret_code = 0;
+	enum iavf_status ret_code = 0;
 
 	mutex_lock(&hw->aq.arq_mutex);
 
 	if (hw->aq.arq.count == 0) {
-		ret_code = I40E_ERR_NOT_READY;
+		ret_code = IAVF_ERR_NOT_READY;
 		goto shutdown_arq_out;
 	}
 
@@ -487,7 +487,7 @@ static iavf_status i40e_shutdown_arq(struct iavf_hw *hw)
 	hw->aq.arq.count = 0; /* to indicate uninitialized queue */
 
 	/* free ring buffers */
-	i40e_free_arq_bufs(hw);
+	iavf_free_arq_bufs(hw);
 
 shutdown_arq_out:
 	mutex_unlock(&hw->aq.arq_mutex);
@@ -505,32 +505,32 @@ shutdown_arq_out:
  *     - hw->aq.arq_buf_size
  *     - hw->aq.asq_buf_size
  **/
-iavf_status iavf_init_adminq(struct iavf_hw *hw)
+enum iavf_status iavf_init_adminq(struct iavf_hw *hw)
 {
-	iavf_status ret_code;
+	enum iavf_status ret_code;
 
 	/* verify input for valid configuration */
 	if ((hw->aq.num_arq_entries == 0) ||
 	    (hw->aq.num_asq_entries == 0) ||
 	    (hw->aq.arq_buf_size == 0) ||
 	    (hw->aq.asq_buf_size == 0)) {
-		ret_code = I40E_ERR_CONFIG;
+		ret_code = IAVF_ERR_CONFIG;
 		goto init_adminq_exit;
 	}
 
 	/* Set up register offsets */
-	i40e_adminq_init_regs(hw);
+	iavf_adminq_init_regs(hw);
 
 	/* setup ASQ command write back timeout */
-	hw->aq.asq_cmd_timeout = I40E_ASQ_CMD_TIMEOUT;
+	hw->aq.asq_cmd_timeout = IAVF_ASQ_CMD_TIMEOUT;
 
 	/* allocate the ASQ */
-	ret_code = i40e_init_asq(hw);
+	ret_code = iavf_init_asq(hw);
 	if (ret_code)
 		goto init_adminq_destroy_locks;
 
 	/* allocate the ARQ */
-	ret_code = i40e_init_arq(hw);
+	ret_code = iavf_init_arq(hw);
 	if (ret_code)
 		goto init_adminq_free_asq;
 
@@ -538,7 +538,7 @@ iavf_status iavf_init_adminq(struct iavf_hw *hw)
 	goto init_adminq_exit;
 
 init_adminq_free_asq:
-	i40e_shutdown_asq(hw);
+	iavf_shutdown_asq(hw);
 init_adminq_destroy_locks:
 
 init_adminq_exit:
@@ -549,53 +549,53 @@ init_adminq_exit:
  *  iavf_shutdown_adminq - shutdown routine for the Admin Queue
  *  @hw: pointer to the hardware structure
  **/
-iavf_status iavf_shutdown_adminq(struct iavf_hw *hw)
+enum iavf_status iavf_shutdown_adminq(struct iavf_hw *hw)
 {
-	iavf_status ret_code = 0;
+	enum iavf_status ret_code = 0;
 
 	if (iavf_check_asq_alive(hw))
 		iavf_aq_queue_shutdown(hw, true);
 
-	i40e_shutdown_asq(hw);
-	i40e_shutdown_arq(hw);
+	iavf_shutdown_asq(hw);
+	iavf_shutdown_arq(hw);
 
 	return ret_code;
 }
 
 /**
- *  i40e_clean_asq - cleans Admin send queue
+ *  iavf_clean_asq - cleans Admin send queue
  *  @hw: pointer to the hardware structure
  *
  *  returns the number of free desc
  **/
-static u16 i40e_clean_asq(struct iavf_hw *hw)
+static u16 iavf_clean_asq(struct iavf_hw *hw)
 {
 	struct iavf_adminq_ring *asq = &hw->aq.asq;
-	struct i40e_asq_cmd_details *details;
+	struct iavf_asq_cmd_details *details;
 	u16 ntc = asq->next_to_clean;
-	struct i40e_aq_desc desc_cb;
-	struct i40e_aq_desc *desc;
+	struct iavf_aq_desc desc_cb;
+	struct iavf_aq_desc *desc;
 
 	desc = IAVF_ADMINQ_DESC(*asq, ntc);
-	details = I40E_ADMINQ_DETAILS(*asq, ntc);
+	details = IAVF_ADMINQ_DETAILS(*asq, ntc);
 	while (rd32(hw, hw->aq.asq.head) != ntc) {
 		iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 			   "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
 
 		if (details->callback) {
-			I40E_ADMINQ_CALLBACK cb_func =
-					(I40E_ADMINQ_CALLBACK)details->callback;
+			IAVF_ADMINQ_CALLBACK cb_func =
+					(IAVF_ADMINQ_CALLBACK)details->callback;
 			desc_cb = *desc;
 			cb_func(hw, &desc_cb);
 		}
-		memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+		memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
 		memset((void *)details, 0,
-		       sizeof(struct i40e_asq_cmd_details));
+		       sizeof(struct iavf_asq_cmd_details));
 		ntc++;
 		if (ntc == asq->count)
 			ntc = 0;
 		desc = IAVF_ADMINQ_DESC(*asq, ntc);
-		details = I40E_ADMINQ_DETAILS(*asq, ntc);
+		details = IAVF_ADMINQ_DETAILS(*asq, ntc);
 	}
 
 	asq->next_to_clean = ntc;
@@ -629,16 +629,17 @@ bool iavf_asq_done(struct iavf_hw *hw)
  *  This is the main send command driver routine for the Admin Queue send
  *  queue.  It runs the queue, cleans the queue, etc
  **/
-iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
-				  void *buff, /* can be NULL */
-				  u16  buff_size,
-				  struct i40e_asq_cmd_details *cmd_details)
+enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
+				       struct iavf_aq_desc *desc,
+				       void *buff, /* can be NULL */
+				       u16  buff_size,
+				       struct iavf_asq_cmd_details *cmd_details)
 {
 	struct iavf_dma_mem *dma_buff = NULL;
-	struct i40e_asq_cmd_details *details;
-	struct i40e_aq_desc *desc_on_ring;
+	struct iavf_asq_cmd_details *details;
+	struct iavf_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
-	iavf_status status = 0;
+	enum iavf_status status = 0;
 	u16  retval = 0;
 	u32  val = 0;
 
@@ -647,21 +648,21 @@ iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
 	if (hw->aq.asq.count == 0) {
 		iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 			   "AQTX: Admin queue not initialized.\n");
-		status = I40E_ERR_QUEUE_EMPTY;
+		status = IAVF_ERR_QUEUE_EMPTY;
 		goto asq_send_command_error;
 	}
 
-	hw->aq.asq_last_status = I40E_AQ_RC_OK;
+	hw->aq.asq_last_status = IAVF_AQ_RC_OK;
 
 	val = rd32(hw, hw->aq.asq.head);
 	if (val >= hw->aq.num_asq_entries) {
 		iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 			   "AQTX: head overrun at %d\n", val);
-		status = I40E_ERR_QUEUE_EMPTY;
+		status = IAVF_ERR_QUEUE_EMPTY;
 		goto asq_send_command_error;
 	}
 
-	details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
+	details = IAVF_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
 	if (cmd_details) {
 		*details = *cmd_details;
 
@@ -676,7 +677,7 @@ iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
 				cpu_to_le32(lower_32_bits(details->cookie));
 		}
 	} else {
-		memset(details, 0, sizeof(struct i40e_asq_cmd_details));
+		memset(details, 0, sizeof(struct iavf_asq_cmd_details));
 	}
 
 	/* clear requested flags and then set additional flags if defined */
@@ -688,7 +689,7 @@ iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
 			   IAVF_DEBUG_AQ_MESSAGE,
 			   "AQTX: Invalid buffer size: %d.\n",
 			   buff_size);
-		status = I40E_ERR_INVALID_SIZE;
+		status = IAVF_ERR_INVALID_SIZE;
 		goto asq_send_command_error;
 	}
 
@@ -696,7 +697,7 @@ iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
 		iavf_debug(hw,
 			   IAVF_DEBUG_AQ_MESSAGE,
 			   "AQTX: Async flag not set along with postpone flag");
-		status = I40E_ERR_PARAM;
+		status = IAVF_ERR_PARAM;
 		goto asq_send_command_error;
 	}
 
@@ -707,11 +708,11 @@ iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
 	/* the clean function called here could be called in a separate thread
 	 * in case of asynchronous completions
 	 */
-	if (i40e_clean_asq(hw) == 0) {
+	if (iavf_clean_asq(hw) == 0) {
 		iavf_debug(hw,
 			   IAVF_DEBUG_AQ_MESSAGE,
 			   "AQTX: Error queue is full.\n");
-		status = I40E_ERR_ADMIN_QUEUE_FULL;
+		status = IAVF_ERR_ADMIN_QUEUE_FULL;
 		goto asq_send_command_error;
 	}
 
@@ -780,13 +781,13 @@ iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
 			retval &= 0xff;
 		}
 		cmd_completed = true;
-		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
+		if ((enum iavf_admin_queue_err)retval == IAVF_AQ_RC_OK)
 			status = 0;
-		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
-			status = I40E_ERR_NOT_READY;
+		else if ((enum iavf_admin_queue_err)retval == IAVF_AQ_RC_EBUSY)
+			status = IAVF_ERR_NOT_READY;
 		else
-			status = I40E_ERR_ADMIN_QUEUE_ERROR;
-		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
+			status = IAVF_ERR_ADMIN_QUEUE_ERROR;
+		hw->aq.asq_last_status = (enum iavf_admin_queue_err)retval;
 	}
 
 	iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
@@ -803,11 +804,11 @@ iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
 		if (rd32(hw, hw->aq.asq.len) & IAVF_VF_ATQLEN1_ATQCRIT_MASK) {
 			iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 				   "AQTX: AQ Critical error.\n");
-			status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR;
+			status = IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR;
 		} else {
 			iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 				   "AQTX: Writeback timeout.\n");
-			status = I40E_ERR_ADMIN_QUEUE_TIMEOUT;
+			status = IAVF_ERR_ADMIN_QUEUE_TIMEOUT;
 		}
 	}
 
@@ -823,12 +824,12 @@ asq_send_command_error:
  *
  *  Fill the desc with default values
  **/
-void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode)
+void iavf_fill_default_direct_cmd_desc(struct iavf_aq_desc *desc, u16 opcode)
 {
 	/* zero out the desc */
-	memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+	memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
 	desc->opcode = cpu_to_le16(opcode);
-	desc->flags = cpu_to_le16(I40E_AQ_FLAG_SI);
+	desc->flags = cpu_to_le16(IAVF_AQ_FLAG_SI);
 }
 
 /**
@@ -841,13 +842,13 @@ void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode)
  *  the contents through e.  It can also return how many events are
  *  left to process through 'pending'
  **/
-iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
-				   struct i40e_arq_event_info *e,
-				   u16 *pending)
+enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
+					struct iavf_arq_event_info *e,
+					u16 *pending)
 {
 	u16 ntc = hw->aq.arq.next_to_clean;
-	struct i40e_aq_desc *desc;
-	iavf_status ret_code = 0;
+	struct iavf_aq_desc *desc;
+	enum iavf_status ret_code = 0;
 	struct iavf_dma_mem *bi;
 	u16 desc_idx;
 	u16 datalen;
@@ -863,7 +864,7 @@ iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	if (hw->aq.arq.count == 0) {
 		iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE,
 			   "AQRX: Admin queue not initialized.\n");
-		ret_code = I40E_ERR_QUEUE_EMPTY;
+		ret_code = IAVF_ERR_QUEUE_EMPTY;
 		goto clean_arq_element_err;
 	}
 
@@ -871,7 +872,7 @@ iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	ntu = rd32(hw, hw->aq.arq.head) & IAVF_VF_ARQH1_ARQH_MASK;
 	if (ntu == ntc) {
 		/* nothing to do - shouldn't need to update ring's values */
-		ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK;
+		ret_code = IAVF_ERR_ADMIN_QUEUE_NO_WORK;
 		goto clean_arq_element_out;
 	}
 
@@ -880,10 +881,10 @@ iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	desc_idx = ntc;
 
 	hw->aq.arq_last_status =
-		(enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
+		(enum iavf_admin_queue_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
-	if (flags & I40E_AQ_FLAG_ERR) {
-		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+	if (flags & IAVF_AQ_FLAG_ERR) {
+		ret_code = IAVF_ERR_ADMIN_QUEUE_ERROR;
 		iavf_debug(hw,
 			   IAVF_DEBUG_AQ_MESSAGE,
 			   "AQRX: Event received with error 0x%X.\n",
@@ -906,11 +907,11 @@ iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
 	 * size
 	 */
 	bi = &hw->aq.arq.r.arq_bi[ntc];
-	memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+	memset((void *)desc, 0, sizeof(struct iavf_aq_desc));
 
-	desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
-	if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
-		desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+	desc->flags = cpu_to_le16(IAVF_AQ_FLAG_BUF);
+	if (hw->aq.arq_buf_size > IAVF_AQ_LARGE_BUF)
+		desc->flags |= cpu_to_le16(IAVF_AQ_FLAG_LB);
 	desc->datalen = cpu_to_le16((u16)bi->size);
 	desc->params.external.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
 	desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq.h b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
index ee983889eab0..baf2fe26f302 100644
--- a/drivers/net/ethernet/intel/iavf/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq.h
@@ -6,10 +6,10 @@
 
 #include "iavf_osdep.h"
 #include "iavf_status.h"
-#include "i40e_adminq_cmd.h"
+#include "iavf_adminq_cmd.h"
 
 #define IAVF_ADMINQ_DESC(R, i)   \
-	(&(((struct i40e_aq_desc *)((R).desc_buf.va))[i]))
+	(&(((struct iavf_aq_desc *)((R).desc_buf.va))[i]))
 
 #define IAVF_ADMINQ_DESC_ALIGNMENT 4096
 
@@ -39,22 +39,22 @@ struct iavf_adminq_ring {
 };
 
 /* ASQ transaction details */
-struct i40e_asq_cmd_details {
-	void *callback; /* cast from type I40E_ADMINQ_CALLBACK */
+struct iavf_asq_cmd_details {
+	void *callback; /* cast from type IAVF_ADMINQ_CALLBACK */
 	u64 cookie;
 	u16 flags_ena;
 	u16 flags_dis;
 	bool async;
 	bool postpone;
-	struct i40e_aq_desc *wb_desc;
+	struct iavf_aq_desc *wb_desc;
 };
 
-#define I40E_ADMINQ_DETAILS(R, i)   \
-	(&(((struct i40e_asq_cmd_details *)((R).cmd_buf.va))[i]))
+#define IAVF_ADMINQ_DETAILS(R, i)   \
+	(&(((struct iavf_asq_cmd_details *)((R).cmd_buf.va))[i]))
 
 /* ARQ event information */
-struct i40e_arq_event_info {
-	struct i40e_aq_desc desc;
+struct iavf_arq_event_info {
+	struct iavf_aq_desc desc;
 	u16 msg_len;
 	u16 buf_len;
 	u8 *msg_buf;
@@ -79,45 +79,45 @@ struct iavf_adminq_info {
 	struct mutex arq_mutex; /* Receive queue lock */
 
 	/* last status values on send and receive queues */
-	enum i40e_admin_queue_err asq_last_status;
-	enum i40e_admin_queue_err arq_last_status;
+	enum iavf_admin_queue_err asq_last_status;
+	enum iavf_admin_queue_err arq_last_status;
 };
 
 /**
- * i40e_aq_rc_to_posix - convert errors to user-land codes
+ * iavf_aq_rc_to_posix - convert errors to user-land codes
  * aq_ret: AdminQ handler error code can override aq_rc
  * aq_rc: AdminQ firmware error code to convert
  **/
-static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
+static inline int iavf_aq_rc_to_posix(int aq_ret, int aq_rc)
 {
 	int aq_to_posix[] = {
-		0,           /* I40E_AQ_RC_OK */
-		-EPERM,      /* I40E_AQ_RC_EPERM */
-		-ENOENT,     /* I40E_AQ_RC_ENOENT */
-		-ESRCH,      /* I40E_AQ_RC_ESRCH */
-		-EINTR,      /* I40E_AQ_RC_EINTR */
-		-EIO,        /* I40E_AQ_RC_EIO */
-		-ENXIO,      /* I40E_AQ_RC_ENXIO */
-		-E2BIG,      /* I40E_AQ_RC_E2BIG */
-		-EAGAIN,     /* I40E_AQ_RC_EAGAIN */
-		-ENOMEM,     /* I40E_AQ_RC_ENOMEM */
-		-EACCES,     /* I40E_AQ_RC_EACCES */
-		-EFAULT,     /* I40E_AQ_RC_EFAULT */
-		-EBUSY,      /* I40E_AQ_RC_EBUSY */
-		-EEXIST,     /* I40E_AQ_RC_EEXIST */
-		-EINVAL,     /* I40E_AQ_RC_EINVAL */
-		-ENOTTY,     /* I40E_AQ_RC_ENOTTY */
-		-ENOSPC,     /* I40E_AQ_RC_ENOSPC */
-		-ENOSYS,     /* I40E_AQ_RC_ENOSYS */
-		-ERANGE,     /* I40E_AQ_RC_ERANGE */
-		-EPIPE,      /* I40E_AQ_RC_EFLUSHED */
-		-ESPIPE,     /* I40E_AQ_RC_BAD_ADDR */
-		-EROFS,      /* I40E_AQ_RC_EMODE */
-		-EFBIG,      /* I40E_AQ_RC_EFBIG */
+		0,           /* IAVF_AQ_RC_OK */
+		-EPERM,      /* IAVF_AQ_RC_EPERM */
+		-ENOENT,     /* IAVF_AQ_RC_ENOENT */
+		-ESRCH,      /* IAVF_AQ_RC_ESRCH */
+		-EINTR,      /* IAVF_AQ_RC_EINTR */
+		-EIO,        /* IAVF_AQ_RC_EIO */
+		-ENXIO,      /* IAVF_AQ_RC_ENXIO */
+		-E2BIG,      /* IAVF_AQ_RC_E2BIG */
+		-EAGAIN,     /* IAVF_AQ_RC_EAGAIN */
+		-ENOMEM,     /* IAVF_AQ_RC_ENOMEM */
+		-EACCES,     /* IAVF_AQ_RC_EACCES */
+		-EFAULT,     /* IAVF_AQ_RC_EFAULT */
+		-EBUSY,      /* IAVF_AQ_RC_EBUSY */
+		-EEXIST,     /* IAVF_AQ_RC_EEXIST */
+		-EINVAL,     /* IAVF_AQ_RC_EINVAL */
+		-ENOTTY,     /* IAVF_AQ_RC_ENOTTY */
+		-ENOSPC,     /* IAVF_AQ_RC_ENOSPC */
+		-ENOSYS,     /* IAVF_AQ_RC_ENOSYS */
+		-ERANGE,     /* IAVF_AQ_RC_ERANGE */
+		-EPIPE,      /* IAVF_AQ_RC_EFLUSHED */
+		-ESPIPE,     /* IAVF_AQ_RC_BAD_ADDR */
+		-EROFS,      /* IAVF_AQ_RC_EMODE */
+		-EFBIG,      /* IAVF_AQ_RC_EFBIG */
 	};
 
 	/* aq_rc is invalid if AQ timed out */
-	if (aq_ret == I40E_ERR_ADMIN_QUEUE_TIMEOUT)
+	if (aq_ret == IAVF_ERR_ADMIN_QUEUE_TIMEOUT)
 		return -EAGAIN;
 
 	if (!((u32)aq_rc < (sizeof(aq_to_posix) / sizeof((aq_to_posix)[0]))))
@@ -127,9 +127,9 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
 }
 
 /* general information */
-#define I40E_AQ_LARGE_BUF	512
-#define I40E_ASQ_CMD_TIMEOUT	250000  /* usecs */
+#define IAVF_AQ_LARGE_BUF	512
+#define IAVF_ASQ_CMD_TIMEOUT	250000  /* usecs */
 
-void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode);
+void iavf_fill_default_direct_cmd_desc(struct iavf_aq_desc *desc, u16 opcode);
 
 #endif /* _IAVF_ADMINQ_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h b/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h
new file mode 100644
index 000000000000..bc512308557b
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_adminq_cmd.h
@@ -0,0 +1,528 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2013 - 2018 Intel Corporation. */
+
+#ifndef _IAVF_ADMINQ_CMD_H_
+#define _IAVF_ADMINQ_CMD_H_
+
+/* This header file defines the iavf Admin Queue commands and is shared between
+ * iavf Firmware and Software.
+ *
+ * This file needs to comply with the Linux Kernel coding style.
+ */
+
+#define IAVF_FW_API_VERSION_MAJOR	0x0001
+#define IAVF_FW_API_VERSION_MINOR_X722	0x0005
+#define IAVF_FW_API_VERSION_MINOR_X710	0x0008
+
+#define IAVF_FW_MINOR_VERSION(_h) ((_h)->mac.type == IAVF_MAC_XL710 ? \
+					IAVF_FW_API_VERSION_MINOR_X710 : \
+					IAVF_FW_API_VERSION_MINOR_X722)
+
+/* API version 1.7 implements additional link and PHY-specific APIs  */
+#define IAVF_MINOR_VER_GET_LINK_INFO_XL710 0x0007
+
+struct iavf_aq_desc {
+	__le16 flags;
+	__le16 opcode;
+	__le16 datalen;
+	__le16 retval;
+	__le32 cookie_high;
+	__le32 cookie_low;
+	union {
+		struct {
+			__le32 param0;
+			__le32 param1;
+			__le32 param2;
+			__le32 param3;
+		} internal;
+		struct {
+			__le32 param0;
+			__le32 param1;
+			__le32 addr_high;
+			__le32 addr_low;
+		} external;
+		u8 raw[16];
+	} params;
+};
+
+/* Flags sub-structure
+ * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
+ * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
+ */
+
+/* command flags and offsets*/
+#define IAVF_AQ_FLAG_DD_SHIFT	0
+#define IAVF_AQ_FLAG_CMP_SHIFT	1
+#define IAVF_AQ_FLAG_ERR_SHIFT	2
+#define IAVF_AQ_FLAG_VFE_SHIFT	3
+#define IAVF_AQ_FLAG_LB_SHIFT	9
+#define IAVF_AQ_FLAG_RD_SHIFT	10
+#define IAVF_AQ_FLAG_VFC_SHIFT	11
+#define IAVF_AQ_FLAG_BUF_SHIFT	12
+#define IAVF_AQ_FLAG_SI_SHIFT	13
+#define IAVF_AQ_FLAG_EI_SHIFT	14
+#define IAVF_AQ_FLAG_FE_SHIFT	15
+
+#define IAVF_AQ_FLAG_DD		BIT(IAVF_AQ_FLAG_DD_SHIFT)  /* 0x1    */
+#define IAVF_AQ_FLAG_CMP	BIT(IAVF_AQ_FLAG_CMP_SHIFT) /* 0x2    */
+#define IAVF_AQ_FLAG_ERR	BIT(IAVF_AQ_FLAG_ERR_SHIFT) /* 0x4    */
+#define IAVF_AQ_FLAG_VFE	BIT(IAVF_AQ_FLAG_VFE_SHIFT) /* 0x8    */
+#define IAVF_AQ_FLAG_LB		BIT(IAVF_AQ_FLAG_LB_SHIFT)  /* 0x200  */
+#define IAVF_AQ_FLAG_RD		BIT(IAVF_AQ_FLAG_RD_SHIFT)  /* 0x400  */
+#define IAVF_AQ_FLAG_VFC	BIT(IAVF_AQ_FLAG_VFC_SHIFT) /* 0x800  */
+#define IAVF_AQ_FLAG_BUF	BIT(IAVF_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
+#define IAVF_AQ_FLAG_SI		BIT(IAVF_AQ_FLAG_SI_SHIFT)  /* 0x2000 */
+#define IAVF_AQ_FLAG_EI		BIT(IAVF_AQ_FLAG_EI_SHIFT)  /* 0x4000 */
+#define IAVF_AQ_FLAG_FE		BIT(IAVF_AQ_FLAG_FE_SHIFT)  /* 0x8000 */
+
+/* error codes */
+enum iavf_admin_queue_err {
+	IAVF_AQ_RC_OK		= 0,  /* success */
+	IAVF_AQ_RC_EPERM	= 1,  /* Operation not permitted */
+	IAVF_AQ_RC_ENOENT	= 2,  /* No such element */
+	IAVF_AQ_RC_ESRCH	= 3,  /* Bad opcode */
+	IAVF_AQ_RC_EINTR	= 4,  /* operation interrupted */
+	IAVF_AQ_RC_EIO		= 5,  /* I/O error */
+	IAVF_AQ_RC_ENXIO	= 6,  /* No such resource */
+	IAVF_AQ_RC_E2BIG	= 7,  /* Arg too long */
+	IAVF_AQ_RC_EAGAIN	= 8,  /* Try again */
+	IAVF_AQ_RC_ENOMEM	= 9,  /* Out of memory */
+	IAVF_AQ_RC_EACCES	= 10, /* Permission denied */
+	IAVF_AQ_RC_EFAULT	= 11, /* Bad address */
+	IAVF_AQ_RC_EBUSY	= 12, /* Device or resource busy */
+	IAVF_AQ_RC_EEXIST	= 13, /* object already exists */
+	IAVF_AQ_RC_EINVAL	= 14, /* Invalid argument */
+	IAVF_AQ_RC_ENOTTY	= 15, /* Not a typewriter */
+	IAVF_AQ_RC_ENOSPC	= 16, /* No space left or alloc failure */
+	IAVF_AQ_RC_ENOSYS	= 17, /* Function not implemented */
+	IAVF_AQ_RC_ERANGE	= 18, /* Parameter out of range */
+	IAVF_AQ_RC_EFLUSHED	= 19, /* Cmd flushed due to prev cmd error */
+	IAVF_AQ_RC_BAD_ADDR	= 20, /* Descriptor contains a bad pointer */
+	IAVF_AQ_RC_EMODE	= 21, /* Op not allowed in current dev mode */
+	IAVF_AQ_RC_EFBIG	= 22, /* File too large */
+};
+
+/* Admin Queue command opcodes */
+enum iavf_admin_queue_opc {
+	/* aq commands */
+	iavf_aqc_opc_get_version	= 0x0001,
+	iavf_aqc_opc_driver_version	= 0x0002,
+	iavf_aqc_opc_queue_shutdown	= 0x0003,
+	iavf_aqc_opc_set_pf_context	= 0x0004,
+
+	/* resource ownership */
+	iavf_aqc_opc_request_resource	= 0x0008,
+	iavf_aqc_opc_release_resource	= 0x0009,
+
+	iavf_aqc_opc_list_func_capabilities	= 0x000A,
+	iavf_aqc_opc_list_dev_capabilities	= 0x000B,
+
+	/* Proxy commands */
+	iavf_aqc_opc_set_proxy_config		= 0x0104,
+	iavf_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
+
+	/* LAA */
+	iavf_aqc_opc_mac_address_read	= 0x0107,
+	iavf_aqc_opc_mac_address_write	= 0x0108,
+
+	/* PXE */
+	iavf_aqc_opc_clear_pxe_mode	= 0x0110,
+
+	/* WoL commands */
+	iavf_aqc_opc_set_wol_filter	= 0x0120,
+	iavf_aqc_opc_get_wake_reason	= 0x0121,
+
+	/* internal switch commands */
+	iavf_aqc_opc_get_switch_config		= 0x0200,
+	iavf_aqc_opc_add_statistics		= 0x0201,
+	iavf_aqc_opc_remove_statistics		= 0x0202,
+	iavf_aqc_opc_set_port_parameters	= 0x0203,
+	iavf_aqc_opc_get_switch_resource_alloc	= 0x0204,
+	iavf_aqc_opc_set_switch_config		= 0x0205,
+	iavf_aqc_opc_rx_ctl_reg_read		= 0x0206,
+	iavf_aqc_opc_rx_ctl_reg_write		= 0x0207,
+
+	iavf_aqc_opc_add_vsi			= 0x0210,
+	iavf_aqc_opc_update_vsi_parameters	= 0x0211,
+	iavf_aqc_opc_get_vsi_parameters		= 0x0212,
+
+	iavf_aqc_opc_add_pv			= 0x0220,
+	iavf_aqc_opc_update_pv_parameters	= 0x0221,
+	iavf_aqc_opc_get_pv_parameters		= 0x0222,
+
+	iavf_aqc_opc_add_veb			= 0x0230,
+	iavf_aqc_opc_update_veb_parameters	= 0x0231,
+	iavf_aqc_opc_get_veb_parameters		= 0x0232,
+
+	iavf_aqc_opc_delete_element		= 0x0243,
+
+	iavf_aqc_opc_add_macvlan		= 0x0250,
+	iavf_aqc_opc_remove_macvlan		= 0x0251,
+	iavf_aqc_opc_add_vlan			= 0x0252,
+	iavf_aqc_opc_remove_vlan		= 0x0253,
+	iavf_aqc_opc_set_vsi_promiscuous_modes	= 0x0254,
+	iavf_aqc_opc_add_tag			= 0x0255,
+	iavf_aqc_opc_remove_tag			= 0x0256,
+	iavf_aqc_opc_add_multicast_etag		= 0x0257,
+	iavf_aqc_opc_remove_multicast_etag	= 0x0258,
+	iavf_aqc_opc_update_tag			= 0x0259,
+	iavf_aqc_opc_add_control_packet_filter	= 0x025A,
+	iavf_aqc_opc_remove_control_packet_filter	= 0x025B,
+	iavf_aqc_opc_add_cloud_filters		= 0x025C,
+	iavf_aqc_opc_remove_cloud_filters	= 0x025D,
+	iavf_aqc_opc_clear_wol_switch_filters	= 0x025E,
+
+	iavf_aqc_opc_add_mirror_rule	= 0x0260,
+	iavf_aqc_opc_delete_mirror_rule	= 0x0261,
+
+	/* Dynamic Device Personalization */
+	iavf_aqc_opc_write_personalization_profile	= 0x0270,
+	iavf_aqc_opc_get_personalization_profile_list	= 0x0271,
+
+	/* DCB commands */
+	iavf_aqc_opc_dcb_ignore_pfc	= 0x0301,
+	iavf_aqc_opc_dcb_updated	= 0x0302,
+	iavf_aqc_opc_set_dcb_parameters = 0x0303,
+
+	/* TX scheduler */
+	iavf_aqc_opc_configure_vsi_bw_limit		= 0x0400,
+	iavf_aqc_opc_configure_vsi_ets_sla_bw_limit	= 0x0406,
+	iavf_aqc_opc_configure_vsi_tc_bw		= 0x0407,
+	iavf_aqc_opc_query_vsi_bw_config		= 0x0408,
+	iavf_aqc_opc_query_vsi_ets_sla_config		= 0x040A,
+	iavf_aqc_opc_configure_switching_comp_bw_limit	= 0x0410,
+
+	iavf_aqc_opc_enable_switching_comp_ets			= 0x0413,
+	iavf_aqc_opc_modify_switching_comp_ets			= 0x0414,
+	iavf_aqc_opc_disable_switching_comp_ets			= 0x0415,
+	iavf_aqc_opc_configure_switching_comp_ets_bw_limit	= 0x0416,
+	iavf_aqc_opc_configure_switching_comp_bw_config		= 0x0417,
+	iavf_aqc_opc_query_switching_comp_ets_config		= 0x0418,
+	iavf_aqc_opc_query_port_ets_config			= 0x0419,
+	iavf_aqc_opc_query_switching_comp_bw_config		= 0x041A,
+	iavf_aqc_opc_suspend_port_tx				= 0x041B,
+	iavf_aqc_opc_resume_port_tx				= 0x041C,
+	iavf_aqc_opc_configure_partition_bw			= 0x041D,
+	/* hmc */
+	iavf_aqc_opc_query_hmc_resource_profile	= 0x0500,
+	iavf_aqc_opc_set_hmc_resource_profile	= 0x0501,
+
+	/* phy commands*/
+	iavf_aqc_opc_get_phy_abilities		= 0x0600,
+	iavf_aqc_opc_set_phy_config		= 0x0601,
+	iavf_aqc_opc_set_mac_config		= 0x0603,
+	iavf_aqc_opc_set_link_restart_an	= 0x0605,
+	iavf_aqc_opc_get_link_status		= 0x0607,
+	iavf_aqc_opc_set_phy_int_mask		= 0x0613,
+	iavf_aqc_opc_get_local_advt_reg		= 0x0614,
+	iavf_aqc_opc_set_local_advt_reg		= 0x0615,
+	iavf_aqc_opc_get_partner_advt		= 0x0616,
+	iavf_aqc_opc_set_lb_modes		= 0x0618,
+	iavf_aqc_opc_get_phy_wol_caps		= 0x0621,
+	iavf_aqc_opc_set_phy_debug		= 0x0622,
+	iavf_aqc_opc_upload_ext_phy_fm		= 0x0625,
+	iavf_aqc_opc_run_phy_activity		= 0x0626,
+	iavf_aqc_opc_set_phy_register		= 0x0628,
+	iavf_aqc_opc_get_phy_register		= 0x0629,
+
+	/* NVM commands */
+	iavf_aqc_opc_nvm_read			= 0x0701,
+	iavf_aqc_opc_nvm_erase			= 0x0702,
+	iavf_aqc_opc_nvm_update			= 0x0703,
+	iavf_aqc_opc_nvm_config_read		= 0x0704,
+	iavf_aqc_opc_nvm_config_write		= 0x0705,
+	iavf_aqc_opc_oem_post_update		= 0x0720,
+	iavf_aqc_opc_thermal_sensor		= 0x0721,
+
+	/* virtualization commands */
+	iavf_aqc_opc_send_msg_to_pf		= 0x0801,
+	iavf_aqc_opc_send_msg_to_vf		= 0x0802,
+	iavf_aqc_opc_send_msg_to_peer		= 0x0803,
+
+	/* alternate structure */
+	iavf_aqc_opc_alternate_write		= 0x0900,
+	iavf_aqc_opc_alternate_write_indirect	= 0x0901,
+	iavf_aqc_opc_alternate_read		= 0x0902,
+	iavf_aqc_opc_alternate_read_indirect	= 0x0903,
+	iavf_aqc_opc_alternate_write_done	= 0x0904,
+	iavf_aqc_opc_alternate_set_mode		= 0x0905,
+	iavf_aqc_opc_alternate_clear_port	= 0x0906,
+
+	/* LLDP commands */
+	iavf_aqc_opc_lldp_get_mib	= 0x0A00,
+	iavf_aqc_opc_lldp_update_mib	= 0x0A01,
+	iavf_aqc_opc_lldp_add_tlv	= 0x0A02,
+	iavf_aqc_opc_lldp_update_tlv	= 0x0A03,
+	iavf_aqc_opc_lldp_delete_tlv	= 0x0A04,
+	iavf_aqc_opc_lldp_stop		= 0x0A05,
+	iavf_aqc_opc_lldp_start		= 0x0A06,
+
+	/* Tunnel commands */
+	iavf_aqc_opc_add_udp_tunnel	= 0x0B00,
+	iavf_aqc_opc_del_udp_tunnel	= 0x0B01,
+	iavf_aqc_opc_set_rss_key	= 0x0B02,
+	iavf_aqc_opc_set_rss_lut	= 0x0B03,
+	iavf_aqc_opc_get_rss_key	= 0x0B04,
+	iavf_aqc_opc_get_rss_lut	= 0x0B05,
+
+	/* Async Events */
+	iavf_aqc_opc_event_lan_overflow		= 0x1001,
+
+	/* OEM commands */
+	iavf_aqc_opc_oem_parameter_change	= 0xFE00,
+	iavf_aqc_opc_oem_device_status_change	= 0xFE01,
+	iavf_aqc_opc_oem_ocsd_initialize	= 0xFE02,
+	iavf_aqc_opc_oem_ocbb_initialize	= 0xFE03,
+
+	/* debug commands */
+	iavf_aqc_opc_debug_read_reg		= 0xFF03,
+	iavf_aqc_opc_debug_write_reg		= 0xFF04,
+	iavf_aqc_opc_debug_modify_reg		= 0xFF07,
+	iavf_aqc_opc_debug_dump_internals	= 0xFF08,
+};
+
+/* command structures and indirect data structures */
+
+/* Structure naming conventions:
+ * - no suffix for direct command descriptor structures
+ * - _data for indirect sent data
+ * - _resp for indirect return data (data which is both will use _data)
+ * - _completion for direct return data
+ * - _element_ for repeated elements (may also be _data or _resp)
+ *
+ * Command structures are expected to overlay the params.raw member of the basic
+ * descriptor, and as such cannot exceed 16 bytes in length.
+ */
+
+/* This macro is used to generate a compilation error if a structure
+ * is not exactly the correct length. It gives a divide by zero error if the
+ * structure is not of the correct size, otherwise it creates an enum that is
+ * never used.
+ */
+#define IAVF_CHECK_STRUCT_LEN(n, X) enum iavf_static_assert_enum_##X \
+	{ iavf_static_assert_##X = (n) / ((sizeof(struct X) == (n)) ? 1 : 0) }
+
+/* This macro is used extensively to ensure that command structures are 16
+ * bytes in length as they have to map to the raw array of that size.
+ */
+#define IAVF_CHECK_CMD_LENGTH(X)	IAVF_CHECK_STRUCT_LEN(16, X)
+
+/* Queue Shutdown (direct 0x0003) */
+struct iavf_aqc_queue_shutdown {
+	__le32	driver_unloading;
+#define IAVF_AQ_DRIVER_UNLOADING	0x1
+	u8	reserved[12];
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_queue_shutdown);
+
+struct iavf_aqc_vsi_properties_data {
+	/* first 96 byte are written by SW */
+	__le16	valid_sections;
+#define IAVF_AQ_VSI_PROP_SWITCH_VALID		0x0001
+#define IAVF_AQ_VSI_PROP_SECURITY_VALID		0x0002
+#define IAVF_AQ_VSI_PROP_VLAN_VALID		0x0004
+#define IAVF_AQ_VSI_PROP_CAS_PV_VALID		0x0008
+#define IAVF_AQ_VSI_PROP_INGRESS_UP_VALID	0x0010
+#define IAVF_AQ_VSI_PROP_EGRESS_UP_VALID	0x0020
+#define IAVF_AQ_VSI_PROP_QUEUE_MAP_VALID	0x0040
+#define IAVF_AQ_VSI_PROP_QUEUE_OPT_VALID	0x0080
+#define IAVF_AQ_VSI_PROP_OUTER_UP_VALID		0x0100
+#define IAVF_AQ_VSI_PROP_SCHED_VALID		0x0200
+	/* switch section */
+	__le16	switch_id; /* 12bit id combined with flags below */
+#define IAVF_AQ_VSI_SW_ID_SHIFT		0x0000
+#define IAVF_AQ_VSI_SW_ID_MASK		(0xFFF << IAVF_AQ_VSI_SW_ID_SHIFT)
+#define IAVF_AQ_VSI_SW_ID_FLAG_NOT_STAG	0x1000
+#define IAVF_AQ_VSI_SW_ID_FLAG_ALLOW_LB	0x2000
+#define IAVF_AQ_VSI_SW_ID_FLAG_LOCAL_LB	0x4000
+	u8	sw_reserved[2];
+	/* security section */
+	u8	sec_flags;
+#define IAVF_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD	0x01
+#define IAVF_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK	0x02
+#define IAVF_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK	0x04
+	u8	sec_reserved;
+	/* VLAN section */
+	__le16	pvid; /* VLANS include priority bits */
+	__le16	fcoe_pvid;
+	u8	port_vlan_flags;
+#define IAVF_AQ_VSI_PVLAN_MODE_SHIFT	0x00
+#define IAVF_AQ_VSI_PVLAN_MODE_MASK	(0x03 << \
+					 IAVF_AQ_VSI_PVLAN_MODE_SHIFT)
+#define IAVF_AQ_VSI_PVLAN_MODE_TAGGED	0x01
+#define IAVF_AQ_VSI_PVLAN_MODE_UNTAGGED	0x02
+#define IAVF_AQ_VSI_PVLAN_MODE_ALL	0x03
+#define IAVF_AQ_VSI_PVLAN_INSERT_PVID	0x04
+#define IAVF_AQ_VSI_PVLAN_EMOD_SHIFT	0x03
+#define IAVF_AQ_VSI_PVLAN_EMOD_MASK	(0x3 << \
+					 IAVF_AQ_VSI_PVLAN_EMOD_SHIFT)
+#define IAVF_AQ_VSI_PVLAN_EMOD_STR_BOTH	0x0
+#define IAVF_AQ_VSI_PVLAN_EMOD_STR_UP	0x08
+#define IAVF_AQ_VSI_PVLAN_EMOD_STR	0x10
+#define IAVF_AQ_VSI_PVLAN_EMOD_NOTHING	0x18
+	u8	pvlan_reserved[3];
+	/* ingress egress up sections */
+	__le32	ingress_table; /* bitmap, 3 bits per up */
+#define IAVF_AQ_VSI_UP_TABLE_UP0_SHIFT	0
+#define IAVF_AQ_VSI_UP_TABLE_UP0_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP0_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP1_SHIFT	3
+#define IAVF_AQ_VSI_UP_TABLE_UP1_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP1_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP2_SHIFT	6
+#define IAVF_AQ_VSI_UP_TABLE_UP2_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP2_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP3_SHIFT	9
+#define IAVF_AQ_VSI_UP_TABLE_UP3_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP3_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP4_SHIFT	12
+#define IAVF_AQ_VSI_UP_TABLE_UP4_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP4_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP5_SHIFT	15
+#define IAVF_AQ_VSI_UP_TABLE_UP5_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP5_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP6_SHIFT	18
+#define IAVF_AQ_VSI_UP_TABLE_UP6_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP6_SHIFT)
+#define IAVF_AQ_VSI_UP_TABLE_UP7_SHIFT	21
+#define IAVF_AQ_VSI_UP_TABLE_UP7_MASK	(0x7 << \
+					 IAVF_AQ_VSI_UP_TABLE_UP7_SHIFT)
+	__le32	egress_table;   /* same defines as for ingress table */
+	/* cascaded PV section */
+	__le16	cas_pv_tag;
+	u8	cas_pv_flags;
+#define IAVF_AQ_VSI_CAS_PV_TAGX_SHIFT		0x00
+#define IAVF_AQ_VSI_CAS_PV_TAGX_MASK		(0x03 << \
+						 IAVF_AQ_VSI_CAS_PV_TAGX_SHIFT)
+#define IAVF_AQ_VSI_CAS_PV_TAGX_LEAVE		0x00
+#define IAVF_AQ_VSI_CAS_PV_TAGX_REMOVE		0x01
+#define IAVF_AQ_VSI_CAS_PV_TAGX_COPY		0x02
+#define IAVF_AQ_VSI_CAS_PV_INSERT_TAG		0x10
+#define IAVF_AQ_VSI_CAS_PV_ETAG_PRUNE		0x20
+#define IAVF_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG	0x40
+	u8	cas_pv_reserved;
+	/* queue mapping section */
+	__le16	mapping_flags;
+#define IAVF_AQ_VSI_QUE_MAP_CONTIG	0x0
+#define IAVF_AQ_VSI_QUE_MAP_NONCONTIG	0x1
+	__le16	queue_mapping[16];
+#define IAVF_AQ_VSI_QUEUE_SHIFT		0x0
+#define IAVF_AQ_VSI_QUEUE_MASK		(0x7FF << IAVF_AQ_VSI_QUEUE_SHIFT)
+	__le16	tc_mapping[8];
+#define IAVF_AQ_VSI_TC_QUE_OFFSET_SHIFT	0
+#define IAVF_AQ_VSI_TC_QUE_OFFSET_MASK	(0x1FF << \
+					 IAVF_AQ_VSI_TC_QUE_OFFSET_SHIFT)
+#define IAVF_AQ_VSI_TC_QUE_NUMBER_SHIFT	9
+#define IAVF_AQ_VSI_TC_QUE_NUMBER_MASK	(0x7 << \
+					 IAVF_AQ_VSI_TC_QUE_NUMBER_SHIFT)
+	/* queueing option section */
+	u8	queueing_opt_flags;
+#define IAVF_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA	0x04
+#define IAVF_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA	0x08
+#define IAVF_AQ_VSI_QUE_OPT_TCP_ENA	0x10
+#define IAVF_AQ_VSI_QUE_OPT_FCOE_ENA	0x20
+#define IAVF_AQ_VSI_QUE_OPT_RSS_LUT_PF	0x00
+#define IAVF_AQ_VSI_QUE_OPT_RSS_LUT_VSI	0x40
+	u8	queueing_opt_reserved[3];
+	/* scheduler section */
+	u8	up_enable_bits;
+	u8	sched_reserved;
+	/* outer up section */
+	__le32	outer_up_table; /* same structure and defines as ingress tbl */
+	u8	cmd_reserved[8];
+	/* last 32 bytes are written by FW */
+	__le16	qs_handle[8];
+#define IAVF_AQ_VSI_QS_HANDLE_INVALID	0xFFFF
+	__le16	stat_counter_idx;
+	__le16	sched_id;
+	u8	resp_reserved[12];
+};
+
+IAVF_CHECK_STRUCT_LEN(128, iavf_aqc_vsi_properties_data);
+
+/* Get VEB Parameters (direct 0x0232)
+ * uses iavf_aqc_switch_seid for the descriptor
+ */
+struct iavf_aqc_get_veb_parameters_completion {
+	__le16	seid;
+	__le16	switch_id;
+	__le16	veb_flags; /* only the first/last flags from 0x0230 is valid */
+	__le16	statistic_index;
+	__le16	vebs_used;
+	__le16	vebs_free;
+	u8	reserved[4];
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_get_veb_parameters_completion);
+
+#define IAVF_LINK_SPEED_100MB_SHIFT	0x1
+#define IAVF_LINK_SPEED_1000MB_SHIFT	0x2
+#define IAVF_LINK_SPEED_10GB_SHIFT	0x3
+#define IAVF_LINK_SPEED_40GB_SHIFT	0x4
+#define IAVF_LINK_SPEED_20GB_SHIFT	0x5
+#define IAVF_LINK_SPEED_25GB_SHIFT	0x6
+
+enum iavf_aq_link_speed {
+	IAVF_LINK_SPEED_UNKNOWN	= 0,
+	IAVF_LINK_SPEED_100MB	= BIT(IAVF_LINK_SPEED_100MB_SHIFT),
+	IAVF_LINK_SPEED_1GB	= BIT(IAVF_LINK_SPEED_1000MB_SHIFT),
+	IAVF_LINK_SPEED_10GB	= BIT(IAVF_LINK_SPEED_10GB_SHIFT),
+	IAVF_LINK_SPEED_40GB	= BIT(IAVF_LINK_SPEED_40GB_SHIFT),
+	IAVF_LINK_SPEED_20GB	= BIT(IAVF_LINK_SPEED_20GB_SHIFT),
+	IAVF_LINK_SPEED_25GB	= BIT(IAVF_LINK_SPEED_25GB_SHIFT),
+};
+
+/* Send to PF command (indirect 0x0801) id is only used by PF
+ * Send to VF command (indirect 0x0802) id is only used by PF
+ * Send to Peer PF command (indirect 0x0803)
+ */
+struct iavf_aqc_pf_vf_message {
+	__le32	id;
+	u8	reserved[4];
+	__le32	addr_high;
+	__le32	addr_low;
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_pf_vf_message);
+
+struct iavf_aqc_get_set_rss_key {
+#define IAVF_AQC_SET_RSS_KEY_VSI_VALID		BIT(15)
+#define IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT	0
+#define IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK	(0x3FF << \
+					IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT)
+	__le16	vsi_id;
+	u8	reserved[6];
+	__le32	addr_high;
+	__le32	addr_low;
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_get_set_rss_key);
+
+struct iavf_aqc_get_set_rss_key_data {
+	u8 standard_rss_key[0x28];
+	u8 extended_hash_key[0xc];
+};
+
+IAVF_CHECK_STRUCT_LEN(0x34, iavf_aqc_get_set_rss_key_data);
+
+struct  iavf_aqc_get_set_rss_lut {
+#define IAVF_AQC_SET_RSS_LUT_VSI_VALID		BIT(15)
+#define IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT	0
+#define IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK	(0x3FF << \
+					IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT)
+	__le16	vsi_id;
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT	0
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \
+				BIT(IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT)
+
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI	0
+#define IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF	1
+	__le16	flags;
+	u8	reserved[4];
+	__le32	addr_high;
+	__le32	addr_low;
+};
+
+IAVF_CHECK_CMD_LENGTH(iavf_aqc_get_set_rss_lut);
+#endif /* _IAVF_ADMINQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_alloc.h b/drivers/net/ethernet/intel/iavf/iavf_alloc.h
index bf2753146f30..2711573c14ec 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_alloc.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_alloc.h
@@ -20,12 +20,15 @@ enum iavf_memory_type {
 };
 
 /* prototype for functions used for dynamic memory allocation */
-iavf_status iavf_allocate_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem,
-				  enum iavf_memory_type type,
-				  u64 size, u32 alignment);
-iavf_status iavf_free_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem);
-iavf_status iavf_allocate_virt_mem(struct iavf_hw *hw,
-				   struct iavf_virt_mem *mem, u32 size);
-iavf_status iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem);
+enum iavf_status iavf_allocate_dma_mem(struct iavf_hw *hw,
+				       struct iavf_dma_mem *mem,
+				       enum iavf_memory_type type,
+				       u64 size, u32 alignment);
+enum iavf_status iavf_free_dma_mem(struct iavf_hw *hw,
+				   struct iavf_dma_mem *mem);
+enum iavf_status iavf_allocate_virt_mem(struct iavf_hw *hw,
+					struct iavf_virt_mem *mem, u32 size);
+enum iavf_status iavf_free_virt_mem(struct iavf_hw *hw,
+				    struct iavf_virt_mem *mem);
 
 #endif /* _IAVF_ALLOC_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c
index aea45364fd1c..0c77e4171808 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_client.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_client.c
@@ -10,19 +10,19 @@
 
 static
 const char iavf_client_interface_version_str[] = IAVF_CLIENT_VERSION_STR;
-static struct i40e_client *vf_registered_client;
-static LIST_HEAD(i40e_devices);
+static struct iavf_client *vf_registered_client;
+static LIST_HEAD(iavf_devices);
 static DEFINE_MUTEX(iavf_device_mutex);
 
-static u32 iavf_client_virtchnl_send(struct i40e_info *ldev,
-				     struct i40e_client *client,
+static u32 iavf_client_virtchnl_send(struct iavf_info *ldev,
+				     struct iavf_client *client,
 				     u8 *msg, u16 len);
 
-static int iavf_client_setup_qvlist(struct i40e_info *ldev,
-				    struct i40e_client *client,
-				    struct i40e_qvlist_info *qvlist_info);
+static int iavf_client_setup_qvlist(struct iavf_info *ldev,
+				    struct iavf_client *client,
+				    struct iavf_qvlist_info *qvlist_info);
 
-static struct i40e_ops iavf_lan_ops = {
+static struct iavf_ops iavf_lan_ops = {
 	.virtchnl_send = iavf_client_virtchnl_send,
 	.setup_qvlist = iavf_client_setup_qvlist,
 };
@@ -33,11 +33,11 @@ static struct i40e_ops iavf_lan_ops = {
  * @params: client param struct
  **/
 static
-void iavf_client_get_params(struct iavf_vsi *vsi, struct i40e_params *params)
+void iavf_client_get_params(struct iavf_vsi *vsi, struct iavf_params *params)
 {
 	int i;
 
-	memset(params, 0, sizeof(struct i40e_params));
+	memset(params, 0, sizeof(struct iavf_params));
 	params->mtu = vsi->netdev->mtu;
 	params->link_up = vsi->back->link_up;
 
@@ -57,7 +57,7 @@ void iavf_client_get_params(struct iavf_vsi *vsi, struct i40e_params *params)
  **/
 void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len)
 {
-	struct i40e_client_instance *cinst;
+	struct iavf_client_instance *cinst;
 
 	if (!vsi)
 		return;
@@ -81,8 +81,8 @@ void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len)
  **/
 void iavf_notify_client_l2_params(struct iavf_vsi *vsi)
 {
-	struct i40e_client_instance *cinst;
-	struct i40e_params params;
+	struct iavf_client_instance *cinst;
+	struct iavf_params params;
 
 	if (!vsi)
 		return;
@@ -110,7 +110,7 @@ void iavf_notify_client_l2_params(struct iavf_vsi *vsi)
 void iavf_notify_client_open(struct iavf_vsi *vsi)
 {
 	struct iavf_adapter *adapter = vsi->back;
-	struct i40e_client_instance *cinst = adapter->cinst;
+	struct iavf_client_instance *cinst = adapter->cinst;
 	int ret;
 
 	if (!cinst || !cinst->client || !cinst->client->ops ||
@@ -119,10 +119,10 @@ void iavf_notify_client_open(struct iavf_vsi *vsi)
 			"Cannot locate client instance open function\n");
 		return;
 	}
-	if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) {
+	if (!(test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state))) {
 		ret = cinst->client->ops->open(&cinst->lan_info, cinst->client);
 		if (!ret)
-			set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+			set_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state);
 	}
 }
 
@@ -132,17 +132,17 @@ void iavf_notify_client_open(struct iavf_vsi *vsi)
  *
  * Return 0 on success or < 0 on error
  **/
-static int iavf_client_release_qvlist(struct i40e_info *ldev)
+static int iavf_client_release_qvlist(struct iavf_info *ldev)
 {
 	struct iavf_adapter *adapter = ldev->vf;
-	iavf_status err;
+	enum iavf_status err;
 
 	if (adapter->aq_required)
 		return -EAGAIN;
 
 	err = iavf_aq_send_msg_to_pf(&adapter->hw,
 				     VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
-				     I40E_SUCCESS, NULL, 0, NULL);
+				     IAVF_SUCCESS, NULL, 0, NULL);
 
 	if (err)
 		dev_err(&adapter->pdev->dev,
@@ -162,7 +162,7 @@ static int iavf_client_release_qvlist(struct i40e_info *ldev)
 void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset)
 {
 	struct iavf_adapter *adapter = vsi->back;
-	struct i40e_client_instance *cinst = adapter->cinst;
+	struct iavf_client_instance *cinst = adapter->cinst;
 
 	if (!cinst || !cinst->client || !cinst->client->ops ||
 	    !cinst->client->ops->close) {
@@ -172,7 +172,7 @@ void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset)
 	}
 	cinst->client->ops->close(&cinst->lan_info, cinst->client, reset);
 	iavf_client_release_qvlist(&cinst->lan_info);
-	clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+	clear_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state);
 }
 
 /**
@@ -181,13 +181,13 @@ void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset)
  *
  * Returns cinst ptr on success, NULL on failure
  **/
-static struct i40e_client_instance *
+static struct iavf_client_instance *
 iavf_client_add_instance(struct iavf_adapter *adapter)
 {
-	struct i40e_client_instance *cinst = NULL;
+	struct iavf_client_instance *cinst = NULL;
 	struct iavf_vsi *vsi = &adapter->vsi;
 	struct netdev_hw_addr *mac = NULL;
-	struct i40e_params params;
+	struct iavf_params params;
 
 	if (!vf_registered_client)
 		goto out;
@@ -205,7 +205,7 @@ iavf_client_add_instance(struct iavf_adapter *adapter)
 	cinst->lan_info.netdev = vsi->netdev;
 	cinst->lan_info.pcidev = adapter->pdev;
 	cinst->lan_info.fid = 0;
-	cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF;
+	cinst->lan_info.ftype = IAVF_CLIENT_FTYPE_VF;
 	cinst->lan_info.hw_addr = adapter->hw.hw_addr;
 	cinst->lan_info.ops = &iavf_lan_ops;
 	cinst->lan_info.version.major = IAVF_CLIENT_VERSION_MAJOR;
@@ -213,7 +213,7 @@ iavf_client_add_instance(struct iavf_adapter *adapter)
 	cinst->lan_info.version.build = IAVF_CLIENT_VERSION_BUILD;
 	iavf_client_get_params(vsi, &params);
 	cinst->lan_info.params = params;
-	set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state);
+	set_bit(__IAVF_CLIENT_INSTANCE_NONE, &cinst->state);
 
 	cinst->lan_info.msix_count = adapter->num_iwarp_msix;
 	cinst->lan_info.msix_entries =
@@ -250,8 +250,8 @@ void iavf_client_del_instance(struct iavf_adapter *adapter)
  **/
 void iavf_client_subtask(struct iavf_adapter *adapter)
 {
-	struct i40e_client *client = vf_registered_client;
-	struct i40e_client_instance *cinst;
+	struct iavf_client *client = vf_registered_client;
+	struct iavf_client_instance *cinst;
 	int ret = 0;
 
 	if (adapter->state < __IAVF_DOWN)
@@ -269,13 +269,13 @@ void iavf_client_subtask(struct iavf_adapter *adapter)
 	dev_info(&adapter->pdev->dev, "Added instance of Client %s\n",
 		 client->name);
 
-	if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+	if (!test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state)) {
 		/* Send an Open request to the client */
 
 		if (client->ops && client->ops->open)
 			ret = client->ops->open(&cinst->lan_info, client);
 		if (!ret)
-			set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+			set_bit(__IAVF_CLIENT_INSTANCE_OPENED,
 				&cinst->state);
 		else
 			/* remove client instance */
@@ -291,11 +291,11 @@ void iavf_client_subtask(struct iavf_adapter *adapter)
  **/
 int iavf_lan_add_device(struct iavf_adapter *adapter)
 {
-	struct i40e_device *ldev;
+	struct iavf_device *ldev;
 	int ret = 0;
 
 	mutex_lock(&iavf_device_mutex);
-	list_for_each_entry(ldev, &i40e_devices, list) {
+	list_for_each_entry(ldev, &iavf_devices, list) {
 		if (ldev->vf == adapter) {
 			ret = -EEXIST;
 			goto out;
@@ -308,7 +308,7 @@ int iavf_lan_add_device(struct iavf_adapter *adapter)
 	}
 	ldev->vf = adapter;
 	INIT_LIST_HEAD(&ldev->list);
-	list_add(&ldev->list, &i40e_devices);
+	list_add(&ldev->list, &iavf_devices);
 	dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
 		 adapter->hw.bus.bus_id, adapter->hw.bus.device,
 		 adapter->hw.bus.func);
@@ -331,11 +331,11 @@ out:
  **/
 int iavf_lan_del_device(struct iavf_adapter *adapter)
 {
-	struct i40e_device *ldev, *tmp;
+	struct iavf_device *ldev, *tmp;
 	int ret = -ENODEV;
 
 	mutex_lock(&iavf_device_mutex);
-	list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) {
+	list_for_each_entry_safe(ldev, tmp, &iavf_devices, list) {
 		if (ldev->vf == adapter) {
 			dev_info(&adapter->pdev->dev,
 				 "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n",
@@ -357,24 +357,24 @@ int iavf_lan_del_device(struct iavf_adapter *adapter)
  * @client: pointer to the registered client
  *
  **/
-static void iavf_client_release(struct i40e_client *client)
+static void iavf_client_release(struct iavf_client *client)
 {
-	struct i40e_client_instance *cinst;
-	struct i40e_device *ldev;
+	struct iavf_client_instance *cinst;
+	struct iavf_device *ldev;
 	struct iavf_adapter *adapter;
 
 	mutex_lock(&iavf_device_mutex);
-	list_for_each_entry(ldev, &i40e_devices, list) {
+	list_for_each_entry(ldev, &iavf_devices, list) {
 		adapter = ldev->vf;
 		cinst = adapter->cinst;
 		if (!cinst)
 			continue;
-		if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) {
+		if (test_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state)) {
 			if (client->ops && client->ops->close)
 				client->ops->close(&cinst->lan_info, client,
 						   false);
 			iavf_client_release_qvlist(&cinst->lan_info);
-			clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state);
+			clear_bit(__IAVF_CLIENT_INSTANCE_OPENED, &cinst->state);
 
 			dev_warn(&adapter->pdev->dev,
 				 "Client %s instance closed\n", client->name);
@@ -392,13 +392,13 @@ static void iavf_client_release(struct i40e_client *client)
  * @client: pointer to the registered client
  *
  **/
-static void iavf_client_prepare(struct i40e_client *client)
+static void iavf_client_prepare(struct iavf_client *client)
 {
-	struct i40e_device *ldev;
+	struct iavf_device *ldev;
 	struct iavf_adapter *adapter;
 
 	mutex_lock(&iavf_device_mutex);
-	list_for_each_entry(ldev, &i40e_devices, list) {
+	list_for_each_entry(ldev, &iavf_devices, list) {
 		adapter = ldev->vf;
 		/* Signal the watchdog to service the client */
 		adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED;
@@ -415,18 +415,18 @@ static void iavf_client_prepare(struct i40e_client *client)
  *
  * Return 0 on success or < 0 on error
  **/
-static u32 iavf_client_virtchnl_send(struct i40e_info *ldev,
-				     struct i40e_client *client,
+static u32 iavf_client_virtchnl_send(struct iavf_info *ldev,
+				     struct iavf_client *client,
 				     u8 *msg, u16 len)
 {
 	struct iavf_adapter *adapter = ldev->vf;
-	iavf_status err;
+	enum iavf_status err;
 
 	if (adapter->aq_required)
 		return -EAGAIN;
 
 	err = iavf_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP,
-				     I40E_SUCCESS, msg, len, NULL);
+				     IAVF_SUCCESS, msg, len, NULL);
 	if (err)
 		dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n",
 			err, adapter->hw.aq.asq_last_status);
@@ -442,16 +442,16 @@ static u32 iavf_client_virtchnl_send(struct i40e_info *ldev,
  *
  * Return 0 on success or < 0 on error
  **/
-static int iavf_client_setup_qvlist(struct i40e_info *ldev,
-				    struct i40e_client *client,
-				    struct i40e_qvlist_info *qvlist_info)
+static int iavf_client_setup_qvlist(struct iavf_info *ldev,
+				    struct iavf_client *client,
+				    struct iavf_qvlist_info *qvlist_info)
 {
 	struct virtchnl_iwarp_qvlist_info *v_qvlist_info;
 	struct iavf_adapter *adapter = ldev->vf;
-	struct i40e_qv_info *qv_info;
-	iavf_status err;
+	struct iavf_qv_info *qv_info;
+	enum iavf_status err;
 	u32 v_idx, i;
-	u32 msg_size;
+	size_t msg_size;
 
 	if (adapter->aq_required)
 		return -EAGAIN;
@@ -469,13 +469,12 @@ static int iavf_client_setup_qvlist(struct i40e_info *ldev,
 	}
 
 	v_qvlist_info = (struct virtchnl_iwarp_qvlist_info *)qvlist_info;
-	msg_size = sizeof(struct virtchnl_iwarp_qvlist_info) +
-			(sizeof(struct virtchnl_iwarp_qv_info) *
-			(v_qvlist_info->num_vectors - 1));
+	msg_size = struct_size(v_qvlist_info, qv_info,
+			       v_qvlist_info->num_vectors - 1);
 
 	adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP);
 	err = iavf_aq_send_msg_to_pf(&adapter->hw,
-				VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, I40E_SUCCESS,
+				VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, IAVF_SUCCESS,
 				(u8 *)v_qvlist_info, msg_size, NULL);
 
 	if (err) {
@@ -499,12 +498,12 @@ out:
 }
 
 /**
- * iavf_register_client - Register a i40e client driver with the L2 driver
- * @client: pointer to the i40e_client struct
+ * iavf_register_client - Register a iavf client driver with the L2 driver
+ * @client: pointer to the iavf_client struct
  *
  * Returns 0 on success or non-0 on error
  **/
-int iavf_register_client(struct i40e_client *client)
+int iavf_register_client(struct iavf_client *client)
 {
 	int ret = 0;
 
@@ -550,12 +549,12 @@ out:
 EXPORT_SYMBOL(iavf_register_client);
 
 /**
- * iavf_unregister_client - Unregister a i40e client driver with the L2 driver
- * @client: pointer to the i40e_client struct
+ * iavf_unregister_client - Unregister a iavf client driver with the L2 driver
+ * @client: pointer to the iavf_client struct
  *
  * Returns 0 on success or non-0 on error
  **/
-int iavf_unregister_client(struct i40e_client *client)
+int iavf_unregister_client(struct iavf_client *client)
 {
 	int ret = 0;
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h
index e216fc9dfd81..9a7cf39ea75a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_client.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_client.h
@@ -17,86 +17,86 @@
 	__stringify(IAVF_CLIENT_VERSION_MINOR) "." \
 	__stringify(IAVF_CLIENT_VERSION_BUILD)
 
-struct i40e_client_version {
+struct iavf_client_version {
 	u8 major;
 	u8 minor;
 	u8 build;
 	u8 rsvd;
 };
 
-enum i40e_client_state {
-	__I40E_CLIENT_NULL,
-	__I40E_CLIENT_REGISTERED
+enum iavf_client_state {
+	__IAVF_CLIENT_NULL,
+	__IAVF_CLIENT_REGISTERED
 };
 
-enum i40e_client_instance_state {
-	__I40E_CLIENT_INSTANCE_NONE,
-	__I40E_CLIENT_INSTANCE_OPENED,
+enum iavf_client_instance_state {
+	__IAVF_CLIENT_INSTANCE_NONE,
+	__IAVF_CLIENT_INSTANCE_OPENED,
 };
 
-struct i40e_ops;
-struct i40e_client;
+struct iavf_ops;
+struct iavf_client;
 
 /* HW does not define a type value for AEQ; only for RX/TX and CEQ.
  * In order for us to keep the interface simple, SW will define a
  * unique type value for AEQ.
  */
-#define I40E_QUEUE_TYPE_PE_AEQ  0x80
-#define I40E_QUEUE_INVALID_IDX	0xFFFF
+#define IAVF_QUEUE_TYPE_PE_AEQ	0x80
+#define IAVF_QUEUE_INVALID_IDX	0xFFFF
 
-struct i40e_qv_info {
+struct iavf_qv_info {
 	u32 v_idx; /* msix_vector */
 	u16 ceq_idx;
 	u16 aeq_idx;
 	u8 itr_idx;
 };
 
-struct i40e_qvlist_info {
+struct iavf_qvlist_info {
 	u32 num_vectors;
-	struct i40e_qv_info qv_info[1];
+	struct iavf_qv_info qv_info[1];
 };
 
-#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
+#define IAVF_CLIENT_MSIX_ALL 0xFFFFFFFF
 
 /* set of LAN parameters useful for clients managed by LAN */
 
 /* Struct to hold per priority info */
-struct i40e_prio_qos_params {
+struct iavf_prio_qos_params {
 	u16 qs_handle; /* qs handle for prio */
 	u8 tc; /* TC mapped to prio */
 	u8 reserved;
 };
 
-#define I40E_CLIENT_MAX_USER_PRIORITY        8
+#define IAVF_CLIENT_MAX_USER_PRIORITY	8
 /* Struct to hold Client QoS */
-struct i40e_qos_params {
-	struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
+struct iavf_qos_params {
+	struct iavf_prio_qos_params prio_qos[IAVF_CLIENT_MAX_USER_PRIORITY];
 };
 
-struct i40e_params {
-	struct i40e_qos_params qos;
+struct iavf_params {
+	struct iavf_qos_params qos;
 	u16 mtu;
 	u16 link_up; /* boolean */
 };
 
 /* Structure to hold LAN device info for a client device */
-struct i40e_info {
-	struct i40e_client_version version;
+struct iavf_info {
+	struct iavf_client_version version;
 	u8 lanmac[6];
 	struct net_device *netdev;
 	struct pci_dev *pcidev;
 	u8 __iomem *hw_addr;
 	u8 fid;	/* function id, PF id or VF id */
-#define I40E_CLIENT_FTYPE_PF 0
-#define I40E_CLIENT_FTYPE_VF 1
+#define IAVF_CLIENT_FTYPE_PF 0
+#define IAVF_CLIENT_FTYPE_VF 1
 	u8 ftype; /* function type, PF or VF */
 	void *vf; /* cast to iavf_adapter */
 
 	/* All L2 params that could change during the life span of the device
 	 * and needs to be communicated to the client when they change
 	 */
-	struct i40e_params params;
-	struct i40e_ops *ops;
+	struct iavf_params params;
+	struct iavf_ops *ops;
 
 	u16 msix_count;	 /* number of msix vectors*/
 	/* Array down below will be dynamically allocated based on msix_count */
@@ -104,66 +104,66 @@ struct i40e_info {
 	u16 itr_index; /* Which ITR index the PE driver is suppose to use */
 };
 
-struct i40e_ops {
+struct iavf_ops {
 	/* setup_q_vector_list enables queues with a particular vector */
-	int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
-			    struct i40e_qvlist_info *qv_info);
+	int (*setup_qvlist)(struct iavf_info *ldev, struct iavf_client *client,
+			    struct iavf_qvlist_info *qv_info);
 
-	u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
+	u32 (*virtchnl_send)(struct iavf_info *ldev, struct iavf_client *client,
 			     u8 *msg, u16 len);
 
 	/* If the PE Engine is unresponsive, RDMA driver can request a reset.*/
-	void (*request_reset)(struct i40e_info *ldev,
-			      struct i40e_client *client);
+	void (*request_reset)(struct iavf_info *ldev,
+			      struct iavf_client *client);
 };
 
-struct i40e_client_ops {
+struct iavf_client_ops {
 	/* Should be called from register_client() or whenever the driver is
 	 * ready to create a specific client instance.
 	 */
-	int (*open)(struct i40e_info *ldev, struct i40e_client *client);
+	int (*open)(struct iavf_info *ldev, struct iavf_client *client);
 
 	/* Should be closed when netdev is unavailable or when unregister
 	 * call comes in. If the close happens due to a reset, set the reset
 	 * bit to true.
 	 */
-	void (*close)(struct i40e_info *ldev, struct i40e_client *client,
+	void (*close)(struct iavf_info *ldev, struct iavf_client *client,
 		      bool reset);
 
 	/* called when some l2 managed parameters changes - mss */
-	void (*l2_param_change)(struct i40e_info *ldev,
-				struct i40e_client *client,
-				struct i40e_params *params);
+	void (*l2_param_change)(struct iavf_info *ldev,
+				struct iavf_client *client,
+				struct iavf_params *params);
 
 	/* called when a message is received from the PF */
-	int (*virtchnl_receive)(struct i40e_info *ldev,
-				struct i40e_client *client,
+	int (*virtchnl_receive)(struct iavf_info *ldev,
+				struct iavf_client *client,
 				u8 *msg, u16 len);
 };
 
 /* Client device */
-struct i40e_client_instance {
+struct iavf_client_instance {
 	struct list_head list;
-	struct i40e_info lan_info;
-	struct i40e_client *client;
+	struct iavf_info lan_info;
+	struct iavf_client *client;
 	unsigned long  state;
 };
 
-struct i40e_client {
+struct iavf_client {
 	struct list_head list;		/* list of registered clients */
 	char name[IAVF_CLIENT_STR_LENGTH];
-	struct i40e_client_version version;
+	struct iavf_client_version version;
 	unsigned long state;		/* client state */
 	atomic_t ref_cnt;  /* Count of all the client devices of this kind */
 	u32 flags;
-#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
-#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
+#define IAVF_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
+#define IAVF_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
 	u8 type;
-#define I40E_CLIENT_IWARP 0
-	struct i40e_client_ops *ops;	/* client ops provided by the client */
+#define IAVF_CLIENT_IWARP 0
+	struct iavf_client_ops *ops;	/* client ops provided by the client */
 };
 
 /* used by clients */
-int iavf_register_client(struct i40e_client *client);
-int iavf_unregister_client(struct i40e_client *client);
+int iavf_register_client(struct iavf_client *client);
+int iavf_unregister_client(struct iavf_client *client);
 #endif /* _IAVF_CLIENT_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c
index 768369c89e77..8547fc8fdfd6 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_common.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_common.c
@@ -2,7 +2,7 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include "iavf_type.h"
-#include "i40e_adminq.h"
+#include "iavf_adminq.h"
 #include "iavf_prototype.h"
 #include <linux/avf/virtchnl.h>
 
@@ -13,9 +13,9 @@
  * This function sets the mac type of the adapter based on the
  * vendor ID and device ID stored in the hw structure.
  **/
-iavf_status iavf_set_mac_type(struct iavf_hw *hw)
+enum iavf_status iavf_set_mac_type(struct iavf_hw *hw)
 {
-	iavf_status status = 0;
+	enum iavf_status status = 0;
 
 	if (hw->vendor_id == PCI_VENDOR_ID_INTEL) {
 		switch (hw->device_id) {
@@ -32,7 +32,7 @@ iavf_status iavf_set_mac_type(struct iavf_hw *hw)
 			break;
 		}
 	} else {
-		status = I40E_ERR_DEVICE_NOT_SUPPORTED;
+		status = IAVF_ERR_DEVICE_NOT_SUPPORTED;
 	}
 
 	hw_dbg(hw, "found mac: %d, returns: %d\n", hw->mac.type, status);
@@ -44,55 +44,55 @@ iavf_status iavf_set_mac_type(struct iavf_hw *hw)
  * @hw: pointer to the HW structure
  * @aq_err: the AQ error code to convert
  **/
-const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err)
+const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err)
 {
 	switch (aq_err) {
-	case I40E_AQ_RC_OK:
+	case IAVF_AQ_RC_OK:
 		return "OK";
-	case I40E_AQ_RC_EPERM:
-		return "I40E_AQ_RC_EPERM";
-	case I40E_AQ_RC_ENOENT:
-		return "I40E_AQ_RC_ENOENT";
-	case I40E_AQ_RC_ESRCH:
-		return "I40E_AQ_RC_ESRCH";
-	case I40E_AQ_RC_EINTR:
-		return "I40E_AQ_RC_EINTR";
-	case I40E_AQ_RC_EIO:
-		return "I40E_AQ_RC_EIO";
-	case I40E_AQ_RC_ENXIO:
-		return "I40E_AQ_RC_ENXIO";
-	case I40E_AQ_RC_E2BIG:
-		return "I40E_AQ_RC_E2BIG";
-	case I40E_AQ_RC_EAGAIN:
-		return "I40E_AQ_RC_EAGAIN";
-	case I40E_AQ_RC_ENOMEM:
-		return "I40E_AQ_RC_ENOMEM";
-	case I40E_AQ_RC_EACCES:
-		return "I40E_AQ_RC_EACCES";
-	case I40E_AQ_RC_EFAULT:
-		return "I40E_AQ_RC_EFAULT";
-	case I40E_AQ_RC_EBUSY:
-		return "I40E_AQ_RC_EBUSY";
-	case I40E_AQ_RC_EEXIST:
-		return "I40E_AQ_RC_EEXIST";
-	case I40E_AQ_RC_EINVAL:
-		return "I40E_AQ_RC_EINVAL";
-	case I40E_AQ_RC_ENOTTY:
-		return "I40E_AQ_RC_ENOTTY";
-	case I40E_AQ_RC_ENOSPC:
-		return "I40E_AQ_RC_ENOSPC";
-	case I40E_AQ_RC_ENOSYS:
-		return "I40E_AQ_RC_ENOSYS";
-	case I40E_AQ_RC_ERANGE:
-		return "I40E_AQ_RC_ERANGE";
-	case I40E_AQ_RC_EFLUSHED:
-		return "I40E_AQ_RC_EFLUSHED";
-	case I40E_AQ_RC_BAD_ADDR:
-		return "I40E_AQ_RC_BAD_ADDR";
-	case I40E_AQ_RC_EMODE:
-		return "I40E_AQ_RC_EMODE";
-	case I40E_AQ_RC_EFBIG:
-		return "I40E_AQ_RC_EFBIG";
+	case IAVF_AQ_RC_EPERM:
+		return "IAVF_AQ_RC_EPERM";
+	case IAVF_AQ_RC_ENOENT:
+		return "IAVF_AQ_RC_ENOENT";
+	case IAVF_AQ_RC_ESRCH:
+		return "IAVF_AQ_RC_ESRCH";
+	case IAVF_AQ_RC_EINTR:
+		return "IAVF_AQ_RC_EINTR";
+	case IAVF_AQ_RC_EIO:
+		return "IAVF_AQ_RC_EIO";
+	case IAVF_AQ_RC_ENXIO:
+		return "IAVF_AQ_RC_ENXIO";
+	case IAVF_AQ_RC_E2BIG:
+		return "IAVF_AQ_RC_E2BIG";
+	case IAVF_AQ_RC_EAGAIN:
+		return "IAVF_AQ_RC_EAGAIN";
+	case IAVF_AQ_RC_ENOMEM:
+		return "IAVF_AQ_RC_ENOMEM";
+	case IAVF_AQ_RC_EACCES:
+		return "IAVF_AQ_RC_EACCES";
+	case IAVF_AQ_RC_EFAULT:
+		return "IAVF_AQ_RC_EFAULT";
+	case IAVF_AQ_RC_EBUSY:
+		return "IAVF_AQ_RC_EBUSY";
+	case IAVF_AQ_RC_EEXIST:
+		return "IAVF_AQ_RC_EEXIST";
+	case IAVF_AQ_RC_EINVAL:
+		return "IAVF_AQ_RC_EINVAL";
+	case IAVF_AQ_RC_ENOTTY:
+		return "IAVF_AQ_RC_ENOTTY";
+	case IAVF_AQ_RC_ENOSPC:
+		return "IAVF_AQ_RC_ENOSPC";
+	case IAVF_AQ_RC_ENOSYS:
+		return "IAVF_AQ_RC_ENOSYS";
+	case IAVF_AQ_RC_ERANGE:
+		return "IAVF_AQ_RC_ERANGE";
+	case IAVF_AQ_RC_EFLUSHED:
+		return "IAVF_AQ_RC_EFLUSHED";
+	case IAVF_AQ_RC_BAD_ADDR:
+		return "IAVF_AQ_RC_BAD_ADDR";
+	case IAVF_AQ_RC_EMODE:
+		return "IAVF_AQ_RC_EMODE";
+	case IAVF_AQ_RC_EFBIG:
+		return "IAVF_AQ_RC_EFBIG";
 	}
 
 	snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err);
@@ -104,143 +104,143 @@ const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err)
  * @hw: pointer to the HW structure
  * @stat_err: the status error code to convert
  **/
-const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err)
+const char *iavf_stat_str(struct iavf_hw *hw, enum iavf_status stat_err)
 {
 	switch (stat_err) {
 	case 0:
 		return "OK";
-	case I40E_ERR_NVM:
-		return "I40E_ERR_NVM";
-	case I40E_ERR_NVM_CHECKSUM:
-		return "I40E_ERR_NVM_CHECKSUM";
-	case I40E_ERR_PHY:
-		return "I40E_ERR_PHY";
-	case I40E_ERR_CONFIG:
-		return "I40E_ERR_CONFIG";
-	case I40E_ERR_PARAM:
-		return "I40E_ERR_PARAM";
-	case I40E_ERR_MAC_TYPE:
-		return "I40E_ERR_MAC_TYPE";
-	case I40E_ERR_UNKNOWN_PHY:
-		return "I40E_ERR_UNKNOWN_PHY";
-	case I40E_ERR_LINK_SETUP:
-		return "I40E_ERR_LINK_SETUP";
-	case I40E_ERR_ADAPTER_STOPPED:
-		return "I40E_ERR_ADAPTER_STOPPED";
-	case I40E_ERR_INVALID_MAC_ADDR:
-		return "I40E_ERR_INVALID_MAC_ADDR";
-	case I40E_ERR_DEVICE_NOT_SUPPORTED:
-		return "I40E_ERR_DEVICE_NOT_SUPPORTED";
-	case I40E_ERR_MASTER_REQUESTS_PENDING:
-		return "I40E_ERR_MASTER_REQUESTS_PENDING";
-	case I40E_ERR_INVALID_LINK_SETTINGS:
-		return "I40E_ERR_INVALID_LINK_SETTINGS";
-	case I40E_ERR_AUTONEG_NOT_COMPLETE:
-		return "I40E_ERR_AUTONEG_NOT_COMPLETE";
-	case I40E_ERR_RESET_FAILED:
-		return "I40E_ERR_RESET_FAILED";
-	case I40E_ERR_SWFW_SYNC:
-		return "I40E_ERR_SWFW_SYNC";
-	case I40E_ERR_NO_AVAILABLE_VSI:
-		return "I40E_ERR_NO_AVAILABLE_VSI";
-	case I40E_ERR_NO_MEMORY:
-		return "I40E_ERR_NO_MEMORY";
-	case I40E_ERR_BAD_PTR:
-		return "I40E_ERR_BAD_PTR";
-	case I40E_ERR_RING_FULL:
-		return "I40E_ERR_RING_FULL";
-	case I40E_ERR_INVALID_PD_ID:
-		return "I40E_ERR_INVALID_PD_ID";
-	case I40E_ERR_INVALID_QP_ID:
-		return "I40E_ERR_INVALID_QP_ID";
-	case I40E_ERR_INVALID_CQ_ID:
-		return "I40E_ERR_INVALID_CQ_ID";
-	case I40E_ERR_INVALID_CEQ_ID:
-		return "I40E_ERR_INVALID_CEQ_ID";
-	case I40E_ERR_INVALID_AEQ_ID:
-		return "I40E_ERR_INVALID_AEQ_ID";
-	case I40E_ERR_INVALID_SIZE:
-		return "I40E_ERR_INVALID_SIZE";
-	case I40E_ERR_INVALID_ARP_INDEX:
-		return "I40E_ERR_INVALID_ARP_INDEX";
-	case I40E_ERR_INVALID_FPM_FUNC_ID:
-		return "I40E_ERR_INVALID_FPM_FUNC_ID";
-	case I40E_ERR_QP_INVALID_MSG_SIZE:
-		return "I40E_ERR_QP_INVALID_MSG_SIZE";
-	case I40E_ERR_QP_TOOMANY_WRS_POSTED:
-		return "I40E_ERR_QP_TOOMANY_WRS_POSTED";
-	case I40E_ERR_INVALID_FRAG_COUNT:
-		return "I40E_ERR_INVALID_FRAG_COUNT";
-	case I40E_ERR_QUEUE_EMPTY:
-		return "I40E_ERR_QUEUE_EMPTY";
-	case I40E_ERR_INVALID_ALIGNMENT:
-		return "I40E_ERR_INVALID_ALIGNMENT";
-	case I40E_ERR_FLUSHED_QUEUE:
-		return "I40E_ERR_FLUSHED_QUEUE";
-	case I40E_ERR_INVALID_PUSH_PAGE_INDEX:
-		return "I40E_ERR_INVALID_PUSH_PAGE_INDEX";
-	case I40E_ERR_INVALID_IMM_DATA_SIZE:
-		return "I40E_ERR_INVALID_IMM_DATA_SIZE";
-	case I40E_ERR_TIMEOUT:
-		return "I40E_ERR_TIMEOUT";
-	case I40E_ERR_OPCODE_MISMATCH:
-		return "I40E_ERR_OPCODE_MISMATCH";
-	case I40E_ERR_CQP_COMPL_ERROR:
-		return "I40E_ERR_CQP_COMPL_ERROR";
-	case I40E_ERR_INVALID_VF_ID:
-		return "I40E_ERR_INVALID_VF_ID";
-	case I40E_ERR_INVALID_HMCFN_ID:
-		return "I40E_ERR_INVALID_HMCFN_ID";
-	case I40E_ERR_BACKING_PAGE_ERROR:
-		return "I40E_ERR_BACKING_PAGE_ERROR";
-	case I40E_ERR_NO_PBLCHUNKS_AVAILABLE:
-		return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE";
-	case I40E_ERR_INVALID_PBLE_INDEX:
-		return "I40E_ERR_INVALID_PBLE_INDEX";
-	case I40E_ERR_INVALID_SD_INDEX:
-		return "I40E_ERR_INVALID_SD_INDEX";
-	case I40E_ERR_INVALID_PAGE_DESC_INDEX:
-		return "I40E_ERR_INVALID_PAGE_DESC_INDEX";
-	case I40E_ERR_INVALID_SD_TYPE:
-		return "I40E_ERR_INVALID_SD_TYPE";
-	case I40E_ERR_MEMCPY_FAILED:
-		return "I40E_ERR_MEMCPY_FAILED";
-	case I40E_ERR_INVALID_HMC_OBJ_INDEX:
-		return "I40E_ERR_INVALID_HMC_OBJ_INDEX";
-	case I40E_ERR_INVALID_HMC_OBJ_COUNT:
-		return "I40E_ERR_INVALID_HMC_OBJ_COUNT";
-	case I40E_ERR_INVALID_SRQ_ARM_LIMIT:
-		return "I40E_ERR_INVALID_SRQ_ARM_LIMIT";
-	case I40E_ERR_SRQ_ENABLED:
-		return "I40E_ERR_SRQ_ENABLED";
-	case I40E_ERR_ADMIN_QUEUE_ERROR:
-		return "I40E_ERR_ADMIN_QUEUE_ERROR";
-	case I40E_ERR_ADMIN_QUEUE_TIMEOUT:
-		return "I40E_ERR_ADMIN_QUEUE_TIMEOUT";
-	case I40E_ERR_BUF_TOO_SHORT:
-		return "I40E_ERR_BUF_TOO_SHORT";
-	case I40E_ERR_ADMIN_QUEUE_FULL:
-		return "I40E_ERR_ADMIN_QUEUE_FULL";
-	case I40E_ERR_ADMIN_QUEUE_NO_WORK:
-		return "I40E_ERR_ADMIN_QUEUE_NO_WORK";
-	case I40E_ERR_BAD_IWARP_CQE:
-		return "I40E_ERR_BAD_IWARP_CQE";
-	case I40E_ERR_NVM_BLANK_MODE:
-		return "I40E_ERR_NVM_BLANK_MODE";
-	case I40E_ERR_NOT_IMPLEMENTED:
-		return "I40E_ERR_NOT_IMPLEMENTED";
-	case I40E_ERR_PE_DOORBELL_NOT_ENABLED:
-		return "I40E_ERR_PE_DOORBELL_NOT_ENABLED";
-	case I40E_ERR_DIAG_TEST_FAILED:
-		return "I40E_ERR_DIAG_TEST_FAILED";
-	case I40E_ERR_NOT_READY:
-		return "I40E_ERR_NOT_READY";
-	case I40E_NOT_SUPPORTED:
-		return "I40E_NOT_SUPPORTED";
-	case I40E_ERR_FIRMWARE_API_VERSION:
-		return "I40E_ERR_FIRMWARE_API_VERSION";
-	case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR:
-		return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR";
+	case IAVF_ERR_NVM:
+		return "IAVF_ERR_NVM";
+	case IAVF_ERR_NVM_CHECKSUM:
+		return "IAVF_ERR_NVM_CHECKSUM";
+	case IAVF_ERR_PHY:
+		return "IAVF_ERR_PHY";
+	case IAVF_ERR_CONFIG:
+		return "IAVF_ERR_CONFIG";
+	case IAVF_ERR_PARAM:
+		return "IAVF_ERR_PARAM";
+	case IAVF_ERR_MAC_TYPE:
+		return "IAVF_ERR_MAC_TYPE";
+	case IAVF_ERR_UNKNOWN_PHY:
+		return "IAVF_ERR_UNKNOWN_PHY";
+	case IAVF_ERR_LINK_SETUP:
+		return "IAVF_ERR_LINK_SETUP";
+	case IAVF_ERR_ADAPTER_STOPPED:
+		return "IAVF_ERR_ADAPTER_STOPPED";
+	case IAVF_ERR_INVALID_MAC_ADDR:
+		return "IAVF_ERR_INVALID_MAC_ADDR";
+	case IAVF_ERR_DEVICE_NOT_SUPPORTED:
+		return "IAVF_ERR_DEVICE_NOT_SUPPORTED";
+	case IAVF_ERR_MASTER_REQUESTS_PENDING:
+		return "IAVF_ERR_MASTER_REQUESTS_PENDING";
+	case IAVF_ERR_INVALID_LINK_SETTINGS:
+		return "IAVF_ERR_INVALID_LINK_SETTINGS";
+	case IAVF_ERR_AUTONEG_NOT_COMPLETE:
+		return "IAVF_ERR_AUTONEG_NOT_COMPLETE";
+	case IAVF_ERR_RESET_FAILED:
+		return "IAVF_ERR_RESET_FAILED";
+	case IAVF_ERR_SWFW_SYNC:
+		return "IAVF_ERR_SWFW_SYNC";
+	case IAVF_ERR_NO_AVAILABLE_VSI:
+		return "IAVF_ERR_NO_AVAILABLE_VSI";
+	case IAVF_ERR_NO_MEMORY:
+		return "IAVF_ERR_NO_MEMORY";
+	case IAVF_ERR_BAD_PTR:
+		return "IAVF_ERR_BAD_PTR";
+	case IAVF_ERR_RING_FULL:
+		return "IAVF_ERR_RING_FULL";
+	case IAVF_ERR_INVALID_PD_ID:
+		return "IAVF_ERR_INVALID_PD_ID";
+	case IAVF_ERR_INVALID_QP_ID:
+		return "IAVF_ERR_INVALID_QP_ID";
+	case IAVF_ERR_INVALID_CQ_ID:
+		return "IAVF_ERR_INVALID_CQ_ID";
+	case IAVF_ERR_INVALID_CEQ_ID:
+		return "IAVF_ERR_INVALID_CEQ_ID";
+	case IAVF_ERR_INVALID_AEQ_ID:
+		return "IAVF_ERR_INVALID_AEQ_ID";
+	case IAVF_ERR_INVALID_SIZE:
+		return "IAVF_ERR_INVALID_SIZE";
+	case IAVF_ERR_INVALID_ARP_INDEX:
+		return "IAVF_ERR_INVALID_ARP_INDEX";
+	case IAVF_ERR_INVALID_FPM_FUNC_ID:
+		return "IAVF_ERR_INVALID_FPM_FUNC_ID";
+	case IAVF_ERR_QP_INVALID_MSG_SIZE:
+		return "IAVF_ERR_QP_INVALID_MSG_SIZE";
+	case IAVF_ERR_QP_TOOMANY_WRS_POSTED:
+		return "IAVF_ERR_QP_TOOMANY_WRS_POSTED";
+	case IAVF_ERR_INVALID_FRAG_COUNT:
+		return "IAVF_ERR_INVALID_FRAG_COUNT";
+	case IAVF_ERR_QUEUE_EMPTY:
+		return "IAVF_ERR_QUEUE_EMPTY";
+	case IAVF_ERR_INVALID_ALIGNMENT:
+		return "IAVF_ERR_INVALID_ALIGNMENT";
+	case IAVF_ERR_FLUSHED_QUEUE:
+		return "IAVF_ERR_FLUSHED_QUEUE";
+	case IAVF_ERR_INVALID_PUSH_PAGE_INDEX:
+		return "IAVF_ERR_INVALID_PUSH_PAGE_INDEX";
+	case IAVF_ERR_INVALID_IMM_DATA_SIZE:
+		return "IAVF_ERR_INVALID_IMM_DATA_SIZE";
+	case IAVF_ERR_TIMEOUT:
+		return "IAVF_ERR_TIMEOUT";
+	case IAVF_ERR_OPCODE_MISMATCH:
+		return "IAVF_ERR_OPCODE_MISMATCH";
+	case IAVF_ERR_CQP_COMPL_ERROR:
+		return "IAVF_ERR_CQP_COMPL_ERROR";
+	case IAVF_ERR_INVALID_VF_ID:
+		return "IAVF_ERR_INVALID_VF_ID";
+	case IAVF_ERR_INVALID_HMCFN_ID:
+		return "IAVF_ERR_INVALID_HMCFN_ID";
+	case IAVF_ERR_BACKING_PAGE_ERROR:
+		return "IAVF_ERR_BACKING_PAGE_ERROR";
+	case IAVF_ERR_NO_PBLCHUNKS_AVAILABLE:
+		return "IAVF_ERR_NO_PBLCHUNKS_AVAILABLE";
+	case IAVF_ERR_INVALID_PBLE_INDEX:
+		return "IAVF_ERR_INVALID_PBLE_INDEX";
+	case IAVF_ERR_INVALID_SD_INDEX:
+		return "IAVF_ERR_INVALID_SD_INDEX";
+	case IAVF_ERR_INVALID_PAGE_DESC_INDEX:
+		return "IAVF_ERR_INVALID_PAGE_DESC_INDEX";
+	case IAVF_ERR_INVALID_SD_TYPE:
+		return "IAVF_ERR_INVALID_SD_TYPE";
+	case IAVF_ERR_MEMCPY_FAILED:
+		return "IAVF_ERR_MEMCPY_FAILED";
+	case IAVF_ERR_INVALID_HMC_OBJ_INDEX:
+		return "IAVF_ERR_INVALID_HMC_OBJ_INDEX";
+	case IAVF_ERR_INVALID_HMC_OBJ_COUNT:
+		return "IAVF_ERR_INVALID_HMC_OBJ_COUNT";
+	case IAVF_ERR_INVALID_SRQ_ARM_LIMIT:
+		return "IAVF_ERR_INVALID_SRQ_ARM_LIMIT";
+	case IAVF_ERR_SRQ_ENABLED:
+		return "IAVF_ERR_SRQ_ENABLED";
+	case IAVF_ERR_ADMIN_QUEUE_ERROR:
+		return "IAVF_ERR_ADMIN_QUEUE_ERROR";
+	case IAVF_ERR_ADMIN_QUEUE_TIMEOUT:
+		return "IAVF_ERR_ADMIN_QUEUE_TIMEOUT";
+	case IAVF_ERR_BUF_TOO_SHORT:
+		return "IAVF_ERR_BUF_TOO_SHORT";
+	case IAVF_ERR_ADMIN_QUEUE_FULL:
+		return "IAVF_ERR_ADMIN_QUEUE_FULL";
+	case IAVF_ERR_ADMIN_QUEUE_NO_WORK:
+		return "IAVF_ERR_ADMIN_QUEUE_NO_WORK";
+	case IAVF_ERR_BAD_IWARP_CQE:
+		return "IAVF_ERR_BAD_IWARP_CQE";
+	case IAVF_ERR_NVM_BLANK_MODE:
+		return "IAVF_ERR_NVM_BLANK_MODE";
+	case IAVF_ERR_NOT_IMPLEMENTED:
+		return "IAVF_ERR_NOT_IMPLEMENTED";
+	case IAVF_ERR_PE_DOORBELL_NOT_ENABLED:
+		return "IAVF_ERR_PE_DOORBELL_NOT_ENABLED";
+	case IAVF_ERR_DIAG_TEST_FAILED:
+		return "IAVF_ERR_DIAG_TEST_FAILED";
+	case IAVF_ERR_NOT_READY:
+		return "IAVF_ERR_NOT_READY";
+	case IAVF_NOT_SUPPORTED:
+		return "IAVF_NOT_SUPPORTED";
+	case IAVF_ERR_FIRMWARE_API_VERSION:
+		return "IAVF_ERR_FIRMWARE_API_VERSION";
+	case IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR:
+		return "IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR";
 	}
 
 	snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err);
@@ -260,7 +260,7 @@ const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err)
 void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc,
 		   void *buffer, u16 buf_len)
 {
-	struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
+	struct iavf_aq_desc *aq_desc = (struct iavf_aq_desc *)desc;
 	u8 *buf = (u8 *)buffer;
 
 	if ((!(mask & hw->debug_mask)) || !desc)
@@ -327,17 +327,17 @@ bool iavf_check_asq_alive(struct iavf_hw *hw)
  * Tell the Firmware that we're shutting down the AdminQ and whether
  * or not the driver is unloading as well.
  **/
-iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading)
+enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_queue_shutdown *cmd =
-		(struct i40e_aqc_queue_shutdown *)&desc.params.raw;
-	iavf_status status;
+	struct iavf_aq_desc desc;
+	struct iavf_aqc_queue_shutdown *cmd =
+		(struct iavf_aqc_queue_shutdown *)&desc.params.raw;
+	enum iavf_status status;
 
-	iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_queue_shutdown);
+	iavf_fill_default_direct_cmd_desc(&desc, iavf_aqc_opc_queue_shutdown);
 
 	if (unloading)
-		cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING);
+		cmd->driver_unloading = cpu_to_le32(IAVF_AQ_DRIVER_UNLOADING);
 	status = iavf_asq_send_command(hw, &desc, NULL, 0, NULL);
 
 	return status;
@@ -354,43 +354,43 @@ iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading)
  *
  * Internal function to get or set RSS look up table
  **/
-static iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
-					   u16 vsi_id, bool pf_lut,
-					   u8 *lut, u16 lut_size,
-					   bool set)
+static enum iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
+						u16 vsi_id, bool pf_lut,
+						u8 *lut, u16 lut_size,
+						bool set)
 {
-	iavf_status status;
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_set_rss_lut *cmd_resp =
-		   (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw;
+	enum iavf_status status;
+	struct iavf_aq_desc desc;
+	struct iavf_aqc_get_set_rss_lut *cmd_resp =
+		   (struct iavf_aqc_get_set_rss_lut *)&desc.params.raw;
 
 	if (set)
 		iavf_fill_default_direct_cmd_desc(&desc,
-						  i40e_aqc_opc_set_rss_lut);
+						  iavf_aqc_opc_set_rss_lut);
 	else
 		iavf_fill_default_direct_cmd_desc(&desc,
-						  i40e_aqc_opc_get_rss_lut);
+						  iavf_aqc_opc_get_rss_lut);
 
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
 
 	cmd_resp->vsi_id =
 			cpu_to_le16((u16)((vsi_id <<
-					  I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) &
-					  I40E_AQC_SET_RSS_LUT_VSI_ID_MASK));
-	cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID);
+					  IAVF_AQC_SET_RSS_LUT_VSI_ID_SHIFT) &
+					  IAVF_AQC_SET_RSS_LUT_VSI_ID_MASK));
+	cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_LUT_VSI_VALID);
 
 	if (pf_lut)
 		cmd_resp->flags |= cpu_to_le16((u16)
-					((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF <<
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+					((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_PF <<
+					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
+					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
 	else
 		cmd_resp->flags |= cpu_to_le16((u16)
-					((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI <<
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
-					I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
+					((IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_VSI <<
+					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) &
+					IAVF_AQC_SET_RSS_LUT_TABLE_TYPE_MASK));
 
 	status = iavf_asq_send_command(hw, &desc, lut, lut_size, NULL);
 
@@ -407,8 +407,8 @@ static iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw,
  *
  * get the RSS lookup table, PF or VSI type
  **/
-iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 vsi_id,
-				bool pf_lut, u8 *lut, u16 lut_size)
+enum iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 vsi_id,
+				     bool pf_lut, u8 *lut, u16 lut_size)
 {
 	return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size,
 				       false);
@@ -424,8 +424,8 @@ iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 vsi_id,
  *
  * set the RSS lookup table, PF or VSI type
  **/
-iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 vsi_id,
-				bool pf_lut, u8 *lut, u16 lut_size)
+enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 vsi_id,
+				     bool pf_lut, u8 *lut, u16 lut_size)
 {
 	return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true);
 }
@@ -439,33 +439,33 @@ iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 vsi_id,
  *
  * get the RSS key per VSI
  **/
-static
+static enum
 iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
-				    struct i40e_aqc_get_set_rss_key_data *key,
+				    struct iavf_aqc_get_set_rss_key_data *key,
 				    bool set)
 {
-	iavf_status status;
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_set_rss_key *cmd_resp =
-			(struct i40e_aqc_get_set_rss_key *)&desc.params.raw;
-	u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data);
+	enum iavf_status status;
+	struct iavf_aq_desc desc;
+	struct iavf_aqc_get_set_rss_key *cmd_resp =
+			(struct iavf_aqc_get_set_rss_key *)&desc.params.raw;
+	u16 key_size = sizeof(struct iavf_aqc_get_set_rss_key_data);
 
 	if (set)
 		iavf_fill_default_direct_cmd_desc(&desc,
-						  i40e_aqc_opc_set_rss_key);
+						  iavf_aqc_opc_set_rss_key);
 	else
 		iavf_fill_default_direct_cmd_desc(&desc,
-						  i40e_aqc_opc_get_rss_key);
+						  iavf_aqc_opc_get_rss_key);
 
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_RD);
 
 	cmd_resp->vsi_id =
 			cpu_to_le16((u16)((vsi_id <<
-					  I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
-					  I40E_AQC_SET_RSS_KEY_VSI_ID_MASK));
-	cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID);
+					  IAVF_AQC_SET_RSS_KEY_VSI_ID_SHIFT) &
+					  IAVF_AQC_SET_RSS_KEY_VSI_ID_MASK));
+	cmd_resp->vsi_id |= cpu_to_le16((u16)IAVF_AQC_SET_RSS_KEY_VSI_VALID);
 
 	status = iavf_asq_send_command(hw, &desc, key, key_size, NULL);
 
@@ -479,8 +479,8 @@ iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
  * @key: pointer to key info struct
  *
  **/
-iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 vsi_id,
-				struct i40e_aqc_get_set_rss_key_data *key)
+enum iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 vsi_id,
+				     struct iavf_aqc_get_set_rss_key_data *key)
 {
 	return iavf_aq_get_set_rss_key(hw, vsi_id, key, false);
 }
@@ -493,8 +493,8 @@ iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 vsi_id,
  *
  * set the RSS key per VSI
  **/
-iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
-				struct i40e_aqc_get_set_rss_key_data *key)
+enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
+				     struct iavf_aqc_get_set_rss_key_data *key)
 {
 	return iavf_aq_get_set_rss_key(hw, vsi_id, key, true);
 }
@@ -515,7 +515,7 @@ iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id,
  * IF NOT iavf_ptype_lookup[ptype].known
  * THEN
  *      Packet is unknown
- * ELSE IF iavf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP
+ * ELSE IF iavf_ptype_lookup[ptype].outer_ip == IAVF_RX_PTYPE_OUTER_IP
  *      Use the rest of the fields to look at the tunnels, inner protocols, etc
  * ELSE
  *      Use the enum iavf_rx_l2_ptype to decode the packet type
@@ -877,24 +877,25 @@ struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = {
  * is sent asynchronously, i.e. iavf_asq_send_command() does not wait for
  * completion before returning.
  **/
-iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
-				   enum virtchnl_ops v_opcode,
-				   iavf_status v_retval, u8 *msg, u16 msglen,
-				   struct i40e_asq_cmd_details *cmd_details)
+enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
+					enum virtchnl_ops v_opcode,
+					enum iavf_status v_retval,
+					u8 *msg, u16 msglen,
+					struct iavf_asq_cmd_details *cmd_details)
 {
-	struct i40e_asq_cmd_details details;
-	struct i40e_aq_desc desc;
-	iavf_status status;
+	struct iavf_asq_cmd_details details;
+	struct iavf_aq_desc desc;
+	enum iavf_status status;
 
-	iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_pf);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI);
+	iavf_fill_default_direct_cmd_desc(&desc, iavf_aqc_opc_send_msg_to_pf);
+	desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_SI);
 	desc.cookie_high = cpu_to_le32(v_opcode);
 	desc.cookie_low = cpu_to_le32(v_retval);
 	if (msglen) {
-		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF
-						| I40E_AQ_FLAG_RD));
-		if (msglen > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)(IAVF_AQ_FLAG_BUF
+						| IAVF_AQ_FLAG_RD));
+		if (msglen > IAVF_AQ_LARGE_BUF)
+			desc.flags |= cpu_to_le16((u16)IAVF_AQ_FLAG_LB);
 		desc.datalen = cpu_to_le16(msglen);
 	}
 	if (!cmd_details) {
@@ -948,7 +949,7 @@ void iavf_vf_parse_hw_config(struct iavf_hw *hw,
  * as none will be forthcoming. Immediately after calling this function,
  * the admin queue should be shut down and (optionally) reinitialized.
  **/
-iavf_status iavf_vf_reset(struct iavf_hw *hw)
+enum iavf_status iavf_vf_reset(struct iavf_hw *hw)
 {
 	return iavf_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF,
 				      0, NULL, 0, NULL);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 9f87304109fe..dad3eec8ccd8 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -280,10 +280,10 @@ static int iavf_get_link_ksettings(struct net_device *netdev,
 	cmd->base.port = PORT_NONE;
 	/* Set speed and duplex */
 	switch (adapter->link_speed) {
-	case I40E_LINK_SPEED_40GB:
+	case IAVF_LINK_SPEED_40GB:
 		cmd->base.speed = SPEED_40000;
 		break;
-	case I40E_LINK_SPEED_25GB:
+	case IAVF_LINK_SPEED_25GB:
 #ifdef SPEED_25000
 		cmd->base.speed = SPEED_25000;
 #else
@@ -291,16 +291,16 @@ static int iavf_get_link_ksettings(struct net_device *netdev,
 			    "Speed is 25G, display not supported by this version of ethtool.\n");
 #endif
 		break;
-	case I40E_LINK_SPEED_20GB:
+	case IAVF_LINK_SPEED_20GB:
 		cmd->base.speed = SPEED_20000;
 		break;
-	case I40E_LINK_SPEED_10GB:
+	case IAVF_LINK_SPEED_10GB:
 		cmd->base.speed = SPEED_10000;
 		break;
-	case I40E_LINK_SPEED_1GB:
+	case IAVF_LINK_SPEED_1GB:
 		cmd->base.speed = SPEED_1000;
 		break;
-	case I40E_LINK_SPEED_100MB:
+	case IAVF_LINK_SPEED_100MB:
 		cmd->base.speed = SPEED_100;
 		break;
 	default:
@@ -510,7 +510,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags)
 	if (changed_flags & IAVF_FLAG_LEGACY_RX) {
 		if (netif_running(netdev)) {
 			adapter->flags |= IAVF_FLAG_RESET_NEEDED;
-			schedule_work(&adapter->reset_task);
+			queue_work(iavf_wq, &adapter->reset_task);
 		}
 	}
 
@@ -622,7 +622,7 @@ static int iavf_set_ringparam(struct net_device *netdev,
 
 	if (netif_running(netdev)) {
 		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
-		schedule_work(&adapter->reset_task);
+		queue_work(iavf_wq, &adapter->reset_task);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 9f2b7b7adf6b..9d2b50964a08 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -14,6 +14,8 @@
 static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter);
 static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter);
 static int iavf_close(struct net_device *netdev);
+static int iavf_init_get_resources(struct iavf_adapter *adapter);
+static int iavf_check_reset_complete(struct iavf_hw *hw);
 
 char iavf_driver_name[] = "iavf";
 static const char iavf_driver_string[] =
@@ -57,7 +59,8 @@ MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver")
 MODULE_LICENSE("GPL v2");
 MODULE_VERSION(DRV_VERSION);
 
-static struct workqueue_struct *iavf_wq;
+static const struct net_device_ops iavf_netdev_ops;
+struct workqueue_struct *iavf_wq;
 
 /**
  * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code
@@ -66,14 +69,14 @@ static struct workqueue_struct *iavf_wq;
  * @size: size of memory requested
  * @alignment: what to align the allocation to
  **/
-iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw,
-				    struct iavf_dma_mem *mem,
-				    u64 size, u32 alignment)
+enum iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw,
+					 struct iavf_dma_mem *mem,
+					 u64 size, u32 alignment)
 {
 	struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back;
 
 	if (!mem)
-		return I40E_ERR_PARAM;
+		return IAVF_ERR_PARAM;
 
 	mem->size = ALIGN(size, alignment);
 	mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size,
@@ -81,7 +84,7 @@ iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw,
 	if (mem->va)
 		return 0;
 	else
-		return I40E_ERR_NO_MEMORY;
+		return IAVF_ERR_NO_MEMORY;
 }
 
 /**
@@ -89,12 +92,13 @@ iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw,
  * @hw:   pointer to the HW structure
  * @mem:  ptr to mem struct to free
  **/
-iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw, struct iavf_dma_mem *mem)
+enum iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw,
+				     struct iavf_dma_mem *mem)
 {
 	struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back;
 
 	if (!mem || !mem->va)
-		return I40E_ERR_PARAM;
+		return IAVF_ERR_PARAM;
 	dma_free_coherent(&adapter->pdev->dev, mem->size,
 			  mem->va, (dma_addr_t)mem->pa);
 	return 0;
@@ -106,11 +110,11 @@ iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw, struct iavf_dma_mem *mem)
  * @mem:  ptr to mem struct to fill out
  * @size: size of memory requested
  **/
-iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw,
-				     struct iavf_virt_mem *mem, u32 size)
+enum iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw,
+					  struct iavf_virt_mem *mem, u32 size)
 {
 	if (!mem)
-		return I40E_ERR_PARAM;
+		return IAVF_ERR_PARAM;
 
 	mem->size = size;
 	mem->va = kzalloc(size, GFP_KERNEL);
@@ -118,7 +122,7 @@ iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw,
 	if (mem->va)
 		return 0;
 	else
-		return I40E_ERR_NO_MEMORY;
+		return IAVF_ERR_NO_MEMORY;
 }
 
 /**
@@ -126,10 +130,11 @@ iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw,
  * @hw:   pointer to the HW structure
  * @mem:  ptr to mem struct to free
  **/
-iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, struct iavf_virt_mem *mem)
+enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw,
+				      struct iavf_virt_mem *mem)
 {
 	if (!mem)
-		return I40E_ERR_PARAM;
+		return IAVF_ERR_PARAM;
 
 	/* it's ok to kfree a NULL pointer */
 	kfree(mem->va);
@@ -168,7 +173,7 @@ void iavf_schedule_reset(struct iavf_adapter *adapter)
 	if (!(adapter->flags &
 	      (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) {
 		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
-		schedule_work(&adapter->reset_task);
+		queue_work(iavf_wq, &adapter->reset_task);
 	}
 }
 
@@ -287,7 +292,7 @@ static irqreturn_t iavf_msix_aq(int irq, void *data)
 	rd32(hw, IAVF_VFINT_ICR0_ENA1);
 
 	/* schedule work on the private workqueue */
-	schedule_work(&adapter->adminq_task);
+	queue_work(iavf_wq, &adapter->adminq_task);
 
 	return IRQ_HANDLED;
 }
@@ -657,14 +662,13 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, u16 vlan)
 
 	f = iavf_find_vlan(adapter, vlan);
 	if (!f) {
-		f = kzalloc(sizeof(*f), GFP_KERNEL);
+		f = kzalloc(sizeof(*f), GFP_ATOMIC);
 		if (!f)
 			goto clearout;
 
 		f->vlan = vlan;
 
-		INIT_LIST_HEAD(&f->list);
-		list_add(&f->list, &adapter->vlan_filter_list);
+		list_add_tail(&f->list, &adapter->vlan_filter_list);
 		f->add = true;
 		adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER;
 	}
@@ -979,7 +983,7 @@ static void iavf_up_complete(struct iavf_adapter *adapter)
 	adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES;
 	if (CLIENT_ENABLED(adapter))
 		adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN;
-	mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
+	mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
 }
 
 /**
@@ -1043,7 +1047,7 @@ void iavf_down(struct iavf_adapter *adapter)
 		adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES;
 	}
 
-	mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
+	mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
 }
 
 /**
@@ -1227,8 +1231,8 @@ out:
  **/
 static int iavf_config_rss_aq(struct iavf_adapter *adapter)
 {
-	struct i40e_aqc_get_set_rss_key_data *rss_key =
-		(struct i40e_aqc_get_set_rss_key_data *)adapter->rss_key;
+	struct iavf_aqc_get_set_rss_key_data *rss_key =
+		(struct iavf_aqc_get_set_rss_key_data *)adapter->rss_key;
 	struct iavf_hw *hw = &adapter->hw;
 	int ret = 0;
 
@@ -1532,136 +1536,66 @@ err:
 }
 
 /**
- * iavf_watchdog_timer - Periodic call-back timer
- * @data: pointer to adapter disguised as unsigned long
- **/
-static void iavf_watchdog_timer(struct timer_list *t)
-{
-	struct iavf_adapter *adapter = from_timer(adapter, t,
-						    watchdog_timer);
-
-	schedule_work(&adapter->watchdog_task);
-	/* timer will be rescheduled in watchdog task */
-}
-
-/**
- * iavf_watchdog_task - Periodic call-back task
- * @work: pointer to work_struct
+ * iavf_process_aq_command - process aq_required flags
+ * and sends aq command
+ * @adapter: pointer to iavf adapter structure
+ *
+ * Returns 0 on success
+ * Returns error code if no command was sent
+ * or error code if the command failed.
  **/
-static void iavf_watchdog_task(struct work_struct *work)
+static int iavf_process_aq_command(struct iavf_adapter *adapter)
 {
-	struct iavf_adapter *adapter = container_of(work,
-						      struct iavf_adapter,
-						      watchdog_task);
-	struct iavf_hw *hw = &adapter->hw;
-	u32 reg_val;
-
-	if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section))
-		goto restart_watchdog;
-
-	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) {
-		reg_val = rd32(hw, IAVF_VFGEN_RSTAT) &
-			  IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
-		if ((reg_val == VIRTCHNL_VFR_VFACTIVE) ||
-		    (reg_val == VIRTCHNL_VFR_COMPLETED)) {
-			/* A chance for redemption! */
-			dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n");
-			adapter->state = __IAVF_STARTUP;
-			adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
-			schedule_delayed_work(&adapter->init_task, 10);
-			clear_bit(__IAVF_IN_CRITICAL_TASK,
-				  &adapter->crit_section);
-			/* Don't reschedule the watchdog, since we've restarted
-			 * the init task. When init_task contacts the PF and
-			 * gets everything set up again, it'll restart the
-			 * watchdog for us. Down, boy. Sit. Stay. Woof.
-			 */
-			return;
-		}
-		adapter->aq_required = 0;
-		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		goto watchdog_done;
-	}
-
-	if ((adapter->state < __IAVF_DOWN) ||
-	    (adapter->flags & IAVF_FLAG_RESET_PENDING))
-		goto watchdog_done;
-
-	/* check for reset */
-	reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
-	if (!(adapter->flags & IAVF_FLAG_RESET_PENDING) && !reg_val) {
-		adapter->state = __IAVF_RESETTING;
-		adapter->flags |= IAVF_FLAG_RESET_PENDING;
-		dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
-		schedule_work(&adapter->reset_task);
-		adapter->aq_required = 0;
-		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-		goto watchdog_done;
-	}
-
-	/* Process admin queue tasks. After init, everything gets done
-	 * here so we don't race on the admin queue.
-	 */
-	if (adapter->current_op) {
-		if (!iavf_asq_done(hw)) {
-			dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n");
-			iavf_send_api_ver(adapter);
-		}
-		goto watchdog_done;
-	}
-	if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG) {
-		iavf_send_vf_config_msg(adapter);
-		goto watchdog_done;
-	}
-
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG)
+		return iavf_send_vf_config_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) {
 		iavf_disable_queues(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_MAP_VECTORS) {
 		iavf_map_queues(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_ADD_MAC_FILTER) {
 		iavf_add_ether_addrs(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_ADD_VLAN_FILTER) {
 		iavf_add_vlans(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_DEL_MAC_FILTER) {
 		iavf_del_ether_addrs(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_DEL_VLAN_FILTER) {
 		iavf_del_vlans(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) {
 		iavf_enable_vlan_stripping(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) {
 		iavf_disable_vlan_stripping(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) {
 		iavf_configure_queues(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_QUEUES) {
 		iavf_enable_queues(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_RSS) {
@@ -1669,81 +1603,414 @@ static void iavf_watchdog_task(struct work_struct *work)
 		 * PF, so we don't have to set current_op as we will
 		 * not get a response through the ARQ.
 		 */
-		iavf_init_rss(adapter);
 		adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS;
-		goto watchdog_done;
+		return 0;
 	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) {
 		iavf_get_hena(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) {
 		iavf_set_hena(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) {
 		iavf_set_rss_key(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_LUT) {
 		iavf_set_rss_lut(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) {
 		iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC |
 				       FLAG_VF_MULTICAST_PROMISC);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) {
 		iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) &&
 	    (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) {
 		iavf_set_promiscuous(adapter, 0);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CHANNELS) {
 		iavf_enable_channels(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CHANNELS) {
 		iavf_disable_channels(adapter);
-		goto watchdog_done;
+		return 0;
 	}
-
 	if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) {
 		iavf_add_cloud_filter(adapter);
-		goto watchdog_done;
+		return 0;
 	}
 
 	if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) {
 		iavf_del_cloud_filter(adapter);
+		return 0;
+	}
+	if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) {
+		iavf_del_cloud_filter(adapter);
+		return 0;
+	}
+	if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) {
+		iavf_add_cloud_filter(adapter);
+		return 0;
+	}
+	return -EAGAIN;
+}
+
+/**
+ * iavf_startup - first step of driver startup
+ * @adapter: board private structure
+ *
+ * Function process __IAVF_STARTUP driver state.
+ * When success the state is changed to __IAVF_INIT_VERSION_CHECK
+ * when fails it returns -EAGAIN
+ **/
+static int iavf_startup(struct iavf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct iavf_hw *hw = &adapter->hw;
+	int err;
+
+	WARN_ON(adapter->state != __IAVF_STARTUP);
+
+	/* driver loaded, probe complete */
+	adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
+	adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
+	err = iavf_set_mac_type(hw);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", err);
+		goto err;
+	}
+
+	err = iavf_check_reset_complete(hw);
+	if (err) {
+		dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n",
+			 err);
+		goto err;
+	}
+	hw->aq.num_arq_entries = IAVF_AQ_LEN;
+	hw->aq.num_asq_entries = IAVF_AQ_LEN;
+	hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE;
+	hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE;
+
+	err = iavf_init_adminq(hw);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", err);
+		goto err;
+	}
+	err = iavf_send_api_ver(adapter);
+	if (err) {
+		dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err);
+		iavf_shutdown_adminq(hw);
+		goto err;
+	}
+	adapter->state = __IAVF_INIT_VERSION_CHECK;
+err:
+	return err;
+}
+
+/**
+ * iavf_init_version_check - second step of driver startup
+ * @adapter: board private structure
+ *
+ * Function process __IAVF_INIT_VERSION_CHECK driver state.
+ * When success the state is changed to __IAVF_INIT_GET_RESOURCES
+ * when fails it returns -EAGAIN
+ **/
+static int iavf_init_version_check(struct iavf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct iavf_hw *hw = &adapter->hw;
+	int err = -EAGAIN;
+
+	WARN_ON(adapter->state != __IAVF_INIT_VERSION_CHECK);
+
+	if (!iavf_asq_done(hw)) {
+		dev_err(&pdev->dev, "Admin queue command never completed\n");
+		iavf_shutdown_adminq(hw);
+		adapter->state = __IAVF_STARTUP;
+		goto err;
+	}
+
+	/* aq msg sent, awaiting reply */
+	err = iavf_verify_api_ver(adapter);
+	if (err) {
+		if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK)
+			err = iavf_send_api_ver(adapter);
+		else
+			dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n",
+				adapter->pf_version.major,
+				adapter->pf_version.minor,
+				VIRTCHNL_VERSION_MAJOR,
+				VIRTCHNL_VERSION_MINOR);
+		goto err;
+	}
+	err = iavf_send_vf_config_msg(adapter);
+	if (err) {
+		dev_err(&pdev->dev, "Unable to send config request (%d)\n",
+			err);
+		goto err;
+	}
+	adapter->state = __IAVF_INIT_GET_RESOURCES;
+
+err:
+	return err;
+}
+
+/**
+ * iavf_init_get_resources - third step of driver startup
+ * @adapter: board private structure
+ *
+ * Function process __IAVF_INIT_GET_RESOURCES driver state and
+ * finishes driver initialization procedure.
+ * When success the state is changed to __IAVF_DOWN
+ * when fails it returns -EAGAIN
+ **/
+static int iavf_init_get_resources(struct iavf_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	struct iavf_hw *hw = &adapter->hw;
+	int err = 0, bufsz;
+
+	WARN_ON(adapter->state != __IAVF_INIT_GET_RESOURCES);
+	/* aq msg sent, awaiting reply */
+	if (!adapter->vf_res) {
+		bufsz = sizeof(struct virtchnl_vf_resource) +
+			(IAVF_MAX_VF_VSI *
+			sizeof(struct virtchnl_vsi_resource));
+		adapter->vf_res = kzalloc(bufsz, GFP_KERNEL);
+		if (!adapter->vf_res)
+			goto err;
+	}
+	err = iavf_get_vf_config(adapter);
+	if (err == IAVF_ERR_ADMIN_QUEUE_NO_WORK) {
+		err = iavf_send_vf_config_msg(adapter);
+		goto err;
+	} else if (err == IAVF_ERR_PARAM) {
+		/* We only get ERR_PARAM if the device is in a very bad
+		 * state or if we've been disabled for previous bad
+		 * behavior. Either way, we're done now.
+		 */
+		iavf_shutdown_adminq(hw);
+		dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n");
+		return 0;
+	}
+	if (err) {
+		dev_err(&pdev->dev, "Unable to get VF config (%d)\n", err);
+		goto err_alloc;
+	}
+
+	if (iavf_process_config(adapter))
+		goto err_alloc;
+	adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+
+	adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED;
+
+	netdev->netdev_ops = &iavf_netdev_ops;
+	iavf_set_ethtool_ops(netdev);
+	netdev->watchdog_timeo = 5 * HZ;
+
+	/* MTU range: 68 - 9710 */
+	netdev->min_mtu = ETH_MIN_MTU;
+	netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD;
+
+	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
+		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
+			 adapter->hw.mac.addr);
+		eth_hw_addr_random(netdev);
+		ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
+	} else {
+		adapter->flags |= IAVF_FLAG_ADDR_SET_BY_PF;
+		ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
+		ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
+	}
+
+	adapter->tx_desc_count = IAVF_DEFAULT_TXD;
+	adapter->rx_desc_count = IAVF_DEFAULT_RXD;
+	err = iavf_init_interrupt_scheme(adapter);
+	if (err)
+		goto err_sw_init;
+	iavf_map_rings_to_vectors(adapter);
+	if (adapter->vf_res->vf_cap_flags &
+		VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
+		adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE;
+
+	err = iavf_request_misc_irq(adapter);
+	if (err)
+		goto err_sw_init;
+
+	netif_carrier_off(netdev);
+	adapter->link_up = false;
+
+	/* set the semaphore to prevent any callbacks after device registration
+	 * up to time when state of driver will be set to __IAVF_DOWN
+	 */
+	rtnl_lock();
+	if (!adapter->netdev_registered) {
+		err = register_netdevice(netdev);
+		if (err) {
+			rtnl_unlock();
+			goto err_register;
+		}
+	}
+
+	adapter->netdev_registered = true;
+
+	netif_tx_stop_all_queues(netdev);
+	if (CLIENT_ALLOWED(adapter)) {
+		err = iavf_lan_add_device(adapter);
+		if (err) {
+			rtnl_unlock();
+			dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
+				 err);
+		}
+	}
+	dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
+	if (netdev->features & NETIF_F_GRO)
+		dev_info(&pdev->dev, "GRO is enabled\n");
+
+	adapter->state = __IAVF_DOWN;
+	set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
+	rtnl_unlock();
+
+	iavf_misc_irq_enable(adapter);
+	wake_up(&adapter->down_waitqueue);
+
+	adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL);
+	adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL);
+	if (!adapter->rss_key || !adapter->rss_lut)
+		goto err_mem;
+	if (RSS_AQ(adapter))
+		adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS;
+	else
+		iavf_init_rss(adapter);
+
+	return err;
+err_mem:
+	iavf_free_rss(adapter);
+err_register:
+	iavf_free_misc_irq(adapter);
+err_sw_init:
+	iavf_reset_interrupt_capability(adapter);
+err_alloc:
+	kfree(adapter->vf_res);
+	adapter->vf_res = NULL;
+err:
+	return err;
+}
+
+/**
+ * iavf_watchdog_task - Periodic call-back task
+ * @work: pointer to work_struct
+ **/
+static void iavf_watchdog_task(struct work_struct *work)
+{
+	struct iavf_adapter *adapter = container_of(work,
+						    struct iavf_adapter,
+						    watchdog_task.work);
+	struct iavf_hw *hw = &adapter->hw;
+	u32 reg_val;
+
+	if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section))
+		goto restart_watchdog;
+
+	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
+		adapter->state = __IAVF_COMM_FAILED;
+
+	switch (adapter->state) {
+	case __IAVF_COMM_FAILED:
+		reg_val = rd32(hw, IAVF_VFGEN_RSTAT) &
+			  IAVF_VFGEN_RSTAT_VFR_STATE_MASK;
+		if (reg_val == VIRTCHNL_VFR_VFACTIVE ||
+		    reg_val == VIRTCHNL_VFR_COMPLETED) {
+			/* A chance for redemption! */
+			dev_err(&adapter->pdev->dev,
+				"Hardware came out of reset. Attempting reinit.\n");
+			adapter->state = __IAVF_STARTUP;
+			adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
+			queue_delayed_work(iavf_wq, &adapter->init_task, 10);
+			clear_bit(__IAVF_IN_CRITICAL_TASK,
+				  &adapter->crit_section);
+			/* Don't reschedule the watchdog, since we've restarted
+			 * the init task. When init_task contacts the PF and
+			 * gets everything set up again, it'll restart the
+			 * watchdog for us. Down, boy. Sit. Stay. Woof.
+			 */
+			return;
+		}
+		adapter->aq_required = 0;
+		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+		clear_bit(__IAVF_IN_CRITICAL_TASK,
+			  &adapter->crit_section);
+		queue_delayed_work(iavf_wq,
+				   &adapter->watchdog_task,
+				   msecs_to_jiffies(10));
 		goto watchdog_done;
+	case __IAVF_RESETTING:
+		clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+		queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+		return;
+	case __IAVF_DOWN:
+	case __IAVF_DOWN_PENDING:
+	case __IAVF_TESTING:
+	case __IAVF_RUNNING:
+		if (adapter->current_op) {
+			if (!iavf_asq_done(hw)) {
+				dev_dbg(&adapter->pdev->dev,
+					"Admin queue timeout\n");
+				iavf_send_api_ver(adapter);
+			}
+		} else {
+			if (!iavf_process_aq_command(adapter) &&
+			    adapter->state == __IAVF_RUNNING)
+				iavf_request_stats(adapter);
+		}
+		break;
+	case __IAVF_REMOVE:
+		clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
+		return;
+	default:
+		goto restart_watchdog;
 	}
 
-	schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
+		/* check for hw reset */
+	reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
+	if (!reg_val) {
+		adapter->state = __IAVF_RESETTING;
+		adapter->flags |= IAVF_FLAG_RESET_PENDING;
+		adapter->aq_required = 0;
+		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+		dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
+		queue_work(iavf_wq, &adapter->reset_task);
+		goto watchdog_done;
+	}
 
-	if (adapter->state == __IAVF_RUNNING)
-		iavf_request_stats(adapter);
+	schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
 watchdog_done:
-	if (adapter->state == __IAVF_RUNNING)
+	if (adapter->state == __IAVF_RUNNING ||
+	    adapter->state == __IAVF_COMM_FAILED)
 		iavf_detect_recover_hung(&adapter->vsi);
 	clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section);
 restart_watchdog:
-	if (adapter->state == __IAVF_REMOVE)
-		return;
 	if (adapter->aq_required)
-		mod_timer(&adapter->watchdog_timer,
-			  jiffies + msecs_to_jiffies(20));
+		queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+				   msecs_to_jiffies(20));
 	else
-		mod_timer(&adapter->watchdog_timer, jiffies + (HZ * 2));
-	schedule_work(&adapter->adminq_task);
+		queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+	queue_work(iavf_wq, &adapter->adminq_task);
 }
 
 static void iavf_disable_vf(struct iavf_adapter *adapter)
@@ -1967,7 +2234,7 @@ continue_reset:
 	adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER;
 	iavf_misc_irq_enable(adapter);
 
-	mod_timer(&adapter->watchdog_timer, jiffies + 2);
+	mod_delayed_work(iavf_wq, &adapter->watchdog_task, 2);
 
 	/* We were running when the reset started, so we need to restore some
 	 * state here.
@@ -2020,9 +2287,9 @@ static void iavf_adminq_task(struct work_struct *work)
 	struct iavf_adapter *adapter =
 		container_of(work, struct iavf_adapter, adminq_task);
 	struct iavf_hw *hw = &adapter->hw;
-	struct i40e_arq_event_info event;
+	struct iavf_arq_event_info event;
 	enum virtchnl_ops v_op;
-	iavf_status ret, v_ret;
+	enum iavf_status ret, v_ret;
 	u32 val, oldval;
 	u16 pending;
 
@@ -2037,7 +2304,7 @@ static void iavf_adminq_task(struct work_struct *work)
 	do {
 		ret = iavf_clean_arq_element(hw, &event, &pending);
 		v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high);
-		v_ret = (iavf_status)le32_to_cpu(event.desc.cookie_low);
+		v_ret = (enum iavf_status)le32_to_cpu(event.desc.cookie_low);
 
 		if (ret || !v_op)
 			break; /* No event to process or error cleaning ARQ */
@@ -2239,22 +2506,22 @@ static int iavf_validate_tx_bandwidth(struct iavf_adapter *adapter,
 	int speed = 0, ret = 0;
 
 	switch (adapter->link_speed) {
-	case I40E_LINK_SPEED_40GB:
+	case IAVF_LINK_SPEED_40GB:
 		speed = 40000;
 		break;
-	case I40E_LINK_SPEED_25GB:
+	case IAVF_LINK_SPEED_25GB:
 		speed = 25000;
 		break;
-	case I40E_LINK_SPEED_20GB:
+	case IAVF_LINK_SPEED_20GB:
 		speed = 20000;
 		break;
-	case I40E_LINK_SPEED_10GB:
+	case IAVF_LINK_SPEED_10GB:
 		speed = 10000;
 		break;
-	case I40E_LINK_SPEED_1GB:
+	case IAVF_LINK_SPEED_1GB:
 		speed = 1000;
 		break;
-	case I40E_LINK_SPEED_100MB:
+	case IAVF_LINK_SPEED_100MB:
 		speed = 100;
 		break;
 	default:
@@ -2432,13 +2699,15 @@ exit:
 /**
  * iavf_parse_cls_flower - Parse tc flower filters provided by kernel
  * @adapter: board private structure
- * @cls_flower: pointer to struct tc_cls_flower_offload
+ * @cls_flower: pointer to struct flow_cls_offload
  * @filter: pointer to cloud filter structure
  */
 static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
-				 struct tc_cls_flower_offload *f,
+				 struct flow_cls_offload *f,
 				 struct iavf_cloud_filter *filter)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0;
 	u16 n_proto_key = 0;
 	u8 field_flags = 0;
@@ -2447,7 +2716,7 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 	int i = 0;
 	struct virtchnl_filter *vf = &filter->f;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -2457,32 +2726,24 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
 		dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n",
-			f->dissector->used_keys);
+			dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
 
-		if (mask->keyid != 0)
+		flow_rule_match_enc_keyid(rule, &match);
+		if (match.mask->keyid != 0)
 			field_flags |= IAVF_CLOUD_FIELD_TEN_ID;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
-		n_proto_key = ntohs(key->n_proto);
-		n_proto_mask = ntohs(mask->n_proto);
+		flow_rule_match_basic(rule, &match);
+		n_proto_key = ntohs(match.key->n_proto);
+		n_proto_mask = ntohs(match.mask->n_proto);
 
 		if (n_proto_key == ETH_P_ALL) {
 			n_proto_key = 0;
@@ -2496,215 +2757,186 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 			vf->flow_type = VIRTCHNL_TCP_V6_FLOW;
 		}
 
-		if (key->ip_proto != IPPROTO_TCP) {
+		if (match.key->ip_proto != IPPROTO_TCP) {
 			dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n");
 			return -EINVAL;
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
+
+		flow_rule_match_eth_addrs(rule, &match);
 
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
 		/* use is_broadcast and is_zero to check for all 0xf or 0 */
-		if (!is_zero_ether_addr(mask->dst)) {
-			if (is_broadcast_ether_addr(mask->dst)) {
+		if (!is_zero_ether_addr(match.mask->dst)) {
+			if (is_broadcast_ether_addr(match.mask->dst)) {
 				field_flags |= IAVF_CLOUD_FIELD_OMAC;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n",
-					mask->dst);
-				return I40E_ERR_CONFIG;
+					match.mask->dst);
+				return IAVF_ERR_CONFIG;
 			}
 		}
 
-		if (!is_zero_ether_addr(mask->src)) {
-			if (is_broadcast_ether_addr(mask->src)) {
+		if (!is_zero_ether_addr(match.mask->src)) {
+			if (is_broadcast_ether_addr(match.mask->src)) {
 				field_flags |= IAVF_CLOUD_FIELD_IMAC;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n",
-					mask->src);
-				return I40E_ERR_CONFIG;
+					match.mask->src);
+				return IAVF_ERR_CONFIG;
 			}
 		}
 
-		if (!is_zero_ether_addr(key->dst))
-			if (is_valid_ether_addr(key->dst) ||
-			    is_multicast_ether_addr(key->dst)) {
+		if (!is_zero_ether_addr(match.key->dst))
+			if (is_valid_ether_addr(match.key->dst) ||
+			    is_multicast_ether_addr(match.key->dst)) {
 				/* set the mask if a valid dst_mac address */
 				for (i = 0; i < ETH_ALEN; i++)
 					vf->mask.tcp_spec.dst_mac[i] |= 0xff;
 				ether_addr_copy(vf->data.tcp_spec.dst_mac,
-						key->dst);
+						match.key->dst);
 			}
 
-		if (!is_zero_ether_addr(key->src))
-			if (is_valid_ether_addr(key->src) ||
-			    is_multicast_ether_addr(key->src)) {
+		if (!is_zero_ether_addr(match.key->src))
+			if (is_valid_ether_addr(match.key->src) ||
+			    is_multicast_ether_addr(match.key->src)) {
 				/* set the mask if a valid dst_mac address */
 				for (i = 0; i < ETH_ALEN; i++)
 					vf->mask.tcp_spec.src_mac[i] |= 0xff;
 				ether_addr_copy(vf->data.tcp_spec.src_mac,
-						key->src);
+						match.key->src);
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
-		if (mask->vlan_id) {
-			if (mask->vlan_id == VLAN_VID_MASK) {
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_id) {
+			if (match.mask->vlan_id == VLAN_VID_MASK) {
 				field_flags |= IAVF_CLOUD_FIELD_IVLAN;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n",
-					mask->vlan_id);
-				return I40E_ERR_CONFIG;
+					match.mask->vlan_id);
+				return IAVF_ERR_CONFIG;
 			}
 		}
 		vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff);
-		vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id);
+		vf->data.tcp_spec.vlan_id = cpu_to_be16(match.key->vlan_id);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->mask);
-
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be32(0xffffffff)) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_ipv4_addrs(rule, &match);
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be32(0xffffffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n",
-					be32_to_cpu(mask->dst));
-				return I40E_ERR_CONFIG;
+					be32_to_cpu(match.mask->dst));
+				return IAVF_ERR_CONFIG;
 			}
 		}
 
-		if (mask->src) {
-			if (mask->src == cpu_to_be32(0xffffffff)) {
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be32(0xffffffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n",
-					be32_to_cpu(mask->dst));
-				return I40E_ERR_CONFIG;
+					be32_to_cpu(match.mask->dst));
+				return IAVF_ERR_CONFIG;
 			}
 		}
 
 		if (field_flags & IAVF_CLOUD_FIELD_TEN_ID) {
 			dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n");
-			return I40E_ERR_CONFIG;
+			return IAVF_ERR_CONFIG;
 		}
-		if (key->dst) {
+		if (match.key->dst) {
 			vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff);
-			vf->data.tcp_spec.dst_ip[0] = key->dst;
+			vf->data.tcp_spec.dst_ip[0] = match.key->dst;
 		}
-		if (key->src) {
+		if (match.key->src) {
 			vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff);
-			vf->data.tcp_spec.src_ip[0] = key->src;
+			vf->data.tcp_spec.src_ip[0] = match.key->src;
 		}
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->mask);
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
 
 		/* validate mask, make sure it is not IPV6_ADDR_ANY */
-		if (ipv6_addr_any(&mask->dst)) {
+		if (ipv6_addr_any(&match.mask->dst)) {
 			dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n",
 				IPV6_ADDR_ANY);
-			return I40E_ERR_CONFIG;
+			return IAVF_ERR_CONFIG;
 		}
 
 		/* src and dest IPv6 address should not be LOOPBACK
 		 * (0:0:0:0:0:0:0:1) which can be represented as ::1
 		 */
-		if (ipv6_addr_loopback(&key->dst) ||
-		    ipv6_addr_loopback(&key->src)) {
+		if (ipv6_addr_loopback(&match.key->dst) ||
+		    ipv6_addr_loopback(&match.key->src)) {
 			dev_err(&adapter->pdev->dev,
 				"ipv6 addr should not be loopback\n");
-			return I40E_ERR_CONFIG;
+			return IAVF_ERR_CONFIG;
 		}
-		if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
+		if (!ipv6_addr_any(&match.mask->dst) ||
+		    !ipv6_addr_any(&match.mask->src))
 			field_flags |= IAVF_CLOUD_FIELD_IIP;
 
 		for (i = 0; i < 4; i++)
 			vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff);
-		memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32,
+		memcpy(&vf->data.tcp_spec.dst_ip, &match.key->dst.s6_addr32,
 		       sizeof(vf->data.tcp_spec.dst_ip));
 		for (i = 0; i < 4; i++)
 			vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff);
-		memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32,
+		memcpy(&vf->data.tcp_spec.src_ip, &match.key->src.s6_addr32,
 		       sizeof(vf->data.tcp_spec.src_ip));
 	}
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->mask);
-
-		if (mask->src) {
-			if (mask->src == cpu_to_be16(0xffff)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(rule, &match);
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be16(0xffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad src port mask %u\n",
-					be16_to_cpu(mask->src));
-				return I40E_ERR_CONFIG;
+					be16_to_cpu(match.mask->src));
+				return IAVF_ERR_CONFIG;
 			}
 		}
 
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be16(0xffff)) {
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be16(0xffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n",
-					be16_to_cpu(mask->dst));
-				return I40E_ERR_CONFIG;
+					be16_to_cpu(match.mask->dst));
+				return IAVF_ERR_CONFIG;
 			}
 		}
-		if (key->dst) {
+		if (match.key->dst) {
 			vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff);
-			vf->data.tcp_spec.dst_port = key->dst;
+			vf->data.tcp_spec.dst_port = match.key->dst;
 		}
 
-		if (key->src) {
+		if (match.key->src) {
 			vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff);
-			vf->data.tcp_spec.src_port = key->src;
+			vf->data.tcp_spec.src_port = match.key->src;
 		}
 	}
 	vf->field_flags = field_flags;
@@ -2739,10 +2971,10 @@ static int iavf_handle_tclass(struct iavf_adapter *adapter, u32 tc,
 /**
  * iavf_configure_clsflower - Add tc flower filters
  * @adapter: board private structure
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  */
 static int iavf_configure_clsflower(struct iavf_adapter *adapter,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
 	struct iavf_cloud_filter *filter = NULL;
@@ -2818,10 +3050,10 @@ static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter,
 /**
  * iavf_delete_clsflower - Remove tc flower filters
  * @adapter: board private structure
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  */
 static int iavf_delete_clsflower(struct iavf_adapter *adapter,
-				 struct tc_cls_flower_offload *cls_flower)
+				 struct flow_cls_offload *cls_flower)
 {
 	struct iavf_cloud_filter *filter = NULL;
 	int err = 0;
@@ -2845,17 +3077,17 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter,
  * @type_data: offload data
  */
 static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	if (cls_flower->common.chain_index)
 		return -EOPNOTSUPP;
 
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return iavf_configure_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return iavf_delete_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return -EOPNOTSUPP;
 	default:
 		return -EOPNOTSUPP;
@@ -2881,34 +3113,7 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-/**
- * iavf_setup_tc_block - register callbacks for tc
- * @netdev: network interface device structure
- * @f: tc offload data
- *
- * This function registers block callbacks for tc
- * offloads
- **/
-static int iavf_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct iavf_adapter *adapter = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, iavf_setup_tc_block_cb,
-					     adapter, adapter, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, iavf_setup_tc_block_cb,
-					adapter);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(iavf_block_cb_list);
 
 /**
  * iavf_setup_tc - configure multiple traffic classes
@@ -2924,11 +3129,16 @@ static int iavf_setup_tc_block(struct net_device *dev,
 static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 			 void *type_data)
 {
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
 	switch (type) {
 	case TC_SETUP_QDISC_MQPRIO:
 		return __iavf_setup_tc(netdev, type_data);
 	case TC_SETUP_BLOCK:
-		return iavf_setup_tc_block(netdev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &iavf_block_cb_list,
+						  iavf_setup_tc_block_cb,
+						  adapter, adapter, true);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2943,7 +3153,7 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
  * The open entry point is called when a network interface is made
  * active by the system (IFF_UP).  At this point all resources needed
  * for transmit and receive operations are allocated, the interrupt
- * handler is registered with the OS, the watchdog timer is started,
+ * handler is registered with the OS, the watchdog is started,
  * and the stack is notified that the interface is ready.
  **/
 static int iavf_open(struct net_device *netdev)
@@ -3055,7 +3265,7 @@ static int iavf_close(struct net_device *netdev)
 
 	status = wait_event_timeout(adapter->down_waitqueue,
 				    adapter->state == __IAVF_DOWN,
-				    msecs_to_jiffies(200));
+				    msecs_to_jiffies(500));
 	if (!status)
 		netdev_warn(netdev, "Device resources not yet released\n");
 	return 0;
@@ -3078,7 +3288,7 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
 		adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED;
 	}
 	adapter->flags |= IAVF_FLAG_RESET_NEEDED;
-	schedule_work(&adapter->reset_task);
+	queue_work(iavf_wq, &adapter->reset_task);
 
 	return 0;
 }
@@ -3383,217 +3593,41 @@ int iavf_process_config(struct iavf_adapter *adapter)
 static void iavf_init_task(struct work_struct *work)
 {
 	struct iavf_adapter *adapter = container_of(work,
-						      struct iavf_adapter,
-						      init_task.work);
-	struct net_device *netdev = adapter->netdev;
+						    struct iavf_adapter,
+						    init_task.work);
 	struct iavf_hw *hw = &adapter->hw;
-	struct pci_dev *pdev = adapter->pdev;
-	int err, bufsz;
 
 	switch (adapter->state) {
 	case __IAVF_STARTUP:
-		/* driver loaded, probe complete */
-		adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED;
-		adapter->flags &= ~IAVF_FLAG_RESET_PENDING;
-		err = iavf_set_mac_type(hw);
-		if (err) {
-			dev_err(&pdev->dev, "Failed to set MAC type (%d)\n",
-				err);
-			goto err;
-		}
-		err = iavf_check_reset_complete(hw);
-		if (err) {
-			dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n",
-				 err);
-			goto err;
-		}
-		hw->aq.num_arq_entries = IAVF_AQ_LEN;
-		hw->aq.num_asq_entries = IAVF_AQ_LEN;
-		hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE;
-		hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE;
-
-		err = iavf_init_adminq(hw);
-		if (err) {
-			dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n",
-				err);
-			goto err;
-		}
-		err = iavf_send_api_ver(adapter);
-		if (err) {
-			dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err);
-			iavf_shutdown_adminq(hw);
-			goto err;
-		}
-		adapter->state = __IAVF_INIT_VERSION_CHECK;
-		goto restart;
+		if (iavf_startup(adapter) < 0)
+			goto init_failed;
+		break;
 	case __IAVF_INIT_VERSION_CHECK:
-		if (!iavf_asq_done(hw)) {
-			dev_err(&pdev->dev, "Admin queue command never completed\n");
-			iavf_shutdown_adminq(hw);
-			adapter->state = __IAVF_STARTUP;
-			goto err;
-		}
-
-		/* aq msg sent, awaiting reply */
-		err = iavf_verify_api_ver(adapter);
-		if (err) {
-			if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK)
-				err = iavf_send_api_ver(adapter);
-			else
-				dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n",
-					adapter->pf_version.major,
-					adapter->pf_version.minor,
-					VIRTCHNL_VERSION_MAJOR,
-					VIRTCHNL_VERSION_MINOR);
-			goto err;
-		}
-		err = iavf_send_vf_config_msg(adapter);
-		if (err) {
-			dev_err(&pdev->dev, "Unable to send config request (%d)\n",
-				err);
-			goto err;
-		}
-		adapter->state = __IAVF_INIT_GET_RESOURCES;
-		goto restart;
-	case __IAVF_INIT_GET_RESOURCES:
-		/* aq msg sent, awaiting reply */
-		if (!adapter->vf_res) {
-			bufsz = sizeof(struct virtchnl_vf_resource) +
-				(IAVF_MAX_VF_VSI *
-				 sizeof(struct virtchnl_vsi_resource));
-			adapter->vf_res = kzalloc(bufsz, GFP_KERNEL);
-			if (!adapter->vf_res)
-				goto err;
-		}
-		err = iavf_get_vf_config(adapter);
-		if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) {
-			err = iavf_send_vf_config_msg(adapter);
-			goto err;
-		} else if (err == I40E_ERR_PARAM) {
-			/* We only get ERR_PARAM if the device is in a very bad
-			 * state or if we've been disabled for previous bad
-			 * behavior. Either way, we're done now.
-			 */
-			iavf_shutdown_adminq(hw);
-			dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n");
-			return;
-		}
-		if (err) {
-			dev_err(&pdev->dev, "Unable to get VF config (%d)\n",
-				err);
-			goto err_alloc;
-		}
-		adapter->state = __IAVF_INIT_SW;
+		if (iavf_init_version_check(adapter) < 0)
+			goto init_failed;
 		break;
+	case __IAVF_INIT_GET_RESOURCES:
+		if (iavf_init_get_resources(adapter) < 0)
+			goto init_failed;
+		return;
 	default:
-		goto err_alloc;
-	}
-
-	if (iavf_process_config(adapter))
-		goto err_alloc;
-	adapter->current_op = VIRTCHNL_OP_UNKNOWN;
-
-	adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED;
-
-	netdev->netdev_ops = &iavf_netdev_ops;
-	iavf_set_ethtool_ops(netdev);
-	netdev->watchdog_timeo = 5 * HZ;
-
-	/* MTU range: 68 - 9710 */
-	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD;
-
-	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
-		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
-			 adapter->hw.mac.addr);
-		eth_hw_addr_random(netdev);
-		ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
-	} else {
-		adapter->flags |= IAVF_FLAG_ADDR_SET_BY_PF;
-		ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
-		ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
+		goto init_failed;
 	}
 
-	timer_setup(&adapter->watchdog_timer, iavf_watchdog_timer, 0);
-	mod_timer(&adapter->watchdog_timer, jiffies + 1);
-
-	adapter->tx_desc_count = IAVF_DEFAULT_TXD;
-	adapter->rx_desc_count = IAVF_DEFAULT_RXD;
-	err = iavf_init_interrupt_scheme(adapter);
-	if (err)
-		goto err_sw_init;
-	iavf_map_rings_to_vectors(adapter);
-	if (adapter->vf_res->vf_cap_flags &
-	    VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
-		adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE;
-
-	err = iavf_request_misc_irq(adapter);
-	if (err)
-		goto err_sw_init;
-
-	netif_carrier_off(netdev);
-	adapter->link_up = false;
-
-	if (!adapter->netdev_registered) {
-		err = register_netdev(netdev);
-		if (err)
-			goto err_register;
-	}
-
-	adapter->netdev_registered = true;
-
-	netif_tx_stop_all_queues(netdev);
-	if (CLIENT_ALLOWED(adapter)) {
-		err = iavf_lan_add_device(adapter);
-		if (err)
-			dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
-				 err);
-	}
-
-	dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
-	if (netdev->features & NETIF_F_GRO)
-		dev_info(&pdev->dev, "GRO is enabled\n");
-
-	adapter->state = __IAVF_DOWN;
-	set_bit(__IAVF_VSI_DOWN, adapter->vsi.state);
-	iavf_misc_irq_enable(adapter);
-	wake_up(&adapter->down_waitqueue);
-
-	adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL);
-	adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL);
-	if (!adapter->rss_key || !adapter->rss_lut)
-		goto err_mem;
-
-	if (RSS_AQ(adapter)) {
-		adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS;
-		mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
-	} else {
-		iavf_init_rss(adapter);
-	}
-	return;
-restart:
-	schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(30));
+	queue_delayed_work(iavf_wq, &adapter->init_task,
+			   msecs_to_jiffies(30));
 	return;
-err_mem:
-	iavf_free_rss(adapter);
-err_register:
-	iavf_free_misc_irq(adapter);
-err_sw_init:
-	iavf_reset_interrupt_capability(adapter);
-err_alloc:
-	kfree(adapter->vf_res);
-	adapter->vf_res = NULL;
-err:
-	/* Things went into the weeds, so try again later */
+init_failed:
 	if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) {
-		dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n");
+		dev_err(&adapter->pdev->dev,
+			"Failed to communicate with PF; waiting before retry\n");
 		adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
 		iavf_shutdown_adminq(hw);
 		adapter->state = __IAVF_STARTUP;
-		schedule_delayed_work(&adapter->init_task, HZ * 5);
+		queue_delayed_work(iavf_wq, &adapter->init_task, HZ * 5);
 		return;
 	}
-	schedule_delayed_work(&adapter->init_task, HZ);
+	queue_delayed_work(iavf_wq, &adapter->init_task, HZ);
 }
 
 /**
@@ -3718,11 +3752,11 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&adapter->reset_task, iavf_reset_task);
 	INIT_WORK(&adapter->adminq_task, iavf_adminq_task);
-	INIT_WORK(&adapter->watchdog_task, iavf_watchdog_task);
+	INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task);
 	INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task);
 	INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task);
-	schedule_delayed_work(&adapter->init_task,
-			      msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
+	queue_delayed_work(iavf_wq, &adapter->init_task,
+			   msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
 
 	/* Setup the wait queue for indicating transition to down status */
 	init_waitqueue_head(&adapter->down_waitqueue);
@@ -3818,7 +3852,7 @@ static int iavf_resume(struct pci_dev *pdev)
 		return err;
 	}
 
-	schedule_work(&adapter->reset_task);
+	queue_work(iavf_wq, &adapter->reset_task);
 
 	netif_device_attach(netdev);
 
@@ -3878,8 +3912,7 @@ static void iavf_remove(struct pci_dev *pdev)
 	iavf_reset_interrupt_capability(adapter);
 	iavf_free_q_vectors(adapter);
 
-	if (adapter->watchdog_timer.function)
-		del_timer_sync(&adapter->watchdog_timer);
+	cancel_delayed_work_sync(&adapter->watchdog_task);
 
 	cancel_work_sync(&adapter->adminq_task);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_osdep.h b/drivers/net/ethernet/intel/iavf/iavf_osdep.h
index e6e0b0328706..a452ce90679a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_osdep.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_osdep.h
@@ -44,9 +44,12 @@ struct iavf_virt_mem {
 #define iavf_allocate_virt_mem(h, m, s) iavf_allocate_virt_mem_d(h, m, s)
 #define iavf_free_virt_mem(h, m) iavf_free_virt_mem_d(h, m)
 
-#define iavf_debug(h, m, s, ...)  iavf_debug_d(h, m, s, ##__VA_ARGS__)
-extern void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...)
-	__attribute__ ((format(gnu_printf, 3, 4)));
+#define iavf_debug(h, m, s, ...)				\
+do {								\
+	if (((m) & (h)->debug_mask))				\
+		pr_info("iavf %02x:%02x.%x " s,			\
+			(h)->bus.bus_id, (h)->bus.device,	\
+			(h)->bus.func, ##__VA_ARGS__);		\
+} while (0)
 
-typedef enum iavf_status_code iavf_status;
 #endif /* _IAVF_OSDEP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
index d6685103af39..edebfbbcffdc 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_prototype.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h
@@ -16,39 +16,40 @@
  */
 
 /* adminq functions */
-iavf_status iavf_init_adminq(struct iavf_hw *hw);
-iavf_status iavf_shutdown_adminq(struct iavf_hw *hw);
-void i40e_adminq_init_ring_data(struct iavf_hw *hw);
-iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
-				   struct i40e_arq_event_info *e,
-				   u16 *events_pending);
-iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc,
-				  void *buff, /* can be NULL */
-				  u16 buff_size,
-				  struct i40e_asq_cmd_details *cmd_details);
+enum iavf_status iavf_init_adminq(struct iavf_hw *hw);
+enum iavf_status iavf_shutdown_adminq(struct iavf_hw *hw);
+void iavf_adminq_init_ring_data(struct iavf_hw *hw);
+enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw,
+					struct iavf_arq_event_info *e,
+					u16 *events_pending);
+enum iavf_status iavf_asq_send_command(struct iavf_hw *hw,
+				       struct iavf_aq_desc *desc,
+				       void *buff, /* can be NULL */
+				       u16 buff_size,
+				       struct iavf_asq_cmd_details *cmd_details);
 bool iavf_asq_done(struct iavf_hw *hw);
 
 /* debug function for adminq */
 void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask,
 		   void *desc, void *buffer, u16 buf_len);
 
-void i40e_idle_aq(struct iavf_hw *hw);
+void iavf_idle_aq(struct iavf_hw *hw);
 void iavf_resume_aq(struct iavf_hw *hw);
 bool iavf_check_asq_alive(struct iavf_hw *hw);
-iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading);
-const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err);
-const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err);
+enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading);
+const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err);
+const char *iavf_stat_str(struct iavf_hw *hw, enum iavf_status stat_err);
 
-iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 seid,
-				bool pf_lut, u8 *lut, u16 lut_size);
-iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid,
-				bool pf_lut, u8 *lut, u16 lut_size);
-iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 seid,
-				struct i40e_aqc_get_set_rss_key_data *key);
-iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid,
-				struct i40e_aqc_get_set_rss_key_data *key);
+enum iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 seid,
+				     bool pf_lut, u8 *lut, u16 lut_size);
+enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid,
+				     bool pf_lut, u8 *lut, u16 lut_size);
+enum iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 seid,
+				     struct iavf_aqc_get_set_rss_key_data *key);
+enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid,
+				     struct iavf_aqc_get_set_rss_key_data *key);
 
-iavf_status iavf_set_mac_type(struct iavf_hw *hw);
+enum iavf_status iavf_set_mac_type(struct iavf_hw *hw);
 
 extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[];
 
@@ -59,9 +60,10 @@ static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype)
 
 void iavf_vf_parse_hw_config(struct iavf_hw *hw,
 			     struct virtchnl_vf_resource *msg);
-iavf_status iavf_vf_reset(struct iavf_hw *hw);
-iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
-				   enum virtchnl_ops v_opcode,
-				   iavf_status v_retval, u8 *msg, u16 msglen,
-				   struct i40e_asq_cmd_details *cmd_details);
+enum iavf_status iavf_vf_reset(struct iavf_hw *hw);
+enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
+					enum virtchnl_ops v_opcode,
+					enum iavf_status v_retval,
+					u8 *msg, u16 msglen,
+					struct iavf_asq_cmd_details *cmd_details);
 #endif /* _IAVF_PROTOTYPE_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_status.h b/drivers/net/ethernet/intel/iavf/iavf_status.h
index 46742fab7b8c..46e3d1f6b604 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_status.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_status.h
@@ -5,74 +5,74 @@
 #define _IAVF_STATUS_H_
 
 /* Error Codes */
-enum iavf_status_code {
-	I40E_SUCCESS				= 0,
-	I40E_ERR_NVM				= -1,
-	I40E_ERR_NVM_CHECKSUM			= -2,
-	I40E_ERR_PHY				= -3,
-	I40E_ERR_CONFIG				= -4,
-	I40E_ERR_PARAM				= -5,
-	I40E_ERR_MAC_TYPE			= -6,
-	I40E_ERR_UNKNOWN_PHY			= -7,
-	I40E_ERR_LINK_SETUP			= -8,
-	I40E_ERR_ADAPTER_STOPPED		= -9,
-	I40E_ERR_INVALID_MAC_ADDR		= -10,
-	I40E_ERR_DEVICE_NOT_SUPPORTED		= -11,
-	I40E_ERR_MASTER_REQUESTS_PENDING	= -12,
-	I40E_ERR_INVALID_LINK_SETTINGS		= -13,
-	I40E_ERR_AUTONEG_NOT_COMPLETE		= -14,
-	I40E_ERR_RESET_FAILED			= -15,
-	I40E_ERR_SWFW_SYNC			= -16,
-	I40E_ERR_NO_AVAILABLE_VSI		= -17,
-	I40E_ERR_NO_MEMORY			= -18,
-	I40E_ERR_BAD_PTR			= -19,
-	I40E_ERR_RING_FULL			= -20,
-	I40E_ERR_INVALID_PD_ID			= -21,
-	I40E_ERR_INVALID_QP_ID			= -22,
-	I40E_ERR_INVALID_CQ_ID			= -23,
-	I40E_ERR_INVALID_CEQ_ID			= -24,
-	I40E_ERR_INVALID_AEQ_ID			= -25,
-	I40E_ERR_INVALID_SIZE			= -26,
-	I40E_ERR_INVALID_ARP_INDEX		= -27,
-	I40E_ERR_INVALID_FPM_FUNC_ID		= -28,
-	I40E_ERR_QP_INVALID_MSG_SIZE		= -29,
-	I40E_ERR_QP_TOOMANY_WRS_POSTED		= -30,
-	I40E_ERR_INVALID_FRAG_COUNT		= -31,
-	I40E_ERR_QUEUE_EMPTY			= -32,
-	I40E_ERR_INVALID_ALIGNMENT		= -33,
-	I40E_ERR_FLUSHED_QUEUE			= -34,
-	I40E_ERR_INVALID_PUSH_PAGE_INDEX	= -35,
-	I40E_ERR_INVALID_IMM_DATA_SIZE		= -36,
-	I40E_ERR_TIMEOUT			= -37,
-	I40E_ERR_OPCODE_MISMATCH		= -38,
-	I40E_ERR_CQP_COMPL_ERROR		= -39,
-	I40E_ERR_INVALID_VF_ID			= -40,
-	I40E_ERR_INVALID_HMCFN_ID		= -41,
-	I40E_ERR_BACKING_PAGE_ERROR		= -42,
-	I40E_ERR_NO_PBLCHUNKS_AVAILABLE		= -43,
-	I40E_ERR_INVALID_PBLE_INDEX		= -44,
-	I40E_ERR_INVALID_SD_INDEX		= -45,
-	I40E_ERR_INVALID_PAGE_DESC_INDEX	= -46,
-	I40E_ERR_INVALID_SD_TYPE		= -47,
-	I40E_ERR_MEMCPY_FAILED			= -48,
-	I40E_ERR_INVALID_HMC_OBJ_INDEX		= -49,
-	I40E_ERR_INVALID_HMC_OBJ_COUNT		= -50,
-	I40E_ERR_INVALID_SRQ_ARM_LIMIT		= -51,
-	I40E_ERR_SRQ_ENABLED			= -52,
-	I40E_ERR_ADMIN_QUEUE_ERROR		= -53,
-	I40E_ERR_ADMIN_QUEUE_TIMEOUT		= -54,
-	I40E_ERR_BUF_TOO_SHORT			= -55,
-	I40E_ERR_ADMIN_QUEUE_FULL		= -56,
-	I40E_ERR_ADMIN_QUEUE_NO_WORK		= -57,
-	I40E_ERR_BAD_IWARP_CQE			= -58,
-	I40E_ERR_NVM_BLANK_MODE			= -59,
-	I40E_ERR_NOT_IMPLEMENTED		= -60,
-	I40E_ERR_PE_DOORBELL_NOT_ENABLED	= -61,
-	I40E_ERR_DIAG_TEST_FAILED		= -62,
-	I40E_ERR_NOT_READY			= -63,
-	I40E_NOT_SUPPORTED			= -64,
-	I40E_ERR_FIRMWARE_API_VERSION		= -65,
-	I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR	= -66,
+enum iavf_status {
+	IAVF_SUCCESS				= 0,
+	IAVF_ERR_NVM				= -1,
+	IAVF_ERR_NVM_CHECKSUM			= -2,
+	IAVF_ERR_PHY				= -3,
+	IAVF_ERR_CONFIG				= -4,
+	IAVF_ERR_PARAM				= -5,
+	IAVF_ERR_MAC_TYPE			= -6,
+	IAVF_ERR_UNKNOWN_PHY			= -7,
+	IAVF_ERR_LINK_SETUP			= -8,
+	IAVF_ERR_ADAPTER_STOPPED		= -9,
+	IAVF_ERR_INVALID_MAC_ADDR		= -10,
+	IAVF_ERR_DEVICE_NOT_SUPPORTED		= -11,
+	IAVF_ERR_MASTER_REQUESTS_PENDING	= -12,
+	IAVF_ERR_INVALID_LINK_SETTINGS		= -13,
+	IAVF_ERR_AUTONEG_NOT_COMPLETE		= -14,
+	IAVF_ERR_RESET_FAILED			= -15,
+	IAVF_ERR_SWFW_SYNC			= -16,
+	IAVF_ERR_NO_AVAILABLE_VSI		= -17,
+	IAVF_ERR_NO_MEMORY			= -18,
+	IAVF_ERR_BAD_PTR			= -19,
+	IAVF_ERR_RING_FULL			= -20,
+	IAVF_ERR_INVALID_PD_ID			= -21,
+	IAVF_ERR_INVALID_QP_ID			= -22,
+	IAVF_ERR_INVALID_CQ_ID			= -23,
+	IAVF_ERR_INVALID_CEQ_ID			= -24,
+	IAVF_ERR_INVALID_AEQ_ID			= -25,
+	IAVF_ERR_INVALID_SIZE			= -26,
+	IAVF_ERR_INVALID_ARP_INDEX		= -27,
+	IAVF_ERR_INVALID_FPM_FUNC_ID		= -28,
+	IAVF_ERR_QP_INVALID_MSG_SIZE		= -29,
+	IAVF_ERR_QP_TOOMANY_WRS_POSTED		= -30,
+	IAVF_ERR_INVALID_FRAG_COUNT		= -31,
+	IAVF_ERR_QUEUE_EMPTY			= -32,
+	IAVF_ERR_INVALID_ALIGNMENT		= -33,
+	IAVF_ERR_FLUSHED_QUEUE			= -34,
+	IAVF_ERR_INVALID_PUSH_PAGE_INDEX	= -35,
+	IAVF_ERR_INVALID_IMM_DATA_SIZE		= -36,
+	IAVF_ERR_TIMEOUT			= -37,
+	IAVF_ERR_OPCODE_MISMATCH		= -38,
+	IAVF_ERR_CQP_COMPL_ERROR		= -39,
+	IAVF_ERR_INVALID_VF_ID			= -40,
+	IAVF_ERR_INVALID_HMCFN_ID		= -41,
+	IAVF_ERR_BACKING_PAGE_ERROR		= -42,
+	IAVF_ERR_NO_PBLCHUNKS_AVAILABLE		= -43,
+	IAVF_ERR_INVALID_PBLE_INDEX		= -44,
+	IAVF_ERR_INVALID_SD_INDEX		= -45,
+	IAVF_ERR_INVALID_PAGE_DESC_INDEX	= -46,
+	IAVF_ERR_INVALID_SD_TYPE		= -47,
+	IAVF_ERR_MEMCPY_FAILED			= -48,
+	IAVF_ERR_INVALID_HMC_OBJ_INDEX		= -49,
+	IAVF_ERR_INVALID_HMC_OBJ_COUNT		= -50,
+	IAVF_ERR_INVALID_SRQ_ARM_LIMIT		= -51,
+	IAVF_ERR_SRQ_ENABLED			= -52,
+	IAVF_ERR_ADMIN_QUEUE_ERROR		= -53,
+	IAVF_ERR_ADMIN_QUEUE_TIMEOUT		= -54,
+	IAVF_ERR_BUF_TOO_SHORT			= -55,
+	IAVF_ERR_ADMIN_QUEUE_FULL		= -56,
+	IAVF_ERR_ADMIN_QUEUE_NO_WORK		= -57,
+	IAVF_ERR_BAD_IWARP_CQE			= -58,
+	IAVF_ERR_NVM_BLANK_MODE			= -59,
+	IAVF_ERR_NOT_IMPLEMENTED		= -60,
+	IAVF_ERR_PE_DOORBELL_NOT_ENABLED	= -61,
+	IAVF_ERR_DIAG_TEST_FAILED		= -62,
+	IAVF_ERR_NOT_READY			= -63,
+	IAVF_NOT_SUPPORTED			= -64,
+	IAVF_ERR_FIRMWARE_API_VERSION		= -65,
+	IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR	= -66,
 };
 
 #endif /* _IAVF_STATUS_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h
index 1474f5539751..1058e68a02b4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_trace.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h
@@ -17,8 +17,8 @@
 /* See trace-events-sample.h for a detailed description of why this
  * guard clause is different from most normal include files.
  */
-#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
-#define _I40E_TRACE_H_
+#if !defined(_IAVF_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _IAVF_TRACE_H_
 
 #include <linux/tracepoint.h>
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 9b4d7cec2e18..0cca1b589b56 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -190,7 +190,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi)
 static bool iavf_clean_tx_irq(struct iavf_vsi *vsi,
 			      struct iavf_ring *tx_ring, int napi_budget)
 {
-	u16 i = tx_ring->next_to_clean;
+	int i = tx_ring->next_to_clean;
 	struct iavf_tx_buffer *tx_buf;
 	struct iavf_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
@@ -379,19 +379,19 @@ static inline unsigned int iavf_itr_divisor(struct iavf_q_vector *q_vector)
 	unsigned int divisor;
 
 	switch (q_vector->adapter->link_speed) {
-	case I40E_LINK_SPEED_40GB:
+	case IAVF_LINK_SPEED_40GB:
 		divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 1024;
 		break;
-	case I40E_LINK_SPEED_25GB:
-	case I40E_LINK_SPEED_20GB:
+	case IAVF_LINK_SPEED_25GB:
+	case IAVF_LINK_SPEED_20GB:
 		divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 512;
 		break;
 	default:
-	case I40E_LINK_SPEED_10GB:
+	case IAVF_LINK_SPEED_10GB:
 		divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 256;
 		break;
-	case I40E_LINK_SPEED_1GB:
-	case I40E_LINK_SPEED_100MB:
+	case IAVF_LINK_SPEED_1GB:
+	case IAVF_LINK_SPEED_100MB:
 		divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 32;
 		break;
 	}
@@ -1236,6 +1236,9 @@ static void iavf_add_rx_frag(struct iavf_ring *rx_ring,
 	unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring));
 #endif
 
+	if (!size)
+		return;
+
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
 			rx_buffer->page_offset, size, truesize);
 
@@ -1260,6 +1263,9 @@ static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring,
 {
 	struct iavf_rx_buffer *rx_buffer;
 
+	if (!size)
+		return NULL;
+
 	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
 	prefetchw(rx_buffer->page);
 
@@ -1290,7 +1296,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
 					  struct iavf_rx_buffer *rx_buffer,
 					  unsigned int size)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+	void *va;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
 #else
@@ -1299,7 +1305,10 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
 	unsigned int headlen;
 	struct sk_buff *skb;
 
+	if (!rx_buffer)
+		return NULL;
 	/* prefetch first cache line of first page */
+	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
 	prefetch(va);
 #if L1_CACHE_BYTES < 128
 	prefetch(va + L1_CACHE_BYTES);
@@ -1315,7 +1324,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IAVF_RX_HDR_SIZE)
-		headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
@@ -1354,7 +1363,7 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
 				      struct iavf_rx_buffer *rx_buffer,
 				      unsigned int size)
 {
-	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+	void *va;
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2;
 #else
@@ -1363,7 +1372,10 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
 #endif
 	struct sk_buff *skb;
 
+	if (!rx_buffer)
+		return NULL;
 	/* prefetch first cache line of first page */
+	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
 	prefetch(va);
 #if L1_CACHE_BYTES < 128
 	prefetch(va + L1_CACHE_BYTES);
@@ -1398,6 +1410,9 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
 static void iavf_put_rx_buffer(struct iavf_ring *rx_ring,
 			       struct iavf_rx_buffer *rx_buffer)
 {
+	if (!rx_buffer)
+		return;
+
 	if (iavf_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		iavf_reuse_rx_page(rx_ring, rx_buffer);
@@ -1496,11 +1511,12 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
+#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT)
+		if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
+			break;
 
 		size = (qword & IAVF_RXD_QW1_LENGTH_PBUF_MASK) >>
 		       IAVF_RXD_QW1_LENGTH_PBUF_SHIFT;
-		if (!size)
-			break;
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 		rx_buffer = iavf_get_rx_buffer(rx_ring, size);
@@ -1516,7 +1532,8 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buff_failed++;
-			rx_buffer->pagecnt_bias++;
+			if (rx_buffer)
+				rx_buffer->pagecnt_bias++;
 			break;
 		}
 
@@ -2358,13 +2375,8 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index ca89583613fb..7190a40c540c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -7,7 +7,7 @@
 #include "iavf_status.h"
 #include "iavf_osdep.h"
 #include "iavf_register.h"
-#include "i40e_adminq.h"
+#include "iavf_adminq.h"
 #include "iavf_devids.h"
 
 #define IAVF_RXQ_CTX_DBUFF_SHIFT 7
@@ -21,7 +21,7 @@
 
 /* forward declaration */
 struct iavf_hw;
-typedef void (*I40E_ADMINQ_CALLBACK)(struct iavf_hw *, struct i40e_aq_desc *);
+typedef void (*IAVF_ADMINQ_CALLBACK)(struct iavf_hw *, struct iavf_aq_desc *);
 
 /* Data type manipulation macros. */
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index e64751da0921..d49d58a6de80 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -22,7 +22,7 @@ static int iavf_send_pf_msg(struct iavf_adapter *adapter,
 			    enum virtchnl_ops op, u8 *msg, u16 len)
 {
 	struct iavf_hw *hw = &adapter->hw;
-	iavf_status err;
+	enum iavf_status err;
 
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
 		return 0; /* nothing to see here, move along */
@@ -41,7 +41,7 @@ static int iavf_send_pf_msg(struct iavf_adapter *adapter,
  *
  * Send API version admin queue message to the PF. The reply is not checked
  * in this function. Returns 0 if the message was successfully
- * sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not.
+ * sent, or one of the IAVF_ADMIN_QUEUE_ERROR_ statuses if not.
  **/
 int iavf_send_api_ver(struct iavf_adapter *adapter)
 {
@@ -60,16 +60,16 @@ int iavf_send_api_ver(struct iavf_adapter *adapter)
  *
  * Compare API versions with the PF. Must be called after admin queue is
  * initialized. Returns 0 if API versions match, -EIO if they do not,
- * I40E_ERR_ADMIN_QUEUE_NO_WORK if the admin queue is empty, and any errors
+ * IAVF_ERR_ADMIN_QUEUE_NO_WORK if the admin queue is empty, and any errors
  * from the firmware are propagated.
  **/
 int iavf_verify_api_ver(struct iavf_adapter *adapter)
 {
 	struct virtchnl_version_info *pf_vvi;
 	struct iavf_hw *hw = &adapter->hw;
-	struct i40e_arq_event_info event;
+	struct iavf_arq_event_info event;
 	enum virtchnl_ops op;
-	iavf_status err;
+	enum iavf_status err;
 
 	event.buf_len = IAVF_MAX_AQ_BUF_SIZE;
 	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
@@ -92,7 +92,7 @@ int iavf_verify_api_ver(struct iavf_adapter *adapter)
 	}
 
 
-	err = (iavf_status)le32_to_cpu(event.desc.cookie_low);
+	err = (enum iavf_status)le32_to_cpu(event.desc.cookie_low);
 	if (err)
 		goto out_alloc;
 
@@ -123,7 +123,7 @@ out:
  *
  * Send VF configuration request admin queue message to the PF. The reply
  * is not checked in this function. Returns 0 if the message was
- * successfully sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not.
+ * successfully sent, or one of the IAVF_ADMIN_QUEUE_ERROR_ statuses if not.
  **/
 int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
 {
@@ -189,9 +189,9 @@ static void iavf_validate_num_queues(struct iavf_adapter *adapter)
 int iavf_get_vf_config(struct iavf_adapter *adapter)
 {
 	struct iavf_hw *hw = &adapter->hw;
-	struct i40e_arq_event_info event;
+	struct iavf_arq_event_info event;
 	enum virtchnl_ops op;
-	iavf_status err;
+	enum iavf_status err;
 	u16 len;
 
 	len =  sizeof(struct virtchnl_vf_resource) +
@@ -216,7 +216,7 @@ int iavf_get_vf_config(struct iavf_adapter *adapter)
 			break;
 	}
 
-	err = (iavf_status)le32_to_cpu(event.desc.cookie_low);
+	err = (enum iavf_status)le32_to_cpu(event.desc.cookie_low);
 	memcpy(adapter->vf_res, event.msg_buf, min(event.msg_len, len));
 
 	/* some PFs send more queues than we should have so validate that
@@ -242,7 +242,8 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	struct virtchnl_vsi_queue_config_info *vqci;
 	struct virtchnl_queue_pair_info *vqpi;
 	int pairs = adapter->num_active_queues;
-	int i, len, max_frame = IAVF_MAX_RXBUFFER;
+	int i, max_frame = IAVF_MAX_RXBUFFER;
+	size_t len;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -251,8 +252,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		return;
 	}
 	adapter->current_op = VIRTCHNL_OP_CONFIG_VSI_QUEUES;
-	len = sizeof(struct virtchnl_vsi_queue_config_info) +
-		       (sizeof(struct virtchnl_queue_pair_info) * pairs);
+	len = struct_size(vqci, qpair, pairs);
 	vqci = kzalloc(len, GFP_KERNEL);
 	if (!vqci)
 		return;
@@ -351,8 +351,9 @@ void iavf_map_queues(struct iavf_adapter *adapter)
 {
 	struct virtchnl_irq_map_info *vimi;
 	struct virtchnl_vector_map *vecmap;
-	int v_idx, q_vectors, len;
 	struct iavf_q_vector *q_vector;
+	int v_idx, q_vectors;
+	size_t len;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -364,9 +365,7 @@ void iavf_map_queues(struct iavf_adapter *adapter)
 
 	q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
-	len = sizeof(struct virtchnl_irq_map_info) +
-	      (adapter->num_msix_vectors *
-		sizeof(struct virtchnl_vector_map));
+	len = struct_size(vimi, vecmap, adapter->num_msix_vectors);
 	vimi = kzalloc(len, GFP_KERNEL);
 	if (!vimi)
 		return;
@@ -416,7 +415,7 @@ int iavf_request_queues(struct iavf_adapter *adapter, int num)
 		return -EBUSY;
 	}
 
-	vfres.num_queue_pairs = num;
+	vfres.num_queue_pairs = min_t(int, num, num_online_cpus());
 
 	adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES;
 	adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
@@ -433,9 +432,10 @@ int iavf_request_queues(struct iavf_adapter *adapter, int num)
 void iavf_add_ether_addrs(struct iavf_adapter *adapter)
 {
 	struct virtchnl_ether_addr_list *veal;
-	int len, i = 0, count = 0;
 	struct iavf_mac_filter *f;
+	int i = 0, count = 0;
 	bool more = false;
+	size_t len;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -457,15 +457,13 @@ void iavf_add_ether_addrs(struct iavf_adapter *adapter)
 	}
 	adapter->current_op = VIRTCHNL_OP_ADD_ETH_ADDR;
 
-	len = sizeof(struct virtchnl_ether_addr_list) +
-	      (count * sizeof(struct virtchnl_ether_addr));
+	len = struct_size(veal, list, count);
 	if (len > IAVF_MAX_AQ_BUF_SIZE) {
 		dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n");
 		count = (IAVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct virtchnl_ether_addr_list)) /
 			sizeof(struct virtchnl_ether_addr);
-		len = sizeof(struct virtchnl_ether_addr_list) +
-		      (count * sizeof(struct virtchnl_ether_addr));
+		len = struct_size(veal, list, count);
 		more = true;
 	}
 
@@ -505,8 +503,9 @@ void iavf_del_ether_addrs(struct iavf_adapter *adapter)
 {
 	struct virtchnl_ether_addr_list *veal;
 	struct iavf_mac_filter *f, *ftmp;
-	int len, i = 0, count = 0;
+	int i = 0, count = 0;
 	bool more = false;
+	size_t len;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -528,15 +527,13 @@ void iavf_del_ether_addrs(struct iavf_adapter *adapter)
 	}
 	adapter->current_op = VIRTCHNL_OP_DEL_ETH_ADDR;
 
-	len = sizeof(struct virtchnl_ether_addr_list) +
-	      (count * sizeof(struct virtchnl_ether_addr));
+	len = struct_size(veal, list, count);
 	if (len > IAVF_MAX_AQ_BUF_SIZE) {
 		dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n");
 		count = (IAVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct virtchnl_ether_addr_list)) /
 			sizeof(struct virtchnl_ether_addr);
-		len = sizeof(struct virtchnl_ether_addr_list) +
-		      (count * sizeof(struct virtchnl_ether_addr));
+		len = struct_size(veal, list, count);
 		more = true;
 	}
 	veal = kzalloc(len, GFP_ATOMIC);
@@ -938,22 +935,22 @@ static void iavf_print_link_message(struct iavf_adapter *adapter)
 	}
 
 	switch (adapter->link_speed) {
-	case I40E_LINK_SPEED_40GB:
+	case IAVF_LINK_SPEED_40GB:
 		speed = "40 G";
 		break;
-	case I40E_LINK_SPEED_25GB:
+	case IAVF_LINK_SPEED_25GB:
 		speed = "25 G";
 		break;
-	case I40E_LINK_SPEED_20GB:
+	case IAVF_LINK_SPEED_20GB:
 		speed = "20 G";
 		break;
-	case I40E_LINK_SPEED_10GB:
+	case IAVF_LINK_SPEED_10GB:
 		speed = "10 G";
 		break;
-	case I40E_LINK_SPEED_1GB:
+	case IAVF_LINK_SPEED_1GB:
 		speed = "1000 M";
 		break;
-	case I40E_LINK_SPEED_100MB:
+	case IAVF_LINK_SPEED_100MB:
 		speed = "100 M";
 		break;
 	default:
@@ -973,7 +970,7 @@ static void iavf_print_link_message(struct iavf_adapter *adapter)
 void iavf_enable_channels(struct iavf_adapter *adapter)
 {
 	struct virtchnl_tc_info *vti = NULL;
-	u16 len;
+	size_t len;
 	int i;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
@@ -983,9 +980,7 @@ void iavf_enable_channels(struct iavf_adapter *adapter)
 		return;
 	}
 
-	len = (adapter->num_tc * sizeof(struct virtchnl_channel_info)) +
-	       sizeof(struct virtchnl_tc_info);
-
+	len = struct_size(vti, list, adapter->num_tc - 1);
 	vti = kzalloc(len, GFP_KERNEL);
 	if (!vti)
 		return;
@@ -1184,8 +1179,8 @@ void iavf_request_reset(struct iavf_adapter *adapter)
  * This function handles the reply messages.
  **/
 void iavf_virtchnl_completion(struct iavf_adapter *adapter,
-			      enum virtchnl_ops v_opcode, iavf_status v_retval,
-			      u8 *msg, u16 msglen)
+			      enum virtchnl_ops v_opcode,
+			      enum iavf_status v_retval, u8 *msg, u16 msglen)
 {
 	struct net_device *netdev = adapter->netdev;
 
@@ -1238,7 +1233,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 			if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) {
 				adapter->flags |= IAVF_FLAG_RESET_PENDING;
 				dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
-				schedule_work(&adapter->reset_task);
+				queue_work(iavf_wq, &adapter->reset_task);
 			}
 			break;
 		default:
diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index e5d6f684437e..2d140ba83781 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -17,3 +17,4 @@ ice-y := ice_main.o	\
 	 ice_txrx.o	\
 	 ice_ethtool.o
 ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o
+ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_lib.o
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index a385575600f6..9ee6b55553c0 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -26,6 +26,7 @@
 #include <linux/bitmap.h>
 #include <linux/log2.h>
 #include <linux/ip.h>
+#include <linux/sctp.h>
 #include <linux/ipv6.h>
 #include <linux/if_bridge.h>
 #include <linux/avf/virtchnl.h>
@@ -33,6 +34,7 @@
 #include "ice_devids.h"
 #include "ice_type.h"
 #include "ice_txrx.h"
+#include "ice_dcb.h"
 #include "ice_switch.h"
 #include "ice_common.h"
 #include "ice_sched.h"
@@ -41,10 +43,28 @@
 
 extern const char ice_drv_ver[];
 #define ICE_BAR0		0
-#define ICE_DFLT_NUM_DESC	128
 #define ICE_REQ_DESC_MULTIPLE	32
-#define ICE_MIN_NUM_DESC	ICE_REQ_DESC_MULTIPLE
+#define ICE_MIN_NUM_DESC	64
 #define ICE_MAX_NUM_DESC	8160
+#define ICE_DFLT_MIN_RX_DESC	512
+/* if the default number of Rx descriptors between ICE_MAX_NUM_DESC and the
+ * number of descriptors to fill up an entire page is greater than or equal to
+ * ICE_DFLT_MIN_RX_DESC set it based on page size, otherwise set it to
+ * ICE_DFLT_MIN_RX_DESC
+ */
+#define ICE_DFLT_NUM_RX_DESC \
+	min_t(u16, ICE_MAX_NUM_DESC, \
+	      max_t(u16, ALIGN(PAGE_SIZE / sizeof(union ice_32byte_rx_desc), \
+			       ICE_REQ_DESC_MULTIPLE), \
+		    ICE_DFLT_MIN_RX_DESC))
+/* set default number of Tx descriptors to the minimum between ICE_MAX_NUM_DESC
+ * and the number of descriptors to fill up an entire page
+ */
+#define ICE_DFLT_NUM_TX_DESC	min_t(u16, ICE_MAX_NUM_DESC, \
+				      ALIGN(PAGE_SIZE / \
+					    sizeof(struct ice_tx_desc), \
+					    ICE_REQ_DESC_MULTIPLE))
+
 #define ICE_DFLT_TRAFFIC_CLASS	BIT(0)
 #define ICE_INT_NAME_STR_LEN	(IFNAMSIZ + 16)
 #define ICE_ETHTOOL_FWVER_LEN	32
@@ -70,6 +90,8 @@ extern const char ice_drv_ver[];
 #define ICE_MAX_QS_PER_VF		256
 #define ICE_MIN_QS_PER_VF		1
 #define ICE_DFLT_QS_PER_VF		4
+#define ICE_NONQ_VECS_VF		1
+#define ICE_MAX_SCATTER_QS_PER_VF	16
 #define ICE_MAX_BASE_QS_PER_VF		16
 #define ICE_MAX_INTR_PER_VF		65
 #define ICE_MIN_INTR_PER_VF		(ICE_MIN_QS_PER_VF + 1)
@@ -82,7 +104,7 @@ extern const char ice_drv_ver[];
 #define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
 
 #define ICE_MAX_MTU	(ICE_AQ_SET_MAC_FRAME_SIZE_MAX - \
-			 ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN)
+			(ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)))
 
 #define ICE_UP_TABLE_TRANSLATE(val, i) \
 		(((val) << ICE_AQ_VSI_UP_TABLE_UP##i##_S) & \
@@ -110,6 +132,26 @@ extern const char ice_drv_ver[];
 #define ice_for_each_alloc_rxq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->alloc_rxq; (i)++)
 
+#define ice_for_each_q_vector(vsi, i) \
+	for ((i) = 0; (i) < (vsi)->num_q_vectors; (i)++)
+
+#define ICE_UCAST_PROMISC_BITS (ICE_PROMISC_UCAST_TX | ICE_PROMISC_MCAST_TX | \
+				ICE_PROMISC_UCAST_RX | ICE_PROMISC_MCAST_RX)
+
+#define ICE_UCAST_VLAN_PROMISC_BITS (ICE_PROMISC_UCAST_TX | \
+				     ICE_PROMISC_MCAST_TX | \
+				     ICE_PROMISC_UCAST_RX | \
+				     ICE_PROMISC_MCAST_RX | \
+				     ICE_PROMISC_VLAN_TX  | \
+				     ICE_PROMISC_VLAN_RX)
+
+#define ICE_MCAST_PROMISC_BITS (ICE_PROMISC_MCAST_TX | ICE_PROMISC_MCAST_RX)
+
+#define ICE_MCAST_VLAN_PROMISC_BITS (ICE_PROMISC_MCAST_TX | \
+				     ICE_PROMISC_MCAST_RX | \
+				     ICE_PROMISC_VLAN_TX  | \
+				     ICE_PROMISC_VLAN_RX)
+
 struct ice_tc_info {
 	u16 qoffset;
 	u16 qcount_tx;
@@ -119,16 +161,27 @@ struct ice_tc_info {
 
 struct ice_tc_cfg {
 	u8 numtc; /* Total number of enabled TCs */
-	u8 ena_tc; /* TX map */
+	u8 ena_tc; /* Tx map */
 	struct ice_tc_info tc_info[ICE_MAX_TRAFFIC_CLASS];
 };
 
 struct ice_res_tracker {
 	u16 num_entries;
-	u16 search_hint;
+	u16 end;
 	u16 list[1];
 };
 
+struct ice_qs_cfg {
+	struct mutex *qs_mutex;  /* will be assigned to &pf->avail_q_mutex */
+	unsigned long *pf_map;
+	unsigned long pf_map_size;
+	unsigned int q_count;
+	unsigned int scatter_count;
+	u16 *vsi_map;
+	u16 vsi_map_offset;
+	u8 mapping_mode;
+};
+
 struct ice_sw {
 	struct ice_pf *pf;
 	u16 sw_id;		/* switch ID for this switch */
@@ -136,6 +189,7 @@ struct ice_sw {
 };
 
 enum ice_state {
+	__ICE_TESTING,
 	__ICE_DOWN,
 	__ICE_NEEDS_RESTART,
 	__ICE_PREPARED_FOR_RESET,	/* set by driver when prepared */
@@ -198,8 +252,7 @@ struct ice_vsi {
 	u32 rx_buf_failed;
 	u32 rx_page_failed;
 	int num_q_vectors;
-	int sw_base_vector;		/* Irq base for OS reserved vectors */
-	int hw_base_vector;		/* HW (absolute) index of a vector */
+	int base_vector;		/* IRQ base for OS reserved vectors */
 	enum ice_vsi_type type;
 	u16 vsi_num;			/* HW (absolute) index of this VSI */
 	u16 idx;			/* software index in pf->vsi[] */
@@ -209,6 +262,8 @@ struct ice_vsi {
 
 	s16 vf_id;			/* VF ID for SR-IOV VSIs */
 
+	u16 ethtype;			/* Ethernet protocol for pause frame */
+
 	/* RSS config */
 	u16 rss_table_size;	/* HW RSS table size */
 	u16 rss_size;		/* Allocated RSS queues */
@@ -229,9 +284,10 @@ struct ice_vsi {
 	struct list_head tmp_sync_list;		/* MAC filters to be synced */
 	struct list_head tmp_unsync_list;	/* MAC filters to be unsynced */
 
-	u8 irqs_ready;
-	u8 current_isup;		 /* Sync 'link up' logging */
-	u8 stat_offsets_loaded;
+	u8 irqs_ready:1;
+	u8 current_isup:1;		 /* Sync 'link up' logging */
+	u8 stat_offsets_loaded:1;
+	u8 vlan_ena:1;
 
 	/* queue information */
 	u8 tx_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
@@ -242,26 +298,34 @@ struct ice_vsi {
 	u16 num_txq;			 /* Used Tx queues */
 	u16 alloc_rxq;			 /* Allocated Rx queues */
 	u16 num_rxq;			 /* Used Rx queues */
-	u16 num_desc;
+	u16 num_rx_desc;
+	u16 num_tx_desc;
 	struct ice_tc_cfg tc_cfg;
 } ____cacheline_internodealigned_in_smp;
 
 /* struct that defines an interrupt vector */
 struct ice_q_vector {
 	struct ice_vsi *vsi;
-	cpumask_t affinity_mask;
-	struct napi_struct napi;
-	struct ice_ring_container rx;
-	struct ice_ring_container tx;
-	struct irq_affinity_notify affinity_notify;
+
 	u16 v_idx;			/* index in the vsi->q_vector array. */
-	u8 num_ring_tx;			/* total number of Tx rings in vector */
+	u16 reg_idx;
 	u8 num_ring_rx;			/* total number of Rx rings in vector */
-	char name[ICE_INT_NAME_STR_LEN];
+	u8 num_ring_tx;			/* total number of Tx rings in vector */
+	u8 itr_countdown;		/* when 0 should adjust adaptive ITR */
 	/* in usecs, need to use ice_intrl_to_usecs_reg() before writing this
 	 * value to the device
 	 */
 	u8 intrl;
+
+	struct napi_struct napi;
+
+	struct ice_ring_container rx;
+	struct ice_ring_container tx;
+
+	cpumask_t affinity_mask;
+	struct irq_affinity_notify affinity_notify;
+
+	char name[ICE_INT_NAME_STR_LEN];
 } ____cacheline_internodealigned_in_smp;
 
 enum ice_pf_flags {
@@ -270,6 +334,11 @@ enum ice_pf_flags {
 	ICE_FLAG_RSS_ENA,
 	ICE_FLAG_SRIOV_ENA,
 	ICE_FLAG_SRIOV_CAPABLE,
+	ICE_FLAG_DCB_CAPABLE,
+	ICE_FLAG_DCB_ENA,
+	ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA,
+	ICE_FLAG_ENABLE_FW_LLDP,
+	ICE_FLAG_ETHTOOL_CTXT,		/* set when ethtool holds RTNL lock */
 	ICE_PF_FLAGS_NBITS		/* must be last */
 };
 
@@ -278,10 +347,12 @@ struct ice_pf {
 
 	/* OS reserved IRQ details */
 	struct msix_entry *msix_entries;
-	struct ice_res_tracker *sw_irq_tracker;
-
-	/* HW reserved Interrupts for this PF */
-	struct ice_res_tracker *hw_irq_tracker;
+	struct ice_res_tracker *irq_tracker;
+	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
+	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
+	 * MSIX vectors allowed on this PF.
+	 */
+	u16 sriov_base_vector;
 
 	struct ice_vsi **vsi;		/* VSIs created by the driver */
 	struct ice_sw *first_sw;	/* first switch created by firmware */
@@ -303,13 +374,11 @@ struct ice_pf {
 	struct mutex sw_mutex;		/* lock for protecting VSI alloc flow */
 	u32 msg_enable;
 	u32 hw_csum_rx_error;
-	u32 sw_oicr_idx;	/* Other interrupt cause SW vector index */
+	u32 oicr_idx;		/* Other interrupt cause MSIX vector index */
 	u32 num_avail_sw_msix;	/* remaining MSIX SW vectors left unclaimed */
-	u32 hw_oicr_idx;	/* Other interrupt cause vector HW index */
-	u32 num_avail_hw_msix;	/* remaining HW MSIX vectors left unclaimed */
 	u32 num_lan_msix;	/* Total MSIX vectors for base driver */
-	u16 num_lan_tx;		/* num lan Tx queues setup */
-	u16 num_lan_rx;		/* num lan Rx queues setup */
+	u16 num_lan_tx;		/* num LAN Tx queues setup */
+	u16 num_lan_rx;		/* num LAN Rx queues setup */
 	u16 q_left_tx;		/* remaining num Tx queues left unclaimed */
 	u16 q_left_rx;		/* remaining num Rx queues left unclaimed */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
@@ -322,11 +391,15 @@ struct ice_pf {
 	struct ice_hw_port_stats stats;
 	struct ice_hw_port_stats stats_prev;
 	struct ice_hw hw;
-	u8 stat_prev_loaded;	/* has previous stats been loaded */
+	u8 stat_prev_loaded:1; /* has previous stats been loaded */
+#ifdef CONFIG_DCB
+	u16 dcbx_cap;
+#endif /* CONFIG_DCB */
 	u32 tx_timeout_count;
 	unsigned long tx_timeout_last_recovery;
 	u32 tx_timeout_recovery_level;
 	char int_name[ICE_INT_NAME_STR_LEN];
+	u32 sw_int_count;
 };
 
 struct ice_netdev_priv {
@@ -335,15 +408,16 @@ struct ice_netdev_priv {
 
 /**
  * ice_irq_dynamic_ena - Enable default interrupt generation settings
- * @hw: pointer to hw struct
- * @vsi: pointer to vsi struct, can be NULL
+ * @hw: pointer to HW struct
+ * @vsi: pointer to VSI struct, can be NULL
  * @q_vector: pointer to q_vector, can be NULL
  */
-static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
-				       struct ice_q_vector *q_vector)
+static inline void
+ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
+		    struct ice_q_vector *q_vector)
 {
-	u32 vector = (vsi && q_vector) ? vsi->hw_base_vector + q_vector->v_idx :
-				((struct ice_pf *)hw->back)->hw_oicr_idx;
+	u32 vector = (vsi && q_vector) ? q_vector->reg_idx :
+				((struct ice_pf *)hw->back)->oicr_idx;
 	int itr = ICE_ITR_NONE;
 	u32 val;
 
@@ -358,19 +432,42 @@ static inline void ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi,
 	wr32(hw, GLINT_DYN_CTL(vector), val);
 }
 
-static inline void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
+/**
+ * ice_find_vsi_by_type - Find and return VSI of a given type
+ * @pf: PF to search for VSI
+ * @type: Value indicating type of VSI we are looking for
+ */
+static inline struct ice_vsi *
+ice_find_vsi_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 {
-	vsi->tc_cfg.ena_tc =  ICE_DFLT_TRAFFIC_CLASS;
-	vsi->tc_cfg.numtc = 1;
+	int i;
+
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
+		struct ice_vsi *vsi = pf->vsi[i];
+
+		if (vsi && vsi->type == type)
+			return vsi;
+	}
+
+	return NULL;
 }
 
+int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
+int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
 void ice_set_ethtool_ops(struct net_device *netdev);
 int ice_up(struct ice_vsi *vsi);
 int ice_down(struct ice_vsi *vsi);
+int ice_vsi_cfg(struct ice_vsi *vsi);
+struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi);
 int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
-void ice_napi_del(struct ice_vsi *vsi);
+#ifdef CONFIG_DCB
+int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked);
+void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked);
+#endif /* CONFIG_DCB */
+int ice_open(struct net_device *netdev);
+int ice_stop(struct net_device *netdev);
 
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index fcdcd80b18e7..765e3c2ed045 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -35,8 +35,8 @@ struct ice_aqc_get_ver {
 
 /* Queue Shutdown (direct 0x0003) */
 struct ice_aqc_q_shutdown {
-#define ICE_AQC_DRIVER_UNLOADING	BIT(0)
 	__le32 driver_unloading;
+#define ICE_AQC_DRIVER_UNLOADING	BIT(0)
 	u8 reserved[12];
 };
 
@@ -62,7 +62,7 @@ struct ice_aqc_req_res {
 #define ICE_AQ_RES_NVM_WRITE_DFLT_TIMEOUT_MS	180000
 #define ICE_AQ_RES_CHNG_LOCK_DFLT_TIMEOUT_MS	1000
 #define ICE_AQ_RES_GLBL_LOCK_DFLT_TIMEOUT_MS	3000
-	/* For SDP: pin id of the SDP */
+	/* For SDP: pin ID of the SDP */
 	__le32 res_number;
 	/* Status is only used for ICE_AQC_RES_ID_GLBL_LOCK */
 	__le16 status;
@@ -120,11 +120,9 @@ struct ice_aqc_manage_mac_read {
 #define ICE_AQC_MAN_MAC_WOL_ADDR_VALID		BIT(7)
 #define ICE_AQC_MAN_MAC_READ_S			4
 #define ICE_AQC_MAN_MAC_READ_M			(0xF << ICE_AQC_MAN_MAC_READ_S)
-	u8 lport_num;
-	u8 lport_num_valid;
-#define ICE_AQC_MAN_MAC_PORT_NUM_IS_VALID	BIT(0)
+	u8 rsvd[2];
 	u8 num_addr; /* Used in response */
-	u8 reserved[3];
+	u8 rsvd1[3];
 	__le32 addr_high;
 	__le32 addr_low;
 };
@@ -140,7 +138,7 @@ struct ice_aqc_manage_mac_read_resp {
 
 /* Manage MAC address, write command - direct (0x0108) */
 struct ice_aqc_manage_mac_write {
-	u8 port_num;
+	u8 rsvd;
 	u8 flags;
 #define ICE_AQC_MAN_MAC_WR_MC_MAG_EN		BIT(0)
 #define ICE_AQC_MAN_MAC_WR_WOL_LAA_PFR_KEEP	BIT(1)
@@ -657,8 +655,13 @@ struct ice_aqc_get_topo {
 
 /* Update TSE (indirect 0x0403)
  * Get TSE (indirect 0x0404)
+ * Add TSE (indirect 0x0401)
+ * Delete TSE (indirect 0x040F)
+ * Move TSE (indirect 0x0408)
+ * Suspend Nodes (indirect 0x0409)
+ * Resume Nodes (indirect 0x040A)
  */
-struct ice_aqc_get_cfg_elem {
+struct ice_aqc_sched_elem_cmd {
 	__le16 num_elem_req;	/* Used by commands */
 	__le16 num_elem_resp;	/* Used by responses */
 	__le32 reserved;
@@ -674,18 +677,6 @@ struct ice_aqc_suspend_resume_elem {
 	__le32 teid[1];
 };
 
-/* Add TSE (indirect 0x0401)
- * Delete TSE (indirect 0x040F)
- * Move TSE (indirect 0x0408)
- */
-struct ice_aqc_add_move_delete_elem {
-	__le16 num_grps_req;
-	__le16 num_grps_updated;
-	__le32 reserved;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
 struct ice_aqc_elem_info_bw {
 	__le16 bw_profile_idx;
 	__le16 bw_alloc;
@@ -754,6 +745,32 @@ struct ice_aqc_delete_elem {
 	__le32 teid[1];
 };
 
+/* Query Port ETS (indirect 0x040E)
+ *
+ * This indirect command is used to query port TC node configuration.
+ */
+struct ice_aqc_query_port_ets {
+	__le32 port_teid;
+	__le32 reserved;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+struct ice_aqc_port_ets_elem {
+	u8 tc_valid_bits;
+	u8 reserved[3];
+	/* 3 bits for UP per TC 0-7, 4th byte reserved */
+	__le32 up2tc;
+	u8 tc_bw_share[8];
+	__le32 port_eir_prof_id;
+	__le32 port_cir_prof_id;
+	/* 3 bits per Node priority to TC 0-7, 4th byte reserved */
+	__le32 tc_node_prio;
+#define ICE_TC_NODE_PRIO_S	0x4
+	u8 reserved1[4];
+	__le32 tc_node_teid[8]; /* Used for response, reserved in command */
+};
+
 /* Query Scheduler Resource Allocation (indirect 0x0412)
  * This indirect command retrieves the scheduler resources allocated by
  * EMP Firmware to the given PF.
@@ -854,11 +871,46 @@ struct ice_aqc_get_phy_caps {
 #define ICE_PHY_TYPE_LOW_40GBASE_KR4		BIT_ULL(33)
 #define ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC	BIT_ULL(34)
 #define ICE_PHY_TYPE_LOW_40G_XLAUI		BIT_ULL(35)
+#define ICE_PHY_TYPE_LOW_50GBASE_CR2		BIT_ULL(36)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR2		BIT_ULL(37)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR2		BIT_ULL(38)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR2		BIT_ULL(39)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC	BIT_ULL(40)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2		BIT_ULL(41)
+#define ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC	BIT_ULL(42)
+#define ICE_PHY_TYPE_LOW_50G_AUI2		BIT_ULL(43)
+#define ICE_PHY_TYPE_LOW_50GBASE_CP		BIT_ULL(44)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR		BIT_ULL(45)
+#define ICE_PHY_TYPE_LOW_50GBASE_FR		BIT_ULL(46)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR		BIT_ULL(47)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4	BIT_ULL(48)
+#define ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC	BIT_ULL(49)
+#define ICE_PHY_TYPE_LOW_50G_AUI1		BIT_ULL(50)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR4		BIT_ULL(51)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR4		BIT_ULL(52)
+#define ICE_PHY_TYPE_LOW_100GBASE_LR4		BIT_ULL(53)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR4		BIT_ULL(54)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC	BIT_ULL(55)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4		BIT_ULL(56)
+#define ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC	BIT_ULL(57)
+#define ICE_PHY_TYPE_LOW_100G_AUI4		BIT_ULL(58)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4	BIT_ULL(59)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4	BIT_ULL(60)
+#define ICE_PHY_TYPE_LOW_100GBASE_CP2		BIT_ULL(61)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR2		BIT_ULL(62)
+#define ICE_PHY_TYPE_LOW_100GBASE_DR		BIT_ULL(63)
 #define ICE_PHY_TYPE_LOW_MAX_INDEX		63
+/* The second set of defines is for phy_type_high. */
+#define ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4	BIT_ULL(0)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC	BIT_ULL(1)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2		BIT_ULL(2)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC	BIT_ULL(3)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2		BIT_ULL(4)
+#define ICE_PHY_TYPE_HIGH_MAX_INDEX		19
 
 struct ice_aqc_get_phy_caps_data {
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 reserved;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 	u8 caps;
 #define ICE_AQC_PHY_EN_TX_LINK_PAUSE			BIT(0)
 #define ICE_AQC_PHY_EN_RX_LINK_PAUSE			BIT(1)
@@ -866,6 +918,8 @@ struct ice_aqc_get_phy_caps_data {
 #define ICE_AQC_PHY_EN_LINK				BIT(3)
 #define ICE_AQC_PHY_AN_MODE				BIT(4)
 #define ICE_AQC_GET_PHY_EN_MOD_QUAL			BIT(5)
+#define ICE_AQC_PHY_EN_AUTO_FEC				BIT(7)
+#define ICE_AQC_PHY_CAPS_MASK				ICE_M(0xff, 0)
 	u8 low_power_ctrl;
 #define ICE_AQC_PHY_EN_D3COLD_LOW_POWER_AUTONEG		BIT(0)
 	__le16 eee_cap;
@@ -878,6 +932,7 @@ struct ice_aqc_get_phy_caps_data {
 #define ICE_AQC_PHY_EEE_EN_40GBASE_KR4			BIT(6)
 	__le16 eeer_value;
 	u8 phy_id_oui[4]; /* PHY/Module ID connected on the port */
+	u8 phy_fw_ver[8];
 	u8 link_fec_options;
 #define ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN		BIT(0)
 #define ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ		BIT(1)
@@ -886,6 +941,8 @@ struct ice_aqc_get_phy_caps_data {
 #define ICE_AQC_PHY_FEC_25G_RS_544_REQ			BIT(4)
 #define ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN		BIT(6)
 #define ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN		BIT(7)
+#define ICE_AQC_PHY_FEC_MASK				ICE_M(0xdf, 0)
+	u8 rsvd1;	/* Byte 35 reserved */
 	u8 extended_compliance_code;
 #define ICE_MODULE_TYPE_TOTAL_BYTE			3
 	u8 module_type[ICE_MODULE_TYPE_TOTAL_BYTE];
@@ -900,13 +957,14 @@ struct ice_aqc_get_phy_caps_data {
 #define ICE_AQC_MOD_TYPE_BYTE2_SFP_PLUS			0xA0
 #define ICE_AQC_MOD_TYPE_BYTE2_QSFP_PLUS		0x86
 	u8 qualified_module_count;
+	u8 rsvd2[7];	/* Bytes 47:41 reserved */
 #define ICE_AQC_QUAL_MOD_COUNT_MAX			16
 	struct {
 		u8 v_oui[3];
-		u8 rsvd1;
+		u8 rsvd3;
 		u8 v_part[16];
 		__le32 v_rev;
-		__le64 rsvd8;
+		__le64 rsvd4;
 	} qual_modules[ICE_AQC_QUAL_MOD_COUNT_MAX];
 };
 
@@ -923,10 +981,11 @@ struct ice_aqc_set_phy_cfg {
 /* Set PHY config command data structure */
 struct ice_aqc_set_phy_cfg_data {
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 rsvd0;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 	u8 caps;
-#define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY		BIT(0)
-#define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY		BIT(1)
+#define ICE_AQ_PHY_ENA_VALID_MASK	ICE_M(0xef, 0)
+#define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY	BIT(0)
+#define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY	BIT(1)
 #define ICE_AQ_PHY_ENA_LOW_POWER	BIT(2)
 #define ICE_AQ_PHY_ENA_LINK		BIT(3)
 #define ICE_AQ_PHY_ENA_AUTO_LINK_UPDT	BIT(5)
@@ -995,7 +1054,7 @@ struct ice_aqc_get_link_status_data {
 	u8 ext_info;
 #define ICE_AQ_LINK_PHY_TEMP_ALARM	BIT(0)
 #define ICE_AQ_LINK_EXCESSIVE_ERRORS	BIT(1)	/* Excessive Link Errors */
-	/* Port TX Suspended */
+	/* Port Tx Suspended */
 #define ICE_AQ_LINK_TX_S		2
 #define ICE_AQ_LINK_TX_M		(0x03 << ICE_AQ_LINK_TX_S)
 #define ICE_AQ_LINK_TX_ACTIVE		0
@@ -1007,6 +1066,7 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_LINK_25G_KR_FEC_EN	BIT(0)
 #define ICE_AQ_LINK_25G_RS_528_FEC_EN	BIT(1)
 #define ICE_AQ_LINK_25G_RS_544_FEC_EN	BIT(2)
+#define ICE_AQ_FEC_MASK			ICE_M(0x7, 0)
 	/* Pacing Config */
 #define ICE_AQ_CFG_PACING_S		3
 #define ICE_AQ_CFG_PACING_M		(0xF << ICE_AQ_CFG_PACING_S)
@@ -1032,10 +1092,12 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_LINK_SPEED_20GB		BIT(6)
 #define ICE_AQ_LINK_SPEED_25GB		BIT(7)
 #define ICE_AQ_LINK_SPEED_40GB		BIT(8)
+#define ICE_AQ_LINK_SPEED_50GB		BIT(9)
+#define ICE_AQ_LINK_SPEED_100GB		BIT(10)
 #define ICE_AQ_LINK_SPEED_UNKNOWN	BIT(15)
 	__le32 reserved3; /* Aligns next field to 8-byte boundary */
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 reserved4;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 };
 
 /* Set event mask command (direct 0x0613) */
@@ -1055,6 +1117,24 @@ struct ice_aqc_set_event_mask {
 	u8	reserved1[6];
 };
 
+/* Set MAC Loopback command (direct 0x0620) */
+struct ice_aqc_set_mac_lb {
+	u8 lb_mode;
+#define ICE_AQ_MAC_LB_EN		BIT(0)
+#define ICE_AQ_MAC_LB_OSC_CLK		BIT(1)
+	u8 reserved[15];
+};
+
+/* Set Port Identification LED (direct, 0x06E9) */
+struct ice_aqc_set_port_id_led {
+	u8 lport_num;
+	u8 lport_num_valid;
+	u8 ident_mode;
+#define ICE_AQC_PORT_IDENT_LED_BLINK	BIT(0)
+#define ICE_AQC_PORT_IDENT_LED_ORIG	0
+	u8 rsvd[13];
+};
+
 /* NVM Read command (indirect 0x0701)
  * NVM Erase commands (direct 0x0702)
  * NVM Update commands (indirect 0x0703)
@@ -1078,10 +1158,21 @@ struct ice_aqc_nvm {
 	__le32 addr_low;
 };
 
+/* NVM Checksum Command (direct, 0x0706) */
+struct ice_aqc_nvm_checksum {
+	u8 flags;
+#define ICE_AQC_NVM_CHECKSUM_VERIFY	BIT(0)
+#define ICE_AQC_NVM_CHECKSUM_RECALC	BIT(1)
+	u8 rsvd;
+	__le16 checksum; /* Used only by response */
+#define ICE_AQC_NVM_CHECKSUM_CORRECT	0xBABA
+	u8 rsvd2[12];
+};
+
 /**
- * Send to PF command (indirect 0x0801) id is only used by PF
+ * Send to PF command (indirect 0x0801) ID is only used by PF
  *
- * Send to VF command (indirect 0x0802) id is only used by PF
+ * Send to VF command (indirect 0x0802) ID is only used by PF
  *
  */
 struct ice_aqc_pf_vf_msg {
@@ -1091,6 +1182,126 @@ struct ice_aqc_pf_vf_msg {
 	__le32 addr_low;
 };
 
+/* Get LLDP MIB (indirect 0x0A00)
+ * Note: This is also used by the LLDP MIB Change Event (0x0A01)
+ * as the format is the same.
+ */
+struct ice_aqc_lldp_get_mib {
+	u8 type;
+#define ICE_AQ_LLDP_MIB_TYPE_S			0
+#define ICE_AQ_LLDP_MIB_TYPE_M			(0x3 << ICE_AQ_LLDP_MIB_TYPE_S)
+#define ICE_AQ_LLDP_MIB_LOCAL			0
+#define ICE_AQ_LLDP_MIB_REMOTE			1
+#define ICE_AQ_LLDP_MIB_LOCAL_AND_REMOTE	2
+#define ICE_AQ_LLDP_BRID_TYPE_S			2
+#define ICE_AQ_LLDP_BRID_TYPE_M			(0x3 << ICE_AQ_LLDP_BRID_TYPE_S)
+#define ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID	0
+#define ICE_AQ_LLDP_BRID_TYPE_NON_TPMR		1
+/* Tx pause flags in the 0xA01 event use ICE_AQ_LLDP_TX_* */
+#define ICE_AQ_LLDP_TX_S			0x4
+#define ICE_AQ_LLDP_TX_M			(0x03 << ICE_AQ_LLDP_TX_S)
+#define ICE_AQ_LLDP_TX_ACTIVE			0
+#define ICE_AQ_LLDP_TX_SUSPENDED		1
+#define ICE_AQ_LLDP_TX_FLUSHED			3
+/* The following bytes are reserved for the Get LLDP MIB command (0x0A00)
+ * and in the LLDP MIB Change Event (0x0A01). They are valid for the
+ * Get LLDP MIB (0x0A00) response only.
+ */
+	u8 reserved1;
+	__le16 local_len;
+	__le16 remote_len;
+	u8 reserved2[2];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Configure LLDP MIB Change Event (direct 0x0A01) */
+/* For MIB Change Event use ice_aqc_lldp_get_mib structure above */
+struct ice_aqc_lldp_set_mib_change {
+	u8 command;
+#define ICE_AQ_LLDP_MIB_UPDATE_ENABLE		0x0
+#define ICE_AQ_LLDP_MIB_UPDATE_DIS		0x1
+	u8 reserved[15];
+};
+
+/* Stop LLDP (direct 0x0A05) */
+struct ice_aqc_lldp_stop {
+	u8 command;
+#define ICE_AQ_LLDP_AGENT_STATE_MASK	BIT(0)
+#define ICE_AQ_LLDP_AGENT_STOP		0x0
+#define ICE_AQ_LLDP_AGENT_SHUTDOWN	ICE_AQ_LLDP_AGENT_STATE_MASK
+#define ICE_AQ_LLDP_AGENT_PERSIST_DIS	BIT(1)
+	u8 reserved[15];
+};
+
+/* Start LLDP (direct 0x0A06) */
+struct ice_aqc_lldp_start {
+	u8 command;
+#define ICE_AQ_LLDP_AGENT_START		BIT(0)
+#define ICE_AQ_LLDP_AGENT_PERSIST_ENA	BIT(1)
+	u8 reserved[15];
+};
+
+/* Get CEE DCBX Oper Config (0x0A07)
+ * The command uses the generic descriptor struct and
+ * returns the struct below as an indirect response.
+ */
+struct ice_aqc_get_cee_dcb_cfg_resp {
+	u8 oper_num_tc;
+	u8 oper_prio_tc[4];
+	u8 oper_tc_bw[8];
+	u8 oper_pfc_en;
+	__le16 oper_app_prio;
+#define ICE_AQC_CEE_APP_FCOE_S		0
+#define ICE_AQC_CEE_APP_FCOE_M		(0x7 << ICE_AQC_CEE_APP_FCOE_S)
+#define ICE_AQC_CEE_APP_ISCSI_S		3
+#define ICE_AQC_CEE_APP_ISCSI_M		(0x7 << ICE_AQC_CEE_APP_ISCSI_S)
+#define ICE_AQC_CEE_APP_FIP_S		8
+#define ICE_AQC_CEE_APP_FIP_M		(0x7 << ICE_AQC_CEE_APP_FIP_S)
+	__le32 tlv_status;
+#define ICE_AQC_CEE_PG_STATUS_S		0
+#define ICE_AQC_CEE_PG_STATUS_M		(0x7 << ICE_AQC_CEE_PG_STATUS_S)
+#define ICE_AQC_CEE_PFC_STATUS_S	3
+#define ICE_AQC_CEE_PFC_STATUS_M	(0x7 << ICE_AQC_CEE_PFC_STATUS_S)
+#define ICE_AQC_CEE_FCOE_STATUS_S	8
+#define ICE_AQC_CEE_FCOE_STATUS_M	(0x7 << ICE_AQC_CEE_FCOE_STATUS_S)
+#define ICE_AQC_CEE_ISCSI_STATUS_S	11
+#define ICE_AQC_CEE_ISCSI_STATUS_M	(0x7 << ICE_AQC_CEE_ISCSI_STATUS_S)
+#define ICE_AQC_CEE_FIP_STATUS_S	16
+#define ICE_AQC_CEE_FIP_STATUS_M	(0x7 << ICE_AQC_CEE_FIP_STATUS_S)
+	u8 reserved[12];
+};
+
+/* Set Local LLDP MIB (indirect 0x0A08)
+ * Used to replace the local MIB of a given LLDP agent. e.g. DCBX
+ */
+struct ice_aqc_lldp_set_local_mib {
+	u8 type;
+#define SET_LOCAL_MIB_TYPE_DCBX_M		BIT(0)
+#define SET_LOCAL_MIB_TYPE_LOCAL_MIB		0
+#define SET_LOCAL_MIB_TYPE_CEE_M		BIT(1)
+#define SET_LOCAL_MIB_TYPE_CEE_WILLING		0
+#define SET_LOCAL_MIB_TYPE_CEE_NON_WILLING	SET_LOCAL_MIB_TYPE_CEE_M
+	u8 reserved0;
+	__le16 length;
+	u8 reserved1[4];
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Stop/Start LLDP Agent (direct 0x0A09)
+ * Used for stopping/starting specific LLDP agent. e.g. DCBX.
+ * The same structure is used for the response, with the command field
+ * being used as the status field.
+ */
+struct ice_aqc_lldp_stop_start_specific_agent {
+	u8 command;
+#define ICE_AQC_START_STOP_AGENT_M		BIT(0)
+#define ICE_AQC_START_STOP_AGENT_STOP_DCBX	0
+#define ICE_AQC_START_STOP_AGENT_START_DCBX	ICE_AQC_START_STOP_AGENT_M
+	u8 reserved[15];
+};
+
 /* Get/Set RSS key (indirect 0x0B04/0x0B02) */
 struct ice_aqc_get_set_rss_key {
 #define ICE_AQC_GSET_RSS_KEY_VSI_VALID	BIT(15)
@@ -1104,6 +1315,9 @@ struct ice_aqc_get_set_rss_key {
 
 #define ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE	0x28
 #define ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE	0xC
+#define ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE \
+				(ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE + \
+				 ICE_AQC_GET_SET_RSS_KEY_DATA_HASH_KEY_SIZE)
 
 struct ice_aqc_get_set_rss_keys {
 	u8 standard_rss_key[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE];
@@ -1145,7 +1359,7 @@ struct ice_aqc_get_set_rss_lut {
 	__le32 addr_low;
 };
 
-/* Add TX LAN Queues (indirect 0x0C30) */
+/* Add Tx LAN Queues (indirect 0x0C30) */
 struct ice_aqc_add_txqs {
 	u8 num_qgrps;
 	u8 reserved[3];
@@ -1154,7 +1368,7 @@ struct ice_aqc_add_txqs {
 	__le32 addr_low;
 };
 
-/* This is the descriptor of each queue entry for the Add TX LAN Queues
+/* This is the descriptor of each queue entry for the Add Tx LAN Queues
  * command (0x0C30). Only used within struct ice_aqc_add_tx_qgrp.
  */
 struct ice_aqc_add_txqs_perq {
@@ -1166,7 +1380,7 @@ struct ice_aqc_add_txqs_perq {
 	struct ice_aqc_txsched_elem info;
 };
 
-/* The format of the command buffer for Add TX LAN Queues (0x0C30)
+/* The format of the command buffer for Add Tx LAN Queues (0x0C30)
  * is an array of the following structs. Please note that the length of
  * each struct ice_aqc_add_tx_qgrp is variable due
  * to the variable number of queues in each group!
@@ -1178,7 +1392,7 @@ struct ice_aqc_add_tx_qgrp {
 	struct ice_aqc_add_txqs_perq txqs[1];
 };
 
-/* Disable TX LAN Queues (indirect 0x0C31) */
+/* Disable Tx LAN Queues (indirect 0x0C31) */
 struct ice_aqc_dis_txqs {
 	u8 cmd_type;
 #define ICE_AQC_Q_DIS_CMD_S		0
@@ -1200,7 +1414,7 @@ struct ice_aqc_dis_txqs {
 	__le32 addr_low;
 };
 
-/* The buffer for Disable TX LAN Queues (indirect 0x0C31)
+/* The buffer for Disable Tx LAN Queues (indirect 0x0C31)
  * contains the following structures, arrayed one after the
  * other.
  * Note: Since the q_id is 16 bits wide, if the
@@ -1341,14 +1555,22 @@ struct ice_aq_desc {
 		struct ice_aqc_get_phy_caps get_phy;
 		struct ice_aqc_set_phy_cfg set_phy;
 		struct ice_aqc_restart_an restart_an;
+		struct ice_aqc_set_port_id_led set_port_id_led;
 		struct ice_aqc_get_sw_cfg get_sw_conf;
 		struct ice_aqc_sw_rules sw_rules;
 		struct ice_aqc_get_topo get_topo;
-		struct ice_aqc_get_cfg_elem get_update_elem;
+		struct ice_aqc_sched_elem_cmd sched_elem_cmd;
 		struct ice_aqc_query_txsched_res query_sched_res;
-		struct ice_aqc_add_move_delete_elem add_move_delete_elem;
+		struct ice_aqc_query_port_ets port_ets;
 		struct ice_aqc_nvm nvm;
+		struct ice_aqc_nvm_checksum nvm_checksum;
 		struct ice_aqc_pf_vf_msg virt;
+		struct ice_aqc_lldp_get_mib lldp_get_mib;
+		struct ice_aqc_lldp_set_mib_change lldp_set_event;
+		struct ice_aqc_lldp_stop lldp_stop;
+		struct ice_aqc_lldp_start lldp_start;
+		struct ice_aqc_lldp_set_local_mib lldp_set_mib;
+		struct ice_aqc_lldp_stop_start_specific_agent lldp_agent_ctrl;
 		struct ice_aqc_get_set_rss_lut get_set_rss_lut;
 		struct ice_aqc_get_set_rss_key get_set_rss_key;
 		struct ice_aqc_add_txqs add_txqs;
@@ -1357,6 +1579,7 @@ struct ice_aq_desc {
 		struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;
 		struct ice_aqc_fw_logging fw_logging;
 		struct ice_aqc_get_clear_fw_log get_clear_fw_log;
+		struct ice_aqc_set_mac_lb set_mac_lb;
 		struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
 		struct ice_aqc_set_event_mask set_event_mask;
 		struct ice_aqc_get_link_status get_link_status;
@@ -1381,6 +1604,8 @@ struct ice_aq_desc {
 /* error codes */
 enum ice_aq_err {
 	ICE_AQ_RC_OK		= 0,  /* Success */
+	ICE_AQ_RC_EPERM		= 1,  /* Operation not permitted */
+	ICE_AQ_RC_ENOENT	= 2,  /* No such element */
 	ICE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
 	ICE_AQ_RC_EBUSY		= 12, /* Device or resource busy */
 	ICE_AQ_RC_EEXIST	= 13, /* Object already exists */
@@ -1433,6 +1658,7 @@ enum ice_adminq_opc {
 	ice_aqc_opc_get_sched_elems			= 0x0404,
 	ice_aqc_opc_suspend_sched_elems			= 0x0409,
 	ice_aqc_opc_resume_sched_elems			= 0x040A,
+	ice_aqc_opc_query_port_ets			= 0x040E,
 	ice_aqc_opc_delete_sched_elems			= 0x040F,
 	ice_aqc_opc_query_sched_res			= 0x0412,
 
@@ -1442,13 +1668,24 @@ enum ice_adminq_opc {
 	ice_aqc_opc_restart_an				= 0x0605,
 	ice_aqc_opc_get_link_status			= 0x0607,
 	ice_aqc_opc_set_event_mask			= 0x0613,
+	ice_aqc_opc_set_mac_lb				= 0x0620,
+	ice_aqc_opc_set_port_id_led			= 0x06E9,
 
 	/* NVM commands */
 	ice_aqc_opc_nvm_read				= 0x0701,
+	ice_aqc_opc_nvm_checksum			= 0x0706,
 
 	/* PF/VF mailbox commands */
 	ice_mbx_opc_send_msg_to_pf			= 0x0801,
 	ice_mbx_opc_send_msg_to_vf			= 0x0802,
+	/* LLDP commands */
+	ice_aqc_opc_lldp_get_mib			= 0x0A00,
+	ice_aqc_opc_lldp_set_mib_change			= 0x0A01,
+	ice_aqc_opc_lldp_stop				= 0x0A05,
+	ice_aqc_opc_lldp_start				= 0x0A06,
+	ice_aqc_opc_get_cee_dcb_cfg			= 0x0A07,
+	ice_aqc_opc_lldp_set_local_mib			= 0x0A08,
+	ice_aqc_opc_lldp_stop_start_specific_agent	= 0x0A09,
 
 	/* RSS commands */
 	ice_aqc_opc_set_rss_key				= 0x0B02,
@@ -1456,12 +1693,13 @@ enum ice_adminq_opc {
 	ice_aqc_opc_get_rss_key				= 0x0B04,
 	ice_aqc_opc_get_rss_lut				= 0x0B05,
 
-	/* TX queue handling commands/events */
+	/* Tx queue handling commands/events */
 	ice_aqc_opc_add_txqs				= 0x0C30,
 	ice_aqc_opc_dis_txqs				= 0x0C31,
 
 	/* debug commands */
 	ice_aqc_opc_fw_logging				= 0xFF09,
+	ice_aqc_opc_fw_logging_info			= 0xFF10,
 };
 
 #endif /* _ICE_ADMINQ_CMD_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 4c1d35da940d..2e0731c1e1a3 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -31,7 +31,7 @@
  * @hw: pointer to the HW structure
  *
  * This function sets the MAC type of the adapter based on the
- * vendor ID and device ID stored in the hw structure.
+ * vendor ID and device ID stored in the HW structure.
  */
 static enum ice_status ice_set_mac_type(struct ice_hw *hw)
 {
@@ -51,9 +51,6 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw)
  */
 void ice_dev_onetime_setup(struct ice_hw *hw)
 {
-	/* configure Rx - set non pxe mode */
-	wr32(hw, GLLAN_RCTL_0, 0x1);
-
 #define MBX_PF_VT_PFALLOC	0x00231E80
 	/* set VFs per PF */
 	wr32(hw, MBX_PF_VT_PFALLOC, rd32(hw, PF_VT_PFALLOC_HIF));
@@ -77,7 +74,7 @@ enum ice_status ice_clear_pf_cfg(struct ice_hw *hw)
 
 /**
  * ice_aq_manage_mac_read - manage MAC address read command
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @buf: a virtual buffer to hold the manage MAC read response
  * @buf_size: Size of the virtual buffer
  * @cd: pointer to command details structure or NULL
@@ -165,8 +162,10 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 	cmd->param0 |= cpu_to_le16(report_mode);
 	status = ice_aq_send_cmd(pi->hw, &desc, pcaps, pcaps_size, cd);
 
-	if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP)
+	if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP) {
 		pi->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low);
+		pi->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high);
+	}
 
 	return status;
 }
@@ -183,6 +182,9 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		return ICE_MEDIA_UNKNOWN;
 
 	hw_link_info = &pi->phy.link_info;
+	if (hw_link_info->phy_type_low && hw_link_info->phy_type_high)
+		/* If more than one media type is selected, report unknown */
+		return ICE_MEDIA_UNKNOWN;
 
 	if (hw_link_info->phy_type_low) {
 		switch (hw_link_info->phy_type_low) {
@@ -196,6 +198,15 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		case ICE_PHY_TYPE_LOW_25G_AUI_C2C:
 		case ICE_PHY_TYPE_LOW_40GBASE_SR4:
 		case ICE_PHY_TYPE_LOW_40GBASE_LR4:
+		case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+		case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+		case ICE_PHY_TYPE_LOW_50GBASE_SR:
+		case ICE_PHY_TYPE_LOW_50GBASE_FR:
+		case ICE_PHY_TYPE_LOW_50GBASE_LR:
+		case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+		case ICE_PHY_TYPE_LOW_100GBASE_DR:
 			return ICE_MEDIA_FIBER;
 		case ICE_PHY_TYPE_LOW_100BASE_TX:
 		case ICE_PHY_TYPE_LOW_1000BASE_T:
@@ -209,6 +220,11 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		case ICE_PHY_TYPE_LOW_25GBASE_CR_S:
 		case ICE_PHY_TYPE_LOW_25GBASE_CR1:
 		case ICE_PHY_TYPE_LOW_40GBASE_CR4:
+		case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+		case ICE_PHY_TYPE_LOW_50GBASE_CP:
+		case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+		case ICE_PHY_TYPE_LOW_100GBASE_CP2:
 			return ICE_MEDIA_DA;
 		case ICE_PHY_TYPE_LOW_1000BASE_KX:
 		case ICE_PHY_TYPE_LOW_2500BASE_KX:
@@ -219,10 +235,18 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		case ICE_PHY_TYPE_LOW_25GBASE_KR1:
 		case ICE_PHY_TYPE_LOW_25GBASE_KR_S:
 		case ICE_PHY_TYPE_LOW_40GBASE_KR4:
+		case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+		case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+		case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+			return ICE_MEDIA_BACKPLANE;
+		}
+	} else {
+		switch (hw_link_info->phy_type_high) {
+		case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
 			return ICE_MEDIA_BACKPLANE;
 		}
 	}
-
 	return ICE_MEDIA_UNKNOWN;
 }
 
@@ -235,7 +259,7 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
  *
  * Get Link Status (0x607). Returns the link status of the adapter.
  */
-static enum ice_status
+enum ice_status
 ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 		     struct ice_link_status *link, struct ice_sq_cd *cd)
 {
@@ -274,11 +298,14 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	/* update current link status information */
 	hw_link_info->link_speed = le16_to_cpu(link_data.link_speed);
 	hw_link_info->phy_type_low = le64_to_cpu(link_data.phy_type_low);
+	hw_link_info->phy_type_high = le64_to_cpu(link_data.phy_type_high);
 	*hw_media_type = ice_get_media_type(pi);
 	hw_link_info->link_info = link_data.link_info;
 	hw_link_info->an_info = link_data.an_info;
 	hw_link_info->ext_info = link_data.ext_info;
 	hw_link_info->max_frame_size = le16_to_cpu(link_data.max_frame_size);
+	hw_link_info->fec_info = link_data.cfg & ICE_AQ_FEC_MASK;
+	hw_link_info->topo_media_conflict = link_data.topo_media_conflict;
 	hw_link_info->pacing = link_data.cfg & ICE_AQ_CFG_PACING_M;
 
 	/* update fc info */
@@ -303,7 +330,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	/* flag cleared so calling functions don't call AQ again */
 	pi->phy.get_link_info = false;
 
-	return status;
+	return 0;
 }
 
 /**
@@ -330,22 +357,22 @@ static void ice_init_flex_flags(struct ice_hw *hw, enum ice_rxdid prof_id)
 	 */
 	case ICE_RXDID_FLEX_NIC:
 	case ICE_RXDID_FLEX_NIC_2:
-		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_FRG,
-				   ICE_RXFLG_UDP_GRE, ICE_RXFLG_PKT_DSI,
-				   ICE_RXFLG_FIN, idx++);
+		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_PKT_FRG,
+				   ICE_FLG_UDP_GRE, ICE_FLG_PKT_DSI,
+				   ICE_FLG_FIN, idx++);
 		/* flex flag 1 is not used for flexi-flag programming, skipping
 		 * these four FLG64 bits.
 		 */
-		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_SYN, ICE_RXFLG_RST,
-				   ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++);
-		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_DSI,
-				   ICE_RXFLG_PKT_DSI, ICE_RXFLG_EVLAN_x8100,
-				   ICE_RXFLG_EVLAN_x9100, idx++);
-		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_VLAN_x8100,
-				   ICE_RXFLG_TNL_VLAN, ICE_RXFLG_TNL_MAC,
-				   ICE_RXFLG_TNL0, idx++);
-		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2,
-				   ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx);
+		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_SYN, ICE_FLG_RST,
+				   ICE_FLG_PKT_DSI, ICE_FLG_PKT_DSI, idx++);
+		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_PKT_DSI,
+				   ICE_FLG_PKT_DSI, ICE_FLG_EVLAN_x8100,
+				   ICE_FLG_EVLAN_x9100, idx++);
+		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_VLAN_x8100,
+				   ICE_FLG_TNL_VLAN, ICE_FLG_TNL_MAC,
+				   ICE_FLG_TNL0, idx++);
+		ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_FLG_TNL1, ICE_FLG_TNL2,
+				   ICE_FLG_PKT_DSI, ICE_FLG_PKT_DSI, idx);
 		break;
 
 	default:
@@ -390,7 +417,7 @@ static void ice_init_flex_flds(struct ice_hw *hw, enum ice_rxdid prof_id)
 
 /**
  * ice_init_fltr_mgmt_struct - initializes filter management list and locks
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  */
 static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 {
@@ -410,7 +437,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 
 /**
  * ice_cleanup_fltr_mgmt_struct - cleanup filter management list and locks
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  */
 static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw)
 {
@@ -448,8 +475,51 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw)
 	ICE_FW_LOG_DESC_SIZE(ICE_AQC_FW_LOG_ID_MAX)
 
 /**
+ * ice_get_fw_log_cfg - get FW logging configuration
+ * @hw: pointer to the HW struct
+ */
+static enum ice_status ice_get_fw_log_cfg(struct ice_hw *hw)
+{
+	struct ice_aqc_fw_logging_data *config;
+	struct ice_aq_desc desc;
+	enum ice_status status;
+	u16 size;
+
+	size = ICE_FW_LOG_DESC_SIZE_MAX;
+	config = devm_kzalloc(ice_hw_to_dev(hw), size, GFP_KERNEL);
+	if (!config)
+		return ICE_ERR_NO_MEMORY;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging_info);
+
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+
+	status = ice_aq_send_cmd(hw, &desc, config, size, NULL);
+	if (!status) {
+		u16 i;
+
+		/* Save FW logging information into the HW structure */
+		for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) {
+			u16 v, m, flgs;
+
+			v = le16_to_cpu(config->entry[i]);
+			m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S;
+			flgs = (v & ICE_AQC_FW_LOG_EN_M) >> ICE_AQC_FW_LOG_EN_S;
+
+			if (m < ICE_AQC_FW_LOG_ID_MAX)
+				hw->fw_log.evnts[m].cur = flgs;
+		}
+	}
+
+	devm_kfree(ice_hw_to_dev(hw), config);
+
+	return status;
+}
+
+/**
  * ice_cfg_fw_log - configure FW logging
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @enable: enable certain FW logging events if true, disable all if false
  *
  * This function enables/disables the FW logging via Rx CQ events and a UART
@@ -501,6 +571,11 @@ static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable)
 	    (!hw->fw_log.actv_evnts || !ice_check_sq_alive(hw, &hw->adminq)))
 		return 0;
 
+	/* Get current FW log settings */
+	status = ice_get_fw_log_cfg(hw);
+	if (status)
+		return status;
+
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging);
 	cmd = &desc.params.fw_logging;
 
@@ -598,7 +673,7 @@ out:
 
 /**
  * ice_output_fw_log
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @desc: pointer to the AQ message descriptor
  * @buf: pointer to the buffer accompanying the AQ message
  *
@@ -606,20 +681,20 @@ out:
  */
 void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf)
 {
-	ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg Start ]\n");
-	ice_debug_array(hw, ICE_DBG_AQ_MSG, 16, 1, (u8 *)buf,
+	ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg Start ]\n");
+	ice_debug_array(hw, ICE_DBG_FW_LOG, 16, 1, (u8 *)buf,
 			le16_to_cpu(desc->datalen));
-	ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg End ]\n");
+	ice_debug(hw, ICE_DBG_FW_LOG, "[ FW Log Msg End ]\n");
 }
 
 /**
  * ice_get_itr_intrl_gran - determine int/intrl granularity
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
- * Determines the itr/intrl granularities based on the maximum aggregate
+ * Determines the ITR/intrl granularities based on the maximum aggregate
  * bandwidth according to the device's configuration during power-on.
  */
-static enum ice_status ice_get_itr_intrl_gran(struct ice_hw *hw)
+static void ice_get_itr_intrl_gran(struct ice_hw *hw)
 {
 	u8 max_agg_bw = (rd32(hw, GL_PWR_MODE_CTL) &
 			 GL_PWR_MODE_CTL_CAR_MAX_BW_M) >>
@@ -636,13 +711,7 @@ static enum ice_status ice_get_itr_intrl_gran(struct ice_hw *hw)
 		hw->itr_gran = ICE_ITR_GRAN_MAX_25;
 		hw->intrl_gran = ICE_INTRL_GRAN_MAX_25;
 		break;
-	default:
-		ice_debug(hw, ICE_DBG_INIT,
-			  "Failed to determine itr/intrl granularity\n");
-		return ICE_ERR_CFG;
 	}
-
-	return 0;
 }
 
 /**
@@ -669,9 +738,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	if (status)
 		return status;
 
-	status = ice_get_itr_intrl_gran(hw);
-	if (status)
-		return status;
+	ice_get_itr_intrl_gran(hw);
 
 	status = ice_init_all_ctrlq(hw);
 	if (status)
@@ -703,7 +770,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 		goto err_unroll_cqinit;
 	}
 
-	/* set the back pointer to hw */
+	/* set the back pointer to HW */
 	hw->port_info->hw = hw;
 
 	/* Initialize port_info struct with switch configuration data */
@@ -750,6 +817,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 		status = ICE_ERR_CFG;
 		goto err_unroll_sched;
 	}
+	INIT_LIST_HEAD(&hw->agg_list);
 
 	status = ice_init_fltr_mgmt_struct(hw);
 	if (status)
@@ -794,12 +862,17 @@ err_unroll_cqinit:
 /**
  * ice_deinit_hw - unroll initialization operations done by ice_init_hw
  * @hw: pointer to the hardware structure
+ *
+ * This should be called only during nominal operation, not as a result of
+ * ice_init_hw() failing since ice_init_hw() will take care of unrolling
+ * applicable initializations if it fails for any reason.
  */
 void ice_deinit_hw(struct ice_hw *hw)
 {
 	ice_cleanup_fltr_mgmt_struct(hw);
 
 	ice_sched_cleanup_all(hw);
+	ice_sched_clear_agg(hw);
 
 	if (hw->port_info) {
 		devm_kfree(ice_hw_to_dev(hw), hw->port_info);
@@ -958,7 +1031,7 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req)
  * @ice_rxq_ctx: pointer to the rxq context
  * @rxq_index: the index of the Rx queue
  *
- * Copies rxq context from dense structure to hw register space
+ * Copies rxq context from dense structure to HW register space
  */
 static enum ice_status
 ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index)
@@ -971,7 +1044,7 @@ ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index)
 	if (rxq_index > QRX_CTRL_MAX_INDEX)
 		return ICE_ERR_PARAM;
 
-	/* Copy each dword separately to hw */
+	/* Copy each dword separately to HW */
 	for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) {
 		wr32(hw, QRX_CONTEXT(i, rxq_index),
 		     *((u32 *)(ice_rxq_ctx + (i * sizeof(u32)))));
@@ -1015,7 +1088,7 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = {
  * @rxq_index: the index of the Rx queue
  *
  * Converts rxq context from sparse to dense structure and then writes
- * it to hw register space
+ * it to HW register space
  */
 enum ice_status
 ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
@@ -1070,8 +1143,9 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = {
  *
  * Dumps debug log about control command with descriptor contents.
  */
-void ice_debug_cq(struct ice_hw *hw, u32 __maybe_unused mask, void *desc,
-		  void *buf, u16 buf_len)
+void
+ice_debug_cq(struct ice_hw *hw, u32 __maybe_unused mask, void *desc, void *buf,
+	     u16 buf_len)
 {
 	struct ice_aq_desc *cq_desc = (struct ice_aq_desc *)desc;
 	u16 len;
@@ -1113,7 +1187,7 @@ void ice_debug_cq(struct ice_hw *hw, u32 __maybe_unused mask, void *desc,
 
 /**
  * ice_aq_send_cmd - send FW Admin Queue command to FW Admin Queue
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @desc: descriptor describing the command
  * @buf: buffer to use for indirect commands (NULL for direct commands)
  * @buf_size: size of buffer for indirect commands (0 for direct commands)
@@ -1130,7 +1204,7 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
 
 /**
  * ice_aq_get_fw_ver
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @cd: pointer to command details structure or NULL
  *
  * Get the firmware version (0x0001) from the admin queue commands
@@ -1164,7 +1238,7 @@ enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd)
 
 /**
  * ice_aq_q_shutdown
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @unloading: is the driver unloading itself
  *
  * Tell the Firmware that we're shutting down the AdminQ and whether
@@ -1187,8 +1261,8 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading)
 
 /**
  * ice_aq_req_res
- * @hw: pointer to the hw struct
- * @res: resource id
+ * @hw: pointer to the HW struct
+ * @res: resource ID
  * @access: access type
  * @sdp_number: resource number
  * @timeout: the maximum time in ms that the driver may hold the resource
@@ -1273,8 +1347,8 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 
 /**
  * ice_aq_release_res
- * @hw: pointer to the hw struct
- * @res: resource id
+ * @hw: pointer to the HW struct
+ * @res: resource ID
  * @sdp_number: resource number
  * @cd: pointer to command details structure or NULL
  *
@@ -1300,7 +1374,7 @@ ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number,
 /**
  * ice_acquire_res
  * @hw: pointer to the HW structure
- * @res: resource id
+ * @res: resource ID
  * @access: access type (read or write)
  * @timeout: timeout in milliseconds
  *
@@ -1362,7 +1436,7 @@ ice_acquire_res_exit:
 /**
  * ice_release_res
  * @hw: pointer to the HW structure
- * @res: resource id
+ * @res: resource ID
  *
  * This function will release a resource using the proper Admin Command.
  */
@@ -1374,7 +1448,7 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res)
 	status = ice_aq_release_res(hw, res, 0, NULL);
 
 	/* there are some rare cases when trying to release the resource
-	 * results in an admin Q timeout, so handle them correctly
+	 * results in an admin queue timeout, so handle them correctly
 	 */
 	while ((status == ICE_ERR_AQ_TIMEOUT) &&
 	       (total_delay < hw->adminq.sq_cmd_timeout)) {
@@ -1385,13 +1459,15 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res)
 }
 
 /**
- * ice_get_guar_num_vsi - determine number of guar VSI for a PF
- * @hw: pointer to the hw structure
+ * ice_get_num_per_func - determine number of resources per PF
+ * @hw: pointer to the HW structure
+ * @max: value to be evenly split between each PF
  *
  * Determine the number of valid functions by going through the bitmap returned
- * from parsing capabilities and use this to calculate the number of VSI per PF.
+ * from parsing capabilities and use this to calculate the number of resources
+ * per PF based on the max value passed in.
  */
-static u32 ice_get_guar_num_vsi(struct ice_hw *hw)
+static u32 ice_get_num_per_func(struct ice_hw *hw, u32 max)
 {
 	u8 funcs;
 
@@ -1402,12 +1478,12 @@ static u32 ice_get_guar_num_vsi(struct ice_hw *hw)
 	if (!funcs)
 		return 0;
 
-	return ICE_MAX_VSI / funcs;
+	return max / funcs;
 }
 
 /**
  * ice_parse_caps - parse function/device capabilities
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @buf: pointer to a buffer containing function/device capability records
  * @cap_count: number of capability records in the list
  * @opc: type of capabilities list to parse
@@ -1422,6 +1498,7 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 	struct ice_hw_func_caps *func_p = NULL;
 	struct ice_hw_dev_caps *dev_p = NULL;
 	struct ice_hw_common_caps *caps;
+	char const *prefix;
 	u32 i;
 
 	if (!buf)
@@ -1432,9 +1509,11 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 	if (opc == ice_aqc_opc_list_dev_caps) {
 		dev_p = &hw->dev_caps;
 		caps = &dev_p->common_cap;
+		prefix = "dev cap";
 	} else if (opc == ice_aqc_opc_list_func_caps) {
 		func_p = &hw->func_caps;
 		caps = &func_p->common_cap;
+		prefix = "func cap";
 	} else {
 		ice_debug(hw, ICE_DBG_INIT, "wrong opcode\n");
 		return;
@@ -1450,28 +1529,29 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 		case ICE_AQC_CAPS_VALID_FUNCTIONS:
 			caps->valid_functions = number;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: Valid Functions = %d\n",
+				  "%s: valid functions = %d\n", prefix,
 				  caps->valid_functions);
 			break;
 		case ICE_AQC_CAPS_SRIOV:
 			caps->sr_iov_1_1 = (number == 1);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: SR-IOV = %d\n", caps->sr_iov_1_1);
+				  "%s: SR-IOV = %d\n", prefix,
+				  caps->sr_iov_1_1);
 			break;
 		case ICE_AQC_CAPS_VF:
 			if (dev_p) {
 				dev_p->num_vfs_exposed = number;
 				ice_debug(hw, ICE_DBG_INIT,
-					  "HW caps: VFs exposed = %d\n",
+					  "%s: VFs exposed = %d\n", prefix,
 					  dev_p->num_vfs_exposed);
 			} else if (func_p) {
 				func_p->num_allocd_vfs = number;
 				func_p->vf_base_id = logical_id;
 				ice_debug(hw, ICE_DBG_INIT,
-					  "HW caps: VFs allocated = %d\n",
+					  "%s: VFs allocated = %d\n", prefix,
 					  func_p->num_allocd_vfs);
 				ice_debug(hw, ICE_DBG_INIT,
-					  "HW caps: VF base_id = %d\n",
+					  "%s: VF base_id = %d\n", prefix,
 					  func_p->vf_base_id);
 			}
 			break;
@@ -1479,68 +1559,69 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 			if (dev_p) {
 				dev_p->num_vsi_allocd_to_host = number;
 				ice_debug(hw, ICE_DBG_INIT,
-					  "HW caps: Dev.VSI cnt = %d\n",
+					  "%s: num VSI alloc to host = %d\n",
+					  prefix,
 					  dev_p->num_vsi_allocd_to_host);
 			} else if (func_p) {
-				func_p->guar_num_vsi = ice_get_guar_num_vsi(hw);
+				func_p->guar_num_vsi =
+					ice_get_num_per_func(hw, ICE_MAX_VSI);
 				ice_debug(hw, ICE_DBG_INIT,
-					  "HW caps: Func.VSI cnt = %d\n",
-					  number);
+					  "%s: num guaranteed VSI (fw) = %d\n",
+					  prefix, number);
+				ice_debug(hw, ICE_DBG_INIT,
+					  "%s: num guaranteed VSI = %d\n",
+					  prefix, func_p->guar_num_vsi);
 			}
 			break;
 		case ICE_AQC_CAPS_RSS:
 			caps->rss_table_size = number;
 			caps->rss_table_entry_width = logical_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: RSS table size = %d\n",
+				  "%s: RSS table size = %d\n", prefix,
 				  caps->rss_table_size);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: RSS table width = %d\n",
+				  "%s: RSS table width = %d\n", prefix,
 				  caps->rss_table_entry_width);
 			break;
 		case ICE_AQC_CAPS_RXQS:
 			caps->num_rxq = number;
 			caps->rxq_first_id = phys_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: Num Rx Qs = %d\n", caps->num_rxq);
+				  "%s: num Rx queues = %d\n", prefix,
+				  caps->num_rxq);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: Rx first queue ID = %d\n",
+				  "%s: Rx first queue ID = %d\n", prefix,
 				  caps->rxq_first_id);
 			break;
 		case ICE_AQC_CAPS_TXQS:
 			caps->num_txq = number;
 			caps->txq_first_id = phys_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: Num Tx Qs = %d\n", caps->num_txq);
+				  "%s: num Tx queues = %d\n", prefix,
+				  caps->num_txq);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: Tx first queue ID = %d\n",
+				  "%s: Tx first queue ID = %d\n", prefix,
 				  caps->txq_first_id);
 			break;
 		case ICE_AQC_CAPS_MSIX:
 			caps->num_msix_vectors = number;
 			caps->msix_vector_first_id = phys_id;
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: MSIX vector count = %d\n",
+				  "%s: MSIX vector count = %d\n", prefix,
 				  caps->num_msix_vectors);
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: MSIX first vector index = %d\n",
+				  "%s: MSIX first vector index = %d\n", prefix,
 				  caps->msix_vector_first_id);
 			break;
 		case ICE_AQC_CAPS_MAX_MTU:
 			caps->max_mtu = number;
-			if (dev_p)
-				ice_debug(hw, ICE_DBG_INIT,
-					  "HW caps: Dev.MaxMTU = %d\n",
-					  caps->max_mtu);
-			else if (func_p)
-				ice_debug(hw, ICE_DBG_INIT,
-					  "HW caps: func.MaxMTU = %d\n",
-					  caps->max_mtu);
+			ice_debug(hw, ICE_DBG_INIT, "%s: max MTU = %d\n",
+				  prefix, caps->max_mtu);
 			break;
 		default:
 			ice_debug(hw, ICE_DBG_INIT,
-				  "HW caps: Unknown capability[%d]: 0x%x\n", i,
-				  cap);
+				  "%s: unknown capability[%d]: 0x%x\n", prefix,
+				  i, cap);
 			break;
 		}
 	}
@@ -1548,7 +1629,7 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 
 /**
  * ice_aq_discover_caps - query function/device capabilities
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @buf: a virtual buffer to hold the capabilities
  * @buf_size: Size of the virtual buffer
  * @cap_count: cap count needed if AQ err==ENOMEM
@@ -1587,8 +1668,8 @@ ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count,
  * @hw: pointer to the hardware structure
  * @opc: capabilities type to discover - pass in the command opcode
  */
-static enum ice_status ice_discover_caps(struct ice_hw *hw,
-					 enum ice_adminq_opc opc)
+static enum ice_status
+ice_discover_caps(struct ice_hw *hw, enum ice_adminq_opc opc)
 {
 	enum ice_status status;
 	u32 cap_count;
@@ -1647,7 +1728,7 @@ enum ice_status ice_get_caps(struct ice_hw *hw)
 
 /**
  * ice_aq_manage_mac_write - manage MAC address write command
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @mac_addr: MAC address to be written as LAA/LAA+WoL/Port address
  * @flags: flags to control write behavior
  * @cd: pointer to command details structure or NULL
@@ -1655,7 +1736,7 @@ enum ice_status ice_get_caps(struct ice_hw *hw)
  * This function is used to write MAC address to the NVM (0x0108).
  */
 enum ice_status
-ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd)
 {
 	struct ice_aqc_manage_mac_write *cmd;
@@ -1667,15 +1748,15 @@ ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
 	cmd->flags = flags;
 
 	/* Prep values for flags, sah, sal */
-	cmd->sah = htons(*((u16 *)mac_addr));
-	cmd->sal = htonl(*((u32 *)(mac_addr + 2)));
+	cmd->sah = htons(*((const u16 *)mac_addr));
+	cmd->sal = htonl(*((const u32 *)(mac_addr + 2)));
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
 }
 
 /**
  * ice_aq_clear_pxe_mode
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Tell the firmware that the driver is taking over from PXE (0x0110).
  */
@@ -1691,7 +1772,7 @@ static enum ice_status ice_aq_clear_pxe_mode(struct ice_hw *hw)
 
 /**
  * ice_clear_pxe_mode - clear pxe operations mode
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Make sure all PXE mode settings are cleared, including things
  * like descriptor fetch/write-back mode.
@@ -1705,16 +1786,20 @@ void ice_clear_pxe_mode(struct ice_hw *hw)
 /**
  * ice_get_link_speed_based_on_phy_type - returns link speed
  * @phy_type_low: lower part of phy_type
+ * @phy_type_high: higher part of phy_type
  *
- * This helper function will convert a phy_type_low to its corresponding link
+ * This helper function will convert an entry in PHY type structure
+ * [phy_type_low, phy_type_high] to its corresponding link speed.
+ * Note: In the structure of [phy_type_low, phy_type_high], there should
+ * be one bit set, as this function will convert one PHY type to its
  * speed.
- * Note: In the structure of phy_type_low, there should be one bit set, as
- * this function will convert one phy type to its speed.
  * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
  * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
  */
-static u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low)
+static u16
+ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high)
 {
+	u16 speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
 	u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
 
 	switch (phy_type_low) {
@@ -1768,46 +1853,115 @@ static u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low)
 	case ICE_PHY_TYPE_LOW_40G_XLAUI:
 		speed_phy_type_low = ICE_AQ_LINK_SPEED_40GB;
 		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+	case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_LAUI2:
+	case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI2:
+	case ICE_PHY_TYPE_LOW_50GBASE_CP:
+	case ICE_PHY_TYPE_LOW_50GBASE_SR:
+	case ICE_PHY_TYPE_LOW_50GBASE_FR:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR:
+	case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+	case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI1:
+		speed_phy_type_low = ICE_AQ_LINK_SPEED_50GB;
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+	case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_CAUI4:
+	case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_AUI4:
+	case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+	case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+	case ICE_PHY_TYPE_LOW_100GBASE_CP2:
+	case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+	case ICE_PHY_TYPE_LOW_100GBASE_DR:
+		speed_phy_type_low = ICE_AQ_LINK_SPEED_100GB;
+		break;
 	default:
 		speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
 		break;
 	}
 
-	return speed_phy_type_low;
+	switch (phy_type_high) {
+	case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2:
+		speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB;
+		break;
+	default:
+		speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
+		break;
+	}
+
+	if (speed_phy_type_low == ICE_AQ_LINK_SPEED_UNKNOWN &&
+	    speed_phy_type_high == ICE_AQ_LINK_SPEED_UNKNOWN)
+		return ICE_AQ_LINK_SPEED_UNKNOWN;
+	else if (speed_phy_type_low != ICE_AQ_LINK_SPEED_UNKNOWN &&
+		 speed_phy_type_high != ICE_AQ_LINK_SPEED_UNKNOWN)
+		return ICE_AQ_LINK_SPEED_UNKNOWN;
+	else if (speed_phy_type_low != ICE_AQ_LINK_SPEED_UNKNOWN &&
+		 speed_phy_type_high == ICE_AQ_LINK_SPEED_UNKNOWN)
+		return speed_phy_type_low;
+	else
+		return speed_phy_type_high;
 }
 
 /**
  * ice_update_phy_type
  * @phy_type_low: pointer to the lower part of phy_type
+ * @phy_type_high: pointer to the higher part of phy_type
  * @link_speeds_bitmap: targeted link speeds bitmap
  *
  * Note: For the link_speeds_bitmap structure, you can check it at
  * [ice_aqc_get_link_status->link_speed]. Caller can pass in
  * link_speeds_bitmap include multiple speeds.
  *
- * The value of phy_type_low will present a certain link speed. This helper
- * function will turn on bits in the phy_type_low based on the value of
+ * Each entry in this [phy_type_low, phy_type_high] structure will
+ * present a certain link speed. This helper function will turn on bits
+ * in [phy_type_low, phy_type_high] structure based on the value of
  * link_speeds_bitmap input parameter.
  */
-void ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap)
+void
+ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
+		    u16 link_speeds_bitmap)
 {
-	u16 speed = ICE_AQ_LINK_SPEED_UNKNOWN;
+	u64 pt_high;
 	u64 pt_low;
 	int index;
+	u16 speed;
 
 	/* We first check with low part of phy_type */
 	for (index = 0; index <= ICE_PHY_TYPE_LOW_MAX_INDEX; index++) {
 		pt_low = BIT_ULL(index);
-		speed = ice_get_link_speed_based_on_phy_type(pt_low);
+		speed = ice_get_link_speed_based_on_phy_type(pt_low, 0);
 
 		if (link_speeds_bitmap & speed)
 			*phy_type_low |= BIT_ULL(index);
 	}
+
+	/* We then check with high part of phy_type */
+	for (index = 0; index <= ICE_PHY_TYPE_HIGH_MAX_INDEX; index++) {
+		pt_high = BIT_ULL(index);
+		speed = ice_get_link_speed_based_on_phy_type(0, pt_high);
+
+		if (link_speeds_bitmap & speed)
+			*phy_type_high |= BIT_ULL(index);
+	}
 }
 
 /**
  * ice_aq_set_phy_cfg
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @lport: logical port number
  * @cfg: structure with PHY configuration data to be set
  * @cd: pointer to command details structure or NULL
@@ -1826,6 +1980,15 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
 	if (!cfg)
 		return ICE_ERR_PARAM;
 
+	/* Ensure that only valid bits of cfg->caps can be turned on. */
+	if (cfg->caps & ~ICE_AQ_PHY_ENA_VALID_MASK) {
+		ice_debug(hw, ICE_DBG_PHY,
+			  "Invalid bit is set in ice_aqc_set_phy_cfg_data->caps : 0x%x\n",
+			  cfg->caps);
+
+		cfg->caps &= ICE_AQ_PHY_ENA_VALID_MASK;
+	}
+
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg);
 	desc.params.set_phy.lport_num = lport;
 	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
@@ -1839,36 +2002,37 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
  */
 enum ice_status ice_update_link_info(struct ice_port_info *pi)
 {
-	struct ice_aqc_get_phy_caps_data *pcaps;
-	struct ice_phy_info *phy_info;
+	struct ice_link_status *li;
 	enum ice_status status;
-	struct ice_hw *hw;
 
 	if (!pi)
 		return ICE_ERR_PARAM;
 
-	hw = pi->hw;
-
-	pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL);
-	if (!pcaps)
-		return ICE_ERR_NO_MEMORY;
+	li = &pi->phy.link_info;
 
-	phy_info = &pi->phy;
 	status = ice_aq_get_link_info(pi, true, NULL, NULL);
 	if (status)
-		goto out;
+		return status;
+
+	if (li->link_info & ICE_AQ_MEDIA_AVAILABLE) {
+		struct ice_aqc_get_phy_caps_data *pcaps;
+		struct ice_hw *hw;
+
+		hw = pi->hw;
+		pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps),
+				     GFP_KERNEL);
+		if (!pcaps)
+			return ICE_ERR_NO_MEMORY;
 
-	if (phy_info->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
 		status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG,
 					     pcaps, NULL);
-		if (status)
-			goto out;
+		if (!status)
+			memcpy(li->module_type, &pcaps->module_type,
+			       sizeof(li->module_type));
 
-		memcpy(phy_info->link_info.module_type, &pcaps->module_type,
-		       sizeof(phy_info->link_info.module_type));
+		devm_kfree(ice_hw_to_dev(hw), pcaps);
 	}
-out:
-	devm_kfree(ice_hw_to_dev(hw), pcaps);
+
 	return status;
 }
 
@@ -1913,7 +2077,7 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update)
 	if (!pcaps)
 		return ICE_ERR_NO_MEMORY;
 
-	/* Get the current phy config */
+	/* Get the current PHY config */
 	status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
 				     NULL);
 	if (status) {
@@ -1924,8 +2088,10 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update)
 	/* clear the old pause settings */
 	cfg.caps = pcaps->caps & ~(ICE_AQC_PHY_EN_TX_LINK_PAUSE |
 				   ICE_AQC_PHY_EN_RX_LINK_PAUSE);
+
 	/* set the new capabilities */
 	cfg.caps |= pause_mask;
+
 	/* If the capabilities have changed, then set the new config */
 	if (cfg.caps != pcaps->caps) {
 		int retry_count, retry_max = 10;
@@ -1934,6 +2100,7 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update)
 		if (ena_auto_link_update)
 			cfg.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
 		/* Copy over all the old settings */
+		cfg.phy_type_high = pcaps->phy_type_high;
 		cfg.phy_type_low = pcaps->phy_type_low;
 		cfg.low_power_ctrl = pcaps->low_power_ctrl;
 		cfg.eee_cap = pcaps->eee_cap;
@@ -1970,6 +2137,74 @@ out:
 }
 
 /**
+ * ice_copy_phy_caps_to_cfg - Copy PHY ability data to configuration data
+ * @caps: PHY ability structure to copy date from
+ * @cfg: PHY configuration structure to copy data to
+ *
+ * Helper function to copy AQC PHY get ability data to PHY set configuration
+ * data structure
+ */
+void
+ice_copy_phy_caps_to_cfg(struct ice_aqc_get_phy_caps_data *caps,
+			 struct ice_aqc_set_phy_cfg_data *cfg)
+{
+	if (!caps || !cfg)
+		return;
+
+	cfg->phy_type_low = caps->phy_type_low;
+	cfg->phy_type_high = caps->phy_type_high;
+	cfg->caps = caps->caps;
+	cfg->low_power_ctrl = caps->low_power_ctrl;
+	cfg->eee_cap = caps->eee_cap;
+	cfg->eeer_value = caps->eeer_value;
+	cfg->link_fec_opt = caps->link_fec_options;
+}
+
+/**
+ * ice_cfg_phy_fec - Configure PHY FEC data based on FEC mode
+ * @cfg: PHY configuration data to set FEC mode
+ * @fec: FEC mode to configure
+ *
+ * Caller should copy ice_aqc_get_phy_caps_data.caps ICE_AQC_PHY_EN_AUTO_FEC
+ * (bit 7) and ice_aqc_get_phy_caps_data.link_fec_options to cfg.caps
+ * ICE_AQ_PHY_ENA_AUTO_FEC (bit 7) and cfg.link_fec_options before calling.
+ */
+void
+ice_cfg_phy_fec(struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec)
+{
+	switch (fec) {
+	case ICE_FEC_BASER:
+		/* Clear auto FEC and RS bits, and AND BASE-R ability
+		 * bits and OR request bits.
+		 */
+		cfg->caps &= ~ICE_AQC_PHY_EN_AUTO_FEC;
+		cfg->link_fec_opt &= ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN |
+				     ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN;
+		cfg->link_fec_opt |= ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ |
+				     ICE_AQC_PHY_FEC_25G_KR_REQ;
+		break;
+	case ICE_FEC_RS:
+		/* Clear auto FEC and BASE-R bits, and AND RS ability
+		 * bits and OR request bits.
+		 */
+		cfg->caps &= ~ICE_AQC_PHY_EN_AUTO_FEC;
+		cfg->link_fec_opt &= ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN;
+		cfg->link_fec_opt |= ICE_AQC_PHY_FEC_25G_RS_528_REQ |
+				     ICE_AQC_PHY_FEC_25G_RS_544_REQ;
+		break;
+	case ICE_FEC_NONE:
+		/* Clear auto FEC and all FEC option bits. */
+		cfg->caps &= ~ICE_AQC_PHY_EN_AUTO_FEC;
+		cfg->link_fec_opt &= ~ICE_AQC_PHY_FEC_MASK;
+		break;
+	case ICE_FEC_AUTO:
+		/* AND auto FEC bit, and all caps bits. */
+		cfg->caps &= ICE_AQC_PHY_CAPS_MASK;
+		break;
+	}
+}
+
+/**
  * ice_get_link_status - get status of the HW network link
  * @pi: port information structure
  * @link_up: pointer to bool (true/false = linkup/linkdown)
@@ -2032,6 +2267,83 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 }
 
 /**
+ * ice_aq_set_event_mask
+ * @hw: pointer to the HW struct
+ * @port_num: port number of the physical function
+ * @mask: event mask to be set
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set event mask (0x0613)
+ */
+enum ice_status
+ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
+		      struct ice_sq_cd *cd)
+{
+	struct ice_aqc_set_event_mask *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.set_event_mask;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_event_mask);
+
+	cmd->lport_num = port_num;
+
+	cmd->event_mask = cpu_to_le16(mask);
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_set_mac_loopback
+ * @hw: pointer to the HW struct
+ * @ena_lpbk: Enable or Disable loopback
+ * @cd: pointer to command details structure or NULL
+ *
+ * Enable/disable loopback on a given port
+ */
+enum ice_status
+ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_set_mac_lb *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.set_mac_lb;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_mac_lb);
+	if (ena_lpbk)
+		cmd->lb_mode = ICE_AQ_MAC_LB_EN;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_set_port_id_led
+ * @pi: pointer to the port information
+ * @is_orig_mode: is this LED set to original mode (by the net-list)
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set LED value for the given port (0x06e9)
+ */
+enum ice_status
+ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
+		       struct ice_sq_cd *cd)
+{
+	struct ice_aqc_set_port_id_led *cmd;
+	struct ice_hw *hw = pi->hw;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.set_port_id_led;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_id_led);
+
+	if (is_orig_mode)
+		cmd->ident_mode = ICE_AQC_PORT_IDENT_LED_ORIG;
+	else
+		cmd->ident_mode = ICE_AQC_PORT_IDENT_LED_BLINK;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
  * __ice_aq_get_set_rss_lut
  * @hw: pointer to the hardware structure
  * @vsi_id: VSI FW index
@@ -2165,7 +2477,7 @@ ice_aq_set_rss_lut(struct ice_hw *hw, u16 vsi_handle, u8 lut_type,
 
 /**
  * __ice_aq_get_set_rss_key
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_id: VSI FW index
  * @key: pointer to key info struct
  * @set: set true to set the key, false to get the key
@@ -2200,7 +2512,7 @@ ice_status __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id,
 
 /**
  * ice_aq_get_rss_key
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: software VSI handle
  * @key: pointer to key info struct
  *
@@ -2219,7 +2531,7 @@ ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle,
 
 /**
  * ice_aq_set_rss_key
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: software VSI handle
  * @keys: pointer to key info struct
  *
@@ -2304,7 +2616,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps,
  * @num_qgrps: number of groups in the list
  * @qg_list: the list of groups to disable
  * @buf_size: the total size of the qg_list buffer in bytes
- * @rst_src: if called due to reset, specifies the RST source
+ * @rst_src: if called due to reset, specifies the reset source
  * @vmvf_num: the relative VM or VF number that is undergoing the reset
  * @cd: pointer to command details structure or NULL
  *
@@ -2318,6 +2630,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 {
 	struct ice_aqc_dis_txqs *cmd;
 	struct ice_aq_desc desc;
+	enum ice_status status;
 	u16 i, sz = 0;
 
 	cmd = &desc.params.dis_txqs;
@@ -2343,7 +2656,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 		break;
 	case ICE_VF_RESET:
 		cmd->cmd_type = ICE_AQC_Q_DIS_CMD_VF_RESET;
-		/* In this case, FW expects vmvf_num to be absolute VF id */
+		/* In this case, FW expects vmvf_num to be absolute VF ID */
 		cmd->vmvf_and_timeout |=
 			cpu_to_le16((vmvf_num + hw->func_caps.vf_base_id) &
 				    ICE_AQC_Q_DIS_VMVF_NUM_M);
@@ -2353,6 +2666,8 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 		break;
 	}
 
+	/* flush pipe on time out */
+	cmd->cmd_type |= ICE_AQC_Q_DIS_CMD_FLUSH_PIPE;
 	/* If no queue group info, we are in a reset flow. Issue the AQ */
 	if (!qg_list)
 		goto do_aq;
@@ -2378,7 +2693,17 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 		return ICE_ERR_PARAM;
 
 do_aq:
-	return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+	status = ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+	if (status) {
+		if (!qg_list)
+			ice_debug(hw, ICE_DBG_SCHED, "VM%d disable failed %d\n",
+				  vmvf_num, hw->adminq.sq_last_status);
+		else
+			ice_debug(hw, ICE_DBG_SCHED, "disable queue %d failed %d\n",
+				  le16_to_cpu(qg_list[0].q_id[0]),
+				  hw->adminq.sq_last_status);
+	}
+	return status;
 }
 
 /* End of FW Admin Queue command wrappers */
@@ -2389,8 +2714,8 @@ do_aq:
  * @dest_ctx: the context to be written to
  * @ce_info:  a description of the struct to be filled
  */
-static void ice_write_byte(u8 *src_ctx, u8 *dest_ctx,
-			   const struct ice_ctx_ele *ce_info)
+static void
+ice_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
 {
 	u8 src_byte, dest_byte, mask;
 	u8 *from, *dest;
@@ -2428,8 +2753,8 @@ static void ice_write_byte(u8 *src_ctx, u8 *dest_ctx,
  * @dest_ctx: the context to be written to
  * @ce_info:  a description of the struct to be filled
  */
-static void ice_write_word(u8 *src_ctx, u8 *dest_ctx,
-			   const struct ice_ctx_ele *ce_info)
+static void
+ice_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
 {
 	u16 src_word, mask;
 	__le16 dest_word;
@@ -2471,8 +2796,8 @@ static void ice_write_word(u8 *src_ctx, u8 *dest_ctx,
  * @dest_ctx: the context to be written to
  * @ce_info:  a description of the struct to be filled
  */
-static void ice_write_dword(u8 *src_ctx, u8 *dest_ctx,
-			    const struct ice_ctx_ele *ce_info)
+static void
+ice_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
 {
 	u32 src_dword, mask;
 	__le32 dest_dword;
@@ -2522,8 +2847,8 @@ static void ice_write_dword(u8 *src_ctx, u8 *dest_ctx,
  * @dest_ctx: the context to be written to
  * @ce_info:  a description of the struct to be filled
  */
-static void ice_write_qword(u8 *src_ctx, u8 *dest_ctx,
-			    const struct ice_ctx_ele *ce_info)
+static void
+ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
 {
 	u64 src_qword, mask;
 	__le64 dest_qword;
@@ -2605,24 +2930,50 @@ ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info)
 }
 
 /**
+ * ice_get_lan_q_ctx - get the LAN queue context for the given VSI and TC
+ * @hw: pointer to the HW struct
+ * @vsi_handle: software VSI handle
+ * @tc: TC number
+ * @q_handle: software queue handle
+ */
+static struct ice_q_ctx *
+ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle)
+{
+	struct ice_vsi_ctx *vsi;
+	struct ice_q_ctx *q_ctx;
+
+	vsi = ice_get_vsi_ctx(hw, vsi_handle);
+	if (!vsi)
+		return NULL;
+	if (q_handle >= vsi->num_lan_q_entries[tc])
+		return NULL;
+	if (!vsi->lan_q_ctx[tc])
+		return NULL;
+	q_ctx = vsi->lan_q_ctx[tc];
+	return &q_ctx[q_handle];
+}
+
+/**
  * ice_ena_vsi_txq
  * @pi: port information structure
  * @vsi_handle: software VSI handle
- * @tc: tc number
+ * @tc: TC number
+ * @q_handle: software queue handle
  * @num_qgrps: Number of added queue groups
  * @buf: list of queue groups to be added
  * @buf_size: size of buffer for indirect command
  * @cd: pointer to command details structure or NULL
  *
- * This function adds one lan q
+ * This function adds one LAN queue
  */
 enum ice_status
-ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps,
-		struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
+ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle,
+		u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
 		struct ice_sq_cd *cd)
 {
 	struct ice_aqc_txsched_elem_data node = { 0 };
 	struct ice_sched_node *parent;
+	struct ice_q_ctx *q_ctx;
 	enum ice_status status;
 	struct ice_hw *hw;
 
@@ -2639,6 +2990,14 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps,
 
 	mutex_lock(&pi->sched_lock);
 
+	q_ctx = ice_get_lan_q_ctx(hw, vsi_handle, tc, q_handle);
+	if (!q_ctx) {
+		ice_debug(hw, ICE_DBG_SCHED, "Enaq: invalid queue handle %d\n",
+			  q_handle);
+		status = ICE_ERR_PARAM;
+		goto ena_txq_exit;
+	}
+
 	/* find a parent node */
 	parent = ice_sched_get_free_qparent(pi, vsi_handle, tc,
 					    ICE_SCHED_NODE_OWNER_LAN);
@@ -2658,19 +3017,24 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps,
 	 * Bit 5-6.
 	 * - Bit 7 is reserved.
 	 * Without setting the generic section as valid in valid_sections, the
-	 * Admin Q command will fail with error code ICE_AQ_RC_EINVAL.
+	 * Admin queue command will fail with error code ICE_AQ_RC_EINVAL.
 	 */
 	buf->txqs[0].info.valid_sections = ICE_AQC_ELEM_VALID_GENERIC;
 
-	/* add the lan q */
+	/* add the LAN queue */
 	status = ice_aq_add_lan_txq(hw, num_qgrps, buf, buf_size, cd);
-	if (status)
+	if (status) {
+		ice_debug(hw, ICE_DBG_SCHED, "enable queue %d failed %d\n",
+			  le16_to_cpu(buf->txqs[0].txq_id),
+			  hw->adminq.sq_last_status);
 		goto ena_txq_exit;
+	}
 
 	node.node_teid = buf->txqs[0].q_teid;
 	node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF;
+	q_ctx->q_handle = q_handle;
 
-	/* add a leaf node into schduler tree q layer */
+	/* add a leaf node into schduler tree queue layer */
 	status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, &node);
 
 ena_txq_exit:
@@ -2681,35 +3045,42 @@ ena_txq_exit:
 /**
  * ice_dis_vsi_txq
  * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ * @tc: TC number
  * @num_queues: number of queues
+ * @q_handles: pointer to software queue handle array
  * @q_ids: pointer to the q_id array
  * @q_teids: pointer to queue node teids
- * @rst_src: if called due to reset, specifies the RST source
+ * @rst_src: if called due to reset, specifies the reset source
  * @vmvf_num: the relative VM or VF number that is undergoing the reset
  * @cd: pointer to command details structure or NULL
  *
  * This function removes queues and their corresponding nodes in SW DB
  */
 enum ice_status
-ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
-		u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num,
+ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues,
+		u16 *q_handles, u16 *q_ids, u32 *q_teids,
+		enum ice_disq_rst_src rst_src, u16 vmvf_num,
 		struct ice_sq_cd *cd)
 {
 	enum ice_status status = ICE_ERR_DOES_NOT_EXIST;
 	struct ice_aqc_dis_txq_item qg_list;
+	struct ice_q_ctx *q_ctx;
 	u16 i;
 
 	if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
 		return ICE_ERR_CFG;
 
-	/* if queue is disabled already yet the disable queue command has to be
-	 * sent to complete the VF reset, then call ice_aq_dis_lan_txq without
-	 * any queue information
-	 */
-
-	if (!num_queues && rst_src)
-		return ice_aq_dis_lan_txq(pi->hw, 0, NULL, 0, rst_src, vmvf_num,
-					  NULL);
+	if (!num_queues) {
+		/* if queue is disabled already yet the disable queue command
+		 * has to be sent to complete the VF reset, then call
+		 * ice_aq_dis_lan_txq without any queue information
+		 */
+		if (rst_src)
+			return ice_aq_dis_lan_txq(pi->hw, 0, NULL, 0, rst_src,
+						  vmvf_num, NULL);
+		return ICE_ERR_CFG;
+	}
 
 	mutex_lock(&pi->sched_lock);
 
@@ -2719,6 +3090,17 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
 		node = ice_sched_find_node_by_teid(pi->root, q_teids[i]);
 		if (!node)
 			continue;
+		q_ctx = ice_get_lan_q_ctx(pi->hw, vsi_handle, tc, q_handles[i]);
+		if (!q_ctx) {
+			ice_debug(pi->hw, ICE_DBG_SCHED, "invalid queue handle%d\n",
+				  q_handles[i]);
+			continue;
+		}
+		if (q_ctx->q_handle != q_handles[i]) {
+			ice_debug(pi->hw, ICE_DBG_SCHED, "Err:handles %d %d\n",
+				  q_ctx->q_handle, q_handles[i]);
+			continue;
+		}
 		qg_list.parent_teid = node->info.parent_teid;
 		qg_list.num_qs = 1;
 		qg_list.q_id[0] = cpu_to_le16(q_ids[i]);
@@ -2729,18 +3111,19 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
 		if (status)
 			break;
 		ice_free_sched_node(pi, node);
+		q_ctx->q_handle = ICE_INVAL_Q_HANDLE;
 	}
 	mutex_unlock(&pi->sched_lock);
 	return status;
 }
 
 /**
- * ice_cfg_vsi_qs - configure the new/exisiting VSI queues
+ * ice_cfg_vsi_qs - configure the new/existing VSI queues
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  * @tc_bitmap: TC bitmap
  * @maxqs: max queues array per TC
- * @owner: lan or rdma
+ * @owner: LAN or RDMA
  *
  * This function adds/updates the VSI queues per TC.
  */
@@ -2759,7 +3142,7 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
 
 	mutex_lock(&pi->sched_lock);
 
-	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+	ice_for_each_traffic_class(i) {
 		/* configuration is possible only if TC node is present */
 		if (!ice_sched_get_tc_node(pi, i))
 			continue;
@@ -2775,13 +3158,13 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
 }
 
 /**
- * ice_cfg_vsi_lan - configure VSI lan queues
+ * ice_cfg_vsi_lan - configure VSI LAN queues
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  * @tc_bitmap: TC bitmap
- * @max_lanqs: max lan queues array per TC
+ * @max_lanqs: max LAN queues array per TC
  *
- * This function adds/updates the VSI lan queues per TC.
+ * This function adds/updates the VSI LAN queues per TC.
  */
 enum ice_status
 ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
@@ -2793,7 +3176,7 @@ ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
 
 /**
  * ice_replay_pre_init - replay pre initialization
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Initializes required config data for VSI, FD, ACL, and RSS before replay.
  */
@@ -2817,7 +3200,7 @@ static enum ice_status ice_replay_pre_init(struct ice_hw *hw)
 
 /**
  * ice_replay_vsi - replay VSI configuration
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: driver VSI handle
  *
  * Restore all VSI configuration after reset. It is required to call this
@@ -2844,7 +3227,7 @@ enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle)
 
 /**
  * ice_replay_post - post replay configuration cleanup
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Post replay cleanup.
  */
@@ -2863,8 +3246,9 @@ void ice_replay_post(struct ice_hw *hw)
  * @prev_stat: ptr to previous loaded stat value
  * @cur_stat: ptr to current stat value
  */
-void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg,
-		       bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat)
+void
+ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg,
+		  bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat)
 {
 	u64 new_data;
 
@@ -2894,8 +3278,9 @@ void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg,
  * @prev_stat: ptr to previous loaded stat value
  * @cur_stat: ptr to current stat value
  */
-void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
-		       u64 *prev_stat, u64 *cur_stat)
+void
+ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
+		  u64 *prev_stat, u64 *cur_stat)
 {
 	u32 new_data;
 
@@ -2914,3 +3299,28 @@ void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		/* to manage the potential roll-over */
 		*cur_stat = (new_data + BIT_ULL(32)) - *prev_stat;
 }
+
+/**
+ * ice_sched_query_elem - query element information from HW
+ * @hw: pointer to the HW struct
+ * @node_teid: node TEID to be queried
+ * @buf: buffer to element information
+ *
+ * This function queries HW element information
+ */
+enum ice_status
+ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
+		     struct ice_aqc_get_elem *buf)
+{
+	u16 buf_size, num_elem_ret = 0;
+	enum ice_status status;
+
+	buf_size = sizeof(*buf);
+	memset(buf, 0, buf_size);
+	buf->generic[0].node_teid = cpu_to_le32(node_teid);
+	status = ice_aq_query_sched_elems(hw, 1, buf, buf_size, &num_elem_ret,
+					  NULL);
+	if (status || num_elem_ret != 1)
+		ice_debug(hw, ICE_DBG_SCHED, "query element failed\n");
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index cf760c24a6aa..d1f8353fe6bb 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -9,8 +9,10 @@
 #include "ice_switch.h"
 #include <linux/avf/virtchnl.h>
 
-void ice_debug_cq(struct ice_hw *hw, u32 mask, void *desc, void *buf,
-		  u16 buf_len);
+enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw);
+
+void
+ice_debug_cq(struct ice_hw *hw, u32 mask, void *desc, void *buf, u16 buf_len);
 enum ice_status ice_init_hw(struct ice_hw *hw);
 void ice_deinit_hw(struct ice_hw *hw);
 enum ice_status ice_check_reset(struct ice_hw *hw);
@@ -29,6 +31,8 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res);
 enum ice_status ice_init_nvm(struct ice_hw *hw);
 enum ice_status
+ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words, u16 *data);
+enum ice_status
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		struct ice_aq_desc *desc, void *buf, u16 buf_size,
 		struct ice_sq_cd *cd);
@@ -70,9 +74,10 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 		    struct ice_aqc_get_phy_caps_data *caps,
 		    struct ice_sq_cd *cd);
 void
-ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap);
+ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
+		    u16 link_speeds_bitmap);
 enum ice_status
-ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd);
 enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
 enum ice_status
@@ -81,26 +86,49 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport,
 enum ice_status
 ice_set_fc(struct ice_port_info *pi, u8 *aq_failures,
 	   bool ena_auto_link_update);
-
+void
+ice_cfg_phy_fec(struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec);
+void
+ice_copy_phy_caps_to_cfg(struct ice_aqc_get_phy_caps_data *caps,
+			 struct ice_aqc_set_phy_cfg_data *cfg);
 enum ice_status
 ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 			   struct ice_sq_cd *cd);
 enum ice_status
-ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
-		u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num,
-		struct ice_sq_cd *cmd_details);
+ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
+		     struct ice_link_status *link, struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
+		      struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd);
+
+enum ice_status
+ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
+		       struct ice_sq_cd *cd);
+
+enum ice_status
+ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues,
+		u16 *q_handle, u16 *q_ids, u32 *q_teids,
+		enum ice_disq_rst_src rst_src, u16 vmvf_num,
+		struct ice_sq_cd *cd);
 enum ice_status
 ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap,
 		u16 *max_lanqs);
 enum ice_status
-ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps,
-		struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
+ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle,
+		u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size,
 		struct ice_sq_cd *cd);
 enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle);
 void ice_replay_post(struct ice_hw *hw);
 void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf);
-void ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg,
-		       bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat);
-void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
-		       u64 *prev_stat, u64 *cur_stat);
+void
+ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg,
+		  bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat);
+void
+ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
+		  u64 *prev_stat, u64 *cur_stat);
+enum ice_status
+ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
+		     struct ice_aqc_get_elem *buf);
 #endif /* _ICE_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 2bf5e11f559a..e91ac4df0242 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -51,7 +51,7 @@ static void ice_mailbox_init_regs(struct ice_hw *hw)
 
 /**
  * ice_check_sq_alive
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @cq: pointer to the specific Control queue
  *
  * Returns true if Queue is enabled else false.
@@ -287,7 +287,7 @@ ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
  * @hw: pointer to the hardware structure
  * @cq: pointer to the specific Control queue
  *
- * Configure base address and length registers for the receive (event q)
+ * Configure base address and length registers for the receive (event queue)
  */
 static enum ice_status
 ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
@@ -439,7 +439,7 @@ do {									\
 	/* free the buffer info list */					\
 	if ((qi)->ring.cmd_buf)						\
 		devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);	\
-	/* free dma head */						\
+	/* free DMA head */						\
 	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
 } while (0)
 
@@ -751,7 +751,7 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 
 /**
  * ice_sq_done - check if FW has processed the Admin Send Queue (ATQ)
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @cq: pointer to the specific Control queue
  *
  * Returns true if the firmware has processed all descriptors on the
@@ -767,7 +767,7 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 
 /**
  * ice_sq_send_cmd - send command to Control Queue (ATQ)
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @cq: pointer to the specific Control queue
  * @desc: prefilled descriptor describing the command (non DMA mem)
  * @buf: buffer to use for indirect commands (or NULL for direct commands)
@@ -962,7 +962,7 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode)
 
 /**
  * ice_clean_rq_elem
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @cq: pointer to the specific Control queue
  * @e: event info from the receive descriptor, includes any buffers
  * @pending: number of events that could be left to process
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index 0038a4109c99..44945c2165d8 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -35,7 +35,7 @@ enum ice_ctl_q {
 #define ICE_CTL_Q_SQ_CMD_TIMEOUT	250  /* msecs */
 
 struct ice_ctl_q_ring {
-	void *dma_head;			/* Virtual address to dma head */
+	void *dma_head;			/* Virtual address to DMA head */
 	struct ice_dma_mem desc_buf;	/* descriptor ring memory */
 	void *cmd_buf;			/* command buffer memory */
 
@@ -79,6 +79,7 @@ struct ice_rq_event_info {
 /* Control Queue information */
 struct ice_ctl_q_info {
 	enum ice_ctl_q qtype;
+	enum ice_aq_err rq_last_status;	/* last status on receive queue */
 	struct ice_ctl_q_ring rq;	/* receive queue */
 	struct ice_ctl_q_ring sq;	/* send queue */
 	u32 sq_cmd_timeout;		/* send queue cmd write back timeout */
@@ -86,10 +87,9 @@ struct ice_ctl_q_info {
 	u16 num_sq_entries;		/* send queue depth */
 	u16 rq_buf_size;		/* receive queue buffer size */
 	u16 sq_buf_size;		/* send queue buffer size */
+	enum ice_aq_err sq_last_status;	/* last status on send queue */
 	struct mutex sq_lock;		/* Send queue lock */
 	struct mutex rq_lock;		/* Receive queue lock */
-	enum ice_aq_err sq_last_status;	/* last status on send queue */
-	enum ice_aq_err rq_last_status;	/* last status on receive queue */
 };
 
 #endif /* _ICE_CONTROLQ_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
new file mode 100644
index 000000000000..c2002ded65f6
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -0,0 +1,1403 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Intel Corporation. */
+
+#include "ice_common.h"
+#include "ice_sched.h"
+#include "ice_dcb.h"
+
+/**
+ * ice_aq_get_lldp_mib
+ * @hw: pointer to the HW struct
+ * @bridge_type: type of bridge requested
+ * @mib_type: Local, Remote or both Local and Remote MIBs
+ * @buf: pointer to the caller-supplied buffer to store the MIB block
+ * @buf_size: size of the buffer (in bytes)
+ * @local_len: length of the returned Local LLDP MIB
+ * @remote_len: length of the returned Remote LLDP MIB
+ * @cd: pointer to command details structure or NULL
+ *
+ * Requests the complete LLDP MIB (entire packet). (0x0A00)
+ */
+static enum ice_status
+ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf,
+		    u16 buf_size, u16 *local_len, u16 *remote_len,
+		    struct ice_sq_cd *cd)
+{
+	struct ice_aqc_lldp_get_mib *cmd;
+	struct ice_aq_desc desc;
+	enum ice_status status;
+
+	cmd = &desc.params.lldp_get_mib;
+
+	if (buf_size == 0 || !buf)
+		return ICE_ERR_PARAM;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_get_mib);
+
+	cmd->type = mib_type & ICE_AQ_LLDP_MIB_TYPE_M;
+	cmd->type |= (bridge_type << ICE_AQ_LLDP_BRID_TYPE_S) &
+		ICE_AQ_LLDP_BRID_TYPE_M;
+
+	desc.datalen = cpu_to_le16(buf_size);
+
+	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+	if (!status) {
+		if (local_len)
+			*local_len = le16_to_cpu(cmd->local_len);
+		if (remote_len)
+			*remote_len = le16_to_cpu(cmd->remote_len);
+	}
+
+	return status;
+}
+
+/**
+ * ice_aq_cfg_lldp_mib_change
+ * @hw: pointer to the HW struct
+ * @ena_update: Enable or Disable event posting
+ * @cd: pointer to command details structure or NULL
+ *
+ * Enable or Disable posting of an event on ARQ when LLDP MIB
+ * associated with the interface changes (0x0A01)
+ */
+enum ice_status
+ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
+			   struct ice_sq_cd *cd)
+{
+	struct ice_aqc_lldp_set_mib_change *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.lldp_set_event;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_mib_change);
+
+	if (!ena_update)
+		cmd->command |= ICE_AQ_LLDP_MIB_UPDATE_DIS;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_stop_lldp
+ * @hw: pointer to the HW struct
+ * @shutdown_lldp_agent: True if LLDP Agent needs to be Shutdown
+ *			 False if LLDP Agent needs to be Stopped
+ * @persist: True if Stop/Shutdown of LLDP Agent needs to be persistent across
+ *	     reboots
+ * @cd: pointer to command details structure or NULL
+ *
+ * Stop or Shutdown the embedded LLDP Agent (0x0A05)
+ */
+enum ice_status
+ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
+		 struct ice_sq_cd *cd)
+{
+	struct ice_aqc_lldp_stop *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.lldp_stop;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_stop);
+
+	if (shutdown_lldp_agent)
+		cmd->command |= ICE_AQ_LLDP_AGENT_SHUTDOWN;
+
+	if (persist)
+		cmd->command |= ICE_AQ_LLDP_AGENT_PERSIST_DIS;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_start_lldp
+ * @hw: pointer to the HW struct
+ * @persist: True if Start of LLDP Agent needs to be persistent across reboots
+ * @cd: pointer to command details structure or NULL
+ *
+ * Start the embedded LLDP Agent on all ports. (0x0A06)
+ */
+enum ice_status
+ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_lldp_start *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.lldp_start;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_start);
+
+	cmd->command = ICE_AQ_LLDP_AGENT_START;
+
+	if (persist)
+		cmd->command |= ICE_AQ_LLDP_AGENT_PERSIST_ENA;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
+ * ice_aq_set_lldp_mib - Set the LLDP MIB
+ * @hw: pointer to the HW struct
+ * @mib_type: Local, Remote or both Local and Remote MIBs
+ * @buf: pointer to the caller-supplied buffer to store the MIB block
+ * @buf_size: size of the buffer (in bytes)
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set the LLDP MIB. (0x0A08)
+ */
+static enum ice_status
+ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
+		    struct ice_sq_cd *cd)
+{
+	struct ice_aqc_lldp_set_local_mib *cmd;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.lldp_set_mib;
+
+	if (buf_size == 0 || !buf)
+		return ICE_ERR_PARAM;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_local_mib);
+
+	desc.flags |= cpu_to_le16((u16)ICE_AQ_FLAG_RD);
+	desc.datalen = cpu_to_le16(buf_size);
+
+	cmd->type = mib_type;
+	cmd->length = cpu_to_le16(buf_size);
+
+	return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
+}
+
+/**
+ * ice_get_dcbx_status
+ * @hw: pointer to the HW struct
+ *
+ * Get the DCBX status from the Firmware
+ */
+static u8 ice_get_dcbx_status(struct ice_hw *hw)
+{
+	u32 reg;
+
+	reg = rd32(hw, PRTDCB_GENS);
+	return (u8)((reg & PRTDCB_GENS_DCBX_STATUS_M) >>
+		    PRTDCB_GENS_DCBX_STATUS_S);
+}
+
+/**
+ * ice_parse_ieee_ets_common_tlv
+ * @buf: Data buffer to be parsed for ETS CFG/REC data
+ * @ets_cfg: Container to store parsed data
+ *
+ * Parses the common data of IEEE 802.1Qaz ETS CFG/REC TLV
+ */
+static void
+ice_parse_ieee_ets_common_tlv(u8 *buf, struct ice_dcb_ets_cfg *ets_cfg)
+{
+	u8 offset = 0;
+	int i;
+
+	/* Priority Assignment Table (4 octets)
+	 * Octets:|    1    |    2    |    3    |    4    |
+	 *        -----------------------------------------
+	 *        |pri0|pri1|pri2|pri3|pri4|pri5|pri6|pri7|
+	 *        -----------------------------------------
+	 *   Bits:|7  4|3  0|7  4|3  0|7  4|3  0|7  4|3  0|
+	 *        -----------------------------------------
+	 */
+	for (i = 0; i < 4; i++) {
+		ets_cfg->prio_table[i * 2] =
+			((buf[offset] & ICE_IEEE_ETS_PRIO_1_M) >>
+			 ICE_IEEE_ETS_PRIO_1_S);
+		ets_cfg->prio_table[i * 2 + 1] =
+			((buf[offset] & ICE_IEEE_ETS_PRIO_0_M) >>
+			 ICE_IEEE_ETS_PRIO_0_S);
+		offset++;
+	}
+
+	/* TC Bandwidth Table (8 octets)
+	 * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+	 *        ---------------------------------
+	 *        |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+	 *        ---------------------------------
+	 *
+	 * TSA Assignment Table (8 octets)
+	 * Octets:| 9 | 10| 11| 12| 13| 14| 15| 16|
+	 *        ---------------------------------
+	 *        |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+	 *        ---------------------------------
+	 */
+	ice_for_each_traffic_class(i) {
+		ets_cfg->tcbwtable[i] = buf[offset];
+		ets_cfg->tsatable[i] = buf[ICE_MAX_TRAFFIC_CLASS + offset++];
+	}
+}
+
+/**
+ * ice_parse_ieee_etscfg_tlv
+ * @tlv: IEEE 802.1Qaz ETS CFG TLV
+ * @dcbcfg: Local store to update ETS CFG data
+ *
+ * Parses IEEE 802.1Qaz ETS CFG TLV
+ */
+static void
+ice_parse_ieee_etscfg_tlv(struct ice_lldp_org_tlv *tlv,
+			  struct ice_dcbx_cfg *dcbcfg)
+{
+	struct ice_dcb_ets_cfg *etscfg;
+	u8 *buf = tlv->tlvinfo;
+
+	/* First Octet post subtype
+	 * --------------------------
+	 * |will-|CBS  | Re-  | Max |
+	 * |ing  |     |served| TCs |
+	 * --------------------------
+	 * |1bit | 1bit|3 bits|3bits|
+	 */
+	etscfg = &dcbcfg->etscfg;
+	etscfg->willing = ((buf[0] & ICE_IEEE_ETS_WILLING_M) >>
+			   ICE_IEEE_ETS_WILLING_S);
+	etscfg->cbs = ((buf[0] & ICE_IEEE_ETS_CBS_M) >> ICE_IEEE_ETS_CBS_S);
+	etscfg->maxtcs = ((buf[0] & ICE_IEEE_ETS_MAXTC_M) >>
+			  ICE_IEEE_ETS_MAXTC_S);
+
+	/* Begin parsing at Priority Assignment Table (offset 1 in buf) */
+	ice_parse_ieee_ets_common_tlv(&buf[1], etscfg);
+}
+
+/**
+ * ice_parse_ieee_etsrec_tlv
+ * @tlv: IEEE 802.1Qaz ETS REC TLV
+ * @dcbcfg: Local store to update ETS REC data
+ *
+ * Parses IEEE 802.1Qaz ETS REC TLV
+ */
+static void
+ice_parse_ieee_etsrec_tlv(struct ice_lldp_org_tlv *tlv,
+			  struct ice_dcbx_cfg *dcbcfg)
+{
+	u8 *buf = tlv->tlvinfo;
+
+	/* Begin parsing at Priority Assignment Table (offset 1 in buf) */
+	ice_parse_ieee_ets_common_tlv(&buf[1], &dcbcfg->etsrec);
+}
+
+/**
+ * ice_parse_ieee_pfccfg_tlv
+ * @tlv: IEEE 802.1Qaz PFC CFG TLV
+ * @dcbcfg: Local store to update PFC CFG data
+ *
+ * Parses IEEE 802.1Qaz PFC CFG TLV
+ */
+static void
+ice_parse_ieee_pfccfg_tlv(struct ice_lldp_org_tlv *tlv,
+			  struct ice_dcbx_cfg *dcbcfg)
+{
+	u8 *buf = tlv->tlvinfo;
+
+	/* ----------------------------------------
+	 * |will-|MBC  | Re-  | PFC |  PFC Enable  |
+	 * |ing  |     |served| cap |              |
+	 * -----------------------------------------
+	 * |1bit | 1bit|2 bits|4bits| 1 octet      |
+	 */
+	dcbcfg->pfc.willing = ((buf[0] & ICE_IEEE_PFC_WILLING_M) >>
+			       ICE_IEEE_PFC_WILLING_S);
+	dcbcfg->pfc.mbc = ((buf[0] & ICE_IEEE_PFC_MBC_M) >> ICE_IEEE_PFC_MBC_S);
+	dcbcfg->pfc.pfccap = ((buf[0] & ICE_IEEE_PFC_CAP_M) >>
+			      ICE_IEEE_PFC_CAP_S);
+	dcbcfg->pfc.pfcena = buf[1];
+}
+
+/**
+ * ice_parse_ieee_app_tlv
+ * @tlv: IEEE 802.1Qaz APP TLV
+ * @dcbcfg: Local store to update APP PRIO data
+ *
+ * Parses IEEE 802.1Qaz APP PRIO TLV
+ */
+static void
+ice_parse_ieee_app_tlv(struct ice_lldp_org_tlv *tlv,
+		       struct ice_dcbx_cfg *dcbcfg)
+{
+	u16 offset = 0;
+	u16 typelen;
+	int i = 0;
+	u16 len;
+	u8 *buf;
+
+	typelen = ntohs(tlv->typelen);
+	len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+	buf = tlv->tlvinfo;
+
+	/* Removing sizeof(ouisubtype) and reserved byte from len.
+	 * Remaining len div 3 is number of APP TLVs.
+	 */
+	len -= (sizeof(tlv->ouisubtype) + 1);
+
+	/* Move offset to App Priority Table */
+	offset++;
+
+	/* Application Priority Table (3 octets)
+	 * Octets:|         1          |    2    |    3    |
+	 *        -----------------------------------------
+	 *        |Priority|Rsrvd| Sel |    Protocol ID    |
+	 *        -----------------------------------------
+	 *   Bits:|23    21|20 19|18 16|15                0|
+	 *        -----------------------------------------
+	 */
+	while (offset < len) {
+		dcbcfg->app[i].priority = ((buf[offset] &
+					    ICE_IEEE_APP_PRIO_M) >>
+					   ICE_IEEE_APP_PRIO_S);
+		dcbcfg->app[i].selector = ((buf[offset] &
+					    ICE_IEEE_APP_SEL_M) >>
+					   ICE_IEEE_APP_SEL_S);
+		dcbcfg->app[i].prot_id = (buf[offset + 1] << 0x8) |
+			buf[offset + 2];
+		/* Move to next app */
+		offset += 3;
+		i++;
+		if (i >= ICE_DCBX_MAX_APPS)
+			break;
+	}
+
+	dcbcfg->numapps = i;
+}
+
+/**
+ * ice_parse_ieee_tlv
+ * @tlv: IEEE 802.1Qaz TLV
+ * @dcbcfg: Local store to update ETS REC data
+ *
+ * Get the TLV subtype and send it to parsing function
+ * based on the subtype value
+ */
+static void
+ice_parse_ieee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+	u32 ouisubtype;
+	u8 subtype;
+
+	ouisubtype = ntohl(tlv->ouisubtype);
+	subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >>
+		       ICE_LLDP_TLV_SUBTYPE_S);
+	switch (subtype) {
+	case ICE_IEEE_SUBTYPE_ETS_CFG:
+		ice_parse_ieee_etscfg_tlv(tlv, dcbcfg);
+		break;
+	case ICE_IEEE_SUBTYPE_ETS_REC:
+		ice_parse_ieee_etsrec_tlv(tlv, dcbcfg);
+		break;
+	case ICE_IEEE_SUBTYPE_PFC_CFG:
+		ice_parse_ieee_pfccfg_tlv(tlv, dcbcfg);
+		break;
+	case ICE_IEEE_SUBTYPE_APP_PRI:
+		ice_parse_ieee_app_tlv(tlv, dcbcfg);
+		break;
+	default:
+		break;
+	}
+}
+
+/**
+ * ice_parse_cee_pgcfg_tlv
+ * @tlv: CEE DCBX PG CFG TLV
+ * @dcbcfg: Local store to update ETS CFG data
+ *
+ * Parses CEE DCBX PG CFG TLV
+ */
+static void
+ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv,
+			struct ice_dcbx_cfg *dcbcfg)
+{
+	struct ice_dcb_ets_cfg *etscfg;
+	u8 *buf = tlv->tlvinfo;
+	u16 offset = 0;
+	int i;
+
+	etscfg = &dcbcfg->etscfg;
+
+	if (tlv->en_will_err & ICE_CEE_FEAT_TLV_WILLING_M)
+		etscfg->willing = 1;
+
+	etscfg->cbs = 0;
+	/* Priority Group Table (4 octets)
+	 * Octets:|    1    |    2    |    3    |    4    |
+	 *        -----------------------------------------
+	 *        |pri0|pri1|pri2|pri3|pri4|pri5|pri6|pri7|
+	 *        -----------------------------------------
+	 *   Bits:|7  4|3  0|7  4|3  0|7  4|3  0|7  4|3  0|
+	 *        -----------------------------------------
+	 */
+	for (i = 0; i < 4; i++) {
+		etscfg->prio_table[i * 2] =
+			((buf[offset] & ICE_CEE_PGID_PRIO_1_M) >>
+			 ICE_CEE_PGID_PRIO_1_S);
+		etscfg->prio_table[i * 2 + 1] =
+			((buf[offset] & ICE_CEE_PGID_PRIO_0_M) >>
+			 ICE_CEE_PGID_PRIO_0_S);
+		offset++;
+	}
+
+	/* PG Percentage Table (8 octets)
+	 * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+	 *        ---------------------------------
+	 *        |pg0|pg1|pg2|pg3|pg4|pg5|pg6|pg7|
+	 *        ---------------------------------
+	 */
+	ice_for_each_traffic_class(i)
+		etscfg->tcbwtable[i] = buf[offset++];
+
+	/* Number of TCs supported (1 octet) */
+	etscfg->maxtcs = buf[offset];
+}
+
+/**
+ * ice_parse_cee_pfccfg_tlv
+ * @tlv: CEE DCBX PFC CFG TLV
+ * @dcbcfg: Local store to update PFC CFG data
+ *
+ * Parses CEE DCBX PFC CFG TLV
+ */
+static void
+ice_parse_cee_pfccfg_tlv(struct ice_cee_feat_tlv *tlv,
+			 struct ice_dcbx_cfg *dcbcfg)
+{
+	u8 *buf = tlv->tlvinfo;
+
+	if (tlv->en_will_err & ICE_CEE_FEAT_TLV_WILLING_M)
+		dcbcfg->pfc.willing = 1;
+
+	/* ------------------------
+	 * | PFC Enable | PFC TCs |
+	 * ------------------------
+	 * | 1 octet    | 1 octet |
+	 */
+	dcbcfg->pfc.pfcena = buf[0];
+	dcbcfg->pfc.pfccap = buf[1];
+}
+
+/**
+ * ice_parse_cee_app_tlv
+ * @tlv: CEE DCBX APP TLV
+ * @dcbcfg: Local store to update APP PRIO data
+ *
+ * Parses CEE DCBX APP PRIO TLV
+ */
+static void
+ice_parse_cee_app_tlv(struct ice_cee_feat_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+	u16 len, typelen, offset = 0;
+	struct ice_cee_app_prio *app;
+	u8 i;
+
+	typelen = ntohs(tlv->hdr.typelen);
+	len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+
+	dcbcfg->numapps = len / sizeof(*app);
+	if (!dcbcfg->numapps)
+		return;
+	if (dcbcfg->numapps > ICE_DCBX_MAX_APPS)
+		dcbcfg->numapps = ICE_DCBX_MAX_APPS;
+
+	for (i = 0; i < dcbcfg->numapps; i++) {
+		u8 up, selector;
+
+		app = (struct ice_cee_app_prio *)(tlv->tlvinfo + offset);
+		for (up = 0; up < ICE_MAX_USER_PRIORITY; up++)
+			if (app->prio_map & BIT(up))
+				break;
+
+		dcbcfg->app[i].priority = up;
+
+		/* Get Selector from lower 2 bits, and convert to IEEE */
+		selector = (app->upper_oui_sel & ICE_CEE_APP_SELECTOR_M);
+		switch (selector) {
+		case ICE_CEE_APP_SEL_ETHTYPE:
+			dcbcfg->app[i].selector = ICE_APP_SEL_ETHTYPE;
+			break;
+		case ICE_CEE_APP_SEL_TCPIP:
+			dcbcfg->app[i].selector = ICE_APP_SEL_TCPIP;
+			break;
+		default:
+			/* Keep selector as it is for unknown types */
+			dcbcfg->app[i].selector = selector;
+		}
+
+		dcbcfg->app[i].prot_id = ntohs(app->protocol);
+		/* Move to next app */
+		offset += sizeof(*app);
+	}
+}
+
+/**
+ * ice_parse_cee_tlv
+ * @tlv: CEE DCBX TLV
+ * @dcbcfg: Local store to update DCBX config data
+ *
+ * Get the TLV subtype and send it to parsing function
+ * based on the subtype value
+ */
+static void
+ice_parse_cee_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+	struct ice_cee_feat_tlv *sub_tlv;
+	u8 subtype, feat_tlv_count = 0;
+	u16 len, tlvlen, typelen;
+	u32 ouisubtype;
+
+	ouisubtype = ntohl(tlv->ouisubtype);
+	subtype = (u8)((ouisubtype & ICE_LLDP_TLV_SUBTYPE_M) >>
+		       ICE_LLDP_TLV_SUBTYPE_S);
+	/* Return if not CEE DCBX */
+	if (subtype != ICE_CEE_DCBX_TYPE)
+		return;
+
+	typelen = ntohs(tlv->typelen);
+	tlvlen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+	len = sizeof(tlv->typelen) + sizeof(ouisubtype) +
+		sizeof(struct ice_cee_ctrl_tlv);
+	/* Return if no CEE DCBX Feature TLVs */
+	if (tlvlen <= len)
+		return;
+
+	sub_tlv = (struct ice_cee_feat_tlv *)((char *)tlv + len);
+	while (feat_tlv_count < ICE_CEE_MAX_FEAT_TYPE) {
+		u16 sublen;
+
+		typelen = ntohs(sub_tlv->hdr.typelen);
+		sublen = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+		subtype = (u8)((typelen & ICE_LLDP_TLV_TYPE_M) >>
+			       ICE_LLDP_TLV_TYPE_S);
+		switch (subtype) {
+		case ICE_CEE_SUBTYPE_PG_CFG:
+			ice_parse_cee_pgcfg_tlv(sub_tlv, dcbcfg);
+			break;
+		case ICE_CEE_SUBTYPE_PFC_CFG:
+			ice_parse_cee_pfccfg_tlv(sub_tlv, dcbcfg);
+			break;
+		case ICE_CEE_SUBTYPE_APP_PRI:
+			ice_parse_cee_app_tlv(sub_tlv, dcbcfg);
+			break;
+		default:
+			return;	/* Invalid Sub-type return */
+		}
+		feat_tlv_count++;
+		/* Move to next sub TLV */
+		sub_tlv = (struct ice_cee_feat_tlv *)
+			  ((char *)sub_tlv + sizeof(sub_tlv->hdr.typelen) +
+			   sublen);
+	}
+}
+
+/**
+ * ice_parse_org_tlv
+ * @tlv: Organization specific TLV
+ * @dcbcfg: Local store to update ETS REC data
+ *
+ * Currently only IEEE 802.1Qaz TLV is supported, all others
+ * will be returned
+ */
+static void
+ice_parse_org_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+	u32 ouisubtype;
+	u32 oui;
+
+	ouisubtype = ntohl(tlv->ouisubtype);
+	oui = ((ouisubtype & ICE_LLDP_TLV_OUI_M) >> ICE_LLDP_TLV_OUI_S);
+	switch (oui) {
+	case ICE_IEEE_8021QAZ_OUI:
+		ice_parse_ieee_tlv(tlv, dcbcfg);
+		break;
+	case ICE_CEE_DCBX_OUI:
+		ice_parse_cee_tlv(tlv, dcbcfg);
+		break;
+	default:
+		break;
+	}
+}
+
+/**
+ * ice_lldp_to_dcb_cfg
+ * @lldpmib: LLDPDU to be parsed
+ * @dcbcfg: store for LLDPDU data
+ *
+ * Parse DCB configuration from the LLDPDU
+ */
+static enum ice_status
+ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg)
+{
+	struct ice_lldp_org_tlv *tlv;
+	enum ice_status ret = 0;
+	u16 offset = 0;
+	u16 typelen;
+	u16 type;
+	u16 len;
+
+	if (!lldpmib || !dcbcfg)
+		return ICE_ERR_PARAM;
+
+	/* set to the start of LLDPDU */
+	lldpmib += ETH_HLEN;
+	tlv = (struct ice_lldp_org_tlv *)lldpmib;
+	while (1) {
+		typelen = ntohs(tlv->typelen);
+		type = ((typelen & ICE_LLDP_TLV_TYPE_M) >> ICE_LLDP_TLV_TYPE_S);
+		len = ((typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S);
+		offset += sizeof(typelen) + len;
+
+		/* END TLV or beyond LLDPDU size */
+		if (type == ICE_TLV_TYPE_END || offset > ICE_LLDPDU_SIZE)
+			break;
+
+		switch (type) {
+		case ICE_TLV_TYPE_ORG:
+			ice_parse_org_tlv(tlv, dcbcfg);
+			break;
+		default:
+			break;
+		}
+
+		/* Move to next TLV */
+		tlv = (struct ice_lldp_org_tlv *)
+		      ((char *)tlv + sizeof(tlv->typelen) + len);
+	}
+
+	return ret;
+}
+
+/**
+ * ice_aq_get_dcb_cfg
+ * @hw: pointer to the HW struct
+ * @mib_type: MIB type for the query
+ * @bridgetype: bridge type for the query (remote)
+ * @dcbcfg: store for LLDPDU data
+ *
+ * Query DCB configuration from the firmware
+ */
+enum ice_status
+ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype,
+		   struct ice_dcbx_cfg *dcbcfg)
+{
+	enum ice_status ret;
+	u8 *lldpmib;
+
+	/* Allocate the LLDPDU */
+	lldpmib = devm_kzalloc(ice_hw_to_dev(hw), ICE_LLDPDU_SIZE, GFP_KERNEL);
+	if (!lldpmib)
+		return ICE_ERR_NO_MEMORY;
+
+	ret = ice_aq_get_lldp_mib(hw, bridgetype, mib_type, (void *)lldpmib,
+				  ICE_LLDPDU_SIZE, NULL, NULL, NULL);
+
+	if (!ret)
+		/* Parse LLDP MIB to get DCB configuration */
+		ret = ice_lldp_to_dcb_cfg(lldpmib, dcbcfg);
+
+	devm_kfree(ice_hw_to_dev(hw), lldpmib);
+
+	return ret;
+}
+
+/**
+ * ice_aq_start_stop_dcbx - Start/Stop DCBX service in FW
+ * @hw: pointer to the HW struct
+ * @start_dcbx_agent: True if DCBX Agent needs to be started
+ *		      False if DCBX Agent needs to be stopped
+ * @dcbx_agent_status: FW indicates back the DCBX agent status
+ *		       True if DCBX Agent is active
+ *		       False if DCBX Agent is stopped
+ * @cd: pointer to command details structure or NULL
+ *
+ * Start/Stop the embedded dcbx Agent. In case that this wrapper function
+ * returns ICE_SUCCESS, caller will need to check if FW returns back the same
+ * value as stated in dcbx_agent_status, and react accordingly. (0x0A09)
+ */
+enum ice_status
+ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent,
+		       bool *dcbx_agent_status, struct ice_sq_cd *cd)
+{
+	struct ice_aqc_lldp_stop_start_specific_agent *cmd;
+	enum ice_status status;
+	struct ice_aq_desc desc;
+	u16 opcode;
+
+	cmd = &desc.params.lldp_agent_ctrl;
+
+	opcode = ice_aqc_opc_lldp_stop_start_specific_agent;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, opcode);
+
+	if (start_dcbx_agent)
+		cmd->command = ICE_AQC_START_STOP_AGENT_START_DCBX;
+
+	status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+
+	*dcbx_agent_status = false;
+
+	if (!status &&
+	    cmd->command == ICE_AQC_START_STOP_AGENT_START_DCBX)
+		*dcbx_agent_status = true;
+
+	return status;
+}
+
+/**
+ * ice_aq_get_cee_dcb_cfg
+ * @hw: pointer to the HW struct
+ * @buff: response buffer that stores CEE operational configuration
+ * @cd: pointer to command details structure or NULL
+ *
+ * Get CEE DCBX mode operational configuration from firmware (0x0A07)
+ */
+static enum ice_status
+ice_aq_get_cee_dcb_cfg(struct ice_hw *hw,
+		       struct ice_aqc_get_cee_dcb_cfg_resp *buff,
+		       struct ice_sq_cd *cd)
+{
+	struct ice_aq_desc desc;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cee_dcb_cfg);
+
+	return ice_aq_send_cmd(hw, &desc, (void *)buff, sizeof(*buff), cd);
+}
+
+/**
+ * ice_cee_to_dcb_cfg
+ * @cee_cfg: pointer to CEE configuration struct
+ * @dcbcfg: DCB configuration struct
+ *
+ * Convert CEE configuration from firmware to DCB configuration
+ */
+static void
+ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
+		   struct ice_dcbx_cfg *dcbcfg)
+{
+	u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status);
+	u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift;
+	u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
+	u8 i, err, sync, oper, app_index, ice_app_sel_type;
+	u16 ice_aqc_cee_app_mask, ice_aqc_cee_app_shift;
+	u16 ice_app_prot_id_type;
+
+	/* CEE PG data to ETS config */
+	dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc;
+
+	/* Note that the FW creates the oper_prio_tc nibbles reversed
+	 * from those in the CEE Priority Group sub-TLV.
+	 */
+	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS / 2; i++) {
+		dcbcfg->etscfg.prio_table[i * 2] =
+			((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_0_M) >>
+			 ICE_CEE_PGID_PRIO_0_S);
+		dcbcfg->etscfg.prio_table[i * 2 + 1] =
+			((cee_cfg->oper_prio_tc[i] & ICE_CEE_PGID_PRIO_1_M) >>
+			 ICE_CEE_PGID_PRIO_1_S);
+	}
+
+	ice_for_each_traffic_class(i) {
+		dcbcfg->etscfg.tcbwtable[i] = cee_cfg->oper_tc_bw[i];
+
+		if (dcbcfg->etscfg.prio_table[i] == ICE_CEE_PGID_STRICT) {
+			/* Map it to next empty TC */
+			dcbcfg->etscfg.prio_table[i] = cee_cfg->oper_num_tc - 1;
+			dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_STRICT;
+		} else {
+			dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_ETS;
+		}
+	}
+
+	/* CEE PFC data to ETS config */
+	dcbcfg->pfc.pfcena = cee_cfg->oper_pfc_en;
+	dcbcfg->pfc.pfccap = ICE_MAX_TRAFFIC_CLASS;
+
+	app_index = 0;
+	for (i = 0; i < 3; i++) {
+		if (i == 0) {
+			/* FCoE APP */
+			ice_aqc_cee_status_mask = ICE_AQC_CEE_FCOE_STATUS_M;
+			ice_aqc_cee_status_shift = ICE_AQC_CEE_FCOE_STATUS_S;
+			ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_FCOE_M;
+			ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_FCOE_S;
+			ice_app_sel_type = ICE_APP_SEL_ETHTYPE;
+			ice_app_prot_id_type = ICE_APP_PROT_ID_FCOE;
+		} else if (i == 1) {
+			/* iSCSI APP */
+			ice_aqc_cee_status_mask = ICE_AQC_CEE_ISCSI_STATUS_M;
+			ice_aqc_cee_status_shift = ICE_AQC_CEE_ISCSI_STATUS_S;
+			ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_ISCSI_M;
+			ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_ISCSI_S;
+			ice_app_sel_type = ICE_APP_SEL_TCPIP;
+			ice_app_prot_id_type = ICE_APP_PROT_ID_ISCSI;
+		} else {
+			/* FIP APP */
+			ice_aqc_cee_status_mask = ICE_AQC_CEE_FIP_STATUS_M;
+			ice_aqc_cee_status_shift = ICE_AQC_CEE_FIP_STATUS_S;
+			ice_aqc_cee_app_mask = ICE_AQC_CEE_APP_FIP_M;
+			ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_FIP_S;
+			ice_app_sel_type = ICE_APP_SEL_ETHTYPE;
+			ice_app_prot_id_type = ICE_APP_PROT_ID_FIP;
+		}
+
+		status = (tlv_status & ice_aqc_cee_status_mask) >>
+			 ice_aqc_cee_status_shift;
+		err = (status & ICE_TLV_STATUS_ERR) ? 1 : 0;
+		sync = (status & ICE_TLV_STATUS_SYNC) ? 1 : 0;
+		oper = (status & ICE_TLV_STATUS_OPER) ? 1 : 0;
+		/* Add FCoE/iSCSI/FIP APP if Error is False and
+		 * Oper/Sync is True
+		 */
+		if (!err && sync && oper) {
+			dcbcfg->app[app_index].priority =
+				(app_prio & ice_aqc_cee_app_mask) >>
+				ice_aqc_cee_app_shift;
+			dcbcfg->app[app_index].selector = ice_app_sel_type;
+			dcbcfg->app[app_index].prot_id = ice_app_prot_id_type;
+			app_index++;
+		}
+	}
+
+	dcbcfg->numapps = app_index;
+}
+
+/**
+ * ice_get_ieee_dcb_cfg
+ * @pi: port information structure
+ * @dcbx_mode: mode of DCBX (IEEE or CEE)
+ *
+ * Get IEEE or CEE mode DCB configuration from the Firmware
+ */
+static enum ice_status
+ice_get_ieee_or_cee_dcb_cfg(struct ice_port_info *pi, u8 dcbx_mode)
+{
+	struct ice_dcbx_cfg *dcbx_cfg = NULL;
+	enum ice_status ret;
+
+	if (!pi)
+		return ICE_ERR_PARAM;
+
+	if (dcbx_mode == ICE_DCBX_MODE_IEEE)
+		dcbx_cfg = &pi->local_dcbx_cfg;
+	else if (dcbx_mode == ICE_DCBX_MODE_CEE)
+		dcbx_cfg = &pi->desired_dcbx_cfg;
+
+	/* Get Local DCB Config in case of ICE_DCBX_MODE_IEEE
+	 * or get CEE DCB Desired Config in case of ICE_DCBX_MODE_CEE
+	 */
+	ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_LOCAL,
+				 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, dcbx_cfg);
+	if (ret)
+		goto out;
+
+	/* Get Remote DCB Config */
+	dcbx_cfg = &pi->remote_dcbx_cfg;
+	ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
+				 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, dcbx_cfg);
+	/* Don't treat ENOENT as an error for Remote MIBs */
+	if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT)
+		ret = 0;
+
+out:
+	return ret;
+}
+
+/**
+ * ice_get_dcb_cfg
+ * @pi: port information structure
+ *
+ * Get DCB configuration from the Firmware
+ */
+enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi)
+{
+	struct ice_aqc_get_cee_dcb_cfg_resp cee_cfg;
+	struct ice_dcbx_cfg *dcbx_cfg;
+	enum ice_status ret;
+
+	if (!pi)
+		return ICE_ERR_PARAM;
+
+	ret = ice_aq_get_cee_dcb_cfg(pi->hw, &cee_cfg, NULL);
+	if (!ret) {
+		/* CEE mode */
+		dcbx_cfg = &pi->local_dcbx_cfg;
+		dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_CEE;
+		dcbx_cfg->tlv_status = le32_to_cpu(cee_cfg.tlv_status);
+		ice_cee_to_dcb_cfg(&cee_cfg, dcbx_cfg);
+		ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE);
+	} else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) {
+		/* CEE mode not enabled try querying IEEE data */
+		dcbx_cfg = &pi->local_dcbx_cfg;
+		dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_IEEE;
+		ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_IEEE);
+	}
+
+	return ret;
+}
+
+/**
+ * ice_init_dcb
+ * @hw: pointer to the HW struct
+ *
+ * Update DCB configuration from the Firmware
+ */
+enum ice_status ice_init_dcb(struct ice_hw *hw)
+{
+	struct ice_port_info *pi = hw->port_info;
+	enum ice_status ret = 0;
+
+	if (!hw->func_caps.common_cap.dcb)
+		return ICE_ERR_NOT_SUPPORTED;
+
+	pi->is_sw_lldp = true;
+
+	/* Get DCBX status */
+	pi->dcbx_status = ice_get_dcbx_status(hw);
+
+	if (pi->dcbx_status == ICE_DCBX_STATUS_DONE ||
+	    pi->dcbx_status == ICE_DCBX_STATUS_IN_PROGRESS) {
+		/* Get current DCBX configuration */
+		ret = ice_get_dcb_cfg(pi);
+		pi->is_sw_lldp = (hw->adminq.sq_last_status == ICE_AQ_RC_EPERM);
+		if (ret)
+			return ret;
+	} else if (pi->dcbx_status == ICE_DCBX_STATUS_DIS) {
+		return ICE_ERR_NOT_READY;
+	}
+
+	/* Configure the LLDP MIB change event */
+	ret = ice_aq_cfg_lldp_mib_change(hw, true, NULL);
+	if (!ret)
+		pi->is_sw_lldp = false;
+
+	return ret;
+}
+
+/**
+ * ice_add_ieee_ets_common_tlv
+ * @buf: Data buffer to be populated with ice_dcb_ets_cfg data
+ * @ets_cfg: Container for ice_dcb_ets_cfg data
+ *
+ * Populate the TLV buffer with ice_dcb_ets_cfg data
+ */
+static void
+ice_add_ieee_ets_common_tlv(u8 *buf, struct ice_dcb_ets_cfg *ets_cfg)
+{
+	u8 priority0, priority1;
+	u8 offset = 0;
+	int i;
+
+	/* Priority Assignment Table (4 octets)
+	 * Octets:|    1    |    2    |    3    |    4    |
+	 *        -----------------------------------------
+	 *        |pri0|pri1|pri2|pri3|pri4|pri5|pri6|pri7|
+	 *        -----------------------------------------
+	 *   Bits:|7  4|3  0|7  4|3  0|7  4|3  0|7  4|3  0|
+	 *        -----------------------------------------
+	 */
+	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS / 2; i++) {
+		priority0 = ets_cfg->prio_table[i * 2] & 0xF;
+		priority1 = ets_cfg->prio_table[i * 2 + 1] & 0xF;
+		buf[offset] = (priority0 << ICE_IEEE_ETS_PRIO_1_S) | priority1;
+		offset++;
+	}
+
+	/* TC Bandwidth Table (8 octets)
+	 * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+	 *        ---------------------------------
+	 *        |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+	 *        ---------------------------------
+	 *
+	 * TSA Assignment Table (8 octets)
+	 * Octets:| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
+	 *        ---------------------------------
+	 *        |tc0|tc1|tc2|tc3|tc4|tc5|tc6|tc7|
+	 *        ---------------------------------
+	 */
+	ice_for_each_traffic_class(i) {
+		buf[offset] = ets_cfg->tcbwtable[i];
+		buf[ICE_MAX_TRAFFIC_CLASS + offset] = ets_cfg->tsatable[i];
+		offset++;
+	}
+}
+
+/**
+ * ice_add_ieee_ets_tlv - Prepare ETS TLV in IEEE format
+ * @tlv: Fill the ETS config data in IEEE format
+ * @dcbcfg: Local store which holds the DCB Config
+ *
+ * Prepare IEEE 802.1Qaz ETS CFG TLV
+ */
+static void
+ice_add_ieee_ets_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+	struct ice_dcb_ets_cfg *etscfg;
+	u8 *buf = tlv->tlvinfo;
+	u8 maxtcwilling = 0;
+	u32 ouisubtype;
+	u16 typelen;
+
+	typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) |
+		   ICE_IEEE_ETS_TLV_LEN);
+	tlv->typelen = htons(typelen);
+
+	ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+		      ICE_IEEE_SUBTYPE_ETS_CFG);
+	tlv->ouisubtype = htonl(ouisubtype);
+
+	/* First Octet post subtype
+	 * --------------------------
+	 * |will-|CBS  | Re-  | Max |
+	 * |ing  |     |served| TCs |
+	 * --------------------------
+	 * |1bit | 1bit|3 bits|3bits|
+	 */
+	etscfg = &dcbcfg->etscfg;
+	if (etscfg->willing)
+		maxtcwilling = BIT(ICE_IEEE_ETS_WILLING_S);
+	maxtcwilling |= etscfg->maxtcs & ICE_IEEE_ETS_MAXTC_M;
+	buf[0] = maxtcwilling;
+
+	/* Begin adding at Priority Assignment Table (offset 1 in buf) */
+	ice_add_ieee_ets_common_tlv(&buf[1], etscfg);
+}
+
+/**
+ * ice_add_ieee_etsrec_tlv - Prepare ETS Recommended TLV in IEEE format
+ * @tlv: Fill ETS Recommended TLV in IEEE format
+ * @dcbcfg: Local store which holds the DCB Config
+ *
+ * Prepare IEEE 802.1Qaz ETS REC TLV
+ */
+static void
+ice_add_ieee_etsrec_tlv(struct ice_lldp_org_tlv *tlv,
+			struct ice_dcbx_cfg *dcbcfg)
+{
+	struct ice_dcb_ets_cfg *etsrec;
+	u8 *buf = tlv->tlvinfo;
+	u32 ouisubtype;
+	u16 typelen;
+
+	typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) |
+		   ICE_IEEE_ETS_TLV_LEN);
+	tlv->typelen = htons(typelen);
+
+	ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+		      ICE_IEEE_SUBTYPE_ETS_REC);
+	tlv->ouisubtype = htonl(ouisubtype);
+
+	etsrec = &dcbcfg->etsrec;
+
+	/* First Octet is reserved */
+	/* Begin adding at Priority Assignment Table (offset 1 in buf) */
+	ice_add_ieee_ets_common_tlv(&buf[1], etsrec);
+}
+
+/**
+ * ice_add_ieee_pfc_tlv - Prepare PFC TLV in IEEE format
+ * @tlv: Fill PFC TLV in IEEE format
+ * @dcbcfg: Local store which holds the PFC CFG data
+ *
+ * Prepare IEEE 802.1Qaz PFC CFG TLV
+ */
+static void
+ice_add_ieee_pfc_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg)
+{
+	u8 *buf = tlv->tlvinfo;
+	u32 ouisubtype;
+	u16 typelen;
+
+	typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) |
+		   ICE_IEEE_PFC_TLV_LEN);
+	tlv->typelen = htons(typelen);
+
+	ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+		      ICE_IEEE_SUBTYPE_PFC_CFG);
+	tlv->ouisubtype = htonl(ouisubtype);
+
+	/* ----------------------------------------
+	 * |will-|MBC  | Re-  | PFC |  PFC Enable  |
+	 * |ing  |     |served| cap |              |
+	 * -----------------------------------------
+	 * |1bit | 1bit|2 bits|4bits| 1 octet      |
+	 */
+	if (dcbcfg->pfc.willing)
+		buf[0] = BIT(ICE_IEEE_PFC_WILLING_S);
+
+	if (dcbcfg->pfc.mbc)
+		buf[0] |= BIT(ICE_IEEE_PFC_MBC_S);
+
+	buf[0] |= dcbcfg->pfc.pfccap & 0xF;
+	buf[1] = dcbcfg->pfc.pfcena;
+}
+
+/**
+ * ice_add_ieee_app_pri_tlv -  Prepare APP TLV in IEEE format
+ * @tlv: Fill APP TLV in IEEE format
+ * @dcbcfg: Local store which holds the APP CFG data
+ *
+ * Prepare IEEE 802.1Qaz APP CFG TLV
+ */
+static void
+ice_add_ieee_app_pri_tlv(struct ice_lldp_org_tlv *tlv,
+			 struct ice_dcbx_cfg *dcbcfg)
+{
+	u16 typelen, len, offset = 0;
+	u8 priority, selector, i = 0;
+	u8 *buf = tlv->tlvinfo;
+	u32 ouisubtype;
+
+	/* No APP TLVs then just return */
+	if (dcbcfg->numapps == 0)
+		return;
+	ouisubtype = ((ICE_IEEE_8021QAZ_OUI << ICE_LLDP_TLV_OUI_S) |
+		      ICE_IEEE_SUBTYPE_APP_PRI);
+	tlv->ouisubtype = htonl(ouisubtype);
+
+	/* Move offset to App Priority Table */
+	offset++;
+	/* Application Priority Table (3 octets)
+	 * Octets:|         1          |    2    |    3    |
+	 *        -----------------------------------------
+	 *        |Priority|Rsrvd| Sel |    Protocol ID    |
+	 *        -----------------------------------------
+	 *   Bits:|23    21|20 19|18 16|15                0|
+	 *        -----------------------------------------
+	 */
+	while (i < dcbcfg->numapps) {
+		priority = dcbcfg->app[i].priority & 0x7;
+		selector = dcbcfg->app[i].selector & 0x7;
+		buf[offset] = (priority << ICE_IEEE_APP_PRIO_S) | selector;
+		buf[offset + 1] = (dcbcfg->app[i].prot_id >> 0x8) & 0xFF;
+		buf[offset + 2] = dcbcfg->app[i].prot_id & 0xFF;
+		/* Move to next app */
+		offset += 3;
+		i++;
+		if (i >= ICE_DCBX_MAX_APPS)
+			break;
+	}
+	/* len includes size of ouisubtype + 1 reserved + 3*numapps */
+	len = sizeof(tlv->ouisubtype) + 1 + (i * 3);
+	typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | (len & 0x1FF));
+	tlv->typelen = htons(typelen);
+}
+
+/**
+ * ice_add_dcb_tlv - Add all IEEE TLVs
+ * @tlv: Fill TLV data in IEEE format
+ * @dcbcfg: Local store which holds the DCB Config
+ * @tlvid: Type of IEEE TLV
+ *
+ * Add tlv information
+ */
+static void
+ice_add_dcb_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg,
+		u16 tlvid)
+{
+	switch (tlvid) {
+	case ICE_IEEE_TLV_ID_ETS_CFG:
+		ice_add_ieee_ets_tlv(tlv, dcbcfg);
+		break;
+	case ICE_IEEE_TLV_ID_ETS_REC:
+		ice_add_ieee_etsrec_tlv(tlv, dcbcfg);
+		break;
+	case ICE_IEEE_TLV_ID_PFC_CFG:
+		ice_add_ieee_pfc_tlv(tlv, dcbcfg);
+		break;
+	case ICE_IEEE_TLV_ID_APP_PRI:
+		ice_add_ieee_app_pri_tlv(tlv, dcbcfg);
+		break;
+	default:
+		break;
+	}
+}
+
+/**
+ * ice_dcb_cfg_to_lldp - Convert DCB configuration to MIB format
+ * @lldpmib: pointer to the HW struct
+ * @miblen: length of LLDP MIB
+ * @dcbcfg: Local store which holds the DCB Config
+ *
+ * Convert the DCB configuration to MIB format
+ */
+static void
+ice_dcb_cfg_to_lldp(u8 *lldpmib, u16 *miblen, struct ice_dcbx_cfg *dcbcfg)
+{
+	u16 len, offset = 0, tlvid = ICE_TLV_ID_START;
+	struct ice_lldp_org_tlv *tlv;
+	u16 typelen;
+
+	tlv = (struct ice_lldp_org_tlv *)lldpmib;
+	while (1) {
+		ice_add_dcb_tlv(tlv, dcbcfg, tlvid++);
+		typelen = ntohs(tlv->typelen);
+		len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+		if (len)
+			offset += len + 2;
+		/* END TLV or beyond LLDPDU size */
+		if (tlvid >= ICE_TLV_ID_END_OF_LLDPPDU ||
+		    offset > ICE_LLDPDU_SIZE)
+			break;
+		/* Move to next TLV */
+		if (len)
+			tlv = (struct ice_lldp_org_tlv *)
+				((char *)tlv + sizeof(tlv->typelen) + len);
+	}
+	*miblen = offset;
+}
+
+/**
+ * ice_set_dcb_cfg - Set the local LLDP MIB to FW
+ * @pi: port information structure
+ *
+ * Set DCB configuration to the Firmware
+ */
+enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi)
+{
+	u8 mib_type, *lldpmib = NULL;
+	struct ice_dcbx_cfg *dcbcfg;
+	enum ice_status ret;
+	struct ice_hw *hw;
+	u16 miblen;
+
+	if (!pi)
+		return ICE_ERR_PARAM;
+
+	hw = pi->hw;
+
+	/* update the HW local config */
+	dcbcfg = &pi->local_dcbx_cfg;
+	/* Allocate the LLDPDU */
+	lldpmib = devm_kzalloc(ice_hw_to_dev(hw), ICE_LLDPDU_SIZE, GFP_KERNEL);
+	if (!lldpmib)
+		return ICE_ERR_NO_MEMORY;
+
+	mib_type = SET_LOCAL_MIB_TYPE_LOCAL_MIB;
+	if (dcbcfg->app_mode == ICE_DCBX_APPS_NON_WILLING)
+		mib_type |= SET_LOCAL_MIB_TYPE_CEE_NON_WILLING;
+
+	ice_dcb_cfg_to_lldp(lldpmib, &miblen, dcbcfg);
+	ret = ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, miblen,
+				  NULL);
+
+	devm_kfree(ice_hw_to_dev(hw), lldpmib);
+
+	return ret;
+}
+
+/**
+ * ice_aq_query_port_ets - query port ets configuration
+ * @pi: port information structure
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @cd: pointer to command details structure or NULL
+ *
+ * query current port ets configuration
+ */
+static enum ice_status
+ice_aq_query_port_ets(struct ice_port_info *pi,
+		      struct ice_aqc_port_ets_elem *buf, u16 buf_size,
+		      struct ice_sq_cd *cd)
+{
+	struct ice_aqc_query_port_ets *cmd;
+	struct ice_aq_desc desc;
+	enum ice_status status;
+
+	if (!pi)
+		return ICE_ERR_PARAM;
+	cmd = &desc.params.port_ets;
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_query_port_ets);
+	cmd->port_teid = pi->root->info.node_teid;
+
+	status = ice_aq_send_cmd(pi->hw, &desc, buf, buf_size, cd);
+	return status;
+}
+
+/**
+ * ice_update_port_tc_tree_cfg - update TC tree configuration
+ * @pi: port information structure
+ * @buf: pointer to buffer
+ *
+ * update the SW DB with the new TC changes
+ */
+static enum ice_status
+ice_update_port_tc_tree_cfg(struct ice_port_info *pi,
+			    struct ice_aqc_port_ets_elem *buf)
+{
+	struct ice_sched_node *node, *tc_node;
+	struct ice_aqc_get_elem elem;
+	enum ice_status status = 0;
+	u32 teid1, teid2;
+	u8 i, j;
+
+	if (!pi)
+		return ICE_ERR_PARAM;
+	/* suspend the missing TC nodes */
+	for (i = 0; i < pi->root->num_children; i++) {
+		teid1 = le32_to_cpu(pi->root->children[i]->info.node_teid);
+		ice_for_each_traffic_class(j) {
+			teid2 = le32_to_cpu(buf->tc_node_teid[j]);
+			if (teid1 == teid2)
+				break;
+		}
+		if (j < ICE_MAX_TRAFFIC_CLASS)
+			continue;
+		/* TC is missing */
+		pi->root->children[i]->in_use = false;
+	}
+	/* add the new TC nodes */
+	ice_for_each_traffic_class(j) {
+		teid2 = le32_to_cpu(buf->tc_node_teid[j]);
+		if (teid2 == ICE_INVAL_TEID)
+			continue;
+		/* Is it already present in the tree ? */
+		for (i = 0; i < pi->root->num_children; i++) {
+			tc_node = pi->root->children[i];
+			if (!tc_node)
+				continue;
+			teid1 = le32_to_cpu(tc_node->info.node_teid);
+			if (teid1 == teid2) {
+				tc_node->tc_num = j;
+				tc_node->in_use = true;
+				break;
+			}
+		}
+		if (i < pi->root->num_children)
+			continue;
+		/* new TC */
+		status = ice_sched_query_elem(pi->hw, teid2, &elem);
+		if (!status)
+			status = ice_sched_add_node(pi, 1, &elem.generic[0]);
+		if (status)
+			break;
+		/* update the TC number */
+		node = ice_sched_find_node_by_teid(pi->root, teid2);
+		if (node)
+			node->tc_num = j;
+	}
+	return status;
+}
+
+/**
+ * ice_query_port_ets - query port ets configuration
+ * @pi: port information structure
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @cd: pointer to command details structure or NULL
+ *
+ * query current port ets configuration and update the
+ * SW DB with the TC changes
+ */
+enum ice_status
+ice_query_port_ets(struct ice_port_info *pi,
+		   struct ice_aqc_port_ets_elem *buf, u16 buf_size,
+		   struct ice_sq_cd *cd)
+{
+	enum ice_status status;
+
+	mutex_lock(&pi->sched_lock);
+	status = ice_aq_query_port_ets(pi, buf, buf_size, cd);
+	if (!status)
+		status = ice_update_port_tc_tree_cfg(pi, buf);
+	mutex_unlock(&pi->sched_lock);
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h
new file mode 100644
index 000000000000..522e1452abe2
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_DCB_H_
+#define _ICE_DCB_H_
+
+#include "ice_type.h"
+
+#define ICE_DCBX_STATUS_NOT_STARTED	0
+#define ICE_DCBX_STATUS_IN_PROGRESS	1
+#define ICE_DCBX_STATUS_DONE		2
+#define ICE_DCBX_STATUS_DIS		7
+
+#define ICE_TLV_TYPE_END		0
+#define ICE_TLV_TYPE_ORG		127
+
+#define ICE_IEEE_8021QAZ_OUI		0x0080C2
+#define ICE_IEEE_SUBTYPE_ETS_CFG	9
+#define ICE_IEEE_SUBTYPE_ETS_REC	10
+#define ICE_IEEE_SUBTYPE_PFC_CFG	11
+#define ICE_IEEE_SUBTYPE_APP_PRI	12
+
+#define ICE_CEE_DCBX_OUI		0x001B21
+#define ICE_CEE_DCBX_TYPE		2
+#define ICE_CEE_SUBTYPE_PG_CFG		2
+#define ICE_CEE_SUBTYPE_PFC_CFG		3
+#define ICE_CEE_SUBTYPE_APP_PRI		4
+#define ICE_CEE_MAX_FEAT_TYPE		3
+/* Defines for LLDP TLV header */
+#define ICE_LLDP_TLV_LEN_S		0
+#define ICE_LLDP_TLV_LEN_M		(0x01FF << ICE_LLDP_TLV_LEN_S)
+#define ICE_LLDP_TLV_TYPE_S		9
+#define ICE_LLDP_TLV_TYPE_M		(0x7F << ICE_LLDP_TLV_TYPE_S)
+#define ICE_LLDP_TLV_SUBTYPE_S		0
+#define ICE_LLDP_TLV_SUBTYPE_M		(0xFF << ICE_LLDP_TLV_SUBTYPE_S)
+#define ICE_LLDP_TLV_OUI_S		8
+#define ICE_LLDP_TLV_OUI_M		(0xFFFFFFUL << ICE_LLDP_TLV_OUI_S)
+
+/* Defines for IEEE ETS TLV */
+#define ICE_IEEE_ETS_MAXTC_S	0
+#define ICE_IEEE_ETS_MAXTC_M		(0x7 << ICE_IEEE_ETS_MAXTC_S)
+#define ICE_IEEE_ETS_CBS_S		6
+#define ICE_IEEE_ETS_CBS_M		BIT(ICE_IEEE_ETS_CBS_S)
+#define ICE_IEEE_ETS_WILLING_S		7
+#define ICE_IEEE_ETS_WILLING_M		BIT(ICE_IEEE_ETS_WILLING_S)
+#define ICE_IEEE_ETS_PRIO_0_S		0
+#define ICE_IEEE_ETS_PRIO_0_M		(0x7 << ICE_IEEE_ETS_PRIO_0_S)
+#define ICE_IEEE_ETS_PRIO_1_S		4
+#define ICE_IEEE_ETS_PRIO_1_M		(0x7 << ICE_IEEE_ETS_PRIO_1_S)
+#define ICE_CEE_PGID_PRIO_0_S		0
+#define ICE_CEE_PGID_PRIO_0_M		(0xF << ICE_CEE_PGID_PRIO_0_S)
+#define ICE_CEE_PGID_PRIO_1_S		4
+#define ICE_CEE_PGID_PRIO_1_M		(0xF << ICE_CEE_PGID_PRIO_1_S)
+#define ICE_CEE_PGID_STRICT		15
+
+/* Defines for IEEE TSA types */
+#define ICE_IEEE_TSA_STRICT		0
+#define ICE_IEEE_TSA_ETS		2
+
+/* Defines for IEEE PFC TLV */
+#define ICE_IEEE_PFC_CAP_S		0
+#define ICE_IEEE_PFC_CAP_M		(0xF << ICE_IEEE_PFC_CAP_S)
+#define ICE_IEEE_PFC_MBC_S		6
+#define ICE_IEEE_PFC_MBC_M		BIT(ICE_IEEE_PFC_MBC_S)
+#define ICE_IEEE_PFC_WILLING_S		7
+#define ICE_IEEE_PFC_WILLING_M		BIT(ICE_IEEE_PFC_WILLING_S)
+
+/* Defines for IEEE APP TLV */
+#define ICE_IEEE_APP_SEL_S		0
+#define ICE_IEEE_APP_SEL_M		(0x7 << ICE_IEEE_APP_SEL_S)
+#define ICE_IEEE_APP_PRIO_S		5
+#define ICE_IEEE_APP_PRIO_M		(0x7 << ICE_IEEE_APP_PRIO_S)
+
+/* TLV definitions for preparing MIB */
+#define ICE_IEEE_TLV_ID_ETS_CFG		3
+#define ICE_IEEE_TLV_ID_ETS_REC		4
+#define ICE_IEEE_TLV_ID_PFC_CFG		5
+#define ICE_IEEE_TLV_ID_APP_PRI		6
+#define ICE_TLV_ID_END_OF_LLDPPDU	7
+#define ICE_TLV_ID_START		ICE_IEEE_TLV_ID_ETS_CFG
+
+#define ICE_IEEE_ETS_TLV_LEN		25
+#define ICE_IEEE_PFC_TLV_LEN		6
+#define ICE_IEEE_APP_TLV_LEN		11
+
+/* IEEE 802.1AB LLDP Organization specific TLV */
+struct ice_lldp_org_tlv {
+	__be16 typelen;
+	__be32 ouisubtype;
+	u8 tlvinfo[1];
+} __packed;
+
+struct ice_cee_tlv_hdr {
+	__be16 typelen;
+	u8 operver;
+	u8 maxver;
+};
+
+struct ice_cee_ctrl_tlv {
+	struct ice_cee_tlv_hdr hdr;
+	__be32 seqno;
+	__be32 ackno;
+};
+
+struct ice_cee_feat_tlv {
+	struct ice_cee_tlv_hdr hdr;
+	u8 en_will_err; /* Bits: |En|Will|Err|Reserved(5)| */
+#define ICE_CEE_FEAT_TLV_ENA_M		0x80
+#define ICE_CEE_FEAT_TLV_WILLING_M	0x40
+#define ICE_CEE_FEAT_TLV_ERR_M		0x20
+	u8 subtype;
+	u8 tlvinfo[1];
+};
+
+struct ice_cee_app_prio {
+	__be16 protocol;
+	u8 upper_oui_sel; /* Bits: |Upper OUI(6)|Selector(2)| */
+#define ICE_CEE_APP_SELECTOR_M	0x03
+	__be16 lower_oui;
+	u8 prio_map;
+} __packed;
+
+enum ice_status
+ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype,
+		   struct ice_dcbx_cfg *dcbcfg);
+enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi);
+enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi);
+enum ice_status ice_init_dcb(struct ice_hw *hw);
+enum ice_status
+ice_query_port_ets(struct ice_port_info *pi,
+		   struct ice_aqc_port_ets_elem *buf, u16 buf_size,
+		   struct ice_sq_cd *cmd_details);
+#ifdef CONFIG_DCB
+enum ice_status
+ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
+		 struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent,
+		       bool *dcbx_agent_status, struct ice_sq_cd *cd);
+enum ice_status
+ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
+			   struct ice_sq_cd *cd);
+#else /* CONFIG_DCB */
+static inline enum ice_status
+ice_aq_stop_lldp(struct ice_hw __always_unused *hw,
+		 bool __always_unused shutdown_lldp_agent,
+		 bool __always_unused persist,
+		 struct ice_sq_cd __always_unused *cd)
+{
+	return 0;
+}
+
+static inline enum ice_status
+ice_aq_start_lldp(struct ice_hw __always_unused *hw,
+		  bool __always_unused persist,
+		  struct ice_sq_cd __always_unused *cd)
+{
+	return 0;
+}
+
+static inline enum ice_status
+ice_aq_start_stop_dcbx(struct ice_hw __always_unused *hw,
+		       bool __always_unused start_dcbx_agent,
+		       bool *dcbx_agent_status,
+		       struct ice_sq_cd __always_unused *cd)
+{
+	*dcbx_agent_status = false;
+
+	return 0;
+}
+
+static inline enum ice_status
+ice_aq_cfg_lldp_mib_change(struct ice_hw __always_unused *hw,
+			   bool __always_unused ena_update,
+			   struct ice_sq_cd __always_unused *cd)
+{
+	return 0;
+}
+
+#endif /* CONFIG_DCB */
+#endif /* _ICE_DCB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
new file mode 100644
index 000000000000..fe88b127ca42
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -0,0 +1,653 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Intel Corporation. */
+
+#include "ice_dcb_lib.h"
+
+/**
+ * ice_dcb_get_ena_tc - return bitmap of enabled TCs
+ * @dcbcfg: DCB config to evaluate for enabled TCs
+ */
+u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg)
+{
+	u8 i, num_tc, ena_tc = 1;
+
+	num_tc = ice_dcb_get_num_tc(dcbcfg);
+
+	for (i = 0; i < num_tc; i++)
+		ena_tc |= BIT(i);
+
+	return ena_tc;
+}
+
+/**
+ * ice_dcb_get_num_tc - Get the number of TCs from DCBX config
+ * @dcbcfg: config to retrieve number of TCs from
+ */
+u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg)
+{
+	bool tc_unused = false;
+	u8 num_tc = 0;
+	u8 ret = 0;
+	int i;
+
+	/* Scan the ETS Config Priority Table to find traffic classes
+	 * enabled and create a bitmask of enabled TCs
+	 */
+	for (i = 0; i < CEE_DCBX_MAX_PRIO; i++)
+		num_tc |= BIT(dcbcfg->etscfg.prio_table[i]);
+
+	/* Scan bitmask for contiguous TCs starting with TC0 */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		if (num_tc & BIT(i)) {
+			if (!tc_unused) {
+				ret++;
+			} else {
+				pr_err("Non-contiguous TCs - Disabling DCB\n");
+				return 1;
+			}
+		} else {
+			tc_unused = true;
+		}
+	}
+
+	/* There is always at least 1 TC */
+	if (!ret)
+		ret = 1;
+
+	return ret;
+}
+
+/**
+ * ice_vsi_cfg_dcb_rings - Update rings to reflect DCB TC
+ * @vsi: VSI owner of rings being updated
+ */
+void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi)
+{
+	struct ice_ring *tx_ring, *rx_ring;
+	u16 qoffset, qcount;
+	int i, n;
+
+	if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) {
+		/* Reset the TC information */
+		for (i = 0; i < vsi->num_txq; i++) {
+			tx_ring = vsi->tx_rings[i];
+			tx_ring->dcb_tc = 0;
+		}
+		for (i = 0; i < vsi->num_rxq; i++) {
+			rx_ring = vsi->rx_rings[i];
+			rx_ring->dcb_tc = 0;
+		}
+		return;
+	}
+
+	ice_for_each_traffic_class(n) {
+		if (!(vsi->tc_cfg.ena_tc & BIT(n)))
+			break;
+
+		qoffset = vsi->tc_cfg.tc_info[n].qoffset;
+		qcount = vsi->tc_cfg.tc_info[n].qcount_tx;
+		for (i = qoffset; i < (qoffset + qcount); i++) {
+			tx_ring = vsi->tx_rings[i];
+			rx_ring = vsi->rx_rings[i];
+			tx_ring->dcb_tc = n;
+			rx_ring->dcb_tc = n;
+		}
+	}
+}
+
+/**
+ * ice_pf_dcb_recfg - Reconfigure all VEBs and VSIs
+ * @pf: pointer to the PF struct
+ *
+ * Assumed caller has already disabled all VSIs before
+ * calling this function. Reconfiguring DCB based on
+ * local_dcbx_cfg.
+ */
+static void ice_pf_dcb_recfg(struct ice_pf *pf)
+{
+	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->local_dcbx_cfg;
+	u8 tc_map = 0;
+	int v, ret;
+
+	/* Update each VSI */
+	ice_for_each_vsi(pf, v) {
+		if (!pf->vsi[v])
+			continue;
+
+		if (pf->vsi[v]->type == ICE_VSI_PF)
+			tc_map = ice_dcb_get_ena_tc(dcbcfg);
+		else
+			tc_map = ICE_DFLT_TRAFFIC_CLASS;
+
+		ret = ice_vsi_cfg_tc(pf->vsi[v], tc_map);
+		if (ret) {
+			dev_err(&pf->pdev->dev,
+				"Failed to config TC for VSI index: %d\n",
+				pf->vsi[v]->idx);
+			continue;
+		}
+
+		ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+	}
+}
+
+/**
+ * ice_pf_dcb_cfg - Apply new DCB configuration
+ * @pf: pointer to the PF struct
+ * @new_cfg: DCBX config to apply
+ * @locked: is the RTNL held
+ */
+static
+int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
+{
+	struct ice_dcbx_cfg *old_cfg, *curr_cfg;
+	struct ice_aqc_port_ets_elem buf = { 0 };
+	int ret = 0;
+
+	curr_cfg = &pf->hw.port_info->local_dcbx_cfg;
+
+	/* Enable DCB tagging only when more than one TC */
+	if (ice_dcb_get_num_tc(new_cfg) > 1) {
+		dev_dbg(&pf->pdev->dev, "DCB tagging enabled (num TC > 1)\n");
+		set_bit(ICE_FLAG_DCB_ENA, pf->flags);
+	} else {
+		dev_dbg(&pf->pdev->dev, "DCB tagging disabled (num TC = 1)\n");
+		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+	}
+
+	if (!memcmp(new_cfg, curr_cfg, sizeof(*new_cfg))) {
+		dev_dbg(&pf->pdev->dev, "No change in DCB config required\n");
+		return ret;
+	}
+
+	/* Store old config in case FW config fails */
+	old_cfg = devm_kzalloc(&pf->pdev->dev, sizeof(*old_cfg), GFP_KERNEL);
+	memcpy(old_cfg, curr_cfg, sizeof(*old_cfg));
+
+	/* avoid race conditions by holding the lock while disabling and
+	 * re-enabling the VSI
+	 */
+	if (!locked)
+		rtnl_lock();
+	ice_pf_dis_all_vsi(pf, true);
+
+	memcpy(curr_cfg, new_cfg, sizeof(*curr_cfg));
+	memcpy(&curr_cfg->etsrec, &curr_cfg->etscfg, sizeof(curr_cfg->etsrec));
+
+	/* Only send new config to HW if we are in SW LLDP mode. Otherwise,
+	 * the new config came from the HW in the first place.
+	 */
+	if (pf->hw.port_info->is_sw_lldp) {
+		ret = ice_set_dcb_cfg(pf->hw.port_info);
+		if (ret) {
+			dev_err(&pf->pdev->dev, "Set DCB Config failed\n");
+			/* Restore previous settings to local config */
+			memcpy(curr_cfg, old_cfg, sizeof(*curr_cfg));
+			goto out;
+		}
+	}
+
+	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+		goto out;
+	}
+
+	ice_pf_dcb_recfg(pf);
+
+out:
+	ice_pf_ena_all_vsi(pf, true);
+	if (!locked)
+		rtnl_unlock();
+	devm_kfree(&pf->pdev->dev, old_cfg);
+	return ret;
+}
+
+/**
+ * ice_dcb_rebuild - rebuild DCB post reset
+ * @pf: physical function instance
+ */
+void ice_dcb_rebuild(struct ice_pf *pf)
+{
+	struct ice_aqc_port_ets_elem buf = { 0 };
+	struct ice_dcbx_cfg *prev_cfg;
+	enum ice_status ret;
+	u8 willing;
+
+	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+		goto dcb_error;
+	}
+
+	/* If DCB was not enabled previously, we are done */
+	if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags))
+		return;
+
+	/* Save current willing state and force FW to unwilling */
+	willing = pf->hw.port_info->local_dcbx_cfg.etscfg.willing;
+	pf->hw.port_info->local_dcbx_cfg.etscfg.willing = 0x0;
+	ret = ice_set_dcb_cfg(pf->hw.port_info);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Failed to set DCB to unwilling\n");
+		goto dcb_error;
+	}
+
+	/* Retrieve DCB config and ensure same as current in SW */
+	prev_cfg = devm_kmemdup(&pf->pdev->dev,
+				&pf->hw.port_info->local_dcbx_cfg,
+				sizeof(*prev_cfg), GFP_KERNEL);
+	if (!prev_cfg) {
+		dev_err(&pf->pdev->dev, "Failed to alloc space for DCB cfg\n");
+		goto dcb_error;
+	}
+
+	ice_init_dcb(&pf->hw);
+	if (memcmp(prev_cfg, &pf->hw.port_info->local_dcbx_cfg,
+		   sizeof(*prev_cfg))) {
+		/* difference in cfg detected - disable DCB till next MIB */
+		dev_err(&pf->pdev->dev, "Set local MIB not accurate\n");
+		devm_kfree(&pf->pdev->dev, prev_cfg);
+		goto dcb_error;
+	}
+
+	/* fetched config congruent to previous configuration */
+	devm_kfree(&pf->pdev->dev, prev_cfg);
+
+	/* Configuration replayed - reset willing state to previous */
+	pf->hw.port_info->local_dcbx_cfg.etscfg.willing = willing;
+	ret = ice_set_dcb_cfg(pf->hw.port_info);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Fail restoring prev willing state\n");
+		goto dcb_error;
+	}
+	dev_info(&pf->pdev->dev, "DCB restored after reset\n");
+	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+		goto dcb_error;
+	}
+
+	return;
+
+dcb_error:
+	dev_err(&pf->pdev->dev, "Disabling DCB until new settings occur\n");
+	prev_cfg = devm_kzalloc(&pf->pdev->dev, sizeof(*prev_cfg), GFP_KERNEL);
+	prev_cfg->etscfg.willing = true;
+	prev_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW;
+	prev_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
+	memcpy(&prev_cfg->etsrec, &prev_cfg->etscfg, sizeof(prev_cfg->etsrec));
+	ice_pf_dcb_cfg(pf, prev_cfg, false);
+	devm_kfree(&pf->pdev->dev, prev_cfg);
+}
+
+/**
+ * ice_dcb_init_cfg - set the initial DCB config in SW
+ * @pf: PF to apply config to
+ * @locked: Is the RTNL held
+ */
+static int ice_dcb_init_cfg(struct ice_pf *pf, bool locked)
+{
+	struct ice_dcbx_cfg *newcfg;
+	struct ice_port_info *pi;
+	int ret = 0;
+
+	pi = pf->hw.port_info;
+	newcfg = devm_kzalloc(&pf->pdev->dev, sizeof(*newcfg), GFP_KERNEL);
+	if (!newcfg)
+		return -ENOMEM;
+
+	memcpy(newcfg, &pi->local_dcbx_cfg, sizeof(*newcfg));
+	memset(&pi->local_dcbx_cfg, 0, sizeof(*newcfg));
+
+	dev_info(&pf->pdev->dev, "Configuring initial DCB values\n");
+	if (ice_pf_dcb_cfg(pf, newcfg, locked))
+		ret = -EINVAL;
+
+	devm_kfree(&pf->pdev->dev, newcfg);
+
+	return ret;
+}
+
+/**
+ * ice_dcb_sw_default_config - Apply a default DCB config
+ * @pf: PF to apply config to
+ * @locked: was this function called with RTNL held
+ */
+static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked)
+{
+	struct ice_aqc_port_ets_elem buf = { 0 };
+	struct ice_dcbx_cfg *dcbcfg;
+	struct ice_port_info *pi;
+	struct ice_hw *hw;
+	int ret;
+
+	hw = &pf->hw;
+	pi = hw->port_info;
+	dcbcfg = devm_kzalloc(&pf->pdev->dev, sizeof(*dcbcfg), GFP_KERNEL);
+
+	memset(dcbcfg, 0, sizeof(*dcbcfg));
+	memset(&pi->local_dcbx_cfg, 0, sizeof(*dcbcfg));
+
+	dcbcfg->etscfg.willing = 1;
+	dcbcfg->etscfg.maxtcs = 8;
+	dcbcfg->etscfg.tcbwtable[0] = 100;
+	dcbcfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
+
+	memcpy(&dcbcfg->etsrec, &dcbcfg->etscfg,
+	       sizeof(dcbcfg->etsrec));
+	dcbcfg->etsrec.willing = 0;
+
+	dcbcfg->pfc.willing = 1;
+	dcbcfg->pfc.pfccap = IEEE_8021QAZ_MAX_TCS;
+
+	dcbcfg->numapps = 1;
+	dcbcfg->app[0].selector = ICE_APP_SEL_ETHTYPE;
+	dcbcfg->app[0].priority = 3;
+	dcbcfg->app[0].prot_id = ICE_APP_PROT_ID_FCOE;
+
+	ret = ice_pf_dcb_cfg(pf, dcbcfg, locked);
+	devm_kfree(&pf->pdev->dev, dcbcfg);
+	if (ret)
+		return ret;
+
+	return ice_query_port_ets(pi, &buf, sizeof(buf), NULL);
+}
+
+/**
+ * ice_init_pf_dcb - initialize DCB for a PF
+ * @pf: PF to initialize DCB for
+ * @locked: Was function called with RTNL held
+ */
+int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
+{
+	struct device *dev = &pf->pdev->dev;
+	struct ice_port_info *port_info;
+	struct ice_hw *hw = &pf->hw;
+	int sw_default = 0;
+	int err;
+
+	port_info = hw->port_info;
+
+	err = ice_init_dcb(hw);
+	if (err) {
+		/* FW LLDP is not active, default to SW DCBX/LLDP */
+		dev_info(&pf->pdev->dev, "FW LLDP is not active\n");
+		hw->port_info->dcbx_status = ICE_DCBX_STATUS_NOT_STARTED;
+		hw->port_info->is_sw_lldp = true;
+	}
+
+	if (port_info->dcbx_status == ICE_DCBX_STATUS_DIS)
+		dev_info(&pf->pdev->dev, "DCBX disabled\n");
+
+	/* LLDP disabled in FW */
+	if (port_info->is_sw_lldp) {
+		sw_default = 1;
+		dev_info(&pf->pdev->dev, "DCBx/LLDP in SW mode.\n");
+		clear_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags);
+	} else {
+		set_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags);
+	}
+
+	if (port_info->dcbx_status == ICE_DCBX_STATUS_NOT_STARTED)
+		dev_info(&pf->pdev->dev, "DCBX not started\n");
+
+	if (sw_default) {
+		err = ice_dcb_sw_dflt_cfg(pf, locked);
+		if (err) {
+			dev_err(&pf->pdev->dev,
+				"Failed to set local DCB config %d\n", err);
+			err = -EIO;
+			goto dcb_init_err;
+		}
+
+		pf->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE;
+		set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+		set_bit(ICE_FLAG_DCB_ENA, pf->flags);
+		return 0;
+	}
+
+	/* DCBX in FW and LLDP enabled in FW */
+	pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_IEEE;
+
+	set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+
+	err = ice_dcb_init_cfg(pf, locked);
+	if (err)
+		goto dcb_init_err;
+
+	dev_info(&pf->pdev->dev, "DCBX offload supported\n");
+	return err;
+
+dcb_init_err:
+	dev_err(dev, "DCB init failed\n");
+	return err;
+}
+
+/**
+ * ice_update_dcb_stats - Update DCB stats counters
+ * @pf: PF whose stats needs to be updated
+ */
+void ice_update_dcb_stats(struct ice_pf *pf)
+{
+	struct ice_hw_port_stats *prev_ps, *cur_ps;
+	struct ice_hw *hw = &pf->hw;
+	u8 pf_id = hw->pf_id;
+	int i;
+
+	prev_ps = &pf->stats_prev;
+	cur_ps = &pf->stats;
+
+	for (i = 0; i < 8; i++) {
+		ice_stat_update32(hw, GLPRT_PXOFFRXC(pf_id, i),
+				  pf->stat_prev_loaded,
+				  &prev_ps->priority_xoff_rx[i],
+				  &cur_ps->priority_xoff_rx[i]);
+		ice_stat_update32(hw, GLPRT_PXONRXC(pf_id, i),
+				  pf->stat_prev_loaded,
+				  &prev_ps->priority_xon_rx[i],
+				  &cur_ps->priority_xon_rx[i]);
+		ice_stat_update32(hw, GLPRT_PXONTXC(pf_id, i),
+				  pf->stat_prev_loaded,
+				  &prev_ps->priority_xon_tx[i],
+				  &cur_ps->priority_xon_tx[i]);
+		ice_stat_update32(hw, GLPRT_PXOFFTXC(pf_id, i),
+				  pf->stat_prev_loaded,
+				  &prev_ps->priority_xoff_tx[i],
+				  &cur_ps->priority_xoff_tx[i]);
+		ice_stat_update32(hw, GLPRT_RXON2OFFCNT(pf_id, i),
+				  pf->stat_prev_loaded,
+				  &prev_ps->priority_xon_2_xoff[i],
+				  &cur_ps->priority_xon_2_xoff[i]);
+	}
+}
+
+/**
+ * ice_tx_prepare_vlan_flags_dcb - prepare VLAN tagging for DCB
+ * @tx_ring: ring to send buffer on
+ * @first: pointer to struct ice_tx_buf
+ */
+int
+ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
+			      struct ice_tx_buf *first)
+{
+	struct sk_buff *skb = first->skb;
+
+	if (!test_bit(ICE_FLAG_DCB_ENA, tx_ring->vsi->back->flags))
+		return 0;
+
+	/* Insert 802.1p priority into VLAN header */
+	if ((first->tx_flags & (ICE_TX_FLAGS_HW_VLAN | ICE_TX_FLAGS_SW_VLAN)) ||
+	    skb->priority != TC_PRIO_CONTROL) {
+		first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M;
+		/* Mask the lower 3 bits to set the 802.1p priority */
+		first->tx_flags |= (skb->priority & 0x7) <<
+				   ICE_TX_FLAGS_VLAN_PR_S;
+		if (first->tx_flags & ICE_TX_FLAGS_SW_VLAN) {
+			struct vlan_ethhdr *vhdr;
+			int rc;
+
+			rc = skb_cow_head(skb, 0);
+			if (rc < 0)
+				return rc;
+			vhdr = (struct vlan_ethhdr *)skb->data;
+			vhdr->h_vlan_TCI = htons(first->tx_flags >>
+						 ICE_TX_FLAGS_VLAN_S);
+		} else {
+			first->tx_flags |= ICE_TX_FLAGS_HW_VLAN;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ice_dcb_need_recfg - Check if DCB needs reconfig
+ * @pf: board private structure
+ * @old_cfg: current DCB config
+ * @new_cfg: new DCB config
+ */
+static bool ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
+			       struct ice_dcbx_cfg *new_cfg)
+{
+	bool need_reconfig = false;
+
+	/* Check if ETS configuration has changed */
+	if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg,
+		   sizeof(new_cfg->etscfg))) {
+		/* If Priority Table has changed reconfig is needed */
+		if (memcmp(&new_cfg->etscfg.prio_table,
+			   &old_cfg->etscfg.prio_table,
+			   sizeof(new_cfg->etscfg.prio_table))) {
+			need_reconfig = true;
+			dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n");
+		}
+
+		if (memcmp(&new_cfg->etscfg.tcbwtable,
+			   &old_cfg->etscfg.tcbwtable,
+			   sizeof(new_cfg->etscfg.tcbwtable)))
+			dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n");
+
+		if (memcmp(&new_cfg->etscfg.tsatable,
+			   &old_cfg->etscfg.tsatable,
+			   sizeof(new_cfg->etscfg.tsatable)))
+			dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n");
+	}
+
+	/* Check if PFC configuration has changed */
+	if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) {
+		need_reconfig = true;
+		dev_dbg(&pf->pdev->dev, "PFC config change detected.\n");
+	}
+
+	/* Check if APP Table has changed */
+	if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) {
+		need_reconfig = true;
+		dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");
+	}
+
+	dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig);
+	return need_reconfig;
+}
+
+/**
+ * ice_dcb_process_lldp_set_mib_change - Process MIB change
+ * @pf: ptr to ice_pf
+ * @event: pointer to the admin queue receive event
+ */
+void
+ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
+				    struct ice_rq_event_info *event)
+{
+	struct ice_aqc_port_ets_elem buf = { 0 };
+	struct ice_aqc_lldp_get_mib *mib;
+	struct ice_dcbx_cfg tmp_dcbx_cfg;
+	bool need_reconfig = false;
+	struct ice_port_info *pi;
+	u8 type;
+	int ret;
+
+	/* Not DCB capable or capability disabled */
+	if (!(test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)))
+		return;
+
+	if (pf->dcbx_cap & DCB_CAP_DCBX_HOST) {
+		dev_dbg(&pf->pdev->dev,
+			"MIB Change Event in HOST mode\n");
+		return;
+	}
+
+	pi = pf->hw.port_info;
+	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+	/* Ignore if event is not for Nearest Bridge */
+	type = ((mib->type >> ICE_AQ_LLDP_BRID_TYPE_S) &
+		ICE_AQ_LLDP_BRID_TYPE_M);
+	dev_dbg(&pf->pdev->dev, "LLDP event MIB bridge type 0x%x\n", type);
+	if (type != ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID)
+		return;
+
+	/* Check MIB Type and return if event for Remote MIB update */
+	type = mib->type & ICE_AQ_LLDP_MIB_TYPE_M;
+	dev_dbg(&pf->pdev->dev,
+		"LLDP event mib type %s\n", type ? "remote" : "local");
+	if (type == ICE_AQ_LLDP_MIB_REMOTE) {
+		/* Update the remote cached instance and return */
+		ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
+					 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID,
+					 &pi->remote_dcbx_cfg);
+		if (ret) {
+			dev_err(&pf->pdev->dev, "Failed to get remote DCB config\n");
+			return;
+		}
+	}
+
+	/* store the old configuration */
+	tmp_dcbx_cfg = pf->hw.port_info->local_dcbx_cfg;
+
+	/* Reset the old DCBX configuration data */
+	memset(&pi->local_dcbx_cfg, 0, sizeof(pi->local_dcbx_cfg));
+
+	/* Get updated DCBX data from firmware */
+	ret = ice_get_dcb_cfg(pf->hw.port_info);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Failed to get DCB config\n");
+		return;
+	}
+
+	/* No change detected in DCBX configs */
+	if (!memcmp(&tmp_dcbx_cfg, &pi->local_dcbx_cfg, sizeof(tmp_dcbx_cfg))) {
+		dev_dbg(&pf->pdev->dev,
+			"No change detected in DCBX configuration.\n");
+		return;
+	}
+
+	need_reconfig = ice_dcb_need_recfg(pf, &tmp_dcbx_cfg,
+					   &pi->local_dcbx_cfg);
+	if (!need_reconfig)
+		return;
+
+	/* Enable DCB tagging only when more than one TC */
+	if (ice_dcb_get_num_tc(&pi->local_dcbx_cfg) > 1) {
+		dev_dbg(&pf->pdev->dev, "DCB tagging enabled (num TC > 1)\n");
+		set_bit(ICE_FLAG_DCB_ENA, pf->flags);
+	} else {
+		dev_dbg(&pf->pdev->dev, "DCB tagging disabled (num TC = 1)\n");
+		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+	}
+
+	rtnl_lock();
+	ice_pf_dis_all_vsi(pf, true);
+
+	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+		rtnl_unlock();
+		return;
+	}
+
+	/* changes in configuration update VSI */
+	ice_pf_dcb_recfg(pf);
+
+	ice_pf_ena_all_vsi(pf, true);
+	rtnl_unlock();
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
new file mode 100644
index 000000000000..819081053ff5
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Intel Corporation. */
+
+#ifndef _ICE_DCB_LIB_H_
+#define _ICE_DCB_LIB_H_
+
+#include "ice.h"
+#include "ice_lib.h"
+
+#ifdef CONFIG_DCB
+#define ICE_TC_MAX_BW 100 /* Default Max BW percentage */
+
+void ice_dcb_rebuild(struct ice_pf *pf);
+u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg);
+u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg);
+void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi);
+int ice_init_pf_dcb(struct ice_pf *pf, bool locked);
+void ice_update_dcb_stats(struct ice_pf *pf);
+int
+ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
+			      struct ice_tx_buf *first);
+void
+ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
+				    struct ice_rq_event_info *event);
+static inline void
+ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring)
+{
+	tlan_ctx->cgd_num = ring->dcb_tc;
+}
+#else
+#define ice_dcb_rebuild(pf) do {} while (0)
+
+static inline u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg __always_unused *dcbcfg)
+{
+	return ICE_DFLT_TRAFFIC_CLASS;
+}
+
+static inline u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg __always_unused *dcbcfg)
+{
+	return 1;
+}
+
+static inline int
+ice_init_pf_dcb(struct ice_pf *pf, bool __always_unused locked)
+{
+	dev_dbg(&pf->pdev->dev, "DCB not supported\n");
+	return -EOPNOTSUPP;
+}
+
+static inline int
+ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring,
+			      struct ice_tx_buf __always_unused *first)
+{
+	return 0;
+}
+
+#define ice_update_dcb_stats(pf) do {} while (0)
+#define ice_vsi_cfg_dcb_rings(vsi) do {} while (0)
+#define ice_dcb_process_lldp_set_mib_change(pf, event) do {} while (0)
+#define ice_set_cgd_num(tlan_ctx, ring) do {} while (0)
+#endif /* CONFIG_DCB */
+#endif /* _ICE_DCB_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 3b6e387f5440..52083a63dee6 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4,6 +4,8 @@
 /* ethtool support for ice */
 
 #include "ice.h"
+#include "ice_lib.h"
+#include "ice_dcb_lib.h"
 
 struct ice_stats {
 	char stat_string[ETH_GSTRING_LEN];
@@ -33,26 +35,50 @@ static int ice_q_stats_len(struct net_device *netdev)
 #define ICE_PF_STATS_LEN	ARRAY_SIZE(ice_gstrings_pf_stats)
 #define ICE_VSI_STATS_LEN	ARRAY_SIZE(ice_gstrings_vsi_stats)
 
-#define ICE_ALL_STATS_LEN(n)	(ICE_PF_STATS_LEN + ICE_VSI_STATS_LEN + \
-				 ice_q_stats_len(n))
+#define ICE_PFC_STATS_LEN ( \
+		(FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_rx) + \
+		 FIELD_SIZEOF(struct ice_pf, stats.priority_xon_rx) + \
+		 FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_tx) + \
+		 FIELD_SIZEOF(struct ice_pf, stats.priority_xon_tx)) \
+		 / sizeof(u64))
+#define ICE_ALL_STATS_LEN(n)	(ICE_PF_STATS_LEN + ICE_PFC_STATS_LEN + \
+				 ICE_VSI_STATS_LEN + ice_q_stats_len(n))
 
 static const struct ice_stats ice_gstrings_vsi_stats[] = {
-	ICE_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
 	ICE_VSI_STAT("rx_unicast", eth_stats.rx_unicast),
-	ICE_VSI_STAT("tx_multicast", eth_stats.tx_multicast),
+	ICE_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
 	ICE_VSI_STAT("rx_multicast", eth_stats.rx_multicast),
-	ICE_VSI_STAT("tx_broadcast", eth_stats.tx_broadcast),
+	ICE_VSI_STAT("tx_multicast", eth_stats.tx_multicast),
 	ICE_VSI_STAT("rx_broadcast", eth_stats.rx_broadcast),
-	ICE_VSI_STAT("tx_bytes", eth_stats.tx_bytes),
+	ICE_VSI_STAT("tx_broadcast", eth_stats.tx_broadcast),
 	ICE_VSI_STAT("rx_bytes", eth_stats.rx_bytes),
-	ICE_VSI_STAT("rx_discards", eth_stats.rx_discards),
-	ICE_VSI_STAT("tx_errors", eth_stats.tx_errors),
-	ICE_VSI_STAT("tx_linearize", tx_linearize),
+	ICE_VSI_STAT("tx_bytes", eth_stats.tx_bytes),
+	ICE_VSI_STAT("rx_dropped", eth_stats.rx_discards),
 	ICE_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
 	ICE_VSI_STAT("rx_alloc_fail", rx_buf_failed),
 	ICE_VSI_STAT("rx_pg_alloc_fail", rx_page_failed),
+	ICE_VSI_STAT("tx_errors", eth_stats.tx_errors),
+	ICE_VSI_STAT("tx_linearize", tx_linearize),
+};
+
+enum ice_ethtool_test_id {
+	ICE_ETH_TEST_REG = 0,
+	ICE_ETH_TEST_EEPROM,
+	ICE_ETH_TEST_INTR,
+	ICE_ETH_TEST_LOOP,
+	ICE_ETH_TEST_LINK,
 };
 
+static const char ice_gstrings_test[][ETH_GSTRING_LEN] = {
+	"Register test  (offline)",
+	"EEPROM test    (offline)",
+	"Interrupt test (offline)",
+	"Loopback test  (offline)",
+	"Link test   (on/offline)",
+};
+
+#define ICE_TEST_LEN (sizeof(ice_gstrings_test) / ETH_GSTRING_LEN)
+
 /* These PF_STATs might look like duplicates of some NETDEV_STATs,
  * but they aren't. This device is capable of supporting multiple
  * VSIs/netdevs on a single PF. The NETDEV_STATs are for individual
@@ -63,45 +89,45 @@ static const struct ice_stats ice_gstrings_vsi_stats[] = {
  * is queried on the base PF netdev.
  */
 static const struct ice_stats ice_gstrings_pf_stats[] = {
-	ICE_PF_STAT("tx_bytes", stats.eth.tx_bytes),
-	ICE_PF_STAT("rx_bytes", stats.eth.rx_bytes),
-	ICE_PF_STAT("tx_unicast", stats.eth.tx_unicast),
-	ICE_PF_STAT("rx_unicast", stats.eth.rx_unicast),
-	ICE_PF_STAT("tx_multicast", stats.eth.tx_multicast),
-	ICE_PF_STAT("rx_multicast", stats.eth.rx_multicast),
-	ICE_PF_STAT("tx_broadcast", stats.eth.tx_broadcast),
-	ICE_PF_STAT("rx_broadcast", stats.eth.rx_broadcast),
-	ICE_PF_STAT("tx_errors", stats.eth.tx_errors),
-	ICE_PF_STAT("tx_size_64", stats.tx_size_64),
-	ICE_PF_STAT("rx_size_64", stats.rx_size_64),
-	ICE_PF_STAT("tx_size_127", stats.tx_size_127),
-	ICE_PF_STAT("rx_size_127", stats.rx_size_127),
-	ICE_PF_STAT("tx_size_255", stats.tx_size_255),
-	ICE_PF_STAT("rx_size_255", stats.rx_size_255),
-	ICE_PF_STAT("tx_size_511", stats.tx_size_511),
-	ICE_PF_STAT("rx_size_511", stats.rx_size_511),
-	ICE_PF_STAT("tx_size_1023", stats.tx_size_1023),
-	ICE_PF_STAT("rx_size_1023", stats.rx_size_1023),
-	ICE_PF_STAT("tx_size_1522", stats.tx_size_1522),
-	ICE_PF_STAT("rx_size_1522", stats.rx_size_1522),
-	ICE_PF_STAT("tx_size_big", stats.tx_size_big),
-	ICE_PF_STAT("rx_size_big", stats.rx_size_big),
-	ICE_PF_STAT("link_xon_tx", stats.link_xon_tx),
-	ICE_PF_STAT("link_xon_rx", stats.link_xon_rx),
-	ICE_PF_STAT("link_xoff_tx", stats.link_xoff_tx),
-	ICE_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
-	ICE_PF_STAT("tx_dropped_link_down", stats.tx_dropped_link_down),
-	ICE_PF_STAT("rx_undersize", stats.rx_undersize),
-	ICE_PF_STAT("rx_fragments", stats.rx_fragments),
-	ICE_PF_STAT("rx_oversize", stats.rx_oversize),
-	ICE_PF_STAT("rx_jabber", stats.rx_jabber),
-	ICE_PF_STAT("rx_csum_bad", hw_csum_rx_error),
-	ICE_PF_STAT("rx_length_errors", stats.rx_len_errors),
-	ICE_PF_STAT("rx_dropped", stats.eth.rx_discards),
-	ICE_PF_STAT("rx_crc_errors", stats.crc_errors),
-	ICE_PF_STAT("illegal_bytes", stats.illegal_bytes),
-	ICE_PF_STAT("mac_local_faults", stats.mac_local_faults),
-	ICE_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
+	ICE_PF_STAT("rx_bytes.nic", stats.eth.rx_bytes),
+	ICE_PF_STAT("tx_bytes.nic", stats.eth.tx_bytes),
+	ICE_PF_STAT("rx_unicast.nic", stats.eth.rx_unicast),
+	ICE_PF_STAT("tx_unicast.nic", stats.eth.tx_unicast),
+	ICE_PF_STAT("rx_multicast.nic", stats.eth.rx_multicast),
+	ICE_PF_STAT("tx_multicast.nic", stats.eth.tx_multicast),
+	ICE_PF_STAT("rx_broadcast.nic", stats.eth.rx_broadcast),
+	ICE_PF_STAT("tx_broadcast.nic", stats.eth.tx_broadcast),
+	ICE_PF_STAT("tx_errors.nic", stats.eth.tx_errors),
+	ICE_PF_STAT("rx_size_64.nic", stats.rx_size_64),
+	ICE_PF_STAT("tx_size_64.nic", stats.tx_size_64),
+	ICE_PF_STAT("rx_size_127.nic", stats.rx_size_127),
+	ICE_PF_STAT("tx_size_127.nic", stats.tx_size_127),
+	ICE_PF_STAT("rx_size_255.nic", stats.rx_size_255),
+	ICE_PF_STAT("tx_size_255.nic", stats.tx_size_255),
+	ICE_PF_STAT("rx_size_511.nic", stats.rx_size_511),
+	ICE_PF_STAT("tx_size_511.nic", stats.tx_size_511),
+	ICE_PF_STAT("rx_size_1023.nic", stats.rx_size_1023),
+	ICE_PF_STAT("tx_size_1023.nic", stats.tx_size_1023),
+	ICE_PF_STAT("rx_size_1522.nic", stats.rx_size_1522),
+	ICE_PF_STAT("tx_size_1522.nic", stats.tx_size_1522),
+	ICE_PF_STAT("rx_size_big.nic", stats.rx_size_big),
+	ICE_PF_STAT("tx_size_big.nic", stats.tx_size_big),
+	ICE_PF_STAT("link_xon_rx.nic", stats.link_xon_rx),
+	ICE_PF_STAT("link_xon_tx.nic", stats.link_xon_tx),
+	ICE_PF_STAT("link_xoff_rx.nic", stats.link_xoff_rx),
+	ICE_PF_STAT("link_xoff_tx.nic", stats.link_xoff_tx),
+	ICE_PF_STAT("tx_dropped_link_down.nic", stats.tx_dropped_link_down),
+	ICE_PF_STAT("rx_undersize.nic", stats.rx_undersize),
+	ICE_PF_STAT("rx_fragments.nic", stats.rx_fragments),
+	ICE_PF_STAT("rx_oversize.nic", stats.rx_oversize),
+	ICE_PF_STAT("rx_jabber.nic", stats.rx_jabber),
+	ICE_PF_STAT("rx_csum_bad.nic", hw_csum_rx_error),
+	ICE_PF_STAT("rx_length_errors.nic", stats.rx_len_errors),
+	ICE_PF_STAT("rx_dropped.nic", stats.eth.rx_discards),
+	ICE_PF_STAT("rx_crc_errors.nic", stats.crc_errors),
+	ICE_PF_STAT("illegal_bytes.nic", stats.illegal_bytes),
+	ICE_PF_STAT("mac_local_faults.nic", stats.mac_local_faults),
+	ICE_PF_STAT("mac_remote_faults.nic", stats.mac_remote_faults),
 };
 
 static const u32 ice_regs_dump_list[] = {
@@ -112,8 +138,28 @@ static const u32 ice_regs_dump_list[] = {
 	QINT_RQCTL(0),
 	PFINT_OICR_ENA,
 	QRX_ITR(0),
+	PF0INT_ITR_0(0),
+	PF0INT_ITR_1(0),
+	PF0INT_ITR_2(0),
+};
+
+struct ice_priv_flag {
+	char name[ETH_GSTRING_LEN];
+	u32 bitno;			/* bit position in pf->flags */
+};
+
+#define ICE_PRIV_FLAG(_name, _bitno) { \
+	.name = _name, \
+	.bitno = _bitno, \
+}
+
+static const struct ice_priv_flag ice_gstrings_priv_flags[] = {
+	ICE_PRIV_FLAG("link-down-on-close", ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA),
+	ICE_PRIV_FLAG("enable-fw-lldp", ICE_FLAG_ENABLE_FW_LLDP),
 };
 
+#define ICE_PRIV_FLAG_ARRAY_SIZE	ARRAY_SIZE(ice_gstrings_priv_flags)
+
 /**
  * ice_nvm_version_str - format the NVM version strings
  * @hw: ptr to the hardware info
@@ -152,6 +198,7 @@ ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 		sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(pf->pdev),
 		sizeof(drvinfo->bus_info));
+	drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE;
 }
 
 static int ice_get_regs_len(struct net_device __always_unused *netdev)
@@ -203,6 +250,620 @@ static void ice_set_msglevel(struct net_device *netdev, u32 data)
 #endif /* !CONFIG_DYNAMIC_DEBUG */
 }
 
+static int ice_get_eeprom_len(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = np->vsi->back;
+
+	return (int)(pf->hw.nvm.sr_words * sizeof(u16));
+}
+
+static int
+ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+	       u8 *bytes)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	u16 first_word, last_word, nwords;
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	enum ice_status status;
+	struct device *dev;
+	int ret = 0;
+	u16 *buf;
+
+	dev = &pf->pdev->dev;
+
+	eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+	first_word = eeprom->offset >> 1;
+	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+	nwords = last_word - first_word + 1;
+
+	buf = devm_kcalloc(dev, nwords, sizeof(u16), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	status = ice_read_sr_buf(hw, first_word, &nwords, buf);
+	if (status) {
+		dev_err(dev, "ice_read_sr_buf failed, err %d aq_err %d\n",
+			status, hw->adminq.sq_last_status);
+		eeprom->len = sizeof(u16) * nwords;
+		ret = -EIO;
+		goto out;
+	}
+
+	memcpy(bytes, (u8 *)buf + (eeprom->offset & 1), eeprom->len);
+out:
+	devm_kfree(dev, buf);
+	return ret;
+}
+
+/**
+ * ice_active_vfs - check if there are any active VFs
+ * @pf: board private structure
+ *
+ * Returns true if an active VF is found, otherwise returns false
+ */
+static bool ice_active_vfs(struct ice_pf *pf)
+{
+	struct ice_vf *vf = pf->vf;
+	int i;
+
+	for (i = 0; i < pf->num_alloc_vfs; i++, vf++)
+		if (test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+			return true;
+	return false;
+}
+
+/**
+ * ice_link_test - perform a link test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_link_test(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	enum ice_status status;
+	bool link_up = false;
+
+	netdev_info(netdev, "link test\n");
+	status = ice_get_link_status(np->vsi->port_info, &link_up);
+	if (status) {
+		netdev_err(netdev, "link query error, status = %d\n", status);
+		return 1;
+	}
+
+	if (!link_up)
+		return 2;
+
+	return 0;
+}
+
+/**
+ * ice_eeprom_test - perform an EEPROM test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_eeprom_test(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = np->vsi->back;
+
+	netdev_info(netdev, "EEPROM test\n");
+	return !!(ice_nvm_validate_checksum(&pf->hw));
+}
+
+/**
+ * ice_reg_pattern_test
+ * @hw: pointer to the HW struct
+ * @reg: reg to be tested
+ * @mask: bits to be touched
+ */
+static int ice_reg_pattern_test(struct ice_hw *hw, u32 reg, u32 mask)
+{
+	struct ice_pf *pf = (struct ice_pf *)hw->back;
+	static const u32 patterns[] = {
+		0x5A5A5A5A, 0xA5A5A5A5,
+		0x00000000, 0xFFFFFFFF
+	};
+	u32 val, orig_val;
+	int i;
+
+	orig_val = rd32(hw, reg);
+	for (i = 0; i < ARRAY_SIZE(patterns); ++i) {
+		u32 pattern = patterns[i] & mask;
+
+		wr32(hw, reg, pattern);
+		val = rd32(hw, reg);
+		if (val == pattern)
+			continue;
+		dev_err(&pf->pdev->dev,
+			"%s: reg pattern test failed - reg 0x%08x pat 0x%08x val 0x%08x\n"
+			, __func__, reg, pattern, val);
+		return 1;
+	}
+
+	wr32(hw, reg, orig_val);
+	val = rd32(hw, reg);
+	if (val != orig_val) {
+		dev_err(&pf->pdev->dev,
+			"%s: reg restore test failed - reg 0x%08x orig 0x%08x val 0x%08x\n"
+			, __func__, reg, orig_val, val);
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_reg_test - perform a register test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_reg_test(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_hw *hw = np->vsi->port_info->hw;
+	u32 int_elements = hw->func_caps.common_cap.num_msix_vectors ?
+		hw->func_caps.common_cap.num_msix_vectors - 1 : 1;
+	struct ice_diag_reg_test_info {
+		u32 address;
+		u32 mask;
+		u32 elem_num;
+		u32 elem_size;
+	} ice_reg_list[] = {
+		{GLINT_ITR(0, 0), 0x00000fff, int_elements,
+			GLINT_ITR(0, 1) - GLINT_ITR(0, 0)},
+		{GLINT_ITR(1, 0), 0x00000fff, int_elements,
+			GLINT_ITR(1, 1) - GLINT_ITR(1, 0)},
+		{GLINT_ITR(0, 0), 0x00000fff, int_elements,
+			GLINT_ITR(2, 1) - GLINT_ITR(2, 0)},
+		{GLINT_CTL, 0xffff0001, 1, 0}
+	};
+	int i;
+
+	netdev_dbg(netdev, "Register test\n");
+	for (i = 0; i < ARRAY_SIZE(ice_reg_list); ++i) {
+		u32 j;
+
+		for (j = 0; j < ice_reg_list[i].elem_num; ++j) {
+			u32 mask = ice_reg_list[i].mask;
+			u32 reg = ice_reg_list[i].address +
+				(j * ice_reg_list[i].elem_size);
+
+			/* bail on failure (non-zero return) */
+			if (ice_reg_pattern_test(hw, reg, mask))
+				return 1;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * ice_lbtest_prepare_rings - configure Tx/Rx test rings
+ * @vsi: pointer to the VSI structure
+ *
+ * Function configures rings of a VSI for loopback test without
+ * enabling interrupts or informing the kernel about new queues.
+ *
+ * Returns 0 on success, negative on failure.
+ */
+static int ice_lbtest_prepare_rings(struct ice_vsi *vsi)
+{
+	int status;
+
+	status = ice_vsi_setup_tx_rings(vsi);
+	if (status)
+		goto err_setup_tx_ring;
+
+	status = ice_vsi_setup_rx_rings(vsi);
+	if (status)
+		goto err_setup_rx_ring;
+
+	status = ice_vsi_cfg(vsi);
+	if (status)
+		goto err_setup_rx_ring;
+
+	status = ice_vsi_start_rx_rings(vsi);
+	if (status)
+		goto err_start_rx_ring;
+
+	return status;
+
+err_start_rx_ring:
+	ice_vsi_free_rx_rings(vsi);
+err_setup_rx_ring:
+	ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
+err_setup_tx_ring:
+	ice_vsi_free_tx_rings(vsi);
+
+	return status;
+}
+
+/**
+ * ice_lbtest_disable_rings - disable Tx/Rx test rings after loopback test
+ * @vsi: pointer to the VSI structure
+ *
+ * Function stops and frees VSI rings after a loopback test.
+ * Returns 0 on success, negative on failure.
+ */
+static int ice_lbtest_disable_rings(struct ice_vsi *vsi)
+{
+	int status;
+
+	status = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
+	if (status)
+		netdev_err(vsi->netdev, "Failed to stop Tx rings, VSI %d error %d\n",
+			   vsi->vsi_num, status);
+
+	status = ice_vsi_stop_rx_rings(vsi);
+	if (status)
+		netdev_err(vsi->netdev, "Failed to stop Rx rings, VSI %d error %d\n",
+			   vsi->vsi_num, status);
+
+	ice_vsi_free_tx_rings(vsi);
+	ice_vsi_free_rx_rings(vsi);
+
+	return status;
+}
+
+/**
+ * ice_lbtest_create_frame - create test packet
+ * @pf: pointer to the PF structure
+ * @ret_data: allocated frame buffer
+ * @size: size of the packet data
+ *
+ * Function allocates a frame with a test pattern on specific offsets.
+ * Returns 0 on success, non-zero on failure.
+ */
+static int ice_lbtest_create_frame(struct ice_pf *pf, u8 **ret_data, u16 size)
+{
+	u8 *data;
+
+	if (!pf)
+		return -EINVAL;
+
+	data = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* Since the ethernet test frame should always be at least
+	 * 64 bytes long, fill some octets in the payload with test data.
+	 */
+	memset(data, 0xFF, size);
+	data[32] = 0xDE;
+	data[42] = 0xAD;
+	data[44] = 0xBE;
+	data[46] = 0xEF;
+
+	*ret_data = data;
+
+	return 0;
+}
+
+/**
+ * ice_lbtest_check_frame - verify received loopback frame
+ * @frame: pointer to the raw packet data
+ *
+ * Function verifies received test frame with a pattern.
+ * Returns true if frame matches the pattern, false otherwise.
+ */
+static bool ice_lbtest_check_frame(u8 *frame)
+{
+	/* Validate bytes of a frame under offsets chosen earlier */
+	if (frame[32] == 0xDE &&
+	    frame[42] == 0xAD &&
+	    frame[44] == 0xBE &&
+	    frame[46] == 0xEF &&
+	    frame[48] == 0xFF)
+		return true;
+
+	return false;
+}
+
+/**
+ * ice_diag_send - send test frames to the test ring
+ * @tx_ring: pointer to the transmit ring
+ * @data: pointer to the raw packet data
+ * @size: size of the packet to send
+ *
+ * Function sends loopback packets on a test Tx ring.
+ */
+static int ice_diag_send(struct ice_ring *tx_ring, u8 *data, u16 size)
+{
+	struct ice_tx_desc *tx_desc;
+	struct ice_tx_buf *tx_buf;
+	dma_addr_t dma;
+	u64 td_cmd;
+
+	tx_desc = ICE_TX_DESC(tx_ring, tx_ring->next_to_use);
+	tx_buf = &tx_ring->tx_buf[tx_ring->next_to_use];
+
+	dma = dma_map_single(tx_ring->dev, data, size, DMA_TO_DEVICE);
+	if (dma_mapping_error(tx_ring->dev, dma))
+		return -EINVAL;
+
+	tx_desc->buf_addr = cpu_to_le64(dma);
+
+	/* These flags are required for a descriptor to be pushed out */
+	td_cmd = (u64)(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS);
+	tx_desc->cmd_type_offset_bsz =
+		cpu_to_le64(ICE_TX_DESC_DTYPE_DATA |
+			    (td_cmd << ICE_TXD_QW1_CMD_S) |
+			    ((u64)0 << ICE_TXD_QW1_OFFSET_S) |
+			    ((u64)size << ICE_TXD_QW1_TX_BUF_SZ_S) |
+			    ((u64)0 << ICE_TXD_QW1_L2TAG1_S));
+
+	tx_buf->next_to_watch = tx_desc;
+
+	/* Force memory write to complete before letting h/w know
+	 * there are new descriptors to fetch.
+	 */
+	wmb();
+
+	tx_ring->next_to_use++;
+	if (tx_ring->next_to_use >= tx_ring->count)
+		tx_ring->next_to_use = 0;
+
+	writel_relaxed(tx_ring->next_to_use, tx_ring->tail);
+
+	/* Wait until the packets get transmitted to the receive queue. */
+	usleep_range(1000, 2000);
+	dma_unmap_single(tx_ring->dev, dma, size, DMA_TO_DEVICE);
+
+	return 0;
+}
+
+#define ICE_LB_FRAME_SIZE 64
+/**
+ * ice_lbtest_receive_frames - receive and verify test frames
+ * @rx_ring: pointer to the receive ring
+ *
+ * Function receives loopback packets and verify their correctness.
+ * Returns number of received valid frames.
+ */
+static int ice_lbtest_receive_frames(struct ice_ring *rx_ring)
+{
+	struct ice_rx_buf *rx_buf;
+	int valid_frames, i;
+	u8 *received_buf;
+
+	valid_frames = 0;
+
+	for (i = 0; i < rx_ring->count; i++) {
+		union ice_32b_rx_flex_desc *rx_desc;
+
+		rx_desc = ICE_RX_DESC(rx_ring, i);
+
+		if (!(rx_desc->wb.status_error0 &
+		    cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)))
+			continue;
+
+		rx_buf = &rx_ring->rx_buf[i];
+		received_buf = page_address(rx_buf->page);
+
+		if (ice_lbtest_check_frame(received_buf))
+			valid_frames++;
+	}
+
+	return valid_frames;
+}
+
+/**
+ * ice_loopback_test - perform a loopback test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_loopback_test(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *orig_vsi = np->vsi, *test_vsi;
+	struct ice_pf *pf = orig_vsi->back;
+	struct ice_ring *tx_ring, *rx_ring;
+	u8 broadcast[ETH_ALEN], ret = 0;
+	int num_frames, valid_frames;
+	LIST_HEAD(tmp_list);
+	u8 *tx_frame;
+	int i;
+
+	netdev_info(netdev, "loopback test\n");
+
+	test_vsi = ice_lb_vsi_setup(pf, pf->hw.port_info);
+	if (!test_vsi) {
+		netdev_err(netdev, "Failed to create a VSI for the loopback test");
+		return 1;
+	}
+
+	test_vsi->netdev = netdev;
+	tx_ring = test_vsi->tx_rings[0];
+	rx_ring = test_vsi->rx_rings[0];
+
+	if (ice_lbtest_prepare_rings(test_vsi)) {
+		ret = 2;
+		goto lbtest_vsi_close;
+	}
+
+	if (ice_alloc_rx_bufs(rx_ring, rx_ring->count)) {
+		ret = 3;
+		goto lbtest_rings_dis;
+	}
+
+	/* Enable MAC loopback in firmware */
+	if (ice_aq_set_mac_loopback(&pf->hw, true, NULL)) {
+		ret = 4;
+		goto lbtest_mac_dis;
+	}
+
+	/* Test VSI needs to receive broadcast packets */
+	eth_broadcast_addr(broadcast);
+	if (ice_add_mac_to_list(test_vsi, &tmp_list, broadcast)) {
+		ret = 5;
+		goto lbtest_mac_dis;
+	}
+
+	if (ice_add_mac(&pf->hw, &tmp_list)) {
+		ret = 6;
+		goto free_mac_list;
+	}
+
+	if (ice_lbtest_create_frame(pf, &tx_frame, ICE_LB_FRAME_SIZE)) {
+		ret = 7;
+		goto remove_mac_filters;
+	}
+
+	num_frames = min_t(int, tx_ring->count, 32);
+	for (i = 0; i < num_frames; i++) {
+		if (ice_diag_send(tx_ring, tx_frame, ICE_LB_FRAME_SIZE)) {
+			ret = 8;
+			goto lbtest_free_frame;
+		}
+	}
+
+	valid_frames = ice_lbtest_receive_frames(rx_ring);
+	if (!valid_frames)
+		ret = 9;
+	else if (valid_frames != num_frames)
+		ret = 10;
+
+lbtest_free_frame:
+	devm_kfree(&pf->pdev->dev, tx_frame);
+remove_mac_filters:
+	if (ice_remove_mac(&pf->hw, &tmp_list))
+		netdev_err(netdev, "Could not remove MAC filter for the test VSI");
+free_mac_list:
+	ice_free_fltr_list(&pf->pdev->dev, &tmp_list);
+lbtest_mac_dis:
+	/* Disable MAC loopback after the test is completed. */
+	if (ice_aq_set_mac_loopback(&pf->hw, false, NULL))
+		netdev_err(netdev, "Could not disable MAC loopback\n");
+lbtest_rings_dis:
+	if (ice_lbtest_disable_rings(test_vsi))
+		netdev_err(netdev, "Could not disable test rings\n");
+lbtest_vsi_close:
+	test_vsi->netdev = NULL;
+	if (ice_vsi_release(test_vsi))
+		netdev_err(netdev, "Failed to remove the test VSI");
+
+	return ret;
+}
+
+/**
+ * ice_intr_test - perform an interrupt test on a given net_device
+ * @netdev: network interface device structure
+ *
+ * This function performs one of the self-tests required by ethtool.
+ * Returns 0 on success, non-zero on failure.
+ */
+static u64 ice_intr_test(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = np->vsi->back;
+	u16 swic_old = pf->sw_int_count;
+
+	netdev_info(netdev, "interrupt test\n");
+
+	wr32(&pf->hw, GLINT_DYN_CTL(pf->oicr_idx),
+	     GLINT_DYN_CTL_SW_ITR_INDX_M |
+	     GLINT_DYN_CTL_INTENA_MSK_M |
+	     GLINT_DYN_CTL_SWINT_TRIG_M);
+
+	usleep_range(1000, 2000);
+	return (swic_old == pf->sw_int_count);
+}
+
+/**
+ * ice_self_test - handler function for performing a self-test by ethtool
+ * @netdev: network interface device structure
+ * @eth_test: ethtool_test structure
+ * @data: required by ethtool.self_test
+ *
+ * This function is called after invoking 'ethtool -t devname' command where
+ * devname is the name of the network device on which ethtool should operate.
+ * It performs a set of self-tests to check if a device works properly.
+ */
+static void
+ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test,
+	      u64 *data)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	bool if_running = netif_running(netdev);
+	struct ice_pf *pf = np->vsi->back;
+
+	if (eth_test->flags == ETH_TEST_FL_OFFLINE) {
+		netdev_info(netdev, "offline testing starting\n");
+
+		set_bit(__ICE_TESTING, pf->state);
+
+		if (ice_active_vfs(pf)) {
+			dev_warn(&pf->pdev->dev,
+				 "Please take active VFs and Netqueues offline and restart the adapter before running NIC diagnostics\n");
+			data[ICE_ETH_TEST_REG] = 1;
+			data[ICE_ETH_TEST_EEPROM] = 1;
+			data[ICE_ETH_TEST_INTR] = 1;
+			data[ICE_ETH_TEST_LOOP] = 1;
+			data[ICE_ETH_TEST_LINK] = 1;
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+			clear_bit(__ICE_TESTING, pf->state);
+			goto skip_ol_tests;
+		}
+		/* If the device is online then take it offline */
+		if (if_running)
+			/* indicate we're in test mode */
+			ice_stop(netdev);
+
+		data[ICE_ETH_TEST_LINK] = ice_link_test(netdev);
+		data[ICE_ETH_TEST_EEPROM] = ice_eeprom_test(netdev);
+		data[ICE_ETH_TEST_INTR] = ice_intr_test(netdev);
+		data[ICE_ETH_TEST_LOOP] = ice_loopback_test(netdev);
+		data[ICE_ETH_TEST_REG] = ice_reg_test(netdev);
+
+		if (data[ICE_ETH_TEST_LINK] ||
+		    data[ICE_ETH_TEST_EEPROM] ||
+		    data[ICE_ETH_TEST_LOOP] ||
+		    data[ICE_ETH_TEST_INTR] ||
+		    data[ICE_ETH_TEST_REG])
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		clear_bit(__ICE_TESTING, pf->state);
+
+		if (if_running) {
+			int status = ice_open(netdev);
+
+			if (status) {
+				dev_err(&pf->pdev->dev,
+					"Could not open device %s, err %d",
+					pf->int_name, status);
+			}
+		}
+	} else {
+		/* Online tests */
+		netdev_info(netdev, "online testing starting\n");
+
+		data[ICE_ETH_TEST_LINK] = ice_link_test(netdev);
+		if (data[ICE_ETH_TEST_LINK])
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+
+		/* Offline only tests, not run in online; pass by default */
+		data[ICE_ETH_TEST_REG] = 0;
+		data[ICE_ETH_TEST_EEPROM] = 0;
+		data[ICE_ETH_TEST_INTR] = 0;
+		data[ICE_ETH_TEST_LOOP] = 0;
+	}
+
+skip_ol_tests:
+	netdev_info(netdev, "testing finished\n");
+}
+
 static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
@@ -220,17 +881,17 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 
 		ice_for_each_alloc_txq(vsi, i) {
 			snprintf(p, ETH_GSTRING_LEN,
-				 "tx-queue-%u.tx_packets", i);
+				 "tx_queue_%u_packets", i);
 			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "tx-queue-%u.tx_bytes", i);
+			snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_bytes", i);
 			p += ETH_GSTRING_LEN;
 		}
 
 		ice_for_each_alloc_rxq(vsi, i) {
 			snprintf(p, ETH_GSTRING_LEN,
-				 "rx-queue-%u.rx_packets", i);
+				 "rx_queue_%u_packets", i);
 			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "rx-queue-%u.rx_bytes", i);
+			snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_bytes", i);
 			p += ETH_GSTRING_LEN;
 		}
 
@@ -238,15 +899,384 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 			return;
 
 		for (i = 0; i < ICE_PF_STATS_LEN; i++) {
-			snprintf(p, ETH_GSTRING_LEN, "port.%s",
+			snprintf(p, ETH_GSTRING_LEN, "%s",
 				 ice_gstrings_pf_stats[i].stat_string);
 			p += ETH_GSTRING_LEN;
 		}
 
+		for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+			snprintf(p, ETH_GSTRING_LEN,
+				 "tx_priority_%u_xon.nic", i);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN,
+				 "tx_priority_%u_xoff.nic", i);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+			snprintf(p, ETH_GSTRING_LEN,
+				 "rx_priority_%u_xon.nic", i);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN,
+				 "rx_priority_%u_xoff.nic", i);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	case ETH_SS_TEST:
+		memcpy(data, ice_gstrings_test, ICE_TEST_LEN * ETH_GSTRING_LEN);
+		break;
+	case ETH_SS_PRIV_FLAGS:
+		for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 ice_gstrings_priv_flags[i].name);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static int
+ice_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	bool led_active;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		led_active = true;
+		break;
+	case ETHTOOL_ID_INACTIVE:
+		led_active = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ice_aq_set_port_id_led(np->vsi->port_info, !led_active, NULL))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * ice_set_fec_cfg - Set link FEC options
+ * @netdev: network interface device structure
+ * @req_fec: FEC mode to configure
+ */
+static int ice_set_fec_cfg(struct net_device *netdev, enum ice_fec_mode req_fec)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_aqc_set_phy_cfg_data config = { 0 };
+	struct ice_aqc_get_phy_caps_data *caps;
+	struct ice_vsi *vsi = np->vsi;
+	u8 sw_cfg_caps, sw_cfg_fec;
+	struct ice_port_info *pi;
+	enum ice_status status;
+	int err = 0;
+
+	pi = vsi->port_info;
+	if (!pi)
+		return -EOPNOTSUPP;
+
+	/* Changing the FEC parameters is not supported if not the PF VSI */
+	if (vsi->type != ICE_VSI_PF) {
+		netdev_info(netdev, "Changing FEC parameters only supported for PF VSI\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Get last SW configuration */
+	caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+	if (!caps)
+		return -ENOMEM;
+
+	status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG,
+				     caps, NULL);
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
+
+	/* Copy SW configuration returned from PHY caps to PHY config */
+	ice_copy_phy_caps_to_cfg(caps, &config);
+	sw_cfg_caps = caps->caps;
+	sw_cfg_fec = caps->link_fec_options;
+
+	/* Get toloplogy caps, then copy PHY FEC topoloy caps to PHY config */
+	memset(caps, 0, sizeof(*caps));
+
+	status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP,
+				     caps, NULL);
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
+
+	config.caps |= (caps->caps & ICE_AQC_PHY_EN_AUTO_FEC);
+	config.link_fec_opt = caps->link_fec_options;
+
+	ice_cfg_phy_fec(&config, req_fec);
+
+	/* If FEC mode has changed, then set PHY configuration and enable AN. */
+	if ((config.caps & ICE_AQ_PHY_ENA_AUTO_FEC) !=
+	    (sw_cfg_caps & ICE_AQC_PHY_EN_AUTO_FEC) ||
+	    config.link_fec_opt != sw_cfg_fec) {
+		if (caps->caps & ICE_AQC_PHY_AN_MODE)
+			config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+
+		status = ice_aq_set_phy_cfg(pi->hw, pi->lport, &config, NULL);
+
+		if (status)
+			err = -EAGAIN;
+	}
+
+done:
+	devm_kfree(&vsi->back->pdev->dev, caps);
+	return err;
+}
+
+/**
+ * ice_set_fecparam - Set FEC link options
+ * @netdev: network interface device structure
+ * @fecparam: Ethtool structure to retrieve FEC parameters
+ */
+static int
+ice_set_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	enum ice_fec_mode fec;
+
+	switch (fecparam->fec) {
+	case ETHTOOL_FEC_AUTO:
+		fec = ICE_FEC_AUTO;
+		break;
+	case ETHTOOL_FEC_RS:
+		fec = ICE_FEC_RS;
+		break;
+	case ETHTOOL_FEC_BASER:
+		fec = ICE_FEC_BASER;
+		break;
+	case ETHTOOL_FEC_OFF:
+	case ETHTOOL_FEC_NONE:
+		fec = ICE_FEC_NONE;
+		break;
+	default:
+		dev_warn(&vsi->back->pdev->dev, "Unsupported FEC mode: %d\n",
+			 fecparam->fec);
+		return -EINVAL;
+	}
+
+	return ice_set_fec_cfg(netdev, fec);
+}
+
+/**
+ * ice_get_fecparam - Get link FEC options
+ * @netdev: network interface device structure
+ * @fecparam: Ethtool structure to retrieve FEC parameters
+ */
+static int
+ice_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_aqc_get_phy_caps_data *caps;
+	struct ice_link_status *link_info;
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_port_info *pi;
+	enum ice_status status;
+	int err = 0;
+
+	pi = vsi->port_info;
+
+	if (!pi)
+		return -EOPNOTSUPP;
+	link_info = &pi->phy.link_info;
+
+	/* Set FEC mode based on negotiated link info */
+	switch (link_info->fec_info) {
+	case ICE_AQ_LINK_25G_KR_FEC_EN:
+		fecparam->active_fec = ETHTOOL_FEC_BASER;
+		break;
+	case ICE_AQ_LINK_25G_RS_528_FEC_EN:
+		/* fall through */
+	case ICE_AQ_LINK_25G_RS_544_FEC_EN:
+		fecparam->active_fec = ETHTOOL_FEC_RS;
 		break;
 	default:
+		fecparam->active_fec = ETHTOOL_FEC_OFF;
 		break;
 	}
+
+	caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+	if (!caps)
+		return -ENOMEM;
+
+	status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP,
+				     caps, NULL);
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
+
+	/* Set supported/configured FEC modes based on PHY capability */
+	if (caps->caps & ICE_AQC_PHY_EN_AUTO_FEC)
+		fecparam->fec |= ETHTOOL_FEC_AUTO;
+	if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_REQ)
+		fecparam->fec |= ETHTOOL_FEC_BASER;
+	if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_528_REQ ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN)
+		fecparam->fec |= ETHTOOL_FEC_RS;
+	if (caps->link_fec_options == 0)
+		fecparam->fec |= ETHTOOL_FEC_OFF;
+
+done:
+	devm_kfree(&vsi->back->pdev->dev, caps);
+	return err;
+}
+
+/**
+ * ice_get_priv_flags - report device private flags
+ * @netdev: network interface device structure
+ *
+ * The get string set count and the string set should be matched for each
+ * flag returned.  Add new strings for each flag to the ice_gstrings_priv_flags
+ * array.
+ *
+ * Returns a u32 bitmap of flags.
+ */
+static u32 ice_get_priv_flags(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	u32 i, ret_flags = 0;
+
+	for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+		const struct ice_priv_flag *priv_flag;
+
+		priv_flag = &ice_gstrings_priv_flags[i];
+
+		if (test_bit(priv_flag->bitno, pf->flags))
+			ret_flags |= BIT(i);
+	}
+
+	return ret_flags;
+}
+
+/**
+ * ice_set_priv_flags - set private flags
+ * @netdev: network interface device structure
+ * @flags: bit flags to be set
+ */
+static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	DECLARE_BITMAP(change_flags, ICE_PF_FLAGS_NBITS);
+	DECLARE_BITMAP(orig_flags, ICE_PF_FLAGS_NBITS);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	int ret = 0;
+	u32 i;
+
+	if (flags > BIT(ICE_PRIV_FLAG_ARRAY_SIZE))
+		return -EINVAL;
+
+	set_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags);
+
+	bitmap_copy(orig_flags, pf->flags, ICE_PF_FLAGS_NBITS);
+	for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+		const struct ice_priv_flag *priv_flag;
+
+		priv_flag = &ice_gstrings_priv_flags[i];
+
+		if (flags & BIT(i))
+			set_bit(priv_flag->bitno, pf->flags);
+		else
+			clear_bit(priv_flag->bitno, pf->flags);
+	}
+
+	bitmap_xor(change_flags, pf->flags, orig_flags, ICE_PF_FLAGS_NBITS);
+
+	if (test_bit(ICE_FLAG_ENABLE_FW_LLDP, change_flags)) {
+		if (!test_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags)) {
+			enum ice_status status;
+
+			/* Disable FW LLDP engine */
+			status = ice_aq_cfg_lldp_mib_change(&pf->hw, false,
+							    NULL);
+			/* If unregistering for LLDP events fails, this is
+			 * not an error state, as there shouldn't be any
+			 * events to respond to.
+			 */
+			if (status)
+				dev_info(&pf->pdev->dev,
+					 "Failed to unreg for LLDP events\n");
+
+			/* The AQ call to stop the FW LLDP agent will generate
+			 * an error if the agent is already stopped.
+			 */
+			status = ice_aq_stop_lldp(&pf->hw, true, true, NULL);
+			if (status)
+				dev_warn(&pf->pdev->dev,
+					 "Fail to stop LLDP agent\n");
+			/* Use case for having the FW LLDP agent stopped
+			 * will likely not need DCB, so failure to init is
+			 * not a concern of ethtool
+			 */
+			status = ice_init_pf_dcb(pf, true);
+			if (status)
+				dev_warn(&pf->pdev->dev, "Fail to init DCB\n");
+
+			/* Forward LLDP packets to default VSI so that they
+			 * are passed up the stack
+			 */
+			ice_cfg_sw_lldp(vsi, false, true);
+		} else {
+			enum ice_status status;
+			bool dcbx_agent_status;
+
+			/* AQ command to start FW LLDP agent will return an
+			 * error if the agent is already started
+			 */
+			status = ice_aq_start_lldp(&pf->hw, true, NULL);
+			if (status)
+				dev_warn(&pf->pdev->dev,
+					 "Fail to start LLDP Agent\n");
+
+			/* AQ command to start FW DCBX agent will fail if
+			 * the agent is already started
+			 */
+			status = ice_aq_start_stop_dcbx(&pf->hw, true,
+							&dcbx_agent_status,
+							NULL);
+			if (status)
+				dev_dbg(&pf->pdev->dev,
+					"Failed to start FW DCBX\n");
+
+			dev_info(&pf->pdev->dev, "FW DCBX agent is %s\n",
+				 dcbx_agent_status ? "ACTIVE" : "DISABLED");
+
+			/* Failure to configure MIB change or init DCB is not
+			 * relevant to ethtool.  Print notification that
+			 * registration/init failed but do not return error
+			 * state to ethtool
+			 */
+			status = ice_init_pf_dcb(pf, true);
+			if (status)
+				dev_dbg(&pf->pdev->dev, "Fail to init DCB\n");
+
+			/* Remove rule to direct LLDP packets to default VSI.
+			 * The FW LLDP engine will now be consuming them.
+			 */
+			ice_cfg_sw_lldp(vsi, false, false);
+		}
+	}
+	clear_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags);
+	return ret;
 }
 
 static int ice_get_sset_count(struct net_device *netdev, int sset)
@@ -272,6 +1302,10 @@ static int ice_get_sset_count(struct net_device *netdev, int sset)
 		 * not safe.
 		 */
 		return ICE_ALL_STATS_LEN(netdev);
+	case ETH_SS_TEST:
+		return ICE_TEST_LEN;
+	case ETH_SS_PRIV_FLAGS:
+		return ICE_PRIV_FLAG_ARRAY_SIZE;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -330,6 +1364,16 @@ ice_get_ethtool_stats(struct net_device *netdev,
 		data[i++] = (ice_gstrings_pf_stats[j].sizeof_stat ==
 			     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
+
+	for (j = 0; j < ICE_MAX_USER_PRIORITY; j++) {
+		data[i++] = pf->stats.priority_xon_tx[j];
+		data[i++] = pf->stats.priority_xoff_tx[j];
+	}
+
+	for (j = 0; j < ICE_MAX_USER_PRIORITY; j++) {
+		data[i++] = pf->stats.priority_xon_rx[j];
+		data[i++] = pf->stats.priority_xoff_rx[j];
+	}
 }
 
 /**
@@ -337,16 +1381,20 @@ ice_get_ethtool_stats(struct net_device *netdev,
  * @netdev: network interface device structure
  * @ks: ethtool link ksettings struct to fill out
  */
-static void ice_phy_type_to_ethtool(struct net_device *netdev,
-				    struct ethtool_link_ksettings *ks)
+static void
+ice_phy_type_to_ethtool(struct net_device *netdev,
+			struct ethtool_link_ksettings *ks)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_link_status *hw_link_info;
+	bool need_add_adv_mode = false;
 	struct ice_vsi *vsi = np->vsi;
+	u64 phy_types_high;
 	u64 phy_types_low;
 
 	hw_link_info = &vsi->port_info->phy.link_info;
 	phy_types_low = vsi->port_info->phy.phy_type_low;
+	phy_types_high = vsi->port_info->phy.phy_type_high;
 
 	ethtool_link_ksettings_zero_link_mode(ks, supported);
 	ethtool_link_ksettings_zero_link_mode(ks, advertising);
@@ -355,7 +1403,8 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_100M_SGMII) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     100baseT_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100MB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100MB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     100baseT_Full);
 	}
@@ -363,14 +1412,16 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_1G_SGMII) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     1000baseT_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     1000baseT_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     1000baseKX_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     1000baseKX_Full);
 	}
@@ -378,14 +1429,16 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_LX) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     1000baseX_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     1000baseX_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     2500baseT_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     2500baseT_Full);
 	}
@@ -393,7 +1446,8 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     2500baseX_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     2500baseX_Full);
 	}
@@ -401,7 +1455,8 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     5000baseT_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_5GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_5GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     5000baseT_Full);
 	}
@@ -411,28 +1466,32 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_C2C) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseT_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     10000baseT_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseKR_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     10000baseKR_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_SR) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseSR_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     10000baseSR_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_LR) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseLR_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     10000baseLR_Full);
 	}
@@ -444,7 +1503,8 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_C2C) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseCR_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     25000baseCR_Full);
 	}
@@ -452,7 +1512,8 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_LR) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseSR_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     25000baseSR_Full);
 	}
@@ -461,14 +1522,16 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseKR_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     25000baseKR_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseKR4_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     40000baseKR4_Full);
 	}
@@ -477,24 +1540,123 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 	    phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseCR4_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     40000baseCR4_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_SR4) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseSR4_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     40000baseSR4_Full);
 	}
 	if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_LR4) {
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     40000baseLR4_Full);
-		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB)
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     40000baseLR4_Full);
 	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_LAUI2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_SR ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI1) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseCR2_Full);
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     50000baseCR2_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseKR2_Full);
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     50000baseKR2_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_SR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_LR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_FR ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_LR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseSR2_Full);
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     50000baseSR2_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_CAUI4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_AUI4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2  ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_CAUI2 ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_AUI2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode) {
+		need_add_adv_mode = false;
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseCR4_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseSR4_Full);
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode) {
+		need_add_adv_mode = false;
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseSR4_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_LR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_DR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseLR4_ER4_Full);
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode) {
+		need_add_adv_mode = false;
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseLR4_ER4_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseKR4_Full);
+		if (!hw_link_info->req_speeds ||
+		    hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode)
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseKR4_Full);
 
 	/* Autoneg PHY types */
 	if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX ||
@@ -520,6 +1682,24 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     Autoneg);
 	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     Autoneg);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     Autoneg);
+	}
 }
 
 #define TEST_SET_BITS_TIMEOUT	50
@@ -531,18 +1711,20 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
  * @ks: ethtool ksettings to fill in
  * @netdev: network interface device structure
  */
-static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
-				     struct net_device *netdev)
+static void
+ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
+			 struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ethtool_link_ksettings cap_ksettings;
 	struct ice_link_status *link_info;
 	struct ice_vsi *vsi = np->vsi;
+	bool unrecog_phy_high = false;
 	bool unrecog_phy_low = false;
 
 	link_info = &vsi->port_info->phy.link_info;
 
-	/* Initialize supported and advertised settings based on phy settings */
+	/* Initialize supported and advertised settings based on PHY settings */
 	switch (link_info->phy_type_low) {
 	case ICE_PHY_TYPE_LOW_100BASE_TX:
 		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
@@ -652,6 +1834,7 @@ static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
 						     25000baseCR_Full);
 		break;
 	case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_25G_AUI_C2C:
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseCR_Full);
 		break;
@@ -699,25 +1882,133 @@ static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     40000baseKR4_Full);
 		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_CP:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseCR2_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     50000baseCR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_LAUI2:
+	case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI2:
+	case ICE_PHY_TYPE_LOW_50GBASE_SR:
+	case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI1:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseCR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseKR2_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     50000baseKR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_FR:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseSR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseCR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_CAUI4:
+	case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_AUI4:
+	case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_CP2:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseCR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseSR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_DR:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseLR4_ER4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseKR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseKR4_Full);
+		break;
 	default:
 		unrecog_phy_low = true;
 	}
 
-	if (unrecog_phy_low) {
+	switch (link_info->phy_type_high) {
+	case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseKR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseKR4_Full);
+		break;
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		break;
+	default:
+		unrecog_phy_high = true;
+	}
+
+	if (unrecog_phy_low && unrecog_phy_high) {
 		/* if we got here and link is up something bad is afoot */
-		netdev_info(netdev, "WARNING: Unrecognized PHY_Low (0x%llx).\n",
+		netdev_info(netdev,
+			    "WARNING: Unrecognized PHY_Low (0x%llx).\n",
 			    (u64)link_info->phy_type_low);
+		netdev_info(netdev,
+			    "WARNING: Unrecognized PHY_High (0x%llx).\n",
+			    (u64)link_info->phy_type_high);
 	}
 
 	/* Now that we've worked out everything that could be supported by the
 	 * current PHY type, get what is supported by the NVM and intersect
 	 * them to get what is truly supported
 	 */
-	memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings));
+	memset(&cap_ksettings, 0, sizeof(cap_ksettings));
 	ice_phy_type_to_ethtool(netdev, &cap_ksettings);
 	ethtool_intersect_link_masks(ks, &cap_ksettings);
 
 	switch (link_info->link_speed) {
+	case ICE_AQ_LINK_SPEED_100GB:
+		ks->base.speed = SPEED_100000;
+		break;
+	case ICE_AQ_LINK_SPEED_50GB:
+		ks->base.speed = SPEED_50000;
+		break;
 	case ICE_AQ_LINK_SPEED_40GB:
 		ks->base.speed = SPEED_40000;
 		break;
@@ -760,10 +2051,10 @@ static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
  */
 static void
 ice_get_settings_link_down(struct ethtool_link_ksettings *ks,
-			   struct net_device __always_unused *netdev)
+			   struct net_device *netdev)
 {
 	/* link is down and the driver needs to fall back on
-	 * supported phy types to figure out what info to display
+	 * supported PHY types to figure out what info to display
 	 */
 	ice_phy_type_to_ethtool(netdev, ks);
 
@@ -779,10 +2070,12 @@ ice_get_settings_link_down(struct ethtool_link_ksettings *ks,
  *
  * Reports speed/duplex settings based on media_type
  */
-static int ice_get_link_ksettings(struct net_device *netdev,
-				  struct ethtool_link_ksettings *ks)
+static int
+ice_get_link_ksettings(struct net_device *netdev,
+		       struct ethtool_link_ksettings *ks)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_aqc_get_phy_caps_data *caps;
 	struct ice_link_status *hw_link_info;
 	struct ice_vsi *vsi = np->vsi;
 
@@ -853,6 +2146,40 @@ static int ice_get_link_ksettings(struct net_device *netdev,
 		break;
 	}
 
+	caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+	if (!caps)
+		goto done;
+
+	if (ice_aq_get_phy_caps(vsi->port_info, false, ICE_AQC_REPORT_TOPO_CAP,
+				caps, NULL))
+		netdev_info(netdev, "Get phy capability failed.\n");
+
+	/* Set supported FEC modes based on PHY capability */
+	ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+
+	if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN)
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+	if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN)
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+
+	if (ice_aq_get_phy_caps(vsi->port_info, false, ICE_AQC_REPORT_SW_CFG,
+				caps, NULL))
+		netdev_info(netdev, "Get phy capability failed.\n");
+
+	/* Set advertised FEC modes based on PHY capability */
+	ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+
+	if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_REQ)
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
+	if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_528_REQ ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ)
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+
+done:
+	devm_kfree(&vsi->back->pdev->dev, caps);
 	return 0;
 }
 
@@ -911,6 +2238,23 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks)
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  40000baseKR4_Full))
 		adv_link_speed |= ICE_AQ_LINK_SPEED_40GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  50000baseCR2_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  50000baseKR2_Full))
+		adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  50000baseSR2_Full))
+		adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseCR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseSR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseLR4_ER4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseKR4_Full))
+		adv_link_speed |= ICE_AQ_LINK_SPEED_100GB;
 
 	return adv_link_speed;
 }
@@ -955,7 +2299,7 @@ ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks,
 	} else {
 		/* If autoneg is currently enabled */
 		if (p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) {
-			/* If autoneg is supported 10GBASE_T is the only phy
+			/* If autoneg is supported 10GBASE_T is the only PHY
 			 * that can disable it, so otherwise return error
 			 */
 			if (ethtool_link_ksettings_test_link_mode(ks,
@@ -981,8 +2325,9 @@ ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks,
  *
  * Set speed/duplex per media_types advertised/forced
  */
-static int ice_set_link_ksettings(struct net_device *netdev,
-				  const struct ethtool_link_ksettings *ks)
+static int
+ice_set_link_ksettings(struct net_device *netdev,
+		       const struct ethtool_link_ksettings *ks)
 {
 	u8 autoneg, timeout = TEST_SET_BITS_TIMEOUT, lport = 0;
 	struct ice_netdev_priv *np = netdev_priv(netdev);
@@ -994,6 +2339,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	struct ice_port_info *p;
 	u8 autoneg_changed = 0;
 	enum ice_status status;
+	u64 phy_type_high;
 	u64 phy_type_low;
 	int err = 0;
 	bool linkup;
@@ -1003,14 +2349,13 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	if (!p)
 		return -EOPNOTSUPP;
 
-	/* Check if this is lan vsi */
-	for (idx = 0 ; idx <  pf->num_alloc_vsi ; idx++) {
+	/* Check if this is LAN VSI */
+	ice_for_each_vsi(pf, idx)
 		if (pf->vsi[idx]->type == ICE_VSI_PF) {
 			if (np->vsi != pf->vsi[idx])
 				return -EOPNOTSUPP;
 			break;
 		}
-	}
 
 	if (p->phy.media_type != ICE_MEDIA_BASET &&
 	    p->phy.media_type != ICE_MEDIA_FIBER &&
@@ -1020,7 +2365,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 		return -EOPNOTSUPP;
 
 	/* copy the ksettings to copy_ks to avoid modifying the original */
-	memcpy(&copy_ks, ks, sizeof(struct ethtool_link_ksettings));
+	memcpy(&copy_ks, ks, sizeof(copy_ks));
 
 	/* save autoneg out of ksettings */
 	autoneg = copy_ks.base.autoneg;
@@ -1039,7 +2384,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 		return -EINVAL;
 
 	/* get our own copy of the bits to check against */
-	memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings));
+	memset(&safe_ks, 0, sizeof(safe_ks));
 	safe_ks.base.cmd = copy_ks.base.cmd;
 	safe_ks.base.link_mode_masks_nwords =
 		copy_ks.base.link_mode_masks_nwords;
@@ -1053,8 +2398,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	/* If copy_ks.base and safe_ks.base are not the same now, then they are
 	 * trying to set something that we do not support.
 	 */
-	if (memcmp(&copy_ks.base, &safe_ks.base,
-		   sizeof(struct ethtool_link_settings)))
+	if (memcmp(&copy_ks.base, &safe_ks.base, sizeof(copy_ks.base)))
 		return -EOPNOTSUPP;
 
 	while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) {
@@ -1069,7 +2413,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	if (!abilities)
 		return -ENOMEM;
 
-	/* Get the current phy config */
+	/* Get the current PHY config */
 	status = ice_aq_get_phy_caps(p, false, ICE_AQC_REPORT_SW_CFG, abilities,
 				     NULL);
 	if (status) {
@@ -1078,7 +2422,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	}
 
 	/* Copy abilities to config in case autoneg is not set below */
-	memset(&config, 0, sizeof(struct ice_aqc_set_phy_cfg_data));
+	memset(&config, 0, sizeof(config));
 	config.caps = abilities->caps & ~ICE_AQC_PHY_AN_MODE;
 	if (abilities->caps & ICE_AQC_PHY_AN_MODE)
 		config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
@@ -1109,7 +2453,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 		adv_link_speed = curr_link_speed;
 
 	/* Convert the advertise link speeds to their corresponded PHY_TYPE */
-	ice_update_phy_type(&phy_type_low, adv_link_speed);
+	ice_update_phy_type(&phy_type_low, &phy_type_high, adv_link_speed);
 
 	if (!autoneg_changed && adv_link_speed == curr_link_speed) {
 		netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");
@@ -1128,7 +2472,9 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	/* set link and auto negotiation so changes take effect */
 	config.caps |= ICE_AQ_PHY_ENA_LINK;
 
-	if (phy_type_low) {
+	if (phy_type_low || phy_type_high) {
+		config.phy_type_high = cpu_to_le64(phy_type_high) &
+			abilities->phy_type_high;
 		config.phy_type_low = cpu_to_le64(phy_type_low) &
 			abilities->phy_type_low;
 	} else {
@@ -1162,15 +2508,16 @@ done:
 }
 
 /**
- * ice_get_rxnfc - command to get RX flow classification rules
+ * ice_get_rxnfc - command to get Rx flow classification rules
  * @netdev: network interface device structure
  * @cmd: ethtool rxnfc command
  * @rule_locs: buffer to rturn Rx flow classification rules
  *
  * Returns Success if the command is supported.
  */
-static int ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
-			 u32 __always_unused *rule_locs)
+static int
+ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
+	      u32 __always_unused *rule_locs)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -1270,7 +2617,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
 		    vsi->tx_rings[0]->count, new_tx_cnt);
 
 	tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
-				sizeof(struct ice_ring), GFP_KERNEL);
+				sizeof(*tx_rings), GFP_KERNEL);
 	if (!tx_rings) {
 		err = -ENOMEM;
 		goto done;
@@ -1302,7 +2649,7 @@ process_rx:
 		    vsi->rx_rings[0]->count, new_rx_cnt);
 
 	rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
-				sizeof(struct ice_ring), GFP_KERNEL);
+				sizeof(*rx_rings), GFP_KERNEL);
 	if (!rx_rings) {
 		err = -ENOMEM;
 		goto done;
@@ -1421,21 +2768,43 @@ static void
 ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_port_info *pi;
+	struct ice_port_info *pi = np->vsi->port_info;
+	struct ice_aqc_get_phy_caps_data *pcaps;
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_dcbx_cfg *dcbx_cfg;
+	enum ice_status status;
 
-	pi = np->vsi->port_info;
-	pause->autoneg =
-		((pi->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) ?
-		 AUTONEG_ENABLE : AUTONEG_DISABLE);
+	/* Initialize pause params */
+	pause->rx_pause = 0;
+	pause->tx_pause = 0;
 
-	if (pi->fc.current_mode == ICE_FC_RX_PAUSE) {
-		pause->rx_pause = 1;
-	} else if (pi->fc.current_mode == ICE_FC_TX_PAUSE) {
+	dcbx_cfg = &pi->local_dcbx_cfg;
+
+	pcaps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*pcaps),
+			     GFP_KERNEL);
+	if (!pcaps)
+		return;
+
+	/* Get current PHY config */
+	status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+				     NULL);
+	if (status)
+		goto out;
+
+	pause->autoneg = ((pcaps->caps & ICE_AQC_PHY_AN_MODE) ?
+			AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+	if (dcbx_cfg->pfc.pfcena)
+		/* PFC enabled so report LFC as off */
+		goto out;
+
+	if (pcaps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE)
 		pause->tx_pause = 1;
-	} else if (pi->fc.current_mode == ICE_FC_FULL) {
+	if (pcaps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE)
 		pause->rx_pause = 1;
-		pause->tx_pause = 1;
-	}
+
+out:
+	devm_kfree(&vsi->back->pdev->dev, pcaps);
 }
 
 /**
@@ -1449,6 +2818,7 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_link_status *hw_link_info;
 	struct ice_pf *pf = np->vsi->back;
+	struct ice_dcbx_cfg *dcbx_cfg;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_hw *hw = &pf->hw;
 	struct ice_port_info *pi;
@@ -1459,6 +2829,7 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 
 	pi = vsi->port_info;
 	hw_link_info = &pi->phy.link_info;
+	dcbx_cfg = &pi->local_dcbx_cfg;
 	link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
 
 	/* Changing the port's flow control is not supported if this isn't the
@@ -1481,6 +2852,10 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 		netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n");
 	}
 
+	if (dcbx_cfg->pfc.pfcena) {
+		netdev_info(netdev, "Priority flow control enabled. Cannot set link flow control.\n");
+		return -EOPNOTSUPP;
+	}
 	if (pause->rx_pause && pause->tx_pause)
 		pi->fc.req_mode = ICE_FC_FULL;
 	else if (pause->rx_pause && !pause->tx_pause)
@@ -1609,11 +2984,12 @@ out:
  * @key: hash key
  * @hfunc: hash function
  *
- * Returns -EINVAL if the table specifies an invalid queue id, otherwise
+ * Returns -EINVAL if the table specifies an invalid queue ID, otherwise
  * returns 0 after programming the table.
  */
-static int ice_set_rxfh(struct net_device *netdev, const u32 *indir,
-			const u8 *key, const u8 hfunc)
+static int
+ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key,
+	     const u8 hfunc)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -1667,6 +3043,322 @@ static int ice_set_rxfh(struct net_device *netdev, const u32 *indir,
 	return 0;
 }
 
+enum ice_container_type {
+	ICE_RX_CONTAINER,
+	ICE_TX_CONTAINER,
+};
+
+/**
+ * ice_get_rc_coalesce - get ITR values for specific ring container
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @c_type: container type, Rx or Tx
+ * @rc: ring container that the ITR values will come from
+ *
+ * Query the device for ice_ring_container specific ITR values. This is
+ * done per ice_ring_container because each q_vector can have 1 or more rings
+ * and all of said ring(s) will have the same ITR values.
+ *
+ * Returns 0 on success, negative otherwise.
+ */
+static int
+ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type,
+		    struct ice_ring_container *rc)
+{
+	struct ice_pf *pf;
+
+	if (!rc->ring)
+		return -EINVAL;
+
+	pf = rc->ring->vsi->back;
+
+	switch (c_type) {
+	case ICE_RX_CONTAINER:
+		ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting);
+		ec->rx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+		ec->rx_coalesce_usecs_high = rc->ring->q_vector->intrl;
+		break;
+	case ICE_TX_CONTAINER:
+		ec->use_adaptive_tx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting);
+		ec->tx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+		break;
+	default:
+		dev_dbg(&pf->pdev->dev, "Invalid c_type %d\n", c_type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_get_q_coalesce - get a queue's ITR/INTRL (coalesce) settings
+ * @vsi: VSI associated to the queue for getting ITR/INTRL (coalesce) settings
+ * @ec: coalesce settings to program the device with
+ * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index
+ *
+ * Return 0 on success, and negative under the following conditions:
+ * 1. Getting Tx or Rx ITR/INTRL (coalesce) settings failed.
+ * 2. The q_num passed in is not a valid number/index for Tx and Rx rings.
+ */
+static int
+ice_get_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num)
+{
+	if (q_num < vsi->num_rxq && q_num < vsi->num_txq) {
+		if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER,
+					&vsi->rx_rings[q_num]->q_vector->rx))
+			return -EINVAL;
+		if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER,
+					&vsi->tx_rings[q_num]->q_vector->tx))
+			return -EINVAL;
+	} else if (q_num < vsi->num_rxq) {
+		if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER,
+					&vsi->rx_rings[q_num]->q_vector->rx))
+			return -EINVAL;
+	} else if (q_num < vsi->num_txq) {
+		if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER,
+					&vsi->tx_rings[q_num]->q_vector->tx))
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * __ice_get_coalesce - get ITR/INTRL values for the device
+ * @netdev: pointer to the netdev associated with this query
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @q_num: queue number to get the coalesce settings for
+ *
+ * If the caller passes in a negative q_num then we return coalesce settings
+ * based on queue number 0, else use the actual q_num passed in.
+ */
+static int
+__ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
+		   int q_num)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+
+	if (q_num < 0)
+		q_num = 0;
+
+	if (ice_get_q_coalesce(vsi, ec, q_num))
+		return -EINVAL;
+
+	if (q_num < vsi->num_txq)
+		ec->tx_max_coalesced_frames_irq = vsi->work_lmt;
+
+	if (q_num < vsi->num_rxq)
+		ec->rx_max_coalesced_frames_irq = vsi->work_lmt;
+
+	return 0;
+}
+
+static int
+ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	return __ice_get_coalesce(netdev, ec, -1);
+}
+
+static int
+ice_get_per_q_coalesce(struct net_device *netdev, u32 q_num,
+		       struct ethtool_coalesce *ec)
+{
+	return __ice_get_coalesce(netdev, ec, q_num);
+}
+
+/**
+ * ice_set_rc_coalesce - set ITR values for specific ring container
+ * @c_type: container type, Rx or Tx
+ * @ec: ethtool structure from user to update ITR settings
+ * @rc: ring container that the ITR values will come from
+ * @vsi: VSI associated to the ring container
+ *
+ * Set specific ITR values. This is done per ice_ring_container because each
+ * q_vector can have 1 or more rings and all of said ring(s) will have the same
+ * ITR values.
+ *
+ * Returns 0 on success, negative otherwise.
+ */
+static int
+ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec,
+		    struct ice_ring_container *rc, struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	u16 itr_setting;
+
+	if (!rc->ring)
+		return -EINVAL;
+
+	itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+
+	switch (c_type) {
+	case ICE_RX_CONTAINER:
+		if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL ||
+		    (ec->rx_coalesce_usecs_high &&
+		     ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) {
+			netdev_info(vsi->netdev,
+				    "Invalid value, rx-usecs-high valid values are 0 (disabled), %d-%d\n",
+				    pf->hw.intrl_gran, ICE_MAX_INTRL);
+			return -EINVAL;
+		}
+
+		if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) {
+			rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high;
+			wr32(&pf->hw, GLINT_RATE(rc->ring->q_vector->reg_idx),
+			     ice_intrl_usec_to_reg(ec->rx_coalesce_usecs_high,
+						   pf->hw.intrl_gran));
+		}
+
+		if (ec->rx_coalesce_usecs != itr_setting &&
+		    ec->use_adaptive_rx_coalesce) {
+			netdev_info(vsi->netdev,
+				    "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n");
+			return -EINVAL;
+		}
+
+		if (ec->rx_coalesce_usecs > ICE_ITR_MAX) {
+			netdev_info(vsi->netdev,
+				    "Invalid value, rx-usecs range is 0-%d\n",
+				   ICE_ITR_MAX);
+			return -EINVAL;
+		}
+
+		if (ec->use_adaptive_rx_coalesce) {
+			rc->itr_setting |= ICE_ITR_DYNAMIC;
+		} else {
+			rc->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs);
+			rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		}
+		break;
+	case ICE_TX_CONTAINER:
+		if (ec->tx_coalesce_usecs_high) {
+			netdev_info(vsi->netdev,
+				    "setting tx-usecs-high is not supported\n");
+			return -EINVAL;
+		}
+
+		if (ec->tx_coalesce_usecs != itr_setting &&
+		    ec->use_adaptive_tx_coalesce) {
+			netdev_info(vsi->netdev,
+				    "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n");
+			return -EINVAL;
+		}
+
+		if (ec->tx_coalesce_usecs > ICE_ITR_MAX) {
+			netdev_info(vsi->netdev,
+				    "Invalid value, tx-usecs range is 0-%d\n",
+				   ICE_ITR_MAX);
+			return -EINVAL;
+		}
+
+		if (ec->use_adaptive_tx_coalesce) {
+			rc->itr_setting |= ICE_ITR_DYNAMIC;
+		} else {
+			rc->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs);
+			rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		}
+		break;
+	default:
+		dev_dbg(&pf->pdev->dev, "Invalid container type %d\n", c_type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_set_q_coalesce - set a queue's ITR/INTRL (coalesce) settings
+ * @vsi: VSI associated to the queue that need updating
+ * @ec: coalesce settings to program the device with
+ * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index
+ *
+ * Return 0 on success, and negative under the following conditions:
+ * 1. Setting Tx or Rx ITR/INTRL (coalesce) settings failed.
+ * 2. The q_num passed in is not a valid number/index for Tx and Rx rings.
+ */
+static int
+ice_set_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num)
+{
+	if (q_num < vsi->num_rxq && q_num < vsi->num_txq) {
+		if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec,
+					&vsi->rx_rings[q_num]->q_vector->rx,
+					vsi))
+			return -EINVAL;
+
+		if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec,
+					&vsi->tx_rings[q_num]->q_vector->tx,
+					vsi))
+			return -EINVAL;
+	} else if (q_num < vsi->num_rxq) {
+		if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec,
+					&vsi->rx_rings[q_num]->q_vector->rx,
+					vsi))
+			return -EINVAL;
+	} else if (q_num < vsi->num_txq) {
+		if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec,
+					&vsi->tx_rings[q_num]->q_vector->tx,
+					vsi))
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * __ice_set_coalesce - set ITR/INTRL values for the device
+ * @netdev: pointer to the netdev associated with this query
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @q_num: queue number to get the coalesce settings for
+ *
+ * If the caller passes in a negative q_num then we set the coalesce settings
+ * for all Tx/Rx queues, else use the actual q_num passed in.
+ */
+static int
+__ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
+		   int q_num)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+
+	if (q_num < 0) {
+		int i;
+
+		ice_for_each_q_vector(vsi, i) {
+			if (ice_set_q_coalesce(vsi, ec, i))
+				return -EINVAL;
+		}
+		goto set_work_lmt;
+	}
+
+	if (ice_set_q_coalesce(vsi, ec, q_num))
+		return -EINVAL;
+
+set_work_lmt:
+
+	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
+		vsi->work_lmt = max(ec->tx_max_coalesced_frames_irq,
+				    ec->rx_max_coalesced_frames_irq);
+
+	return 0;
+}
+
+static int
+ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	return __ice_set_coalesce(netdev, ec, -1);
+}
+
+static int
+ice_set_per_q_coalesce(struct net_device *netdev, u32 q_num,
+		       struct ethtool_coalesce *ec)
+{
+	return __ice_set_coalesce(netdev, ec, q_num);
+}
+
 static const struct ethtool_ops ice_ethtool_ops = {
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
@@ -1675,9 +3367,17 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.get_regs               = ice_get_regs,
 	.get_msglevel           = ice_get_msglevel,
 	.set_msglevel           = ice_set_msglevel,
+	.self_test		= ice_self_test,
 	.get_link		= ethtool_op_get_link,
+	.get_eeprom_len		= ice_get_eeprom_len,
+	.get_eeprom		= ice_get_eeprom,
+	.get_coalesce		= ice_get_coalesce,
+	.set_coalesce		= ice_set_coalesce,
 	.get_strings		= ice_get_strings,
+	.set_phys_id		= ice_set_phys_id,
 	.get_ethtool_stats      = ice_get_ethtool_stats,
+	.get_priv_flags		= ice_get_priv_flags,
+	.set_priv_flags		= ice_set_priv_flags,
 	.get_sset_count		= ice_get_sset_count,
 	.get_rxnfc		= ice_get_rxnfc,
 	.get_ringparam		= ice_get_ringparam,
@@ -1689,6 +3389,11 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.get_rxfh_indir_size	= ice_get_rxfh_indir_size,
 	.get_rxfh		= ice_get_rxfh,
 	.set_rxfh		= ice_set_rxfh,
+	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_per_queue_coalesce = ice_get_per_q_coalesce,
+	.set_per_queue_coalesce = ice_set_per_q_coalesce,
+	.get_fecparam		= ice_get_fecparam,
+	.set_fecparam		= ice_set_fecparam,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 5507928c8fbe..6c5ce05742b1 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -6,6 +6,9 @@
 #ifndef _ICE_HW_AUTOGEN_H_
 #define _ICE_HW_AUTOGEN_H_
 
+#define PF0INT_ITR_0(_i)			(0x03000004 + ((_i) * 4096))
+#define PF0INT_ITR_1(_i)			(0x03000008 + ((_i) * 4096))
+#define PF0INT_ITR_2(_i)			(0x0300000C + ((_i) * 4096))
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD_HEAD_S			0
@@ -30,6 +33,7 @@
 #define PF_FW_ATQLEN_ATQVFE_M			BIT(28)
 #define PF_FW_ATQLEN_ATQOVFL_M			BIT(29)
 #define PF_FW_ATQLEN_ATQCRIT_M			BIT(30)
+#define VF_MBX_ARQLEN(_VF)			(0x0022BC00 + ((_VF) * 4))
 #define PF_FW_ATQLEN_ATQENABLE_M		BIT(31)
 #define PF_FW_ATQT				0x00080400
 #define PF_MBX_ARQBAH				0x0022E400
@@ -48,6 +52,9 @@
 #define PF_MBX_ATQLEN_ATQLEN_M			ICE_M(0x3FF, 0)
 #define PF_MBX_ATQLEN_ATQENABLE_M		BIT(31)
 #define PF_MBX_ATQT				0x0022E300
+#define PRTDCB_GENS				0x00083020
+#define PRTDCB_GENS_DCBX_STATUS_S		0
+#define PRTDCB_GENS_DCBX_STATUS_M		ICE_M(0x7, 0)
 #define GLFLXP_RXDID_FLAGS(_i, _j)		(0x0045D000 + ((_i) * 4 + (_j) * 256))
 #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S	0
 #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M	ICE_M(0x3F, 0)
@@ -105,11 +112,22 @@
 #define VPGEN_VFRTRIG_VFSWR_M			BIT(0)
 #define PFHMC_ERRORDATA				0x00520500
 #define PFHMC_ERRORINFO				0x00520400
+#define GLINT_CTL				0x0016CC54
+#define GLINT_CTL_DIS_AUTOMASK_M		BIT(0)
+#define GLINT_CTL_ITR_GRAN_200_S		16
+#define GLINT_CTL_ITR_GRAN_200_M		ICE_M(0xF, 16)
+#define GLINT_CTL_ITR_GRAN_100_S		20
+#define GLINT_CTL_ITR_GRAN_100_M		ICE_M(0xF, 20)
+#define GLINT_CTL_ITR_GRAN_50_S			24
+#define GLINT_CTL_ITR_GRAN_50_M			ICE_M(0xF, 24)
+#define GLINT_CTL_ITR_GRAN_25_S			28
+#define GLINT_CTL_ITR_GRAN_25_M			ICE_M(0xF, 28)
 #define GLINT_DYN_CTL(_INT)			(0x00160000 + ((_INT) * 4))
 #define GLINT_DYN_CTL_INTENA_M			BIT(0)
 #define GLINT_DYN_CTL_CLEARPBA_M		BIT(1)
 #define GLINT_DYN_CTL_SWINT_TRIG_M		BIT(2)
 #define GLINT_DYN_CTL_ITR_INDX_S		3
+#define GLINT_DYN_CTL_INTERVAL_S		5
 #define GLINT_DYN_CTL_SW_ITR_INDX_M		ICE_M(0x3, 25)
 #define GLINT_DYN_CTL_INTENA_MSK_M		BIT(31)
 #define GLINT_ITR(_i, _INT)			(0x00154000 + ((_i) * 8192 + (_INT) * 4))
@@ -140,6 +158,7 @@
 #define PFINT_OICR_HMC_ERR_M			BIT(26)
 #define PFINT_OICR_PE_CRITERR_M			BIT(28)
 #define PFINT_OICR_VFLR_M			BIT(29)
+#define PFINT_OICR_SWINT_M			BIT(31)
 #define PFINT_OICR_CTL				0x0016CA80
 #define PFINT_OICR_CTL_MSIX_INDX_M		ICE_M(0x7FF, 0)
 #define PFINT_OICR_CTL_ITR_INDX_S		11
@@ -148,11 +167,15 @@
 #define PFINT_OICR_ENA				0x0016C900
 #define QINT_RQCTL(_QRX)			(0x00150000 + ((_QRX) * 4))
 #define QINT_RQCTL_MSIX_INDX_S			0
+#define QINT_RQCTL_MSIX_INDX_M			ICE_M(0x7FF, 0)
 #define QINT_RQCTL_ITR_INDX_S			11
+#define QINT_RQCTL_ITR_INDX_M			ICE_M(0x3, 11)
 #define QINT_RQCTL_CAUSE_ENA_M			BIT(30)
 #define QINT_TQCTL(_DBQM)			(0x00140000 + ((_DBQM) * 4))
 #define QINT_TQCTL_MSIX_INDX_S			0
+#define QINT_TQCTL_MSIX_INDX_M			ICE_M(0x7FF, 0)
 #define QINT_TQCTL_ITR_INDX_S			11
+#define QINT_TQCTL_ITR_INDX_M			ICE_M(0x3, 11)
 #define QINT_TQCTL_CAUSE_ENA_M			BIT(30)
 #define VPINT_ALLOC(_VF)			(0x001D1000 + ((_VF) * 4))
 #define VPINT_ALLOC_FIRST_S			0
@@ -166,6 +189,8 @@
 #define VPINT_ALLOC_PCI_LAST_S			12
 #define VPINT_ALLOC_PCI_LAST_M			ICE_M(0x7FF, 12)
 #define VPINT_ALLOC_PCI_VALID_M			BIT(31)
+#define VPINT_MBX_CTL(_VSI)			(0x0016A000 + ((_VSI) * 4))
+#define VPINT_MBX_CTL_CAUSE_ENA_M		BIT(30)
 #define GLLAN_RCTL_0				0x002941F8
 #define QRX_CONTEXT(_i, _QRX)			(0x00280000 + ((_i) * 8192 + (_QRX) * 4))
 #define QRX_CTRL(_QRX)				(0x00120000 + ((_QRX) * 4))
@@ -304,11 +329,16 @@
 #define GLPRT_PTC64L(_i)			(0x00380B80 + ((_i) * 8))
 #define GLPRT_PTC9522H(_i)			(0x00380D04 + ((_i) * 8))
 #define GLPRT_PTC9522L(_i)			(0x00380D00 + ((_i) * 8))
+#define GLPRT_PXOFFRXC(_i, _j)			(0x00380500 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_PXOFFTXC(_i, _j)			(0x00380F40 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_PXONRXC(_i, _j)			(0x00380300 + ((_i) * 8 + (_j) * 64))
+#define GLPRT_PXONTXC(_i, _j)			(0x00380D40 + ((_i) * 8 + (_j) * 64))
 #define GLPRT_RFC(_i)				(0x00380AC0 + ((_i) * 8))
 #define GLPRT_RJC(_i)				(0x00380B00 + ((_i) * 8))
 #define GLPRT_RLEC(_i)				(0x00380140 + ((_i) * 8))
 #define GLPRT_ROC(_i)				(0x00380240 + ((_i) * 8))
 #define GLPRT_RUC(_i)				(0x00380200 + ((_i) * 8))
+#define GLPRT_RXON2OFFCNT(_i, _j)		(0x00380700 + ((_i) * 8 + (_j) * 64))
 #define GLPRT_TDOLD(_i)				(0x00381280 + ((_i) * 8))
 #define GLPRT_UPRCH(_i)				(0x00381304 + ((_i) * 8))
 #define GLPRT_UPRCL(_i)				(0x00381300 + ((_i) * 8))
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index bb51dd7defb5..510a8c900e61 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -20,7 +20,7 @@ union ice_32byte_rx_desc {
 			} lo_dword;
 			union {
 				__le32 rss; /* RSS Hash */
-				__le32 fd_id; /* Flow Director filter id */
+				__le32 fd_id; /* Flow Director filter ID */
 			} hi_dword;
 		} qword0;
 		struct {
@@ -99,7 +99,7 @@ enum ice_rx_ptype_payload_layer {
 	ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4	= 3,
 };
 
-/* RX Flex Descriptor
+/* Rx Flex Descriptor
  * This descriptor is used instead of the legacy version descriptor when
  * ice_rlan_ctx.adv_desc is set
  */
@@ -113,7 +113,7 @@ union ice_32b_rx_flex_desc {
 	} read;
 	struct {
 		/* Qword 0 */
-		u8 rxdid; /* descriptor builder profile id */
+		u8 rxdid; /* descriptor builder profile ID */
 		u8 mir_id_umb_cast; /* mirror=[5:0], umb=[7:6] */
 		__le16 ptype_flex_flags0; /* ptype=[9:0], ff0=[15:10] */
 		__le16 pkt_len; /* [15:14] are reserved */
@@ -149,7 +149,7 @@ union ice_32b_rx_flex_desc {
 
 /* Rx Flex Descriptor NIC Profile
  * This descriptor corresponds to RxDID 2 which contains
- * metadata fields for RSS, flow id and timestamp info
+ * metadata fields for RSS, flow ID and timestamp info
  */
 struct ice_32b_rx_flex_desc_nic {
 	/* Qword 0 */
@@ -208,23 +208,23 @@ enum ice_flex_rx_mdid {
 	ICE_RX_MDID_HASH_HIGH,
 };
 
-/* Rx Flag64 packet flag bits */
-enum ice_rx_flg64_bits {
-	ICE_RXFLG_PKT_DSI	= 0,
-	ICE_RXFLG_EVLAN_x8100	= 15,
-	ICE_RXFLG_EVLAN_x9100,
-	ICE_RXFLG_VLAN_x8100,
-	ICE_RXFLG_TNL_MAC	= 22,
-	ICE_RXFLG_TNL_VLAN,
-	ICE_RXFLG_PKT_FRG,
-	ICE_RXFLG_FIN		= 32,
-	ICE_RXFLG_SYN,
-	ICE_RXFLG_RST,
-	ICE_RXFLG_TNL0		= 38,
-	ICE_RXFLG_TNL1,
-	ICE_RXFLG_TNL2,
-	ICE_RXFLG_UDP_GRE,
-	ICE_RXFLG_RSVD		= 63
+/* Rx/Tx Flag64 packet flag bits */
+enum ice_flg64_bits {
+	ICE_FLG_PKT_DSI		= 0,
+	ICE_FLG_EVLAN_x8100	= 15,
+	ICE_FLG_EVLAN_x9100,
+	ICE_FLG_VLAN_x8100,
+	ICE_FLG_TNL_MAC		= 22,
+	ICE_FLG_TNL_VLAN,
+	ICE_FLG_PKT_FRG,
+	ICE_FLG_FIN		= 32,
+	ICE_FLG_SYN,
+	ICE_FLG_RST,
+	ICE_FLG_TNL0		= 38,
+	ICE_FLG_TNL1,
+	ICE_FLG_TNL2,
+	ICE_FLG_UDP_GRE,
+	ICE_FLG_RSVD		= 63
 };
 
 /* for ice_32byte_rx_flex_desc.ptype_flexi_flags0 member */
@@ -322,7 +322,7 @@ enum ice_rlan_ctx_rx_hsplit_1 {
 	ICE_RLAN_RX_HSPLIT_1_SPLIT_ALWAYS	= 2,
 };
 
-/* TX Descriptor */
+/* Tx Descriptor */
 struct ice_tx_desc {
 	__le64 buf_addr; /* Address of descriptor's data buf */
 	__le64 cmd_type_offset_bsz;
@@ -342,11 +342,12 @@ enum ice_tx_desc_cmd_bits {
 	ICE_TX_DESC_CMD_EOP			= 0x0001,
 	ICE_TX_DESC_CMD_RS			= 0x0002,
 	ICE_TX_DESC_CMD_IL2TAG1			= 0x0008,
-	ICE_TX_DESC_CMD_IIPT_IPV6		= 0x0020, /* 2 BITS */
-	ICE_TX_DESC_CMD_IIPT_IPV4		= 0x0040, /* 2 BITS */
-	ICE_TX_DESC_CMD_IIPT_IPV4_CSUM		= 0x0060, /* 2 BITS */
-	ICE_TX_DESC_CMD_L4T_EOFT_TCP		= 0x0100, /* 2 BITS */
-	ICE_TX_DESC_CMD_L4T_EOFT_UDP		= 0x0300, /* 2 BITS */
+	ICE_TX_DESC_CMD_IIPT_IPV6		= 0x0020,
+	ICE_TX_DESC_CMD_IIPT_IPV4		= 0x0040,
+	ICE_TX_DESC_CMD_IIPT_IPV4_CSUM		= 0x0060,
+	ICE_TX_DESC_CMD_L4T_EOFT_TCP		= 0x0100,
+	ICE_TX_DESC_CMD_L4T_EOFT_SCTP		= 0x0200,
+	ICE_TX_DESC_CMD_L4T_EOFT_UDP		= 0x0300,
 };
 
 #define ICE_TXD_QW1_OFFSET_S	16
@@ -488,5 +489,7 @@ static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
 #define ICE_LINK_SPEED_20000MBPS	20000
 #define ICE_LINK_SPEED_25000MBPS	25000
 #define ICE_LINK_SPEED_40000MBPS	40000
+#define ICE_LINK_SPEED_50000MBPS	50000
+#define ICE_LINK_SPEED_100000MBPS	100000
 
 #endif /* _ICE_LAN_TX_RX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 29b1dcfd4331..a19f5920733b 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3,6 +3,7 @@
 
 #include "ice.h"
 #include "ice_lib.h"
+#include "ice_dcb_lib.h"
 
 /**
  * ice_setup_rx_ctx - Configure a receive ring context
@@ -73,7 +74,7 @@ static int ice_setup_rx_ctx(struct ice_ring *ring)
 		regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) &
 			QRXFLXP_CNTXT_RXDID_IDX_M;
 
-		/* increasing context priority to pick up profile id;
+		/* increasing context priority to pick up profile ID;
 		 * default is 0x01; setting to 0x03 to ensure profile
 		 * is programming if prev context is of same priority
 		 */
@@ -124,6 +125,8 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
 	/* Transmit Queue Length */
 	tlan_ctx->qlen = ring->count;
 
+	ice_set_cgd_num(tlan_ctx, ring);
+
 	/* PF number */
 	tlan_ctx->pf_num = hw->pf_id;
 
@@ -134,11 +137,13 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
 	 * for PF or EMP this field should be set to zero
 	 */
 	switch (vsi->type) {
+	case ICE_VSI_LB:
+		/* fall through */
 	case ICE_VSI_PF:
 		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF;
 		break;
 	case ICE_VSI_VF:
-		/* Firmware expects vmvf_num to be absolute VF id */
+		/* Firmware expects vmvf_num to be absolute VF ID */
 		tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf_id;
 		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF;
 		break;
@@ -175,17 +180,14 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
 	int i;
 
 	for (i = 0; i < ICE_Q_WAIT_MAX_RETRY; i++) {
-		u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q));
-
-		if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
-			break;
+		if (ena == !!(rd32(&pf->hw, QRX_CTRL(pf_q)) &
+			      QRX_CTRL_QENA_STAT_M))
+			return 0;
 
 		usleep_range(20, 40);
 	}
-	if (i >= ICE_Q_WAIT_MAX_RETRY)
-		return -ETIMEDOUT;
 
-	return 0;
+	return -ETIMEDOUT;
 }
 
 /**
@@ -197,19 +199,13 @@ static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
-	int i, j, ret = 0;
+	int i, ret = 0;
 
 	for (i = 0; i < vsi->num_rxq; i++) {
 		int pf_q = vsi->rxq_map[i];
 		u32 rx_reg;
 
-		for (j = 0; j < ICE_Q_WAIT_MAX_RETRY; j++) {
-			rx_reg = rd32(hw, QRX_CTRL(pf_q));
-			if (((rx_reg >> QRX_CTRL_QENA_REQ_S) & 1) ==
-			    ((rx_reg >> QRX_CTRL_QENA_STAT_S) & 1))
-				break;
-			usleep_range(1000, 2000);
-		}
+		rx_reg = rd32(hw, QRX_CTRL(pf_q));
 
 		/* Skip if the queue is already in the requested state */
 		if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
@@ -238,35 +234,34 @@ static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena)
 /**
  * ice_vsi_alloc_arrays - Allocate queue and vector pointer arrays for the VSI
  * @vsi: VSI pointer
- * @alloc_qvectors: a bool to specify if q_vectors need to be allocated.
  *
  * On error: returns error code (negative)
  * On success: returns 0
  */
-static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors)
+static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 
 	/* allocate memory for both Tx and Rx ring pointers */
 	vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
-				     sizeof(struct ice_ring *), GFP_KERNEL);
+				     sizeof(*vsi->tx_rings), GFP_KERNEL);
 	if (!vsi->tx_rings)
 		goto err_txrings;
 
 	vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
-				     sizeof(struct ice_ring *), GFP_KERNEL);
+				     sizeof(*vsi->rx_rings), GFP_KERNEL);
 	if (!vsi->rx_rings)
 		goto err_rxrings;
 
-	if (alloc_qvectors) {
-		/* allocate memory for q_vector pointers */
-		vsi->q_vectors = devm_kcalloc(&pf->pdev->dev,
-					      vsi->num_q_vectors,
-					      sizeof(struct ice_q_vector *),
-					      GFP_KERNEL);
-		if (!vsi->q_vectors)
-			goto err_vectors;
-	}
+	/* There is no need to allocate q_vectors for a loopback VSI. */
+	if (vsi->type == ICE_VSI_LB)
+		return 0;
+
+	/* allocate memory for q_vector pointers */
+	vsi->q_vectors = devm_kcalloc(&pf->pdev->dev, vsi->num_q_vectors,
+				      sizeof(*vsi->q_vectors), GFP_KERNEL);
+	if (!vsi->q_vectors)
+		goto err_vectors;
 
 	return 0;
 
@@ -279,37 +274,68 @@ err_txrings:
 }
 
 /**
- * ice_vsi_set_num_qs - Set num queues, descriptors and vectors for a VSI
+ * ice_vsi_set_num_desc - Set number of descriptors for queues on this VSI
+ * @vsi: the VSI being configured
+ */
+static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
+{
+	switch (vsi->type) {
+	case ICE_VSI_PF:
+		/* fall through */
+	case ICE_VSI_LB:
+		vsi->num_rx_desc = ICE_DFLT_NUM_RX_DESC;
+		vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC;
+		break;
+	default:
+		dev_dbg(&vsi->back->pdev->dev,
+			"Not setting number of Tx/Rx descriptors for VSI type %d\n",
+			vsi->type);
+		break;
+	}
+}
+
+/**
+ * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI
  * @vsi: the VSI being configured
+ * @vf_id: ID of the VF being configured
  *
  * Return 0 on success and a negative value on error
  */
-static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
+static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 {
 	struct ice_pf *pf = vsi->back;
+	struct ice_vf *vf = NULL;
+
+	if (vsi->type == ICE_VSI_VF)
+		vsi->vf_id = vf_id;
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
 		vsi->alloc_txq = pf->num_lan_tx;
 		vsi->alloc_rxq = pf->num_lan_rx;
-		vsi->num_desc = ALIGN(ICE_DFLT_NUM_DESC, ICE_REQ_DESC_MULTIPLE);
 		vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx);
 		break;
 	case ICE_VSI_VF:
-		vsi->alloc_txq = pf->num_vf_qps;
-		vsi->alloc_rxq = pf->num_vf_qps;
+		vf = &pf->vf[vsi->vf_id];
+		vsi->alloc_txq = vf->num_vf_qs;
+		vsi->alloc_rxq = vf->num_vf_qs;
 		/* pf->num_vf_msix includes (VF miscellaneous vector +
 		 * data queue interrupts). Since vsi->num_q_vectors is number
-		 * of queues vectors, subtract 1 from the original vector
-		 * count
+		 * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the
+		 * original vector count
 		 */
-		vsi->num_q_vectors = pf->num_vf_msix - 1;
+		vsi->num_q_vectors = pf->num_vf_msix - ICE_NONQ_VECS_VF;
+		break;
+	case ICE_VSI_LB:
+		vsi->alloc_txq = 1;
+		vsi->alloc_rxq = 1;
 		break;
 	default:
-		dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n",
-			 vsi->type);
+		dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
 		break;
 	}
+
+	ice_vsi_set_num_desc(vsi);
 }
 
 /**
@@ -348,32 +374,37 @@ static int ice_get_free_slot(void *array, int size, int curr)
 void ice_vsi_delete(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
-	struct ice_vsi_ctx ctxt;
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
 
+	ctxt = devm_kzalloc(&pf->pdev->dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return;
+
 	if (vsi->type == ICE_VSI_VF)
-		ctxt.vf_num = vsi->vf_id;
-	ctxt.vsi_num = vsi->vsi_num;
+		ctxt->vf_num = vsi->vf_id;
+	ctxt->vsi_num = vsi->vsi_num;
 
-	memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props));
+	memcpy(&ctxt->info, &vsi->info, sizeof(ctxt->info));
 
-	status = ice_free_vsi(&pf->hw, vsi->idx, &ctxt, false, NULL);
+	status = ice_free_vsi(&pf->hw, vsi->idx, ctxt, false, NULL);
 	if (status)
 		dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n",
 			vsi->vsi_num);
+
+	devm_kfree(&pf->pdev->dev, ctxt);
 }
 
 /**
- * ice_vsi_free_arrays - clean up VSI resources
+ * ice_vsi_free_arrays - De-allocate queue and vector pointer arrays for the VSI
  * @vsi: pointer to VSI being cleared
- * @free_qvectors: bool to specify if q_vectors should be deallocated
  */
-static void ice_vsi_free_arrays(struct ice_vsi *vsi, bool free_qvectors)
+static void ice_vsi_free_arrays(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
 
 	/* free the ring and vector containers */
-	if (free_qvectors && vsi->q_vectors) {
+	if (vsi->q_vectors) {
 		devm_kfree(&pf->pdev->dev, vsi->q_vectors);
 		vsi->q_vectors = NULL;
 	}
@@ -421,7 +452,7 @@ int ice_vsi_clear(struct ice_vsi *vsi)
 	if (vsi->idx < pf->next_vsi)
 		pf->next_vsi = vsi->idx;
 
-	ice_vsi_free_arrays(vsi, true);
+	ice_vsi_free_arrays(vsi);
 	mutex_unlock(&pf->sw_mutex);
 	devm_kfree(&pf->pdev->dev, vsi);
 
@@ -449,10 +480,12 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
  * ice_vsi_alloc - Allocates the next available struct VSI in the PF
  * @pf: board private structure
  * @type: type of VSI
+ * @vf_id: ID of the VF being configured
  *
  * returns a pointer to a VSI on success, NULL on failure.
  */
-static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type)
+static struct ice_vsi *
+ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type, u16 vf_id)
 {
 	struct ice_vsi *vsi = NULL;
 
@@ -478,18 +511,25 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type)
 	vsi->idx = pf->next_vsi;
 	vsi->work_lmt = ICE_DFLT_IRQ_WORK;
 
-	ice_vsi_set_num_qs(vsi);
+	if (type == ICE_VSI_VF)
+		ice_vsi_set_num_qs(vsi, vf_id);
+	else
+		ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID);
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-		if (ice_vsi_alloc_arrays(vsi, true))
+		if (ice_vsi_alloc_arrays(vsi))
 			goto err_rings;
 
 		/* Setup default MSIX irq handler for VSI */
 		vsi->irq_handler = ice_msix_clean_rings;
 		break;
 	case ICE_VSI_VF:
-		if (ice_vsi_alloc_arrays(vsi, true))
+		if (ice_vsi_alloc_arrays(vsi))
+			goto err_rings;
+		break;
+	case ICE_VSI_LB:
+		if (ice_vsi_alloc_arrays(vsi))
 			goto err_rings;
 		break;
 	default:
@@ -514,110 +554,88 @@ unlock_pf:
 }
 
 /**
- * ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
- * @vsi: the VSI getting queues
+ * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
+ * @qs_cfg: gathered variables needed for PF->VSI queues assignment
  *
- * Return 0 on success and a negative value on error
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
  */
-static int ice_vsi_get_qs_contig(struct ice_vsi *vsi)
+static int __ice_vsi_get_qs_contig(struct ice_qs_cfg *qs_cfg)
 {
-	struct ice_pf *pf = vsi->back;
-	int offset, ret = 0;
-
-	mutex_lock(&pf->avail_q_mutex);
-	/* look for contiguous block of queues for Tx */
-	offset = bitmap_find_next_zero_area(pf->avail_txqs, ICE_MAX_TXQS,
-					    0, vsi->alloc_txq, 0);
-	if (offset < ICE_MAX_TXQS) {
-		int i;
+	int offset, i;
 
-		bitmap_set(pf->avail_txqs, offset, vsi->alloc_txq);
-		for (i = 0; i < vsi->alloc_txq; i++)
-			vsi->txq_map[i] = i + offset;
-	} else {
-		ret = -ENOMEM;
-		vsi->tx_mapping_mode = ICE_VSI_MAP_SCATTER;
+	mutex_lock(qs_cfg->qs_mutex);
+	offset = bitmap_find_next_zero_area(qs_cfg->pf_map, qs_cfg->pf_map_size,
+					    0, qs_cfg->q_count, 0);
+	if (offset >= qs_cfg->pf_map_size) {
+		mutex_unlock(qs_cfg->qs_mutex);
+		return -ENOMEM;
 	}
 
-	/* look for contiguous block of queues for Rx */
-	offset = bitmap_find_next_zero_area(pf->avail_rxqs, ICE_MAX_RXQS,
-					    0, vsi->alloc_rxq, 0);
-	if (offset < ICE_MAX_RXQS) {
-		int i;
+	bitmap_set(qs_cfg->pf_map, offset, qs_cfg->q_count);
+	for (i = 0; i < qs_cfg->q_count; i++)
+		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = i + offset;
+	mutex_unlock(qs_cfg->qs_mutex);
 
-		bitmap_set(pf->avail_rxqs, offset, vsi->alloc_rxq);
-		for (i = 0; i < vsi->alloc_rxq; i++)
-			vsi->rxq_map[i] = i + offset;
-	} else {
-		ret = -ENOMEM;
-		vsi->rx_mapping_mode = ICE_VSI_MAP_SCATTER;
-	}
-	mutex_unlock(&pf->avail_q_mutex);
-
-	return ret;
+	return 0;
 }
 
 /**
- * ice_vsi_get_qs_scatter - Assign a scattered queues to VSI
- * @vsi: the VSI getting queues
+ * __ice_vsi_get_qs_sc - Assign a scattered queues from PF to VSI
+ * @qs_cfg: gathered variables needed for pf->vsi queues assignment
  *
- * Return 0 on success and a negative value on error
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
  */
-static int ice_vsi_get_qs_scatter(struct ice_vsi *vsi)
+static int __ice_vsi_get_qs_sc(struct ice_qs_cfg *qs_cfg)
 {
-	struct ice_pf *pf = vsi->back;
 	int i, index = 0;
 
-	mutex_lock(&pf->avail_q_mutex);
-
-	if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) {
-		for (i = 0; i < vsi->alloc_txq; i++) {
-			index = find_next_zero_bit(pf->avail_txqs,
-						   ICE_MAX_TXQS, index);
-			if (index < ICE_MAX_TXQS) {
-				set_bit(index, pf->avail_txqs);
-				vsi->txq_map[i] = index;
-			} else {
-				goto err_scatter_tx;
-			}
-		}
+	mutex_lock(qs_cfg->qs_mutex);
+	for (i = 0; i < qs_cfg->q_count; i++) {
+		index = find_next_zero_bit(qs_cfg->pf_map,
+					   qs_cfg->pf_map_size, index);
+		if (index >= qs_cfg->pf_map_size)
+			goto err_scatter;
+		set_bit(index, qs_cfg->pf_map);
+		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = index;
 	}
+	mutex_unlock(qs_cfg->qs_mutex);
 
-	if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) {
-		for (i = 0; i < vsi->alloc_rxq; i++) {
-			index = find_next_zero_bit(pf->avail_rxqs,
-						   ICE_MAX_RXQS, index);
-			if (index < ICE_MAX_RXQS) {
-				set_bit(index, pf->avail_rxqs);
-				vsi->rxq_map[i] = index;
-			} else {
-				goto err_scatter_rx;
-			}
-		}
-	}
-
-	mutex_unlock(&pf->avail_q_mutex);
 	return 0;
-
-err_scatter_rx:
-	/* unflag any queues we have grabbed (i is failed position) */
+err_scatter:
 	for (index = 0; index < i; index++) {
-		clear_bit(vsi->rxq_map[index], pf->avail_rxqs);
-		vsi->rxq_map[index] = 0;
-	}
-	i = vsi->alloc_txq;
-err_scatter_tx:
-	/* i is either position of failed attempt or vsi->alloc_txq */
-	for (index = 0; index < i; index++) {
-		clear_bit(vsi->txq_map[index], pf->avail_txqs);
-		vsi->txq_map[index] = 0;
+		clear_bit(qs_cfg->vsi_map[index], qs_cfg->pf_map);
+		qs_cfg->vsi_map[index + qs_cfg->vsi_map_offset] = 0;
 	}
+	mutex_unlock(qs_cfg->qs_mutex);
 
-	mutex_unlock(&pf->avail_q_mutex);
 	return -ENOMEM;
 }
 
 /**
+ * __ice_vsi_get_qs - helper function for assigning queues from PF to VSI
+ * @qs_cfg: gathered variables needed for pf->vsi queues assignment
+ *
+ * This function first tries to find contiguous space. If it is not successful,
+ * it tries with the scatter approach.
+ *
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
+ */
+static int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg)
+{
+	int ret = 0;
+
+	ret = __ice_vsi_get_qs_contig(qs_cfg);
+	if (ret) {
+		/* contig failed, so try with scatter approach */
+		qs_cfg->mapping_mode = ICE_VSI_MAP_SCATTER;
+		qs_cfg->q_count = min_t(u16, qs_cfg->q_count,
+					qs_cfg->scatter_count);
+		ret = __ice_vsi_get_qs_sc(qs_cfg);
+	}
+	return ret;
+}
+
+/**
  * ice_vsi_get_qs - Assign queues from PF to VSI
  * @vsi: the VSI to assign queues to
  *
@@ -625,25 +643,35 @@ err_scatter_tx:
  */
 static int ice_vsi_get_qs(struct ice_vsi *vsi)
 {
+	struct ice_pf *pf = vsi->back;
+	struct ice_qs_cfg tx_qs_cfg = {
+		.qs_mutex = &pf->avail_q_mutex,
+		.pf_map = pf->avail_txqs,
+		.pf_map_size = ICE_MAX_TXQS,
+		.q_count = vsi->alloc_txq,
+		.scatter_count = ICE_MAX_SCATTER_TXQS,
+		.vsi_map = vsi->txq_map,
+		.vsi_map_offset = 0,
+		.mapping_mode = vsi->tx_mapping_mode
+	};
+	struct ice_qs_cfg rx_qs_cfg = {
+		.qs_mutex = &pf->avail_q_mutex,
+		.pf_map = pf->avail_rxqs,
+		.pf_map_size = ICE_MAX_RXQS,
+		.q_count = vsi->alloc_rxq,
+		.scatter_count = ICE_MAX_SCATTER_RXQS,
+		.vsi_map = vsi->rxq_map,
+		.vsi_map_offset = 0,
+		.mapping_mode = vsi->rx_mapping_mode
+	};
 	int ret = 0;
 
 	vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG;
 	vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG;
 
-	/* NOTE: ice_vsi_get_qs_contig() will set the Rx/Tx mapping
-	 * modes individually to scatter if assigning contiguous queues
-	 * to Rx or Tx fails
-	 */
-	ret = ice_vsi_get_qs_contig(vsi);
-	if (ret < 0) {
-		if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER)
-			vsi->alloc_txq = max_t(u16, vsi->alloc_txq,
-					       ICE_MAX_SCATTER_TXQS);
-		if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER)
-			vsi->alloc_rxq = max_t(u16, vsi->alloc_rxq,
-					       ICE_MAX_SCATTER_RXQS);
-		ret = ice_vsi_get_qs_scatter(vsi);
-	}
+	ret = __ice_vsi_get_qs(&tx_qs_cfg);
+	if (!ret)
+		ret = __ice_vsi_get_qs(&rx_qs_cfg);
 
 	return ret;
 }
@@ -720,6 +748,8 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
 				      BIT(cap->rss_table_entry_width));
 		vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI;
 		break;
+	case ICE_VSI_LB:
+		break;
 	default:
 		dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n",
 			 vsi->type);
@@ -832,7 +862,7 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	/* find the (rounded up) power-of-2 of qcount */
 	pow = order_base_2(qcount_rx);
 
-	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+	ice_for_each_traffic_class(i) {
 		if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
 			/* TC is not enabled */
 			vsi->tc_cfg.tc_info[i].qoffset = 0;
@@ -857,7 +887,18 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 		tx_count += tx_numq_tc;
 		ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
 	}
-	vsi->num_rxq = offset;
+
+	/* if offset is non-zero, means it is calculated correctly based on
+	 * enabled TCs for a given VSI otherwise qcount_rx will always
+	 * be correct and non-zero because it is based off - VSI's
+	 * allocated Rx queues which is at least 1 (hence qcount_tx will be
+	 * at least 1)
+	 */
+	if (offset)
+		vsi->num_rxq = offset;
+	else
+		vsi->num_rxq = qcount_rx;
+
 	vsi->num_txq = tx_count;
 
 	if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
@@ -886,6 +927,9 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 {
 	u8 lut_type, hash_type;
+	struct ice_pf *pf;
+
+	pf = vsi->back;
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
@@ -898,9 +942,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI;
 		hash_type = ICE_AQ_VSI_Q_OPT_RSS_TPLZ;
 		break;
+	case ICE_VSI_LB:
+		dev_dbg(&pf->pdev->dev, "Unsupported VSI type %d\n", vsi->type);
+		return;
 	default:
-		dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n",
-			 vsi->type);
+		dev_warn(&pf->pdev->dev, "Unknown VSI type %d\n", vsi->type);
 		return;
 	}
 
@@ -919,37 +965,52 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
  */
 static int ice_vsi_init(struct ice_vsi *vsi)
 {
-	struct ice_vsi_ctx ctxt = { 0 };
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
+	struct ice_vsi_ctx *ctxt;
 	int ret = 0;
 
+	ctxt = devm_kzalloc(&pf->pdev->dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
+
+	ctxt->info = vsi->info;
 	switch (vsi->type) {
+	case ICE_VSI_LB:
+		/* fall through */
 	case ICE_VSI_PF:
-		ctxt.flags = ICE_AQ_VSI_TYPE_PF;
+		ctxt->flags = ICE_AQ_VSI_TYPE_PF;
 		break;
 	case ICE_VSI_VF:
-		ctxt.flags = ICE_AQ_VSI_TYPE_VF;
+		ctxt->flags = ICE_AQ_VSI_TYPE_VF;
 		/* VF number here is the absolute VF number (0-255) */
-		ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id;
+		ctxt->vf_num = vsi->vf_id + hw->func_caps.vf_base_id;
 		break;
 	default:
 		return -ENODEV;
 	}
 
-	ice_set_dflt_vsi_ctx(&ctxt);
+	ice_set_dflt_vsi_ctx(ctxt);
 	/* if the switch is in VEB mode, allow VSI loopback */
 	if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB)
-		ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+		ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
 
 	/* Set LUT type and HASH type if RSS is enabled */
 	if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
-		ice_set_rss_vsi_ctx(&ctxt, vsi);
+		ice_set_rss_vsi_ctx(ctxt, vsi);
+
+	ctxt->info.sw_id = vsi->port_info->sw_id;
+	ice_vsi_setup_q_map(vsi, ctxt);
 
-	ctxt.info.sw_id = vsi->port_info->sw_id;
-	ice_vsi_setup_q_map(vsi, &ctxt);
+	/* Enable MAC Antispoof with new VSI being initialized or updated */
+	if (vsi->type == ICE_VSI_VF && pf->vf[vsi->vf_id].spoofchk) {
+		ctxt->info.valid_sections |=
+			cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+		ctxt->info.sec_flags |=
+			ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
+	}
 
-	ret = ice_add_vsi(hw, vsi->idx, &ctxt, NULL);
+	ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL);
 	if (ret) {
 		dev_err(&pf->pdev->dev,
 			"Add VSI failed, err %d\n", ret);
@@ -957,11 +1018,12 @@ static int ice_vsi_init(struct ice_vsi *vsi)
 	}
 
 	/* keep context for update VSI operations */
-	vsi->info = ctxt.info;
+	vsi->info = ctxt->info;
 
 	/* record VSI number returned */
-	vsi->vsi_num = ctxt.vsi_num;
+	vsi->vsi_num = ctxt->vsi_num;
 
+	devm_kfree(&pf->pdev->dev, ctxt);
 	return ret;
 }
 
@@ -973,10 +1035,11 @@ static int ice_vsi_init(struct ice_vsi *vsi)
 static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
 {
 	struct ice_q_vector *q_vector;
+	struct ice_pf *pf = vsi->back;
 	struct ice_ring *ring;
 
 	if (!vsi->q_vectors[v_idx]) {
-		dev_dbg(&vsi->back->pdev->dev, "Queue vector at index %d not found\n",
+		dev_dbg(&pf->pdev->dev, "Queue vector at index %d not found\n",
 			v_idx);
 		return;
 	}
@@ -991,7 +1054,7 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
 	if (vsi->netdev)
 		netif_napi_del(&q_vector->napi);
 
-	devm_kfree(&vsi->back->pdev->dev, q_vector);
+	devm_kfree(&pf->pdev->dev, q_vector);
 	vsi->q_vectors[v_idx] = NULL;
 }
 
@@ -1003,7 +1066,7 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
 {
 	int v_idx;
 
-	for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++)
+	ice_for_each_q_vector(vsi, v_idx)
 		ice_free_q_vector(vsi, v_idx);
 }
 
@@ -1105,62 +1168,32 @@ err_out:
 static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
-	int num_q_vectors = 0;
+	u16 num_q_vectors;
+
+	/* SRIOV doesn't grab irq_tracker entries for each VSI */
+	if (vsi->type == ICE_VSI_VF)
+		return 0;
 
-	if (vsi->sw_base_vector || vsi->hw_base_vector) {
-		dev_dbg(&pf->pdev->dev, "VSI %d has non-zero HW base vector %d or SW base vector %d\n",
-			vsi->vsi_num, vsi->hw_base_vector, vsi->sw_base_vector);
+	if (vsi->base_vector) {
+		dev_dbg(&pf->pdev->dev, "VSI %d has non-zero base vector %d\n",
+			vsi->vsi_num, vsi->base_vector);
 		return -EEXIST;
 	}
 
 	if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 		return -ENOENT;
 
-	switch (vsi->type) {
-	case ICE_VSI_PF:
-		num_q_vectors = vsi->num_q_vectors;
-		/* reserve slots from OS requested IRQs */
-		vsi->sw_base_vector = ice_get_res(pf, pf->sw_irq_tracker,
-						  num_q_vectors, vsi->idx);
-		if (vsi->sw_base_vector < 0) {
-			dev_err(&pf->pdev->dev,
-				"Failed to get tracking for %d SW vectors for VSI %d, err=%d\n",
-				num_q_vectors, vsi->vsi_num,
-				vsi->sw_base_vector);
-			return -ENOENT;
-		}
-		pf->num_avail_sw_msix -= num_q_vectors;
-
-		/* reserve slots from HW interrupts */
-		vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker,
-						  num_q_vectors, vsi->idx);
-		break;
-	case ICE_VSI_VF:
-		/* take VF misc vector and data vectors into account */
-		num_q_vectors = pf->num_vf_msix;
-		/* For VF VSI, reserve slots only from HW interrupts */
-		vsi->hw_base_vector = ice_get_res(pf, pf->hw_irq_tracker,
-						  num_q_vectors, vsi->idx);
-		break;
-	default:
-		dev_warn(&vsi->back->pdev->dev, "Unknown VSI type %d\n",
-			 vsi->type);
-		break;
-	}
-
-	if (vsi->hw_base_vector < 0) {
+	num_q_vectors = vsi->num_q_vectors;
+	/* reserve slots from OS requested IRQs */
+	vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors,
+				       vsi->idx);
+	if (vsi->base_vector < 0) {
 		dev_err(&pf->pdev->dev,
-			"Failed to get tracking for %d HW vectors for VSI %d, err=%d\n",
-			num_q_vectors, vsi->vsi_num, vsi->hw_base_vector);
-		if (vsi->type != ICE_VSI_VF) {
-			ice_free_res(vsi->back->sw_irq_tracker,
-				     vsi->sw_base_vector, vsi->idx);
-			pf->num_avail_sw_msix += num_q_vectors;
-		}
+			"Failed to get tracking for %d vectors for VSI %d, err=%d\n",
+			num_q_vectors, vsi->vsi_num, vsi->base_vector);
 		return -ENOENT;
 	}
-
-	pf->num_avail_hw_msix -= num_q_vectors;
+	pf->num_avail_sw_msix -= num_q_vectors;
 
 	return 0;
 }
@@ -1215,7 +1248,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->ring_active = false;
 		ring->vsi = vsi;
 		ring->dev = &pf->pdev->dev;
-		ring->count = vsi->num_desc;
+		ring->count = vsi->num_tx_desc;
 		vsi->tx_rings[i] = ring;
 	}
 
@@ -1234,7 +1267,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->vsi = vsi;
 		ring->netdev = vsi->netdev;
 		ring->dev = &pf->pdev->dev;
-		ring->count = vsi->num_desc;
+		ring->count = vsi->num_rx_desc;
 		vsi->rx_rings[i] = ring;
 	}
 
@@ -1253,7 +1286,11 @@ err_out:
  * through the MSI-X enabling code. On a constrained vector budget, we map Tx
  * and Rx rings to the vector as "efficiently" as possible.
  */
+#ifdef CONFIG_DCB
+void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
+#else
 static void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
+#endif /* CONFIG_DCB */
 {
 	int q_vectors = vsi->num_q_vectors;
 	int tx_rings_rem, rx_rings_rem;
@@ -1339,7 +1376,6 @@ int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena)
  */
 static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi)
 {
-	u8 seed[ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE];
 	struct ice_aqc_get_set_rss_keys *key;
 	struct ice_pf *pf = vsi->back;
 	enum ice_status status;
@@ -1361,31 +1397,30 @@ static int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi)
 				    vsi->rss_table_size);
 
 	if (status) {
-		dev_err(&vsi->back->pdev->dev,
+		dev_err(&pf->pdev->dev,
 			"set_rss_lut failed, error %d\n", status);
 		err = -EIO;
 		goto ice_vsi_cfg_rss_exit;
 	}
 
-	key = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*key), GFP_KERNEL);
+	key = devm_kzalloc(&pf->pdev->dev, sizeof(*key), GFP_KERNEL);
 	if (!key) {
 		err = -ENOMEM;
 		goto ice_vsi_cfg_rss_exit;
 	}
 
 	if (vsi->rss_hkey_user)
-		memcpy(seed, vsi->rss_hkey_user,
-		       ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
+		memcpy(key,
+		       (struct ice_aqc_get_set_rss_keys *)vsi->rss_hkey_user,
+		       ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE);
 	else
-		netdev_rss_key_fill((void *)seed,
-				    ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
-	memcpy(&key->standard_rss_key, seed,
-	       ICE_AQC_GET_SET_RSS_KEY_DATA_RSS_KEY_SIZE);
+		netdev_rss_key_fill((void *)key,
+				    ICE_GET_SET_RSS_KEY_EXTEND_KEY_SIZE);
 
 	status = ice_aq_set_rss_key(&pf->hw, vsi->idx, key);
 
 	if (status) {
-		dev_err(&vsi->back->pdev->dev, "set_rss_key failed, error %d\n",
+		dev_err(&pf->pdev->dev, "set_rss_key failed, error %d\n",
 			status);
 		err = -EIO;
 	}
@@ -1397,12 +1432,12 @@ ice_vsi_cfg_rss_exit:
 }
 
 /**
- * ice_add_mac_to_list - Add a mac address filter entry to the list
+ * ice_add_mac_to_list - Add a MAC address filter entry to the list
  * @vsi: the VSI to be forwarded to
  * @add_list: pointer to the list which contains MAC filter entries
  * @macaddr: the MAC address to be added.
  *
- * Adds mac address filter entry to the temp list
+ * Adds MAC address filter entry to the temp list
  *
  * Returns 0 on success or ENOMEM on failure.
  */
@@ -1504,7 +1539,7 @@ void ice_free_fltr_list(struct device *dev, struct list_head *h)
 /**
  * ice_vsi_add_vlan - Add VSI membership for given VLAN
  * @vsi: the VSI being configured
- * @vid: VLAN id to be added
+ * @vid: VLAN ID to be added
  */
 int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
 {
@@ -1542,7 +1577,7 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid)
 /**
  * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN
  * @vsi: the VSI being configured
- * @vid: VLAN id to be removed
+ * @vid: VLAN ID to be removed
  *
  * Returns 0 on success and negative on failure
  */
@@ -1551,7 +1586,8 @@ int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
 	struct ice_fltr_list_entry *list;
 	struct ice_pf *pf = vsi->back;
 	LIST_HEAD(tmp_add_list);
-	int status = 0;
+	enum ice_status status;
+	int err = 0;
 
 	list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
 	if (!list)
@@ -1567,14 +1603,20 @@ int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
 	INIT_LIST_HEAD(&list->list_entry);
 	list_add(&list->list_entry, &tmp_add_list);
 
-	if (ice_remove_vlan(&pf->hw, &tmp_add_list)) {
-		dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n",
-			vid, vsi->vsi_num);
-		status = -EIO;
+	status = ice_remove_vlan(&pf->hw, &tmp_add_list);
+	if (status == ICE_ERR_DOES_NOT_EXIST) {
+		dev_dbg(&pf->pdev->dev,
+			"Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n",
+			vid, vsi->vsi_num, status);
+	} else if (status) {
+		dev_err(&pf->pdev->dev,
+			"Error removing VLAN %d on vsi %i error: %d\n",
+			vid, vsi->vsi_num, status);
+		err = -EIO;
 	}
 
 	ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
-	return status;
+	return err;
 }
 
 /**
@@ -1586,7 +1628,6 @@ int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid)
  */
 int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
 {
-	int err = 0;
 	u16 i;
 
 	if (vsi->type == ICE_VSI_VF)
@@ -1601,24 +1642,32 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
 	vsi->rx_buf_len = ICE_RXBUF_2048;
 setup_rings:
 	/* set up individual rings */
-	for (i = 0; i < vsi->num_rxq && !err; i++)
-		err = ice_setup_rx_ctx(vsi->rx_rings[i]);
+	for (i = 0; i < vsi->num_rxq; i++) {
+		int err;
 
-	if (err) {
-		dev_err(&vsi->back->pdev->dev, "ice_setup_rx_ctx failed\n");
-		return -EIO;
+		err = ice_setup_rx_ctx(vsi->rx_rings[i]);
+		if (err) {
+			dev_err(&vsi->back->pdev->dev,
+				"ice_setup_rx_ctx failed for RxQ %d, err %d\n",
+				i, err);
+			return err;
+		}
 	}
-	return err;
+
+	return 0;
 }
 
 /**
  * ice_vsi_cfg_txqs - Configure the VSI for Tx
  * @vsi: the VSI being configured
+ * @rings: Tx ring array to be configured
+ * @offset: offset within vsi->txq_map
  *
  * Return 0 on success and a negative value on error
  * Configure the Tx VSI for operation.
  */
-int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
+static int
+ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, int offset)
 {
 	struct ice_aqc_add_tx_qgrp *qg_buf;
 	struct ice_aqc_add_txqs_perq *txq;
@@ -1626,9 +1675,9 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 	u8 num_q_grps, q_idx = 0;
 	enum ice_status status;
 	u16 buf_len, i, pf_q;
-	int err = 0, tc = 0;
+	int err = 0, tc;
 
-	buf_len = sizeof(struct ice_aqc_add_tx_qgrp);
+	buf_len = sizeof(*qg_buf);
 	qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL);
 	if (!qg_buf)
 		return -ENOMEM;
@@ -1637,16 +1686,15 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 	num_q_grps = 1;
 
 	/* set up and configure the Tx queues for each enabled TC */
-	for (tc = 0; tc < ICE_MAX_TRAFFIC_CLASS; tc++) {
+	ice_for_each_traffic_class(tc) {
 		if (!(vsi->tc_cfg.ena_tc & BIT(tc)))
 			break;
 
 		for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) {
 			struct ice_tlan_ctx tlan_ctx = { 0 };
 
-			pf_q = vsi->txq_map[q_idx];
-			ice_setup_tx_ctx(vsi->tx_rings[q_idx], &tlan_ctx,
-					 pf_q);
+			pf_q = vsi->txq_map[q_idx + offset];
+			ice_setup_tx_ctx(rings[q_idx], &tlan_ctx, pf_q);
 			/* copy context contents into the qg_buf */
 			qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
 			ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
@@ -1655,13 +1703,13 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 			/* init queue specific tail reg. It is referred as
 			 * transmit comm scheduler queue doorbell.
 			 */
-			vsi->tx_rings[q_idx]->tail =
+			rings[q_idx]->tail =
 				pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
 			status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
-						 num_q_grps, qg_buf, buf_len,
-						 NULL);
+						 i, num_q_grps, qg_buf,
+						 buf_len, NULL);
 			if (status) {
-				dev_err(&vsi->back->pdev->dev,
+				dev_err(&pf->pdev->dev,
 					"Failed to set LAN Tx queue context, error: %d\n",
 					status);
 				err = -ENODEV;
@@ -1674,7 +1722,7 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
 			 */
 			txq = &qg_buf->txqs[0];
 			if (pf_q == le16_to_cpu(txq->txq_id))
-				vsi->tx_rings[q_idx]->txq_teid =
+				rings[q_idx]->txq_teid =
 					le32_to_cpu(txq->q_teid);
 
 			q_idx++;
@@ -1686,6 +1734,18 @@ err_cfg_txqs:
 }
 
 /**
+ * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx
+ * @vsi: the VSI being configured
+ *
+ * Return 0 on success and a negative value on error
+ * Configure the Tx VSI for operation.
+ */
+int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi)
+{
+	return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, 0);
+}
+
+/**
  * ice_intrl_usec_to_reg - convert interrupt rate limit to register value
  * @intrl: interrupt rate limit in usecs
  * @gran: interrupt rate limit granularity in usecs
@@ -1693,7 +1753,7 @@ err_cfg_txqs:
  * This function converts a decimal interrupt rate limit in usecs to the format
  * expected by firmware.
  */
-static u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran)
+u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran)
 {
 	u32 val = intrl / gran;
 
@@ -1703,54 +1763,161 @@ static u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran)
 }
 
 /**
+ * ice_cfg_itr_gran - set the ITR granularity to 2 usecs if not already set
+ * @hw: board specific structure
+ */
+static void ice_cfg_itr_gran(struct ice_hw *hw)
+{
+	u32 regval = rd32(hw, GLINT_CTL);
+
+	/* no need to update global register if ITR gran is already set */
+	if (!(regval & GLINT_CTL_DIS_AUTOMASK_M) &&
+	    (((regval & GLINT_CTL_ITR_GRAN_200_M) >>
+	     GLINT_CTL_ITR_GRAN_200_S) == ICE_ITR_GRAN_US) &&
+	    (((regval & GLINT_CTL_ITR_GRAN_100_M) >>
+	     GLINT_CTL_ITR_GRAN_100_S) == ICE_ITR_GRAN_US) &&
+	    (((regval & GLINT_CTL_ITR_GRAN_50_M) >>
+	     GLINT_CTL_ITR_GRAN_50_S) == ICE_ITR_GRAN_US) &&
+	    (((regval & GLINT_CTL_ITR_GRAN_25_M) >>
+	      GLINT_CTL_ITR_GRAN_25_S) == ICE_ITR_GRAN_US))
+		return;
+
+	regval = ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_200_S) &
+		  GLINT_CTL_ITR_GRAN_200_M) |
+		 ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_100_S) &
+		  GLINT_CTL_ITR_GRAN_100_M) |
+		 ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_50_S) &
+		  GLINT_CTL_ITR_GRAN_50_M) |
+		 ((ICE_ITR_GRAN_US << GLINT_CTL_ITR_GRAN_25_S) &
+		  GLINT_CTL_ITR_GRAN_25_M);
+	wr32(hw, GLINT_CTL, regval);
+}
+
+/**
  * ice_cfg_itr - configure the initial interrupt throttle values
  * @hw: pointer to the HW structure
  * @q_vector: interrupt vector that's being configured
- * @vector: HW vector index to apply the interrupt throttling to
  *
  * Configure interrupt throttling values for the ring containers that are
  * associated with the interrupt vector passed in.
  */
 static void
-ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector, u16 vector)
+ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector)
 {
-	u8 itr_gran = hw->itr_gran;
+	ice_cfg_itr_gran(hw);
 
 	if (q_vector->num_ring_rx) {
 		struct ice_ring_container *rc = &q_vector->rx;
 
-		rc->itr = ITR_TO_REG(ICE_DFLT_RX_ITR, itr_gran);
-		rc->latency_range = ICE_LOW_LATENCY;
-		wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr);
+		/* if this value is set then don't overwrite with default */
+		if (!rc->itr_setting)
+			rc->itr_setting = ICE_DFLT_RX_ITR;
+
+		rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		rc->next_update = jiffies + 1;
+		rc->current_itr = rc->target_itr;
+		wr32(hw, GLINT_ITR(rc->itr_idx, q_vector->reg_idx),
+		     ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
 	}
 
 	if (q_vector->num_ring_tx) {
 		struct ice_ring_container *rc = &q_vector->tx;
 
-		rc->itr = ITR_TO_REG(ICE_DFLT_TX_ITR, itr_gran);
-		rc->latency_range = ICE_LOW_LATENCY;
-		wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr);
+		/* if this value is set then don't overwrite with default */
+		if (!rc->itr_setting)
+			rc->itr_setting = ICE_DFLT_TX_ITR;
+
+		rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		rc->next_update = jiffies + 1;
+		rc->current_itr = rc->target_itr;
+		wr32(hw, GLINT_ITR(rc->itr_idx, q_vector->reg_idx),
+		     ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
 	}
 }
 
 /**
+ * ice_cfg_txq_interrupt - configure interrupt on Tx queue
+ * @vsi: the VSI being configured
+ * @txq: Tx queue being mapped to MSI-X vector
+ * @msix_idx: MSI-X vector index within the function
+ * @itr_idx: ITR index of the interrupt cause
+ *
+ * Configure interrupt on Tx queue by associating Tx queue to MSI-X vector
+ * within the function space.
+ */
+#ifdef CONFIG_PCI_IOV
+void
+ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx)
+#else
+static void
+ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx)
+#endif /* CONFIG_PCI_IOV */
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	u32 val;
+
+	itr_idx = (itr_idx << QINT_TQCTL_ITR_INDX_S) & QINT_TQCTL_ITR_INDX_M;
+
+	val = QINT_TQCTL_CAUSE_ENA_M | itr_idx |
+	      ((msix_idx << QINT_TQCTL_MSIX_INDX_S) & QINT_TQCTL_MSIX_INDX_M);
+
+	wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val);
+}
+
+/**
+ * ice_cfg_rxq_interrupt - configure interrupt on Rx queue
+ * @vsi: the VSI being configured
+ * @rxq: Rx queue being mapped to MSI-X vector
+ * @msix_idx: MSI-X vector index within the function
+ * @itr_idx: ITR index of the interrupt cause
+ *
+ * Configure interrupt on Rx queue by associating Rx queue to MSI-X vector
+ * within the function space.
+ */
+#ifdef CONFIG_PCI_IOV
+void
+ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx)
+#else
+static void
+ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx)
+#endif /* CONFIG_PCI_IOV */
+{
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	u32 val;
+
+	itr_idx = (itr_idx << QINT_RQCTL_ITR_INDX_S) & QINT_RQCTL_ITR_INDX_M;
+
+	val = QINT_RQCTL_CAUSE_ENA_M | itr_idx |
+	      ((msix_idx << QINT_RQCTL_MSIX_INDX_S) & QINT_RQCTL_MSIX_INDX_M);
+
+	wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val);
+
+	ice_flush(hw);
+}
+
+/**
  * ice_vsi_cfg_msix - MSIX mode Interrupt Config in the HW
  * @vsi: the VSI being configured
+ *
+ * This configures MSIX mode interrupts for the PF VSI, and should not be used
+ * for the VF VSI.
  */
 void ice_vsi_cfg_msix(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
-	u16 vector = vsi->hw_base_vector;
 	struct ice_hw *hw = &pf->hw;
 	u32 txq = 0, rxq = 0;
 	int i, q;
 
-	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
+	for (i = 0; i < vsi->num_q_vectors; i++) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[i];
+		u16 reg_idx = q_vector->reg_idx;
 
-		ice_cfg_itr(hw, q_vector, vector);
+		ice_cfg_itr(hw, q_vector);
 
-		wr32(hw, GLINT_RATE(vector),
+		wr32(hw, GLINT_RATE(reg_idx),
 		     ice_intrl_usec_to_reg(q_vector->intrl, hw->intrl_gran));
 
 		/* Both Transmit Queue Interrupt Cause Control register
@@ -1765,39 +1932,17 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi)
 		 * tracked for this PF.
 		 */
 		for (q = 0; q < q_vector->num_ring_tx; q++) {
-			int itr_idx = q_vector->tx.itr_idx;
-			u32 val;
-
-			if (vsi->type == ICE_VSI_VF)
-				val = QINT_TQCTL_CAUSE_ENA_M |
-				      (itr_idx << QINT_TQCTL_ITR_INDX_S)  |
-				      ((i + 1) << QINT_TQCTL_MSIX_INDX_S);
-			else
-				val = QINT_TQCTL_CAUSE_ENA_M |
-				      (itr_idx << QINT_TQCTL_ITR_INDX_S)  |
-				      (vector << QINT_TQCTL_MSIX_INDX_S);
-			wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), val);
+			ice_cfg_txq_interrupt(vsi, txq, reg_idx,
+					      q_vector->tx.itr_idx);
 			txq++;
 		}
 
 		for (q = 0; q < q_vector->num_ring_rx; q++) {
-			int itr_idx = q_vector->rx.itr_idx;
-			u32 val;
-
-			if (vsi->type == ICE_VSI_VF)
-				val = QINT_RQCTL_CAUSE_ENA_M |
-				      (itr_idx << QINT_RQCTL_ITR_INDX_S)  |
-				      ((i + 1) << QINT_RQCTL_MSIX_INDX_S);
-			else
-				val = QINT_RQCTL_CAUSE_ENA_M |
-				      (itr_idx << QINT_RQCTL_ITR_INDX_S)  |
-				      (vector << QINT_RQCTL_MSIX_INDX_S);
-			wr32(hw, QINT_RQCTL(vsi->rxq_map[rxq]), val);
+			ice_cfg_rxq_interrupt(vsi, rxq, reg_idx,
+					      q_vector->rx.itr_idx);
 			rxq++;
 		}
 	}
-
-	ice_flush(hw);
 }
 
 /**
@@ -1808,26 +1953,38 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi)
 {
 	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
+	int ret = 0;
+
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
 
 	/* Here we are configuring the VSI to let the driver add VLAN tags by
 	 * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag
 	 * insertion happens in the Tx hot path, in ice_tx_map.
 	 */
-	ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL;
+	ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL;
+
+	/* Preserve existing VLAN strip setting */
+	ctxt->info.vlan_flags |= (vsi->info.vlan_flags &
+				  ICE_AQ_VSI_VLAN_EMOD_M);
 
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
 
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
 			status, hw->adminq.sq_last_status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	vsi->info.vlan_flags = ctxt.info.vlan_flags;
-	return 0;
+	vsi->info.vlan_flags = ctxt->info.vlan_flags;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
@@ -1839,35 +1996,42 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
 {
 	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
+	int ret = 0;
+
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
 
 	/* Here we are configuring what the VSI should do with the VLAN tag in
 	 * the Rx packet. We can either leave the tag in the packet or put it in
 	 * the Rx descriptor.
 	 */
-	if (ena) {
+	if (ena)
 		/* Strip VLAN tag from Rx packet and put it in the desc */
-		ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH;
-	} else {
+		ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH;
+	else
 		/* Disable stripping. Leave tag in packet */
-		ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
-	}
+		ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
 
 	/* Allow all packets untagged/tagged */
-	ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
+	ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
 
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
 
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_err(dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n",
 			ena, status, hw->adminq.sq_last_status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	vsi->info.vlan_flags = ctxt.info.vlan_flags;
-	return 0;
+	vsi->info.vlan_flags = ctxt->info.vlan_flags;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
@@ -1893,20 +2057,36 @@ int ice_vsi_stop_rx_rings(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_trigger_sw_intr - trigger a software interrupt
+ * @hw: pointer to the HW structure
+ * @q_vector: interrupt vector to trigger the software interrupt for
+ */
+void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector)
+{
+	wr32(hw, GLINT_DYN_CTL(q_vector->reg_idx),
+	     (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S) |
+	     GLINT_DYN_CTL_SWINT_TRIG_M |
+	     GLINT_DYN_CTL_INTENA_M);
+}
+
+/**
  * ice_vsi_stop_tx_rings - Disable Tx rings
  * @vsi: the VSI being configured
  * @rst_src: reset source
- * @rel_vmvf_num: Relative id of VF/VM
+ * @rel_vmvf_num: Relative ID of VF/VM
+ * @rings: Tx ring array to be stopped
+ * @offset: offset within vsi->txq_map
  */
-int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
-			  u16 rel_vmvf_num)
+static int
+ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+		      u16 rel_vmvf_num, struct ice_ring **rings, int offset)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
+	int tc, q_idx = 0, err = 0;
+	u16 *q_ids, *q_handles, i;
 	enum ice_status status;
 	u32 *q_teids, val;
-	u16 *q_ids, i;
-	int err = 0;
 
 	if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS)
 		return -EINVAL;
@@ -1923,51 +2103,71 @@ int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 		goto err_alloc_q_ids;
 	}
 
-	/* set up the Tx queue list to be disabled */
-	ice_for_each_txq(vsi, i) {
-		u16 v_idx;
+	q_handles = devm_kcalloc(&pf->pdev->dev, vsi->num_txq,
+				 sizeof(*q_handles), GFP_KERNEL);
+	if (!q_handles) {
+		err = -ENOMEM;
+		goto err_alloc_q_handles;
+	}
 
-		if (!vsi->tx_rings || !vsi->tx_rings[i] ||
-		    !vsi->tx_rings[i]->q_vector) {
-			err = -EINVAL;
-			goto err_out;
-		}
+	/* set up the Tx queue list to be disabled for each enabled TC */
+	ice_for_each_traffic_class(tc) {
+		if (!(vsi->tc_cfg.ena_tc & BIT(tc)))
+			break;
 
-		q_ids[i] = vsi->txq_map[i];
-		q_teids[i] = vsi->tx_rings[i]->txq_teid;
+		for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) {
+			struct ice_q_vector *q_vector;
 
-		/* clear cause_ena bit for disabled queues */
-		val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx));
-		val &= ~QINT_TQCTL_CAUSE_ENA_M;
-		wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val);
+			if (!rings || !rings[q_idx]) {
+				err = -EINVAL;
+				goto err_out;
+			}
+
+			q_ids[i] = vsi->txq_map[q_idx + offset];
+			q_teids[i] = rings[q_idx]->txq_teid;
+			q_handles[i] = i;
 
-		/* software is expected to wait for 100 ns */
-		ndelay(100);
+			/* clear cause_ena bit for disabled queues */
+			val = rd32(hw, QINT_TQCTL(rings[i]->reg_idx));
+			val &= ~QINT_TQCTL_CAUSE_ENA_M;
+			wr32(hw, QINT_TQCTL(rings[i]->reg_idx), val);
 
-		/* trigger a software interrupt for the vector associated to
-		 * the queue to schedule NAPI handler
+			/* software is expected to wait for 100 ns */
+			ndelay(100);
+
+			/* trigger a software interrupt for the vector
+			 * associated to the queue to schedule NAPI handler
+			 */
+			q_vector = rings[i]->q_vector;
+			if (q_vector)
+				ice_trigger_sw_intr(hw, q_vector);
+
+			q_idx++;
+		}
+		status = ice_dis_vsi_txq(vsi->port_info, vsi->idx, tc,
+					 vsi->num_txq, q_handles, q_ids,
+					 q_teids, rst_src, rel_vmvf_num, NULL);
+
+		/* if the disable queue command was exercised during an active
+		 * reset flow, ICE_ERR_RESET_ONGOING is returned. This is not
+		 * an error as the reset operation disables queues at the
+		 * hardware level anyway.
 		 */
-		v_idx = vsi->tx_rings[i]->q_vector->v_idx;
-		wr32(hw, GLINT_DYN_CTL(vsi->hw_base_vector + v_idx),
-		     GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M);
-	}
-	status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids,
-				 rst_src, rel_vmvf_num, NULL);
-	/* if the disable queue command was exercised during an active reset
-	 * flow, ICE_ERR_RESET_ONGOING is returned. This is not an error as
-	 * the reset operation disables queues at the hardware level anyway.
-	 */
-	if (status == ICE_ERR_RESET_ONGOING) {
-		dev_info(&pf->pdev->dev,
-			 "Reset in progress. LAN Tx queues already disabled\n");
-	} else if (status) {
-		dev_err(&pf->pdev->dev,
-			"Failed to disable LAN Tx queues, error: %d\n",
-			status);
-		err = -ENODEV;
+		if (status == ICE_ERR_RESET_ONGOING) {
+			dev_dbg(&pf->pdev->dev,
+				"Reset in progress. LAN Tx queues already disabled\n");
+		} else if (status) {
+			dev_err(&pf->pdev->dev,
+				"Failed to disable LAN Tx queues, error: %d\n",
+				status);
+			err = -ENODEV;
+		}
 	}
 
 err_out:
+	devm_kfree(&pf->pdev->dev, q_handles);
+
+err_alloc_q_handles:
 	devm_kfree(&pf->pdev->dev, q_ids);
 
 err_alloc_q_ids:
@@ -1977,22 +2177,39 @@ err_alloc_q_ids:
 }
 
 /**
+ * ice_vsi_stop_lan_tx_rings - Disable LAN Tx rings
+ * @vsi: the VSI being configured
+ * @rst_src: reset source
+ * @rel_vmvf_num: Relative ID of VF/VM
+ */
+int
+ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+			  u16 rel_vmvf_num)
+{
+	return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings,
+				     0);
+}
+
+/**
  * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI
  * @vsi: VSI to enable or disable VLAN pruning on
  * @ena: set to true to enable VLAN pruning and false to disable it
+ * @vlan_promisc: enable valid security flags if not in VLAN promiscuous mode
  *
  * returns 0 if VSI is updated, negative otherwise
  */
-int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena)
+int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc)
 {
 	struct ice_vsi_ctx *ctxt;
 	struct device *dev;
+	struct ice_pf *pf;
 	int status;
 
 	if (!vsi)
 		return -EINVAL;
 
-	dev = &vsi->back->pdev->dev;
+	pf = vsi->back;
+	dev = &pf->pdev->dev;
 	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
 	if (!ctxt)
 		return -ENOMEM;
@@ -2011,14 +2228,16 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena)
 		ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
 	}
 
-	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID |
-						ICE_AQ_VSI_PROP_SW_VALID);
+	if (!vlan_promisc)
+		ctxt->info.valid_sections =
+			cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID |
+				    ICE_AQ_VSI_PROP_SW_VALID);
 
-	status = ice_update_vsi(&vsi->back->hw, vsi->idx, ctxt, NULL);
+	status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n",
 			   ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status,
-			   vsi->back->hw.adminq.sq_last_status);
+			   pf->hw.adminq.sq_last_status);
 		goto err_out;
 	}
 
@@ -2033,12 +2252,153 @@ err_out:
 	return -EIO;
 }
 
+static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi)
+{
+	struct ice_dcbx_cfg *cfg = &vsi->port_info->local_dcbx_cfg;
+
+	vsi->tc_cfg.ena_tc = ice_dcb_get_ena_tc(cfg);
+	vsi->tc_cfg.numtc = ice_dcb_get_num_tc(cfg);
+}
+
+/**
+ * ice_vsi_set_q_vectors_reg_idx - set the HW register index for all q_vectors
+ * @vsi: VSI to set the q_vectors register index on
+ */
+static int
+ice_vsi_set_q_vectors_reg_idx(struct ice_vsi *vsi)
+{
+	u16 i;
+
+	if (!vsi || !vsi->q_vectors)
+		return -EINVAL;
+
+	ice_for_each_q_vector(vsi, i) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+		if (!q_vector) {
+			dev_err(&vsi->back->pdev->dev,
+				"Failed to set reg_idx on q_vector %d VSI %d\n",
+				i, vsi->vsi_num);
+			goto clear_reg_idx;
+		}
+
+		if (vsi->type == ICE_VSI_VF) {
+			struct ice_vf *vf = &vsi->back->vf[vsi->vf_id];
+
+			q_vector->reg_idx = ice_calc_vf_reg_idx(vf, q_vector);
+		} else {
+			q_vector->reg_idx =
+				q_vector->v_idx + vsi->base_vector;
+		}
+	}
+
+	return 0;
+
+clear_reg_idx:
+	ice_for_each_q_vector(vsi, i) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+		if (q_vector)
+			q_vector->reg_idx = 0;
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * ice_vsi_add_rem_eth_mac - Program VSI ethertype based filter with rule
+ * @vsi: the VSI being configured
+ * @add_rule: boolean value to add or remove ethertype filter rule
+ */
+static void
+ice_vsi_add_rem_eth_mac(struct ice_vsi *vsi, bool add_rule)
+{
+	struct ice_fltr_list_entry *list;
+	struct ice_pf *pf = vsi->back;
+	LIST_HEAD(tmp_add_list);
+	enum ice_status status;
+
+	list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
+	if (!list)
+		return;
+
+	list->fltr_info.lkup_type = ICE_SW_LKUP_ETHERTYPE;
+	list->fltr_info.fltr_act = ICE_DROP_PACKET;
+	list->fltr_info.flag = ICE_FLTR_TX;
+	list->fltr_info.src_id = ICE_SRC_ID_VSI;
+	list->fltr_info.vsi_handle = vsi->idx;
+	list->fltr_info.l_data.ethertype_mac.ethertype = vsi->ethtype;
+
+	INIT_LIST_HEAD(&list->list_entry);
+	list_add(&list->list_entry, &tmp_add_list);
+
+	if (add_rule)
+		status = ice_add_eth_mac(&pf->hw, &tmp_add_list);
+	else
+		status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
+
+	if (status)
+		dev_err(&pf->pdev->dev,
+			"Failure Adding or Removing Ethertype on VSI %i error: %d\n",
+			vsi->vsi_num, status);
+
+	ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+}
+
+/**
+ * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling
+ * @vsi: the VSI being configured
+ * @tx: bool to determine Tx or Rx rule
+ * @create: bool to determine create or remove Rule
+ */
+void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
+{
+	struct ice_fltr_list_entry *list;
+	struct ice_pf *pf = vsi->back;
+	LIST_HEAD(tmp_add_list);
+	enum ice_status status;
+
+	list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL);
+	if (!list)
+		return;
+
+	list->fltr_info.lkup_type = ICE_SW_LKUP_ETHERTYPE;
+	list->fltr_info.vsi_handle = vsi->idx;
+	list->fltr_info.l_data.ethertype_mac.ethertype = ETH_P_LLDP;
+
+	if (tx) {
+		list->fltr_info.fltr_act = ICE_DROP_PACKET;
+		list->fltr_info.flag = ICE_FLTR_TX;
+		list->fltr_info.src_id = ICE_SRC_ID_VSI;
+	} else {
+		list->fltr_info.fltr_act = ICE_FWD_TO_VSI;
+		list->fltr_info.flag = ICE_FLTR_RX;
+		list->fltr_info.src_id = ICE_SRC_ID_LPORT;
+	}
+
+	INIT_LIST_HEAD(&list->list_entry);
+	list_add(&list->list_entry, &tmp_add_list);
+
+	if (create)
+		status = ice_add_eth_mac(&pf->hw, &tmp_add_list);
+	else
+		status = ice_remove_eth_mac(&pf->hw, &tmp_add_list);
+
+	if (status)
+		dev_err(&pf->pdev->dev,
+			"Fail %s %s LLDP rule on VSI %i error: %d\n",
+			create ? "adding" : "removing", tx ? "TX" : "RX",
+			vsi->vsi_num, status);
+
+	ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+}
+
 /**
  * ice_vsi_setup - Set up a VSI by a given type
  * @pf: board private structure
  * @pi: pointer to the port_info instance
  * @type: VSI type
- * @vf_id: defines VF id to which this VSI connects. This field is meant to be
+ * @vf_id: defines VF ID to which this VSI connects. This field is meant to be
  *         used only for ICE_VSI_VF VSI type. For other VSI types, should
  *         fill-in ICE_INVAL_VFID as input.
  *
@@ -2053,10 +2413,15 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
 	struct device *dev = &pf->pdev->dev;
+	enum ice_status status;
 	struct ice_vsi *vsi;
 	int ret, i;
 
-	vsi = ice_vsi_alloc(pf, type);
+	if (type == ICE_VSI_VF)
+		vsi = ice_vsi_alloc(pf, type, vf_id);
+	else
+		vsi = ice_vsi_alloc(pf, type, ICE_INVAL_VFID);
+
 	if (!vsi) {
 		dev_err(dev, "could not allocate VSI\n");
 		return NULL;
@@ -2064,6 +2429,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 
 	vsi->port_info = pi;
 	vsi->vsw = pf->first_sw;
+	if (vsi->type == ICE_VSI_PF)
+		vsi->ethtype = ETH_P_PAUSE;
+
 	if (vsi->type == ICE_VSI_VF)
 		vsi->vf_id = vf_id;
 
@@ -2076,7 +2444,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	/* set RSS capabilities */
 	ice_vsi_set_rss_params(vsi);
 
-	/* set tc configuration */
+	/* set TC configuration */
 	ice_vsi_set_tc_cfg(vsi);
 
 	/* create the VSI */
@@ -2094,6 +2462,10 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		if (ret)
 			goto unroll_alloc_q_vector;
 
+		ret = ice_vsi_set_q_vectors_reg_idx(vsi);
+		if (ret)
+			goto unroll_vector_base;
+
 		ret = ice_vsi_alloc_rings(vsi);
 		if (ret)
 			goto unroll_vector_base;
@@ -2121,19 +2493,24 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		if (ret)
 			goto unroll_alloc_q_vector;
 
-		/* Setup Vector base only during VF init phase or when VF asks
-		 * for more vectors than assigned number. In all other cases,
-		 * assign hw_base_vector to the value given earlier.
-		 */
-		if (test_bit(ICE_VF_STATE_CFG_INTR, pf->vf[vf_id].vf_states)) {
-			ret = ice_vsi_setup_vector_base(vsi);
-			if (ret)
-				goto unroll_vector_base;
-		} else {
-			vsi->hw_base_vector = pf->vf[vf_id].first_vector_idx;
-		}
+		ret = ice_vsi_set_q_vectors_reg_idx(vsi);
+		if (ret)
+			goto unroll_vector_base;
+
 		pf->q_left_tx -= vsi->alloc_txq;
 		pf->q_left_rx -= vsi->alloc_rxq;
+
+		/* Do not exit if configuring RSS had an issue, at least
+		 * receive traffic on first queue. Hence no need to capture
+		 * return value
+		 */
+		if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+			ice_vsi_cfg_rss_lut_key(vsi);
+		break;
+	case ICE_VSI_LB:
+		ret = ice_vsi_alloc_rings(vsi);
+		if (ret)
+			goto unroll_vsi_init;
 		break;
 	default:
 		/* clean up the resources and exit */
@@ -2144,22 +2521,42 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
 		max_txqs[i] = pf->num_lan_tx;
 
-	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
-			      max_txqs);
-	if (ret) {
-		dev_info(&pf->pdev->dev, "Failed VSI lan queue config\n");
+	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+				 max_txqs);
+	if (status) {
+		dev_err(&pf->pdev->dev,
+			"VSI %d failed lan queue config, error %d\n",
+			vsi->vsi_num, status);
 		goto unroll_vector_base;
 	}
 
+	/* Add switch rule to drop all Tx Flow Control Frames, of look up
+	 * type ETHERTYPE from VSIs, and restrict malicious VF from sending
+	 * out PAUSE or PFC frames. If enabled, FW can still send FC frames.
+	 * The rule is added once for PF VSI in order to create appropriate
+	 * recipe, since VSI/VSI list is ignored with drop action...
+	 * Also add rules to handle LLDP Tx and Rx packets.  Tx LLDP packets
+	 * need to be dropped so that VFs cannot send LLDP packets to reconfig
+	 * DCB settings in the HW.  Also, if the FW DCBX engine is not running
+	 * then Rx LLDP packets need to be redirected up the stack.
+	 */
+	if (vsi->type == ICE_VSI_PF) {
+		ice_vsi_add_rem_eth_mac(vsi, true);
+
+		/* Tx LLDP packets */
+		ice_cfg_sw_lldp(vsi, true, true);
+
+		/* Rx LLDP packets */
+		if (!test_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags))
+			ice_cfg_sw_lldp(vsi, false, true);
+	}
+
 	return vsi;
 
 unroll_vector_base:
 	/* reclaim SW interrupts back to the common pool */
-	ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx);
+	ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
 	pf->num_avail_sw_msix += vsi->num_q_vectors;
-	/* reclaim HW interrupt back to the common pool */
-	ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx);
-	pf->num_avail_hw_msix += vsi->num_q_vectors;
 unroll_alloc_q_vector:
 	ice_vsi_free_q_vectors(vsi);
 unroll_vsi_init:
@@ -2180,17 +2577,17 @@ unroll_get_qs:
 static void ice_vsi_release_msix(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
-	u16 vector = vsi->hw_base_vector;
 	struct ice_hw *hw = &pf->hw;
 	u32 txq = 0;
 	u32 rxq = 0;
 	int i, q;
 
-	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
+	for (i = 0; i < vsi->num_q_vectors; i++) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[i];
+		u16 reg_idx = q_vector->reg_idx;
 
-		wr32(hw, GLINT_ITR(ICE_IDX_ITR0, vector), 0);
-		wr32(hw, GLINT_ITR(ICE_IDX_ITR1, vector), 0);
+		wr32(hw, GLINT_ITR(ICE_IDX_ITR0, reg_idx), 0);
+		wr32(hw, GLINT_ITR(ICE_IDX_ITR1, reg_idx), 0);
 		for (q = 0; q < q_vector->num_ring_tx; q++) {
 			wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0);
 			txq++;
@@ -2212,7 +2609,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi)
 void ice_vsi_free_irq(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
-	int base = vsi->sw_base_vector;
+	int base = vsi->base_vector;
 
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
 		int i;
@@ -2225,7 +2622,7 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 			return;
 
 		vsi->irqs_ready = false;
-		for (i = 0; i < vsi->num_q_vectors; i++) {
+		ice_for_each_q_vector(vsi, i) {
 			u16 vector = i + base;
 			int irq_num;
 
@@ -2308,11 +2705,11 @@ int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id)
 	int count = 0;
 	int i;
 
-	if (!res || index >= res->num_entries)
+	if (!res || index >= res->end)
 		return -EINVAL;
 
 	id |= ICE_RES_VALID_BIT;
-	for (i = index; i < res->num_entries && res->list[i] == id; i++) {
+	for (i = index; i < res->end && res->list[i] == id; i++) {
 		res->list[i] = 0;
 		count++;
 	}
@@ -2330,10 +2727,9 @@ int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id)
  */
 static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
 {
-	int start = res->search_hint;
-	int end = start;
+	int start = 0, end = 0;
 
-	if ((start + needed) > res->num_entries)
+	if (needed > res->end)
 		return -ENOMEM;
 
 	id |= ICE_RES_VALID_BIT;
@@ -2342,7 +2738,7 @@ static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
 		/* skip already allocated entries */
 		if (res->list[end++] & ICE_RES_VALID_BIT) {
 			start = end;
-			if ((start + needed) > res->num_entries)
+			if ((start + needed) > res->end)
 				break;
 		}
 
@@ -2353,13 +2749,9 @@ static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
 			while (i != end)
 				res->list[i++] = id;
 
-			if (end == res->num_entries)
-				end = 0;
-
-			res->search_hint = end;
 			return start;
 		}
-	} while (1);
+	} while (end < res->end);
 
 	return -ENOMEM;
 }
@@ -2371,16 +2763,11 @@ static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
  * @needed: size of the block needed
  * @id: identifier to track owner
  *
- * Returns the base item index of the block, or -ENOMEM for error
- * The search_hint trick and lack of advanced fit-finding only works
- * because we're highly likely to have all the same sized requests.
- * Linear search time and any fragmentation should be minimal.
+ * Returns the base item index of the block, or negative for error
  */
 int
 ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id)
 {
-	int ret;
-
 	if (!res || !pf)
 		return -EINVAL;
 
@@ -2391,16 +2778,7 @@ ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id)
 		return -EINVAL;
 	}
 
-	/* search based on search_hint */
-	ret = ice_search_res(res, needed, id);
-
-	if (ret < 0) {
-		/* previous search failed. Reset search hint and try again */
-		res->search_hint = 0;
-		ret = ice_search_res(res, needed, id);
-	}
-
-	return ret;
+	return ice_search_res(res, needed, id);
 }
 
 /**
@@ -2409,7 +2787,7 @@ ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id)
  */
 void ice_vsi_dis_irq(struct ice_vsi *vsi)
 {
-	int base = vsi->sw_base_vector;
+	int base = vsi->base_vector;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
 	u32 val;
@@ -2444,17 +2822,32 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
 
 	/* disable each interrupt */
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
-		for (i = vsi->hw_base_vector;
-		     i < (vsi->num_q_vectors + vsi->hw_base_vector); i++)
-			wr32(hw, GLINT_DYN_CTL(i), 0);
+		ice_for_each_q_vector(vsi, i)
+			wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0);
 
 		ice_flush(hw);
-		for (i = 0; i < vsi->num_q_vectors; i++)
+
+		ice_for_each_q_vector(vsi, i)
 			synchronize_irq(pf->msix_entries[i + base].vector);
 	}
 }
 
 /**
+ * ice_napi_del - Remove NAPI handler for the VSI
+ * @vsi: VSI for which NAPI handler is to be removed
+ */
+void ice_napi_del(struct ice_vsi *vsi)
+{
+	int v_idx;
+
+	if (!vsi->netdev)
+		return;
+
+	ice_for_each_q_vector(vsi, v_idx)
+		netif_napi_del(&vsi->q_vectors[v_idx]->napi);
+}
+
+/**
  * ice_vsi_release - Delete a VSI and free its resources
  * @vsi: the VSI being removed
  *
@@ -2463,56 +2856,60 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
 int ice_vsi_release(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf;
-	struct ice_vf *vf;
 
 	if (!vsi->back)
 		return -ENODEV;
 	pf = vsi->back;
-	vf = &pf->vf[vsi->vf_id];
-	/* do not unregister and free netdevs while driver is in the reset
-	 * recovery pending state. Since reset/rebuild happens through PF
-	 * service task workqueue, its not a good idea to unregister netdev
-	 * that is associated to the PF that is running the work queue items
-	 * currently. This is done to avoid check_flush_dependency() warning
-	 * on this wq
+
+	/* do not unregister while driver is in the reset recovery pending
+	 * state. Since reset/rebuild happens through PF service task workqueue,
+	 * it's not a good idea to unregister netdev that is associated to the
+	 * PF that is running the work queue items currently. This is done to
+	 * avoid check_flush_dependency() warning on this wq
 	 */
-	if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) {
-		ice_napi_del(vsi);
+	if (vsi->netdev && !ice_is_reset_in_progress(pf->state))
 		unregister_netdev(vsi->netdev);
-		free_netdev(vsi->netdev);
-		vsi->netdev = NULL;
-	}
 
 	if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
 		ice_rss_clean(vsi);
 
 	/* Disable VSI and free resources */
-	ice_vsi_dis_irq(vsi);
+	if (vsi->type != ICE_VSI_LB)
+		ice_vsi_dis_irq(vsi);
 	ice_vsi_close(vsi);
 
-	/* reclaim interrupt vectors back to PF */
+	/* SR-IOV determines needed MSIX resources all at once instead of per
+	 * VSI since when VFs are spawned we know how many VFs there are and how
+	 * many interrupts each VF needs. SR-IOV MSIX resources are also
+	 * cleared in the same manner.
+	 */
 	if (vsi->type != ICE_VSI_VF) {
 		/* reclaim SW interrupts back to the common pool */
-		ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector,
-			     vsi->idx);
+		ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
 		pf->num_avail_sw_msix += vsi->num_q_vectors;
-		/* reclaim HW interrupts back to the common pool */
-		ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector,
-			     vsi->idx);
-		pf->num_avail_hw_msix += vsi->num_q_vectors;
-	} else if (test_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states)) {
-		/* Reclaim VF resources back only while freeing all VFs or
-		 * vector reassignment is requested
+	}
+
+	if (vsi->type == ICE_VSI_PF) {
+		ice_vsi_add_rem_eth_mac(vsi, false);
+		ice_cfg_sw_lldp(vsi, true, false);
+		/* The Rx rule will only exist to remove if the LLDP FW
+		 * engine is currently stopped
 		 */
-		ice_free_res(vsi->back->hw_irq_tracker, vf->first_vector_idx,
-			     vsi->idx);
-		pf->num_avail_hw_msix += pf->num_vf_msix;
+		if (!test_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags))
+			ice_cfg_sw_lldp(vsi, false, false);
 	}
 
 	ice_remove_vsi_fltr(&pf->hw, vsi->idx);
 	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_delete(vsi);
 	ice_vsi_free_q_vectors(vsi);
+
+	/* make sure unregister_netdev() was called by checking __ICE_DOWN */
+	if (vsi->netdev && test_bit(__ICE_DOWN, vsi->state)) {
+		free_netdev(vsi->netdev);
+		vsi->netdev = NULL;
+	}
+
 	ice_vsi_clear_rings(vsi);
 
 	ice_vsi_put_qs(vsi);
@@ -2538,6 +2935,8 @@ int ice_vsi_release(struct ice_vsi *vsi)
 int ice_vsi_rebuild(struct ice_vsi *vsi)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct ice_vf *vf = NULL;
+	enum ice_status status;
 	struct ice_pf *pf;
 	int ret, i;
 
@@ -2545,16 +2944,31 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		return -EINVAL;
 
 	pf = vsi->back;
+	if (vsi->type == ICE_VSI_VF)
+		vf = &pf->vf[vsi->vf_id];
+
 	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_free_q_vectors(vsi);
-	ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx);
-	ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx);
-	vsi->sw_base_vector = 0;
-	vsi->hw_base_vector = 0;
+
+	/* SR-IOV determines needed MSIX resources all at once instead of per
+	 * VSI since when VFs are spawned we know how many VFs there are and how
+	 * many interrupts each VF needs. SR-IOV MSIX resources are also
+	 * cleared in the same manner.
+	 */
+	if (vsi->type != ICE_VSI_VF) {
+		/* reclaim SW interrupts back to the common pool */
+		ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx);
+		pf->num_avail_sw_msix += vsi->num_q_vectors;
+		vsi->base_vector = 0;
+	}
+
 	ice_vsi_clear_rings(vsi);
-	ice_vsi_free_arrays(vsi, false);
-	ice_dev_onetime_setup(&vsi->back->hw);
-	ice_vsi_set_num_qs(vsi);
+	ice_vsi_free_arrays(vsi);
+	ice_dev_onetime_setup(&pf->hw);
+	if (vsi->type == ICE_VSI_VF)
+		ice_vsi_set_num_qs(vsi, vf->vf_id);
+	else
+		ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID);
 	ice_vsi_set_tc_cfg(vsi);
 
 	/* Initialize VSI struct elements and create VSI in FW */
@@ -2562,7 +2976,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 	if (ret < 0)
 		goto err_vsi;
 
-	ret = ice_vsi_alloc_arrays(vsi, false);
+	ret = ice_vsi_alloc_arrays(vsi);
 	if (ret < 0)
 		goto err_vsi;
 
@@ -2572,7 +2986,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		if (ret)
 			goto err_rings;
 
-		ret = ice_vsi_setup_vector_base(vsi);
+		ret = ice_vsi_set_q_vectors_reg_idx(vsi);
 		if (ret)
 			goto err_vectors;
 
@@ -2581,6 +2995,12 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 			goto err_vectors;
 
 		ice_vsi_map_rings_to_vectors(vsi);
+		/* Do not exit if configuring RSS had an issue, at least
+		 * receive traffic on first queue. Hence no need to capture
+		 * return value
+		 */
+		if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
+			ice_vsi_cfg_rss_lut_key(vsi);
 		break;
 	case ICE_VSI_VF:
 		ret = ice_vsi_alloc_q_vectors(vsi);
@@ -2591,12 +3011,16 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		if (ret)
 			goto err_vectors;
 
+		ret = ice_vsi_set_q_vectors_reg_idx(vsi);
+		if (ret)
+			goto err_vectors;
+
 		ret = ice_vsi_alloc_rings(vsi);
 		if (ret)
 			goto err_vectors;
 
-		vsi->back->q_left_tx -= vsi->alloc_txq;
-		vsi->back->q_left_rx -= vsi->alloc_rxq;
+		pf->q_left_tx -= vsi->alloc_txq;
+		pf->q_left_rx -= vsi->alloc_rxq;
 		break;
 	default:
 		break;
@@ -2606,11 +3030,12 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
 		max_txqs[i] = pf->num_lan_tx;
 
-	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
-			      max_txqs);
-	if (ret) {
-		dev_info(&vsi->back->pdev->dev,
-			 "Failed VSI lan queue config\n");
+	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+				 max_txqs);
+	if (status) {
+		dev_err(&pf->pdev->dev,
+			"VSI %d failed lan queue config, error %d\n",
+			vsi->vsi_num, status);
 		goto err_vectors;
 	}
 	return 0;
@@ -2626,13 +3051,13 @@ err_rings:
 	}
 err_vsi:
 	ice_vsi_clear(vsi);
-	set_bit(__ICE_RESET_FAILED, vsi->back->state);
+	set_bit(__ICE_RESET_FAILED, pf->state);
 	return ret;
 }
 
 /**
  * ice_is_reset_in_progress - check for a reset in progress
- * @state: pf state field
+ * @state: PF state field
  */
 bool ice_is_reset_in_progress(unsigned long *state)
 {
@@ -2641,3 +3066,125 @@ bool ice_is_reset_in_progress(unsigned long *state)
 	       test_bit(__ICE_CORER_REQ, state) ||
 	       test_bit(__ICE_GLOBR_REQ, state);
 }
+
+#ifdef CONFIG_DCB
+/**
+ * ice_vsi_update_q_map - update our copy of the VSI info with new queue map
+ * @vsi: VSI being configured
+ * @ctx: the context buffer returned from AQ VSI update command
+ */
+static void ice_vsi_update_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctx)
+{
+	vsi->info.mapping_flags = ctx->info.mapping_flags;
+	memcpy(&vsi->info.q_mapping, &ctx->info.q_mapping,
+	       sizeof(vsi->info.q_mapping));
+	memcpy(&vsi->info.tc_mapping, ctx->info.tc_mapping,
+	       sizeof(vsi->info.tc_mapping));
+}
+
+/**
+ * ice_vsi_cfg_netdev_tc - Setup the netdev TC configuration
+ * @vsi: the VSI being configured
+ * @ena_tc: TC map to be enabled
+ */
+static void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc)
+{
+	struct net_device *netdev = vsi->netdev;
+	struct ice_pf *pf = vsi->back;
+	struct ice_dcbx_cfg *dcbcfg;
+	u8 netdev_tc;
+	int i;
+
+	if (!netdev)
+		return;
+
+	if (!ena_tc) {
+		netdev_reset_tc(netdev);
+		return;
+	}
+
+	if (netdev_set_num_tc(netdev, vsi->tc_cfg.numtc))
+		return;
+
+	dcbcfg = &pf->hw.port_info->local_dcbx_cfg;
+
+	ice_for_each_traffic_class(i)
+		if (vsi->tc_cfg.ena_tc & BIT(i))
+			netdev_set_tc_queue(netdev,
+					    vsi->tc_cfg.tc_info[i].netdev_tc,
+					    vsi->tc_cfg.tc_info[i].qcount_tx,
+					    vsi->tc_cfg.tc_info[i].qoffset);
+
+	for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) {
+		u8 ets_tc = dcbcfg->etscfg.prio_table[i];
+
+		/* Get the mapped netdev TC# for the UP */
+		netdev_tc = vsi->tc_cfg.tc_info[ets_tc].netdev_tc;
+		netdev_set_prio_tc_map(netdev, i, netdev_tc);
+	}
+}
+
+/**
+ * ice_vsi_cfg_tc - Configure VSI Tx Sched for given TC map
+ * @vsi: VSI to be configured
+ * @ena_tc: TC bitmap
+ *
+ * VSI queues expected to be quiesced before calling this function
+ */
+int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc)
+{
+	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct ice_vsi_ctx *ctx;
+	struct ice_pf *pf = vsi->back;
+	enum ice_status status;
+	int i, ret = 0;
+	u8 num_tc = 0;
+
+	ice_for_each_traffic_class(i) {
+		/* build bitmap of enabled TCs */
+		if (ena_tc & BIT(i))
+			num_tc++;
+		/* populate max_txqs per TC */
+		max_txqs[i] = pf->num_lan_tx;
+	}
+
+	vsi->tc_cfg.ena_tc = ena_tc;
+	vsi->tc_cfg.numtc = num_tc;
+
+	ctx = devm_kzalloc(&pf->pdev->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->vf_num = 0;
+	ctx->info = vsi->info;
+
+	ice_vsi_setup_q_map(vsi, ctx);
+
+	/* must to indicate which section of VSI context are being modified */
+	ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID);
+	status = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL);
+	if (status) {
+		dev_info(&pf->pdev->dev, "Failed VSI Update\n");
+		ret = -EIO;
+		goto out;
+	}
+
+	status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
+				 max_txqs);
+
+	if (status) {
+		dev_err(&pf->pdev->dev,
+			"VSI %d failed TC config, error %d\n",
+			vsi->vsi_num, status);
+		ret = -EIO;
+		goto out;
+	}
+	ice_vsi_update_q_map(vsi, ctx);
+	vsi->info.valid_sections = 0;
+
+	ice_vsi_cfg_netdev_tc(vsi, ena_tc);
+out:
+	devm_kfree(&pf->pdev->dev, ctx);
+	return ret;
+}
+#endif /* CONFIG_DCB */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 3831b4f0960a..6e43ef03bfc3 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -15,10 +15,18 @@ void ice_update_eth_stats(struct ice_vsi *vsi);
 
 int ice_vsi_cfg_rxqs(struct ice_vsi *vsi);
 
-int ice_vsi_cfg_txqs(struct ice_vsi *vsi);
+int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi);
 
 void ice_vsi_cfg_msix(struct ice_vsi *vsi);
 
+#ifdef CONFIG_PCI_IOV
+void
+ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx);
+
+void
+ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx);
+#endif /* CONFIG_PCI_IOV */
+
 int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid);
 
 int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid);
@@ -31,19 +39,28 @@ int ice_vsi_start_rx_rings(struct ice_vsi *vsi);
 
 int ice_vsi_stop_rx_rings(struct ice_vsi *vsi);
 
-int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+int
+ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 			  u16 rel_vmvf_num);
 
-int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena);
+int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc);
+
+void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create);
 
 void ice_vsi_delete(struct ice_vsi *vsi);
 
 int ice_vsi_clear(struct ice_vsi *vsi);
 
+#ifdef CONFIG_DCB
+int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc);
+#endif /* CONFIG_DCB */
+
 struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	      enum ice_vsi_type type, u16 vf_id);
 
+void ice_napi_del(struct ice_vsi *vsi);
+
 int ice_vsi_release(struct ice_vsi *vsi);
 
 void ice_vsi_close(struct ice_vsi *vsi);
@@ -59,8 +76,14 @@ bool ice_is_reset_in_progress(unsigned long *state);
 
 void ice_vsi_free_q_vectors(struct ice_vsi *vsi);
 
+void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector);
+
 void ice_vsi_put_qs(struct ice_vsi *vsi);
 
+#ifdef CONFIG_DCB
+void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi);
+#endif /* CONFIG_DCB */
+
 void ice_vsi_dis_irq(struct ice_vsi *vsi);
 
 void ice_vsi_free_irq(struct ice_vsi *vsi);
@@ -69,8 +92,7 @@ void ice_vsi_free_rx_rings(struct ice_vsi *vsi);
 
 void ice_vsi_free_tx_rings(struct ice_vsi *vsi);
 
-int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc);
-
 int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena);
 
+u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran);
 #endif /* !_ICE_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 8725569d11f0..63db08d9bafa 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -7,8 +7,9 @@
 
 #include "ice.h"
 #include "ice_lib.h"
+#include "ice_dcb_lib.h"
 
-#define DRV_VERSION	"0.7.2-k"
+#define DRV_VERSION	"0.7.4-k"
 #define DRV_SUMMARY	"Intel(R) Ethernet Connection E800 Series Linux Driver"
 const char ice_drv_ver[] = DRV_VERSION;
 static const char ice_driver_string[] = DRV_SUMMARY;
@@ -30,7 +31,6 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)");
 static struct workqueue_struct *ice_wq;
 static const struct net_device_ops ice_netdev_ops;
 
-static void ice_pf_dis_all_vsi(struct ice_pf *pf);
 static void ice_rebuild(struct ice_pf *pf);
 
 static void ice_vsi_release_all(struct ice_pf *pf);
@@ -61,9 +61,10 @@ static u32 ice_get_tx_pending(struct ice_ring *ring)
 static void ice_check_for_hang_subtask(struct ice_pf *pf)
 {
 	struct ice_vsi *vsi = NULL;
+	struct ice_hw *hw;
 	unsigned int i;
-	u32 v, v_idx;
 	int packets;
+	u32 v;
 
 	ice_for_each_vsi(pf, v)
 		if (pf->vsi[v] && pf->vsi[v]->type == ICE_VSI_PF) {
@@ -77,12 +78,12 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf)
 	if (!(vsi->netdev && netif_carrier_ok(vsi->netdev)))
 		return;
 
+	hw = &vsi->back->hw;
+
 	for (i = 0; i < vsi->num_txq; i++) {
 		struct ice_ring *tx_ring = vsi->tx_rings[i];
 
 		if (tx_ring && tx_ring->desc) {
-			int itr = ICE_ITR_NONE;
-
 			/* If packet counter has not changed the queue is
 			 * likely stalled, so force an interrupt for this
 			 * queue.
@@ -93,12 +94,7 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf)
 			packets = tx_ring->stats.pkts & INT_MAX;
 			if (tx_ring->tx_stats.prev_pkt == packets) {
 				/* Trigger sw interrupt to revive the queue */
-				v_idx = tx_ring->q_vector->v_idx;
-				wr32(&vsi->back->hw,
-				     GLINT_DYN_CTL(vsi->hw_base_vector + v_idx),
-				     (itr << GLINT_DYN_CTL_ITR_INDX_S) |
-				     GLINT_DYN_CTL_SWINT_TRIG_M |
-				     GLINT_DYN_CTL_INTENA_MSK_M);
+				ice_trigger_sw_intr(hw, tx_ring->q_vector);
 				continue;
 			}
 
@@ -113,14 +109,75 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf)
 }
 
 /**
- * ice_add_mac_to_sync_list - creates list of mac addresses to be synced
+ * ice_init_mac_fltr - Set initial MAC filters
+ * @pf: board private structure
+ *
+ * Set initial set of MAC filters for PF VSI; configure filters for permanent
+ * address and broadcast address. If an error is encountered, netdevice will be
+ * unregistered.
+ */
+static int ice_init_mac_fltr(struct ice_pf *pf)
+{
+	LIST_HEAD(tmp_add_list);
+	u8 broadcast[ETH_ALEN];
+	struct ice_vsi *vsi;
+	int status;
+
+	vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF);
+	if (!vsi)
+		return -EINVAL;
+
+	/* To add a MAC filter, first add the MAC to a list and then
+	 * pass the list to ice_add_mac.
+	 */
+
+	 /* Add a unicast MAC filter so the VSI can get its packets */
+	status = ice_add_mac_to_list(vsi, &tmp_add_list,
+				     vsi->port_info->mac.perm_addr);
+	if (status)
+		goto unregister;
+
+	/* VSI needs to receive broadcast traffic, so add the broadcast
+	 * MAC address to the list as well.
+	 */
+	eth_broadcast_addr(broadcast);
+	status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast);
+	if (status)
+		goto free_mac_list;
+
+	/* Program MAC filters for entries in tmp_add_list */
+	status = ice_add_mac(&pf->hw, &tmp_add_list);
+	if (status)
+		status = -ENOMEM;
+
+free_mac_list:
+	ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
+
+unregister:
+	/* We aren't useful with no MAC filters, so unregister if we
+	 * had an error
+	 */
+	if (status && vsi->netdev->reg_state == NETREG_REGISTERED) {
+		dev_err(&pf->pdev->dev,
+			"Could not add MAC filters error %d. Unregistering device\n",
+			status);
+		unregister_netdev(vsi->netdev);
+		free_netdev(vsi->netdev);
+		vsi->netdev = NULL;
+	}
+
+	return status;
+}
+
+/**
+ * ice_add_mac_to_sync_list - creates list of MAC addresses to be synced
  * @netdev: the net device on which the sync is happening
- * @addr: mac address to sync
+ * @addr: MAC address to sync
  *
  * This is a callback function which is called by the in kernel device sync
  * functions (like __dev_uc_sync, __dev_mc_sync, etc). This function only
  * populates the tmp_sync_list, which is later used by ice_add_mac to add the
- * mac filters from the hardware.
+ * MAC filters from the hardware.
  */
 static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
 {
@@ -134,14 +191,14 @@ static int ice_add_mac_to_sync_list(struct net_device *netdev, const u8 *addr)
 }
 
 /**
- * ice_add_mac_to_unsync_list - creates list of mac addresses to be unsynced
+ * ice_add_mac_to_unsync_list - creates list of MAC addresses to be unsynced
  * @netdev: the net device on which the unsync is happening
- * @addr: mac address to unsync
+ * @addr: MAC address to unsync
  *
  * This is a callback function which is called by the in kernel device unsync
  * functions (like __dev_uc_unsync, __dev_mc_unsync, etc). This function only
  * populates the tmp_unsync_list, which is later used by ice_remove_mac to
- * delete the mac filters from the hardware.
+ * delete the MAC filters from the hardware.
  */
 static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr)
 {
@@ -168,6 +225,39 @@ static bool ice_vsi_fltr_changed(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_cfg_promisc - Enable or disable promiscuous mode for a given PF
+ * @vsi: the VSI being configured
+ * @promisc_m: mask of promiscuous config bits
+ * @set_promisc: enable or disable promisc flag request
+ *
+ */
+static int ice_cfg_promisc(struct ice_vsi *vsi, u8 promisc_m, bool set_promisc)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	enum ice_status status = 0;
+
+	if (vsi->type != ICE_VSI_PF)
+		return 0;
+
+	if (vsi->vlan_ena) {
+		status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m,
+						  set_promisc);
+	} else {
+		if (set_promisc)
+			status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m,
+						     0);
+		else
+			status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m,
+						       0);
+	}
+
+	if (status)
+		return -EIO;
+
+	return 0;
+}
+
+/**
  * ice_vsi_sync_fltr - Update the VSI filter list to the HW
  * @vsi: ptr to the VSI
  *
@@ -182,6 +272,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 	struct ice_hw *hw = &pf->hw;
 	enum ice_status status = 0;
 	u32 changed_flags = 0;
+	u8 promisc_m;
 	int err = 0;
 
 	if (!vsi->netdev)
@@ -211,7 +302,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		netif_addr_unlock_bh(netdev);
 	}
 
-	/* Remove mac addresses in the unsync list */
+	/* Remove MAC addresses in the unsync list */
 	status = ice_remove_mac(hw, &vsi->tmp_unsync_list);
 	ice_free_fltr_list(dev, &vsi->tmp_unsync_list);
 	if (status) {
@@ -223,12 +314,16 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		}
 	}
 
-	/* Add mac addresses in the sync list */
+	/* Add MAC addresses in the sync list */
 	status = ice_add_mac(hw, &vsi->tmp_sync_list);
 	ice_free_fltr_list(dev, &vsi->tmp_sync_list);
-	if (status) {
+	/* If filter is added successfully or already exists, do not go into
+	 * 'if' condition and report it as error. Instead continue processing
+	 * rest of the function.
+	 */
+	if (status && status != ICE_ERR_ALREADY_EXISTS) {
 		netdev_err(netdev, "Failed to add MAC filters\n");
-		/* If there is no more space for new umac filters, vsi
+		/* If there is no more space for new umac filters, VSI
 		 * should go into promiscuous mode. There should be some
 		 * space reserved for promiscuous filters.
 		 */
@@ -245,49 +340,56 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		}
 	}
 	/* check for changes in promiscuous modes */
-	if (changed_flags & IFF_ALLMULTI)
-		netdev_warn(netdev, "Unsupported configuration\n");
+	if (changed_flags & IFF_ALLMULTI) {
+		if (vsi->current_netdev_flags & IFF_ALLMULTI) {
+			if (vsi->vlan_ena)
+				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
+			else
+				promisc_m = ICE_MCAST_PROMISC_BITS;
+
+			err = ice_cfg_promisc(vsi, promisc_m, true);
+			if (err) {
+				netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n",
+					   vsi->vsi_num);
+				vsi->current_netdev_flags &= ~IFF_ALLMULTI;
+				goto out_promisc;
+			}
+		} else if (!(vsi->current_netdev_flags & IFF_ALLMULTI)) {
+			if (vsi->vlan_ena)
+				promisc_m = ICE_MCAST_VLAN_PROMISC_BITS;
+			else
+				promisc_m = ICE_MCAST_PROMISC_BITS;
+
+			err = ice_cfg_promisc(vsi, promisc_m, false);
+			if (err) {
+				netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n",
+					   vsi->vsi_num);
+				vsi->current_netdev_flags |= IFF_ALLMULTI;
+				goto out_promisc;
+			}
+		}
+	}
 
 	if (((changed_flags & IFF_PROMISC) || promisc_forced_on) ||
 	    test_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags)) {
 		clear_bit(ICE_VSI_FLAG_PROMISC_CHANGED, vsi->flags);
 		if (vsi->current_netdev_flags & IFF_PROMISC) {
-			/* Apply TX filter rule to get traffic from VMs */
-			status = ice_cfg_dflt_vsi(hw, vsi->idx, true,
-						  ICE_FLTR_TX);
-			if (status) {
-				netdev_err(netdev, "Error setting default VSI %i tx rule\n",
-					   vsi->vsi_num);
-				vsi->current_netdev_flags &= ~IFF_PROMISC;
-				err = -EIO;
-				goto out_promisc;
-			}
-			/* Apply RX filter rule to get traffic from wire */
+			/* Apply Rx filter rule to get traffic from wire */
 			status = ice_cfg_dflt_vsi(hw, vsi->idx, true,
 						  ICE_FLTR_RX);
 			if (status) {
-				netdev_err(netdev, "Error setting default VSI %i rx rule\n",
+				netdev_err(netdev, "Error setting default VSI %i Rx rule\n",
 					   vsi->vsi_num);
 				vsi->current_netdev_flags &= ~IFF_PROMISC;
 				err = -EIO;
 				goto out_promisc;
 			}
 		} else {
-			/* Clear TX filter rule to stop traffic from VMs */
-			status = ice_cfg_dflt_vsi(hw, vsi->idx, false,
-						  ICE_FLTR_TX);
-			if (status) {
-				netdev_err(netdev, "Error clearing default VSI %i tx rule\n",
-					   vsi->vsi_num);
-				vsi->current_netdev_flags |= IFF_PROMISC;
-				err = -EIO;
-				goto out_promisc;
-			}
-			/* Clear RX filter to remove traffic from wire */
+			/* Clear Rx filter to remove traffic from wire */
 			status = ice_cfg_dflt_vsi(hw, vsi->idx, false,
 						  ICE_FLTR_RX);
 			if (status) {
-				netdev_err(netdev, "Error clearing default VSI %i rx rule\n",
+				netdev_err(netdev, "Error clearing default VSI %i Rx rule\n",
 					   vsi->vsi_num);
 				vsi->current_netdev_flags |= IFF_PROMISC;
 				err = -EIO;
@@ -322,7 +424,7 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf)
 
 	clear_bit(ICE_FLAG_FLTR_SYNC, pf->flags);
 
-	for (v = 0; v < pf->num_alloc_vsi; v++)
+	ice_for_each_vsi(pf, v)
 		if (pf->vsi[v] && ice_vsi_fltr_changed(pf->vsi[v]) &&
 		    ice_vsi_sync_fltr(pf->vsi[v])) {
 			/* come back and try again later */
@@ -332,6 +434,51 @@ static void ice_sync_fltr_subtask(struct ice_pf *pf)
 }
 
 /**
+ * ice_dis_vsi - pause a VSI
+ * @vsi: the VSI being paused
+ * @locked: is the rtnl_lock already held
+ */
+static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
+{
+	if (test_bit(__ICE_DOWN, vsi->state))
+		return;
+
+	set_bit(__ICE_NEEDS_RESTART, vsi->state);
+
+	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
+		if (netif_running(vsi->netdev)) {
+			if (!locked) {
+				rtnl_lock();
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+				rtnl_unlock();
+			} else {
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+			}
+		} else {
+			ice_vsi_close(vsi);
+		}
+	}
+}
+
+/**
+ * ice_pf_dis_all_vsi - Pause all VSIs on a PF
+ * @pf: the PF
+ * @locked: is the rtnl_lock already held
+ */
+#ifdef CONFIG_DCB
+void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
+#else
+static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
+#endif /* CONFIG_DCB */
+{
+	int v;
+
+	ice_for_each_vsi(pf, v)
+		if (pf->vsi[v])
+			ice_dis_vsi(pf->vsi[v], locked);
+}
+
+/**
  * ice_prepare_for_reset - prep for the core to reset
  * @pf: board private structure
  *
@@ -342,12 +489,16 @@ ice_prepare_for_reset(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
 
+	/* already prepared for reset */
+	if (test_bit(__ICE_PREPARED_FOR_RESET, pf->state))
+		return;
+
 	/* Notify VFs of impending reset */
 	if (ice_check_sq_alive(hw, &hw->mailboxq))
 		ice_vc_notify_reset(pf);
 
 	/* disable the VSIs and their queues that are not already DOWN */
-	ice_pf_dis_all_vsi(pf);
+	ice_pf_dis_all_vsi(pf, false);
 
 	if (hw->port_info)
 		ice_sched_clear_port(hw->port_info);
@@ -394,6 +545,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 		ice_rebuild(pf);
 		clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
 		clear_bit(__ICE_PFR_REQ, pf->state);
+		ice_reset_all_vfs(pf, true);
 	}
 }
 
@@ -416,10 +568,15 @@ static void ice_reset_subtask(struct ice_pf *pf)
 	 * for the reset now), poll for reset done, rebuild and return.
 	 */
 	if (test_bit(__ICE_RESET_OICR_RECV, pf->state)) {
-		clear_bit(__ICE_GLOBR_RECV, pf->state);
-		clear_bit(__ICE_CORER_RECV, pf->state);
-		if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state))
-			ice_prepare_for_reset(pf);
+		/* Perform the largest reset requested */
+		if (test_and_clear_bit(__ICE_CORER_RECV, pf->state))
+			reset_type = ICE_RESET_CORER;
+		if (test_and_clear_bit(__ICE_GLOBR_RECV, pf->state))
+			reset_type = ICE_RESET_GLOBR;
+		/* return if no valid reset type requested */
+		if (reset_type == ICE_RESET_INVAL)
+			return;
+		ice_prepare_for_reset(pf);
 
 		/* make sure we are ready to rebuild */
 		if (ice_check_reset(&pf->hw)) {
@@ -429,13 +586,14 @@ static void ice_reset_subtask(struct ice_pf *pf)
 			pf->hw.reset_ongoing = false;
 			ice_rebuild(pf);
 			/* clear bit to resume normal operations, but
-			 * ICE_NEEDS_RESTART bit is set incase rebuild failed
+			 * ICE_NEEDS_RESTART bit is set in case rebuild failed
 			 */
 			clear_bit(__ICE_RESET_OICR_RECV, pf->state);
 			clear_bit(__ICE_PREPARED_FOR_RESET, pf->state);
 			clear_bit(__ICE_PFR_REQ, pf->state);
 			clear_bit(__ICE_CORER_REQ, pf->state);
 			clear_bit(__ICE_GLOBR_REQ, pf->state);
+			ice_reset_all_vfs(pf, true);
 		}
 
 		return;
@@ -466,9 +624,16 @@ static void ice_reset_subtask(struct ice_pf *pf)
  */
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 {
+	struct ice_aqc_get_phy_caps_data *caps;
+	enum ice_status status;
+	const char *fec_req;
 	const char *speed;
+	const char *fec;
 	const char *fc;
 
+	if (!vsi)
+		return;
+
 	if (vsi->current_isup == isup)
 		return;
 
@@ -480,6 +645,12 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 	}
 
 	switch (vsi->port_info->phy.link_info.link_speed) {
+	case ICE_AQ_LINK_SPEED_100GB:
+		speed = "100 G";
+		break;
+	case ICE_AQ_LINK_SPEED_50GB:
+		speed = "50 G";
+		break;
 	case ICE_AQ_LINK_SPEED_40GB:
 		speed = "40 G";
 		break;
@@ -511,39 +682,82 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 
 	switch (vsi->port_info->fc.current_mode) {
 	case ICE_FC_FULL:
-		fc = "RX/TX";
+		fc = "Rx/Tx";
 		break;
 	case ICE_FC_TX_PAUSE:
-		fc = "TX";
+		fc = "Tx";
 		break;
 	case ICE_FC_RX_PAUSE:
-		fc = "RX";
+		fc = "Rx";
+		break;
+	case ICE_FC_NONE:
+		fc = "None";
 		break;
 	default:
 		fc = "Unknown";
 		break;
 	}
 
-	netdev_info(vsi->netdev, "NIC Link is up %sbps, Flow Control: %s\n",
-		    speed, fc);
+	/* Get FEC mode based on negotiated link info */
+	switch (vsi->port_info->phy.link_info.fec_info) {
+	case ICE_AQ_LINK_25G_RS_528_FEC_EN:
+		/* fall through */
+	case ICE_AQ_LINK_25G_RS_544_FEC_EN:
+		fec = "RS-FEC";
+		break;
+	case ICE_AQ_LINK_25G_KR_FEC_EN:
+		fec = "FC-FEC/BASE-R";
+		break;
+	default:
+		fec = "NONE";
+		break;
+	}
+
+	/* Get FEC mode requested based on PHY caps last SW configuration */
+	caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL);
+	if (!caps) {
+		fec_req = "Unknown";
+		goto done;
+	}
+
+	status = ice_aq_get_phy_caps(vsi->port_info, false,
+				     ICE_AQC_REPORT_SW_CFG, caps, NULL);
+	if (status)
+		netdev_info(vsi->netdev, "Get phy capability failed.\n");
+
+	if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_528_REQ ||
+	    caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ)
+		fec_req = "RS-FEC";
+	else if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ ||
+		 caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_REQ)
+		fec_req = "FC-FEC/BASE-R";
+	else
+		fec_req = "NONE";
+
+	devm_kfree(&vsi->back->pdev->dev, caps);
+
+done:
+	netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Flow Control: %s\n",
+		    speed, fec_req, fec, fc);
 }
 
 /**
- * ice_vsi_link_event - update the vsi's netdev
- * @vsi: the vsi on which the link event occurred
- * @link_up: whether or not the vsi needs to be set up or down
+ * ice_vsi_link_event - update the VSI's netdev
+ * @vsi: the VSI on which the link event occurred
+ * @link_up: whether or not the VSI needs to be set up or down
  */
 static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up)
 {
-	if (!vsi || test_bit(__ICE_DOWN, vsi->state))
+	if (!vsi)
+		return;
+
+	if (test_bit(__ICE_DOWN, vsi->state) || !vsi->netdev)
 		return;
 
 	if (vsi->type == ICE_VSI_PF) {
-		if (!vsi->netdev) {
-			dev_dbg(&vsi->back->pdev->dev,
-				"vsi->netdev is not initialized!\n");
+		if (link_up == netif_carrier_ok(vsi->netdev))
 			return;
-		}
+
 		if (link_up) {
 			netif_carrier_on(vsi->netdev);
 			netif_tx_wake_all_queues(vsi->netdev);
@@ -556,62 +770,53 @@ static void ice_vsi_link_event(struct ice_vsi *vsi, bool link_up)
 
 /**
  * ice_link_event - process the link event
- * @pf: pf that the link event is associated with
+ * @pf: PF that the link event is associated with
  * @pi: port_info for the port that the link event is associated with
+ * @link_up: true if the physical link is up and false if it is down
+ * @link_speed: current link speed received from the link event
  *
- * Returns -EIO if ice_get_link_status() fails
- * Returns 0 on success
+ * Returns 0 on success and negative on failure
  */
 static int
-ice_link_event(struct ice_pf *pf, struct ice_port_info *pi)
+ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
+	       u16 link_speed)
 {
-	u8 new_link_speed, old_link_speed;
 	struct ice_phy_info *phy_info;
-	bool new_link_same_as_old;
-	bool new_link, old_link;
-	u8 lport;
-	u16 v;
+	struct ice_vsi *vsi;
+	u16 old_link_speed;
+	bool old_link;
+	int result;
 
 	phy_info = &pi->phy;
 	phy_info->link_info_old = phy_info->link_info;
-	/* Force ice_get_link_status() to update link info */
-	phy_info->get_link_info = true;
 
-	old_link = (phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
+	old_link = !!(phy_info->link_info_old.link_info & ICE_AQ_LINK_UP);
 	old_link_speed = phy_info->link_info_old.link_speed;
 
-	lport = pi->lport;
-	if (ice_get_link_status(pi, &new_link)) {
+	/* update the link info structures and re-enable link events,
+	 * don't bail on failure due to other book keeping needed
+	 */
+	result = ice_update_link_info(pi);
+	if (result)
 		dev_dbg(&pf->pdev->dev,
-			"Could not get link status for port %d\n", lport);
-		return -EIO;
-	}
-
-	new_link_speed = phy_info->link_info.link_speed;
-
-	new_link_same_as_old = (new_link == old_link &&
-				new_link_speed == old_link_speed);
+			"Failed to update link status and re-enable link events for port %d\n",
+			pi->lport);
 
-	ice_for_each_vsi(pf, v) {
-		struct ice_vsi *vsi = pf->vsi[v];
-
-		if (!vsi || !vsi->port_info)
-			continue;
+	/* if the old link up/down and speed is the same as the new */
+	if (link_up == old_link && link_speed == old_link_speed)
+		return result;
 
-		if (new_link_same_as_old &&
-		    (test_bit(__ICE_DOWN, vsi->state) ||
-		    new_link == netif_carrier_ok(vsi->netdev)))
-			continue;
+	vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF);
+	if (!vsi || !vsi->port_info)
+		return -EINVAL;
 
-		if (vsi->port_info->lport == lport) {
-			ice_print_link_msg(vsi, new_link);
-			ice_vsi_link_event(vsi, new_link);
-		}
-	}
+	ice_vsi_link_event(vsi, link_up);
+	ice_print_link_msg(vsi, link_up);
 
-	ice_vc_notify_link_state(pf);
+	if (pf->num_alloc_vfs)
+		ice_vc_notify_link_state(pf);
 
-	return 0;
+	return result;
 }
 
 /**
@@ -634,19 +839,73 @@ static void ice_watchdog_subtask(struct ice_pf *pf)
 
 	pf->serv_tmr_prev = jiffies;
 
-	if (ice_link_event(pf, pf->hw.port_info))
-		dev_dbg(&pf->pdev->dev, "ice_link_event failed\n");
-
 	/* Update the stats for active netdevs so the network stack
 	 * can look at updated numbers whenever it cares to
 	 */
 	ice_update_pf_stats(pf);
-	for (i = 0; i < pf->num_alloc_vsi; i++)
+	ice_for_each_vsi(pf, i)
 		if (pf->vsi[i] && pf->vsi[i]->netdev)
 			ice_update_vsi_stats(pf->vsi[i]);
 }
 
 /**
+ * ice_init_link_events - enable/initialize link events
+ * @pi: pointer to the port_info instance
+ *
+ * Returns -EIO on failure, 0 on success
+ */
+static int ice_init_link_events(struct ice_port_info *pi)
+{
+	u16 mask;
+
+	mask = ~((u16)(ICE_AQ_LINK_EVENT_UPDOWN | ICE_AQ_LINK_EVENT_MEDIA_NA |
+		       ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL));
+
+	if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) {
+		dev_dbg(ice_hw_to_dev(pi->hw),
+			"Failed to set link event mask for port %d\n",
+			pi->lport);
+		return -EIO;
+	}
+
+	if (ice_aq_get_link_info(pi, true, NULL, NULL)) {
+		dev_dbg(ice_hw_to_dev(pi->hw),
+			"Failed to enable link events for port %d\n",
+			pi->lport);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_handle_link_event - handle link event via ARQ
+ * @pf: PF that the link event is associated with
+ * @event: event structure containing link status info
+ */
+static int
+ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+	struct ice_aqc_get_link_status_data *link_data;
+	struct ice_port_info *port_info;
+	int status;
+
+	link_data = (struct ice_aqc_get_link_status_data *)event->msg_buf;
+	port_info = pf->hw.port_info;
+	if (!port_info)
+		return -EINVAL;
+
+	status = ice_link_event(pf, port_info,
+				!!(link_data->link_info & ICE_AQ_LINK_UP),
+				le16_to_cpu(link_data->link_speed));
+	if (status)
+		dev_dbg(&pf->pdev->dev,
+			"Could not process link event, error %d\n", status);
+
+	return status;
+}
+
+/**
  * __ice_clean_ctrlq - helper function to clean controlq rings
  * @pf: ptr to struct ice_pf
  * @q_type: specific Control queue type
@@ -749,12 +1008,20 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		opcode = le16_to_cpu(event.desc.opcode);
 
 		switch (opcode) {
+		case ice_aqc_opc_get_link_status:
+			if (ice_handle_link_event(pf, &event))
+				dev_err(&pf->pdev->dev,
+					"Could not handle link event\n");
+			break;
 		case ice_mbx_opc_send_msg_to_pf:
 			ice_vc_process_vf_msg(pf, &event);
 			break;
 		case ice_aqc_opc_fw_logging:
 			ice_output_fw_log(hw, &event.desc, event.msg_buf);
 			break;
+		case ice_aqc_opc_lldp_set_mib_change:
+			ice_dcb_process_lldp_set_mib_change(pf, &event);
+			break;
 		default:
 			dev_dbg(&pf->pdev->dev,
 				"%s Receive Queue unknown event 0x%04x ignored\n",
@@ -876,6 +1143,18 @@ static void ice_service_task_stop(struct ice_pf *pf)
 }
 
 /**
+ * ice_service_task_restart - restart service task and schedule works
+ * @pf: board private structure
+ *
+ * This function is needed for suspend and resume works (e.g WoL scenario)
+ */
+static void ice_service_task_restart(struct ice_pf *pf)
+{
+	clear_bit(__ICE_SERVICE_DIS, pf->state);
+	ice_service_task_schedule(pf);
+}
+
+/**
  * ice_service_timer - timer callback to schedule service task
  * @t: pointer to timer_list
  */
@@ -900,7 +1179,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 	u32 reg;
 	int i;
 
-	if (!test_bit(__ICE_MDD_EVENT_PENDING, pf->state))
+	if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state))
 		return;
 
 	/* find what triggered the MDD event */
@@ -988,14 +1267,16 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		}
 	}
 
-	/* see if one of the VFs needs to be reset */
-	for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) {
+	/* check to see if one of the VFs caused the MDD */
+	for (i = 0; i < pf->num_alloc_vfs; i++) {
 		struct ice_vf *vf = &pf->vf[i];
 
+		bool vf_mdd_detected = false;
+
 		reg = rd32(hw, VP_MDET_TX_PQM(i));
 		if (reg & VP_MDET_TX_PQM_VALID_M) {
 			wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF);
-			vf->num_mdd_events++;
+			vf_mdd_detected = true;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
@@ -1003,7 +1284,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		reg = rd32(hw, VP_MDET_TX_TCLAN(i));
 		if (reg & VP_MDET_TX_TCLAN_VALID_M) {
 			wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF);
-			vf->num_mdd_events++;
+			vf_mdd_detected = true;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
@@ -1011,7 +1292,7 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		reg = rd32(hw, VP_MDET_TX_TDPU(i));
 		if (reg & VP_MDET_TX_TDPU_VALID_M) {
 			wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF);
-			vf->num_mdd_events++;
+			vf_mdd_detected = true;
 			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
 				 i);
 		}
@@ -1019,26 +1300,18 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
 		reg = rd32(hw, VP_MDET_RX(i));
 		if (reg & VP_MDET_RX_VALID_M) {
 			wr32(hw, VP_MDET_RX(i), 0xFFFF);
-			vf->num_mdd_events++;
+			vf_mdd_detected = true;
 			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
 				 i);
 		}
 
-		if (vf->num_mdd_events > ICE_DFLT_NUM_MDD_EVENTS_ALLOWED) {
-			dev_info(&pf->pdev->dev,
-				 "Too many MDD events on VF %d, disabled\n", i);
-			dev_info(&pf->pdev->dev,
-				 "Use PF Control I/F to re-enable the VF\n");
-			set_bit(ICE_VF_STATE_DIS, vf->vf_states);
+		if (vf_mdd_detected) {
+			vf->num_mdd_events++;
+			if (vf->num_mdd_events > 1)
+				dev_info(&pf->pdev->dev, "VF %d has had %llu MDD events since last boot\n",
+					 i, vf->num_mdd_events);
 		}
 	}
-
-	/* re-enable MDD interrupt cause */
-	clear_bit(__ICE_MDD_EVENT_PENDING, pf->state);
-	reg = rd32(hw, PFINT_OICR_ENA);
-	reg |= PFINT_OICR_MAL_DETECT_M;
-	wr32(hw, PFINT_OICR_ENA, reg);
-	ice_flush(hw);
 }
 
 /**
@@ -1088,7 +1361,7 @@ static void ice_service_task(struct work_struct *work)
 
 /**
  * ice_set_ctrlq_len - helper function to set controlq length
- * @hw: pointer to the hw instance
+ * @hw: pointer to the HW instance
  */
 static void ice_set_ctrlq_len(struct ice_hw *hw)
 {
@@ -1110,8 +1383,9 @@ static void ice_set_ctrlq_len(struct ice_hw *hw)
  * This is a callback function used by the irq_set_affinity_notifier function
  * so that we may register to receive changes to the irq affinity masks.
  */
-static void ice_irq_affinity_notify(struct irq_affinity_notify *notify,
-				    const cpumask_t *mask)
+static void
+ice_irq_affinity_notify(struct irq_affinity_notify *notify,
+			const cpumask_t *mask)
 {
 	struct ice_q_vector *q_vector =
 		container_of(notify, struct ice_q_vector, affinity_notify);
@@ -1141,7 +1415,7 @@ static int ice_vsi_ena_irq(struct ice_vsi *vsi)
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
 		int i;
 
-		for (i = 0; i < vsi->num_q_vectors; i++)
+		ice_for_each_q_vector(vsi, i)
 			ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]);
 	}
 
@@ -1158,7 +1432,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 {
 	int q_vectors = vsi->num_q_vectors;
 	struct ice_pf *pf = vsi->back;
-	int base = vsi->sw_base_vector;
+	int base = vsi->base_vector;
 	int rx_int_idx = 0;
 	int tx_int_idx = 0;
 	int vector, err;
@@ -1183,10 +1457,9 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 			/* skip this unused q_vector */
 			continue;
 		}
-		err = devm_request_irq(&pf->pdev->dev,
-				       pf->msix_entries[base + vector].vector,
-				       vsi->irq_handler, 0, q_vector->name,
-				       q_vector);
+		err = devm_request_irq(&pf->pdev->dev, irq_num,
+				       vsi->irq_handler, 0,
+				       q_vector->name, q_vector);
 		if (err) {
 			netdev_err(vsi->netdev,
 				   "MSIX request_irq failed, error: %d\n", err);
@@ -1240,7 +1513,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 	wr32(hw, PFINT_OICR_ENA, val);
 
 	/* SW_ITR_IDX = 0, but don't change INTENA */
-	wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx),
+	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
 	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
 }
 
@@ -1262,6 +1535,11 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 	oicr = rd32(hw, PFINT_OICR);
 	ena_mask = rd32(hw, PFINT_OICR_ENA);
 
+	if (oicr & PFINT_OICR_SWINT_M) {
+		ena_mask &= ~PFINT_OICR_SWINT_M;
+		pf->sw_int_count++;
+	}
+
 	if (oicr & PFINT_OICR_MAL_DETECT_M) {
 		ena_mask &= ~PFINT_OICR_MAL_DETECT_M;
 		set_bit(__ICE_MDD_EVENT_PENDING, pf->state);
@@ -1327,7 +1605,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 			rd32(hw, PFHMC_ERRORDATA));
 	}
 
-	/* Report and mask off any remaining unexpected interrupts */
+	/* Report any remaining unexpected interrupts */
 	oicr &= ena_mask;
 	if (oicr) {
 		dev_dbg(&pf->pdev->dev, "unhandled interrupt oicr=0x%08x\n",
@@ -1341,12 +1619,9 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 			set_bit(__ICE_PFR_REQ, pf->state);
 			ice_service_task_schedule(pf);
 		}
-		ena_mask &= ~oicr;
 	}
 	ret = IRQ_HANDLED;
 
-	/* re-enable interrupt causes that are not handled during this pass */
-	wr32(hw, PFINT_OICR_ENA, ena_mask);
 	if (!test_bit(__ICE_DOWN, pf->state)) {
 		ice_service_task_schedule(pf);
 		ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -1356,25 +1631,74 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 }
 
 /**
+ * ice_dis_ctrlq_interrupts - disable control queue interrupts
+ * @hw: pointer to HW structure
+ */
+static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
+{
+	/* disable Admin queue Interrupt causes */
+	wr32(hw, PFINT_FW_CTL,
+	     rd32(hw, PFINT_FW_CTL) & ~PFINT_FW_CTL_CAUSE_ENA_M);
+
+	/* disable Mailbox queue Interrupt causes */
+	wr32(hw, PFINT_MBX_CTL,
+	     rd32(hw, PFINT_MBX_CTL) & ~PFINT_MBX_CTL_CAUSE_ENA_M);
+
+	/* disable Control queue Interrupt causes */
+	wr32(hw, PFINT_OICR_CTL,
+	     rd32(hw, PFINT_OICR_CTL) & ~PFINT_OICR_CTL_CAUSE_ENA_M);
+
+	ice_flush(hw);
+}
+
+/**
  * ice_free_irq_msix_misc - Unroll misc vector setup
  * @pf: board private structure
  */
 static void ice_free_irq_msix_misc(struct ice_pf *pf)
 {
+	struct ice_hw *hw = &pf->hw;
+
+	ice_dis_ctrlq_interrupts(hw);
+
 	/* disable OICR interrupt */
-	wr32(&pf->hw, PFINT_OICR_ENA, 0);
-	ice_flush(&pf->hw);
+	wr32(hw, PFINT_OICR_ENA, 0);
+	ice_flush(hw);
 
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) {
-		synchronize_irq(pf->msix_entries[pf->sw_oicr_idx].vector);
+		synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
 		devm_free_irq(&pf->pdev->dev,
-			      pf->msix_entries[pf->sw_oicr_idx].vector, pf);
+			      pf->msix_entries[pf->oicr_idx].vector, pf);
 	}
 
 	pf->num_avail_sw_msix += 1;
-	ice_free_res(pf->sw_irq_tracker, pf->sw_oicr_idx, ICE_RES_MISC_VEC_ID);
-	pf->num_avail_hw_msix += 1;
-	ice_free_res(pf->hw_irq_tracker, pf->hw_oicr_idx, ICE_RES_MISC_VEC_ID);
+	ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID);
+}
+
+/**
+ * ice_ena_ctrlq_interrupts - enable control queue interrupts
+ * @hw: pointer to HW structure
+ * @reg_idx: HW vector index to associate the control queue interrupts with
+ */
+static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
+{
+	u32 val;
+
+	val = ((reg_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
+	       PFINT_OICR_CTL_CAUSE_ENA_M);
+	wr32(hw, PFINT_OICR_CTL, val);
+
+	/* enable Admin queue Interrupt causes */
+	val = ((reg_idx & PFINT_FW_CTL_MSIX_INDX_M) |
+	       PFINT_FW_CTL_CAUSE_ENA_M);
+	wr32(hw, PFINT_FW_CTL, val);
+
+	/* enable Mailbox queue Interrupt causes */
+	val = ((reg_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
+	       PFINT_MBX_CTL_CAUSE_ENA_M);
+	wr32(hw, PFINT_MBX_CTL, val);
+
+	ice_flush(hw);
 }
 
 /**
@@ -1389,8 +1713,6 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
 	int oicr_idx, err = 0;
-	u8 itr_gran;
-	u32 val;
 
 	if (!pf->int_name[0])
 		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
@@ -1404,59 +1726,32 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 	if (ice_is_reset_in_progress(pf->state))
 		goto skip_req_irq;
 
-	/* reserve one vector in sw_irq_tracker for misc interrupts */
-	oicr_idx = ice_get_res(pf, pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+	/* reserve one vector in irq_tracker for misc interrupts */
+	oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
 	if (oicr_idx < 0)
 		return oicr_idx;
 
 	pf->num_avail_sw_msix -= 1;
-	pf->sw_oicr_idx = oicr_idx;
-
-	/* reserve one vector in hw_irq_tracker for misc interrupts */
-	oicr_idx = ice_get_res(pf, pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
-	if (oicr_idx < 0) {
-		ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
-		pf->num_avail_sw_msix += 1;
-		return oicr_idx;
-	}
-	pf->num_avail_hw_msix -= 1;
-	pf->hw_oicr_idx = oicr_idx;
+	pf->oicr_idx = oicr_idx;
 
 	err = devm_request_irq(&pf->pdev->dev,
-			       pf->msix_entries[pf->sw_oicr_idx].vector,
+			       pf->msix_entries[pf->oicr_idx].vector,
 			       ice_misc_intr, 0, pf->int_name, pf);
 	if (err) {
 		dev_err(&pf->pdev->dev,
 			"devm_request_irq for %s failed: %d\n",
 			pf->int_name, err);
-		ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+		ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
 		pf->num_avail_sw_msix += 1;
-		ice_free_res(pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
-		pf->num_avail_hw_msix += 1;
 		return err;
 	}
 
 skip_req_irq:
 	ice_ena_misc_vector(pf);
 
-	val = ((pf->hw_oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
-	       PFINT_OICR_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_OICR_CTL, val);
-
-	/* This enables Admin queue Interrupt causes */
-	val = ((pf->hw_oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) |
-	       PFINT_FW_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_FW_CTL, val);
-
-	/* This enables Mailbox queue Interrupt causes */
-	val = ((pf->hw_oicr_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
-	       PFINT_MBX_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_MBX_CTL, val);
-
-	itr_gran = hw->itr_gran;
-
-	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->hw_oicr_idx),
-	     ITR_TO_REG(ICE_ITR_8K, itr_gran));
+	ice_ena_ctrlq_interrupts(hw, pf->oicr_idx);
+	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx),
+	     ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
 
 	ice_flush(hw);
 	ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -1465,21 +1760,6 @@ skip_req_irq:
 }
 
 /**
- * ice_napi_del - Remove NAPI handler for the VSI
- * @vsi: VSI for which NAPI handler is to be removed
- */
-void ice_napi_del(struct ice_vsi *vsi)
-{
-	int v_idx;
-
-	if (!vsi->netdev)
-		return;
-
-	for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++)
-		netif_napi_del(&vsi->q_vectors[v_idx]->napi);
-}
-
-/**
  * ice_napi_add - register NAPI handler for the VSI
  * @vsi: VSI for which NAPI handler is to be registered
  *
@@ -1494,7 +1774,7 @@ static void ice_napi_add(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (v_idx = 0; v_idx < vsi->num_q_vectors; v_idx++)
+	ice_for_each_q_vector(vsi, v_idx)
 		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
 			       ice_napi_poll, NAPI_POLL_WEIGHT);
 }
@@ -1516,8 +1796,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 	u8 mac_addr[ETH_ALEN];
 	int err;
 
-	netdev = alloc_etherdev_mqs(sizeof(struct ice_netdev_priv),
-				    vsi->alloc_txq, vsi->alloc_rxq);
+	netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
+				    vsi->alloc_rxq);
 	if (!netdev)
 		return -ENOMEM;
 
@@ -1531,6 +1811,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 
 	csumo_features = NETIF_F_RXCSUM	  |
 			 NETIF_F_IP_CSUM  |
+			 NETIF_F_SCTP_CRC |
 			 NETIF_F_IPV6_CSUM;
 
 	vlano_features = NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -1603,8 +1884,8 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size)
  * @pf: board private structure
  * @pi: pointer to the port_info instance
  *
- * Returns pointer to the successfully allocated VSI sw struct on success,
- * otherwise returns NULL on failure.
+ * Returns pointer to the successfully allocated VSI software struct
+ * on success, otherwise returns NULL on failure.
  */
 static struct ice_vsi *
 ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
@@ -1613,18 +1894,34 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
 }
 
 /**
- * ice_vlan_rx_add_vid - Add a vlan id filter to HW offload
+ * ice_lb_vsi_setup - Set up a loopback VSI
+ * @pf: board private structure
+ * @pi: pointer to the port_info instance
+ *
+ * Returns pointer to the successfully allocated VSI software struct
+ * on success, otherwise returns NULL on failure.
+ */
+struct ice_vsi *
+ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
+{
+	return ice_vsi_setup(pf, pi, ICE_VSI_LB, ICE_INVAL_VFID);
+}
+
+/**
+ * ice_vlan_rx_add_vid - Add a VLAN ID filter to HW offload
  * @netdev: network interface to be adjusted
  * @proto: unused protocol
- * @vid: vlan id to be added
+ * @vid: VLAN ID to be added
  *
- * net_device_ops implementation for adding vlan ids
+ * net_device_ops implementation for adding VLAN IDs
  */
-static int ice_vlan_rx_add_vid(struct net_device *netdev,
-			       __always_unused __be16 proto, u16 vid)
+static int
+ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto,
+		    u16 vid)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
+	int ret;
 
 	if (vid >= VLAN_N_VID) {
 		netdev_err(netdev, "VLAN id requested %d is out of range %d\n",
@@ -1637,33 +1934,39 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev,
 
 	/* Enable VLAN pruning when VLAN 0 is added */
 	if (unlikely(!vid)) {
-		int ret = ice_cfg_vlan_pruning(vsi, true);
-
+		ret = ice_cfg_vlan_pruning(vsi, true, false);
 		if (ret)
 			return ret;
 	}
 
-	/* Add all VLAN ids including 0 to the switch filter. VLAN id 0 is
+	/* Add all VLAN IDs including 0 to the switch filter. VLAN ID 0 is
 	 * needed to continue allowing all untagged packets since VLAN prune
 	 * list is applied to all packets by the switch
 	 */
-	return ice_vsi_add_vlan(vsi, vid);
+	ret = ice_vsi_add_vlan(vsi, vid);
+	if (!ret) {
+		vsi->vlan_ena = true;
+		set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+	}
+
+	return ret;
 }
 
 /**
- * ice_vlan_rx_kill_vid - Remove a vlan id filter from HW offload
+ * ice_vlan_rx_kill_vid - Remove a VLAN ID filter from HW offload
  * @netdev: network interface to be adjusted
  * @proto: unused protocol
- * @vid: vlan id to be removed
+ * @vid: VLAN ID to be removed
  *
- * net_device_ops implementation for removing vlan ids
+ * net_device_ops implementation for removing VLAN IDs
  */
-static int ice_vlan_rx_kill_vid(struct net_device *netdev,
-				__always_unused __be16 proto, u16 vid)
+static int
+ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto,
+		     u16 vid)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
-	int status;
+	int ret;
 
 	if (vsi->info.pvid)
 		return -EINVAL;
@@ -1671,15 +1974,17 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev,
 	/* Make sure ice_vsi_kill_vlan is successful before updating VLAN
 	 * information
 	 */
-	status = ice_vsi_kill_vlan(vsi, vid);
-	if (status)
-		return status;
+	ret = ice_vsi_kill_vlan(vsi, vid);
+	if (ret)
+		return ret;
 
 	/* Disable VLAN pruning when VLAN 0 is removed */
 	if (unlikely(!vid))
-		status = ice_cfg_vlan_pruning(vsi, false);
+		ret = ice_cfg_vlan_pruning(vsi, false, false);
 
-	return status;
+	vsi->vlan_ena = false;
+	set_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags);
+	return ret;
 }
 
 /**
@@ -1690,8 +1995,6 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev,
  */
 static int ice_setup_pf_sw(struct ice_pf *pf)
 {
-	LIST_HEAD(tmp_add_list);
-	u8 broadcast[ETH_ALEN];
 	struct ice_vsi *vsi;
 	int status = 0;
 
@@ -1716,38 +2019,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf)
 	 */
 	ice_napi_add(vsi);
 
-	/* To add a MAC filter, first add the MAC to a list and then
-	 * pass the list to ice_add_mac.
-	 */
-
-	 /* Add a unicast MAC filter so the VSI can get its packets */
-	status = ice_add_mac_to_list(vsi, &tmp_add_list,
-				     vsi->port_info->mac.perm_addr);
+	status = ice_init_mac_fltr(pf);
 	if (status)
 		goto unroll_napi_add;
 
-	/* VSI needs to receive broadcast traffic, so add the broadcast
-	 * MAC address to the list as well.
-	 */
-	eth_broadcast_addr(broadcast);
-	status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast);
-	if (status)
-		goto free_mac_list;
-
-	/* program MAC filters for entries in tmp_add_list */
-	status = ice_add_mac(&pf->hw, &tmp_add_list);
-	if (status) {
-		dev_err(&pf->pdev->dev, "Could not add MAC filters\n");
-		status = -ENOMEM;
-		goto free_mac_list;
-	}
-
-	ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
 	return status;
 
-free_mac_list:
-	ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list);
-
 unroll_napi_add:
 	if (vsi) {
 		ice_napi_del(vsi);
@@ -1869,7 +2146,7 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	v_left -= pf->num_lan_msix;
 
 	pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget,
-					sizeof(struct msix_entry), GFP_KERNEL);
+					sizeof(*pf->msix_entries), GFP_KERNEL);
 
 	if (!pf->msix_entries) {
 		err = -ENOMEM;
@@ -1939,14 +2216,9 @@ static void ice_clear_interrupt_scheme(struct ice_pf *pf)
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 		ice_dis_msix(pf);
 
-	if (pf->sw_irq_tracker) {
-		devm_kfree(&pf->pdev->dev, pf->sw_irq_tracker);
-		pf->sw_irq_tracker = NULL;
-	}
-
-	if (pf->hw_irq_tracker) {
-		devm_kfree(&pf->pdev->dev, pf->hw_irq_tracker);
-		pf->hw_irq_tracker = NULL;
+	if (pf->irq_tracker) {
+		devm_kfree(&pf->pdev->dev, pf->irq_tracker);
+		pf->irq_tracker = NULL;
 	}
 }
 
@@ -1956,8 +2228,7 @@ static void ice_clear_interrupt_scheme(struct ice_pf *pf)
  */
 static int ice_init_interrupt_scheme(struct ice_pf *pf)
 {
-	int vectors = 0, hw_vectors = 0;
-	ssize_t size;
+	int vectors;
 
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 		vectors = ice_ena_msix_range(pf);
@@ -1968,31 +2239,18 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 		return vectors;
 
 	/* set up vector assignment tracking */
-	size = sizeof(struct ice_res_tracker) + (sizeof(u16) * vectors);
-
-	pf->sw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
-	if (!pf->sw_irq_tracker) {
+	pf->irq_tracker =
+		devm_kzalloc(&pf->pdev->dev, sizeof(*pf->irq_tracker) +
+			     (sizeof(u16) * vectors), GFP_KERNEL);
+	if (!pf->irq_tracker) {
 		ice_dis_msix(pf);
 		return -ENOMEM;
 	}
 
 	/* populate SW interrupts pool with number of OS granted IRQs. */
 	pf->num_avail_sw_msix = vectors;
-	pf->sw_irq_tracker->num_entries = vectors;
-
-	/* set up HW vector assignment tracking */
-	hw_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	size = sizeof(struct ice_res_tracker) + (sizeof(u16) * hw_vectors);
-
-	pf->hw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
-	if (!pf->hw_irq_tracker) {
-		ice_clear_interrupt_scheme(pf);
-		return -ENOMEM;
-	}
-
-	/* populate HW interrupts pool with number of HW supported irqs. */
-	pf->num_avail_hw_msix = hw_vectors;
-	pf->hw_irq_tracker->num_entries = hw_vectors;
+	pf->irq_tracker->num_entries = vectors;
+	pf->irq_tracker->end = pf->irq_tracker->num_entries;
 
 	return 0;
 }
@@ -2020,34 +2278,35 @@ static void ice_verify_cacheline_size(struct ice_pf *pf)
  *
  * Returns 0 on success, negative on failure
  */
-static int ice_probe(struct pci_dev *pdev,
-		     const struct pci_device_id __always_unused *ent)
+static int
+ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 {
+	struct device *dev = &pdev->dev;
 	struct ice_pf *pf;
 	struct ice_hw *hw;
 	int err;
 
-	/* this driver uses devres, see Documentation/driver-model/devres.txt */
+	/* this driver uses devres, see Documentation/driver-api/driver-model/devres.rst */
 	err = pcim_enable_device(pdev);
 	if (err)
 		return err;
 
 	err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), pci_name(pdev));
 	if (err) {
-		dev_err(&pdev->dev, "BAR0 I/O map error %d\n", err);
+		dev_err(dev, "BAR0 I/O map error %d\n", err);
 		return err;
 	}
 
-	pf = devm_kzalloc(&pdev->dev, sizeof(*pf), GFP_KERNEL);
+	pf = devm_kzalloc(dev, sizeof(*pf), GFP_KERNEL);
 	if (!pf)
 		return -ENOMEM;
 
-	/* set up for high or low dma */
-	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	/* set up for high or low DMA */
+	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (err)
-		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 	if (err) {
-		dev_err(&pdev->dev, "DMA configuration failed: 0x%x\n", err);
+		dev_err(dev, "DMA configuration failed: 0x%x\n", err);
 		return err;
 	}
 
@@ -2081,17 +2340,26 @@ static int ice_probe(struct pci_dev *pdev,
 
 	err = ice_init_hw(hw);
 	if (err) {
-		dev_err(&pdev->dev, "ice_init_hw failed: %d\n", err);
+		dev_err(dev, "ice_init_hw failed: %d\n", err);
 		err = -EIO;
 		goto err_exit_unroll;
 	}
 
-	dev_info(&pdev->dev, "firmware %d.%d.%05d api %d.%d\n",
+	dev_info(dev, "firmware %d.%d.%05d api %d.%d\n",
 		 hw->fw_maj_ver, hw->fw_min_ver, hw->fw_build,
 		 hw->api_maj_ver, hw->api_min_ver);
 
 	ice_init_pf(pf);
 
+	err = ice_init_pf_dcb(pf, false);
+	if (err) {
+		clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
+		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
+
+		/* do not fail overall init if DCB init fails */
+		err = 0;
+	}
+
 	ice_determine_q_usage(pf);
 
 	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
@@ -2100,8 +2368,8 @@ static int ice_probe(struct pci_dev *pdev,
 		goto err_init_pf_unroll;
 	}
 
-	pf->vsi = devm_kcalloc(&pdev->dev, pf->num_alloc_vsi,
-			       sizeof(struct ice_vsi *), GFP_KERNEL);
+	pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi),
+			       GFP_KERNEL);
 	if (!pf->vsi) {
 		err = -ENOMEM;
 		goto err_init_pf_unroll;
@@ -2109,8 +2377,7 @@ static int ice_probe(struct pci_dev *pdev,
 
 	err = ice_init_interrupt_scheme(pf);
 	if (err) {
-		dev_err(&pdev->dev,
-			"ice_init_interrupt_scheme failed: %d\n", err);
+		dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
 		err = -EIO;
 		goto err_init_interrupt_unroll;
 	}
@@ -2126,15 +2393,13 @@ static int ice_probe(struct pci_dev *pdev,
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) {
 		err = ice_req_irq_msix_misc(pf);
 		if (err) {
-			dev_err(&pdev->dev,
-				"setup of misc vector failed: %d\n", err);
+			dev_err(dev, "setup of misc vector failed: %d\n", err);
 			goto err_init_interrupt_unroll;
 		}
 	}
 
 	/* create switch struct for the switch element created by FW on boot */
-	pf->first_sw = devm_kzalloc(&pdev->dev, sizeof(struct ice_sw),
-				    GFP_KERNEL);
+	pf->first_sw = devm_kzalloc(dev, sizeof(*pf->first_sw), GFP_KERNEL);
 	if (!pf->first_sw) {
 		err = -ENOMEM;
 		goto err_msix_misc_unroll;
@@ -2152,8 +2417,7 @@ static int ice_probe(struct pci_dev *pdev,
 
 	err = ice_setup_pf_sw(pf);
 	if (err) {
-		dev_err(&pdev->dev,
-			"probe failed due to setup pf switch:%d\n", err);
+		dev_err(dev, "probe failed due to setup PF switch:%d\n", err);
 		goto err_alloc_sw_unroll;
 	}
 
@@ -2162,6 +2426,12 @@ static int ice_probe(struct pci_dev *pdev,
 	/* since everything is good, start the service timer */
 	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
 
+	err = ice_init_link_events(pf->hw.port_info);
+	if (err) {
+		dev_err(dev, "ice_init_link_events failed: %d\n", err);
+		goto err_alloc_sw_unroll;
+	}
+
 	ice_verify_cacheline_size(pf);
 
 	return 0;
@@ -2174,7 +2444,7 @@ err_msix_misc_unroll:
 	ice_free_irq_msix_misc(pf);
 err_init_interrupt_unroll:
 	ice_clear_interrupt_scheme(pf);
-	devm_kfree(&pdev->dev, pf->vsi);
+	devm_kfree(dev, pf->vsi);
 err_init_pf_unroll:
 	ice_deinit_pf(pf);
 	ice_deinit_hw(hw);
@@ -2219,6 +2489,136 @@ static void ice_remove(struct pci_dev *pdev)
 	pci_disable_pcie_error_reporting(pdev);
 }
 
+/**
+ * ice_pci_err_detected - warning that PCI error has been detected
+ * @pdev: PCI device information struct
+ * @err: the type of PCI error
+ *
+ * Called to warn that something happened on the PCI bus and the error handling
+ * is in progress.  Allows the driver to gracefully prepare/handle PCI errors.
+ */
+static pci_ers_result_t
+ice_pci_err_detected(struct pci_dev *pdev, enum pci_channel_state err)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+
+	if (!pf) {
+		dev_err(&pdev->dev, "%s: unrecoverable device error %d\n",
+			__func__, err);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	if (!test_bit(__ICE_SUSPENDED, pf->state)) {
+		ice_service_task_stop(pf);
+
+		if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) {
+			set_bit(__ICE_PFR_REQ, pf->state);
+			ice_prepare_for_reset(pf);
+		}
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * ice_pci_err_slot_reset - a PCI slot reset has just happened
+ * @pdev: PCI device information struct
+ *
+ * Called to determine if the driver can recover from the PCI slot reset by
+ * using a register read to determine if the device is recoverable.
+ */
+static pci_ers_result_t ice_pci_err_slot_reset(struct pci_dev *pdev)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+	pci_ers_result_t result;
+	int err;
+	u32 reg;
+
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"Cannot re-enable PCI device after reset, error %d\n",
+			err);
+		result = PCI_ERS_RESULT_DISCONNECT;
+	} else {
+		pci_set_master(pdev);
+		pci_restore_state(pdev);
+		pci_save_state(pdev);
+		pci_wake_from_d3(pdev, false);
+
+		/* Check for life */
+		reg = rd32(&pf->hw, GLGEN_RTRIG);
+		if (!reg)
+			result = PCI_ERS_RESULT_RECOVERED;
+		else
+			result = PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	err = pci_cleanup_aer_uncorrect_error_status(pdev);
+	if (err)
+		dev_dbg(&pdev->dev,
+			"pci_cleanup_aer_uncorrect_error_status failed, error %d\n",
+			err);
+		/* non-fatal, continue */
+
+	return result;
+}
+
+/**
+ * ice_pci_err_resume - restart operations after PCI error recovery
+ * @pdev: PCI device information struct
+ *
+ * Called to allow the driver to bring things back up after PCI error and/or
+ * reset recovery have finished
+ */
+static void ice_pci_err_resume(struct pci_dev *pdev)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+
+	if (!pf) {
+		dev_err(&pdev->dev,
+			"%s failed, device is unrecoverable\n", __func__);
+		return;
+	}
+
+	if (test_bit(__ICE_SUSPENDED, pf->state)) {
+		dev_dbg(&pdev->dev, "%s failed to resume normal operations!\n",
+			__func__);
+		return;
+	}
+
+	ice_do_reset(pf, ICE_RESET_PFR);
+	ice_service_task_restart(pf);
+	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
+}
+
+/**
+ * ice_pci_err_reset_prepare - prepare device driver for PCI reset
+ * @pdev: PCI device information struct
+ */
+static void ice_pci_err_reset_prepare(struct pci_dev *pdev)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+
+	if (!test_bit(__ICE_SUSPENDED, pf->state)) {
+		ice_service_task_stop(pf);
+
+		if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) {
+			set_bit(__ICE_PFR_REQ, pf->state);
+			ice_prepare_for_reset(pf);
+		}
+	}
+}
+
+/**
+ * ice_pci_err_reset_done - PCI reset done, device driver reset can begin
+ * @pdev: PCI device information struct
+ */
+static void ice_pci_err_reset_done(struct pci_dev *pdev)
+{
+	ice_pci_err_resume(pdev);
+}
+
 /* ice_pci_tbl - PCI Device ID Table
  *
  * Wildcard entries (PCI_ANY_ID) should come last
@@ -2236,12 +2636,21 @@ static const struct pci_device_id ice_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, ice_pci_tbl);
 
+static const struct pci_error_handlers ice_pci_err_handler = {
+	.error_detected = ice_pci_err_detected,
+	.slot_reset = ice_pci_err_slot_reset,
+	.reset_prepare = ice_pci_err_reset_prepare,
+	.reset_done = ice_pci_err_reset_done,
+	.resume = ice_pci_err_resume
+};
+
 static struct pci_driver ice_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = ice_pci_tbl,
 	.probe = ice_probe,
 	.remove = ice_remove,
 	.sriov_configure = ice_sriov_configure,
+	.err_handler = &ice_pci_err_handler
 };
 
 /**
@@ -2265,7 +2674,7 @@ static int __init ice_module_init(void)
 
 	status = pci_register_driver(&ice_driver);
 	if (status) {
-		pr_err("failed to register pci driver, err %d\n", status);
+		pr_err("failed to register PCI driver, err %d\n", status);
 		destroy_workqueue(ice_wq);
 	}
 
@@ -2288,7 +2697,7 @@ static void __exit ice_module_exit(void)
 module_exit(ice_module_exit);
 
 /**
- * ice_set_mac_address - NDO callback to set mac address
+ * ice_set_mac_address - NDO callback to set MAC address
  * @netdev: network interface device structure
  * @pi: pointer to an address structure
  *
@@ -2325,14 +2734,14 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi)
 		return -EBUSY;
 	}
 
-	/* When we change the mac address we also have to change the mac address
-	 * based filter rules that were created previously for the old mac
+	/* When we change the MAC address we also have to change the MAC address
+	 * based filter rules that were created previously for the old MAC
 	 * address. So first, we remove the old filter rule using ice_remove_mac
 	 * and then create a new filter rule using ice_add_mac. Note that for
-	 * both these operations, we first need to form a "list" of mac
-	 * addresses (even though in this case, we have only 1 mac address to be
+	 * both these operations, we first need to form a "list" of MAC
+	 * addresses (even though in this case, we have only 1 MAC address to be
 	 * added/removed) and this done using ice_add_mac_to_list. Depending on
-	 * the ensuing operation this "list" of mac addresses is either to be
+	 * the ensuing operation this "list" of MAC addresses is either to be
 	 * added or removed from the filter.
 	 */
 	err = ice_add_mac_to_list(vsi, &r_mac_list, netdev->dev_addr);
@@ -2365,21 +2774,21 @@ free_lists:
 	ice_free_fltr_list(&pf->pdev->dev, &a_mac_list);
 
 	if (err) {
-		netdev_err(netdev, "can't set mac %pM. filter update failed\n",
+		netdev_err(netdev, "can't set MAC %pM. filter update failed\n",
 			   mac);
 		return err;
 	}
 
-	/* change the netdev's mac address */
+	/* change the netdev's MAC address */
 	memcpy(netdev->dev_addr, mac, netdev->addr_len);
-	netdev_dbg(vsi->netdev, "updated mac address to %pM\n",
+	netdev_dbg(vsi->netdev, "updated MAC address to %pM\n",
 		   netdev->dev_addr);
 
-	/* write new mac address to the firmware */
+	/* write new MAC address to the firmware */
 	flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL;
 	status = ice_aq_manage_mac_write(hw, mac, flags, NULL);
 	if (status) {
-		netdev_err(netdev, "can't set mac %pM. write to firmware failed.\n",
+		netdev_err(netdev, "can't set MAC %pM. write to firmware failed.\n",
 			   mac);
 	}
 	return 0;
@@ -2417,12 +2826,14 @@ static void ice_set_rx_mode(struct net_device *netdev)
  * @tb: pointer to array of nladdr (unused)
  * @dev: the net device pointer
  * @addr: the MAC address entry being added
- * @vid: VLAN id
+ * @vid: VLAN ID
  * @flags: instructions from stack about fdb operation
+ * @extack: netlink extended ack
  */
-static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
-		       struct net_device *dev, const unsigned char *addr,
-		       u16 vid, u16 flags)
+static int
+ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
+	    struct net_device *dev, const unsigned char *addr, u16 vid,
+	    u16 flags, struct netlink_ext_ack __always_unused *extack)
 {
 	int err;
 
@@ -2455,11 +2866,12 @@ static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
  * @tb: pointer to array of nladdr (unused)
  * @dev: the net device pointer
  * @addr: the MAC address entry being added
- * @vid: VLAN id
+ * @vid: VLAN ID
  */
-static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
-		       struct net_device *dev, const unsigned char *addr,
-		       __always_unused u16 vid)
+static int
+ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
+	    struct net_device *dev, const unsigned char *addr,
+	    __always_unused u16 vid)
 {
 	int err;
 
@@ -2483,13 +2895,16 @@ static int ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
  * @netdev: ptr to the netdev being adjusted
  * @features: the feature set that the stack is suggesting
  */
-static int ice_set_features(struct net_device *netdev,
-			    netdev_features_t features)
+static int
+ice_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
 	int ret = 0;
 
+	/* Multiple features can be changed in one call so keep features in
+	 * separate if/else statements to guarantee each feature is checked
+	 */
 	if (features & NETIF_F_RXHASH && !(netdev->features & NETIF_F_RXHASH))
 		ret = ice_vsi_manage_rss_lut(vsi, true);
 	else if (!(features & NETIF_F_RXHASH) &&
@@ -2502,19 +2917,27 @@ static int ice_set_features(struct net_device *netdev,
 	else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) &&
 		 (netdev->features & NETIF_F_HW_VLAN_CTAG_RX))
 		ret = ice_vsi_manage_vlan_stripping(vsi, false);
-	else if ((features & NETIF_F_HW_VLAN_CTAG_TX) &&
-		 !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
+
+	if ((features & NETIF_F_HW_VLAN_CTAG_TX) &&
+	    !(netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
 		ret = ice_vsi_manage_vlan_insertion(vsi);
 	else if (!(features & NETIF_F_HW_VLAN_CTAG_TX) &&
 		 (netdev->features & NETIF_F_HW_VLAN_CTAG_TX))
 		ret = ice_vsi_manage_vlan_insertion(vsi);
 
+	if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+	    !(netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+		ret = ice_cfg_vlan_pruning(vsi, true, false);
+	else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+		 (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER))
+		ret = ice_cfg_vlan_pruning(vsi, false, false);
+
 	return ret;
 }
 
 /**
- * ice_vsi_vlan_setup - Setup vlan offload properties on a VSI
- * @vsi: VSI to setup vlan properties for
+ * ice_vsi_vlan_setup - Setup VLAN offload properties on a VSI
+ * @vsi: VSI to setup VLAN properties for
  */
 static int ice_vsi_vlan_setup(struct ice_vsi *vsi)
 {
@@ -2534,7 +2957,7 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi)
  *
  * Return 0 on success and negative value on error
  */
-static int ice_vsi_cfg(struct ice_vsi *vsi)
+int ice_vsi_cfg(struct ice_vsi *vsi)
 {
 	int err;
 
@@ -2546,7 +2969,9 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
 		if (err)
 			return err;
 	}
-	err = ice_vsi_cfg_txqs(vsi);
+	ice_vsi_cfg_dcb_rings(vsi);
+
+	err = ice_vsi_cfg_lan_txqs(vsi);
 	if (!err)
 		err = ice_vsi_cfg_rxqs(vsi);
 
@@ -2564,7 +2989,7 @@ static void ice_napi_enable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+	ice_for_each_q_vector(vsi, q_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
 		if (q_vector->rx.ring || q_vector->tx.ring)
@@ -2610,7 +3035,7 @@ static int ice_up_complete(struct ice_vsi *vsi)
 
 	ice_service_task_schedule(pf);
 
-	return err;
+	return 0;
 }
 
 /**
@@ -2637,8 +3062,8 @@ int ice_up(struct ice_vsi *vsi)
  * This function fetches stats from the ring considering the atomic operations
  * that needs to be performed to read u64 values in 32 bit machine.
  */
-static void ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts,
-					 u64 *bytes)
+static void
+ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes)
 {
 	unsigned int start;
 	*pkts = 0;
@@ -2855,6 +3280,8 @@ static void ice_update_pf_stats(struct ice_pf *pf)
 	ice_stat_update32(hw, GLPRT_LXOFFTXC(pf_id), pf->stat_prev_loaded,
 			  &prev_ps->link_xoff_tx, &cur_ps->link_xoff_tx);
 
+	ice_update_dcb_stats(pf);
+
 	ice_stat_update32(hw, GLPRT_CRCERRS(pf_id), pf->stat_prev_loaded,
 			  &prev_ps->crc_errors, &cur_ps->crc_errors);
 
@@ -2936,7 +3363,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+	ice_for_each_q_vector(vsi, q_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
 		if (q_vector->rx.ring || q_vector->tx.ring)
@@ -2945,12 +3372,91 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
 }
 
 /**
+ * ice_force_phys_link_state - Force the physical link state
+ * @vsi: VSI to force the physical link state to up/down
+ * @link_up: true/false indicates to set the physical link to up/down
+ *
+ * Force the physical link state by getting the current PHY capabilities from
+ * hardware and setting the PHY config based on the determined capabilities. If
+ * link changes a link event will be triggered because both the Enable Automatic
+ * Link Update and LESM Enable bits are set when setting the PHY capabilities.
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
+{
+	struct ice_aqc_get_phy_caps_data *pcaps;
+	struct ice_aqc_set_phy_cfg_data *cfg;
+	struct ice_port_info *pi;
+	struct device *dev;
+	int retcode;
+
+	if (!vsi || !vsi->port_info || !vsi->back)
+		return -EINVAL;
+	if (vsi->type != ICE_VSI_PF)
+		return 0;
+
+	dev = &vsi->back->pdev->dev;
+
+	pi = vsi->port_info;
+
+	pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL);
+	if (!pcaps)
+		return -ENOMEM;
+
+	retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+				      NULL);
+	if (retcode) {
+		dev_err(dev,
+			"Failed to get phy capabilities, VSI %d error %d\n",
+			vsi->vsi_num, retcode);
+		retcode = -EIO;
+		goto out;
+	}
+
+	/* No change in link */
+	if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) &&
+	    link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP))
+		goto out;
+
+	cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL);
+	if (!cfg) {
+		retcode = -ENOMEM;
+		goto out;
+	}
+
+	cfg->phy_type_low = pcaps->phy_type_low;
+	cfg->phy_type_high = pcaps->phy_type_high;
+	cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+	cfg->low_power_ctrl = pcaps->low_power_ctrl;
+	cfg->eee_cap = pcaps->eee_cap;
+	cfg->eeer_value = pcaps->eeer_value;
+	cfg->link_fec_opt = pcaps->link_fec_options;
+	if (link_up)
+		cfg->caps |= ICE_AQ_PHY_ENA_LINK;
+	else
+		cfg->caps &= ~ICE_AQ_PHY_ENA_LINK;
+
+	retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL);
+	if (retcode) {
+		dev_err(dev, "Failed to set phy config, VSI %d error %d\n",
+			vsi->vsi_num, retcode);
+		retcode = -EIO;
+	}
+
+	devm_kfree(dev, cfg);
+out:
+	devm_kfree(dev, pcaps);
+	return retcode;
+}
+
+/**
  * ice_down - Shutdown the connection
  * @vsi: The VSI being stopped
  */
 int ice_down(struct ice_vsi *vsi)
 {
-	int i, tx_err, rx_err;
+	int i, tx_err, rx_err, link_err = 0;
 
 	/* Caller of this function is expected to set the
 	 * vsi->state __ICE_DOWN bit
@@ -2961,7 +3467,8 @@ int ice_down(struct ice_vsi *vsi)
 	}
 
 	ice_vsi_dis_irq(vsi);
-	tx_err = ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0);
+
+	tx_err = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
 	if (tx_err)
 		netdev_err(vsi->netdev,
 			   "Failed stop Tx rings, VSI %d error %d\n",
@@ -2975,13 +3482,21 @@ int ice_down(struct ice_vsi *vsi)
 
 	ice_napi_disable_all(vsi);
 
+	if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
+		link_err = ice_force_phys_link_state(vsi, false);
+		if (link_err)
+			netdev_err(vsi->netdev,
+				   "Failed to set physical link down, VSI %d error %d\n",
+				   vsi->vsi_num, link_err);
+	}
+
 	ice_for_each_txq(vsi, i)
 		ice_clean_tx_ring(vsi->tx_rings[i]);
 
 	ice_for_each_rxq(vsi, i)
 		ice_clean_rx_ring(vsi->rx_rings[i]);
 
-	if (tx_err || rx_err) {
+	if (tx_err || rx_err || link_err) {
 		netdev_err(vsi->netdev,
 			   "Failed to close VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
@@ -2997,7 +3512,7 @@ int ice_down(struct ice_vsi *vsi)
  *
  * Return 0 on success, negative on failure
  */
-static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
+int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
 {
 	int i, err = 0;
 
@@ -3023,7 +3538,7 @@ static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi)
  *
  * Return 0 on success, negative on failure
  */
-static int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
+int ice_vsi_setup_rx_rings(struct ice_vsi *vsi)
 {
 	int i, err = 0;
 
@@ -3132,7 +3647,7 @@ static void ice_vsi_release_all(struct ice_pf *pf)
 	if (!pf->vsi)
 		return;
 
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		if (!pf->vsi[i])
 			continue;
 
@@ -3145,47 +3660,31 @@ static void ice_vsi_release_all(struct ice_pf *pf)
 }
 
 /**
- * ice_dis_vsi - pause a VSI
- * @vsi: the VSI being paused
+ * ice_ena_vsi - resume a VSI
+ * @vsi: the VSI being resume
  * @locked: is the rtnl_lock already held
  */
-static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
+static int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
 {
-	if (test_bit(__ICE_DOWN, vsi->state))
-		return;
+	int err = 0;
 
-	set_bit(__ICE_NEEDS_RESTART, vsi->state);
+	if (!test_bit(__ICE_NEEDS_RESTART, vsi->state))
+		return err;
+
+	clear_bit(__ICE_NEEDS_RESTART, vsi->state);
+
+	if (vsi->netdev && vsi->type == ICE_VSI_PF) {
+		struct net_device *netd = vsi->netdev;
 
-	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
 		if (netif_running(vsi->netdev)) {
-			if (!locked) {
+			if (locked) {
+				err = netd->netdev_ops->ndo_open(netd);
+			} else {
 				rtnl_lock();
-				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+				err = netd->netdev_ops->ndo_open(netd);
 				rtnl_unlock();
-			} else {
-				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
 			}
 		} else {
-			ice_vsi_close(vsi);
-		}
-	}
-}
-
-/**
- * ice_ena_vsi - resume a VSI
- * @vsi: the VSI being resume
- */
-static int ice_ena_vsi(struct ice_vsi *vsi)
-{
-	int err = 0;
-
-	if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state) &&
-	    vsi->netdev) {
-		if (netif_running(vsi->netdev)) {
-			rtnl_lock();
-			err = vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
-			rtnl_unlock();
-		} else {
 			err = ice_vsi_open(vsi);
 		}
 	}
@@ -3194,36 +3693,28 @@ static int ice_ena_vsi(struct ice_vsi *vsi)
 }
 
 /**
- * ice_pf_dis_all_vsi - Pause all VSIs on a PF
- * @pf: the PF
- */
-static void ice_pf_dis_all_vsi(struct ice_pf *pf)
-{
-	int v;
-
-	ice_for_each_vsi(pf, v)
-		if (pf->vsi[v])
-			ice_dis_vsi(pf->vsi[v], false);
-}
-
-/**
  * ice_pf_ena_all_vsi - Resume all VSIs on a PF
  * @pf: the PF
+ * @locked: is the rtnl_lock already held
  */
-static int ice_pf_ena_all_vsi(struct ice_pf *pf)
+#ifdef CONFIG_DCB
+int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked)
+#else
+static int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked)
+#endif /* CONFIG_DCB */
 {
 	int v;
 
 	ice_for_each_vsi(pf, v)
 		if (pf->vsi[v])
-			if (ice_ena_vsi(pf->vsi[v]))
+			if (ice_ena_vsi(pf->vsi[v], locked))
 				return -EIO;
 
 	return 0;
 }
 
 /**
- * ice_vsi_rebuild_all - rebuild all VSIs in pf
+ * ice_vsi_rebuild_all - rebuild all VSIs in PF
  * @pf: the PF
  */
 static int ice_vsi_rebuild_all(struct ice_pf *pf)
@@ -3231,16 +3722,12 @@ static int ice_vsi_rebuild_all(struct ice_pf *pf)
 	int i;
 
 	/* loop through pf->vsi array and reinit the VSI if found */
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		int err;
 
 		if (!pf->vsi[i])
 			continue;
 
-		/* VF VSI rebuild isn't supported yet */
-		if (pf->vsi[i]->type == ICE_VSI_VF)
-			continue;
-
 		err = ice_vsi_rebuild(pf->vsi[i]);
 		if (err) {
 			dev_err(&pf->pdev->dev,
@@ -3268,7 +3755,7 @@ static int ice_vsi_replay_all(struct ice_pf *pf)
 	int i;
 
 	/* loop through pf->vsi array and replay the VSI if found */
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		if (!pf->vsi[i])
 			continue;
 
@@ -3297,7 +3784,7 @@ static int ice_vsi_replay_all(struct ice_pf *pf)
 
 /**
  * ice_rebuild - rebuild after reset
- * @pf: pf to rebuild
+ * @pf: PF to rebuild
  */
 static void ice_rebuild(struct ice_pf *pf)
 {
@@ -3309,7 +3796,7 @@ static void ice_rebuild(struct ice_pf *pf)
 	if (test_bit(__ICE_DOWN, pf->state))
 		goto clear_recovery;
 
-	dev_dbg(dev, "rebuilding pf\n");
+	dev_dbg(dev, "rebuilding PF\n");
 
 	ret = ice_init_all_ctrlq(hw);
 	if (ret) {
@@ -3335,11 +3822,7 @@ static void ice_rebuild(struct ice_pf *pf)
 	if (err)
 		goto err_sched_init_port;
 
-	/* reset search_hint of irq_trackers to 0 since interrupts are
-	 * reclaimed and could be allocated from beginning during VSI rebuild
-	 */
-	pf->sw_irq_tracker->search_hint = 0;
-	pf->hw_irq_tracker->search_hint = 0;
+	ice_dcb_rebuild(pf);
 
 	err = ice_vsi_rebuild_all(pf);
 	if (err) {
@@ -3368,7 +3851,7 @@ static void ice_rebuild(struct ice_pf *pf)
 	}
 
 	/* restart the VSIs that were rebuilt and running before the reset */
-	err = ice_pf_ena_all_vsi(pf);
+	err = ice_pf_ena_all_vsi(pf, false);
 	if (err) {
 		dev_err(&pf->pdev->dev, "error enabling VSIs\n");
 		/* no need to disable VSIs in tear down path in ice_rebuild()
@@ -3377,9 +3860,7 @@ static void ice_rebuild(struct ice_pf *pf)
 		goto err_vsi_rebuild;
 	}
 
-	ice_reset_all_vfs(pf, true);
-
-	for (i = 0; i < pf->num_alloc_vsi; i++) {
+	ice_for_each_vsi(pf, i) {
 		bool link_up;
 
 		if (!pf->vsi[i] || pf->vsi[i]->type != ICE_VSI_PF)
@@ -3426,16 +3907,16 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 	u8 count = 0;
 
 	if (new_mtu == netdev->mtu) {
-		netdev_warn(netdev, "mtu is already %u\n", netdev->mtu);
+		netdev_warn(netdev, "MTU is already %u\n", netdev->mtu);
 		return 0;
 	}
 
 	if (new_mtu < netdev->min_mtu) {
-		netdev_err(netdev, "new mtu invalid. min_mtu is %d\n",
+		netdev_err(netdev, "new MTU invalid. min_mtu is %d\n",
 			   netdev->min_mtu);
 		return -EINVAL;
 	} else if (new_mtu > netdev->max_mtu) {
-		netdev_err(netdev, "new mtu invalid. max_mtu is %d\n",
+		netdev_err(netdev, "new MTU invalid. max_mtu is %d\n",
 			   netdev->min_mtu);
 		return -EINVAL;
 	}
@@ -3451,7 +3932,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 	} while (count < 100);
 
 	if (count == 100) {
-		netdev_err(netdev, "can't change mtu. Device is busy\n");
+		netdev_err(netdev, "can't change MTU. Device is busy\n");
 		return -EBUSY;
 	}
 
@@ -3463,18 +3944,18 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
 
 		err = ice_down(vsi);
 		if (err) {
-			netdev_err(netdev, "change mtu if_up err %d\n", err);
+			netdev_err(netdev, "change MTU if_up err %d\n", err);
 			return err;
 		}
 
 		err = ice_up(vsi);
 		if (err) {
-			netdev_err(netdev, "change mtu if_up err %d\n", err);
+			netdev_err(netdev, "change MTU if_up err %d\n", err);
 			return err;
 		}
 	}
 
-	netdev_dbg(netdev, "changed mtu to %d\n", new_mtu);
+	netdev_info(netdev, "changed MTU to %d\n", new_mtu);
 	return 0;
 }
 
@@ -3566,7 +4047,7 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
 /**
  * ice_bridge_getlink - Get the hardware bridge mode
  * @skb: skb buff
- * @pid: process id
+ * @pid: process ID
  * @seq: RTNL message seq
  * @dev: the netdev being configured
  * @filter_mask: filter mask passed in
@@ -3601,30 +4082,39 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_aqc_vsi_props *vsi_props;
 	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
+	int ret = 0;
 
 	vsi_props = &vsi->info;
-	ctxt.info = vsi->info;
+
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
+
+	ctxt->info = vsi->info;
 
 	if (bmode == BRIDGE_MODE_VEB)
 		/* change from VEPA to VEB mode */
-		ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+		ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
 	else
 		/* change from VEB to VEPA mode */
-		ctxt.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);
+		ctxt->info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);
 
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
 			bmode, status, hw->adminq.sq_last_status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 	/* Update sw flags for book keeping */
-	vsi_props->sw_flags = ctxt.info.sw_flags;
+	vsi_props->sw_flags = ctxt->info.sw_flags;
 
-	return 0;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
@@ -3641,7 +4131,8 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
  */
 static int
 ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-		   u16 __always_unused flags, struct netlink_ext_ack *extack)
+		   u16 __always_unused flags,
+		   struct netlink_ext_ack __always_unused *extack)
 {
 	struct ice_netdev_priv *np = netdev_priv(dev);
 	struct ice_pf *pf = np->vsi->back;
@@ -3755,8 +4246,7 @@ static void ice_tx_timeout(struct net_device *netdev)
 		/* Read interrupt register */
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 			val = rd32(hw,
-				   GLINT_DYN_CTL(tx_ring->q_vector->v_idx +
-						 tx_ring->vsi->hw_base_vector));
+				   GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, hung_queue, tx_ring->next_to_clean,
@@ -3801,7 +4291,7 @@ static void ice_tx_timeout(struct net_device *netdev)
  *
  * Returns 0 on success, negative value on failure
  */
-static int ice_open(struct net_device *netdev)
+int ice_open(struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -3814,8 +4304,14 @@ static int ice_open(struct net_device *netdev)
 
 	netif_carrier_off(netdev);
 
-	err = ice_vsi_open(vsi);
+	err = ice_force_phys_link_state(vsi, true);
+	if (err) {
+		netdev_err(netdev,
+			   "Failed to set physical link up, error %d\n", err);
+		return err;
+	}
 
+	err = ice_vsi_open(vsi);
 	if (err)
 		netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
@@ -3832,7 +4328,7 @@ static int ice_open(struct net_device *netdev)
  *
  * Returns success only - not allowed to fail
  */
-static int ice_stop(struct net_device *netdev)
+int ice_stop(struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 3274c543283c..bcb431f1bd92 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -5,7 +5,7 @@
 
 /**
  * ice_aq_read_nvm
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @module_typeid: module pointer location in words from the NVM beginning
  * @offset: byte offset from the module beginning
  * @length: length of the section to be read (in bytes from the offset)
@@ -119,12 +119,69 @@ ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data)
 
 	status = ice_read_sr_aq(hw, offset, 1, data, true);
 	if (!status)
-		*data = le16_to_cpu(*(__le16 *)data);
+		*data = le16_to_cpu(*(__force __le16 *)data);
 
 	return status;
 }
 
 /**
+ * ice_read_sr_buf_aq - Reads Shadow RAM buf via AQ
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_sr_aq
+ * method. Ownership of the NVM is taken before reading the buffer and later
+ * released.
+ */
+static enum ice_status
+ice_read_sr_buf_aq(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+	enum ice_status status;
+	bool last_cmd = false;
+	u16 words_read = 0;
+	u16 i = 0;
+
+	do {
+		u16 read_size, off_w;
+
+		/* Calculate number of bytes we should read in this step.
+		 * It's not allowed to read more than one page at a time or
+		 * to cross page boundaries.
+		 */
+		off_w = offset % ICE_SR_SECTOR_SIZE_IN_WORDS;
+		read_size = off_w ?
+			min_t(u16, *words,
+			      (ICE_SR_SECTOR_SIZE_IN_WORDS - off_w)) :
+			min_t(u16, (*words - words_read),
+			      ICE_SR_SECTOR_SIZE_IN_WORDS);
+
+		/* Check if this is last command, if so set proper flag */
+		if ((words_read + read_size) >= *words)
+			last_cmd = true;
+
+		status = ice_read_sr_aq(hw, offset, read_size,
+					data + words_read, last_cmd);
+		if (status)
+			goto read_nvm_buf_aq_exit;
+
+		/* Increment counter for words already read and move offset to
+		 * new read location
+		 */
+		words_read += read_size;
+		offset += read_size;
+	} while (words_read < *words);
+
+	for (i = 0; i < *words; i++)
+		data[i] = le16_to_cpu(((__force __le16 *)data)[i]);
+
+read_nvm_buf_aq_exit:
+	*words = words_read;
+	return status;
+}
+
+/**
  * ice_acquire_nvm - Generic request for acquiring the NVM ownership
  * @hw: pointer to the HW structure
  * @access: NVM access type (read or write)
@@ -178,7 +235,7 @@ ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data)
 
 /**
  * ice_init_nvm - initializes NVM setting
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * This function reads and populates NVM settings such as Shadow RAM size,
  * max_timeout, and blank_nvm_mode
@@ -191,7 +248,7 @@ enum ice_status ice_init_nvm(struct ice_hw *hw)
 	u32 fla, gens_stat;
 	u8 sr_size;
 
-	/* The SR size is stored regardless of the nvm programming mode
+	/* The SR size is stored regardless of the NVM programming mode
 	 * as the blank mode may be used in the factory line.
 	 */
 	gens_stat = rd32(hw, GLNVM_GENS);
@@ -234,3 +291,59 @@ enum ice_status ice_init_nvm(struct ice_hw *hw)
 
 	return status;
 }
+
+/**
+ * ice_read_sr_buf - Reads Shadow RAM buf and acquire lock if necessary
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_nvm_buf_aq
+ * method. The buf read is preceded by the NVM ownership take
+ * and followed by the release.
+ */
+enum ice_status
+ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+	enum ice_status status;
+
+	status = ice_acquire_nvm(hw, ICE_RES_READ);
+	if (!status) {
+		status = ice_read_sr_buf_aq(hw, offset, words, data);
+		ice_release_nvm(hw);
+	}
+
+	return status;
+}
+
+/**
+ * ice_nvm_validate_checksum
+ * @hw: pointer to the HW struct
+ *
+ * Verify NVM PFA checksum validity (0x0706)
+ */
+enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw)
+{
+	struct ice_aqc_nvm_checksum *cmd;
+	struct ice_aq_desc desc;
+	enum ice_status status;
+
+	status = ice_acquire_nvm(hw, ICE_RES_READ);
+	if (status)
+		return status;
+
+	cmd = &desc.params.nvm_checksum;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_checksum);
+	cmd->flags = ICE_AQC_NVM_CHECKSUM_VERIFY;
+
+	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+	ice_release_nvm(hw);
+
+	if (!status)
+		if (le16_to_cpu(cmd->checksum) != ICE_AQC_NVM_CHECKSUM_CORRECT)
+			status = ICE_ERR_NVM_CHECKSUM;
+
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index a1681853df2e..2a232504379d 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -43,9 +43,9 @@ ice_sched_add_root_node(struct ice_port_info *pi,
 /**
  * ice_sched_find_node_by_teid - Find the Tx scheduler node in SW DB
  * @start_node: pointer to the starting ice_sched_node struct in a sub-tree
- * @teid: node teid to search
+ * @teid: node TEID to search
  *
- * This function searches for a node matching the teid in the scheduling tree
+ * This function searches for a node matching the TEID in the scheduling tree
  * from the SW DB. The search is recursive and is restricted by the number of
  * layers it has searched through; stopping at the max supported layer.
  *
@@ -66,7 +66,7 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 	    start_node->info.data.elem_type == ICE_AQC_ELEM_TYPE_LEAF)
 		return NULL;
 
-	/* Check if teid matches to any of the children nodes */
+	/* Check if TEID matches to any of the children nodes */
 	for (i = 0; i < start_node->num_children; i++)
 		if (ICE_TXSCHED_GET_NODE_TEID(start_node->children[i]) == teid)
 			return start_node->children[i];
@@ -85,59 +85,56 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 }
 
 /**
- * ice_aq_query_sched_elems - query scheduler elements
- * @hw: pointer to the hw struct
- * @elems_req: number of elements to query
+ * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
+ * @hw: pointer to the HW struct
+ * @cmd_opc: cmd opcode
+ * @elems_req: number of elements to request
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
- * @elems_ret: returns total number of elements returned
+ * @elems_resp: returns total number of elements response
  * @cd: pointer to command details structure or NULL
  *
- * Query scheduling elements (0x0404)
+ * This function sends a scheduling elements cmd (cmd_opc)
  */
 static enum ice_status
-ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
-			 struct ice_aqc_get_elem *buf, u16 buf_size,
-			 u16 *elems_ret, struct ice_sq_cd *cd)
+ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc,
+			    u16 elems_req, void *buf, u16 buf_size,
+			    u16 *elems_resp, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_get_cfg_elem *cmd;
+	struct ice_aqc_sched_elem_cmd *cmd;
 	struct ice_aq_desc desc;
 	enum ice_status status;
 
-	cmd = &desc.params.get_update_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sched_elems);
+	cmd = &desc.params.sched_elem_cmd;
+	ice_fill_dflt_direct_cmd_desc(&desc, cmd_opc);
 	cmd->num_elem_req = cpu_to_le16(elems_req);
 	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && elems_ret)
-		*elems_ret = le16_to_cpu(cmd->num_elem_resp);
+	if (!status && elems_resp)
+		*elems_resp = le16_to_cpu(cmd->num_elem_resp);
 
 	return status;
 }
 
 /**
- * ice_sched_query_elem - query element information from hw
- * @hw: pointer to the hw struct
- * @node_teid: node teid to be queried
- * @buf: buffer to element information
+ * ice_aq_query_sched_elems - query scheduler elements
+ * @hw: pointer to the HW struct
+ * @elems_req: number of elements to query
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_ret: returns total number of elements returned
+ * @cd: pointer to command details structure or NULL
  *
- * This function queries HW element information
+ * Query scheduling elements (0x0404)
  */
-static enum ice_status
-ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
-		     struct ice_aqc_get_elem *buf)
+enum ice_status
+ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
+			 struct ice_aqc_get_elem *buf, u16 buf_size,
+			 u16 *elems_ret, struct ice_sq_cd *cd)
 {
-	u16 buf_size, num_elem_ret = 0;
-	enum ice_status status;
-
-	buf_size = sizeof(*buf);
-	memset(buf, 0, buf_size);
-	buf->generic[0].node_teid = cpu_to_le32(node_teid);
-	status = ice_aq_query_sched_elems(hw, 1, buf, buf_size, &num_elem_ret,
-					  NULL);
-	if (status || num_elem_ret != 1)
-		ice_debug(hw, ICE_DBG_SCHED, "query element failed\n");
-	return status;
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_get_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
 }
 
 /**
@@ -204,7 +201,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer,
 
 /**
  * ice_aq_delete_sched_elems - delete scheduler elements
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @grps_req: number of groups to delete
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
@@ -218,30 +215,19 @@ ice_aq_delete_sched_elems(struct ice_hw *hw, u16 grps_req,
 			  struct ice_aqc_delete_elem *buf, u16 buf_size,
 			  u16 *grps_del, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_add_move_delete_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.add_move_delete_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_delete_sched_elems);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	cmd->num_grps_req = cpu_to_le16(grps_req);
-
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && grps_del)
-		*grps_del = le16_to_cpu(cmd->num_grps_updated);
-
-	return status;
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_delete_sched_elems,
+					   grps_req, (void *)buf, buf_size,
+					   grps_del, cd);
 }
 
 /**
- * ice_sched_remove_elems - remove nodes from hw
- * @hw: pointer to the hw struct
+ * ice_sched_remove_elems - remove nodes from HW
+ * @hw: pointer to the HW struct
  * @parent: pointer to the parent node
  * @num_nodes: number of nodes
  * @node_teids: array of node teids to be deleted
  *
- * This function remove nodes from hw
+ * This function remove nodes from HW
  */
 static enum ice_status
 ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent,
@@ -265,7 +251,8 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent,
 	status = ice_aq_delete_sched_elems(hw, 1, buf, buf_size,
 					   &num_groups_removed, NULL);
 	if (status || num_groups_removed != 1)
-		ice_debug(hw, ICE_DBG_SCHED, "remove elements failed\n");
+		ice_debug(hw, ICE_DBG_SCHED, "remove node failed FW error %d\n",
+			  hw->adminq.sq_last_status);
 
 	devm_kfree(ice_hw_to_dev(hw), buf);
 	return status;
@@ -273,7 +260,7 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent,
 
 /**
  * ice_sched_get_first_node - get the first node of the given layer
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @parent: pointer the base node of the subtree
  * @layer: layer number
  *
@@ -349,12 +336,8 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node)
 	    node->info.data.elem_type != ICE_AQC_ELEM_TYPE_ROOT_PORT &&
 	    node->info.data.elem_type != ICE_AQC_ELEM_TYPE_LEAF) {
 		u32 teid = le32_to_cpu(node->info.node_teid);
-		enum ice_status status;
 
-		status = ice_sched_remove_elems(hw, node->parent, 1, &teid);
-		if (status)
-			ice_debug(hw, ICE_DBG_SCHED,
-				  "remove element failed %d\n", status);
+		ice_sched_remove_elems(hw, node->parent, 1, &teid);
 	}
 	parent = node->parent;
 	/* root has no parent */
@@ -398,7 +381,7 @@ err_exit:
 
 /**
  * ice_aq_get_dflt_topo - gets default scheduler topology
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @lport: logical port number
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
@@ -428,7 +411,7 @@ ice_aq_get_dflt_topo(struct ice_hw *hw, u8 lport,
 
 /**
  * ice_aq_add_sched_elems - adds scheduling element
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @grps_req: the number of groups that are requested to be added
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
@@ -442,57 +425,14 @@ ice_aq_add_sched_elems(struct ice_hw *hw, u16 grps_req,
 		       struct ice_aqc_add_elem *buf, u16 buf_size,
 		       u16 *grps_added, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_add_move_delete_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.add_move_delete_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_sched_elems);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	cmd->num_grps_req = cpu_to_le16(grps_req);
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && grps_added)
-		*grps_added = le16_to_cpu(cmd->num_grps_updated);
-
-	return status;
-}
-
-/**
- * ice_suspend_resume_elems - suspend/resume scheduler elements
- * @hw: pointer to the hw struct
- * @elems_req: number of elements to suspend
- * @buf: pointer to buffer
- * @buf_size: buffer size in bytes
- * @elems_ret: returns total number of elements suspended
- * @cd: pointer to command details structure or NULL
- * @cmd_code: command code for suspend or resume
- *
- * suspend/resume scheduler elements
- */
-static enum ice_status
-ice_suspend_resume_elems(struct ice_hw *hw, u16 elems_req,
-			 struct ice_aqc_suspend_resume_elem *buf, u16 buf_size,
-			 u16 *elems_ret, struct ice_sq_cd *cd,
-			 enum ice_adminq_opc cmd_code)
-{
-	struct ice_aqc_get_cfg_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.get_update_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, cmd_code);
-	cmd->num_elem_req = cpu_to_le16(elems_req);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && elems_ret)
-		*elems_ret = le16_to_cpu(cmd->num_elem_resp);
-	return status;
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_add_sched_elems,
+					   grps_req, (void *)buf, buf_size,
+					   grps_added, cd);
 }
 
 /**
  * ice_aq_suspend_sched_elems - suspend scheduler elements
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @elems_req: number of elements to suspend
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
@@ -506,13 +446,14 @@ ice_aq_suspend_sched_elems(struct ice_hw *hw, u16 elems_req,
 			   struct ice_aqc_suspend_resume_elem *buf,
 			   u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
 {
-	return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
-					cd, ice_aqc_opc_suspend_sched_elems);
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_suspend_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
 }
 
 /**
  * ice_aq_resume_sched_elems - resume scheduler elements
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @elems_req: number of elements to resume
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
@@ -526,13 +467,14 @@ ice_aq_resume_sched_elems(struct ice_hw *hw, u16 elems_req,
 			  struct ice_aqc_suspend_resume_elem *buf,
 			  u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
 {
-	return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
-					cd, ice_aqc_opc_resume_sched_elems);
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_resume_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
 }
 
 /**
  * ice_aq_query_sched_res - query scheduler resource
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @buf_size: buffer size in bytes
  * @buf: pointer to buffer
  * @cd: pointer to command details structure or NULL
@@ -551,13 +493,13 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size,
 }
 
 /**
- * ice_sched_suspend_resume_elems - suspend or resume hw nodes
- * @hw: pointer to the hw struct
+ * ice_sched_suspend_resume_elems - suspend or resume HW nodes
+ * @hw: pointer to the HW struct
  * @num_nodes: number of nodes
  * @node_teids: array of node teids to be suspended or resumed
  * @suspend: true means suspend / false means resume
  *
- * This function suspends or resumes hw nodes
+ * This function suspends or resumes HW nodes
  */
 static enum ice_status
 ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
@@ -591,23 +533,62 @@ ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
 }
 
 /**
- * ice_sched_clear_tx_topo - clears the schduler tree nodes
- * @pi: port information structure
+ * ice_alloc_lan_q_ctx - allocate LAN queue contexts for the given VSI and TC
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ * @tc: TC number
+ * @new_numqs: number of queues
+ */
+static enum ice_status
+ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs)
+{
+	struct ice_vsi_ctx *vsi_ctx;
+	struct ice_q_ctx *q_ctx;
+
+	vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
+	if (!vsi_ctx)
+		return ICE_ERR_PARAM;
+	/* allocate LAN queue contexts */
+	if (!vsi_ctx->lan_q_ctx[tc]) {
+		vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw),
+						      new_numqs,
+						      sizeof(*q_ctx),
+						      GFP_KERNEL);
+		if (!vsi_ctx->lan_q_ctx[tc])
+			return ICE_ERR_NO_MEMORY;
+		vsi_ctx->num_lan_q_entries[tc] = new_numqs;
+		return 0;
+	}
+	/* num queues are increased, update the queue contexts */
+	if (new_numqs > vsi_ctx->num_lan_q_entries[tc]) {
+		u16 prev_num = vsi_ctx->num_lan_q_entries[tc];
+
+		q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs,
+				     sizeof(*q_ctx), GFP_KERNEL);
+		if (!q_ctx)
+			return ICE_ERR_NO_MEMORY;
+		memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc],
+		       prev_num * sizeof(*q_ctx));
+		devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]);
+		vsi_ctx->lan_q_ctx[tc] = q_ctx;
+		vsi_ctx->num_lan_q_entries[tc] = new_numqs;
+	}
+	return 0;
+}
+
+/**
+ * ice_sched_clear_agg - clears the aggregator related information
+ * @hw: pointer to the hardware structure
  *
- * This function removes all the nodes from HW as well as from SW DB.
+ * This function removes aggregator list and free up aggregator related memory
+ * previously allocated.
  */
-static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+void ice_sched_clear_agg(struct ice_hw *hw)
 {
 	struct ice_sched_agg_info *agg_info;
 	struct ice_sched_agg_info *atmp;
-	struct ice_hw *hw;
 
-	if (!pi)
-		return;
-
-	hw = pi->hw;
-
-	list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) {
+	list_for_each_entry_safe(agg_info, atmp, &hw->agg_list, list_entry) {
 		struct ice_sched_agg_vsi_info *agg_vsi_info;
 		struct ice_sched_agg_vsi_info *vtmp;
 
@@ -616,8 +597,21 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
 			list_del(&agg_vsi_info->list_entry);
 			devm_kfree(ice_hw_to_dev(hw), agg_vsi_info);
 		}
+		list_del(&agg_info->list_entry);
+		devm_kfree(ice_hw_to_dev(hw), agg_info);
 	}
+}
 
+/**
+ * ice_sched_clear_tx_topo - clears the scheduler tree nodes
+ * @pi: port information structure
+ *
+ * This function removes all the nodes from HW as well as from SW DB.
+ */
+static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+{
+	if (!pi)
+		return;
 	if (pi->root) {
 		ice_free_sched_node(pi, pi->root);
 		pi->root = NULL;
@@ -644,7 +638,7 @@ void ice_sched_clear_port(struct ice_port_info *pi)
 
 /**
  * ice_sched_cleanup_all - cleanup scheduler elements from SW DB for all ports
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Cleanup scheduling elements from SW DB for all the ports
  */
@@ -668,16 +662,16 @@ void ice_sched_cleanup_all(struct ice_hw *hw)
 }
 
 /**
- * ice_sched_add_elems - add nodes to hw and SW DB
+ * ice_sched_add_elems - add nodes to HW and SW DB
  * @pi: port information structure
  * @tc_node: pointer to the branch node
  * @parent: pointer to the parent node
  * @layer: layer number to add nodes
  * @num_nodes: number of nodes
  * @num_nodes_added: pointer to num nodes added
- * @first_node_teid: if new nodes are added then return the teid of first node
+ * @first_node_teid: if new nodes are added then return the TEID of first node
  *
- * This function add nodes to hw as well as to SW DB for a given layer
+ * This function add nodes to HW as well as to SW DB for a given layer
  */
 static enum ice_status
 ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node,
@@ -689,10 +683,10 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node,
 	u16 i, num_groups_added = 0;
 	enum ice_status status = 0;
 	struct ice_hw *hw = pi->hw;
-	u16 buf_size;
+	size_t buf_size;
 	u32 teid;
 
-	buf_size = sizeof(*buf) + sizeof(*buf->generic) * (num_nodes - 1);
+	buf_size = struct_size(buf, generic, num_nodes - 1);
 	buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL);
 	if (!buf)
 		return ICE_ERR_NO_MEMORY;
@@ -719,7 +713,8 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node,
 	status = ice_aq_add_sched_elems(hw, 1, buf, buf_size,
 					&num_groups_added, NULL);
 	if (status || num_groups_added != 1) {
-		ice_debug(hw, ICE_DBG_SCHED, "add elements failed\n");
+		ice_debug(hw, ICE_DBG_SCHED, "add node failed FW Error %d\n",
+			  hw->adminq.sq_last_status);
 		devm_kfree(ice_hw_to_dev(hw), buf);
 		return ICE_ERR_CFG;
 	}
@@ -770,7 +765,7 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node,
  * @parent: pointer to parent node
  * @layer: layer number to add nodes
  * @num_nodes: number of nodes to be added
- * @first_node_teid: pointer to the first node teid
+ * @first_node_teid: pointer to the first node TEID
  * @num_nodes_added: pointer to number of nodes added
  *
  * This function add nodes to a given layer.
@@ -822,7 +817,7 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 
 			*num_nodes_added += num_added;
 		}
-		/* Don't modify the first node teid memory if the first node was
+		/* Don't modify the first node TEID memory if the first node was
 		 * added already in the above call. Instead send some temp
 		 * memory for all other recursive calls.
 		 */
@@ -854,7 +849,7 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi,
 
 /**
  * ice_sched_get_qgrp_layer - get the current queue group layer number
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * This function returns the current queue group layer number
  */
@@ -866,7 +861,7 @@ static u8 ice_sched_get_qgrp_layer(struct ice_hw *hw)
 
 /**
  * ice_sched_get_vsi_layer - get the current VSI layer number
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * This function returns the current VSI layer number
  */
@@ -877,7 +872,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
 	 *     7               4
 	 *     5 or less       sw_entry_point_layer
 	 */
-	/* calculate the vsi layer based on number of layers. */
+	/* calculate the VSI layer based on number of layers. */
 	if (hw->num_tx_sched_layers > ICE_VSI_LAYER_OFFSET + 1) {
 		u8 layer = hw->num_tx_sched_layers - ICE_VSI_LAYER_OFFSET;
 
@@ -995,7 +990,7 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi)
 		goto err_init_port;
 	}
 
-	/* If the last node is a leaf node then the index of the Q group
+	/* If the last node is a leaf node then the index of the queue group
 	 * layer is two less than the number of elements.
 	 */
 	if (num_elems > 2 && buf[0].generic[num_elems - 1].data.elem_type ==
@@ -1035,7 +1030,6 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi)
 	/* initialize the port for handling the scheduler tree */
 	pi->port_state = ICE_SCHED_PORT_STATE_READY;
 	mutex_init(&pi->sched_lock);
-	INIT_LIST_HEAD(&pi->agg_list);
 
 err_init_port:
 	if (status && pi->root) {
@@ -1089,11 +1083,10 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw)
 		hw->max_children[i] = le16_to_cpu(max_sibl);
 	}
 
-	hw->layer_info = (struct ice_aqc_layer_props *)
-			  devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props,
-				       (hw->num_tx_sched_layers *
-					sizeof(*hw->layer_info)),
-				       GFP_KERNEL);
+	hw->layer_info = devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props,
+				      (hw->num_tx_sched_layers *
+				       sizeof(*hw->layer_info)),
+				      GFP_KERNEL);
 	if (!hw->layer_info) {
 		status = ICE_ERR_NO_MEMORY;
 		goto sched_query_out;
@@ -1106,7 +1099,7 @@ sched_query_out:
 
 /**
  * ice_sched_find_node_in_subtree - Find node in part of base node subtree
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @base: pointer to the base node
  * @node: pointer to the node to search
  *
@@ -1138,13 +1131,13 @@ ice_sched_find_node_in_subtree(struct ice_hw *hw, struct ice_sched_node *base,
 }
 
 /**
- * ice_sched_get_free_qparent - Get a free lan or rdma q group node
+ * ice_sched_get_free_qparent - Get a free LAN or RDMA queue group node
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  * @tc: branch number
- * @owner: lan or rdma
+ * @owner: LAN or RDMA
  *
- * This function retrieves a free lan or rdma q group node
+ * This function retrieves a free LAN or RDMA queue group node
  */
 struct ice_sched_node *
 ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
@@ -1162,11 +1155,11 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 	if (!vsi_ctx)
 		return NULL;
 	vsi_node = vsi_ctx->sched.vsi_node[tc];
-	/* validate invalid VSI id */
+	/* validate invalid VSI ID */
 	if (!vsi_node)
 		goto lan_q_exit;
 
-	/* get the first q group node from VSI sub-tree */
+	/* get the first queue group node from VSI sub-tree */
 	qgrp_node = ice_sched_get_first_node(pi->hw, vsi_node, qgrp_layer);
 	while (qgrp_node) {
 		/* make sure the qgroup node is part of the VSI subtree */
@@ -1182,12 +1175,12 @@ lan_q_exit:
 }
 
 /**
- * ice_sched_get_vsi_node - Get a VSI node based on VSI id
- * @hw: pointer to the hw struct
+ * ice_sched_get_vsi_node - Get a VSI node based on VSI ID
+ * @hw: pointer to the HW struct
  * @tc_node: pointer to the TC node
  * @vsi_handle: software VSI handle
  *
- * This function retrieves a VSI node for a given VSI id from a given
+ * This function retrieves a VSI node for a given VSI ID from a given
  * TC branch
  */
 static struct ice_sched_node *
@@ -1212,7 +1205,7 @@ ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node,
 
 /**
  * ice_sched_calc_vsi_child_nodes - calculate number of VSI child nodes
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @num_qs: number of queues
  * @num_nodes: num nodes array
  *
@@ -1228,7 +1221,7 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes)
 	qgl = ice_sched_get_qgrp_layer(hw);
 	vsil = ice_sched_get_vsi_layer(hw);
 
-	/* calculate num nodes from q group to VSI layer */
+	/* calculate num nodes from queue group to VSI layer */
 	for (i = qgl; i > vsil; i--) {
 		/* round to the next integer if there is a remainder */
 		num = DIV_ROUND_UP(num, hw->max_children[i]);
@@ -1244,10 +1237,10 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes)
  * @vsi_handle: software VSI handle
  * @tc_node: pointer to the TC node
  * @num_nodes: pointer to the num nodes that needs to be added per layer
- * @owner: node owner (lan or rdma)
+ * @owner: node owner (LAN or RDMA)
  *
  * This function adds the VSI child nodes to tree. It gets called for
- * lan and rdma separately.
+ * LAN and RDMA separately.
  */
 static enum ice_status
 ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
@@ -1295,44 +1288,8 @@ ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 }
 
 /**
- * ice_sched_rm_vsi_child_nodes - remove VSI child nodes from the tree
- * @pi: port information structure
- * @vsi_node: pointer to the VSI node
- * @num_nodes: pointer to the num nodes that needs to be removed per layer
- * @owner: node owner (lan or rdma)
- *
- * This function removes the VSI child nodes from the tree. It gets called for
- * lan and rdma separately.
- */
-static void
-ice_sched_rm_vsi_child_nodes(struct ice_port_info *pi,
-			     struct ice_sched_node *vsi_node, u16 *num_nodes,
-			     u8 owner)
-{
-	struct ice_sched_node *node, *next;
-	u8 i, qgl, vsil;
-	u16 num;
-
-	qgl = ice_sched_get_qgrp_layer(pi->hw);
-	vsil = ice_sched_get_vsi_layer(pi->hw);
-
-	for (i = qgl; i > vsil; i--) {
-		num = num_nodes[i];
-		node = ice_sched_get_first_node(pi->hw, vsi_node, i);
-		while (node && num) {
-			next = node->sibling;
-			if (node->owner == owner && !node->num_children) {
-				ice_free_sched_node(pi, node);
-				num--;
-			}
-			node = next;
-		}
-	}
-}
-
-/**
  * ice_sched_calc_vsi_support_nodes - calculate number of VSI support nodes
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @tc_node: pointer to TC node
  * @num_nodes: pointer to num nodes array
  *
@@ -1367,9 +1324,14 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw,
 				node = node->sibling;
 			}
 
+			/* tree has one intermediate node to add this new VSI.
+			 * So no need to calculate supported nodes for below
+			 * layers.
+			 */
+			if (node)
+				break;
 			/* all the nodes are full, allocate a new one */
-			if (!node)
-				num_nodes[i]++;
+			num_nodes[i]++;
 		}
 }
 
@@ -1446,7 +1408,7 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc)
 	/* calculate number of supported nodes needed for this VSI */
 	ice_sched_calc_vsi_support_nodes(hw, tc_node, num_nodes);
 
-	/* add vsi supported nodes to tc subtree */
+	/* add VSI supported nodes to TC subtree */
 	return ice_sched_add_vsi_support_nodes(pi, vsi_handle, tc_node,
 					       num_nodes);
 }
@@ -1465,7 +1427,6 @@ static enum ice_status
 ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 				 u8 tc, u16 new_numqs, u8 owner)
 {
-	u16 prev_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
 	u16 new_num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 };
 	struct ice_sched_node *vsi_node;
 	struct ice_sched_node *tc_node;
@@ -1473,7 +1434,6 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 	enum ice_status status = 0;
 	struct ice_hw *hw = pi->hw;
 	u16 prev_numqs;
-	u8 i;
 
 	tc_node = ice_sched_get_tc_node(pi, tc);
 	if (!tc_node)
@@ -1487,41 +1447,30 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 	if (!vsi_ctx)
 		return ICE_ERR_PARAM;
 
-	if (owner == ICE_SCHED_NODE_OWNER_LAN)
-		prev_numqs = vsi_ctx->sched.max_lanq[tc];
-	else
-		return ICE_ERR_PARAM;
-
-	/* num queues are not changed */
-	if (prev_numqs == new_numqs)
+	prev_numqs = vsi_ctx->sched.max_lanq[tc];
+	/* num queues are not changed or less than the previous number */
+	if (new_numqs <= prev_numqs)
+		return status;
+	status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs);
+	if (status)
 		return status;
-
-	/* calculate number of nodes based on prev/new number of qs */
-	if (prev_numqs)
-		ice_sched_calc_vsi_child_nodes(hw, prev_numqs, prev_num_nodes);
 
 	if (new_numqs)
 		ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes);
-
-	if (prev_numqs > new_numqs) {
-		for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++)
-			new_num_nodes[i] = prev_num_nodes[i] - new_num_nodes[i];
-
-		ice_sched_rm_vsi_child_nodes(pi, vsi_node, new_num_nodes,
-					     owner);
-	} else {
-		for (i = 0; i < ICE_AQC_TOPO_MAX_LEVEL_NUM; i++)
-			new_num_nodes[i] -= prev_num_nodes[i];
-
-		status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node,
-						       new_num_nodes, owner);
-		if (status)
-			return status;
-	}
-
+	/* Keep the max number of queue configuration all the time. Update the
+	 * tree only if number of queues > previous number of queues. This may
+	 * leave some extra nodes in the tree if number of queues < previous
+	 * number but that wouldn't harm anything. Removing those extra nodes
+	 * may complicate the code if those nodes are part of SRL or
+	 * individually rate limited.
+	 */
+	status = ice_sched_add_vsi_child_nodes(pi, vsi_handle, tc_node,
+					       new_num_nodes, owner);
+	if (status)
+		return status;
 	vsi_ctx->sched.max_lanq[tc] = new_numqs;
 
-	return status;
+	return 0;
 }
 
 /**
@@ -1530,7 +1479,7 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
  * @vsi_handle: software VSI handle
  * @tc: TC number
  * @maxqs: max number of queues
- * @owner: lan or rdma
+ * @owner: LAN or RDMA
  * @enable: TC enabled or disabled
  *
  * This function adds/updates VSI nodes based on the number of queues. If TC is
@@ -1546,6 +1495,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 	enum ice_status status = 0;
 	struct ice_hw *hw = pi->hw;
 
+	ice_debug(pi->hw, ICE_DBG_SCHED, "add/config VSI %d\n", vsi_handle);
 	tc_node = ice_sched_get_tc_node(pi, tc);
 	if (!tc_node)
 		return ICE_ERR_PARAM;
@@ -1554,7 +1504,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 		return ICE_ERR_PARAM;
 	vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_handle);
 
-	/* suspend the VSI if tc is not enabled */
+	/* suspend the VSI if TC is not enabled */
 	if (!enable) {
 		if (vsi_node && vsi_node->in_use) {
 			u32 teid = le32_to_cpu(vsi_node->info.node_teid);
@@ -1605,7 +1555,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 }
 
 /**
- * ice_sched_rm_agg_vsi_entry - remove agg related VSI info entry
+ * ice_sched_rm_agg_vsi_entry - remove aggregator related VSI info entry
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  *
@@ -1618,7 +1568,8 @@ ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
 	struct ice_sched_agg_info *agg_info;
 	struct ice_sched_agg_info *atmp;
 
-	list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) {
+	list_for_each_entry_safe(agg_info, atmp, &pi->hw->agg_list,
+				 list_entry) {
 		struct ice_sched_agg_vsi_info *agg_vsi_info;
 		struct ice_sched_agg_vsi_info *vtmp;
 
@@ -1634,6 +1585,23 @@ ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
 }
 
 /**
+ * ice_sched_is_leaf_node_present - check for a leaf node in the sub-tree
+ * @node: pointer to the sub-tree node
+ *
+ * This function checks for a leaf node presence in a given sub-tree node.
+ */
+static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node)
+{
+	u8 i;
+
+	for (i = 0; i < node->num_children; i++)
+		if (ice_sched_is_leaf_node_present(node->children[i]))
+			return true;
+	/* check for a leaf node */
+	return (node->info.data.elem_type == ICE_AQC_ELEM_TYPE_LEAF);
+}
+
+/**
  * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
  * @pi: port information structure
  * @vsi_handle: software VSI handle
@@ -1647,8 +1615,9 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 {
 	enum ice_status status = ICE_ERR_PARAM;
 	struct ice_vsi_ctx *vsi_ctx;
-	u8 i, j = 0;
+	u8 i;
 
+	ice_debug(pi->hw, ICE_DBG_SCHED, "removing VSI %d\n", vsi_handle);
 	if (!ice_is_vsi_valid(pi->hw, vsi_handle))
 		return status;
 	mutex_lock(&pi->sched_lock);
@@ -1656,8 +1625,9 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 	if (!vsi_ctx)
 		goto exit_sched_rm_vsi_cfg;
 
-	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+	ice_for_each_traffic_class(i) {
 		struct ice_sched_node *vsi_node, *tc_node;
+		u8 j = 0;
 
 		tc_node = ice_sched_get_tc_node(pi, i);
 		if (!tc_node)
@@ -1667,6 +1637,12 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 		if (!vsi_node)
 			continue;
 
+		if (ice_sched_is_leaf_node_present(vsi_node)) {
+			ice_debug(pi->hw, ICE_DBG_SCHED,
+				  "VSI has leaf nodes in TC %d\n", i);
+			status = ICE_ERR_IN_USE;
+			goto exit_sched_rm_vsi_cfg;
+		}
 		while (j < vsi_node->num_children) {
 			if (vsi_node->children[j]->owner == owner) {
 				ice_free_sched_node(pi, vsi_node->children[j]);
@@ -1684,7 +1660,7 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
 			ice_free_sched_node(pi, vsi_node);
 			vsi_ctx->sched.vsi_node[i] = NULL;
 
-			/* clean up agg related vsi info if any */
+			/* clean up aggregator related VSI info if any */
 			ice_sched_rm_agg_vsi_info(pi, vsi_handle);
 		}
 		if (owner == ICE_SCHED_NODE_OWNER_LAN)
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index da5b4c166da8..3902a8ad3025 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -24,10 +24,16 @@ struct ice_sched_agg_info {
 };
 
 /* FW AQ command calls */
+enum ice_status
+ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
+			 struct ice_aqc_get_elem *buf, u16 buf_size,
+			 u16 *elems_ret, struct ice_sq_cd *cd);
 enum ice_status ice_sched_init_port(struct ice_port_info *pi);
 enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw);
 void ice_sched_clear_port(struct ice_port_info *pi);
 void ice_sched_cleanup_all(struct ice_hw *hw);
+void ice_sched_clear_agg(struct ice_hw *hw);
+
 struct ice_sched_node *
 ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid);
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 533b989a23e1..d2db0d04e117 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -85,6 +85,12 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
 		case ICE_AQ_LINK_SPEED_40GB:
 			speed = ICE_LINK_SPEED_40000MBPS;
 			break;
+		case ICE_AQ_LINK_SPEED_50GB:
+			speed = ICE_LINK_SPEED_50000MBPS;
+			break;
+		case ICE_AQ_LINK_SPEED_100GB:
+			speed = ICE_LINK_SPEED_100000MBPS;
+			break;
 		default:
 			speed = ICE_LINK_SPEED_UNKNOWN;
 			break;
@@ -116,6 +122,9 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
 			break;
 		case ICE_AQ_LINK_SPEED_40GB:
 			/* fall through */
+		case ICE_AQ_LINK_SPEED_50GB:
+			/* fall through */
+		case ICE_AQ_LINK_SPEED_100GB:
 			speed = (u32)VIRTCHNL_LINK_SPEED_40GB;
 			break;
 		default:
diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h
index f49f299ddf2c..c01597885629 100644
--- a/drivers/net/ethernet/intel/ice/ice_status.h
+++ b/drivers/net/ethernet/intel/ice/ice_status.h
@@ -12,6 +12,7 @@ enum ice_status {
 	ICE_ERR_PARAM				= -1,
 	ICE_ERR_NOT_IMPL			= -2,
 	ICE_ERR_NOT_READY			= -3,
+	ICE_ERR_NOT_SUPPORTED			= -4,
 	ICE_ERR_BAD_PTR				= -5,
 	ICE_ERR_INVAL_SIZE			= -6,
 	ICE_ERR_DEVICE_NOT_SUPPORTED		= -8,
@@ -22,8 +23,10 @@ enum ice_status {
 	ICE_ERR_OUT_OF_RANGE			= -13,
 	ICE_ERR_ALREADY_EXISTS			= -14,
 	ICE_ERR_DOES_NOT_EXIST			= -15,
+	ICE_ERR_IN_USE				= -16,
 	ICE_ERR_MAX_LIMIT			= -17,
 	ICE_ERR_RESET_ONGOING			= -18,
+	ICE_ERR_NVM_CHECKSUM			= -51,
 	ICE_ERR_BUF_TOO_SHORT			= -52,
 	ICE_ERR_NVM_BLANK_MODE			= -53,
 	ICE_ERR_AQ_ERROR			= -100,
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 2e5693107fa4..8271fd651725 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -19,7 +19,7 @@
  * byte 6 = 0x2: to identify it as locally administered SA MAC
  * byte 12 = 0x81 & byte 13 = 0x00:
  *	In case of VLAN filter first two bytes defines ether type (0x8100)
- *	and remaining two bytes are placeholder for programming a given VLAN id
+ *	and remaining two bytes are placeholder for programming a given VLAN ID
  *	In case of Ether type filter it is treated as header without VLAN tag
  *	and byte 12 and 13 is used to program a given Ether type instead
  */
@@ -51,7 +51,7 @@ static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0,
 
 /**
  * ice_aq_alloc_free_res - command to allocate/free resources
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @num_entries: number of resource entries in buffer
  * @buf: Indirect buffer to hold data parameters and response
  * @buf_size: size of buffer for indirect commands
@@ -87,7 +87,7 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
 
 /**
  * ice_init_def_sw_recp - initialize the recipe book keeping tables
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Allocate memory for the entire recipe table and initialize the structures/
  * entries corresponding to basic recipes.
@@ -98,7 +98,7 @@ enum ice_status ice_init_def_sw_recp(struct ice_hw *hw)
 	u8 i;
 
 	recps = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_NUM_RECIPES,
-			     sizeof(struct ice_sw_recipe), GFP_KERNEL);
+			     sizeof(*recps), GFP_KERNEL);
 	if (!recps)
 		return ICE_ERR_NO_MEMORY;
 
@@ -163,7 +163,7 @@ ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp *buf,
 
 /**
  * ice_aq_add_vsi
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_ctx: pointer to a VSI context struct
  * @cd: pointer to command details structure or NULL
  *
@@ -206,7 +206,7 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 
 /**
  * ice_aq_free_vsi
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_ctx: pointer to a VSI context struct
  * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources
  * @cd: pointer to command details structure or NULL
@@ -242,7 +242,7 @@ ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 
 /**
  * ice_aq_update_vsi
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_ctx: pointer to a VSI context struct
  * @cd: pointer to command details structure or NULL
  *
@@ -279,7 +279,7 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 
 /**
  * ice_is_vsi_valid - check whether the VSI is valid or not
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: VSI handle
  *
  * check whether the VSI is valid or not
@@ -290,11 +290,11 @@ bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle)
 }
 
 /**
- * ice_get_hw_vsi_num - return the hw VSI number
- * @hw: pointer to the hw struct
+ * ice_get_hw_vsi_num - return the HW VSI number
+ * @hw: pointer to the HW struct
  * @vsi_handle: VSI handle
  *
- * return the hw VSI number
+ * return the HW VSI number
  * Caution: call this function only if VSI is valid (ice_is_vsi_valid)
  */
 u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle)
@@ -304,7 +304,7 @@ u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle)
 
 /**
  * ice_get_vsi_ctx - return the VSI context entry for a given VSI handle
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: VSI handle
  *
  * return the VSI context entry for a given VSI handle
@@ -316,21 +316,42 @@ struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle)
 
 /**
  * ice_save_vsi_ctx - save the VSI context for a given VSI handle
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: VSI handle
  * @vsi: VSI context pointer
  *
  * save the VSI context entry for a given VSI handle
  */
-static void ice_save_vsi_ctx(struct ice_hw *hw, u16 vsi_handle,
-			     struct ice_vsi_ctx *vsi)
+static void
+ice_save_vsi_ctx(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi)
 {
 	hw->vsi_ctx[vsi_handle] = vsi;
 }
 
 /**
+ * ice_clear_vsi_q_ctx - clear VSI queue contexts for all TCs
+ * @hw: pointer to the HW struct
+ * @vsi_handle: VSI handle
+ */
+static void ice_clear_vsi_q_ctx(struct ice_hw *hw, u16 vsi_handle)
+{
+	struct ice_vsi_ctx *vsi;
+	u8 i;
+
+	vsi = ice_get_vsi_ctx(hw, vsi_handle);
+	if (!vsi)
+		return;
+	ice_for_each_traffic_class(i) {
+		if (vsi->lan_q_ctx[i]) {
+			devm_kfree(ice_hw_to_dev(hw), vsi->lan_q_ctx[i]);
+			vsi->lan_q_ctx[i] = NULL;
+		}
+	}
+}
+
+/**
  * ice_clear_vsi_ctx - clear the VSI context entry
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: VSI handle
  *
  * clear the VSI context entry
@@ -341,6 +362,7 @@ static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle)
 
 	vsi = ice_get_vsi_ctx(hw, vsi_handle);
 	if (vsi) {
+		ice_clear_vsi_q_ctx(hw, vsi_handle);
 		devm_kfree(ice_hw_to_dev(hw), vsi);
 		hw->vsi_ctx[vsi_handle] = NULL;
 	}
@@ -348,7 +370,7 @@ static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle)
 
 /**
  * ice_clear_all_vsi_ctx - clear all the VSI context entries
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  */
 void ice_clear_all_vsi_ctx(struct ice_hw *hw)
 {
@@ -360,7 +382,7 @@ void ice_clear_all_vsi_ctx(struct ice_hw *hw)
 
 /**
  * ice_add_vsi - add VSI context to the hardware and VSI handle list
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: unique VSI handle provided by drivers
  * @vsi_ctx: pointer to a VSI context struct
  * @cd: pointer to command details structure or NULL
@@ -383,7 +405,7 @@ ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
 		return status;
 	tmp_vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle);
 	if (!tmp_vsi_ctx) {
-		/* Create a new vsi context */
+		/* Create a new VSI context */
 		tmp_vsi_ctx = devm_kzalloc(ice_hw_to_dev(hw),
 					   sizeof(*tmp_vsi_ctx), GFP_KERNEL);
 		if (!tmp_vsi_ctx) {
@@ -398,12 +420,12 @@ ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
 			tmp_vsi_ctx->vsi_num = vsi_ctx->vsi_num;
 	}
 
-	return status;
+	return 0;
 }
 
 /**
  * ice_free_vsi- free VSI context from hardware and VSI handle list
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: unique VSI handle
  * @vsi_ctx: pointer to a VSI context struct
  * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources
@@ -428,7 +450,7 @@ ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
 
 /**
  * ice_update_vsi
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle: unique VSI handle
  * @vsi_ctx: pointer to a VSI context struct
  * @cd: pointer to command details structure or NULL
@@ -447,8 +469,8 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
 
 /**
  * ice_aq_alloc_free_vsi_list
- * @hw: pointer to the hw struct
- * @vsi_list_id: VSI list id returned or used for lookup
+ * @hw: pointer to the HW struct
+ * @vsi_list_id: VSI list ID returned or used for lookup
  * @lkup_type: switch rule filter lookup type
  * @opc: switch rules population command type - pass in the command opcode
  *
@@ -504,7 +526,7 @@ ice_aq_alloc_free_vsi_list_exit:
 
 /**
  * ice_aq_sw_rules - add/update/remove switch rules
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @rule_list: pointer to switch rule population list
  * @rule_list_sz: total size of the rule list in bytes
  * @num_rules: number of switch rules in the rule_list
@@ -643,21 +665,43 @@ static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi)
 	     fi->fltr_act == ICE_FWD_TO_VSI_LIST ||
 	     fi->fltr_act == ICE_FWD_TO_Q ||
 	     fi->fltr_act == ICE_FWD_TO_QGRP)) {
-		fi->lb_en = true;
-		/* Do not set lan_en to TRUE if
+		/* Setting LB for prune actions will result in replicated
+		 * packets to the internal switch that will be dropped.
+		 */
+		if (fi->lkup_type != ICE_SW_LKUP_VLAN)
+			fi->lb_en = true;
+
+		/* Set lan_en to TRUE if
 		 * 1. The switch is a VEB AND
 		 * 2
-		 * 2.1 The lookup is MAC with unicast addr for MAC, OR
-		 * 2.2 The lookup is MAC_VLAN with unicast addr for MAC
+		 * 2.1 The lookup is a directional lookup like ethertype,
+		 * promiscuous, ethertype-MAC, promiscuous-VLAN
+		 * and default-port OR
+		 * 2.2 The lookup is VLAN, OR
+		 * 2.3 The lookup is MAC with mcast or bcast addr for MAC, OR
+		 * 2.4 The lookup is MAC_VLAN with mcast or bcast addr for MAC.
+		 *
+		 * OR
+		 *
+		 * The switch is a VEPA.
 		 *
-		 * In all other cases, the LAN enable has to be set to true.
+		 * In all other cases, the LAN enable has to be set to false.
 		 */
-		if (!(hw->evb_veb &&
-		      ((fi->lkup_type == ICE_SW_LKUP_MAC &&
-			is_unicast_ether_addr(fi->l_data.mac.mac_addr)) ||
-		       (fi->lkup_type == ICE_SW_LKUP_MAC_VLAN &&
-			is_unicast_ether_addr(fi->l_data.mac_vlan.mac_addr)))))
+		if (hw->evb_veb) {
+			if (fi->lkup_type == ICE_SW_LKUP_ETHERTYPE ||
+			    fi->lkup_type == ICE_SW_LKUP_PROMISC ||
+			    fi->lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC ||
+			    fi->lkup_type == ICE_SW_LKUP_PROMISC_VLAN ||
+			    fi->lkup_type == ICE_SW_LKUP_DFLT ||
+			    fi->lkup_type == ICE_SW_LKUP_VLAN ||
+			    (fi->lkup_type == ICE_SW_LKUP_MAC &&
+			     !is_unicast_ether_addr(fi->l_data.mac.mac_addr)) ||
+			    (fi->lkup_type == ICE_SW_LKUP_MAC_VLAN &&
+			     !is_unicast_ether_addr(fi->l_data.mac.mac_addr)))
+				fi->lan_en = true;
+		} else {
 			fi->lan_en = true;
+		}
 	}
 }
 
@@ -755,7 +799,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info,
 		daddr = f_info->l_data.ethertype_mac.mac_addr;
 		/* fall-through */
 	case ICE_SW_LKUP_ETHERTYPE:
-		off = (__be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET);
+		off = (__force __be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET);
 		*off = cpu_to_be16(f_info->l_data.ethertype_mac.ethertype);
 		break;
 	case ICE_SW_LKUP_MAC_VLAN:
@@ -785,7 +829,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info,
 		ether_addr_copy(eth_hdr + ICE_ETH_DA_OFFSET, daddr);
 
 	if (!(vlan_id > ICE_MAX_VLAN_ID)) {
-		off = (__be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET);
+		off = (__force __be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET);
 		*off = cpu_to_be16(vlan_id);
 	}
 
@@ -799,7 +843,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info,
  * @hw: pointer to the hardware structure
  * @m_ent: the management entry for which sw marker needs to be added
  * @sw_marker: sw marker to tag the Rx descriptor with
- * @l_id: large action resource id
+ * @l_id: large action resource ID
  *
  * Create a large action to hold software marker and update the switch rule
  * entry pointed by m_ent with newly created large action
@@ -811,8 +855,8 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 	struct ice_aqc_sw_rules_elem *lg_act, *rx_tx;
 	/* For software marker we need 3 large actions
 	 * 1. FWD action: FWD TO VSI or VSI LIST
-	 * 2. GENERIC VALUE action to hold the profile id
-	 * 3. GENERIC VALUE action to hold the software marker id
+	 * 2. GENERIC VALUE action to hold the profile ID
+	 * 3. GENERIC VALUE action to hold the software marker ID
 	 */
 	const u16 num_lg_acts = 3;
 	enum ice_status status;
@@ -875,13 +919,13 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 	ice_fill_sw_rule(hw, &m_ent->fltr_info, rx_tx,
 			 ice_aqc_opc_update_sw_rules);
 
-	/* Update the action to point to the large action id */
+	/* Update the action to point to the large action ID */
 	rx_tx->pdata.lkup_tx_rx.act =
 		cpu_to_le32(ICE_SINGLE_ACT_PTR |
 			    ((l_id << ICE_SINGLE_ACT_PTR_VAL_S) &
 			     ICE_SINGLE_ACT_PTR_VAL_M));
 
-	/* Use the filter rule id of the previously created rule with single
+	/* Use the filter rule ID of the previously created rule with single
 	 * act. Once the update happens, hardware will treat this as large
 	 * action
 	 */
@@ -904,10 +948,10 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
  * @hw: pointer to the hardware structure
  * @vsi_handle_arr: array of VSI handles to set in the VSI mapping
  * @num_vsi: number of VSI handles in the array
- * @vsi_list_id: VSI list id generated as part of allocate resource
+ * @vsi_list_id: VSI list ID generated as part of allocate resource
  *
- * Helper function to create a new entry of VSI list id to VSI mapping
- * using the given VSI list id
+ * Helper function to create a new entry of VSI list ID to VSI mapping
+ * using the given VSI list ID
  */
 static struct ice_vsi_list_map_info *
 ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi,
@@ -935,13 +979,13 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi,
  * @hw: pointer to the hardware structure
  * @vsi_handle_arr: array of VSI handles to form a VSI list
  * @num_vsi: number of VSI handles in the array
- * @vsi_list_id: VSI list id generated as part of allocate resource
+ * @vsi_list_id: VSI list ID generated as part of allocate resource
  * @remove: Boolean value to indicate if this is a remove action
  * @opc: switch rules population command type - pass in the command opcode
  * @lkup_type: lookup type of the filter
  *
  * Call AQ command to add a new switch rule or update existing switch rule
- * using the given VSI list id
+ * using the given VSI list ID
  */
 static enum ice_status
 ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi,
@@ -998,7 +1042,7 @@ exit:
 
 /**
  * ice_create_vsi_list_rule - Creates and populates a VSI list rule
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  * @vsi_handle_arr: array of VSI handles to form a VSI list
  * @num_vsi: number of VSI handles in the array
  * @vsi_list_id: stores the ID of the VSI list to be created
@@ -1092,7 +1136,7 @@ ice_create_pkt_fwd_rule_exit:
  * @f_info: filter information for switch rule
  *
  * Call AQ command to update a previously created switch rule with a
- * VSI list id
+ * VSI list ID
  */
 static enum ice_status
 ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info)
@@ -1119,7 +1163,7 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info)
 
 /**
  * ice_update_sw_rule_bridge_mode
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Updates unicast switch filter rules based on VEB/VEPA mode
  */
@@ -1174,7 +1218,7 @@ enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw)
  *		Allocate a new VSI list and add two VSIs
  *		to this list using switch rule command
  *		Update the previously created switch rule with the
- *		newly created VSI list id
+ *		newly created VSI list ID
  *	if a VSI list was previously created
  *		Add the new VSI to the previously created VSI list set
  *		using the update switch rule command
@@ -1255,7 +1299,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 			return 0;
 
 		/* Update the previously created VSI list set with
-		 * the new VSI id passed in
+		 * the new VSI ID passed in
 		 */
 		vsi_list_id = cur_fltr->fwd_id.vsi_list_id;
 		opcode = ice_aqc_opc_update_sw_rules;
@@ -1263,7 +1307,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 		status = ice_update_vsi_list_rule(hw, &vsi_handle, 1,
 						  vsi_list_id, false, opcode,
 						  new_fltr->lkup_type);
-		/* update VSI list mapping info with new VSI id */
+		/* update VSI list mapping info with new VSI ID */
 		if (!status)
 			set_bit(vsi_handle, m_entry->vsi_list_info->vsi_map);
 	}
@@ -1305,7 +1349,7 @@ ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info)
  * @hw: pointer to the hardware structure
  * @recp_id: lookup type for which VSI lists needs to be searched
  * @vsi_handle: VSI handle to be found in VSI list
- * @vsi_list_id: VSI list id found containing vsi_handle
+ * @vsi_list_id: VSI list ID found containing vsi_handle
  *
  * Helper function to search a VSI list with single entry containing given VSI
  * handle element. This can be extended further to search VSI list with more
@@ -1336,7 +1380,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
 /**
  * ice_add_rule_internal - add rule for a given lookup type
  * @hw: pointer to the hardware structure
- * @recp_id: lookup type (recipe id) for which rule has to be added
+ * @recp_id: lookup type (recipe ID) for which rule has to be added
  * @f_entry: structure containing MAC forwarding information
  *
  * Adds or updates the rule lists for a given recipe
@@ -1381,7 +1425,7 @@ ice_add_rule_internal(struct ice_hw *hw, u8 recp_id,
 /**
  * ice_remove_vsi_list_rule
  * @hw: pointer to the hardware structure
- * @vsi_list_id: VSI list id generated as part of allocate resource
+ * @vsi_list_id: VSI list ID generated as part of allocate resource
  * @lkup_type: switch rule filter lookup type
  *
  * The VSI list should be emptied before this function is called to remove the
@@ -1506,7 +1550,7 @@ ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle,
 /**
  * ice_remove_rule_internal - Remove a filter rule of a given type
  * @hw: pointer to the hardware structure
- * @recp_id: recipe id for which the rule needs to removed
+ * @recp_id: recipe ID for which the rule needs to removed
  * @f_entry: rule entry containing filter information
  */
 static enum ice_status
@@ -1538,14 +1582,25 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id,
 	} else if (!list_elem->vsi_list_info) {
 		status = ICE_ERR_DOES_NOT_EXIST;
 		goto exit;
+	} else if (list_elem->vsi_list_info->ref_cnt > 1) {
+		/* a ref_cnt > 1 indicates that the vsi_list is being
+		 * shared by multiple rules. Decrement the ref_cnt and
+		 * remove this rule, but do not modify the list, as it
+		 * is in-use by other rules.
+		 */
+		list_elem->vsi_list_info->ref_cnt--;
+		remove_rule = true;
 	} else {
-		if (list_elem->vsi_list_info->ref_cnt > 1)
-			list_elem->vsi_list_info->ref_cnt--;
+		/* a ref_cnt of 1 indicates the vsi_list is only used
+		 * by one rule. However, the original removal request is only
+		 * for a single VSI. Update the vsi_list first, and only
+		 * remove the rule if there are no further VSIs in this list.
+		 */
 		vsi_handle = f_entry->fltr_info.vsi_handle;
 		status = ice_rem_update_vsi_list(hw, vsi_handle, list_elem);
 		if (status)
 			goto exit;
-		/* if vsi count goes to zero after updating the vsi list */
+		/* if VSI count goes to zero after updating the VSI list */
 		if (list_elem->vsi_count == 0)
 			remove_rule = true;
 	}
@@ -1623,7 +1678,7 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list)
 			return ICE_ERR_PARAM;
 		hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
 		m_list_itr->fltr_info.fwd_id.hw_vsi_id = hw_vsi_id;
-		/* update the src in case it is vsi num */
+		/* update the src in case it is VSI num */
 		if (m_list_itr->fltr_info.src_id != ICE_SRC_ID_VSI)
 			return ICE_ERR_PARAM;
 		m_list_itr->fltr_info.src = hw_vsi_id;
@@ -1699,7 +1754,7 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list)
 			((u8 *)r_iter + (elem_sent * s_rule_size));
 	}
 
-	/* Fill up rule id based on the value returned from FW */
+	/* Fill up rule ID based on the value returned from FW */
 	r_iter = s_rule;
 	list_for_each_entry(m_list_itr, m_list, list_entry) {
 		struct ice_fltr_info *f_info = &m_list_itr->fltr_info;
@@ -1759,7 +1814,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
 		ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle);
 	new_fltr = &f_entry->fltr_info;
 
-	/* VLAN id should only be 12 bits */
+	/* VLAN ID should only be 12 bits */
 	if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID)
 		return ICE_ERR_PARAM;
 
@@ -1817,7 +1872,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
 			}
 		}
 	} else if (v_list_itr->vsi_list_info->ref_cnt == 1) {
-		/* Update existing VSI list to add new VSI id only if it used
+		/* Update existing VSI list to add new VSI ID only if it used
 		 * by one VLAN rule.
 		 */
 		cur_fltr = &v_list_itr->fltr_info;
@@ -1827,7 +1882,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
 		/* If VLAN rule exists and VSI list being used by this rule is
 		 * referenced by more than 1 VLAN rule. Then create a new VSI
 		 * list appending previous VSI with new VSI and update existing
-		 * VLAN rule to point to new VSI list id
+		 * VLAN rule to point to new VSI list ID
 		 */
 		struct ice_fltr_info tmp_fltr;
 		u16 vsi_handle_arr[2];
@@ -1915,6 +1970,68 @@ ice_add_vlan(struct ice_hw *hw, struct list_head *v_list)
 }
 
 /**
+ * ice_add_eth_mac - Add ethertype and MAC based filter rule
+ * @hw: pointer to the hardware structure
+ * @em_list: list of ether type MAC filter, MAC is optional
+ *
+ * This function requires the caller to populate the entries in
+ * the filter list with the necessary fields (including flags to
+ * indicate Tx or Rx rules).
+ */
+enum ice_status
+ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list)
+{
+	struct ice_fltr_list_entry *em_list_itr;
+
+	if (!em_list || !hw)
+		return ICE_ERR_PARAM;
+
+	list_for_each_entry(em_list_itr, em_list, list_entry) {
+		enum ice_sw_lkup_type l_type =
+			em_list_itr->fltr_info.lkup_type;
+
+		if (l_type != ICE_SW_LKUP_ETHERTYPE_MAC &&
+		    l_type != ICE_SW_LKUP_ETHERTYPE)
+			return ICE_ERR_PARAM;
+
+		em_list_itr->status = ice_add_rule_internal(hw, l_type,
+							    em_list_itr);
+		if (em_list_itr->status)
+			return em_list_itr->status;
+	}
+	return 0;
+}
+
+/**
+ * ice_remove_eth_mac - Remove an ethertype (or MAC) based filter rule
+ * @hw: pointer to the hardware structure
+ * @em_list: list of ethertype or ethertype MAC entries
+ */
+enum ice_status
+ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list)
+{
+	struct ice_fltr_list_entry *em_list_itr, *tmp;
+
+	if (!em_list || !hw)
+		return ICE_ERR_PARAM;
+
+	list_for_each_entry_safe(em_list_itr, tmp, em_list, list_entry) {
+		enum ice_sw_lkup_type l_type =
+			em_list_itr->fltr_info.lkup_type;
+
+		if (l_type != ICE_SW_LKUP_ETHERTYPE_MAC &&
+		    l_type != ICE_SW_LKUP_ETHERTYPE)
+			return ICE_ERR_PARAM;
+
+		em_list_itr->status = ice_remove_rule_internal(hw, l_type,
+							       em_list_itr);
+		if (em_list_itr->status)
+			return em_list_itr->status;
+	}
+	return 0;
+}
+
+/**
  * ice_rem_sw_rule_info
  * @hw: pointer to the hardware structure
  * @rule_head: pointer to the switch list structure that we want to delete
@@ -2159,7 +2276,7 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle,
 	struct ice_fltr_mgmt_list_entry *fm_entry;
 	enum ice_status status = 0;
 
-	/* check to make sure VSI id is valid and within boundary */
+	/* check to make sure VSI ID is valid and within boundary */
 	if (!ice_is_vsi_valid(hw, vsi_handle))
 		return ICE_ERR_PARAM;
 
@@ -2179,6 +2296,291 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle,
 }
 
 /**
+ * ice_determine_promisc_mask
+ * @fi: filter info to parse
+ *
+ * Helper function to determine which ICE_PROMISC_ mask corresponds
+ * to given filter into.
+ */
+static u8 ice_determine_promisc_mask(struct ice_fltr_info *fi)
+{
+	u16 vid = fi->l_data.mac_vlan.vlan_id;
+	u8 *macaddr = fi->l_data.mac.mac_addr;
+	bool is_tx_fltr = false;
+	u8 promisc_mask = 0;
+
+	if (fi->flag == ICE_FLTR_TX)
+		is_tx_fltr = true;
+
+	if (is_broadcast_ether_addr(macaddr))
+		promisc_mask |= is_tx_fltr ?
+			ICE_PROMISC_BCAST_TX : ICE_PROMISC_BCAST_RX;
+	else if (is_multicast_ether_addr(macaddr))
+		promisc_mask |= is_tx_fltr ?
+			ICE_PROMISC_MCAST_TX : ICE_PROMISC_MCAST_RX;
+	else if (is_unicast_ether_addr(macaddr))
+		promisc_mask |= is_tx_fltr ?
+			ICE_PROMISC_UCAST_TX : ICE_PROMISC_UCAST_RX;
+	if (vid)
+		promisc_mask |= is_tx_fltr ?
+			ICE_PROMISC_VLAN_TX : ICE_PROMISC_VLAN_RX;
+
+	return promisc_mask;
+}
+
+/**
+ * ice_remove_promisc - Remove promisc based filter rules
+ * @hw: pointer to the hardware structure
+ * @recp_id: recipe ID for which the rule needs to removed
+ * @v_list: list of promisc entries
+ */
+static enum ice_status
+ice_remove_promisc(struct ice_hw *hw, u8 recp_id,
+		   struct list_head *v_list)
+{
+	struct ice_fltr_list_entry *v_list_itr, *tmp;
+
+	list_for_each_entry_safe(v_list_itr, tmp, v_list, list_entry) {
+		v_list_itr->status =
+			ice_remove_rule_internal(hw, recp_id, v_list_itr);
+		if (v_list_itr->status)
+			return v_list_itr->status;
+	}
+	return 0;
+}
+
+/**
+ * ice_clear_vsi_promisc - clear specified promiscuous mode(s) for given VSI
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to clear mode
+ * @promisc_mask: mask of promiscuous config bits to clear
+ * @vid: VLAN ID to clear VLAN promiscuous
+ */
+enum ice_status
+ice_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+		      u16 vid)
+{
+	struct ice_switch_info *sw = hw->switch_info;
+	struct ice_fltr_list_entry *fm_entry, *tmp;
+	struct list_head remove_list_head;
+	struct ice_fltr_mgmt_list_entry *itr;
+	struct list_head *rule_head;
+	struct mutex *rule_lock;	/* Lock to protect filter rule list */
+	enum ice_status status = 0;
+	u8 recipe_id;
+
+	if (!ice_is_vsi_valid(hw, vsi_handle))
+		return ICE_ERR_PARAM;
+
+	if (vid)
+		recipe_id = ICE_SW_LKUP_PROMISC_VLAN;
+	else
+		recipe_id = ICE_SW_LKUP_PROMISC;
+
+	rule_head = &sw->recp_list[recipe_id].filt_rules;
+	rule_lock = &sw->recp_list[recipe_id].filt_rule_lock;
+
+	INIT_LIST_HEAD(&remove_list_head);
+
+	mutex_lock(rule_lock);
+	list_for_each_entry(itr, rule_head, list_entry) {
+		u8 fltr_promisc_mask = 0;
+
+		if (!ice_vsi_uses_fltr(itr, vsi_handle))
+			continue;
+
+		fltr_promisc_mask |=
+			ice_determine_promisc_mask(&itr->fltr_info);
+
+		/* Skip if filter is not completely specified by given mask */
+		if (fltr_promisc_mask & ~promisc_mask)
+			continue;
+
+		status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle,
+							&remove_list_head,
+							&itr->fltr_info);
+		if (status) {
+			mutex_unlock(rule_lock);
+			goto free_fltr_list;
+		}
+	}
+	mutex_unlock(rule_lock);
+
+	status = ice_remove_promisc(hw, recipe_id, &remove_list_head);
+
+free_fltr_list:
+	list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) {
+		list_del(&fm_entry->list_entry);
+		devm_kfree(ice_hw_to_dev(hw), fm_entry);
+	}
+
+	return status;
+}
+
+/**
+ * ice_set_vsi_promisc - set given VSI to given promiscuous mode(s)
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to configure
+ * @promisc_mask: mask of promiscuous config bits
+ * @vid: VLAN ID to set VLAN promiscuous
+ */
+enum ice_status
+ice_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid)
+{
+	enum { UCAST_FLTR = 1, MCAST_FLTR, BCAST_FLTR };
+	struct ice_fltr_list_entry f_list_entry;
+	struct ice_fltr_info new_fltr;
+	enum ice_status status = 0;
+	bool is_tx_fltr;
+	u16 hw_vsi_id;
+	int pkt_type;
+	u8 recipe_id;
+
+	if (!ice_is_vsi_valid(hw, vsi_handle))
+		return ICE_ERR_PARAM;
+	hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
+
+	memset(&new_fltr, 0, sizeof(new_fltr));
+
+	if (promisc_mask & (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX)) {
+		new_fltr.lkup_type = ICE_SW_LKUP_PROMISC_VLAN;
+		new_fltr.l_data.mac_vlan.vlan_id = vid;
+		recipe_id = ICE_SW_LKUP_PROMISC_VLAN;
+	} else {
+		new_fltr.lkup_type = ICE_SW_LKUP_PROMISC;
+		recipe_id = ICE_SW_LKUP_PROMISC;
+	}
+
+	/* Separate filters must be set for each direction/packet type
+	 * combination, so we will loop over the mask value, store the
+	 * individual type, and clear it out in the input mask as it
+	 * is found.
+	 */
+	while (promisc_mask) {
+		u8 *mac_addr;
+
+		pkt_type = 0;
+		is_tx_fltr = false;
+
+		if (promisc_mask & ICE_PROMISC_UCAST_RX) {
+			promisc_mask &= ~ICE_PROMISC_UCAST_RX;
+			pkt_type = UCAST_FLTR;
+		} else if (promisc_mask & ICE_PROMISC_UCAST_TX) {
+			promisc_mask &= ~ICE_PROMISC_UCAST_TX;
+			pkt_type = UCAST_FLTR;
+			is_tx_fltr = true;
+		} else if (promisc_mask & ICE_PROMISC_MCAST_RX) {
+			promisc_mask &= ~ICE_PROMISC_MCAST_RX;
+			pkt_type = MCAST_FLTR;
+		} else if (promisc_mask & ICE_PROMISC_MCAST_TX) {
+			promisc_mask &= ~ICE_PROMISC_MCAST_TX;
+			pkt_type = MCAST_FLTR;
+			is_tx_fltr = true;
+		} else if (promisc_mask & ICE_PROMISC_BCAST_RX) {
+			promisc_mask &= ~ICE_PROMISC_BCAST_RX;
+			pkt_type = BCAST_FLTR;
+		} else if (promisc_mask & ICE_PROMISC_BCAST_TX) {
+			promisc_mask &= ~ICE_PROMISC_BCAST_TX;
+			pkt_type = BCAST_FLTR;
+			is_tx_fltr = true;
+		}
+
+		/* Check for VLAN promiscuous flag */
+		if (promisc_mask & ICE_PROMISC_VLAN_RX) {
+			promisc_mask &= ~ICE_PROMISC_VLAN_RX;
+		} else if (promisc_mask & ICE_PROMISC_VLAN_TX) {
+			promisc_mask &= ~ICE_PROMISC_VLAN_TX;
+			is_tx_fltr = true;
+		}
+
+		/* Set filter DA based on packet type */
+		mac_addr = new_fltr.l_data.mac.mac_addr;
+		if (pkt_type == BCAST_FLTR) {
+			eth_broadcast_addr(mac_addr);
+		} else if (pkt_type == MCAST_FLTR ||
+			   pkt_type == UCAST_FLTR) {
+			/* Use the dummy ether header DA */
+			ether_addr_copy(mac_addr, dummy_eth_header);
+			if (pkt_type == MCAST_FLTR)
+				mac_addr[0] |= 0x1;	/* Set multicast bit */
+		}
+
+		/* Need to reset this to zero for all iterations */
+		new_fltr.flag = 0;
+		if (is_tx_fltr) {
+			new_fltr.flag |= ICE_FLTR_TX;
+			new_fltr.src = hw_vsi_id;
+		} else {
+			new_fltr.flag |= ICE_FLTR_RX;
+			new_fltr.src = hw->port_info->lport;
+		}
+
+		new_fltr.fltr_act = ICE_FWD_TO_VSI;
+		new_fltr.vsi_handle = vsi_handle;
+		new_fltr.fwd_id.hw_vsi_id = hw_vsi_id;
+		f_list_entry.fltr_info = new_fltr;
+
+		status = ice_add_rule_internal(hw, recipe_id, &f_list_entry);
+		if (status)
+			goto set_promisc_exit;
+	}
+
+set_promisc_exit:
+	return status;
+}
+
+/**
+ * ice_set_vlan_vsi_promisc
+ * @hw: pointer to the hardware structure
+ * @vsi_handle: VSI handle to configure
+ * @promisc_mask: mask of promiscuous config bits
+ * @rm_vlan_promisc: Clear VLANs VSI promisc mode
+ *
+ * Configure VSI with all associated VLANs to given promiscuous mode(s)
+ */
+enum ice_status
+ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+			 bool rm_vlan_promisc)
+{
+	struct ice_switch_info *sw = hw->switch_info;
+	struct ice_fltr_list_entry *list_itr, *tmp;
+	struct list_head vsi_list_head;
+	struct list_head *vlan_head;
+	struct mutex *vlan_lock; /* Lock to protect filter rule list */
+	enum ice_status status;
+	u16 vlan_id;
+
+	INIT_LIST_HEAD(&vsi_list_head);
+	vlan_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock;
+	vlan_head = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rules;
+	mutex_lock(vlan_lock);
+	status = ice_add_to_vsi_fltr_list(hw, vsi_handle, vlan_head,
+					  &vsi_list_head);
+	mutex_unlock(vlan_lock);
+	if (status)
+		goto free_fltr_list;
+
+	list_for_each_entry(list_itr, &vsi_list_head, list_entry) {
+		vlan_id = list_itr->fltr_info.l_data.vlan.vlan_id;
+		if (rm_vlan_promisc)
+			status = ice_clear_vsi_promisc(hw, vsi_handle,
+						       promisc_mask, vlan_id);
+		else
+			status = ice_set_vsi_promisc(hw, vsi_handle,
+						     promisc_mask, vlan_id);
+		if (status)
+			break;
+	}
+
+free_fltr_list:
+	list_for_each_entry_safe(list_itr, tmp, &vsi_list_head, list_entry) {
+		list_del(&list_itr->list_entry);
+		devm_kfree(ice_hw_to_dev(hw), list_itr);
+	}
+	return status;
+}
+
+/**
  * ice_remove_vsi_lkup_fltr - Remove lookup type filters for a VSI
  * @hw: pointer to the hardware structure
  * @vsi_handle: VSI handle to remove filters from
@@ -2213,12 +2615,14 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle,
 	case ICE_SW_LKUP_VLAN:
 		ice_remove_vlan(hw, &remove_list_head);
 		break;
+	case ICE_SW_LKUP_PROMISC:
+	case ICE_SW_LKUP_PROMISC_VLAN:
+		ice_remove_promisc(hw, lkup, &remove_list_head);
+		break;
 	case ICE_SW_LKUP_MAC_VLAN:
 	case ICE_SW_LKUP_ETHERTYPE:
 	case ICE_SW_LKUP_ETHERTYPE_MAC:
-	case ICE_SW_LKUP_PROMISC:
 	case ICE_SW_LKUP_DFLT:
-	case ICE_SW_LKUP_PROMISC_VLAN:
 	case ICE_SW_LKUP_LAST:
 	default:
 		ice_debug(hw, ICE_DBG_SW, "Unsupported lookup type %d\n", lkup);
@@ -2252,7 +2656,7 @@ void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle)
  * ice_replay_vsi_fltr - Replay filters for requested VSI
  * @hw: pointer to the hardware structure
  * @vsi_handle: driver VSI handle
- * @recp_id: Recipe id for which rules need to be replayed
+ * @recp_id: Recipe ID for which rules need to be replayed
  * @list_head: list for which filters need to be replayed
  *
  * Replays the filter of recipe recp_id for a VSI represented via vsi_handle.
@@ -2276,7 +2680,7 @@ ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id,
 		f_entry.fltr_info = itr->fltr_info;
 		if (itr->vsi_count < 2 && recp_id != ICE_SW_LKUP_VLAN &&
 		    itr->fltr_info.vsi_handle == vsi_handle) {
-			/* update the src in case it is vsi num */
+			/* update the src in case it is VSI num */
 			if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI)
 				f_entry.fltr_info.src = hw_vsi_id;
 			status = ice_add_rule_internal(hw, recp_id, &f_entry);
@@ -2291,7 +2695,7 @@ ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id,
 		clear_bit(vsi_handle, itr->vsi_list_info->vsi_map);
 		f_entry.fltr_info.vsi_handle = vsi_handle;
 		f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI;
-		/* update the src in case it is vsi num */
+		/* update the src in case it is VSI num */
 		if (f_entry.fltr_info.src_id == ICE_SRC_ID_VSI)
 			f_entry.fltr_info.src = hw_vsi_id;
 		if (recp_id == ICE_SW_LKUP_VLAN)
@@ -2331,7 +2735,7 @@ enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle)
 
 /**
  * ice_rm_all_sw_replay_rule_info - deletes filter replay rules
- * @hw: pointer to the hw struct
+ * @hw: pointer to the HW struct
  *
  * Deletes the filter replay rules.
  */
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h
index d5ef0bd58bf9..cb123fbe30be 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.h
+++ b/drivers/net/ethernet/intel/ice/ice_switch.h
@@ -8,7 +8,16 @@
 
 #define ICE_SW_CFG_MAX_BUF_LEN 2048
 #define ICE_DFLT_VSI_INVAL 0xff
+#define ICE_FLTR_RX BIT(0)
+#define ICE_FLTR_TX BIT(1)
+#define ICE_FLTR_TX_RX (ICE_FLTR_RX | ICE_FLTR_TX)
 #define ICE_VSI_INVAL_ID 0xffff
+#define ICE_INVAL_Q_HANDLE 0xFFFF
+
+/* VSI queue context structure */
+struct ice_q_ctx {
+	u16  q_handle;
+};
 
 /* VSI context structure for add/get/update/free operations */
 struct ice_vsi_ctx {
@@ -20,6 +29,8 @@ struct ice_vsi_ctx {
 	struct ice_sched_vsi_info sched;
 	u8 alloc_from_pool;
 	u8 vf_num;
+	u16 num_lan_q_entries[ICE_MAX_TRAFFIC_CLASS];
+	struct ice_q_ctx *lan_q_ctx[ICE_MAX_TRAFFIC_CLASS];
 };
 
 enum ice_sw_fwd_act_type {
@@ -44,7 +55,7 @@ enum ice_sw_lkup_type {
 	ICE_SW_LKUP_LAST
 };
 
-/* type of filter src id */
+/* type of filter src ID */
 enum ice_src_id {
 	ICE_SRC_ID_UNKNOWN = 0,
 	ICE_SRC_ID_VSI,
@@ -60,9 +71,6 @@ struct ice_fltr_info {
 	/* rule ID returned by firmware once filter rule is created */
 	u16 fltr_rule_id;
 	u16 flag;
-#define ICE_FLTR_RX		BIT(0)
-#define ICE_FLTR_TX		BIT(1)
-#define ICE_FLTR_TX_RX		(ICE_FLTR_RX | ICE_FLTR_TX)
 
 	/* Source VSI for LOOKUP_TX or source port for LOOKUP_RX */
 	u16 src;
@@ -95,8 +103,8 @@ struct ice_fltr_info {
 
 	/* Depending on filter action */
 	union {
-		/* queue id in case of ICE_FWD_TO_Q and starting
-		 * queue id in case of ICE_FWD_TO_QGRP.
+		/* queue ID in case of ICE_FWD_TO_Q and starting
+		 * queue ID in case of ICE_FWD_TO_QGRP.
 		 */
 		u16 q_id:11;
 		u16 hw_vsi_id:10;
@@ -143,7 +151,7 @@ struct ice_sw_recipe {
 	DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES);
 };
 
-/* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list id */
+/* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list ID */
 struct ice_vsi_list_map_info {
 	struct list_head list_entry;
 	DECLARE_BITMAP(vsi_map, ICE_MAX_VSI);
@@ -165,7 +173,7 @@ struct ice_fltr_list_entry {
  * used for VLAN membership.
  */
 struct ice_fltr_mgmt_list_entry {
-	/* back pointer to VSI list id to VSI list mapping */
+	/* back pointer to VSI list ID to VSI list mapping */
 	struct ice_vsi_list_map_info *vsi_list_info;
 	u16 vsi_count;
 #define ICE_INVAL_LG_ACT_INDEX 0xffff
@@ -178,6 +186,17 @@ struct ice_fltr_mgmt_list_entry {
 	u8 counter_index;
 };
 
+enum ice_promisc_flags {
+	ICE_PROMISC_UCAST_RX = 0x1,
+	ICE_PROMISC_UCAST_TX = 0x2,
+	ICE_PROMISC_MCAST_RX = 0x4,
+	ICE_PROMISC_MCAST_TX = 0x8,
+	ICE_PROMISC_BCAST_RX = 0x10,
+	ICE_PROMISC_BCAST_TX = 0x20,
+	ICE_PROMISC_VLAN_RX = 0x40,
+	ICE_PROMISC_VLAN_TX = 0x80,
+};
+
 /* VSI related commands */
 enum ice_status
 ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,
@@ -198,11 +217,27 @@ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw);
 enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw);
 enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst);
 enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst);
+enum ice_status
+ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list);
+enum ice_status
+ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list);
 void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle);
-enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
+enum ice_status
+ice_add_vlan(struct ice_hw *hw, struct list_head *m_list);
 enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list);
+
+/* Promisc/defport setup for VSIs */
 enum ice_status
 ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction);
+enum ice_status
+ice_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+		    u16 vid);
+enum ice_status
+ice_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+		      u16 vid);
+enum ice_status
+ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask,
+			 bool rm_vlan_promisc);
 
 enum ice_status ice_init_def_sw_recp(struct ice_hw *hw);
 u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 49fc38094185..3c83230434b6 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -6,6 +6,7 @@
 #include <linux/prefetch.h>
 #include <linux/mm.h>
 #include "ice.h"
+#include "ice_dcb_lib.h"
 
 #define ICE_RX_HDR_SIZE		256
 
@@ -48,19 +49,17 @@ static struct netdev_queue *txring_txq(const struct ice_ring *ring)
  */
 void ice_clean_tx_ring(struct ice_ring *tx_ring)
 {
-	unsigned long size;
 	u16 i;
 
 	/* ring already cleared, nothing to do */
 	if (!tx_ring->tx_buf)
 		return;
 
-	/* Free all the Tx ring sk_bufss */
+	/* Free all the Tx ring sk_buffs */
 	for (i = 0; i < tx_ring->count; i++)
 		ice_unmap_and_free_tx_buf(tx_ring, &tx_ring->tx_buf[i]);
 
-	size = sizeof(struct ice_tx_buf) * tx_ring->count;
-	memset(tx_ring->tx_buf, 0, size);
+	memset(tx_ring->tx_buf, 0, sizeof(*tx_ring->tx_buf) * tx_ring->count);
 
 	/* Zero out the descriptor ring */
 	memset(tx_ring->desc, 0, tx_ring->size);
@@ -102,8 +101,8 @@ void ice_free_tx_ring(struct ice_ring *tx_ring)
  *
  * Returns true if there's any budget left (e.g. the clean is finished)
  */
-static bool ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring,
-			     int napi_budget)
+static bool
+ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget)
 {
 	unsigned int total_bytes = 0, total_pkts = 0;
 	unsigned int budget = vsi->work_lmt;
@@ -226,21 +225,21 @@ static bool ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring,
 int ice_setup_tx_ring(struct ice_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
-	int bi_size;
 
 	if (!dev)
 		return -ENOMEM;
 
 	/* warn if we are about to overwrite the pointer */
 	WARN_ON(tx_ring->tx_buf);
-	bi_size = sizeof(struct ice_tx_buf) * tx_ring->count;
-	tx_ring->tx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+	tx_ring->tx_buf =
+		devm_kzalloc(dev, sizeof(*tx_ring->tx_buf) * tx_ring->count,
+			     GFP_KERNEL);
 	if (!tx_ring->tx_buf)
 		return -ENOMEM;
 
-	/* round up to nearest 4K */
-	tx_ring->size = tx_ring->count * sizeof(struct ice_tx_desc);
-	tx_ring->size = ALIGN(tx_ring->size, 4096);
+	/* round up to nearest page */
+	tx_ring->size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc),
+			      PAGE_SIZE);
 	tx_ring->desc = dmam_alloc_coherent(dev, tx_ring->size, &tx_ring->dma,
 					    GFP_KERNEL);
 	if (!tx_ring->desc) {
@@ -267,7 +266,6 @@ err:
 void ice_clean_rx_ring(struct ice_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	unsigned long size;
 	u16 i;
 
 	/* ring already cleared, nothing to do */
@@ -285,15 +283,23 @@ void ice_clean_rx_ring(struct ice_ring *rx_ring)
 		if (!rx_buf->page)
 			continue;
 
-		dma_unmap_page(dev, rx_buf->dma, PAGE_SIZE, DMA_FROM_DEVICE);
-		__free_pages(rx_buf->page, 0);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(dev, rx_buf->dma,
+					      rx_buf->page_offset,
+					      ICE_RXBUF_2048, DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(dev, rx_buf->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
 
 		rx_buf->page = NULL;
 		rx_buf->page_offset = 0;
 	}
 
-	size = sizeof(struct ice_rx_buf) * rx_ring->count;
-	memset(rx_ring->rx_buf, 0, size);
+	memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count);
 
 	/* Zero out the descriptor ring */
 	memset(rx_ring->desc, 0, rx_ring->size);
@@ -331,21 +337,21 @@ void ice_free_rx_ring(struct ice_ring *rx_ring)
 int ice_setup_rx_ring(struct ice_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int bi_size;
 
 	if (!dev)
 		return -ENOMEM;
 
 	/* warn if we are about to overwrite the pointer */
 	WARN_ON(rx_ring->rx_buf);
-	bi_size = sizeof(struct ice_rx_buf) * rx_ring->count;
-	rx_ring->rx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+	rx_ring->rx_buf =
+		devm_kzalloc(dev, sizeof(*rx_ring->rx_buf) * rx_ring->count,
+			     GFP_KERNEL);
 	if (!rx_ring->rx_buf)
 		return -ENOMEM;
 
-	/* round up to nearest 4K */
-	rx_ring->size = rx_ring->count * sizeof(union ice_32byte_rx_desc);
-	rx_ring->size = ALIGN(rx_ring->size, 4096);
+	/* round up to nearest page */
+	rx_ring->size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
+			      PAGE_SIZE);
 	rx_ring->desc = dmam_alloc_coherent(dev, rx_ring->size, &rx_ring->dma,
 					    GFP_KERNEL);
 	if (!rx_ring->desc) {
@@ -393,8 +399,8 @@ static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
  * Returns true if the page was successfully allocated or
  * reused.
  */
-static bool ice_alloc_mapped_page(struct ice_ring *rx_ring,
-				  struct ice_rx_buf *bi)
+static bool
+ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi)
 {
 	struct page *page = bi->page;
 	dma_addr_t dma;
@@ -413,7 +419,8 @@ static bool ice_alloc_mapped_page(struct ice_ring *rx_ring,
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE,
+				 DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
@@ -427,6 +434,8 @@ static bool ice_alloc_mapped_page(struct ice_ring *rx_ring,
 	bi->dma = dma;
 	bi->page = page;
 	bi->page_offset = 0;
+	page_ref_add(page, USHRT_MAX - 1);
+	bi->pagecnt_bias = USHRT_MAX;
 
 	return true;
 }
@@ -448,7 +457,7 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
 	if (!rx_ring->netdev || !cleaned_count)
 		return false;
 
-	/* get the RX descriptor and buffer based on next_to_use */
+	/* get the Rx descriptor and buffer based on next_to_use */
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
 	bi = &rx_ring->rx_buf[ntu];
 
@@ -456,6 +465,12 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count)
 		if (!ice_alloc_mapped_page(rx_ring, bi))
 			goto no_bufs;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 ICE_RXBUF_2048,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -501,61 +516,43 @@ static bool ice_page_is_reserved(struct page *page)
 }
 
 /**
- * ice_add_rx_frag - Add contents of Rx buffer to sk_buff
- * @rx_buf: buffer containing page to add
- * @rx_desc: descriptor containing length of buffer written by hardware
- * @skb: sk_buf to place the data into
- *
- * This function will add the data contained in rx_buf->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * ice_rx_buf_adjust_pg_offset - Prepare Rx buffer for reuse
+ * @rx_buf: Rx buffer to adjust
+ * @size: Size of adjustment
  *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * Update the offset within page so that Rx buf will be ready to be reused.
+ * For systems with PAGE_SIZE < 8192 this function will flip the page offset
+ * so the second half of page assigned to Rx buffer will be used, otherwise
+ * the offset is moved by the @size bytes
  */
-static bool ice_add_rx_frag(struct ice_rx_buf *rx_buf,
-			    union ice_32b_rx_flex_desc *rx_desc,
-			    struct sk_buff *skb)
+static void
+ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size)
 {
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = ICE_RXBUF_2048;
+	/* flip page offset to other buffer */
+	rx_buf->page_offset ^= size;
 #else
-	unsigned int last_offset = PAGE_SIZE - ICE_RXBUF_2048;
-	unsigned int truesize;
-#endif /* PAGE_SIZE < 8192) */
-
-	struct page *page;
-	unsigned int size;
-
-	size = le16_to_cpu(rx_desc->wb.pkt_len) &
-		ICE_RX_FLX_DESC_PKT_LEN_M;
-
-	page = rx_buf->page;
+	/* move offset up to the next cache line */
+	rx_buf->page_offset += size;
+#endif
+}
 
+/**
+ * ice_can_reuse_rx_page - Determine if page can be reused for another Rx
+ * @rx_buf: buffer containing the page
+ *
+ * If page is reusable, we have a green light for calling ice_reuse_rx_page,
+ * which will assign the current buffer to the buffer that next_to_alloc is
+ * pointing to; otherwise, the DMA mapping needs to be destroyed and
+ * page freed
+ */
+static bool ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
+{
 #if (PAGE_SIZE >= 8192)
-	truesize = ALIGN(size, L1_CACHE_BYTES);
-#endif /* PAGE_SIZE >= 8192) */
-
-	/* will the data fit in the skb we allocated? if so, just
-	 * copy it as it is pretty small anyway
-	 */
-	if (size <= ICE_RX_HDR_SIZE && !skb_is_nonlinear(skb)) {
-		unsigned char *va = page_address(page) + rx_buf->page_offset;
-
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
-		/* page is not reserved, we can reuse buffer as-is */
-		if (likely(!ice_page_is_reserved(page)))
-			return true;
-
-		/* this page cannot be reused so discard it */
-		__free_pages(page, 0);
-		return false;
-	}
-
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			rx_buf->page_offset, size, truesize);
+	unsigned int last_offset = PAGE_SIZE - ICE_RXBUF_2048;
+#endif
+	unsigned int pagecnt_bias = rx_buf->pagecnt_bias;
+	struct page *page = rx_buf->page;
 
 	/* avoid re-using remote pages */
 	if (unlikely(ice_page_is_reserved(page)))
@@ -563,36 +560,61 @@ static bool ice_add_rx_frag(struct ice_rx_buf *rx_buf,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely((page_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buf->page_offset ^= truesize;
 #else
-	/* move offset up to the next cache line */
-	rx_buf->page_offset += truesize;
-
 	if (rx_buf->page_offset > last_offset)
 		return false;
 #endif /* PAGE_SIZE < 8192) */
 
-	/* Even if we own the page, we are not allowed to use atomic_set()
-	 * This would break get_page_unless_zero() users.
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
 	 */
-	get_page(rx_buf->page);
+	if (unlikely(pagecnt_bias == 1)) {
+		page_ref_add(page, USHRT_MAX - 1);
+		rx_buf->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }
 
 /**
+ * ice_add_rx_frag - Add contents of Rx buffer to sk_buff as a frag
+ * @rx_buf: buffer containing page to add
+ * @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
+ *
+ * This function will add the data contained in rx_buf->page to the skb.
+ * It will just attach the page as a frag to the skb.
+ * The function will then update the page offset.
+ */
+static void
+ice_add_rx_frag(struct ice_rx_buf *rx_buf, struct sk_buff *skb,
+		unsigned int size)
+{
+#if (PAGE_SIZE >= 8192)
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#else
+	unsigned int truesize = ICE_RXBUF_2048;
+#endif
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
+			rx_buf->page_offset, size, truesize);
+
+	/* page is being used so we must update the page offset */
+	ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
+}
+
+/**
  * ice_reuse_rx_page - page flip buffer and store it back on the ring
  * @rx_ring: Rx descriptor ring to store buffers on
  * @old_buf: donor buffer to have page reused
  *
  * Synchronizes page for reuse by the adapter
  */
-static void ice_reuse_rx_page(struct ice_ring *rx_ring,
-			      struct ice_rx_buf *old_buf)
+static void
+ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf)
 {
 	u16 nta = rx_ring->next_to_alloc;
 	struct ice_rx_buf *new_buf;
@@ -603,121 +625,132 @@ static void ice_reuse_rx_page(struct ice_ring *rx_ring,
 	nta++;
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
-	/* transfer page from old buffer to new buffer */
-	*new_buf = *old_buf;
+	/* Transfer page from old buffer to new buffer.
+	 * Move each member individually to avoid possible store
+	 * forwarding stalls and unnecessary copy of skb.
+	 */
+	new_buf->dma = old_buf->dma;
+	new_buf->page = old_buf->page;
+	new_buf->page_offset = old_buf->page_offset;
+	new_buf->pagecnt_bias = old_buf->pagecnt_bias;
 }
 
 /**
- * ice_fetch_rx_buf - Allocate skb and populate it
+ * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use
  * @rx_ring: Rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @skb: skb to be used
+ * @size: size of buffer to add to skb
  *
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
  */
-static struct sk_buff *ice_fetch_rx_buf(struct ice_ring *rx_ring,
-					union ice_32b_rx_flex_desc *rx_desc)
+static struct ice_rx_buf *
+ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb,
+	       const unsigned int size)
 {
 	struct ice_rx_buf *rx_buf;
-	struct sk_buff *skb;
-	struct page *page;
 
 	rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean];
-	page = rx_buf->page;
-	prefetchw(page);
+	prefetchw(rx_buf->page);
+	*skb = rx_buf->skb;
 
-	skb = rx_buf->skb;
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
+				      rx_buf->page_offset, size,
+				      DMA_FROM_DEVICE);
 
-	if (likely(!skb)) {
-		u8 *page_addr = page_address(page) + rx_buf->page_offset;
+	/* We have pulled a buffer for use, so decrement pagecnt_bias */
+	rx_buf->pagecnt_bias--;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	return rx_buf;
+}
+
+/**
+ * ice_construct_skb - Allocate skb and populate it
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buf: Rx buffer to pull data from
+ * @size: the length of the packet
+ *
+ * This function allocates an skb. It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
+ */
+static struct sk_buff *
+ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
+		  unsigned int size)
+{
+	void *va = page_address(rx_buf->page) + rx_buf->page_offset;
+	unsigned int headlen;
+	struct sk_buff *skb;
+
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch((void *)(page_addr + L1_CACHE_BYTES));
+	prefetch((u8 *)va + L1_CACHE_BYTES);
 #endif /* L1_CACHE_BYTES */
 
-		/* allocate a skb to store the frags */
-		skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-				       ICE_RX_HDR_SIZE,
-				       GFP_ATOMIC | __GFP_NOWARN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_buf_failed++;
-			return NULL;
-		}
-
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
+	/* allocate a skb to store the frags */
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
 
-		skb_record_rx_queue(skb, rx_ring->q_index);
-	} else {
-		/* we are reusing so sync this buffer for CPU use */
-		dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
-					      rx_buf->page_offset,
-					      ICE_RXBUF_2048,
-					      DMA_FROM_DEVICE);
+	skb_record_rx_queue(skb, rx_ring->q_index);
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > ICE_RX_HDR_SIZE)
+		headlen = eth_get_headlen(skb->dev, va, ICE_RX_HDR_SIZE);
 
-		rx_buf->skb = NULL;
-	}
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
 
-	/* pull page into skb */
-	if (ice_add_rx_frag(rx_buf, rx_desc, skb)) {
-		/* hand second half of page back to the ring */
-		ice_reuse_rx_page(rx_ring, rx_buf);
-		rx_ring->rx_stats.page_reuse_count++;
+	/* if we exhaust the linear part then add what is left as a frag */
+	size -= headlen;
+	if (size) {
+#if (PAGE_SIZE >= 8192)
+		unsigned int truesize = SKB_DATA_ALIGN(size);
+#else
+		unsigned int truesize = ICE_RXBUF_2048;
+#endif
+		skb_add_rx_frag(skb, 0, rx_buf->page,
+				rx_buf->page_offset + headlen, size, truesize);
+		/* buffer is used by skb, update page_offset */
+		ice_rx_buf_adjust_pg_offset(rx_buf, truesize);
 	} else {
-		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buf->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		/* buffer is unused, reset bias back to rx_buf; data was copied
+		 * onto skb's linear part so there's no need for adjusting
+		 * page offset and we can reuse this buffer as-is
+		 */
+		rx_buf->pagecnt_bias++;
 	}
 
-	/* clear contents of buffer_info */
-	rx_buf->page = NULL;
-
 	return skb;
 }
 
 /**
- * ice_pull_tail - ice specific version of skb_pull_tail
- * @skb: pointer to current skb being adjusted
+ * ice_put_rx_buf - Clean up used buffer and either recycle or free
+ * @rx_ring: Rx descriptor ring to transact packets on
+ * @rx_buf: Rx buffer to pull data from
  *
- * This function is an ice specific version of __pskb_pull_tail. The
- * main difference between this version and the original function is that
- * this function can make several assumptions about the state of things
- * that allow for significant optimizations versus the standard function.
- * As a result we can do things like drop a frag and maintain an accurate
- * truesize for the skb.
+ * This function will  clean up the contents of the rx_buf. It will
+ * either recycle the buffer or unmap it and free the associated resources.
  */
-static void ice_pull_tail(struct sk_buff *skb)
+static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
 {
-	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
-	unsigned int pull_len;
-	unsigned char *va;
-
-	/* it is valid to use page_address instead of kmap since we are
-	 * working with pages allocated out of the lomem pool per
-	 * alloc_page(GFP_ATOMIC)
-	 */
-	va = skb_frag_address(frag);
-
-	/* we need the header to contain the greater of either ETH_HLEN or
-	 * 60 bytes if the skb->len is less than 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, ICE_RX_HDR_SIZE);
-
-	/* align pull length to size of long to optimize memcpy performance */
-	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+		/* hand second half of page back to the ring */
+	if (ice_can_reuse_rx_page(rx_buf)) {
+		ice_reuse_rx_page(rx_ring, rx_buf);
+		rx_ring->rx_stats.page_reuse_count++;
+	} else {
+		/* we are not reusing the buffer so unmap it */
+		dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, ICE_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias);
+	}
 
-	/* update all of the pointers */
-	skb_frag_size_sub(frag, pull_len);
-	frag->page_offset += pull_len;
-	skb->data_len -= pull_len;
-	skb->tail += pull_len;
+	/* clear contents of buffer_info */
+	rx_buf->page = NULL;
+	rx_buf->skb = NULL;
 }
 
 /**
@@ -734,10 +767,6 @@ static void ice_pull_tail(struct sk_buff *skb)
  */
 static bool ice_cleanup_headers(struct sk_buff *skb)
 {
-	/* place header in linear portion of buffer */
-	if (skb_is_nonlinear(skb))
-		ice_pull_tail(skb);
-
 	/* if eth_skb_pad returns an error the skb was freed */
 	if (eth_skb_pad(skb))
 		return true;
@@ -755,8 +784,8 @@ static bool ice_cleanup_headers(struct sk_buff *skb)
  * The status_error_len doesn't need to be shifted because it begins
  * at offset zero.
  */
-static bool ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc,
-			     const u16 stat_err_bits)
+static bool
+ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc, const u16 stat_err_bits)
 {
 	return !!(rx_desc->wb.status_error0 &
 		  cpu_to_le16(stat_err_bits));
@@ -773,9 +802,9 @@ static bool ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc,
  * sk_buff in the next buffer to be chained and return true indicating
  * that this is in fact a non-EOP buffer.
  */
-static bool ice_is_non_eop(struct ice_ring *rx_ring,
-			   union ice_32b_rx_flex_desc *rx_desc,
-			   struct sk_buff *skb)
+static bool
+ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
+	       struct sk_buff *skb)
 {
 	u32 ntc = rx_ring->next_to_clean + 1;
 
@@ -842,8 +871,9 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
  *
  * skb->protocol must be set before this function is called
  */
-static void ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
-			union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
+static void
+ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb,
+	    union ice_32b_rx_flex_desc *rx_desc, u8 ptype)
 {
 	struct ice_rx_ptype_decoded decoded;
 	u32 rx_error, rx_status;
@@ -913,9 +943,10 @@ checksum_fail:
  * order to populate the hash, checksum, VLAN, protocol, and
  * other fields within the skb.
  */
-static void ice_process_skb_fields(struct ice_ring *rx_ring,
-				   union ice_32b_rx_flex_desc *rx_desc,
-				   struct sk_buff *skb, u8 ptype)
+static void
+ice_process_skb_fields(struct ice_ring *rx_ring,
+		       union ice_32b_rx_flex_desc *rx_desc,
+		       struct sk_buff *skb, u8 ptype)
 {
 	ice_rx_hash(rx_ring, rx_desc, skb, ptype);
 
@@ -929,18 +960,17 @@ static void ice_process_skb_fields(struct ice_ring *rx_ring,
  * ice_receive_skb - Send a completed packet up the stack
  * @rx_ring: Rx ring in play
  * @skb: packet to send up
- * @vlan_tag: vlan tag for packet
+ * @vlan_tag: VLAN tag for packet
  *
  * This function sends the completed packet (via. skb) up the stack using
- * gro receive functions (with/without vlan tag)
+ * gro receive functions (with/without VLAN tag)
  */
-static void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb,
-			    u16 vlan_tag)
+static void
+ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
 {
 	if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
-	    (vlan_tag & VLAN_VID_MASK)) {
+	    (vlan_tag & VLAN_VID_MASK))
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
-	}
 	napi_gro_receive(&rx_ring->q_vector->napi, skb);
 }
 
@@ -962,10 +992,12 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
 	bool failure = false;
 
-	/* start the loop to process RX packets bounded by 'budget' */
+	/* start the loop to process Rx packets bounded by 'budget' */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
+		struct ice_rx_buf *rx_buf;
 		struct sk_buff *skb;
+		unsigned int size;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
 		u8 rx_ptype;
@@ -977,7 +1009,7 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 			cleaned_count = 0;
 		}
 
-		/* get the RX desc from RX ring based on 'next_to_clean' */
+		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
 		/* status_error_len will always be zero for unused descriptors
@@ -995,11 +1027,24 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		size = le16_to_cpu(rx_desc->wb.pkt_len) &
+			ICE_RX_FLX_DESC_PKT_LEN_M;
+
+		rx_buf = ice_get_rx_buf(rx_ring, &skb, size);
 		/* allocate (if needed) and populate skb */
-		skb = ice_fetch_rx_buf(rx_ring, rx_desc);
-		if (!skb)
+		if (skb)
+			ice_add_rx_frag(rx_buf, skb, size);
+		else
+			skb = ice_construct_skb(rx_ring, rx_buf, size);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buf_failed++;
+			rx_buf->pagecnt_bias++;
 			break;
+		}
 
+		ice_put_rx_buf(rx_ring, rx_buf);
 		cleaned_count++;
 
 		/* skip if it is NOP desc */
@@ -1053,6 +1098,304 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 }
 
 /**
+ * ice_adjust_itr_by_size_and_speed - Adjust ITR based on current traffic
+ * @port_info: port_info structure containing the current link speed
+ * @avg_pkt_size: average size of Tx or Rx packets based on clean routine
+ * @itr: ITR value to update
+ *
+ * Calculate how big of an increment should be applied to the ITR value passed
+ * in based on wmem_default, SKB overhead, Ethernet overhead, and the current
+ * link speed.
+ *
+ * The following is a calculation derived from:
+ *  wmem_default / (size + overhead) = desired_pkts_per_int
+ *  rate / bits_per_byte / (size + Ethernet overhead) = pkt_rate
+ *  (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value
+ *
+ * Assuming wmem_default is 212992 and overhead is 640 bytes per
+ * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the
+ * formula down to:
+ *
+ *	 wmem_default * bits_per_byte * usecs_per_sec   pkt_size + 24
+ * ITR = -------------------------------------------- * --------------
+ *			     rate			pkt_size + 640
+ */
+static unsigned int
+ice_adjust_itr_by_size_and_speed(struct ice_port_info *port_info,
+				 unsigned int avg_pkt_size,
+				 unsigned int itr)
+{
+	switch (port_info->phy.link_info.link_speed) {
+	case ICE_AQ_LINK_SPEED_100GB:
+		itr += DIV_ROUND_UP(17 * (avg_pkt_size + 24),
+				    avg_pkt_size + 640);
+		break;
+	case ICE_AQ_LINK_SPEED_50GB:
+		itr += DIV_ROUND_UP(34 * (avg_pkt_size + 24),
+				    avg_pkt_size + 640);
+		break;
+	case ICE_AQ_LINK_SPEED_40GB:
+		itr += DIV_ROUND_UP(43 * (avg_pkt_size + 24),
+				    avg_pkt_size + 640);
+		break;
+	case ICE_AQ_LINK_SPEED_25GB:
+		itr += DIV_ROUND_UP(68 * (avg_pkt_size + 24),
+				    avg_pkt_size + 640);
+		break;
+	case ICE_AQ_LINK_SPEED_20GB:
+		itr += DIV_ROUND_UP(85 * (avg_pkt_size + 24),
+				    avg_pkt_size + 640);
+		break;
+	case ICE_AQ_LINK_SPEED_10GB:
+		/* fall through */
+	default:
+		itr += DIV_ROUND_UP(170 * (avg_pkt_size + 24),
+				    avg_pkt_size + 640);
+		break;
+	}
+
+	if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) {
+		itr &= ICE_ITR_ADAPTIVE_LATENCY;
+		itr += ICE_ITR_ADAPTIVE_MAX_USECS;
+	}
+
+	return itr;
+}
+
+/**
+ * ice_update_itr - update the adaptive ITR value based on statistics
+ * @q_vector: structure containing interrupt and ring information
+ * @rc: structure containing ring performance data
+ *
+ * Stores a new ITR value based on packets and byte
+ * counts during the last interrupt.  The advantage of per interrupt
+ * computation is faster updates and more accurate ITR for the current
+ * traffic pattern.  Constants in this function were computed
+ * based on theoretical maximum wire speed and thresholds were set based
+ * on testing data as well as attempting to minimize response time
+ * while increasing bulk throughput.
+ */
+static void
+ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc)
+{
+	unsigned long next_update = jiffies;
+	unsigned int packets, bytes, itr;
+	bool container_is_rx;
+
+	if (!rc->ring || !ITR_IS_DYNAMIC(rc->itr_setting))
+		return;
+
+	/* If itr_countdown is set it means we programmed an ITR within
+	 * the last 4 interrupt cycles. This has a side effect of us
+	 * potentially firing an early interrupt. In order to work around
+	 * this we need to throw out any data received for a few
+	 * interrupts following the update.
+	 */
+	if (q_vector->itr_countdown) {
+		itr = rc->target_itr;
+		goto clear_counts;
+	}
+
+	container_is_rx = (&q_vector->rx == rc);
+	/* For Rx we want to push the delay up and default to low latency.
+	 * for Tx we want to pull the delay down and default to high latency.
+	 */
+	itr = container_is_rx ?
+		ICE_ITR_ADAPTIVE_MIN_USECS | ICE_ITR_ADAPTIVE_LATENCY :
+		ICE_ITR_ADAPTIVE_MAX_USECS | ICE_ITR_ADAPTIVE_LATENCY;
+
+	/* If we didn't update within up to 1 - 2 jiffies we can assume
+	 * that either packets are coming in so slow there hasn't been
+	 * any work, or that there is so much work that NAPI is dealing
+	 * with interrupt moderation and we don't need to do anything.
+	 */
+	if (time_after(next_update, rc->next_update))
+		goto clear_counts;
+
+	packets = rc->total_pkts;
+	bytes = rc->total_bytes;
+
+	if (container_is_rx) {
+		/* If Rx there are 1 to 4 packets and bytes are less than
+		 * 9000 assume insufficient data to use bulk rate limiting
+		 * approach unless Tx is already in bulk rate limiting. We
+		 * are likely latency driven.
+		 */
+		if (packets && packets < 4 && bytes < 9000 &&
+		    (q_vector->tx.target_itr & ICE_ITR_ADAPTIVE_LATENCY)) {
+			itr = ICE_ITR_ADAPTIVE_LATENCY;
+			goto adjust_by_size_and_speed;
+		}
+	} else if (packets < 4) {
+		/* If we have Tx and Rx ITR maxed and Tx ITR is running in
+		 * bulk mode and we are receiving 4 or fewer packets just
+		 * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so
+		 * that the Rx can relax.
+		 */
+		if (rc->target_itr == ICE_ITR_ADAPTIVE_MAX_USECS &&
+		    (q_vector->rx.target_itr & ICE_ITR_MASK) ==
+		    ICE_ITR_ADAPTIVE_MAX_USECS)
+			goto clear_counts;
+	} else if (packets > 32) {
+		/* If we have processed over 32 packets in a single interrupt
+		 * for Tx assume we need to switch over to "bulk" mode.
+		 */
+		rc->target_itr &= ~ICE_ITR_ADAPTIVE_LATENCY;
+	}
+
+	/* We have no packets to actually measure against. This means
+	 * either one of the other queues on this vector is active or
+	 * we are a Tx queue doing TSO with too high of an interrupt rate.
+	 *
+	 * Between 4 and 56 we can assume that our current interrupt delay
+	 * is only slightly too low. As such we should increase it by a small
+	 * fixed amount.
+	 */
+	if (packets < 56) {
+		itr = rc->target_itr + ICE_ITR_ADAPTIVE_MIN_INC;
+		if ((itr & ICE_ITR_MASK) > ICE_ITR_ADAPTIVE_MAX_USECS) {
+			itr &= ICE_ITR_ADAPTIVE_LATENCY;
+			itr += ICE_ITR_ADAPTIVE_MAX_USECS;
+		}
+		goto clear_counts;
+	}
+
+	if (packets <= 256) {
+		itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr);
+		itr &= ICE_ITR_MASK;
+
+		/* Between 56 and 112 is our "goldilocks" zone where we are
+		 * working out "just right". Just report that our current
+		 * ITR is good for us.
+		 */
+		if (packets <= 112)
+			goto clear_counts;
+
+		/* If packet count is 128 or greater we are likely looking
+		 * at a slight overrun of the delay we want. Try halving
+		 * our delay to see if that will cut the number of packets
+		 * in half per interrupt.
+		 */
+		itr >>= 1;
+		itr &= ICE_ITR_MASK;
+		if (itr < ICE_ITR_ADAPTIVE_MIN_USECS)
+			itr = ICE_ITR_ADAPTIVE_MIN_USECS;
+
+		goto clear_counts;
+	}
+
+	/* The paths below assume we are dealing with a bulk ITR since
+	 * number of packets is greater than 256. We are just going to have
+	 * to compute a value and try to bring the count under control,
+	 * though for smaller packet sizes there isn't much we can do as
+	 * NAPI polling will likely be kicking in sooner rather than later.
+	 */
+	itr = ICE_ITR_ADAPTIVE_BULK;
+
+adjust_by_size_and_speed:
+
+	/* based on checks above packets cannot be 0 so division is safe */
+	itr = ice_adjust_itr_by_size_and_speed(q_vector->vsi->port_info,
+					       bytes / packets, itr);
+
+clear_counts:
+	/* write back value */
+	rc->target_itr = itr;
+
+	/* next update should occur within next jiffy */
+	rc->next_update = next_update + 1;
+
+	rc->total_bytes = 0;
+	rc->total_pkts = 0;
+}
+
+/**
+ * ice_buildreg_itr - build value for writing to the GLINT_DYN_CTL register
+ * @itr_idx: interrupt throttling index
+ * @itr: interrupt throttling value in usecs
+ */
+static u32 ice_buildreg_itr(u16 itr_idx, u16 itr)
+{
+	/* The ITR value is reported in microseconds, and the register value is
+	 * recorded in 2 microsecond units. For this reason we only need to
+	 * shift by the GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S to apply this
+	 * granularity as a shift instead of division. The mask makes sure the
+	 * ITR value is never odd so we don't accidentally write into the field
+	 * prior to the ITR field.
+	 */
+	itr &= ICE_ITR_MASK;
+
+	return GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+		(itr_idx << GLINT_DYN_CTL_ITR_INDX_S) |
+		(itr << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S));
+}
+
+/* The act of updating the ITR will cause it to immediately trigger. In order
+ * to prevent this from throwing off adaptive update statistics we defer the
+ * update so that it can only happen so often. So after either Tx or Rx are
+ * updated we make the adaptive scheme wait until either the ITR completely
+ * expires via the next_update expiration or we have been through at least
+ * 3 interrupts.
+ */
+#define ITR_COUNTDOWN_START 3
+
+/**
+ * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt
+ * @vsi: the VSI associated with the q_vector
+ * @q_vector: q_vector for which ITR is being updated and interrupt enabled
+ */
+static void
+ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+{
+	struct ice_ring_container *tx = &q_vector->tx;
+	struct ice_ring_container *rx = &q_vector->rx;
+	u32 itr_val;
+
+	/* This will do nothing if dynamic updates are not enabled */
+	ice_update_itr(q_vector, tx);
+	ice_update_itr(q_vector, rx);
+
+	/* This block of logic allows us to get away with only updating
+	 * one ITR value with each interrupt. The idea is to perform a
+	 * pseudo-lazy update with the following criteria.
+	 *
+	 * 1. Rx is given higher priority than Tx if both are in same state
+	 * 2. If we must reduce an ITR that is given highest priority.
+	 * 3. We then give priority to increasing ITR based on amount.
+	 */
+	if (rx->target_itr < rx->current_itr) {
+		/* Rx ITR needs to be reduced, this is highest priority */
+		itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr);
+		rx->current_itr = rx->target_itr;
+		q_vector->itr_countdown = ITR_COUNTDOWN_START;
+	} else if ((tx->target_itr < tx->current_itr) ||
+		   ((rx->target_itr - rx->current_itr) <
+		    (tx->target_itr - tx->current_itr))) {
+		/* Tx ITR needs to be reduced, this is second priority
+		 * Tx ITR needs to be increased more than Rx, fourth priority
+		 */
+		itr_val = ice_buildreg_itr(tx->itr_idx, tx->target_itr);
+		tx->current_itr = tx->target_itr;
+		q_vector->itr_countdown = ITR_COUNTDOWN_START;
+	} else if (rx->current_itr != rx->target_itr) {
+		/* Rx ITR needs to be increased, third priority */
+		itr_val = ice_buildreg_itr(rx->itr_idx, rx->target_itr);
+		rx->current_itr = rx->target_itr;
+		q_vector->itr_countdown = ITR_COUNTDOWN_START;
+	} else {
+		/* Still have to re-enable the interrupts */
+		itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0);
+		if (q_vector->itr_countdown)
+			q_vector->itr_countdown--;
+	}
+
+	if (!test_bit(__ICE_DOWN, vsi->state))
+		wr32(&vsi->back->hw,
+		     GLINT_DYN_CTL(q_vector->reg_idx),
+		     itr_val);
+}
+
+/**
  * ice_napi_poll - NAPI polling Rx/Tx cleanup routine
  * @napi: napi struct with our devices info in it
  * @budget: amount of work driver is allowed to do this pass, in packets
@@ -1108,9 +1451,9 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-			ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
+			ice_update_ena_itr(vsi, q_vector);
 
-	return min(work_done, budget - 1);
+	return min_t(int, work_done, budget - 1);
 }
 
 /* helper function for building cmd/type/offset */
@@ -1295,19 +1638,14 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 	ice_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
 
 dma_error:
-	/* clear dma mappings for failed tx_buf map */
+	/* clear DMA mappings for failed tx_buf map */
 	for (;;) {
 		tx_buf = &tx_ring->tx_buf[i];
 		ice_unmap_and_free_tx_buf(tx_ring, tx_buf);
@@ -1402,6 +1740,12 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
 		break;
 	case IPPROTO_SCTP:
+		/* enable SCTP checksum offload */
+		cmd |= ICE_TX_DESC_CMD_L4T_EOFT_SCTP;
+		l4_len = sizeof(struct sctphdr) >> 2;
+		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
+		break;
+
 	default:
 		if (first->tx_flags & ICE_TX_FLAGS_TSO)
 			return -1;
@@ -1415,7 +1759,7 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 }
 
 /**
- * ice_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
+ * ice_tx_prepare_vlan_flags - prepare generic Tx VLAN tagging flags for HW
  * @tx_ring: ring to send buffer on
  * @first: pointer to struct ice_tx_buf
  *
@@ -1441,7 +1785,7 @@ ice_tx_prepare_vlan_flags(struct ice_ring *tx_ring, struct ice_tx_buf *first)
 		 * to the encapsulated ethertype.
 		 */
 		skb->protocol = vlan_get_protocol(skb);
-		goto out;
+		return 0;
 	}
 
 	/* if we have a HW VLAN tag being added, default to the HW one */
@@ -1463,8 +1807,7 @@ ice_tx_prepare_vlan_flags(struct ice_ring *tx_ring, struct ice_tx_buf *first)
 		first->tx_flags |= ICE_TX_FLAGS_SW_VLAN;
 	}
 
-out:
-	return 0;
+	return ice_tx_prepare_vlan_flags_dcb(tx_ring, first);
 }
 
 /**
@@ -1501,6 +1844,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	if (err < 0)
 		return err;
 
+	/* cppcheck-suppress unreadVariable */
 	ip.hdr = skb_network_header(skb);
 	l4.hdr = skb_transport_header(skb);
 
@@ -1530,10 +1874,10 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	cd_mss = skb_shinfo(skb)->gso_size;
 
 	/* record cdesc_qw1 with TSO parameters */
-	off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX |
-			 (ICE_TX_CTX_DESC_TSO << ICE_TXD_CTX_QW1_CMD_S) |
-			 (cd_tso_len << ICE_TXD_CTX_QW1_TSO_LEN_S) |
-			 (cd_mss << ICE_TXD_CTX_QW1_MSS_S);
+	off->cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
+			     (ICE_TX_CTX_DESC_TSO << ICE_TXD_CTX_QW1_CMD_S) |
+			     (cd_tso_len << ICE_TXD_CTX_QW1_TSO_LEN_S) |
+			     (cd_mss << ICE_TXD_CTX_QW1_MSS_S));
 	first->tx_flags |= ICE_TX_FLAGS_TSO;
 	return 1;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 75d0eaf6c9dd..ec76aba347b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -45,27 +45,32 @@
 #define ICE_TX_FLAGS_HW_VLAN	BIT(1)
 #define ICE_TX_FLAGS_SW_VLAN	BIT(2)
 #define ICE_TX_FLAGS_VLAN_M	0xffff0000
+#define ICE_TX_FLAGS_VLAN_PR_M	0xe0000000
+#define ICE_TX_FLAGS_VLAN_PR_S	29
 #define ICE_TX_FLAGS_VLAN_S	16
 
+#define ICE_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 struct ice_tx_buf {
 	struct ice_tx_desc *next_to_watch;
 	struct sk_buff *skb;
 	unsigned int bytecount;
 	unsigned short gso_segs;
 	u32 tx_flags;
-	DEFINE_DMA_UNMAP_ADDR(dma);
 	DEFINE_DMA_UNMAP_LEN(len);
+	DEFINE_DMA_UNMAP_ADDR(dma);
 };
 
 struct ice_tx_offload_params {
-	u8 header_len;
+	u64 cd_qw1;
+	struct ice_ring *tx_ring;
 	u32 td_cmd;
 	u32 td_offset;
 	u32 td_l2tag1;
-	u16 cd_l2tag2;
 	u32 cd_tunnel_params;
-	u64 cd_qw1;
-	struct ice_ring *tx_ring;
+	u16 cd_l2tag2;
+	u8 header_len;
 };
 
 struct ice_rx_buf {
@@ -73,6 +78,7 @@ struct ice_rx_buf {
 	dma_addr_t dma;
 	struct page *page;
 	unsigned int page_offset;
+	u16 pagecnt_bias;
 };
 
 struct ice_q_stats {
@@ -116,18 +122,27 @@ enum ice_rx_dtype {
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
-#define ICE_ITR_DYNAMIC	0x8000  /* use top bit as a flag */
-#define ICE_ITR_8K	125
+#define ICE_ITR_8K	124
 #define ICE_ITR_20K	50
-#define ICE_DFLT_TX_ITR	ICE_ITR_20K
-#define ICE_DFLT_RX_ITR	ICE_ITR_20K
-/* apply ITR granularity translation to program the register. itr_gran is either
- * 2 or 4 usecs so we need to divide by 2 first then shift by that value
- */
-#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> \
-				   ((itr_gran) / 2))
+#define ICE_ITR_MAX	8160
+#define ICE_DFLT_TX_ITR	(ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_DFLT_RX_ITR	(ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_ITR_DYNAMIC	0x8000  /* used as flag for itr_setting */
+#define ITR_IS_DYNAMIC(setting) (!!((setting) & ICE_ITR_DYNAMIC))
+#define ITR_TO_REG(setting)	((setting) & ~ICE_ITR_DYNAMIC)
+#define ICE_ITR_GRAN_S		1	/* ITR granularity is always 2us */
+#define ICE_ITR_GRAN_US		BIT(ICE_ITR_GRAN_S)
+#define ICE_ITR_MASK		0x1FFE	/* ITR register value alignment mask */
+#define ITR_REG_ALIGN(setting)	__ALIGN_MASK(setting, ~ICE_ITR_MASK)
+
+#define ICE_ITR_ADAPTIVE_MIN_INC	0x0002
+#define ICE_ITR_ADAPTIVE_MIN_USECS	0x0002
+#define ICE_ITR_ADAPTIVE_MAX_USECS	0x00FA
+#define ICE_ITR_ADAPTIVE_LATENCY	0x8000
+#define ICE_ITR_ADAPTIVE_BULK		0x0000
 
 #define ICE_DFLT_INTRL	0
+#define ICE_MAX_INTRL	236
 
 /* Legacy or Advanced Mode Queue */
 #define ICE_TX_ADVANCED	0
@@ -135,6 +150,7 @@ enum ice_rx_dtype {
 
 /* descriptor ring, associated with a VSI */
 struct ice_ring {
+	/* CL1 - 1st cacheline starts here */
 	struct ice_ring *next;		/* pointer to next ring in q_vector */
 	void *desc;			/* Descriptor ring memory */
 	struct device *dev;		/* Used for DMA mapping */
@@ -146,8 +162,11 @@ struct ice_ring {
 		struct ice_tx_buf *tx_buf;
 		struct ice_rx_buf *rx_buf;
 	};
+	/* CL2 - 2nd cacheline starts here */
 	u16 q_index;			/* Queue number of ring */
-	u32 txq_teid;			/* Added Tx queue TEID */
+	u16 q_handle;			/* Queue handle per TC */
+
+	u8 ring_active:1;		/* is ring online or not */
 
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
@@ -155,8 +174,7 @@ struct ice_ring {
 	/* used in interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
-
-	u8 ring_active;			/* is ring online or not */
+	u16 next_to_alloc;
 
 	/* stats structs */
 	struct ice_q_stats	stats;
@@ -166,27 +184,33 @@ struct ice_ring {
 		struct ice_rxq_stats rx_stats;
 	};
 
-	unsigned int size;		/* length of descriptor ring in bytes */
-	dma_addr_t dma;			/* physical address of ring */
 	struct rcu_head rcu;		/* to avoid race on free */
-	u16 next_to_alloc;
+	/* CLX - the below items are only accessed infrequently and should be
+	 * in their own cache line if possible
+	 */
+	dma_addr_t dma;			/* physical address of ring */
+	unsigned int size;		/* length of descriptor ring in bytes */
+	u32 txq_teid;			/* Added Tx queue TEID */
+	u16 rx_buf_len;
+#ifdef CONFIG_DCB
+	u8 dcb_tc;			/* Traffic class of ring */
+#endif /* CONFIG_DCB */
 } ____cacheline_internodealigned_in_smp;
 
-enum ice_latency_range {
-	ICE_LOWEST_LATENCY = 0,
-	ICE_LOW_LATENCY = 1,
-	ICE_BULK_LATENCY = 2,
-	ICE_ULTRA_LATENCY = 3,
-};
-
 struct ice_ring_container {
-	/* array of pointers to rings */
+	/* head of linked-list of rings */
 	struct ice_ring *ring;
+	unsigned long next_update;	/* jiffies value of next queue update */
 	unsigned int total_bytes;	/* total bytes processed this int */
 	unsigned int total_pkts;	/* total packets processed this int */
-	enum ice_latency_range latency_range;
-	int itr_idx;	/* index in the interrupt vector */
-	u16 itr;
+	u16 itr_idx;		/* index in the interrupt vector */
+	u16 target_itr;		/* value in usecs divided by the hw->itr_gran */
+	u16 current_itr;	/* value in usecs divided by the hw->itr_gran */
+	/* high bit set means dynamic ITR, rest is used to store user
+	 * readable ITR value in usecs and must be converted before programming
+	 * to a register.
+	 */
+	u16 itr_setting;
 };
 
 /* iterator for handling rings in ring container */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 0ea428104215..24bbef8bbe69 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -23,7 +23,9 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc)
 
 /* debug masks - set these bits in hw->debug_mask to control output */
 #define ICE_DBG_INIT		BIT_ULL(1)
+#define ICE_DBG_FW_LOG		BIT_ULL(3)
 #define ICE_DBG_LINK		BIT_ULL(4)
+#define ICE_DBG_PHY		BIT_ULL(5)
 #define ICE_DBG_QCTX		BIT_ULL(6)
 #define ICE_DBG_NVM		BIT_ULL(7)
 #define ICE_DBG_LAN		BIT_ULL(8)
@@ -60,6 +62,13 @@ enum ice_fc_mode {
 	ICE_FC_DFLT
 };
 
+enum ice_fec_mode {
+	ICE_FEC_NONE = 0,
+	ICE_FEC_RS,
+	ICE_FEC_BASER,
+	ICE_FEC_AUTO
+};
+
 enum ice_set_fc_aq_failures {
 	ICE_SET_FC_AQ_FAIL_NONE = 0,
 	ICE_SET_FC_AQ_FAIL_GET,
@@ -85,11 +94,14 @@ enum ice_media_type {
 enum ice_vsi_type {
 	ICE_VSI_PF = 0,
 	ICE_VSI_VF,
+	ICE_VSI_LB = 6,
 };
 
 struct ice_link_status {
 	/* Refer to ice_aq_phy_type for bits definition */
 	u64 phy_type_low;
+	u64 phy_type_high;
+	u8 topo_media_conflict;
 	u16 max_frame_size;
 	u16 link_speed;
 	u16 req_speeds;
@@ -97,6 +109,7 @@ struct ice_link_status {
 	u8 link_info;
 	u8 an_info;
 	u8 ext_info;
+	u8 fec_info;
 	u8 pacing;
 	/* Refer to #define from module_type[ICE_MODULE_TYPE_TOTAL_BYTE] of
 	 * ice_aqc_get_phy_caps structure
@@ -105,7 +118,7 @@ struct ice_link_status {
 };
 
 /* Different reset sources for which a disable queue AQ call has to be made in
- * order to clean the TX scheduler as a part of the reset
+ * order to clean the Tx scheduler as a part of the reset
  */
 enum ice_disq_rst_src {
 	ICE_NO_RESET = 0,
@@ -118,6 +131,7 @@ struct ice_phy_info {
 	struct ice_link_status link_info;
 	struct ice_link_status link_info_old;
 	u64 phy_type_low;
+	u64 phy_type_high;
 	enum ice_media_type media_type;
 	u8 get_link_info;
 };
@@ -126,11 +140,11 @@ struct ice_phy_info {
 struct ice_hw_common_caps {
 	u32 valid_functions;
 
-	/* TX/RX queues */
-	u16 num_rxq;		/* Number/Total RX queues */
-	u16 rxq_first_id;	/* First queue ID for RX queues */
-	u16 num_txq;		/* Number/Total TX queues */
-	u16 txq_first_id;	/* First queue ID for TX queues */
+	/* Tx/Rx queues */
+	u16 num_rxq;		/* Number/Total Rx queues */
+	u16 rxq_first_id;	/* First queue ID for Rx queues */
+	u16 num_txq;		/* Number/Total Tx queues */
+	u16 txq_first_id;	/* First queue ID for Tx queues */
 
 	/* MSI-X vectors */
 	u16 num_msix_vectors;
@@ -145,6 +159,8 @@ struct ice_hw_common_caps {
 	/* RSS related capabilities */
 	u16 rss_table_size;		/* 512 for PFs and 64 for VFs */
 	u8 rss_table_entry_width;	/* RSS Entry width in bits */
+
+	u8 dcb;
 };
 
 /* Function specific capabilities */
@@ -207,12 +223,17 @@ struct ice_nvm_info {
 #define ICE_MAX_TRAFFIC_CLASS 8
 #define ICE_TXSCHED_MAX_BRANCHES ICE_MAX_TRAFFIC_CLASS
 
+#define ice_for_each_traffic_class(_i)	\
+	for ((_i) = 0; (_i) < ICE_MAX_TRAFFIC_CLASS; (_i)++)
+
+#define ICE_INVAL_TEID 0xFFFFFFFF
+
 struct ice_sched_node {
 	struct ice_sched_node *parent;
 	struct ice_sched_node *sibling; /* next sibling in the same layer */
 	struct ice_sched_node **children;
 	struct ice_aqc_txsched_elem_data info;
-	u32 agg_id;			/* aggregator group id */
+	u32 agg_id;			/* aggregator group ID */
 	u16 vsi_handle;
 	u8 in_use;			/* suspended or in use */
 	u8 tx_sched_layer;		/* Logical Layer (1-9) */
@@ -239,13 +260,12 @@ enum ice_agg_type {
 #define ICE_SCHED_DFLT_RL_PROF_ID	0
 #define ICE_SCHED_DFLT_BW_WT		1
 
-/* vsi type list entry to locate corresponding vsi/ag nodes */
+/* VSI type list entry to locate corresponding VSI/ag nodes */
 struct ice_sched_vsi_info {
 	struct ice_sched_node *vsi_node[ICE_MAX_TRAFFIC_CLASS];
 	struct ice_sched_node *ag_node[ICE_MAX_TRAFFIC_CLASS];
 	struct list_head list_entry;
 	u16 max_lanq[ICE_MAX_TRAFFIC_CLASS];
-	u16 vsi_id;
 };
 
 /* driver defines the policy */
@@ -255,15 +275,70 @@ struct ice_sched_tx_policy {
 	u8 rdma_ena;
 };
 
+/* CEE or IEEE 802.1Qaz ETS Configuration data */
+struct ice_dcb_ets_cfg {
+	u8 willing;
+	u8 cbs;
+	u8 maxtcs;
+	u8 prio_table[ICE_MAX_TRAFFIC_CLASS];
+	u8 tcbwtable[ICE_MAX_TRAFFIC_CLASS];
+	u8 tsatable[ICE_MAX_TRAFFIC_CLASS];
+};
+
+/* CEE or IEEE 802.1Qaz PFC Configuration data */
+struct ice_dcb_pfc_cfg {
+	u8 willing;
+	u8 mbc;
+	u8 pfccap;
+	u8 pfcena;
+};
+
+/* CEE or IEEE 802.1Qaz Application Priority data */
+struct ice_dcb_app_priority_table {
+	u16 prot_id;
+	u8 priority;
+	u8 selector;
+};
+
+#define ICE_MAX_USER_PRIORITY	8
+#define ICE_DCBX_MAX_APPS	32
+#define ICE_LLDPDU_SIZE		1500
+#define ICE_TLV_STATUS_OPER	0x1
+#define ICE_TLV_STATUS_SYNC	0x2
+#define ICE_TLV_STATUS_ERR	0x4
+#define ICE_APP_PROT_ID_FCOE	0x8906
+#define ICE_APP_PROT_ID_ISCSI	0x0cbc
+#define ICE_APP_PROT_ID_FIP	0x8914
+#define ICE_APP_SEL_ETHTYPE	0x1
+#define ICE_APP_SEL_TCPIP	0x2
+#define ICE_CEE_APP_SEL_ETHTYPE	0x0
+#define ICE_CEE_APP_SEL_TCPIP	0x1
+
+struct ice_dcbx_cfg {
+	u32 numapps;
+	u32 tlv_status; /* CEE mode TLV status */
+	struct ice_dcb_ets_cfg etscfg;
+	struct ice_dcb_ets_cfg etsrec;
+	struct ice_dcb_pfc_cfg pfc;
+	struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS];
+	u8 dcbx_mode;
+#define ICE_DCBX_MODE_CEE	0x1
+#define ICE_DCBX_MODE_IEEE	0x2
+	u8 app_mode;
+#define ICE_DCBX_APPS_NON_WILLING	0x1
+};
+
 struct ice_port_info {
 	struct ice_sched_node *root;	/* Root Node per Port */
-	struct ice_hw *hw;		/* back pointer to hw instance */
+	struct ice_hw *hw;		/* back pointer to HW instance */
 	u32 last_node_teid;		/* scheduler last node info */
 	u16 sw_id;			/* Initial switch ID belongs to port */
 	u16 pf_vf_num;
 	u8 port_state;
 #define ICE_SCHED_PORT_STATE_INIT	0x0
 #define ICE_SCHED_PORT_STATE_READY	0x1
+	u8 lport;
+#define ICE_LPORT_MASK			0xff
 	u16 dflt_tx_vsi_rule_id;
 	u16 dflt_tx_vsi_num;
 	u16 dflt_rx_vsi_rule_id;
@@ -272,10 +347,14 @@ struct ice_port_info {
 	struct ice_mac_info mac;
 	struct ice_phy_info phy;
 	struct mutex sched_lock;	/* protect access to TXSched tree */
-	struct list_head agg_list;	/* lists all aggregator */
-	u8 lport;
-#define ICE_LPORT_MASK		0xff
-	u8 is_vf;
+	struct ice_dcbx_cfg local_dcbx_cfg;	/* Oper/Local Cfg */
+	/* DCBX info */
+	struct ice_dcbx_cfg remote_dcbx_cfg;	/* Peer Cfg */
+	struct ice_dcbx_cfg desired_dcbx_cfg;	/* CEE Desired Cfg */
+	/* LLDP/DCBX Status */
+	u8 dcbx_status:3;		/* see ICE_DCBX_STATUS_DIS */
+	u8 is_sw_lldp:1;
+	u8 is_vf:1;
 };
 
 struct ice_switch_info {
@@ -319,17 +398,18 @@ struct ice_hw {
 
 	u8 pf_id;		/* device profile info */
 
-	/* TX Scheduler values */
+	/* Tx Scheduler values */
 	u16 num_tx_sched_layers;
 	u16 num_tx_sched_phys_layers;
 	u8 flattened_layers;
 	u8 max_cgds;
 	u8 sw_entry_point_layer;
 	u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM];
+	struct list_head agg_list;	/* lists all aggregator */
 
 	struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI];
 	u8 evb_veb;		/* true for VEB, false for VEPA */
-	u8 reset_ongoing;	/* true if hw is in reset, false otherwise */
+	u8 reset_ongoing;	/* true if HW is in reset, false otherwise */
 	struct ice_bus_info bus;
 	struct ice_nvm_info nvm;
 	struct ice_hw_dev_caps dev_caps;	/* device capabilities */
@@ -354,7 +434,7 @@ struct ice_hw {
 	struct ice_fw_log_cfg fw_log;
 
 /* Device max aggregate bandwidths corresponding to the GL_PWR_MODE_CTL
- * register. Used for determining the itr/intrl granularity during
+ * register. Used for determining the ITR/intrl granularity during
  * initialization.
  */
 #define ICE_MAX_AGG_BW_200G	0x0
@@ -408,6 +488,11 @@ struct ice_hw_port_stats {
 	u64 link_xoff_rx;		/* lxoffrxc */
 	u64 link_xon_tx;		/* lxontxc */
 	u64 link_xoff_tx;		/* lxofftxc */
+	u64 priority_xon_rx[8];		/* pxonrxc[8] */
+	u64 priority_xoff_rx[8];	/* pxoffrxc[8] */
+	u64 priority_xon_tx[8];		/* pxontxc[8] */
+	u64 priority_xoff_tx[8];	/* pxofftxc[8] */
+	u64 priority_xon_2_xoff[8];	/* pxon2offc[8] */
 	u64 rx_size_64;			/* prc64 */
 	u64 rx_size_127;		/* prc127 */
 	u64 rx_size_255;		/* prc255 */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 05ff4f910649..5d24b539648f 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -5,6 +5,37 @@
 #include "ice_lib.h"
 
 /**
+ * ice_err_to_virt err - translate errors for VF return code
+ * @ice_err: error return code
+ */
+static enum virtchnl_status_code ice_err_to_virt_err(enum ice_status ice_err)
+{
+	switch (ice_err) {
+	case ICE_SUCCESS:
+		return VIRTCHNL_STATUS_SUCCESS;
+	case ICE_ERR_BAD_PTR:
+	case ICE_ERR_INVAL_SIZE:
+	case ICE_ERR_DEVICE_NOT_SUPPORTED:
+	case ICE_ERR_PARAM:
+	case ICE_ERR_CFG:
+		return VIRTCHNL_STATUS_ERR_PARAM;
+	case ICE_ERR_NO_MEMORY:
+		return VIRTCHNL_STATUS_ERR_NO_MEMORY;
+	case ICE_ERR_NOT_READY:
+	case ICE_ERR_RESET_FAILED:
+	case ICE_ERR_FW_API_VER:
+	case ICE_ERR_AQ_ERROR:
+	case ICE_ERR_AQ_TIMEOUT:
+	case ICE_ERR_AQ_FULL:
+	case ICE_ERR_AQ_NO_WORK:
+	case ICE_ERR_AQ_EMPTY:
+		return VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
+	default:
+		return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED;
+	}
+}
+
+/**
  * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF
  * @pf: pointer to the PF structure
  * @v_opcode: operation code
@@ -14,7 +45,7 @@
  */
 static void
 ice_vc_vf_broadcast(struct ice_pf *pf, enum virtchnl_ops v_opcode,
-		    enum ice_status v_retval, u8 *msg, u16 msglen)
+		    enum virtchnl_status_code v_retval, u8 *msg, u16 msglen)
 {
 	struct ice_hw *hw = &pf->hw;
 	struct ice_vf *vf = pf->vf;
@@ -72,7 +103,7 @@ ice_set_pfe_link_forced(struct ice_vf *vf, struct virtchnl_pf_event *pfe,
 	u16 link_speed;
 
 	if (link_up)
-		link_speed = ICE_AQ_LINK_SPEED_40GB;
+		link_speed = ICE_AQ_LINK_SPEED_100GB;
 	else
 		link_speed = ICE_AQ_LINK_SPEED_UNKNOWN;
 
@@ -104,37 +135,26 @@ static void ice_vc_notify_vf_link_state(struct ice_vf *vf)
 		ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info &
 				 ICE_AQ_LINK_UP);
 
-	ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe,
+	ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT,
+			      VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe,
 			      sizeof(pfe), NULL);
 }
 
 /**
- * ice_get_vf_vector - get VF interrupt vector register offset
- * @vf_msix: number of MSIx vector per VF on a PF
- * @vf_id: VF identifier
- * @i: index of MSIx vector
- */
-static u32 ice_get_vf_vector(int vf_msix, int vf_id, int i)
-{
-	return ((i == 0) ? VFINT_DYN_CTLN(vf_id) :
-		 VFINT_DYN_CTLN(((vf_msix - 1) * (vf_id)) + (i - 1)));
-}
-
-/**
  * ice_free_vf_res - Free a VF's resources
  * @vf: pointer to the VF info
  */
 static void ice_free_vf_res(struct ice_vf *vf)
 {
 	struct ice_pf *pf = vf->pf;
-	int i, pf_vf_msix;
+	int i, last_vector_idx;
 
 	/* First, disable VF's configuration API to prevent OS from
 	 * accessing the VF's VSI after it's freed or invalidated.
 	 */
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
-	/* free vsi & disconnect it from the parent uplink */
+	/* free VSI and disconnect it from the parent uplink */
 	if (vf->lan_vsi_idx) {
 		ice_vsi_release(pf->vsi[vf->lan_vsi_idx]);
 		vf->lan_vsi_idx = 0;
@@ -142,13 +162,10 @@ static void ice_free_vf_res(struct ice_vf *vf)
 		vf->num_mac = 0;
 	}
 
-	pf_vf_msix = pf->num_vf_msix;
+	last_vector_idx = vf->first_vector_idx + pf->num_vf_msix - 1;
 	/* Disable interrupts so that VF starts in a known state */
-	for (i = 0; i < pf_vf_msix; i++) {
-		u32 reg_idx;
-
-		reg_idx = ice_get_vf_vector(pf_vf_msix, vf->vf_id, i);
-		wr32(&pf->hw, reg_idx, VFINT_DYN_CTLN_CLEARPBA_M);
+	for (i = vf->first_vector_idx; i <= last_vector_idx; i++) {
+		wr32(&pf->hw, GLINT_DYN_CTL(i), GLINT_DYN_CTL_CLEARPBA_M);
 		ice_flush(&pf->hw);
 	}
 	/* reset some of the state variables keeping track of the resources */
@@ -199,6 +216,42 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 }
 
 /**
+ * ice_sriov_free_msix_res - Reset/free any used MSIX resources
+ * @pf: pointer to the PF structure
+ *
+ * If MSIX entries from the pf->irq_tracker were needed then we need to
+ * reset the irq_tracker->end and give back the entries we needed to
+ * num_avail_sw_msix.
+ *
+ * If no MSIX entries were taken from the pf->irq_tracker then just clear
+ * the pf->sriov_base_vector.
+ *
+ * Returns 0 on success, and -EINVAL on error.
+ */
+static int ice_sriov_free_msix_res(struct ice_pf *pf)
+{
+	struct ice_res_tracker *res;
+
+	if (!pf)
+		return -EINVAL;
+
+	res = pf->irq_tracker;
+	if (!res)
+		return -EINVAL;
+
+	/* give back irq_tracker resources used */
+	if (pf->sriov_base_vector < res->num_entries) {
+		res->end = res->num_entries;
+		pf->num_avail_sw_msix +=
+			res->num_entries - pf->sriov_base_vector;
+	}
+
+	pf->sriov_base_vector = 0;
+
+	return 0;
+}
+
+/**
  * ice_free_vfs - Free all VFs
  * @pf: pointer to the PF structure
  */
@@ -213,28 +266,30 @@ void ice_free_vfs(struct ice_pf *pf)
 	while (test_and_set_bit(__ICE_VF_DIS, pf->state))
 		usleep_range(1000, 2000);
 
-	/* Disable IOV before freeing resources. This lets any VF drivers
-	 * running in the host get themselves cleaned up before we yank
-	 * the carpet out from underneath their feet.
-	 */
-	if (!pci_vfs_assigned(pf->pdev))
-		pci_disable_sriov(pf->pdev);
-	else
-		dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
-
 	/* Avoid wait time by stopping all VFs at the same time */
 	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		struct ice_vsi *vsi;
+
 		if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states))
 			continue;
 
+		vsi = pf->vsi[pf->vf[i].lan_vsi_idx];
 		/* stop rings without wait time */
-		ice_vsi_stop_tx_rings(pf->vsi[pf->vf[i].lan_vsi_idx],
-				      ICE_NO_RESET, i);
-		ice_vsi_stop_rx_rings(pf->vsi[pf->vf[i].lan_vsi_idx]);
+		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, i);
+		ice_vsi_stop_rx_rings(vsi);
 
 		clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states);
 	}
 
+	/* Disable IOV before freeing resources. This lets any VF drivers
+	 * running in the host get themselves cleaned up before we yank
+	 * the carpet out from underneath their feet.
+	 */
+	if (!pci_vfs_assigned(pf->pdev))
+		pci_disable_sriov(pf->pdev);
+	else
+		dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
+
 	tmp = pf->num_alloc_vfs;
 	pf->num_vf_qps = 0;
 	pf->num_alloc_vfs = 0;
@@ -253,6 +308,10 @@ void ice_free_vfs(struct ice_pf *pf)
 		}
 	}
 
+	if (ice_sriov_free_msix_res(pf))
+		dev_err(&pf->pdev->dev,
+			"Failed to free MSIX resources used by SR-IOV\n");
+
 	devm_kfree(&pf->pdev->dev, pf->vf);
 	pf->vf = NULL;
 
@@ -308,6 +367,11 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr)
 	 */
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
+	/* Clear the VF's ARQLEN register. This is how the VF detects reset,
+	 * since the VFGEN_RSTAT register doesn't stick at 0 after reset.
+	 */
+	wr32(hw, VF_MBX_ARQLEN(vf_abs_id), 0);
+
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
 	 */
@@ -335,58 +399,77 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr)
 }
 
 /**
- * ice_vsi_set_pvid - Set port VLAN id for the VSI
- * @vsi: the VSI being changed
- * @vid: the VLAN id to set as a PVID
+ * ice_vsi_set_pvid_fill_ctxt - Set VSI ctxt for add PVID
+ * @ctxt: the VSI ctxt to fill
+ * @vid: the VLAN ID to set as a PVID
  */
-static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid)
+static void ice_vsi_set_pvid_fill_ctxt(struct ice_vsi_ctx *ctxt, u16 vid)
 {
-	struct device *dev = &vsi->back->pdev->dev;
-	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
-	enum ice_status status;
-
-	ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED |
-			       ICE_AQ_VSI_PVLAN_INSERT_PVID |
-			       ICE_AQ_VSI_VLAN_EMOD_STR;
-	ctxt.info.pvid = cpu_to_le16(vid);
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
-
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
-	if (status) {
-		dev_info(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
-			 status, hw->adminq.sq_last_status);
-		return -EIO;
-	}
+	ctxt->info.vlan_flags = (ICE_AQ_VSI_VLAN_MODE_UNTAGGED |
+				 ICE_AQ_VSI_PVLAN_INSERT_PVID |
+				 ICE_AQ_VSI_VLAN_EMOD_STR);
+	ctxt->info.pvid = cpu_to_le16(vid);
+	ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID |
+						ICE_AQ_VSI_PROP_SW_VALID);
+}
 
-	vsi->info.pvid = ctxt.info.pvid;
-	vsi->info.vlan_flags = ctxt.info.vlan_flags;
-	return 0;
+/**
+ * ice_vsi_kill_pvid_fill_ctxt - Set VSI ctx for remove PVID
+ * @ctxt: the VSI ctxt to fill
+ */
+static void ice_vsi_kill_pvid_fill_ctxt(struct ice_vsi_ctx *ctxt)
+{
+	ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
+	ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
+	ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA;
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID |
+						ICE_AQ_VSI_PROP_SW_VALID);
 }
 
 /**
- * ice_vsi_kill_pvid - Remove port VLAN id from the VSI
- * @vsi: the VSI being changed
+ * ice_vsi_manage_pvid - Enable or disable port VLAN for VSI
+ * @vsi: the VSI to update
+ * @vid: the VLAN ID to set as a PVID
+ * @enable: true for enable PVID false for disable
  */
-static int ice_vsi_kill_pvid(struct ice_vsi *vsi)
+static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 vid, bool enable)
 {
-	struct ice_pf *pf = vsi->back;
+	struct device *dev = &vsi->back->pdev->dev;
+	struct ice_hw *hw = &vsi->back->hw;
+	struct ice_vsi_ctx *ctxt;
+	enum ice_status status;
+	int ret = 0;
 
-	if (ice_vsi_manage_vlan_stripping(vsi, false)) {
-		dev_err(&pf->pdev->dev, "Error removing Port VLAN on VSI %i\n",
-			vsi->vsi_num);
-		return -ENODEV;
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
+
+	ctxt->info = vsi->info;
+	if (enable)
+		ice_vsi_set_pvid_fill_ctxt(ctxt, vid);
+	else
+		ice_vsi_kill_pvid_fill_ctxt(ctxt);
+
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
+	if (status) {
+		dev_info(dev, "update VSI for port VLAN failed, err %d aq_err %d\n",
+			 status, hw->adminq.sq_last_status);
+		ret = -EIO;
+		goto out;
 	}
 
-	vsi->info.pvid = 0;
-	return 0;
+	vsi->info = ctxt->info;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
  * ice_vf_vsi_setup - Set up a VF VSI
  * @pf: board private structure
  * @pi: pointer to the port_info instance
- * @vf_id: defines VF id to which this VSI connects.
+ * @vf_id: defines VF ID to which this VSI connects.
  *
  * Returns pointer to the successfully allocated VSI struct on success,
  * otherwise returns NULL on failure.
@@ -398,6 +481,22 @@ ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id)
 }
 
 /**
+ * ice_calc_vf_first_vector_idx - Calculate absolute MSIX vector index in HW
+ * @pf: pointer to PF structure
+ * @vf: pointer to VF that the first MSIX vector index is being calculated for
+ *
+ * This returns the first MSIX vector index in HW that is used by this VF and
+ * this will always be the OICR index in the AVF driver so any functionality
+ * using vf->first_vector_idx for queue configuration will have to increment by
+ * 1 to avoid meddling with the OICR index.
+ */
+static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
+{
+	return pf->hw.func_caps.common_cap.msix_vector_first_id +
+		pf->sriov_base_vector + vf->vf_id * pf->num_vf_msix;
+}
+
+/**
  * ice_alloc_vsi_res - Setup VF VSI and its resources
  * @vf: pointer to the VF structure
  *
@@ -411,8 +510,10 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 	struct ice_vsi *vsi;
 	int status = 0;
 
-	vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
+	/* first vector index is the VFs OICR index */
+	vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);
 
+	vsi = ice_vf_vsi_setup(pf, pf->hw.port_info, vf->vf_id);
 	if (!vsi) {
 		dev_err(&pf->pdev->dev, "Failed to create VF VSI\n");
 		return -ENOMEM;
@@ -421,17 +522,11 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 	vf->lan_vsi_idx = vsi->idx;
 	vf->lan_vsi_num = vsi->vsi_num;
 
-	/* first vector index is the VFs OICR index */
-	vf->first_vector_idx = vsi->hw_base_vector;
-	/* Since hw_base_vector holds the vector where data queue interrupts
-	 * starts, increment by 1 since VFs allocated vectors include OICR intr
-	 * as well.
-	 */
-	vsi->hw_base_vector += 1;
-
 	/* Check if port VLAN exist before, and restore it accordingly */
-	if (vf->port_vlan_id)
-		ice_vsi_set_pvid(vsi, vf->port_vlan_id);
+	if (vf->port_vlan_id) {
+		ice_vsi_manage_pvid(vsi, vf->port_vlan_id, true);
+		ice_vsi_add_vlan(vsi, vf->port_vlan_id & ICE_VLAN_M);
+	}
 
 	eth_broadcast_addr(broadcast);
 
@@ -452,7 +547,7 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 
 	/* Clear this bit after VF initialization since we shouldn't reclaim
 	 * and reassign interrupts for synchronous or asynchronous VFR events.
-	 * We dont want to reconfigure interrupts since AVF driver doesn't
+	 * We don't want to reconfigure interrupts since AVF driver doesn't
 	 * expect vector assignment to be changed unless there is a request for
 	 * more vectors.
 	 */
@@ -468,6 +563,8 @@ ice_alloc_vsi_res_exit:
  */
 static int ice_alloc_vf_res(struct ice_vf *vf)
 {
+	struct ice_pf *pf = vf->pf;
+	int tx_rx_queue_left;
 	int status;
 
 	/* setup VF VSI and necessary resources */
@@ -475,6 +572,15 @@ static int ice_alloc_vf_res(struct ice_vf *vf)
 	if (status)
 		goto ice_alloc_vf_res_exit;
 
+	/* Update number of VF queues, in case VF had requested for queue
+	 * changes
+	 */
+	tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx);
+	tx_rx_queue_left += ICE_DFLT_QS_PER_VF;
+	if (vf->num_req_qs && vf->num_req_qs <= tx_rx_queue_left &&
+	    vf->num_req_qs != vf->num_vf_qs)
+		vf->num_vf_qs = vf->num_req_qs;
+
 	if (vf->trusted)
 		set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps);
 	else
@@ -531,6 +637,10 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 		wr32(hw, GLINT_VECT2FUNC(v), reg);
 	}
 
+	/* Map mailbox interrupt. We put an explicit 0 here to remind us that
+	 * VF admin queue interrupts will go to VF MSI-X vector 0.
+	 */
+	wr32(hw, VPINT_MBX_CTL(abs_vf_id), VPINT_MBX_CTL_CAUSE_ENA_M | 0);
 	/* set regardless of mapping mode */
 	wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M);
 
@@ -610,6 +720,97 @@ ice_determine_res(struct ice_pf *pf, u16 avail_res, u16 max_res, u16 min_res)
 }
 
 /**
+ * ice_calc_vf_reg_idx - Calculate the VF's register index in the PF space
+ * @vf: VF to calculate the register index for
+ * @q_vector: a q_vector associated to the VF
+ */
+int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
+{
+	struct ice_pf *pf;
+
+	if (!vf || !q_vector)
+		return -EINVAL;
+
+	pf = vf->pf;
+
+	/* always add one to account for the OICR being the first MSIX */
+	return pf->sriov_base_vector + pf->num_vf_msix * vf->vf_id +
+		q_vector->v_idx + 1;
+}
+
+/**
+ * ice_get_max_valid_res_idx - Get the max valid resource index
+ * @res: pointer to the resource to find the max valid index for
+ *
+ * Start from the end of the ice_res_tracker and return right when we find the
+ * first res->list entry with the ICE_RES_VALID_BIT set. This function is only
+ * valid for SR-IOV because it is the only consumer that manipulates the
+ * res->end and this is always called when res->end is set to res->num_entries.
+ */
+static int ice_get_max_valid_res_idx(struct ice_res_tracker *res)
+{
+	int i;
+
+	if (!res)
+		return -EINVAL;
+
+	for (i = res->num_entries - 1; i >= 0; i--)
+		if (res->list[i] & ICE_RES_VALID_BIT)
+			return i;
+
+	return 0;
+}
+
+/**
+ * ice_sriov_set_msix_res - Set any used MSIX resources
+ * @pf: pointer to PF structure
+ * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs
+ *
+ * This function allows SR-IOV resources to be taken from the end of the PF's
+ * allowed HW MSIX vectors so in many cases the irq_tracker will not
+ * be needed. In these cases we just set the pf->sriov_base_vector and return
+ * success.
+ *
+ * If SR-IOV needs to use any pf->irq_tracker entries it updates the
+ * irq_tracker->end based on the first entry needed for SR-IOV. This makes it
+ * so any calls to ice_get_res() using the irq_tracker will not try to use
+ * resources at or beyond the newly set value.
+ *
+ * Return 0 on success, and -EINVAL when there are not enough MSIX vectors in
+ * in the PF's space available for SR-IOV.
+ */
+static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
+{
+	int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker);
+	u16 pf_total_msix_vectors =
+		pf->hw.func_caps.common_cap.num_msix_vectors;
+	struct ice_res_tracker *res = pf->irq_tracker;
+	int sriov_base_vector;
+
+	if (max_valid_res_idx < 0)
+		return max_valid_res_idx;
+
+	sriov_base_vector = pf_total_msix_vectors - num_msix_needed;
+
+	/* make sure we only grab irq_tracker entries from the list end and
+	 * that we have enough available MSIX vectors
+	 */
+	if (sriov_base_vector <= max_valid_res_idx)
+		return -EINVAL;
+
+	pf->sriov_base_vector = sriov_base_vector;
+
+	/* dip into irq_tracker entries and update used resources */
+	if (num_msix_needed > (pf_total_msix_vectors - res->num_entries)) {
+		pf->num_avail_sw_msix -=
+			res->num_entries - pf->sriov_base_vector;
+		res->end = pf->sriov_base_vector;
+	}
+
+	return 0;
+}
+
+/**
  * ice_check_avail_res - check if vectors and queues are available
  * @pf: pointer to the PF structure
  *
@@ -619,11 +820,16 @@ ice_determine_res(struct ice_pf *pf, u16 avail_res, u16 max_res, u16 min_res)
  */
 static int ice_check_avail_res(struct ice_pf *pf)
 {
-	u16 num_msix, num_txq, num_rxq;
+	int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker);
+	u16 num_msix, num_txq, num_rxq, num_avail_msix;
 
-	if (!pf->num_alloc_vfs)
+	if (!pf->num_alloc_vfs || max_valid_res_idx < 0)
 		return -EINVAL;
 
+	/* add 1 to max_valid_res_idx to account for it being 0-based */
+	num_avail_msix = pf->hw.func_caps.common_cap.num_msix_vectors -
+		(max_valid_res_idx + 1);
+
 	/* Grab from HW interrupts common pool
 	 * Note: By the time the user decides it needs more vectors in a VF
 	 * its already too late since one must decide this prior to creating the
@@ -640,11 +846,11 @@ static int ice_check_avail_res(struct ice_pf *pf)
 	 * grab default interrupt vectors (5 as supported by AVF driver).
 	 */
 	if (pf->num_alloc_vfs <= 16) {
-		num_msix = ice_determine_res(pf, pf->num_avail_hw_msix,
+		num_msix = ice_determine_res(pf, num_avail_msix,
 					     ICE_MAX_INTR_PER_VF,
 					     ICE_MIN_INTR_PER_VF);
 	} else if (pf->num_alloc_vfs <= ICE_MAX_VF_COUNT) {
-		num_msix = ice_determine_res(pf, pf->num_avail_hw_msix,
+		num_msix = ice_determine_res(pf, num_avail_msix,
 					     ICE_DFLT_INTR_PER_VF,
 					     ICE_MIN_INTR_PER_VF);
 	} else {
@@ -673,6 +879,9 @@ static int ice_check_avail_res(struct ice_pf *pf)
 	if (!num_txq || !num_rxq)
 		return -EIO;
 
+	if (ice_sriov_set_msix_res(pf, num_msix * pf->num_alloc_vfs))
+		return -EINVAL;
+
 	/* since AVF driver works with only queue pairs which means, it expects
 	 * to have equal number of Rx and Tx queues, so take the minimum of
 	 * available Tx or Rx queues
@@ -733,6 +942,47 @@ static void ice_cleanup_and_realloc_vf(struct ice_vf *vf)
 }
 
 /**
+ * ice_vf_set_vsi_promisc - set given VF VSI to given promiscuous mode(s)
+ * @vf: pointer to the VF info
+ * @vsi: the VSI being configured
+ * @promisc_m: mask of promiscuous config bits
+ * @rm_promisc: promisc flag request from the VF to remove or add filter
+ *
+ * This function configures VF VSI promiscuous mode, based on the VF requests,
+ * for Unicast, Multicast and VLAN
+ */
+static enum ice_status
+ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m,
+		       bool rm_promisc)
+{
+	struct ice_pf *pf = vf->pf;
+	enum ice_status status = 0;
+	struct ice_hw *hw;
+
+	hw = &pf->hw;
+	if (vf->num_vlan) {
+		status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m,
+						  rm_promisc);
+	} else if (vf->port_vlan_id) {
+		if (rm_promisc)
+			status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m,
+						       vf->port_vlan_id);
+		else
+			status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m,
+						     vf->port_vlan_id);
+	} else {
+		if (rm_promisc)
+			status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m,
+						       0);
+		else
+			status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m,
+						     0);
+	}
+
+	return status;
+}
+
+/**
  * ice_reset_all_vfs - reset all allocated VFs in one go
  * @pf: pointer to the PF structure
  * @is_vflr: true if VFLR was issued, false if not
@@ -747,6 +997,7 @@ static void ice_cleanup_and_realloc_vf(struct ice_vf *vf)
 bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 {
 	struct ice_hw *hw = &pf->hw;
+	struct ice_vf *vf;
 	int v, i;
 
 	/* If we don't have any VFs, then there is nothing to reset */
@@ -761,12 +1012,17 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	for (v = 0; v < pf->num_alloc_vfs; v++)
 		ice_trigger_vf_reset(&pf->vf[v], is_vflr);
 
-	/* Call Disable LAN Tx queue AQ call with VFR bit set and 0
-	 * queues to inform Firmware about VF reset.
-	 */
-	for (v = 0; v < pf->num_alloc_vfs; v++)
-		ice_dis_vsi_txq(pf->vsi[0]->port_info, 0, NULL, NULL,
-				ICE_VF_RESET, v, NULL);
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		struct ice_vsi *vsi;
+
+		vf = &pf->vf[v];
+		vsi = pf->vsi[vf->lan_vsi_idx];
+		if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) {
+			ice_vsi_stop_lan_tx_rings(vsi, ICE_VF_RESET, vf->vf_id);
+			ice_vsi_stop_rx_rings(vsi);
+			clear_bit(ICE_VF_STATE_ENA, vf->vf_states);
+		}
+	}
 
 	/* HW requires some time to make sure it can flush the FIFO for a VF
 	 * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
@@ -779,9 +1035,9 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 
 		/* Check each VF in sequence */
 		while (v < pf->num_alloc_vfs) {
-			struct ice_vf *vf = &pf->vf[v];
 			u32 reg;
 
+			vf = &pf->vf[v];
 			reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id));
 			if (!(reg & VPGEN_VFRSTAT_VFRD_M))
 				break;
@@ -801,8 +1057,22 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	usleep_range(10000, 20000);
 
 	/* free VF resources to begin resetting the VSI state */
-	for (v = 0; v < pf->num_alloc_vfs; v++)
-		ice_free_vf_res(&pf->vf[v]);
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		vf = &pf->vf[v];
+
+		ice_free_vf_res(vf);
+
+		/* Free VF queues as well, and reallocate later.
+		 * If a given VF has different number of queues
+		 * configured, the request for update will come
+		 * via mailbox communication.
+		 */
+		vf->num_vf_qs = 0;
+	}
+
+	if (ice_sriov_free_msix_res(pf))
+		dev_err(&pf->pdev->dev,
+			"Failed to free MSIX resources used by SR-IOV\n");
 
 	if (ice_check_avail_res(pf)) {
 		dev_err(&pf->pdev->dev,
@@ -811,8 +1081,15 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	}
 
 	/* Finish the reset on each VF */
-	for (v = 0; v < pf->num_alloc_vfs; v++)
-		ice_cleanup_and_realloc_vf(&pf->vf[v]);
+	for (v = 0; v < pf->num_alloc_vfs; v++) {
+		vf = &pf->vf[v];
+
+		vf->num_vf_qs = pf->num_vf_qps;
+		dev_dbg(&pf->pdev->dev,
+			"VF-id %d has %d queues configured\n",
+			vf->vf_id, vf->num_vf_qs);
+		ice_cleanup_and_realloc_vf(vf);
+	}
 
 	ice_flush(hw);
 	clear_bit(__ICE_VF_DIS, pf->state);
@@ -830,8 +1107,10 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 {
 	struct ice_pf *pf = vf->pf;
-	struct ice_hw *hw = &pf->hw;
+	struct ice_vsi *vsi;
+	struct ice_hw *hw;
 	bool rsd = false;
+	u8 promisc_m;
 	u32 reg;
 	int i;
 
@@ -843,19 +1122,21 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 
 	ice_trigger_vf_reset(vf, is_vflr);
 
+	vsi = pf->vsi[vf->lan_vsi_idx];
+
 	if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) {
-		ice_vsi_stop_tx_rings(pf->vsi[vf->lan_vsi_idx], ICE_VF_RESET,
-				      vf->vf_id);
-		ice_vsi_stop_rx_rings(pf->vsi[vf->lan_vsi_idx]);
+		ice_vsi_stop_lan_tx_rings(vsi, ICE_VF_RESET, vf->vf_id);
+		ice_vsi_stop_rx_rings(vsi);
 		clear_bit(ICE_VF_STATE_ENA, vf->vf_states);
 	} else {
 		/* Call Disable LAN Tx queue AQ call even when queues are not
 		 * enabled. This is needed for successful completiom of VFR
 		 */
-		ice_dis_vsi_txq(pf->vsi[vf->lan_vsi_idx]->port_info, 0,
-				NULL, NULL, ICE_VF_RESET, vf->vf_id, NULL);
+		ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL,
+				NULL, ICE_VF_RESET, vf->vf_id, NULL);
 	}
 
+	hw = &pf->hw;
 	/* poll VPGEN_VFRSTAT reg to make sure
 	 * that reset is complete
 	 */
@@ -881,6 +1162,21 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 
 	usleep_range(10000, 20000);
 
+	/* disable promiscuous modes in case they were enabled
+	 * ignore any error if disabling process failed
+	 */
+	if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
+	    test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) {
+		if (vf->port_vlan_id ||  vf->num_vlan)
+			promisc_m = ICE_UCAST_VLAN_PROMISC_BITS;
+		else
+			promisc_m = ICE_UCAST_PROMISC_BITS;
+
+		vsi = pf->vsi[vf->lan_vsi_idx];
+		if (ice_vf_set_vsi_promisc(vf, vsi, promisc_m, true))
+			dev_err(&pf->pdev->dev, "disabling promiscuous mode failed\n");
+	}
+
 	/* free VF resources to begin resetting the VSI state */
 	ice_free_vf_res(vf);
 
@@ -919,7 +1215,7 @@ void ice_vc_notify_reset(struct ice_pf *pf)
 
 	pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING;
 	pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM;
-	ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, ICE_SUCCESS,
+	ice_vc_vf_broadcast(pf, VIRTCHNL_OP_EVENT, VIRTCHNL_STATUS_SUCCESS,
 			    (u8 *)&pfe, sizeof(struct virtchnl_pf_event));
 }
 
@@ -942,8 +1238,9 @@ static void ice_vc_notify_vf_reset(struct ice_vf *vf)
 
 	pfe.event = VIRTCHNL_EVENT_RESET_IMPENDING;
 	pfe.severity = PF_EVENT_SEVERITY_CERTAIN_DOOM;
-	ice_aq_send_msg_to_vf(&vf->pf->hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0,
-			      (u8 *)&pfe, sizeof(pfe), NULL);
+	ice_aq_send_msg_to_vf(&vf->pf->hw, vf->vf_id, VIRTCHNL_OP_EVENT,
+			      VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe, sizeof(pfe),
+			      NULL);
 }
 
 /**
@@ -958,7 +1255,7 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
 	int i, ret;
 
 	/* Disable global interrupt 0 so we don't try to handle the VFLR. */
-	wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx),
+	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
 	     ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
 
 	ice_flush(hw);
@@ -973,7 +1270,7 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
 			   GFP_KERNEL);
 	if (!vfs) {
 		ret = -ENOMEM;
-		goto err_unroll_sriov;
+		goto err_pci_disable_sriov;
 	}
 	pf->vf = vfs;
 
@@ -993,12 +1290,19 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)
 	pf->num_alloc_vfs = num_alloc_vfs;
 
 	/* VF resources get allocated during reset */
-	if (!ice_reset_all_vfs(pf, false))
+	if (!ice_reset_all_vfs(pf, true)) {
+		ret = -EIO;
 		goto err_unroll_sriov;
+	}
 
 	goto err_unroll_intr;
 
 err_unroll_sriov:
+	pf->vf = NULL;
+	devm_kfree(&pf->pdev->dev, vfs);
+	vfs = NULL;
+	pf->num_alloc_vfs = 0;
+err_pci_disable_sriov:
 	pci_disable_sriov(pf->pdev);
 err_unroll_intr:
 	/* rearm interrupts here */
@@ -1007,8 +1311,8 @@ err_unroll_intr:
 }
 
 /**
- * ice_pf_state_is_nominal - checks the pf for nominal state
- * @pf: pointer to pf to check
+ * ice_pf_state_is_nominal - checks the PF for nominal state
+ * @pf: pointer to PF to check
  *
  * Check the PF's state for a collection of bits that would indicate
  * the PF is in a state that would inhibit normal operation for
@@ -1112,21 +1416,10 @@ void ice_process_vflr_event(struct ice_pf *pf)
 	int vf_id;
 	u32 reg;
 
-	if (!test_bit(__ICE_VFLR_EVENT_PENDING, pf->state) ||
+	if (!test_and_clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state) ||
 	    !pf->num_alloc_vfs)
 		return;
 
-	/* Re-enable the VFLR interrupt cause here, before looking for which
-	 * VF got reset. Otherwise, if another VF gets a reset while the
-	 * first one is being processed, that interrupt will be lost, and
-	 * that VF will be stuck in reset forever.
-	 */
-	reg = rd32(hw, PFINT_OICR_ENA);
-	reg |= PFINT_OICR_VFLR_M;
-	wr32(hw, PFINT_OICR_ENA, reg);
-	ice_flush(hw);
-
-	clear_bit(__ICE_VFLR_EVENT_PENDING, pf->state);
 	for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) {
 		struct ice_vf *vf = &pf->vf[vf_id];
 		u32 reg_idx, bit_idx;
@@ -1163,8 +1456,9 @@ static void ice_vc_dis_vf(struct ice_vf *vf)
  *
  * send msg to VF
  */
-static int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
-				 enum ice_status v_retval, u8 *msg, u16 msglen)
+static int
+ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
+		      enum virtchnl_status_code v_retval, u8 *msg, u16 msglen)
 {
 	enum ice_status aq_ret;
 	struct ice_pf *pf;
@@ -1224,8 +1518,8 @@ static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg)
 	if (VF_IS_V10(&vf->vf_ver))
 		info.minor = VIRTCHNL_VERSION_MINOR_NO_VF_CAPS;
 
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION, ICE_SUCCESS,
-				     (u8 *)&info,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_VERSION,
+				     VIRTCHNL_STATUS_SUCCESS, (u8 *)&info,
 				     sizeof(struct virtchnl_version_info));
 }
 
@@ -1238,15 +1532,15 @@ static int ice_vc_get_ver_msg(struct ice_vf *vf, u8 *msg)
  */
 static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_vf_resource *vfres = NULL;
-	enum ice_status aq_ret = 0;
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 	int len = 0;
 	int ret;
 
 	if (!test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto err;
 	}
 
@@ -1254,7 +1548,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 
 	vfres = devm_kzalloc(&pf->pdev->dev, len, GFP_KERNEL);
 	if (!vfres) {
-		aq_ret = ICE_ERR_NO_MEMORY;
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
 		len = 0;
 		goto err;
 	}
@@ -1267,6 +1561,11 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 
 	vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2;
 	vsi = pf->vsi[vf->lan_vsi_idx];
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
 	if (!vsi->info.pvid)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN;
 
@@ -1317,7 +1616,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 
 err:
 	/* send the response back to the VF */
-	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, aq_ret,
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_VF_RESOURCES, v_ret,
 				    (u8 *)vfres, len);
 
 	devm_kfree(&pf->pdev->dev, vfres);
@@ -1340,16 +1639,16 @@ static void ice_vc_reset_vf_msg(struct ice_vf *vf)
 
 /**
  * ice_find_vsi_from_id
- * @pf: the pf structure to search for the VSI
- * @id: id of the VSI it is searching for
+ * @pf: the PF structure to search for the VSI
+ * @id: ID of the VSI it is searching for
  *
- * searches for the VSI with the given id
+ * searches for the VSI with the given ID
  */
 static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id)
 {
 	int i;
 
-	for (i = 0; i < pf->num_alloc_vsi; i++)
+	ice_for_each_vsi(pf, i)
 		if (pf->vsi[i] && pf->vsi[i]->vsi_num == id)
 			return pf->vsi[i];
 
@@ -1359,9 +1658,9 @@ static struct ice_vsi *ice_find_vsi_from_id(struct ice_pf *pf, u16 id)
 /**
  * ice_vc_isvalid_vsi_id
  * @vf: pointer to the VF info
- * @vsi_id: VF relative VSI id
+ * @vsi_id: VF relative VSI ID
  *
- * check for the valid VSI id
+ * check for the valid VSI ID
  */
 static bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
 {
@@ -1376,10 +1675,10 @@ static bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
 /**
  * ice_vc_isvalid_q_id
  * @vf: pointer to the VF info
- * @vsi_id: VSI id
- * @qid: VSI relative queue id
+ * @vsi_id: VSI ID
+ * @qid: VSI relative queue ID
  *
- * check for the valid queue id
+ * check for the valid queue ID
  */
 static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid)
 {
@@ -1397,42 +1696,42 @@ static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid)
  */
 static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_rss_key *vrk =
 		(struct virtchnl_rss_key *)msg;
+	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi = NULL;
-	enum ice_status aq_ret;
-	int ret;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!ice_vc_isvalid_vsi_id(vf, vrk->vsi_id)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	vsi = ice_find_vsi_from_id(vf->pf, vrk->vsi_id);
+	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	ret = ice_set_rss(vsi, vrk->key, NULL, 0);
-	aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS;
+	if (ice_set_rss(vsi, vrk->key, NULL, 0))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
 error_param:
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, aq_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_KEY, v_ret,
 				     NULL, 0);
 }
 
@@ -1446,40 +1745,40 @@ error_param:
 static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg)
 {
 	struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi = NULL;
-	enum ice_status aq_ret;
-	int ret;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!ice_vc_isvalid_vsi_id(vf, vrl->vsi_id)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	vsi = ice_find_vsi_from_id(vf->pf, vrl->vsi_id);
+	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	ret = ice_set_rss(vsi, NULL, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE);
-	aq_ret = ret ? ICE_ERR_PARAM : ICE_SUCCESS;
+	if (ice_set_rss(vsi, NULL, vrl->lut, ICE_VSIQF_HLUT_ARRAY_SIZE))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
 error_param:
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, aq_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_RSS_LUT, v_ret,
 				     NULL, 0);
 }
 
@@ -1492,25 +1791,26 @@ error_param:
  */
 static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_queue_select *vqs =
 		(struct virtchnl_queue_select *)msg;
-	enum ice_status aq_ret = 0;
+	struct ice_pf *pf = vf->pf;
 	struct ice_eth_stats stats;
 	struct ice_vsi *vsi;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id);
+	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
@@ -1521,7 +1821,7 @@ static int ice_vc_get_stats_msg(struct ice_vf *vf, u8 *msg)
 
 error_param:
 	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, aq_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_STATS, v_ret,
 				     (u8 *)&stats, sizeof(stats));
 }
 
@@ -1534,29 +1834,30 @@ error_param:
  */
 static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_queue_select *vqs =
 	    (struct virtchnl_queue_select *)msg;
-	enum ice_status aq_ret = 0;
+	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!vqs->rx_queues && !vqs->tx_queues) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id);
+	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
@@ -1565,15 +1866,15 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg)
 	 * programmed using ice_vsi_cfg_txqs
 	 */
 	if (ice_vsi_start_rx_rings(vsi))
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 
 	/* Set flag to indicate that queues are enabled */
-	if (!aq_ret)
+	if (v_ret == VIRTCHNL_STATUS_SUCCESS)
 		set_bit(ICE_VF_STATE_ENA, vf->vf_states);
 
 error_param:
 	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, aq_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, v_ret,
 				     NULL, 0);
 }
 
@@ -1587,54 +1888,55 @@ error_param:
  */
 static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_queue_select *vqs =
 	    (struct virtchnl_queue_select *)msg;
-	enum ice_status aq_ret = 0;
+	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) &&
 	    !test_bit(ICE_VF_STATE_ENA, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!ice_vc_isvalid_vsi_id(vf, vqs->vsi_id)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!vqs->rx_queues && !vqs->tx_queues) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	vsi = ice_find_vsi_from_id(vf->pf, vqs->vsi_id);
+	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	if (ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) {
+	if (ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) {
 		dev_err(&vsi->back->pdev->dev,
 			"Failed to stop tx rings on VSI %d\n",
 			vsi->vsi_num);
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 	}
 
 	if (ice_vsi_stop_rx_rings(vsi)) {
 		dev_err(&vsi->back->pdev->dev,
 			"Failed to stop rx rings on VSI %d\n",
 			vsi->vsi_num);
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 	}
 
 	/* Clear enabled queues flag */
-	if (!aq_ret)
+	if (v_ret == VIRTCHNL_STATUS_SUCCESS)
 		clear_bit(ICE_VF_STATE_ENA, vf->vf_states);
 
 error_param:
 	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, aq_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, v_ret,
 				     NULL, 0);
 }
 
@@ -1647,74 +1949,97 @@ error_param:
  */
 static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg)
 {
-	struct virtchnl_irq_map_info *irqmap_info =
-	    (struct virtchnl_irq_map_info *)msg;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
+	struct virtchnl_irq_map_info *irqmap_info;
 	u16 vsi_id, vsi_q_id, vector_id;
 	struct virtchnl_vector_map *map;
-	struct ice_vsi *vsi = NULL;
 	struct ice_pf *pf = vf->pf;
-	enum ice_status aq_ret = 0;
+	u16 num_q_vectors_mapped;
+	struct ice_vsi *vsi;
 	unsigned long qmap;
 	int i;
 
-	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+	irqmap_info = (struct virtchnl_irq_map_info *)msg;
+	num_q_vectors_mapped = irqmap_info->num_vectors;
+
+	vsi = pf->vsi[vf->lan_vsi_idx];
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	for (i = 0; i < irqmap_info->num_vectors; i++) {
+	/* Check to make sure number of VF vectors mapped is not greater than
+	 * number of VF vectors originally allocated, and check that
+	 * there is actually at least a single VF queue vector mapped
+	 */
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
+	    pf->num_vf_msix < num_q_vectors_mapped ||
+	    !irqmap_info->num_vectors) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
+	for (i = 0; i < num_q_vectors_mapped; i++) {
+		struct ice_q_vector *q_vector;
+
 		map = &irqmap_info->vecmap[i];
 
 		vector_id = map->vector_id;
 		vsi_id = map->vsi_id;
 		/* validate msg params */
 		if (!(vector_id < pf->hw.func_caps.common_cap
-		    .num_msix_vectors) || !ice_vc_isvalid_vsi_id(vf, vsi_id)) {
-			aq_ret = ICE_ERR_PARAM;
+		    .num_msix_vectors) || !ice_vc_isvalid_vsi_id(vf, vsi_id) ||
+		    (!vector_id && (map->rxq_map || map->txq_map))) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
 
-		vsi = ice_find_vsi_from_id(vf->pf, vsi_id);
-		if (!vsi) {
-			aq_ret = ICE_ERR_PARAM;
+		/* No need to map VF miscellaneous or rogue vector */
+		if (!vector_id)
+			continue;
+
+		/* Subtract non queue vector from vector_id passed by VF
+		 * to get actual number of VSI queue vector array index
+		 */
+		q_vector = vsi->q_vectors[vector_id - ICE_NONQ_VECS_VF];
+		if (!q_vector) {
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
 
 		/* lookout for the invalid queue index */
 		qmap = map->rxq_map;
+		q_vector->num_ring_rx = 0;
 		for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) {
-			struct ice_q_vector *q_vector;
-
 			if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) {
-				aq_ret = ICE_ERR_PARAM;
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				goto error_param;
 			}
-			q_vector = vsi->q_vectors[i];
 			q_vector->num_ring_rx++;
 			q_vector->rx.itr_idx = map->rxitr_idx;
 			vsi->rx_rings[vsi_q_id]->q_vector = q_vector;
+			ice_cfg_rxq_interrupt(vsi, vsi_q_id, vector_id,
+					      q_vector->rx.itr_idx);
 		}
 
 		qmap = map->txq_map;
+		q_vector->num_ring_tx = 0;
 		for_each_set_bit(vsi_q_id, &qmap, ICE_MAX_BASE_QS_PER_VF) {
-			struct ice_q_vector *q_vector;
-
 			if (!ice_vc_isvalid_q_id(vf, vsi_id, vsi_q_id)) {
-				aq_ret = ICE_ERR_PARAM;
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 				goto error_param;
 			}
-			q_vector = vsi->q_vectors[i];
 			q_vector->num_ring_tx++;
 			q_vector->tx.itr_idx = map->txitr_idx;
 			vsi->tx_rings[vsi_q_id]->q_vector = q_vector;
+			ice_cfg_txq_interrupt(vsi, vsi_q_id, vector_id,
+					      q_vector->tx.itr_idx);
 		}
 	}
 
-	if (vsi)
-		ice_vsi_cfg_msix(vsi);
 error_param:
 	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, aq_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_IRQ_MAP, v_ret,
 				     NULL, 0);
 }
 
@@ -1727,26 +2052,33 @@ error_param:
  */
 static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_vsi_queue_config_info *qci =
 	    (struct virtchnl_vsi_queue_config_info *)msg;
 	struct virtchnl_queue_pair_info *qpi;
-	enum ice_status aq_ret = 0;
+	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 	int i;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!ice_vc_isvalid_vsi_id(vf, qci->vsi_id)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	vsi = ice_find_vsi_from_id(vf->pf, qci->vsi_id);
-	if (!vsi) {
-		aq_ret = ICE_ERR_PARAM;
+	vsi = pf->vsi[vf->lan_vsi_idx];
+	if (!vsi)
+		goto error_param;
+
+	if (qci->num_queue_pairs > ICE_MAX_BASE_QS_PER_VF) {
+		dev_err(&pf->pdev->dev,
+			"VF-%d requesting more than supported number of queues: %d\n",
+			vf->vf_id, qci->num_queue_pairs);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
@@ -1756,7 +2088,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		    qpi->rxq.vsi_id != qci->vsi_id ||
 		    qpi->rxq.queue_id != qpi->txq.queue_id ||
 		    !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) {
-			aq_ret = ICE_ERR_PARAM;
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
 		/* copy Tx queue info from VF into VSI */
@@ -1766,13 +2098,13 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr;
 		vsi->rx_rings[i]->count = qpi->rxq.ring_len;
 		if (qpi->rxq.databuffer_size > ((16 * 1024) - 128)) {
-			aq_ret = ICE_ERR_PARAM;
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
 		vsi->rx_buf_len = qpi->rxq.databuffer_size;
 		if (qpi->rxq.max_pkt_size >= (16 * 1024) ||
 		    qpi->rxq.max_pkt_size < 64) {
-			aq_ret = ICE_ERR_PARAM;
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto error_param;
 		}
 		vsi->max_frame = qpi->rxq.max_pkt_size;
@@ -1783,15 +2115,16 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	 */
 	vsi->num_txq = qci->num_queue_pairs;
 	vsi->num_rxq = qci->num_queue_pairs;
+	/* All queues of VF VSI are in TC 0 */
+	vsi->tc_cfg.tc_info[0].qcount_tx = qci->num_queue_pairs;
+	vsi->tc_cfg.tc_info[0].qcount_rx = qci->num_queue_pairs;
 
-	if (!ice_vsi_cfg_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi))
-		aq_ret = 0;
-	else
-		aq_ret = ICE_ERR_PARAM;
+	if (ice_vsi_cfg_lan_txqs(vsi) || ice_vsi_cfg_rxqs(vsi))
+		v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR;
 
 error_param:
 	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, aq_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, v_ret,
 				     NULL, 0);
 }
 
@@ -1826,18 +2159,18 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf)
  * ice_vc_handle_mac_addr_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
- * @set: true if mac filters are being set, false otherwise
+ * @set: true if MAC filters are being set, false otherwise
  *
  * add guest MAC address filter
  */
 static int
 ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_ether_addr_list *al =
 	    (struct virtchnl_ether_addr_list *)msg;
 	struct ice_pf *pf = vf->pf;
 	enum virtchnl_ops vc_op;
-	enum ice_status ret;
 	LIST_HEAD(mac_list);
 	struct ice_vsi *vsi;
 	int mac_count = 0;
@@ -1850,19 +2183,27 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) ||
 	    !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) {
-		ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto handle_mac_exit;
 	}
 
 	if (set && !ice_is_vf_trusted(vf) &&
 	    (vf->num_mac + al->num_elements) > ICE_MAX_MACADDR_PER_VF) {
 		dev_err(&pf->pdev->dev,
-			"Can't add more MAC addresses, because VF is not trusted, switch the VF to trusted mode in order to add more functionalities\n");
-		ret = ICE_ERR_PARAM;
+			"Can't add more MAC addresses, because VF-%d is not trusted, switch the VF to trusted mode in order to add more functionalities\n",
+			vf->vf_id);
+		/* There is no need to let VF know about not being trusted
+		 * to add more MAC addr, so we can just return success message.
+		 */
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto handle_mac_exit;
 	}
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto handle_mac_exit;
+	}
 
 	for (i = 0; i < al->num_elements; i++) {
 		u8 *maddr = al->list[i].addr;
@@ -1874,40 +2215,39 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 				 * already added. Just continue.
 				 */
 				dev_info(&pf->pdev->dev,
-					 "mac %pM already set for VF %d\n",
+					 "MAC %pM already set for VF %d\n",
 					 maddr, vf->vf_id);
 				continue;
 			} else {
-				/* VF can't remove dflt_lan_addr/bcast mac */
+				/* VF can't remove dflt_lan_addr/bcast MAC */
 				dev_err(&pf->pdev->dev,
-					"can't remove mac %pM for VF %d\n",
+					"VF can't remove default MAC address or MAC %pM programmed by PF for VF %d\n",
 					maddr, vf->vf_id);
-				ret = ICE_ERR_PARAM;
-				goto handle_mac_exit;
+				continue;
 			}
 		}
 
 		/* check for the invalid cases and bail if necessary */
 		if (is_zero_ether_addr(maddr)) {
 			dev_err(&pf->pdev->dev,
-				"invalid mac %pM provided for VF %d\n",
+				"invalid MAC %pM provided for VF %d\n",
 				maddr, vf->vf_id);
-			ret = ICE_ERR_PARAM;
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto handle_mac_exit;
 		}
 
 		if (is_unicast_ether_addr(maddr) &&
 		    !ice_can_vf_change_mac(vf)) {
 			dev_err(&pf->pdev->dev,
-				"can't change unicast mac for untrusted VF %d\n",
+				"can't change unicast MAC for untrusted VF %d\n",
 				vf->vf_id);
-			ret = ICE_ERR_PARAM;
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			goto handle_mac_exit;
 		}
 
-		/* get here if maddr is multicast or if VF can change mac */
+		/* get here if maddr is multicast or if VF can change MAC */
 		if (ice_add_mac_to_list(vsi, &mac_list, al->list[i].addr)) {
-			ret = ICE_ERR_NO_MEMORY;
+			v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
 			goto handle_mac_exit;
 		}
 		mac_count++;
@@ -1915,14 +2255,14 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 
 	/* program the updated filter list */
 	if (set)
-		ret = ice_add_mac(&pf->hw, &mac_list);
+		v_ret = ice_err_to_virt_err(ice_add_mac(&pf->hw, &mac_list));
 	else
-		ret = ice_remove_mac(&pf->hw, &mac_list);
+		v_ret = ice_err_to_virt_err(ice_remove_mac(&pf->hw, &mac_list));
 
-	if (ret) {
+	if (v_ret) {
 		dev_err(&pf->pdev->dev,
-			"can't update mac filters for VF %d, error %d\n",
-			vf->vf_id, ret);
+			"can't update MAC filters for VF %d, error %d\n",
+			vf->vf_id, v_ret);
 	} else {
 		if (set)
 			vf->num_mac += mac_count;
@@ -1933,7 +2273,7 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 handle_mac_exit:
 	ice_free_fltr_list(&pf->pdev->dev, &mac_list);
 	/* send the response to the VF */
-	return ice_vc_send_msg_to_vf(vf, vc_op, ret, NULL, 0);
+	return ice_vc_send_msg_to_vf(vf, vc_op, v_ret, NULL, 0);
 }
 
 /**
@@ -1968,39 +2308,42 @@ static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg)
  * VFs get a default number of queues but can use this message to request a
  * different number. If the request is successful, PF will reset the VF and
  * return 0. If unsuccessful, PF will send message informing VF of number of
- * available queue pairs via virtchnl message response to vf.
+ * available queue pairs via virtchnl message response to VF.
  */
 static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_vf_res_request *vfres =
 		(struct virtchnl_vf_res_request *)msg;
 	int req_queues = vfres->num_queue_pairs;
-	enum ice_status aq_ret = 0;
 	struct ice_pf *pf = vf->pf;
+	int max_allowed_vf_queues;
 	int tx_rx_queue_left;
 	int cur_queues;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
-	cur_queues = pf->num_vf_qps;
+	cur_queues = vf->num_vf_qs;
 	tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx);
+	max_allowed_vf_queues = tx_rx_queue_left + cur_queues;
 	if (req_queues <= 0) {
 		dev_err(&pf->pdev->dev,
 			"VF %d tried to request %d queues. Ignoring.\n",
 			vf->vf_id, req_queues);
-	} else if (req_queues > ICE_MAX_QS_PER_VF) {
+	} else if (req_queues > ICE_MAX_BASE_QS_PER_VF) {
 		dev_err(&pf->pdev->dev,
 			"VF %d tried to request more than %d queues.\n",
-			vf->vf_id, ICE_MAX_QS_PER_VF);
-		vfres->num_queue_pairs = ICE_MAX_QS_PER_VF;
+			vf->vf_id, ICE_MAX_BASE_QS_PER_VF);
+		vfres->num_queue_pairs = ICE_MAX_BASE_QS_PER_VF;
 	} else if (req_queues - cur_queues > tx_rx_queue_left) {
 		dev_warn(&pf->pdev->dev,
 			 "VF %d requested %d more queues, but only %d left.\n",
 			 vf->vf_id, req_queues - cur_queues, tx_rx_queue_left);
-		vfres->num_queue_pairs = tx_rx_queue_left + cur_queues;
+		vfres->num_queue_pairs = min_t(int, max_allowed_vf_queues,
+					       ICE_MAX_BASE_QS_PER_VF);
 	} else {
 		/* request is successful, then reset VF */
 		vf->num_req_qs = req_queues;
@@ -2014,18 +2357,18 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 error_param:
 	/* send the response to the VF */
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_REQUEST_QUEUES,
-				     aq_ret, (u8 *)vfres, sizeof(*vfres));
+				     v_ret, (u8 *)vfres, sizeof(*vfres));
 }
 
 /**
  * ice_set_vf_port_vlan
  * @netdev: network interface device structure
  * @vf_id: VF identifier
- * @vlan_id: VLAN id being set
+ * @vlan_id: VLAN ID being set
  * @qos: priority setting
  * @vlan_proto: VLAN protocol
  *
- * program VF Port VLAN id and/or qos
+ * program VF Port VLAN ID and/or QoS
  */
 int
 ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
@@ -2068,17 +2411,18 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
 		return ret;
 	}
 
-	/* If pvid, then remove all filters on the old VLAN */
+	/* If PVID, then remove all filters on the old VLAN */
 	if (vsi->info.pvid)
 		ice_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) &
 				  VLAN_VID_MASK));
 
 	if (vlan_id || qos) {
-		ret = ice_vsi_set_pvid(vsi, vlanprio);
+		ret = ice_vsi_manage_pvid(vsi, vlanprio, true);
 		if (ret)
 			goto error_set_pvid;
 	} else {
-		ice_vsi_kill_pvid(vsi);
+		ice_vsi_manage_pvid(vsi, 0, false);
+		vsi->info.pvid = 0;
 	}
 
 	if (vlan_id) {
@@ -2106,52 +2450,60 @@ error_set_pvid:
  * @msg: pointer to the msg buffer
  * @add_v: Add VLAN if true, otherwise delete VLAN
  *
- * Process virtchnl op to add or remove programmed guest VLAN id
+ * Process virtchnl op to add or remove programmed guest VLAN ID
  */
 static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 {
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_vlan_filter_list *vfl =
 	    (struct virtchnl_vlan_filter_list *)msg;
-	enum ice_status aq_ret = 0;
 	struct ice_pf *pf = vf->pf;
+	bool vlan_promisc = false;
 	struct ice_vsi *vsi;
+	struct ice_hw *hw;
+	int status = 0;
+	u8 promisc_m;
 	int i;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (!ice_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (add_v && !ice_is_vf_trusted(vf) &&
 	    vf->num_vlan >= ICE_MAX_VLAN_PER_VF) {
 		dev_info(&pf->pdev->dev,
-			 "VF is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n");
-		aq_ret = ICE_ERR_PARAM;
+			 "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
+			 vf->vf_id);
+		/* There is no need to let VF know about being not trusted,
+		 * so we can just return success message here
+		 */
 		goto error_param;
 	}
 
 	for (i = 0; i < vfl->num_elements; i++) {
 		if (vfl->vlan_id[i] > ICE_MAX_VLANID) {
-			aq_ret = ICE_ERR_PARAM;
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 			dev_err(&pf->pdev->dev,
 				"invalid VF VLAN id %d\n", vfl->vlan_id[i]);
 			goto error_param;
 		}
 	}
 
-	vsi = ice_find_vsi_from_id(vf->pf, vfl->vsi_id);
+	hw = &pf->hw;
+	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (!vsi) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	if (vsi->info.pvid) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
@@ -2159,38 +2511,94 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 		dev_err(&pf->pdev->dev,
 			"%sable VLAN stripping failed for VSI %i\n",
 			 add_v ? "en" : "dis", vsi->vsi_num);
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
+	if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) ||
+	    test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states))
+		vlan_promisc = true;
+
 	if (add_v) {
 		for (i = 0; i < vfl->num_elements; i++) {
 			u16 vid = vfl->vlan_id[i];
 
-			if (!ice_vsi_add_vlan(vsi, vid)) {
-				vf->num_vlan++;
+			if (!ice_is_vf_trusted(vf) &&
+			    vf->num_vlan >= ICE_MAX_VLAN_PER_VF) {
+				dev_info(&pf->pdev->dev,
+					 "VF-%d is not trusted, switch the VF to trusted mode, in order to add more VLAN addresses\n",
+					 vf->vf_id);
+				/* There is no need to let VF know about being
+				 * not trusted, so we can just return success
+				 * message here as well.
+				 */
+				goto error_param;
+			}
+
+			if (ice_vsi_add_vlan(vsi, vid)) {
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
 
-				/* Enable VLAN pruning when VLAN 0 is added */
-				if (unlikely(!vid))
-					if (ice_cfg_vlan_pruning(vsi, true))
-						aq_ret = ICE_ERR_PARAM;
+			vf->num_vlan++;
+			/* Enable VLAN pruning when VLAN is added */
+			if (!vlan_promisc) {
+				status = ice_cfg_vlan_pruning(vsi, true, false);
+				if (status) {
+					v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+					dev_err(&pf->pdev->dev,
+						"Enable VLAN pruning on VLAN ID: %d failed error-%d\n",
+						vid, status);
+					goto error_param;
+				}
 			} else {
-				aq_ret = ICE_ERR_PARAM;
+				/* Enable Ucast/Mcast VLAN promiscuous mode */
+				promisc_m = ICE_PROMISC_VLAN_TX |
+					    ICE_PROMISC_VLAN_RX;
+
+				status = ice_set_vsi_promisc(hw, vsi->idx,
+							     promisc_m, vid);
+				if (status) {
+					v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+					dev_err(&pf->pdev->dev,
+						"Enable Unicast/multicast promiscuous mode on VLAN ID:%d failed error-%d\n",
+						vid, status);
+				}
 			}
 		}
 	} else {
-		for (i = 0; i < vfl->num_elements; i++) {
+		/* In case of non_trusted VF, number of VLAN elements passed
+		 * to PF for removal might be greater than number of VLANs
+		 * filter programmed for that VF - So, use actual number of
+		 * VLANS added earlier with add VLAN opcode. In order to avoid
+		 * removing VLAN that doesn't exist, which result to sending
+		 * erroneous failed message back to the VF
+		 */
+		int num_vf_vlan;
+
+		num_vf_vlan = vf->num_vlan;
+		for (i = 0; i < vfl->num_elements && i < num_vf_vlan; i++) {
 			u16 vid = vfl->vlan_id[i];
 
 			/* Make sure ice_vsi_kill_vlan is successful before
 			 * updating VLAN information
 			 */
-			if (!ice_vsi_kill_vlan(vsi, vid)) {
-				vf->num_vlan--;
+			if (ice_vsi_kill_vlan(vsi, vid)) {
+				v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+				goto error_param;
+			}
+
+			vf->num_vlan--;
+			/* Disable VLAN pruning when removing VLAN */
+			ice_cfg_vlan_pruning(vsi, false, false);
+
+			/* Disable Unicast/Multicast VLAN promiscuous mode */
+			if (vlan_promisc) {
+				promisc_m = ICE_PROMISC_VLAN_TX |
+					    ICE_PROMISC_VLAN_RX;
 
-				/* Disable VLAN pruning when removing VLAN 0 */
-				if (unlikely(!vid))
-					ice_cfg_vlan_pruning(vsi, false);
+				ice_clear_vsi_promisc(hw, vsi->idx,
+						      promisc_m, vid);
 			}
 		}
 	}
@@ -2198,10 +2606,10 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v)
 error_param:
 	/* send the response to the VF */
 	if (add_v)
-		return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, aq_ret,
+		return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, v_ret,
 					     NULL, 0);
 	else
-		return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, aq_ret,
+		return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, v_ret,
 					     NULL, 0);
 }
 
@@ -2210,7 +2618,7 @@ error_param:
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
  *
- * Add and program guest VLAN id
+ * Add and program guest VLAN ID
  */
 static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg)
 {
@@ -2222,7 +2630,7 @@ static int ice_vc_add_vlan_msg(struct ice_vf *vf, u8 *msg)
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
  *
- * remove programmed guest VLAN id
+ * remove programmed guest VLAN ID
  */
 static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg)
 {
@@ -2237,22 +2645,22 @@ static int ice_vc_remove_vlan_msg(struct ice_vf *vf, u8 *msg)
  */
 static int ice_vc_ena_vlan_stripping(struct ice_vf *vf)
 {
-	enum ice_status aq_ret = 0;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	if (ice_vsi_manage_vlan_stripping(vsi, true))
-		aq_ret = ICE_ERR_AQ_ERROR;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 
 error_param:
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING,
-				     aq_ret, NULL, 0);
+				     v_ret, NULL, 0);
 }
 
 /**
@@ -2263,22 +2671,27 @@ error_param:
  */
 static int ice_vc_dis_vlan_stripping(struct ice_vf *vf)
 {
-	enum ice_status aq_ret = 0;
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
-		aq_ret = ICE_ERR_PARAM;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto error_param;
 	}
 
 	vsi = pf->vsi[vf->lan_vsi_idx];
+	if (!vsi) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto error_param;
+	}
+
 	if (ice_vsi_manage_vlan_stripping(vsi, false))
-		aq_ret = ICE_ERR_AQ_ERROR;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 
 error_param:
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING,
-				     aq_ret, NULL, 0);
+				     v_ret, NULL, 0);
 }
 
 /**
@@ -2314,7 +2727,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event)
 	/* Perform basic checks on the msg */
 	err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen);
 	if (err) {
-		if (err == VIRTCHNL_ERR_PARAM)
+		if (err == VIRTCHNL_STATUS_ERR_PARAM)
 			err = -EPERM;
 		else
 			err = -EINVAL;
@@ -2336,7 +2749,8 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event)
 
 error_handler:
 	if (err) {
-		ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_PARAM, NULL, 0);
+		ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM,
+				      NULL, 0);
 		dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n",
 			vf_id, v_opcode, msglen, err);
 		return;
@@ -2399,7 +2813,8 @@ error_handler:
 	default:
 		dev_err(&pf->pdev->dev, "Unsupported opcode %d from VF %d\n",
 			v_opcode, vf_id);
-		err = ice_vc_send_msg_to_vf(vf, v_opcode, ICE_ERR_NOT_IMPL,
+		err = ice_vc_send_msg_to_vf(vf, v_opcode,
+					    VIRTCHNL_STATUS_ERR_NOT_SUPPORTED,
 					    NULL, 0);
 		break;
 	}
@@ -2408,7 +2823,7 @@ error_handler:
 		 * as it is busy with pending work.
 		 */
 		dev_info(&pf->pdev->dev,
-			 "PF failed to honor VF %d, opcode %d\n, error %d\n",
+			 "PF failed to honor VF %d, opcode %d, error %d\n",
 			 vf_id, v_opcode, err);
 	}
 }
@@ -2421,8 +2836,8 @@ error_handler:
  *
  * return VF configuration
  */
-int ice_get_vf_cfg(struct net_device *netdev, int vf_id,
-		   struct ifla_vf_info *ivi)
+int
+ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -2475,11 +2890,12 @@ int ice_get_vf_cfg(struct net_device *netdev, int vf_id,
 int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi_ctx ctx = { 0 };
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
+	struct ice_vsi_ctx *ctx;
+	enum ice_status status;
 	struct ice_vf *vf;
-	int status;
+	int ret = 0;
 
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
@@ -2499,34 +2915,40 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
 		return 0;
 	}
 
-	ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+	ctx = devm_kzalloc(&pf->pdev->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
 
 	if (ena) {
-		ctx.info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
-		ctx.info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M;
+		ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
+		ctx->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M;
 	}
 
-	status = ice_update_vsi(&pf->hw, vsi->idx, &ctx, NULL);
+	status = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL);
 	if (status) {
 		dev_dbg(&pf->pdev->dev,
 			"Error %d, failed to update VSI* parameters\n", status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	vf->spoofchk = ena;
-	vsi->info.sec_flags = ctx.info.sec_flags;
-	vsi->info.sw_flags2 = ctx.info.sw_flags2;
-
-	return status;
+	vsi->info.sec_flags = ctx->info.sec_flags;
+	vsi->info.sw_flags2 = ctx->info.sw_flags2;
+out:
+	devm_kfree(&pf->pdev->dev, ctx);
+	return ret;
 }
 
 /**
  * ice_set_vf_mac
  * @netdev: network interface device structure
  * @vf_id: VF identifier
- * @mac: mac address
+ * @mac: MAC address
  *
- * program VF mac address
+ * program VF MAC address
  */
 int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 {
@@ -2553,7 +2975,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		return -EINVAL;
 	}
 
-	/* copy mac into dflt_lan_addr and trigger a VF reset. The reset
+	/* copy MAC into dflt_lan_addr and trigger a VF reset. The reset
 	 * flow will use the updated dflt_lan_addr and add a MAC filter
 	 * using ice_add_mac. Also set pf_set_mac to indicate that the PF has
 	 * set the MAC address for this VF.
@@ -2561,7 +2983,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	ether_addr_copy(vf->dflt_lan_addr.addr, mac);
 	vf->pf_set_mac = true;
 	netdev_info(netdev,
-		    "mac on VF %d set to %pM\n. VF driver will be reinitialized\n",
+		    "MAC on VF %d set to %pM. VF driver will be reinitialized\n",
 		    vf_id, mac);
 
 	ice_vc_dis_vf(vf);
@@ -2664,7 +3086,8 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state)
 		ice_set_pfe_link(vf, &pfe, ls->link_speed, vf->link_up);
 
 	/* Notify the VF of its new link state */
-	ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe,
+	ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT,
+			      VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe,
 			      sizeof(pfe), NULL);
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 01470a8ee03a..c3ca522c245a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -48,37 +48,43 @@ enum ice_virtchnl_cap {
 struct ice_vf {
 	struct ice_pf *pf;
 
-	s16 vf_id;			/* VF id in the PF space */
-	u32 driver_caps;		/* reported by VF driver */
+	s16 vf_id;			/* VF ID in the PF space */
+	u16 lan_vsi_idx;		/* index into PF struct */
 	int first_vector_idx;		/* first vector index of this VF */
-	struct ice_sw *vf_sw_id;	/* switch id the VF VSIs connect to */
+	struct ice_sw *vf_sw_id;	/* switch ID the VF VSIs connect to */
 	struct virtchnl_version_info vf_ver;
+	u32 driver_caps;		/* reported by VF driver */
 	struct virtchnl_ether_addr dflt_lan_addr;
 	u16 port_vlan_id;
-	u8 pf_set_mac;			/* VF MAC address set by VMM admin */
-	u8 trusted;
-	u16 lan_vsi_idx;		/* index into PF struct */
+	u8 pf_set_mac:1;		/* VF MAC address set by VMM admin */
+	u8 trusted:1;
+	u8 spoofchk:1;
+	u8 link_forced:1;
+	u8 link_up:1;			/* only valid if VF link is forced */
+	/* VSI indices - actual VSI pointers are maintained in the PF structure
+	 * When assigned, these will be non-zero, because VSI 0 is always
+	 * the main LAN VSI for the PF.
+	 */
 	u16 lan_vsi_num;		/* ID as used by firmware */
-	u64 num_mdd_events;		/* number of mdd events detected */
+	unsigned int tx_rate;		/* Tx bandwidth limit in Mbps */
+	DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS);	/* VF runtime states */
+
+	u64 num_mdd_events;		/* number of MDD events detected */
 	u64 num_inval_msgs;		/* number of continuous invalid msgs */
 	u64 num_valid_msgs;		/* number of valid msgs detected */
-	unsigned long vf_caps;		/* vf's adv. capabilities */
-	DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS);	/* VF runtime states */
-	unsigned int tx_rate;		/* Tx bandwidth limit in Mbps */
-	u8 link_forced;
-	u8 link_up;			/* only valid if VF link is forced */
-	u8 spoofchk;
+	unsigned long vf_caps;		/* VF's adv. capabilities */
+	u8 num_req_qs;			/* num of queue pairs requested by VF */
 	u16 num_mac;
 	u16 num_vlan;
-	u8 num_req_qs;			/* num of queue pairs requested by VF */
+	u16 num_vf_qs;			/* num of queue configured per VF */
 };
 
 #ifdef CONFIG_PCI_IOV
 void ice_process_vflr_event(struct ice_pf *pf);
 int ice_sriov_configure(struct pci_dev *pdev, int num_vfs);
 int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac);
-int ice_get_vf_cfg(struct net_device *netdev, int vf_id,
-		   struct ifla_vf_info *ivi);
+int
+ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi);
 
 void ice_free_vfs(struct ice_pf *pf);
 void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event);
@@ -86,17 +92,17 @@ void ice_vc_notify_link_state(struct ice_pf *pf);
 void ice_vc_notify_reset(struct ice_pf *pf);
 bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr);
 
-int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id,
-			 u16 vlan_id, u8 qos, __be16 vlan_proto);
-
-int ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
-		  int max_tx_rate);
+int
+ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
+		     __be16 vlan_proto);
 
 int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted);
 
 int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state);
 
 int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena);
+
+int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector);
 #else /* CONFIG_PCI_IOV */
 #define ice_process_vflr_event(pf) do {} while (0)
 #define ice_free_vfs(pf) do {} while (0)
@@ -163,11 +169,10 @@ ice_set_vf_link_state(struct net_device __always_unused *netdev,
 }
 
 static inline int
-ice_set_vf_bw(struct net_device __always_unused *netdev,
-	      int __always_unused vf_id, int __always_unused min_tx_rate,
-	      int __always_unused max_tx_rate)
+ice_calc_vf_reg_idx(struct ice_vf __always_unused *vf,
+		    struct ice_q_vector __always_unused *q_vector)
 {
-	return -EOPNOTSUPP;
+	return 0;
 }
 #endif /* CONFIG_PCI_IOV */
 #endif /* _ICE_VIRTCHNL_PF_H_ */
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index bafdcf70a353..3ec2ce0725d5 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -638,7 +638,7 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw)
 			dev_spec->sgmii_active = true;
 			break;
 		}
-		/* fall through for I2C based SGMII */
+		/* fall through - for I2C based SGMII */
 	case E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES:
 		/* read media type from SFP EEPROM */
 		ret_val = igb_set_sfp_media_type_82575(hw);
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 01fcfc6f3415..d2e2c50ce257 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -194,6 +194,8 @@
 /* enable link status from external LINK_0 and LINK_1 pins */
 #define E1000_CTRL_SWDPIN0  0x00040000  /* SWDPIN 0 value */
 #define E1000_CTRL_SWDPIN1  0x00080000  /* SWDPIN 1 value */
+#define E1000_CTRL_ADVD3WUC 0x00100000  /* D3 WUC */
+#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */
 #define E1000_CTRL_SDP0_DIR 0x00400000  /* SDP0 Data direction */
 #define E1000_CTRL_SDP1_DIR 0x00800000  /* SDP1 Data direction */
 #define E1000_CTRL_RST      0x04000000  /* Global reset */
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 0ad737d2f289..9cb49980ec2d 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -409,6 +409,8 @@ do { \
 #define E1000_I210_TQAVCC(_n)	(0x3004 + ((_n) * 0x40))
 #define E1000_I210_TQAVHC(_n)	(0x300C + ((_n) * 0x40))
 
+#define E1000_I210_RR2DCDELAY	0x5BF4
+
 #define E1000_INVM_DATA_REG(_n)	(0x12120 + 4*(_n))
 #define E1000_INVM_SIZE		64 /* Number of INVM Data Registers */
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index c57671068245..3182b059bf55 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -448,7 +448,7 @@ static void igb_set_msglevel(struct net_device *netdev, u32 data)
 
 static int igb_get_regs_len(struct net_device *netdev)
 {
-#define IGB_REGS_LEN 739
+#define IGB_REGS_LEN 740
 	return IGB_REGS_LEN * sizeof(u32);
 }
 
@@ -675,41 +675,44 @@ static void igb_get_regs(struct net_device *netdev,
 		regs_buff[554] = adapter->stats.b2ogprc;
 	}
 
-	if (hw->mac.type != e1000_82576)
-		return;
-	for (i = 0; i < 12; i++)
-		regs_buff[555 + i] = rd32(E1000_SRRCTL(i + 4));
-	for (i = 0; i < 4; i++)
-		regs_buff[567 + i] = rd32(E1000_PSRTYPE(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[571 + i] = rd32(E1000_RDBAL(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[583 + i] = rd32(E1000_RDBAH(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[595 + i] = rd32(E1000_RDLEN(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[607 + i] = rd32(E1000_RDH(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[619 + i] = rd32(E1000_RDT(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[631 + i] = rd32(E1000_RXDCTL(i + 4));
-
-	for (i = 0; i < 12; i++)
-		regs_buff[643 + i] = rd32(E1000_TDBAL(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[655 + i] = rd32(E1000_TDBAH(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[667 + i] = rd32(E1000_TDLEN(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[679 + i] = rd32(E1000_TDH(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[691 + i] = rd32(E1000_TDT(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[703 + i] = rd32(E1000_TXDCTL(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[715 + i] = rd32(E1000_TDWBAL(i + 4));
-	for (i = 0; i < 12; i++)
-		regs_buff[727 + i] = rd32(E1000_TDWBAH(i + 4));
+	if (hw->mac.type == e1000_82576) {
+		for (i = 0; i < 12; i++)
+			regs_buff[555 + i] = rd32(E1000_SRRCTL(i + 4));
+		for (i = 0; i < 4; i++)
+			regs_buff[567 + i] = rd32(E1000_PSRTYPE(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[571 + i] = rd32(E1000_RDBAL(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[583 + i] = rd32(E1000_RDBAH(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[595 + i] = rd32(E1000_RDLEN(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[607 + i] = rd32(E1000_RDH(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[619 + i] = rd32(E1000_RDT(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[631 + i] = rd32(E1000_RXDCTL(i + 4));
+
+		for (i = 0; i < 12; i++)
+			regs_buff[643 + i] = rd32(E1000_TDBAL(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[655 + i] = rd32(E1000_TDBAH(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[667 + i] = rd32(E1000_TDLEN(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[679 + i] = rd32(E1000_TDH(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[691 + i] = rd32(E1000_TDT(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[703 + i] = rd32(E1000_TXDCTL(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[715 + i] = rd32(E1000_TDWBAL(i + 4));
+		for (i = 0; i < 12; i++)
+			regs_buff[727 + i] = rd32(E1000_TDWBAH(i + 4));
+	}
+
+	if (hw->mac.type == e1000_i210 || hw->mac.type == e1000_i211)
+		regs_buff[739] = rd32(E1000_I210_RR2DCDELAY);
 }
 
 static int igb_get_eeprom_len(struct net_device *netdev)
@@ -3158,8 +3161,8 @@ static int igb_set_eee(struct net_device *netdev,
 	} else if (!edata->eee_enabled) {
 		dev_err(&adapter->pdev->dev,
 			"Setting EEE options are not supported with EEE disabled\n");
-			return -EINVAL;
-		}
+		return -EINVAL;
+	}
 
 	adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised);
 	if (hw->dev_spec._82575.eee_disable != !edata->eee_enabled) {
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 7137e7f9c7f3..b4df3e319467 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -39,7 +39,7 @@
 #include "igb.h"
 
 #define MAJ 5
-#define MIN 4
+#define MIN 6
 #define BUILD 0
 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
 __stringify(BUILD) "-k"
@@ -753,6 +753,7 @@ u32 igb_rd32(struct e1000_hw *hw, u32 reg)
 		struct net_device *netdev = igb->netdev;
 		hw->hw_addr = NULL;
 		netdev_err(netdev, "PCIe link lost\n");
+		WARN(1, "igb: Failed to read reg 0x%x!\n", reg);
 	}
 
 	return value;
@@ -1189,15 +1190,15 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 {
 	struct igb_q_vector *q_vector;
 	struct igb_ring *ring;
-	int ring_count, size;
+	int ring_count;
+	size_t size;
 
 	/* igb only supports 1 Tx and/or 1 Rx queue per vector */
 	if (txr_count > 1 || rxr_count > 1)
 		return -ENOMEM;
 
 	ring_count = txr_count + rxr_count;
-	size = sizeof(struct igb_q_vector) +
-	       (sizeof(struct igb_ring) * ring_count);
+	size = struct_size(q_vector, ring, ring_count);
 
 	/* allocate q_vector and rings */
 	q_vector = adapter->q_vector[v_idx];
@@ -2480,13 +2481,14 @@ static int igb_set_features(struct net_device *netdev,
 	else
 		igb_reset(adapter);
 
-	return 0;
+	return 1;
 }
 
 static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			   struct net_device *dev,
 			   const unsigned char *addr, u16 vid,
-			   u16 flags)
+			   u16 flags,
+			   struct netlink_ext_ack *extack)
 {
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
@@ -2576,13 +2578,15 @@ static int igb_offload_cbs(struct igb_adapter *adapter,
 #define VLAN_PRIO_FULL_MASK (0x07)
 
 static int igb_parse_cls_flower(struct igb_adapter *adapter,
-				struct tc_cls_flower_offload *f,
+				struct flow_cls_offload *f,
 				int traffic_class,
 				struct igb_nfc_filter *input)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	struct netlink_ext_ack *extack = f->common.extack;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -2592,78 +2596,60 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
-		if (!is_zero_ether_addr(mask->dst)) {
-			if (!is_broadcast_ether_addr(mask->dst)) {
+		flow_rule_match_eth_addrs(rule, &match);
+		if (!is_zero_ether_addr(match.mask->dst)) {
+			if (!is_broadcast_ether_addr(match.mask->dst)) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |=
 				IGB_FILTER_FLAG_DST_MAC_ADDR;
-			ether_addr_copy(input->filter.dst_addr, key->dst);
+			ether_addr_copy(input->filter.dst_addr, match.key->dst);
 		}
 
-		if (!is_zero_ether_addr(mask->src)) {
-			if (!is_broadcast_ether_addr(mask->src)) {
+		if (!is_zero_ether_addr(match.mask->src)) {
+			if (!is_broadcast_ether_addr(match.mask->src)) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |=
 				IGB_FILTER_FLAG_SRC_MAC_ADDR;
-			ether_addr_copy(input->filter.src_addr, key->src);
+			ether_addr_copy(input->filter.src_addr, match.key->src);
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key, *mask;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_BASIC,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_BASIC,
-						 f->mask);
-
-		if (mask->n_proto) {
-			if (mask->n_proto != ETHER_TYPE_FULL_MASK) {
+		flow_rule_match_basic(rule, &match);
+		if (match.mask->n_proto) {
+			if (match.mask->n_proto != ETHER_TYPE_FULL_MASK) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE;
-			input->filter.etype = key->n_proto;
+			input->filter.etype = match.key->n_proto;
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_VLAN,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_VLAN,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
-		if (mask->vlan_priority) {
-			if (mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_priority) {
+			if (match.mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI;
-			input->filter.vlan_tci = key->vlan_priority;
+			input->filter.vlan_tci = match.key->vlan_priority;
 		}
 	}
 
@@ -2674,7 +2660,7 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 }
 
 static int igb_configure_clsflower(struct igb_adapter *adapter,
-				   struct tc_cls_flower_offload *cls_flower)
+				   struct flow_cls_offload *cls_flower)
 {
 	struct netlink_ext_ack *extack = cls_flower->common.extack;
 	struct igb_nfc_filter *filter, *f;
@@ -2736,7 +2722,7 @@ err_parse:
 }
 
 static int igb_delete_clsflower(struct igb_adapter *adapter,
-				struct tc_cls_flower_offload *cls_flower)
+				struct flow_cls_offload *cls_flower)
 {
 	struct igb_nfc_filter *filter;
 	int err;
@@ -2766,14 +2752,14 @@ out:
 }
 
 static int igb_setup_tc_cls_flower(struct igb_adapter *adapter,
-				   struct tc_cls_flower_offload *cls_flower)
+				   struct flow_cls_offload *cls_flower)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return igb_configure_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return igb_delete_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return -EOPNOTSUPP;
 	default:
 		return -EOPNOTSUPP;
@@ -2797,25 +2783,6 @@ static int igb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int igb_setup_tc_block(struct igb_adapter *adapter,
-			      struct tc_block_offload *f)
-{
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
-					     adapter, adapter, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
-					adapter);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int igb_offload_txtime(struct igb_adapter *adapter,
 			      struct tc_etf_qopt_offload *qopt)
 {
@@ -2839,6 +2806,8 @@ static int igb_offload_txtime(struct igb_adapter *adapter,
 	return 0;
 }
 
+static LIST_HEAD(igb_block_cb_list);
+
 static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			void *type_data)
 {
@@ -2848,7 +2817,11 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	case TC_SETUP_QDISC_CBS:
 		return igb_offload_cbs(adapter, type_data);
 	case TC_SETUP_BLOCK:
-		return igb_setup_tc_block(adapter, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &igb_block_cb_list,
+						  igb_setup_tc_block_cb,
+						  adapter, adapter, true);
+
 	case TC_SETUP_QDISC_ETF:
 		return igb_offload_txtime(adapter, type_data);
 
@@ -3467,6 +3440,9 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			break;
 		}
 	}
+
+	dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP);
+
 	pm_runtime_put_noidle(&pdev->dev);
 	return 0;
 
@@ -5699,6 +5675,7 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
 	 */
 	if (tx_ring->launchtime_enable) {
 		ts = ns_to_timespec64(first->skb->tstamp);
+		first->skb->tstamp = 0;
 		context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
 	} else {
 		context_desc->seqnum_seed = 0;
@@ -6041,13 +6018,8 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 	/* Make sure there is space in the ring for the next send. */
 	igb_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 	return 0;
 
@@ -6712,7 +6684,7 @@ static int __igb_notify_dca(struct device *dev, void *data)
 			igb_setup_dca(adapter);
 			break;
 		}
-		/* Fall Through since DCA is disabled. */
+		/* Fall Through - since DCA is disabled. */
 	case DCA_PROVIDER_REMOVE:
 		if (adapter->flags & IGB_FLAG_DCA_ENABLED) {
 			/* without this a class_device is left
@@ -8063,7 +8035,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IGB_RX_HDR_LEN)
-		headlen = eth_get_headlen(va, IGB_RX_HDR_LEN);
+		headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
@@ -8755,9 +8727,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl, rctl, status;
 	u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
-#ifdef CONFIG_PM
-	int retval = 0;
-#endif
+	bool wake;
 
 	rtnl_lock();
 	netif_device_detach(netdev);
@@ -8770,14 +8740,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	igb_clear_interrupt_scheme(adapter);
 	rtnl_unlock();
 
-#ifdef CONFIG_PM
-	if (!runtime) {
-		retval = pci_save_state(pdev);
-		if (retval)
-			return retval;
-	}
-#endif
-
 	status = rd32(E1000_STATUS);
 	if (status & E1000_STATUS_LU)
 		wufc &= ~E1000_WUFC_LNKC;
@@ -8794,10 +8756,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 		}
 
 		ctrl = rd32(E1000_CTRL);
-		/* advertise wake from D3Cold */
-		#define E1000_CTRL_ADVD3WUC 0x00100000
-		/* phy power management enable */
-		#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000
 		ctrl |= E1000_CTRL_ADVD3WUC;
 		wr32(E1000_CTRL, ctrl);
 
@@ -8811,12 +8769,15 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 		wr32(E1000_WUFC, 0);
 	}
 
-	*enable_wake = wufc || adapter->en_mng_pt;
-	if (!*enable_wake)
+	wake = wufc || adapter->en_mng_pt;
+	if (!wake)
 		igb_power_down_link(adapter);
 	else
 		igb_power_up_link(adapter);
 
+	if (enable_wake)
+		*enable_wake = wake;
+
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
 	 * would have already happened in close and is redundant.
 	 */
@@ -8859,22 +8820,7 @@ static void igb_deliver_wake_packet(struct net_device *netdev)
 
 static int __maybe_unused igb_suspend(struct device *dev)
 {
-	int retval;
-	bool wake;
-	struct pci_dev *pdev = to_pci_dev(dev);
-
-	retval = __igb_shutdown(pdev, &wake, 0);
-	if (retval)
-		return retval;
-
-	if (wake) {
-		pci_prepare_to_sleep(pdev);
-	} else {
-		pci_wake_from_d3(pdev, false);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
-
-	return 0;
+	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
 }
 
 static int __maybe_unused igb_resume(struct device *dev)
@@ -8945,22 +8891,7 @@ static int __maybe_unused igb_runtime_idle(struct device *dev)
 
 static int __maybe_unused igb_runtime_suspend(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	int retval;
-	bool wake;
-
-	retval = __igb_shutdown(pdev, &wake, 1);
-	if (retval)
-		return retval;
-
-	if (wake) {
-		pci_prepare_to_sleep(pdev);
-	} else {
-		pci_wake_from_d3(pdev, false);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
-
-	return 0;
+	return __igb_shutdown(to_pci_dev(dev), NULL, 1);
 }
 
 static int __maybe_unused igb_runtime_resume(struct device *dev)
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 4eab83faec62..34cd30d7162f 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2279,10 +2279,6 @@ static inline void igbvf_tx_queue_adv(struct igbvf_adapter *adapter,
 	tx_ring->buffer_info[first].next_to_watch = tx_desc;
 	tx_ring->next_to_use = i;
 	writel(i, adapter->hw.hw_addr + tx_ring->tail);
-	/* we need this if more than one processor can write to our tail
-	 * at a time, it synchronizes IO on IA64/Altix systems
-	 */
-	mmiowb();
 }
 
 static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb,
diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile
index 4387f6ba8e67..88c6f88baac5 100644
--- a/drivers/net/ethernet/intel/igc/Makefile
+++ b/drivers/net/ethernet/intel/igc/Makefile
@@ -7,4 +7,5 @@
 
 obj-$(CONFIG_IGC) += igc.o
 
-igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o
+igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
+igc_ethtool.o
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index b1039dd3dd13..0f5534ce27b0 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -13,19 +13,56 @@
 
 #include "igc_hw.h"
 
-/* main */
+/* forward declaration */
+void igc_set_ethtool_ops(struct net_device *);
+
+struct igc_adapter;
+struct igc_ring;
+
+void igc_up(struct igc_adapter *adapter);
+void igc_down(struct igc_adapter *adapter);
+int igc_setup_tx_resources(struct igc_ring *ring);
+int igc_setup_rx_resources(struct igc_ring *ring);
+void igc_free_tx_resources(struct igc_ring *ring);
+void igc_free_rx_resources(struct igc_ring *ring);
+unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter);
+void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+			      const u32 max_rss_queues);
+int igc_reinit_queues(struct igc_adapter *adapter);
+void igc_write_rss_indir_tbl(struct igc_adapter *adapter);
+bool igc_has_link(struct igc_adapter *adapter);
+void igc_reset(struct igc_adapter *adapter);
+int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
+int igc_add_mac_steering_filter(struct igc_adapter *adapter,
+				const u8 *addr, u8 queue, u8 flags);
+int igc_del_mac_steering_filter(struct igc_adapter *adapter,
+				const u8 *addr, u8 queue, u8 flags);
+void igc_update_stats(struct igc_adapter *adapter);
+
 extern char igc_driver_name[];
 extern char igc_driver_version[];
 
+#define IGC_REGS_LEN			740
+#define IGC_RETA_SIZE			128
+
 /* Interrupt defines */
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_FLAG_HAS_MSI		BIT(0)
-#define IGC_FLAG_QUEUE_PAIRS		BIT(4)
+#define IGC_FLAG_QUEUE_PAIRS		BIT(3)
+#define IGC_FLAG_DMAC			BIT(4)
 #define IGC_FLAG_NEED_LINK_UPDATE	BIT(9)
 #define IGC_FLAG_MEDIA_RESET		BIT(10)
 #define IGC_FLAG_MAS_ENABLE		BIT(12)
 #define IGC_FLAG_HAS_MSIX		BIT(13)
 #define IGC_FLAG_VLAN_PROMISC		BIT(15)
+#define IGC_FLAG_RX_LEGACY		BIT(16)
+
+#define IGC_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
+#define IGC_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
+
+#define IGC_MRQC_ENABLE_RSS_MQ		0x00000002
+#define IGC_MRQC_RSS_FIELD_IPV4_UDP	0x00400000
+#define IGC_MRQC_RSS_FIELD_IPV6_UDP	0x00800000
 
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_4K_ITR			980
@@ -60,6 +97,7 @@ extern char igc_driver_version[];
 #define IGC_RXBUFFER_2048		2048
 #define IGC_RXBUFFER_3072		3072
 
+#define AUTO_ALL_MODES		0
 #define IGC_RX_HDR_LEN			IGC_RXBUFFER_256
 
 /* RX and TX descriptor control thresholds.
@@ -259,15 +297,50 @@ struct igc_q_vector {
 	struct igc_ring ring[0] ____cacheline_internodealigned_in_smp;
 };
 
+#define MAX_ETYPE_FILTER		(4 - 1)
+
+enum igc_filter_match_flags {
+	IGC_FILTER_FLAG_ETHER_TYPE =	0x1,
+	IGC_FILTER_FLAG_VLAN_TCI   =	0x2,
+	IGC_FILTER_FLAG_SRC_MAC_ADDR =	0x4,
+	IGC_FILTER_FLAG_DST_MAC_ADDR =	0x8,
+};
+
+/* RX network flow classification data structure */
+struct igc_nfc_input {
+	/* Byte layout in order, all values with MSB first:
+	 * match_flags - 1 byte
+	 * etype - 2 bytes
+	 * vlan_tci - 2 bytes
+	 */
+	u8 match_flags;
+	__be16 etype;
+	__be16 vlan_tci;
+	u8 src_addr[ETH_ALEN];
+	u8 dst_addr[ETH_ALEN];
+};
+
+struct igc_nfc_filter {
+	struct hlist_node nfc_node;
+	struct igc_nfc_input filter;
+	unsigned long cookie;
+	u16 etype_reg_index;
+	u16 sw_idx;
+	u16 action;
+};
+
 struct igc_mac_addr {
 	u8 addr[ETH_ALEN];
 	u8 queue;
 	u8 state; /* bitmask */
 };
 
-#define IGC_MAC_STATE_DEFAULT	0x1
-#define IGC_MAC_STATE_MODIFIED	0x2
-#define IGC_MAC_STATE_IN_USE	0x4
+#define IGC_MAC_STATE_DEFAULT		0x1
+#define IGC_MAC_STATE_IN_USE		0x2
+#define IGC_MAC_STATE_SRC_ADDR		0x4
+#define IGC_MAC_STATE_QUEUE_STEERING	0x8
+
+#define IGC_MAX_RXNFC_FILTERS		16
 
 /* Board specific private data structure */
 struct igc_adapter {
@@ -331,15 +404,27 @@ struct igc_adapter {
 	u16 tx_ring_count;
 	u16 rx_ring_count;
 
+	u32 tx_hwtstamp_timeouts;
+	u32 tx_hwtstamp_skipped;
+	u32 rx_hwtstamp_cleared;
 	u32 *shadow_vfta;
 
 	u32 rss_queues;
+	u32 rss_indir_tbl_init;
+
+	/* RX network flow classification support */
+	struct hlist_head nfc_filter_list;
+	struct hlist_head cls_flower_list;
+	unsigned int nfc_filter_count;
 
 	/* lock for RX network flow classification filter */
 	spinlock_t nfc_lock;
+	bool etype_bitmap[MAX_ETYPE_FILTER];
 
 	struct igc_mac_addr *mac_table;
 
+	u8 rss_indir_tbl[IGC_RETA_SIZE];
+
 	unsigned long link_check_timeout;
 	struct igc_info ei;
 };
@@ -418,6 +503,13 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data)
 	return 0;
 }
 
+/* forward declaration */
+void igc_reinit_locked(struct igc_adapter *);
+int igc_add_filter(struct igc_adapter *adapter,
+		   struct igc_nfc_filter *input);
+int igc_erase_filter(struct igc_adapter *adapter,
+		     struct igc_nfc_filter *input);
+
 #define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
 
 #define IGC_TXD_DCMD	(IGC_ADVTXD_DCMD_EOP | IGC_ADVTXD_DCMD_RS)
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index df40af759542..59258d791106 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -10,66 +10,6 @@
 #include "igc.h"
 
 /**
- * igc_set_pcie_completion_timeout - set pci-e completion timeout
- * @hw: pointer to the HW structure
- */
-static s32 igc_set_pcie_completion_timeout(struct igc_hw *hw)
-{
-	u32 gcr = rd32(IGC_GCR);
-	u16 pcie_devctl2;
-	s32 ret_val = 0;
-
-	/* only take action if timeout value is defaulted to 0 */
-	if (gcr & IGC_GCR_CMPL_TMOUT_MASK)
-		goto out;
-
-	/* if capabilities version is type 1 we can write the
-	 * timeout of 10ms to 200ms through the GCR register
-	 */
-	if (!(gcr & IGC_GCR_CAP_VER2)) {
-		gcr |= IGC_GCR_CMPL_TMOUT_10ms;
-		goto out;
-	}
-
-	/* for version 2 capabilities we need to write the config space
-	 * directly in order to set the completion timeout value for
-	 * 16ms to 55ms
-	 */
-	ret_val = igc_read_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2,
-					&pcie_devctl2);
-	if (ret_val)
-		goto out;
-
-	pcie_devctl2 |= PCIE_DEVICE_CONTROL2_16ms;
-
-	ret_val = igc_write_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2,
-					 &pcie_devctl2);
-out:
-	/* disable completion timeout resend */
-	gcr &= ~IGC_GCR_CMPL_TMOUT_RESEND;
-
-	wr32(IGC_GCR, gcr);
-
-	return ret_val;
-}
-
-/**
- * igc_check_for_link_base - Check for link
- * @hw: pointer to the HW structure
- *
- * If sgmii is enabled, then use the pcs register to determine link, otherwise
- * use the generic interface for determining link.
- */
-static s32 igc_check_for_link_base(struct igc_hw *hw)
-{
-	s32 ret_val = 0;
-
-	ret_val = igc_check_for_copper_link(hw);
-
-	return ret_val;
-}
-
-/**
  * igc_reset_hw_base - Reset hardware
  * @hw: pointer to the HW structure
  *
@@ -88,11 +28,6 @@ static s32 igc_reset_hw_base(struct igc_hw *hw)
 	if (ret_val)
 		hw_dbg("PCI-E Master disable polling has failed.\n");
 
-	/* set the completion timeout for interface */
-	ret_val = igc_set_pcie_completion_timeout(hw);
-	if (ret_val)
-		hw_dbg("PCI-E Set completion timeout has failed.\n");
-
 	hw_dbg("Masking off all interrupts\n");
 	wr32(IGC_IMC, 0xffffffff);
 
@@ -124,22 +59,6 @@ static s32 igc_reset_hw_base(struct igc_hw *hw)
 }
 
 /**
- * igc_get_phy_id_base - Retrieve PHY addr and id
- * @hw: pointer to the HW structure
- *
- * Retrieves the PHY address and ID for both PHY's which do and do not use
- * sgmi interface.
- */
-static s32 igc_get_phy_id_base(struct igc_hw *hw)
-{
-	s32  ret_val = 0;
-
-	ret_val = igc_get_phy_id(hw);
-
-	return ret_val;
-}
-
-/**
  * igc_init_nvm_params_base - Init NVM func ptrs.
  * @hw: pointer to the HW structure
  */
@@ -163,6 +82,7 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw)
 	if (size > 15)
 		size = 15;
 
+	nvm->type = igc_nvm_eeprom_spi;
 	nvm->word_size = BIT(size);
 	nvm->opcode_bits = 8;
 	nvm->delay_usec = 1;
@@ -261,11 +181,11 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 		goto out;
 	}
 
-	ret_val = igc_get_phy_id_base(hw);
+	ret_val = igc_get_phy_id(hw);
 	if (ret_val)
 		return ret_val;
 
-	igc_check_for_link_base(hw);
+	igc_check_for_copper_link(hw);
 
 	/* Verify phy id and set remaining function pointers */
 	switch (phy->id) {
@@ -350,26 +270,6 @@ static void igc_release_phy_base(struct igc_hw *hw)
 }
 
 /**
- * igc_get_link_up_info_base - Get link speed/duplex info
- * @hw: pointer to the HW structure
- * @speed: stores the current speed
- * @duplex: stores the current duplex
- *
- * This is a wrapper function, if using the serial gigabit media independent
- * interface, use PCS to retrieve the link speed and duplex information.
- * Otherwise, use the generic function to get the link speed and duplex info.
- */
-static s32 igc_get_link_up_info_base(struct igc_hw *hw, u16 *speed,
-				     u16 *duplex)
-{
-	s32 ret_val;
-
-	ret_val = igc_get_speed_and_duplex_copper(hw, speed, duplex);
-
-	return ret_val;
-}
-
-/**
  * igc_init_hw_base - Initialize hardware
  * @hw: pointer to the HW structure
  *
@@ -408,19 +308,6 @@ static s32 igc_init_hw_base(struct igc_hw *hw)
 }
 
 /**
- * igc_read_mac_addr_base - Read device MAC address
- * @hw: pointer to the HW structure
- */
-static s32 igc_read_mac_addr_base(struct igc_hw *hw)
-{
-	s32 ret_val = 0;
-
-	ret_val = igc_read_mac_addr(hw);
-
-	return ret_val;
-}
-
-/**
  * igc_power_down_phy_copper_base - Remove link during PHY power down
  * @hw: pointer to the HW structure
  *
@@ -512,10 +399,10 @@ void igc_rx_fifo_flush_base(struct igc_hw *hw)
 
 static struct igc_mac_operations igc_mac_ops_base = {
 	.init_hw		= igc_init_hw_base,
-	.check_for_link		= igc_check_for_link_base,
+	.check_for_link		= igc_check_for_copper_link,
 	.rar_set		= igc_rar_set,
-	.read_mac_addr		= igc_read_mac_addr_base,
-	.get_speed_and_duplex	= igc_get_link_up_info_base,
+	.read_mac_addr		= igc_read_mac_addr,
+	.get_speed_and_duplex	= igc_get_speed_and_duplex_copper,
 };
 
 static const struct igc_phy_operations igc_phy_ops_base = {
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index 35588fa7b8c5..58d1109d7f3f 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c)  2018 Intel Corporation */
 
-#ifndef _IGC_BASE_H
-#define _IGC_BASE_H
+#ifndef _IGC_BASE_H_
+#define _IGC_BASE_H_
 
 /* forward declaration */
 void igc_rx_fifo_flush_base(struct igc_hw *hw);
@@ -36,28 +36,6 @@ union igc_adv_tx_desc {
 
 #define IGC_RAR_ENTRIES		16
 
-struct igc_adv_data_desc {
-	__le64 buffer_addr;    /* Address of the descriptor's data buffer */
-	union {
-		u32 data;
-		struct {
-			u32 datalen:16; /* Data buffer length */
-			u32 rsvd:4;
-			u32 dtyp:4;  /* Descriptor type */
-			u32 dcmd:8;  /* Descriptor command */
-		} config;
-	} lower;
-	union {
-		u32 data;
-		struct {
-			u32 status:4;  /* Descriptor status */
-			u32 idx:4;
-			u32 popts:6;  /* Packet Options */
-			u32 paylen:18; /* Payload length */
-		} options;
-	} upper;
-};
-
 /* Receive Descriptor - Advanced */
 union igc_adv_rx_desc {
 	struct {
@@ -90,9 +68,6 @@ union igc_adv_rx_desc {
 	} wb;  /* writeback */
 };
 
-/* Adv Transmit Descriptor Config Masks */
-#define IGC_ADVTXD_PAYLEN_SHIFT	14 /* Adv desc PAYLEN shift */
-
 /* Additional Transmit Descriptor Control definitions */
 #define IGC_TXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Tx Queue */
 
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 8740754ea1fd..fc0ccfe38a20 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -4,6 +4,10 @@
 #ifndef _IGC_DEFINES_H_
 #define _IGC_DEFINES_H_
 
+/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+#define REQ_TX_DESCRIPTOR_MULTIPLE	8
+#define REQ_RX_DESCRIPTOR_MULTIPLE	8
+
 #define IGC_CTRL_EXT_DRV_LOAD	0x10000000 /* Drv loaded bit for FW */
 
 /* PCI Bus Info */
@@ -25,12 +29,6 @@
 /* Status of Master requests. */
 #define IGC_STATUS_GIO_MASTER_ENABLE	0x00080000
 
-/* PCI Express Control */
-#define IGC_GCR_CMPL_TMOUT_MASK		0x0000F000
-#define IGC_GCR_CMPL_TMOUT_10ms		0x00001000
-#define IGC_GCR_CMPL_TMOUT_RESEND	0x00010000
-#define IGC_GCR_CAP_VER2		0x00040000
-
 /* Receive Address
  * Number of high/low register pairs in the RAR. The RAR (Receive Address
  * Registers) holds the directed and multicast addresses that we monitor.
@@ -68,6 +66,9 @@
 
 #define IGC_CONNSW_AUTOSENSE_EN	0x1
 
+/* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */
+#define MAX_JUMBO_FRAME_SIZE	0x2600
+
 /* PBA constants */
 #define IGC_PBA_34K		0x0022
 
@@ -260,9 +261,6 @@
 #define IGC_TCTL_RTLC		0x01000000 /* Re-transmit on late collision */
 #define IGC_TCTL_MULR		0x10000000 /* Multiple request support */
 
-#define IGC_CT_SHIFT			4
-#define IGC_COLLISION_THRESHOLD		15
-
 /* Flow Control Constants */
 #define FLOW_CONTROL_ADDRESS_LOW	0x00C28001
 #define FLOW_CONTROL_ADDRESS_HIGH	0x00000100
@@ -306,6 +304,12 @@
 	IGC_RXDEXT_STATERR_CXE |	\
 	IGC_RXDEXT_STATERR_RXE)
 
+#define IGC_MRQC_RSS_FIELD_IPV4_TCP	0x00010000
+#define IGC_MRQC_RSS_FIELD_IPV4		0x00020000
+#define IGC_MRQC_RSS_FIELD_IPV6_TCP_EX	0x00040000
+#define IGC_MRQC_RSS_FIELD_IPV6		0x00100000
+#define IGC_MRQC_RSS_FIELD_IPV6_TCP	0x00200000
+
 /* Header split receive */
 #define IGC_RFCTL_IPV6_EX_DIS	0x00010000
 #define IGC_RFCTL_LEF		0x00040000
@@ -321,6 +325,10 @@
 #define I225_RXPBSIZE_DEFAULT	0x000000A2 /* RXPBSIZE default */
 #define I225_TXPBSIZE_DEFAULT	0x04000014 /* TXPBSIZE default */
 
+/* Receive Checksum Control */
+#define IGC_RXCSUM_CRCOFL	0x00000800   /* CRC32 offload enable */
+#define IGC_RXCSUM_PCSD		0x00002000   /* packet checksum disabled */
+
 /* GPY211 - I225 defines */
 #define GPY_MMD_MASK		0xFFFF0000
 #define GPY_MMD_SHIFT		16
@@ -384,6 +392,13 @@
 #define IGC_MDIC_ERROR		0x40000000
 #define IGC_MDIC_DEST		0x80000000
 
-#define IGC_N0_QUEUE -1
+#define IGC_N0_QUEUE		-1
+
+#define IGC_MAX_MAC_HDR_LEN	127
+#define IGC_MAX_NETWORK_HDR_LEN	511
+
+#define IGC_VLAPQF_QUEUE_SEL(_n, q_idx) ((q_idx) << ((_n) * 4))
+#define IGC_VLAPQF_P_VALID(_n)	(0x1 << (3 + (_n) * 4))
+#define IGC_VLAPQF_QUEUE_MASK	0x03
 
 #endif /* _IGC_DEFINES_H_ */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
new file mode 100644
index 000000000000..ac98f1d96892
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -0,0 +1,1863 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+/* ethtool support for igc */
+#include <linux/if_vlan.h>
+#include <linux/pm_runtime.h>
+
+#include "igc.h"
+
+/* forward declaration */
+struct igc_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int sizeof_stat;
+	int stat_offset;
+};
+
+#define IGC_STAT(_name, _stat) { \
+	.stat_string = _name, \
+	.sizeof_stat = FIELD_SIZEOF(struct igc_adapter, _stat), \
+	.stat_offset = offsetof(struct igc_adapter, _stat) \
+}
+
+static const struct igc_stats igc_gstrings_stats[] = {
+	IGC_STAT("rx_packets", stats.gprc),
+	IGC_STAT("tx_packets", stats.gptc),
+	IGC_STAT("rx_bytes", stats.gorc),
+	IGC_STAT("tx_bytes", stats.gotc),
+	IGC_STAT("rx_broadcast", stats.bprc),
+	IGC_STAT("tx_broadcast", stats.bptc),
+	IGC_STAT("rx_multicast", stats.mprc),
+	IGC_STAT("tx_multicast", stats.mptc),
+	IGC_STAT("multicast", stats.mprc),
+	IGC_STAT("collisions", stats.colc),
+	IGC_STAT("rx_crc_errors", stats.crcerrs),
+	IGC_STAT("rx_no_buffer_count", stats.rnbc),
+	IGC_STAT("rx_missed_errors", stats.mpc),
+	IGC_STAT("tx_aborted_errors", stats.ecol),
+	IGC_STAT("tx_carrier_errors", stats.tncrs),
+	IGC_STAT("tx_window_errors", stats.latecol),
+	IGC_STAT("tx_abort_late_coll", stats.latecol),
+	IGC_STAT("tx_deferred_ok", stats.dc),
+	IGC_STAT("tx_single_coll_ok", stats.scc),
+	IGC_STAT("tx_multi_coll_ok", stats.mcc),
+	IGC_STAT("tx_timeout_count", tx_timeout_count),
+	IGC_STAT("rx_long_length_errors", stats.roc),
+	IGC_STAT("rx_short_length_errors", stats.ruc),
+	IGC_STAT("rx_align_errors", stats.algnerrc),
+	IGC_STAT("tx_tcp_seg_good", stats.tsctc),
+	IGC_STAT("tx_tcp_seg_failed", stats.tsctfc),
+	IGC_STAT("rx_flow_control_xon", stats.xonrxc),
+	IGC_STAT("rx_flow_control_xoff", stats.xoffrxc),
+	IGC_STAT("tx_flow_control_xon", stats.xontxc),
+	IGC_STAT("tx_flow_control_xoff", stats.xofftxc),
+	IGC_STAT("rx_long_byte_count", stats.gorc),
+	IGC_STAT("tx_dma_out_of_sync", stats.doosync),
+	IGC_STAT("tx_smbus", stats.mgptc),
+	IGC_STAT("rx_smbus", stats.mgprc),
+	IGC_STAT("dropped_smbus", stats.mgpdc),
+	IGC_STAT("os2bmc_rx_by_bmc", stats.o2bgptc),
+	IGC_STAT("os2bmc_tx_by_bmc", stats.b2ospc),
+	IGC_STAT("os2bmc_tx_by_host", stats.o2bspc),
+	IGC_STAT("os2bmc_rx_by_host", stats.b2ogprc),
+	IGC_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
+	IGC_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped),
+	IGC_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
+};
+
+#define IGC_NETDEV_STAT(_net_stat) { \
+	.stat_string = __stringify(_net_stat), \
+	.sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \
+	.stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \
+}
+
+static const struct igc_stats igc_gstrings_net_stats[] = {
+	IGC_NETDEV_STAT(rx_errors),
+	IGC_NETDEV_STAT(tx_errors),
+	IGC_NETDEV_STAT(tx_dropped),
+	IGC_NETDEV_STAT(rx_length_errors),
+	IGC_NETDEV_STAT(rx_over_errors),
+	IGC_NETDEV_STAT(rx_frame_errors),
+	IGC_NETDEV_STAT(rx_fifo_errors),
+	IGC_NETDEV_STAT(tx_fifo_errors),
+	IGC_NETDEV_STAT(tx_heartbeat_errors)
+};
+
+enum igc_diagnostics_results {
+	TEST_REG = 0,
+	TEST_EEP,
+	TEST_IRQ,
+	TEST_LOOP,
+	TEST_LINK
+};
+
+static const char igc_gstrings_test[][ETH_GSTRING_LEN] = {
+	[TEST_REG]  = "Register test  (offline)",
+	[TEST_EEP]  = "Eeprom test    (offline)",
+	[TEST_IRQ]  = "Interrupt test (offline)",
+	[TEST_LOOP] = "Loopback test  (offline)",
+	[TEST_LINK] = "Link test   (on/offline)"
+};
+
+#define IGC_TEST_LEN (sizeof(igc_gstrings_test) / ETH_GSTRING_LEN)
+
+#define IGC_GLOBAL_STATS_LEN	\
+	(sizeof(igc_gstrings_stats) / sizeof(struct igc_stats))
+#define IGC_NETDEV_STATS_LEN	\
+	(sizeof(igc_gstrings_net_stats) / sizeof(struct igc_stats))
+#define IGC_RX_QUEUE_STATS_LEN \
+	(sizeof(struct igc_rx_queue_stats) / sizeof(u64))
+#define IGC_TX_QUEUE_STATS_LEN 3 /* packets, bytes, restart_queue */
+#define IGC_QUEUE_STATS_LEN \
+	((((struct igc_adapter *)netdev_priv(netdev))->num_rx_queues * \
+	  IGC_RX_QUEUE_STATS_LEN) + \
+	 (((struct igc_adapter *)netdev_priv(netdev))->num_tx_queues * \
+	  IGC_TX_QUEUE_STATS_LEN))
+#define IGC_STATS_LEN \
+	(IGC_GLOBAL_STATS_LEN + IGC_NETDEV_STATS_LEN + IGC_QUEUE_STATS_LEN)
+
+static const char igc_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define IGC_PRIV_FLAGS_LEGACY_RX	BIT(0)
+	"legacy-rx",
+};
+
+#define IGC_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igc_priv_flags_strings)
+
+static void igc_get_drvinfo(struct net_device *netdev,
+			    struct ethtool_drvinfo *drvinfo)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(drvinfo->driver,  igc_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, igc_driver_version, sizeof(drvinfo->version));
+
+	/* add fw_version here */
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
+
+	drvinfo->n_priv_flags = IGC_PRIV_FLAGS_STR_LEN;
+}
+
+static int igc_get_regs_len(struct net_device *netdev)
+{
+	return IGC_REGS_LEN * sizeof(u32);
+}
+
+static void igc_get_regs(struct net_device *netdev,
+			 struct ethtool_regs *regs, void *p)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 *regs_buff = p;
+	u8 i;
+
+	memset(p, 0, IGC_REGS_LEN * sizeof(u32));
+
+	regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id;
+
+	/* General Registers */
+	regs_buff[0] = rd32(IGC_CTRL);
+	regs_buff[1] = rd32(IGC_STATUS);
+	regs_buff[2] = rd32(IGC_CTRL_EXT);
+	regs_buff[3] = rd32(IGC_MDIC);
+	regs_buff[4] = rd32(IGC_CONNSW);
+
+	/* NVM Register */
+	regs_buff[5] = rd32(IGC_EECD);
+
+	/* Interrupt */
+	/* Reading EICS for EICR because they read the
+	 * same but EICS does not clear on read
+	 */
+	regs_buff[6] = rd32(IGC_EICS);
+	regs_buff[7] = rd32(IGC_EICS);
+	regs_buff[8] = rd32(IGC_EIMS);
+	regs_buff[9] = rd32(IGC_EIMC);
+	regs_buff[10] = rd32(IGC_EIAC);
+	regs_buff[11] = rd32(IGC_EIAM);
+	/* Reading ICS for ICR because they read the
+	 * same but ICS does not clear on read
+	 */
+	regs_buff[12] = rd32(IGC_ICS);
+	regs_buff[13] = rd32(IGC_ICS);
+	regs_buff[14] = rd32(IGC_IMS);
+	regs_buff[15] = rd32(IGC_IMC);
+	regs_buff[16] = rd32(IGC_IAC);
+	regs_buff[17] = rd32(IGC_IAM);
+
+	/* Flow Control */
+	regs_buff[18] = rd32(IGC_FCAL);
+	regs_buff[19] = rd32(IGC_FCAH);
+	regs_buff[20] = rd32(IGC_FCTTV);
+	regs_buff[21] = rd32(IGC_FCRTL);
+	regs_buff[22] = rd32(IGC_FCRTH);
+	regs_buff[23] = rd32(IGC_FCRTV);
+
+	/* Receive */
+	regs_buff[24] = rd32(IGC_RCTL);
+	regs_buff[25] = rd32(IGC_RXCSUM);
+	regs_buff[26] = rd32(IGC_RLPML);
+	regs_buff[27] = rd32(IGC_RFCTL);
+
+	/* Transmit */
+	regs_buff[28] = rd32(IGC_TCTL);
+	regs_buff[29] = rd32(IGC_TIPG);
+
+	/* Wake Up */
+
+	/* MAC */
+
+	/* Statistics */
+	regs_buff[30] = adapter->stats.crcerrs;
+	regs_buff[31] = adapter->stats.algnerrc;
+	regs_buff[32] = adapter->stats.symerrs;
+	regs_buff[33] = adapter->stats.rxerrc;
+	regs_buff[34] = adapter->stats.mpc;
+	regs_buff[35] = adapter->stats.scc;
+	regs_buff[36] = adapter->stats.ecol;
+	regs_buff[37] = adapter->stats.mcc;
+	regs_buff[38] = adapter->stats.latecol;
+	regs_buff[39] = adapter->stats.colc;
+	regs_buff[40] = adapter->stats.dc;
+	regs_buff[41] = adapter->stats.tncrs;
+	regs_buff[42] = adapter->stats.sec;
+	regs_buff[43] = adapter->stats.htdpmc;
+	regs_buff[44] = adapter->stats.rlec;
+	regs_buff[45] = adapter->stats.xonrxc;
+	regs_buff[46] = adapter->stats.xontxc;
+	regs_buff[47] = adapter->stats.xoffrxc;
+	regs_buff[48] = adapter->stats.xofftxc;
+	regs_buff[49] = adapter->stats.fcruc;
+	regs_buff[50] = adapter->stats.prc64;
+	regs_buff[51] = adapter->stats.prc127;
+	regs_buff[52] = adapter->stats.prc255;
+	regs_buff[53] = adapter->stats.prc511;
+	regs_buff[54] = adapter->stats.prc1023;
+	regs_buff[55] = adapter->stats.prc1522;
+	regs_buff[56] = adapter->stats.gprc;
+	regs_buff[57] = adapter->stats.bprc;
+	regs_buff[58] = adapter->stats.mprc;
+	regs_buff[59] = adapter->stats.gptc;
+	regs_buff[60] = adapter->stats.gorc;
+	regs_buff[61] = adapter->stats.gotc;
+	regs_buff[62] = adapter->stats.rnbc;
+	regs_buff[63] = adapter->stats.ruc;
+	regs_buff[64] = adapter->stats.rfc;
+	regs_buff[65] = adapter->stats.roc;
+	regs_buff[66] = adapter->stats.rjc;
+	regs_buff[67] = adapter->stats.mgprc;
+	regs_buff[68] = adapter->stats.mgpdc;
+	regs_buff[69] = adapter->stats.mgptc;
+	regs_buff[70] = adapter->stats.tor;
+	regs_buff[71] = adapter->stats.tot;
+	regs_buff[72] = adapter->stats.tpr;
+	regs_buff[73] = adapter->stats.tpt;
+	regs_buff[74] = adapter->stats.ptc64;
+	regs_buff[75] = adapter->stats.ptc127;
+	regs_buff[76] = adapter->stats.ptc255;
+	regs_buff[77] = adapter->stats.ptc511;
+	regs_buff[78] = adapter->stats.ptc1023;
+	regs_buff[79] = adapter->stats.ptc1522;
+	regs_buff[80] = adapter->stats.mptc;
+	regs_buff[81] = adapter->stats.bptc;
+	regs_buff[82] = adapter->stats.tsctc;
+	regs_buff[83] = adapter->stats.iac;
+	regs_buff[84] = adapter->stats.rpthc;
+	regs_buff[85] = adapter->stats.hgptc;
+	regs_buff[86] = adapter->stats.hgorc;
+	regs_buff[87] = adapter->stats.hgotc;
+	regs_buff[88] = adapter->stats.lenerrs;
+	regs_buff[89] = adapter->stats.scvpc;
+	regs_buff[90] = adapter->stats.hrmpc;
+
+	for (i = 0; i < 4; i++)
+		regs_buff[91 + i] = rd32(IGC_SRRCTL(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[95 + i] = rd32(IGC_PSRTYPE(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[99 + i] = rd32(IGC_RDBAL(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[103 + i] = rd32(IGC_RDBAH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[107 + i] = rd32(IGC_RDLEN(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[111 + i] = rd32(IGC_RDH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[115 + i] = rd32(IGC_RDT(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[119 + i] = rd32(IGC_RXDCTL(i));
+
+	for (i = 0; i < 10; i++)
+		regs_buff[123 + i] = rd32(IGC_EITR(i));
+	for (i = 0; i < 16; i++)
+		regs_buff[139 + i] = rd32(IGC_RAL(i));
+	for (i = 0; i < 16; i++)
+		regs_buff[145 + i] = rd32(IGC_RAH(i));
+
+	for (i = 0; i < 4; i++)
+		regs_buff[149 + i] = rd32(IGC_TDBAL(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[152 + i] = rd32(IGC_TDBAH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[156 + i] = rd32(IGC_TDLEN(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[160 + i] = rd32(IGC_TDH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[164 + i] = rd32(IGC_TDT(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[168 + i] = rd32(IGC_TXDCTL(i));
+}
+
+static u32 igc_get_msglevel(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->msg_enable;
+}
+
+static void igc_set_msglevel(struct net_device *netdev, u32 data)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	adapter->msg_enable = data;
+}
+
+static int igc_nway_reset(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	if (netif_running(netdev))
+		igc_reinit_locked(adapter);
+	return 0;
+}
+
+static u32 igc_get_link(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_mac_info *mac = &adapter->hw.mac;
+
+	/* If the link is not reported up to netdev, interrupts are disabled,
+	 * and so the physical link state may have changed since we last
+	 * looked. Set get_link_status to make sure that the true link
+	 * state is interrogated, rather than pulling a cached and possibly
+	 * stale link state from the driver.
+	 */
+	if (!netif_carrier_ok(netdev))
+		mac->get_link_status = 1;
+
+	return igc_has_link(adapter);
+}
+
+static int igc_get_eeprom_len(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->hw.nvm.word_size * 2;
+}
+
+static int igc_get_eeprom(struct net_device *netdev,
+			  struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	int first_word, last_word;
+	u16 *eeprom_buff;
+	int ret_val = 0;
+	u16 i;
+
+	if (eeprom->len == 0)
+		return -EINVAL;
+
+	eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+	first_word = eeprom->offset >> 1;
+	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+
+	eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16),
+				    GFP_KERNEL);
+	if (!eeprom_buff)
+		return -ENOMEM;
+
+	if (hw->nvm.type == igc_nvm_eeprom_spi) {
+		ret_val = hw->nvm.ops.read(hw, first_word,
+					   last_word - first_word + 1,
+					   eeprom_buff);
+	} else {
+		for (i = 0; i < last_word - first_word + 1; i++) {
+			ret_val = hw->nvm.ops.read(hw, first_word + i, 1,
+						   &eeprom_buff[i]);
+			if (ret_val)
+				break;
+		}
+	}
+
+	/* Device's eeprom is always little-endian, word addressable */
+	for (i = 0; i < last_word - first_word + 1; i++)
+		le16_to_cpus(&eeprom_buff[i]);
+
+	memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1),
+	       eeprom->len);
+	kfree(eeprom_buff);
+
+	return ret_val;
+}
+
+static int igc_set_eeprom(struct net_device *netdev,
+			  struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	int max_len, first_word, last_word, ret_val = 0;
+	u16 *eeprom_buff;
+	void *ptr;
+	u16 i;
+
+	if (eeprom->len == 0)
+		return -EOPNOTSUPP;
+
+	if (hw->mac.type >= igc_i225 &&
+	    !igc_get_flash_presence_i225(hw)) {
+		return -EOPNOTSUPP;
+	}
+
+	if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16)))
+		return -EFAULT;
+
+	max_len = hw->nvm.word_size * 2;
+
+	first_word = eeprom->offset >> 1;
+	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+	eeprom_buff = kmalloc(max_len, GFP_KERNEL);
+	if (!eeprom_buff)
+		return -ENOMEM;
+
+	ptr = (void *)eeprom_buff;
+
+	if (eeprom->offset & 1) {
+		/* need read/modify/write of first changed EEPROM word
+		 * only the second byte of the word is being modified
+		 */
+		ret_val = hw->nvm.ops.read(hw, first_word, 1,
+					    &eeprom_buff[0]);
+		ptr++;
+	}
+	if (((eeprom->offset + eeprom->len) & 1) && ret_val == 0) {
+		/* need read/modify/write of last changed EEPROM word
+		 * only the first byte of the word is being modified
+		 */
+		ret_val = hw->nvm.ops.read(hw, last_word, 1,
+				   &eeprom_buff[last_word - first_word]);
+	}
+
+	/* Device's eeprom is always little-endian, word addressable */
+	for (i = 0; i < last_word - first_word + 1; i++)
+		le16_to_cpus(&eeprom_buff[i]);
+
+	memcpy(ptr, bytes, eeprom->len);
+
+	for (i = 0; i < last_word - first_word + 1; i++)
+		eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+
+	ret_val = hw->nvm.ops.write(hw, first_word,
+				    last_word - first_word + 1, eeprom_buff);
+
+	/* Update the checksum if nvm write succeeded */
+	if (ret_val == 0)
+		hw->nvm.ops.update(hw);
+
+	/* check if need: igc_set_fw_version(adapter); */
+	kfree(eeprom_buff);
+	return ret_val;
+}
+
+static void igc_get_ringparam(struct net_device *netdev,
+			      struct ethtool_ringparam *ring)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	ring->rx_max_pending = IGC_MAX_RXD;
+	ring->tx_max_pending = IGC_MAX_TXD;
+	ring->rx_pending = adapter->rx_ring_count;
+	ring->tx_pending = adapter->tx_ring_count;
+}
+
+static int igc_set_ringparam(struct net_device *netdev,
+			     struct ethtool_ringparam *ring)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_ring *temp_ring;
+	u16 new_rx_count, new_tx_count;
+	int i, err = 0;
+
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+		return -EINVAL;
+
+	new_rx_count = min_t(u32, ring->rx_pending, IGC_MAX_RXD);
+	new_rx_count = max_t(u16, new_rx_count, IGC_MIN_RXD);
+	new_rx_count = ALIGN(new_rx_count, REQ_RX_DESCRIPTOR_MULTIPLE);
+
+	new_tx_count = min_t(u32, ring->tx_pending, IGC_MAX_TXD);
+	new_tx_count = max_t(u16, new_tx_count, IGC_MIN_TXD);
+	new_tx_count = ALIGN(new_tx_count, REQ_TX_DESCRIPTOR_MULTIPLE);
+
+	if (new_tx_count == adapter->tx_ring_count &&
+	    new_rx_count == adapter->rx_ring_count) {
+		/* nothing to do */
+		return 0;
+	}
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	if (!netif_running(adapter->netdev)) {
+		for (i = 0; i < adapter->num_tx_queues; i++)
+			adapter->tx_ring[i]->count = new_tx_count;
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			adapter->rx_ring[i]->count = new_rx_count;
+		adapter->tx_ring_count = new_tx_count;
+		adapter->rx_ring_count = new_rx_count;
+		goto clear_reset;
+	}
+
+	if (adapter->num_tx_queues > adapter->num_rx_queues)
+		temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
+					       adapter->num_tx_queues));
+	else
+		temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
+					       adapter->num_rx_queues));
+
+	if (!temp_ring) {
+		err = -ENOMEM;
+		goto clear_reset;
+	}
+
+	igc_down(adapter);
+
+	/* We can't just free everything and then setup again,
+	 * because the ISRs in MSI-X mode get passed pointers
+	 * to the Tx and Rx ring structs.
+	 */
+	if (new_tx_count != adapter->tx_ring_count) {
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			memcpy(&temp_ring[i], adapter->tx_ring[i],
+			       sizeof(struct igc_ring));
+
+			temp_ring[i].count = new_tx_count;
+			err = igc_setup_tx_resources(&temp_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					igc_free_tx_resources(&temp_ring[i]);
+				}
+				goto err_setup;
+			}
+		}
+
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			igc_free_tx_resources(adapter->tx_ring[i]);
+
+			memcpy(adapter->tx_ring[i], &temp_ring[i],
+			       sizeof(struct igc_ring));
+		}
+
+		adapter->tx_ring_count = new_tx_count;
+	}
+
+	if (new_rx_count != adapter->rx_ring_count) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			memcpy(&temp_ring[i], adapter->rx_ring[i],
+			       sizeof(struct igc_ring));
+
+			temp_ring[i].count = new_rx_count;
+			err = igc_setup_rx_resources(&temp_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					igc_free_rx_resources(&temp_ring[i]);
+				}
+				goto err_setup;
+			}
+		}
+
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			igc_free_rx_resources(adapter->rx_ring[i]);
+
+			memcpy(adapter->rx_ring[i], &temp_ring[i],
+			       sizeof(struct igc_ring));
+		}
+
+		adapter->rx_ring_count = new_rx_count;
+	}
+err_setup:
+	igc_up(adapter);
+	vfree(temp_ring);
+clear_reset:
+	clear_bit(__IGC_RESETTING, &adapter->state);
+	return err;
+}
+
+static void igc_get_pauseparam(struct net_device *netdev,
+			       struct ethtool_pauseparam *pause)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+
+	pause->autoneg =
+		(adapter->fc_autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+	if (hw->fc.current_mode == igc_fc_rx_pause) {
+		pause->rx_pause = 1;
+	} else if (hw->fc.current_mode == igc_fc_tx_pause) {
+		pause->tx_pause = 1;
+	} else if (hw->fc.current_mode == igc_fc_full) {
+		pause->rx_pause = 1;
+		pause->tx_pause = 1;
+	}
+}
+
+static int igc_set_pauseparam(struct net_device *netdev,
+			      struct ethtool_pauseparam *pause)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	int retval = 0;
+
+	adapter->fc_autoneg = pause->autoneg;
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	if (adapter->fc_autoneg == AUTONEG_ENABLE) {
+		hw->fc.requested_mode = igc_fc_default;
+		if (netif_running(adapter->netdev)) {
+			igc_down(adapter);
+			igc_up(adapter);
+		} else {
+			igc_reset(adapter);
+		}
+	} else {
+		if (pause->rx_pause && pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_full;
+		else if (pause->rx_pause && !pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_rx_pause;
+		else if (!pause->rx_pause && pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_tx_pause;
+		else if (!pause->rx_pause && !pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_none;
+
+		hw->fc.current_mode = hw->fc.requested_mode;
+
+		retval = ((hw->phy.media_type == igc_media_type_copper) ?
+			  igc_force_mac_fc(hw) : igc_setup_link(hw));
+	}
+
+	clear_bit(__IGC_RESETTING, &adapter->state);
+	return retval;
+}
+
+static void igc_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	u8 *p = data;
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_TEST:
+		memcpy(data, *igc_gstrings_test,
+		       IGC_TEST_LEN * ETH_GSTRING_LEN);
+		break;
+	case ETH_SS_STATS:
+		for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) {
+			memcpy(p, igc_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) {
+			memcpy(p, igc_gstrings_net_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			sprintf(p, "tx_queue_%u_packets", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "tx_queue_%u_bytes", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "tx_queue_%u_restart", i);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			sprintf(p, "rx_queue_%u_packets", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "rx_queue_%u_bytes", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "rx_queue_%u_drops", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "rx_queue_%u_csum_err", i);
+			p += ETH_GSTRING_LEN;
+			sprintf(p, "rx_queue_%u_alloc_failed", i);
+			p += ETH_GSTRING_LEN;
+		}
+		/* BUG_ON(p - data != IGC_STATS_LEN * ETH_GSTRING_LEN); */
+		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, igc_priv_flags_strings,
+		       IGC_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+		break;
+	}
+}
+
+static int igc_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return IGC_STATS_LEN;
+	case ETH_SS_TEST:
+		return IGC_TEST_LEN;
+	case ETH_SS_PRIV_FLAGS:
+		return IGC_PRIV_FLAGS_STR_LEN;
+	default:
+		return -ENOTSUPP;
+	}
+}
+
+static void igc_get_ethtool_stats(struct net_device *netdev,
+				  struct ethtool_stats *stats, u64 *data)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct rtnl_link_stats64 *net_stats = &adapter->stats64;
+	unsigned int start;
+	struct igc_ring *ring;
+	int i, j;
+	char *p;
+
+	spin_lock(&adapter->stats64_lock);
+	igc_update_stats(adapter);
+
+	for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) {
+		p = (char *)adapter + igc_gstrings_stats[i].stat_offset;
+		data[i] = (igc_gstrings_stats[i].sizeof_stat ==
+			sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+	}
+	for (j = 0; j < IGC_NETDEV_STATS_LEN; j++, i++) {
+		p = (char *)net_stats + igc_gstrings_net_stats[j].stat_offset;
+		data[i] = (igc_gstrings_net_stats[j].sizeof_stat ==
+			sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+	}
+	for (j = 0; j < adapter->num_tx_queues; j++) {
+		u64	restart2;
+
+		ring = adapter->tx_ring[j];
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
+			data[i]   = ring->tx_stats.packets;
+			data[i + 1] = ring->tx_stats.bytes;
+			data[i + 2] = ring->tx_stats.restart_queue;
+		} while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->tx_syncp2);
+			restart2  = ring->tx_stats.restart_queue2;
+		} while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start));
+		data[i + 2] += restart2;
+
+		i += IGC_TX_QUEUE_STATS_LEN;
+	}
+	for (j = 0; j < adapter->num_rx_queues; j++) {
+		ring = adapter->rx_ring[j];
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
+			data[i]   = ring->rx_stats.packets;
+			data[i + 1] = ring->rx_stats.bytes;
+			data[i + 2] = ring->rx_stats.drops;
+			data[i + 3] = ring->rx_stats.csum_err;
+			data[i + 4] = ring->rx_stats.alloc_failed;
+		} while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
+		i += IGC_RX_QUEUE_STATS_LEN;
+	}
+	spin_unlock(&adapter->stats64_lock);
+}
+
+static int igc_get_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	if (adapter->rx_itr_setting <= 3)
+		ec->rx_coalesce_usecs = adapter->rx_itr_setting;
+	else
+		ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2;
+
+	if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) {
+		if (adapter->tx_itr_setting <= 3)
+			ec->tx_coalesce_usecs = adapter->tx_itr_setting;
+		else
+			ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2;
+	}
+
+	return 0;
+}
+
+static int igc_set_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	int i;
+
+	if (ec->rx_max_coalesced_frames ||
+	    ec->rx_coalesce_usecs_irq ||
+	    ec->rx_max_coalesced_frames_irq ||
+	    ec->tx_max_coalesced_frames ||
+	    ec->tx_coalesce_usecs_irq ||
+	    ec->stats_block_coalesce_usecs ||
+	    ec->use_adaptive_rx_coalesce ||
+	    ec->use_adaptive_tx_coalesce ||
+	    ec->pkt_rate_low ||
+	    ec->rx_coalesce_usecs_low ||
+	    ec->rx_max_coalesced_frames_low ||
+	    ec->tx_coalesce_usecs_low ||
+	    ec->tx_max_coalesced_frames_low ||
+	    ec->pkt_rate_high ||
+	    ec->rx_coalesce_usecs_high ||
+	    ec->rx_max_coalesced_frames_high ||
+	    ec->tx_coalesce_usecs_high ||
+	    ec->tx_max_coalesced_frames_high ||
+	    ec->rate_sample_interval)
+		return -ENOTSUPP;
+
+	if (ec->rx_coalesce_usecs > IGC_MAX_ITR_USECS ||
+	    (ec->rx_coalesce_usecs > 3 &&
+	     ec->rx_coalesce_usecs < IGC_MIN_ITR_USECS) ||
+	    ec->rx_coalesce_usecs == 2)
+		return -EINVAL;
+
+	if (ec->tx_coalesce_usecs > IGC_MAX_ITR_USECS ||
+	    (ec->tx_coalesce_usecs > 3 &&
+	     ec->tx_coalesce_usecs < IGC_MIN_ITR_USECS) ||
+	    ec->tx_coalesce_usecs == 2)
+		return -EINVAL;
+
+	if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs)
+		return -EINVAL;
+
+	/* If ITR is disabled, disable DMAC */
+	if (ec->rx_coalesce_usecs == 0) {
+		if (adapter->flags & IGC_FLAG_DMAC)
+			adapter->flags &= ~IGC_FLAG_DMAC;
+	}
+
+	/* convert to rate of irq's per second */
+	if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3)
+		adapter->rx_itr_setting = ec->rx_coalesce_usecs;
+	else
+		adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2;
+
+	/* convert to rate of irq's per second */
+	if (adapter->flags & IGC_FLAG_QUEUE_PAIRS)
+		adapter->tx_itr_setting = adapter->rx_itr_setting;
+	else if (ec->tx_coalesce_usecs && ec->tx_coalesce_usecs <= 3)
+		adapter->tx_itr_setting = ec->tx_coalesce_usecs;
+	else
+		adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2;
+
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		struct igc_q_vector *q_vector = adapter->q_vector[i];
+
+		q_vector->tx.work_limit = adapter->tx_work_limit;
+		if (q_vector->rx.ring)
+			q_vector->itr_val = adapter->rx_itr_setting;
+		else
+			q_vector->itr_val = adapter->tx_itr_setting;
+		if (q_vector->itr_val && q_vector->itr_val <= 3)
+			q_vector->itr_val = IGC_START_ITR;
+		q_vector->set_itr = 1;
+	}
+
+	return 0;
+}
+
+#define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
+static int igc_get_ethtool_nfc_entry(struct igc_adapter *adapter,
+				     struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
+	struct igc_nfc_filter *rule = NULL;
+
+	/* report total rule count */
+	cmd->data = IGC_MAX_RXNFC_FILTERS;
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		if (fsp->location <= rule->sw_idx)
+			break;
+	}
+
+	if (!rule || fsp->location != rule->sw_idx)
+		return -EINVAL;
+
+	if (rule->filter.match_flags) {
+		fsp->flow_type = ETHER_FLOW;
+		fsp->ring_cookie = rule->action;
+		if (rule->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+			fsp->h_u.ether_spec.h_proto = rule->filter.etype;
+			fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK;
+		}
+		if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) {
+			fsp->flow_type |= FLOW_EXT;
+			fsp->h_ext.vlan_tci = rule->filter.vlan_tci;
+			fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK);
+		}
+		if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
+			ether_addr_copy(fsp->h_u.ether_spec.h_dest,
+					rule->filter.dst_addr);
+			/* As we only support matching by the full
+			 * mask, return the mask to userspace
+			 */
+			eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
+		}
+		if (rule->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+			ether_addr_copy(fsp->h_u.ether_spec.h_source,
+					rule->filter.src_addr);
+			/* As we only support matching by the full
+			 * mask, return the mask to userspace
+			 */
+			eth_broadcast_addr(fsp->m_u.ether_spec.h_source);
+		}
+
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int igc_get_ethtool_nfc_all(struct igc_adapter *adapter,
+				   struct ethtool_rxnfc *cmd,
+				   u32 *rule_locs)
+{
+	struct igc_nfc_filter *rule;
+	int cnt = 0;
+
+	/* report total rule count */
+	cmd->data = IGC_MAX_RXNFC_FILTERS;
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		if (cnt == cmd->rule_cnt)
+			return -EMSGSIZE;
+		rule_locs[cnt] = rule->sw_idx;
+		cnt++;
+	}
+
+	cmd->rule_cnt = cnt;
+
+	return 0;
+}
+
+static int igc_get_rss_hash_opts(struct igc_adapter *adapter,
+				 struct ethtool_rxnfc *cmd)
+{
+	cmd->data = 0;
+
+	/* Report default options for RSS on igc */
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
+	case UDP_V4_FLOW:
+		if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV4_UDP)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
+	case SCTP_V4_FLOW:
+		/* Fall through */
+	case AH_ESP_V4_FLOW:
+		/* Fall through */
+	case AH_V4_FLOW:
+		/* Fall through */
+	case ESP_V4_FLOW:
+		/* Fall through */
+	case IPV4_FLOW:
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	case TCP_V6_FLOW:
+		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
+	case UDP_V6_FLOW:
+		if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV6_UDP)
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
+	case SCTP_V6_FLOW:
+		/* Fall through */
+	case AH_ESP_V6_FLOW:
+		/* Fall through */
+	case AH_V6_FLOW:
+		/* Fall through */
+	case ESP_V6_FLOW:
+		/* Fall through */
+	case IPV6_FLOW:
+		cmd->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int igc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
+			 u32 *rule_locs)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = adapter->num_rx_queues;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = adapter->nfc_filter_count;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		ret = igc_get_ethtool_nfc_entry(adapter, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		ret = igc_get_ethtool_nfc_all(adapter, cmd, rule_locs);
+		break;
+	case ETHTOOL_GRXFH:
+		ret = igc_get_rss_hash_opts(adapter, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+#define UDP_RSS_FLAGS (IGC_FLAG_RSS_FIELD_IPV4_UDP | \
+		       IGC_FLAG_RSS_FIELD_IPV6_UDP)
+static int igc_set_rss_hash_opt(struct igc_adapter *adapter,
+				struct ethtool_rxnfc *nfc)
+{
+	u32 flags = adapter->flags;
+
+	/* RSS does not support anything other than hashing
+	 * to queues on src and dst IPs and ports
+	 */
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EINVAL;
+
+	switch (nfc->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    !(nfc->data & RXH_L4_B_0_1) ||
+		    !(nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	case UDP_V4_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			flags &= ~IGC_FLAG_RSS_FIELD_IPV4_UDP;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			flags |= IGC_FLAG_RSS_FIELD_IPV4_UDP;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case UDP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST))
+			return -EINVAL;
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			flags &= ~IGC_FLAG_RSS_FIELD_IPV6_UDP;
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			flags |= IGC_FLAG_RSS_FIELD_IPV6_UDP;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		if (!(nfc->data & RXH_IP_SRC) ||
+		    !(nfc->data & RXH_IP_DST) ||
+		    (nfc->data & RXH_L4_B_0_1) ||
+		    (nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* if we changed something we need to update flags */
+	if (flags != adapter->flags) {
+		struct igc_hw *hw = &adapter->hw;
+		u32 mrqc = rd32(IGC_MRQC);
+
+		if ((flags & UDP_RSS_FLAGS) &&
+		    !(adapter->flags & UDP_RSS_FLAGS))
+			dev_err(&adapter->pdev->dev,
+				"enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
+
+		adapter->flags = flags;
+
+		/* Perform hash on these packet types */
+		mrqc |= IGC_MRQC_RSS_FIELD_IPV4 |
+			IGC_MRQC_RSS_FIELD_IPV4_TCP |
+			IGC_MRQC_RSS_FIELD_IPV6 |
+			IGC_MRQC_RSS_FIELD_IPV6_TCP;
+
+		mrqc &= ~(IGC_MRQC_RSS_FIELD_IPV4_UDP |
+			  IGC_MRQC_RSS_FIELD_IPV6_UDP);
+
+		if (flags & IGC_FLAG_RSS_FIELD_IPV4_UDP)
+			mrqc |= IGC_MRQC_RSS_FIELD_IPV4_UDP;
+
+		if (flags & IGC_FLAG_RSS_FIELD_IPV6_UDP)
+			mrqc |= IGC_MRQC_RSS_FIELD_IPV6_UDP;
+
+		wr32(IGC_MRQC, mrqc);
+	}
+
+	return 0;
+}
+
+static int igc_rxnfc_write_etype_filter(struct igc_adapter *adapter,
+					struct igc_nfc_filter *input)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u8 i;
+	u32 etqf;
+	u16 etype;
+
+	/* find an empty etype filter register */
+	for (i = 0; i < MAX_ETYPE_FILTER; ++i) {
+		if (!adapter->etype_bitmap[i])
+			break;
+	}
+	if (i == MAX_ETYPE_FILTER) {
+		dev_err(&adapter->pdev->dev, "ethtool -N: etype filters are all used.\n");
+		return -EINVAL;
+	}
+
+	adapter->etype_bitmap[i] = true;
+
+	etqf = rd32(IGC_ETQF(i));
+	etype = ntohs(input->filter.etype & ETHER_TYPE_FULL_MASK);
+
+	etqf |= IGC_ETQF_FILTER_ENABLE;
+	etqf &= ~IGC_ETQF_ETYPE_MASK;
+	etqf |= (etype & IGC_ETQF_ETYPE_MASK);
+
+	etqf &= ~IGC_ETQF_QUEUE_MASK;
+	etqf |= ((input->action << IGC_ETQF_QUEUE_SHIFT)
+		& IGC_ETQF_QUEUE_MASK);
+	etqf |= IGC_ETQF_QUEUE_ENABLE;
+
+	wr32(IGC_ETQF(i), etqf);
+
+	input->etype_reg_index = i;
+
+	return 0;
+}
+
+static int igc_rxnfc_write_vlan_prio_filter(struct igc_adapter *adapter,
+					    struct igc_nfc_filter *input)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u8 vlan_priority;
+	u16 queue_index;
+	u32 vlapqf;
+
+	vlapqf = rd32(IGC_VLAPQF);
+	vlan_priority = (ntohs(input->filter.vlan_tci) & VLAN_PRIO_MASK)
+				>> VLAN_PRIO_SHIFT;
+	queue_index = (vlapqf >> (vlan_priority * 4)) & IGC_VLAPQF_QUEUE_MASK;
+
+	/* check whether this vlan prio is already set */
+	if (vlapqf & IGC_VLAPQF_P_VALID(vlan_priority) &&
+	    queue_index != input->action) {
+		dev_err(&adapter->pdev->dev, "ethtool rxnfc set vlan prio filter failed.\n");
+		return -EEXIST;
+	}
+
+	vlapqf |= IGC_VLAPQF_P_VALID(vlan_priority);
+	vlapqf |= IGC_VLAPQF_QUEUE_SEL(vlan_priority, input->action);
+
+	wr32(IGC_VLAPQF, vlapqf);
+
+	return 0;
+}
+
+int igc_add_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int err = -EINVAL;
+
+	if (hw->mac.type == igc_i225 &&
+	    !(input->filter.match_flags & ~IGC_FILTER_FLAG_SRC_MAC_ADDR)) {
+		dev_err(&adapter->pdev->dev,
+			"i225 doesn't support flow classification rules specifying only source addresses.\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE) {
+		err = igc_rxnfc_write_etype_filter(adapter, input);
+		if (err)
+			return err;
+	}
+
+	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) {
+		err = igc_add_mac_steering_filter(adapter,
+						  input->filter.dst_addr,
+						  input->action, 0);
+		err = min_t(int, err, 0);
+		if (err)
+			return err;
+	}
+
+	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR) {
+		err = igc_add_mac_steering_filter(adapter,
+						  input->filter.src_addr,
+						  input->action,
+						  IGC_MAC_STATE_SRC_ADDR);
+		err = min_t(int, err, 0);
+		if (err)
+			return err;
+	}
+
+	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI)
+		err = igc_rxnfc_write_vlan_prio_filter(adapter, input);
+
+	return err;
+}
+
+static void igc_clear_etype_filter_regs(struct igc_adapter *adapter,
+					u16 reg_index)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 etqf = rd32(IGC_ETQF(reg_index));
+
+	etqf &= ~IGC_ETQF_QUEUE_ENABLE;
+	etqf &= ~IGC_ETQF_QUEUE_MASK;
+	etqf &= ~IGC_ETQF_FILTER_ENABLE;
+
+	wr32(IGC_ETQF(reg_index), etqf);
+
+	adapter->etype_bitmap[reg_index] = false;
+}
+
+static void igc_clear_vlan_prio_filter(struct igc_adapter *adapter,
+				       u16 vlan_tci)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u8 vlan_priority;
+	u32 vlapqf;
+
+	vlan_priority = (vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+
+	vlapqf = rd32(IGC_VLAPQF);
+	vlapqf &= ~IGC_VLAPQF_P_VALID(vlan_priority);
+	vlapqf &= ~IGC_VLAPQF_QUEUE_SEL(vlan_priority,
+						IGC_VLAPQF_QUEUE_MASK);
+
+	wr32(IGC_VLAPQF, vlapqf);
+}
+
+int igc_erase_filter(struct igc_adapter *adapter, struct igc_nfc_filter *input)
+{
+	if (input->filter.match_flags & IGC_FILTER_FLAG_ETHER_TYPE)
+		igc_clear_etype_filter_regs(adapter,
+					    input->etype_reg_index);
+
+	if (input->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI)
+		igc_clear_vlan_prio_filter(adapter,
+					   ntohs(input->filter.vlan_tci));
+
+	if (input->filter.match_flags & IGC_FILTER_FLAG_SRC_MAC_ADDR)
+		igc_del_mac_steering_filter(adapter, input->filter.src_addr,
+					    input->action,
+					    IGC_MAC_STATE_SRC_ADDR);
+
+	if (input->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
+		igc_del_mac_steering_filter(adapter, input->filter.dst_addr,
+					    input->action, 0);
+
+	return 0;
+}
+
+static int igc_update_ethtool_nfc_entry(struct igc_adapter *adapter,
+					struct igc_nfc_filter *input,
+					u16 sw_idx)
+{
+	struct igc_nfc_filter *rule, *parent;
+	int err = -EINVAL;
+
+	parent = NULL;
+	rule = NULL;
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		/* hash found, or no matching entry */
+		if (rule->sw_idx >= sw_idx)
+			break;
+		parent = rule;
+	}
+
+	/* if there is an old rule occupying our place remove it */
+	if (rule && rule->sw_idx == sw_idx) {
+		if (!input)
+			err = igc_erase_filter(adapter, rule);
+
+		hlist_del(&rule->nfc_node);
+		kfree(rule);
+		adapter->nfc_filter_count--;
+	}
+
+	/* If no input this was a delete, err should be 0 if a rule was
+	 * successfully found and removed from the list else -EINVAL
+	 */
+	if (!input)
+		return err;
+
+	/* initialize node */
+	INIT_HLIST_NODE(&input->nfc_node);
+
+	/* add filter to the list */
+	if (parent)
+		hlist_add_behind(&input->nfc_node, &parent->nfc_node);
+	else
+		hlist_add_head(&input->nfc_node, &adapter->nfc_filter_list);
+
+	/* update counts */
+	adapter->nfc_filter_count++;
+
+	return 0;
+}
+
+static int igc_add_ethtool_nfc_entry(struct igc_adapter *adapter,
+				     struct ethtool_rxnfc *cmd)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct igc_nfc_filter *input, *rule;
+	int err = 0;
+
+	if (!(netdev->hw_features & NETIF_F_NTUPLE))
+		return -EOPNOTSUPP;
+
+	/* Don't allow programming if the action is a queue greater than
+	 * the number of online Rx queues.
+	 */
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC ||
+	    fsp->ring_cookie >= adapter->num_rx_queues) {
+		dev_err(&adapter->pdev->dev, "ethtool -N: The specified action is invalid\n");
+		return -EINVAL;
+	}
+
+	/* Don't allow indexes to exist outside of available space */
+	if (fsp->location >= IGC_MAX_RXNFC_FILTERS) {
+		dev_err(&adapter->pdev->dev, "Location out of range\n");
+		return -EINVAL;
+	}
+
+	if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW)
+		return -EINVAL;
+
+	input = kzalloc(sizeof(*input), GFP_KERNEL);
+	if (!input)
+		return -ENOMEM;
+
+	if (fsp->m_u.ether_spec.h_proto == ETHER_TYPE_FULL_MASK) {
+		input->filter.etype = fsp->h_u.ether_spec.h_proto;
+		input->filter.match_flags = IGC_FILTER_FLAG_ETHER_TYPE;
+	}
+
+	/* Only support matching addresses by the full mask */
+	if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_source)) {
+		input->filter.match_flags |= IGC_FILTER_FLAG_SRC_MAC_ADDR;
+		ether_addr_copy(input->filter.src_addr,
+				fsp->h_u.ether_spec.h_source);
+	}
+
+	/* Only support matching addresses by the full mask */
+	if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_dest)) {
+		input->filter.match_flags |= IGC_FILTER_FLAG_DST_MAC_ADDR;
+		ether_addr_copy(input->filter.dst_addr,
+				fsp->h_u.ether_spec.h_dest);
+	}
+
+	if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) {
+		if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) {
+			err = -EINVAL;
+			goto err_out;
+		}
+		input->filter.vlan_tci = fsp->h_ext.vlan_tci;
+		input->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI;
+	}
+
+	input->action = fsp->ring_cookie;
+	input->sw_idx = fsp->location;
+
+	spin_lock(&adapter->nfc_lock);
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		if (!memcmp(&input->filter, &rule->filter,
+			    sizeof(input->filter))) {
+			err = -EEXIST;
+			dev_err(&adapter->pdev->dev,
+				"ethtool: this filter is already set\n");
+			goto err_out_w_lock;
+		}
+	}
+
+	err = igc_add_filter(adapter, input);
+	if (err)
+		goto err_out_w_lock;
+
+	igc_update_ethtool_nfc_entry(adapter, input, input->sw_idx);
+
+	spin_unlock(&adapter->nfc_lock);
+	return 0;
+
+err_out_w_lock:
+	spin_unlock(&adapter->nfc_lock);
+err_out:
+	kfree(input);
+	return err;
+}
+
+static int igc_del_ethtool_nfc_entry(struct igc_adapter *adapter,
+				     struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	int err;
+
+	spin_lock(&adapter->nfc_lock);
+	err = igc_update_ethtool_nfc_entry(adapter, NULL, fsp->location);
+	spin_unlock(&adapter->nfc_lock);
+
+	return err;
+}
+
+static int igc_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = igc_set_rss_hash_opt(adapter, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLINS:
+		ret = igc_add_ethtool_nfc_entry(adapter, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = igc_del_ethtool_nfc_entry(adapter, cmd);
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+void igc_write_rss_indir_tbl(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 reg = IGC_RETA(0);
+	u32 shift = 0;
+	int i = 0;
+
+	while (i < IGC_RETA_SIZE) {
+		u32 val = 0;
+		int j;
+
+		for (j = 3; j >= 0; j--) {
+			val <<= 8;
+			val |= adapter->rss_indir_tbl[i + j];
+		}
+
+		wr32(reg, val << shift);
+		reg += 4;
+		i += 4;
+	}
+}
+
+static u32 igc_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return IGC_RETA_SIZE;
+}
+
+static int igc_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+			u8 *hfunc)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	int i;
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!indir)
+		return 0;
+	for (i = 0; i < IGC_RETA_SIZE; i++)
+		indir[i] = adapter->rss_indir_tbl[i];
+
+	return 0;
+}
+
+static int igc_set_rxfh(struct net_device *netdev, const u32 *indir,
+			const u8 *key, const u8 hfunc)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	u32 num_queues;
+	int i;
+
+	/* We do not allow change in unsupported parameters */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+	if (!indir)
+		return 0;
+
+	num_queues = adapter->rss_queues;
+
+	/* Verify user input. */
+	for (i = 0; i < IGC_RETA_SIZE; i++)
+		if (indir[i] >= num_queues)
+			return -EINVAL;
+
+	for (i = 0; i < IGC_RETA_SIZE; i++)
+		adapter->rss_indir_tbl[i] = indir[i];
+
+	igc_write_rss_indir_tbl(adapter);
+
+	return 0;
+}
+
+static unsigned int igc_max_channels(struct igc_adapter *adapter)
+{
+	return igc_get_max_rss_queues(adapter);
+}
+
+static void igc_get_channels(struct net_device *netdev,
+			     struct ethtool_channels *ch)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	/* Report maximum channels */
+	ch->max_combined = igc_max_channels(adapter);
+
+	/* Report info for other vector */
+	if (adapter->flags & IGC_FLAG_HAS_MSIX) {
+		ch->max_other = NON_Q_VECTORS;
+		ch->other_count = NON_Q_VECTORS;
+	}
+
+	ch->combined_count = adapter->rss_queues;
+}
+
+static int igc_set_channels(struct net_device *netdev,
+			    struct ethtool_channels *ch)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	unsigned int count = ch->combined_count;
+	unsigned int max_combined = 0;
+
+	/* Verify they are not requesting separate vectors */
+	if (!count || ch->rx_count || ch->tx_count)
+		return -EINVAL;
+
+	/* Verify other_count is valid and has not been changed */
+	if (ch->other_count != NON_Q_VECTORS)
+		return -EINVAL;
+
+	/* Verify the number of channels doesn't exceed hw limits */
+	max_combined = igc_max_channels(adapter);
+	if (count > max_combined)
+		return -EINVAL;
+
+	if (count != adapter->rss_queues) {
+		adapter->rss_queues = count;
+		igc_set_flag_queue_pairs(adapter, max_combined);
+
+		/* Hardware has to reinitialize queues and interrupts to
+		 * match the new configuration.
+		 */
+		return igc_reinit_queues(adapter);
+	}
+
+	return 0;
+}
+
+static u32 igc_get_priv_flags(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	u32 priv_flags = 0;
+
+	if (adapter->flags & IGC_FLAG_RX_LEGACY)
+		priv_flags |= IGC_PRIV_FLAGS_LEGACY_RX;
+
+	return priv_flags;
+}
+
+static int igc_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	unsigned int flags = adapter->flags;
+
+	flags &= ~IGC_FLAG_RX_LEGACY;
+	if (priv_flags & IGC_PRIV_FLAGS_LEGACY_RX)
+		flags |= IGC_FLAG_RX_LEGACY;
+
+	if (flags != adapter->flags) {
+		adapter->flags = flags;
+
+		/* reset interface to repopulate queues */
+		if (netif_running(netdev))
+			igc_reinit_locked(adapter);
+	}
+
+	return 0;
+}
+
+static int igc_ethtool_begin(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	pm_runtime_get_sync(&adapter->pdev->dev);
+	return 0;
+}
+
+static void igc_ethtool_complete(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	pm_runtime_put(&adapter->pdev->dev);
+}
+
+static int igc_get_link_ksettings(struct net_device *netdev,
+				  struct ethtool_link_ksettings *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 status;
+	u32 speed;
+
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+
+	/* supported link modes */
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 2500baseT_Full);
+
+	/* twisted pair */
+	cmd->base.port = PORT_TP;
+	cmd->base.phy_address = hw->phy.addr;
+
+	/* advertising link modes */
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full);
+
+	/* set autoneg settings */
+	if (hw->mac.autoneg == 1) {
+		ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Autoneg);
+	}
+
+	switch (hw->fc.requested_mode) {
+	case igc_fc_full:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+		break;
+	case igc_fc_rx_pause:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+		break;
+	case igc_fc_tx_pause:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+		break;
+	default:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+	}
+
+	status = rd32(IGC_STATUS);
+
+	if (status & IGC_STATUS_LU) {
+		if (status & IGC_STATUS_SPEED_1000) {
+			/* For I225, STATUS will indicate 1G speed in both
+			 * 1 Gbps and 2.5 Gbps link modes.
+			 * An additional bit is used
+			 * to differentiate between 1 Gbps and 2.5 Gbps.
+			 */
+			if (hw->mac.type == igc_i225 &&
+			    (status & IGC_STATUS_SPEED_2500)) {
+				speed = SPEED_2500;
+			} else {
+				speed = SPEED_1000;
+			}
+		} else if (status & IGC_STATUS_SPEED_100) {
+			speed = SPEED_100;
+		} else {
+			speed = SPEED_10;
+		}
+		if ((status & IGC_STATUS_FD) ||
+		    hw->phy.media_type != igc_media_type_copper)
+			cmd->base.duplex = DUPLEX_FULL;
+		else
+			cmd->base.duplex = DUPLEX_HALF;
+	} else {
+		speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
+	}
+	cmd->base.speed = speed;
+	if (hw->mac.autoneg)
+		cmd->base.autoneg = AUTONEG_ENABLE;
+	else
+		cmd->base.autoneg = AUTONEG_DISABLE;
+
+	/* MDI-X => 2; MDI =>1; Invalid =>0 */
+	if (hw->phy.media_type == igc_media_type_copper)
+		cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+						      ETH_TP_MDI;
+	else
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
+
+	if (hw->phy.mdix == AUTO_ALL_MODES)
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+	else
+		cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
+
+	return 0;
+}
+
+static int igc_set_link_ksettings(struct net_device *netdev,
+				  const struct ethtool_link_ksettings *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 advertising;
+
+	/* When adapter in resetting mode, autoneg/speed/duplex
+	 * cannot be changed
+	 */
+	if (igc_check_reset_block(hw)) {
+		dev_err(&adapter->pdev->dev,
+			"Cannot change link characteristics when reset is active.\n");
+		return -EINVAL;
+	}
+
+	/* MDI setting is only allowed when autoneg enabled because
+	 * some hardware doesn't allow MDI setting when speed or
+	 * duplex is forced.
+	 */
+	if (cmd->base.eth_tp_mdix_ctrl) {
+		if (cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO &&
+		    cmd->base.autoneg != AUTONEG_ENABLE) {
+			dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+			return -EINVAL;
+		}
+	}
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
+
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
+		hw->mac.autoneg = 1;
+		hw->phy.autoneg_advertised = advertising;
+		if (adapter->fc_autoneg)
+			hw->fc.requested_mode = igc_fc_default;
+	} else {
+		/* calling this overrides forced MDI setting */
+		dev_info(&adapter->pdev->dev,
+			 "Force mode currently not supported\n");
+	}
+
+	/* MDI-X => 2; MDI => 1; Auto => 3 */
+	if (cmd->base.eth_tp_mdix_ctrl) {
+		/* fix up the value for auto (3 => 0) as zero is mapped
+		 * internally to auto
+		 */
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+			hw->phy.mdix = AUTO_ALL_MODES;
+		else
+			hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
+	}
+
+	/* reset the link */
+	if (netif_running(adapter->netdev)) {
+		igc_down(adapter);
+		igc_up(adapter);
+	} else {
+		igc_reset(adapter);
+	}
+
+	clear_bit(__IGC_RESETTING, &adapter->state);
+
+	return 0;
+}
+
+static const struct ethtool_ops igc_ethtool_ops = {
+	.get_drvinfo		= igc_get_drvinfo,
+	.get_regs_len		= igc_get_regs_len,
+	.get_regs		= igc_get_regs,
+	.get_msglevel		= igc_get_msglevel,
+	.set_msglevel		= igc_set_msglevel,
+	.nway_reset		= igc_nway_reset,
+	.get_link		= igc_get_link,
+	.get_eeprom_len		= igc_get_eeprom_len,
+	.get_eeprom		= igc_get_eeprom,
+	.set_eeprom		= igc_set_eeprom,
+	.get_ringparam		= igc_get_ringparam,
+	.set_ringparam		= igc_set_ringparam,
+	.get_pauseparam		= igc_get_pauseparam,
+	.set_pauseparam		= igc_set_pauseparam,
+	.get_strings		= igc_get_strings,
+	.get_sset_count		= igc_get_sset_count,
+	.get_ethtool_stats	= igc_get_ethtool_stats,
+	.get_coalesce		= igc_get_coalesce,
+	.set_coalesce		= igc_set_coalesce,
+	.get_rxnfc		= igc_get_rxnfc,
+	.set_rxnfc		= igc_set_rxnfc,
+	.get_rxfh_indir_size	= igc_get_rxfh_indir_size,
+	.get_rxfh		= igc_get_rxfh,
+	.set_rxfh		= igc_set_rxfh,
+	.get_channels		= igc_get_channels,
+	.set_channels		= igc_set_channels,
+	.get_priv_flags		= igc_get_priv_flags,
+	.set_priv_flags		= igc_set_priv_flags,
+	.begin			= igc_ethtool_begin,
+	.complete		= igc_ethtool_complete,
+	.get_link_ksettings	= igc_get_link_ksettings,
+	.set_link_ksettings	= igc_set_link_ksettings,
+};
+
+void igc_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &igc_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index c50414f48f0d..1039a224ac80 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -55,6 +55,7 @@ enum igc_media_type {
 
 enum igc_nvm_type {
 	igc_nvm_unknown = 0,
+	igc_nvm_eeprom_spi,
 	igc_nvm_flash_hw,
 	igc_nvm_invm,
 };
@@ -113,11 +114,8 @@ struct igc_nvm_operations {
 
 struct igc_phy_operations {
 	s32 (*acquire)(struct igc_hw *hw);
-	s32 (*check_polarity)(struct igc_hw *hw);
 	s32 (*check_reset_block)(struct igc_hw *hw);
 	s32 (*force_speed_duplex)(struct igc_hw *hw);
-	s32 (*get_cfg_done)(struct igc_hw *hw);
-	s32 (*get_cable_length)(struct igc_hw *hw);
 	s32 (*get_phy_info)(struct igc_hw *hw);
 	s32 (*read_reg)(struct igc_hw *hw, u32 address, u16 *data);
 	void (*release)(struct igc_hw *hw);
diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c
index f7683d3ae47c..ba4646737288 100644
--- a/drivers/net/ethernet/intel/igc/igc_mac.c
+++ b/drivers/net/ethernet/intel/igc/igc_mac.c
@@ -8,7 +8,6 @@
 #include "igc_hw.h"
 
 /* forward declaration */
-static s32 igc_set_default_fc(struct igc_hw *hw);
 static s32 igc_set_fc_watermarks(struct igc_hw *hw);
 
 /**
@@ -96,13 +95,10 @@ s32 igc_setup_link(struct igc_hw *hw)
 		goto out;
 
 	/* If requested flow control is set to default, set flow control
-	 * based on the EEPROM flow control settings.
+	 * to the both 'rx' and 'tx' pause frames.
 	 */
-	if (hw->fc.requested_mode == igc_fc_default) {
-		ret_val = igc_set_default_fc(hw);
-		if (ret_val)
-			goto out;
-	}
+	if (hw->fc.requested_mode == igc_fc_default)
+		hw->fc.requested_mode = igc_fc_full;
 
 	/* We want to save off the original Flow Control configuration just
 	 * in case we get disconnected and then reconnected into a different
@@ -136,19 +132,6 @@ out:
 }
 
 /**
- * igc_set_default_fc - Set flow control default values
- * @hw: pointer to the HW structure
- *
- * Read the EEPROM for the default values for flow control and store the
- * values.
- */
-static s32 igc_set_default_fc(struct igc_hw *hw)
-{
-	hw->fc.requested_mode = igc_fc_full;
-	return 0;
-}
-
-/**
  * igc_force_mac_fc - Force the MAC's flow control settings
  * @hw: pointer to the HW structure
  *
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f20183037fb2..93f3b4e6185b 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -12,6 +12,8 @@
 #define DRV_VERSION	"0.0.1-k"
 #define DRV_SUMMARY	"Intel(R) 2.5G Ethernet Linux Driver"
 
+#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
+
 static int debug = -1;
 
 MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
@@ -66,10 +68,31 @@ enum latency_range {
 	latency_invalid = 255
 };
 
-static void igc_reset(struct igc_adapter *adapter)
+void igc_reset(struct igc_adapter *adapter)
 {
 	struct pci_dev *pdev = adapter->pdev;
 	struct igc_hw *hw = &adapter->hw;
+	struct igc_fc_info *fc = &hw->fc;
+	u32 pba, hwm;
+
+	/* Repartition PBA for greater than 9k MTU if required */
+	pba = IGC_PBA_34K;
+
+	/* flow control settings
+	 * The high water mark must be low enough to fit one full frame
+	 * after transmitting the pause frame.  As such we must have enough
+	 * space to allow for us to complete our current transmit and then
+	 * receive the frame that is in progress from the link partner.
+	 * Set it to:
+	 * - the full Rx FIFO size minus one full Tx plus one full Rx frame
+	 */
+	hwm = (pba << 10) - (adapter->max_frame_size + MAX_JUMBO_FRAME_SIZE);
+
+	fc->high_water = hwm & 0xFFFFFFF0;	/* 16-byte granularity */
+	fc->low_water = fc->high_water - 16;
+	fc->pause_time = 0xFFFF;
+	fc->send_xon = 1;
+	fc->current_mode = fc->requested_mode;
 
 	hw->mac.ops.reset_hw(hw);
 
@@ -150,7 +173,7 @@ static void igc_get_hw_control(struct igc_adapter *adapter)
  *
  * Free all transmit software resources
  */
-static void igc_free_tx_resources(struct igc_ring *tx_ring)
+void igc_free_tx_resources(struct igc_ring *tx_ring)
 {
 	igc_clean_tx_ring(tx_ring);
 
@@ -261,7 +284,7 @@ static void igc_clean_all_tx_rings(struct igc_adapter *adapter)
  *
  * Return 0 on success, negative on failure
  */
-static int igc_setup_tx_resources(struct igc_ring *tx_ring)
+int igc_setup_tx_resources(struct igc_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
 	int size = 0;
@@ -381,7 +404,7 @@ static void igc_clean_all_rx_rings(struct igc_adapter *adapter)
  *
  * Free all receive software resources
  */
-static void igc_free_rx_resources(struct igc_ring *rx_ring)
+void igc_free_rx_resources(struct igc_ring *rx_ring)
 {
 	igc_clean_rx_ring(rx_ring);
 
@@ -418,7 +441,7 @@ static void igc_free_all_rx_resources(struct igc_adapter *adapter)
  *
  * Returns 0 on success, negative on failure
  */
-static int igc_setup_rx_resources(struct igc_ring *rx_ring)
+int igc_setup_rx_resources(struct igc_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
 	int size, desc_len;
@@ -618,6 +641,55 @@ static void igc_configure_tx(struct igc_adapter *adapter)
  */
 static void igc_setup_mrqc(struct igc_adapter *adapter)
 {
+	struct igc_hw *hw = &adapter->hw;
+	u32 j, num_rx_queues;
+	u32 mrqc, rxcsum;
+	u32 rss_key[10];
+
+	netdev_rss_key_fill(rss_key, sizeof(rss_key));
+	for (j = 0; j < 10; j++)
+		wr32(IGC_RSSRK(j), rss_key[j]);
+
+	num_rx_queues = adapter->rss_queues;
+
+	if (adapter->rss_indir_tbl_init != num_rx_queues) {
+		for (j = 0; j < IGC_RETA_SIZE; j++)
+			adapter->rss_indir_tbl[j] =
+			(j * num_rx_queues) / IGC_RETA_SIZE;
+		adapter->rss_indir_tbl_init = num_rx_queues;
+	}
+	igc_write_rss_indir_tbl(adapter);
+
+	/* Disable raw packet checksumming so that RSS hash is placed in
+	 * descriptor on writeback.  No need to enable TCP/UDP/IP checksum
+	 * offloads as they are enabled by default
+	 */
+	rxcsum = rd32(IGC_RXCSUM);
+	rxcsum |= IGC_RXCSUM_PCSD;
+
+	/* Enable Receive Checksum Offload for SCTP */
+	rxcsum |= IGC_RXCSUM_CRCOFL;
+
+	/* Don't need to set TUOFL or IPOFL, they default to 1 */
+	wr32(IGC_RXCSUM, rxcsum);
+
+	/* Generate RSS hash based on packet types, TCP/UDP
+	 * port numbers and/or IPv4/v6 src and dst addresses
+	 */
+	mrqc = IGC_MRQC_RSS_FIELD_IPV4 |
+	       IGC_MRQC_RSS_FIELD_IPV4_TCP |
+	       IGC_MRQC_RSS_FIELD_IPV6 |
+	       IGC_MRQC_RSS_FIELD_IPV6_TCP |
+	       IGC_MRQC_RSS_FIELD_IPV6_TCP_EX;
+
+	if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV4_UDP)
+		mrqc |= IGC_MRQC_RSS_FIELD_IPV4_UDP;
+	if (adapter->flags & IGC_FLAG_RSS_FIELD_IPV6_UDP)
+		mrqc |= IGC_MRQC_RSS_FIELD_IPV6_UDP;
+
+	mrqc |= IGC_MRQC_ENABLE_RSS_MQ;
+
+	wr32(IGC_MRQC, mrqc);
 }
 
 /**
@@ -888,13 +960,8 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 	/* Make sure there is space in the ring for the next send. */
 	igc_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
@@ -1148,7 +1215,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IGC_RX_HDR_LEN)
-		headlen = eth_get_headlen(va, IGC_RX_HDR_LEN);
+		headlen = eth_get_headlen(skb->dev, va, IGC_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
@@ -1703,7 +1770,7 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
  * igc_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
  */
-static void igc_up(struct igc_adapter *adapter)
+void igc_up(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int i = 0;
@@ -1736,19 +1803,207 @@ static void igc_up(struct igc_adapter *adapter)
  * igc_update_stats - Update the board statistics counters
  * @adapter: board private structure
  */
-static void igc_update_stats(struct igc_adapter *adapter)
+void igc_update_stats(struct igc_adapter *adapter)
 {
+	struct rtnl_link_stats64 *net_stats = &adapter->stats64;
+	struct pci_dev *pdev = adapter->pdev;
+	struct igc_hw *hw = &adapter->hw;
+	u64 _bytes, _packets;
+	u64 bytes, packets;
+	unsigned int start;
+	u32 mpc;
+	int i;
+
+	/* Prevent stats update while adapter is being reset, or if the pci
+	 * connection is down.
+	 */
+	if (adapter->link_speed == 0)
+		return;
+	if (pci_channel_offline(pdev))
+		return;
+
+	packets = 0;
+	bytes = 0;
+
+	rcu_read_lock();
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct igc_ring *ring = adapter->rx_ring[i];
+		u32 rqdpc = rd32(IGC_RQDPC(i));
+
+		if (hw->mac.type >= igc_i225)
+			wr32(IGC_RQDPC(i), 0);
+
+		if (rqdpc) {
+			ring->rx_stats.drops += rqdpc;
+			net_stats->rx_fifo_errors += rqdpc;
+		}
+
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
+			_bytes = ring->rx_stats.bytes;
+			_packets = ring->rx_stats.packets;
+		} while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
+		bytes += _bytes;
+		packets += _packets;
+	}
+
+	net_stats->rx_bytes = bytes;
+	net_stats->rx_packets = packets;
+
+	packets = 0;
+	bytes = 0;
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *ring = adapter->tx_ring[i];
+
+		do {
+			start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
+			_bytes = ring->tx_stats.bytes;
+			_packets = ring->tx_stats.packets;
+		} while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
+		bytes += _bytes;
+		packets += _packets;
+	}
+	net_stats->tx_bytes = bytes;
+	net_stats->tx_packets = packets;
+	rcu_read_unlock();
+
+	/* read stats registers */
+	adapter->stats.crcerrs += rd32(IGC_CRCERRS);
+	adapter->stats.gprc += rd32(IGC_GPRC);
+	adapter->stats.gorc += rd32(IGC_GORCL);
+	rd32(IGC_GORCH); /* clear GORCL */
+	adapter->stats.bprc += rd32(IGC_BPRC);
+	adapter->stats.mprc += rd32(IGC_MPRC);
+	adapter->stats.roc += rd32(IGC_ROC);
+
+	adapter->stats.prc64 += rd32(IGC_PRC64);
+	adapter->stats.prc127 += rd32(IGC_PRC127);
+	adapter->stats.prc255 += rd32(IGC_PRC255);
+	adapter->stats.prc511 += rd32(IGC_PRC511);
+	adapter->stats.prc1023 += rd32(IGC_PRC1023);
+	adapter->stats.prc1522 += rd32(IGC_PRC1522);
+	adapter->stats.symerrs += rd32(IGC_SYMERRS);
+	adapter->stats.sec += rd32(IGC_SEC);
+
+	mpc = rd32(IGC_MPC);
+	adapter->stats.mpc += mpc;
+	net_stats->rx_fifo_errors += mpc;
+	adapter->stats.scc += rd32(IGC_SCC);
+	adapter->stats.ecol += rd32(IGC_ECOL);
+	adapter->stats.mcc += rd32(IGC_MCC);
+	adapter->stats.latecol += rd32(IGC_LATECOL);
+	adapter->stats.dc += rd32(IGC_DC);
+	adapter->stats.rlec += rd32(IGC_RLEC);
+	adapter->stats.xonrxc += rd32(IGC_XONRXC);
+	adapter->stats.xontxc += rd32(IGC_XONTXC);
+	adapter->stats.xoffrxc += rd32(IGC_XOFFRXC);
+	adapter->stats.xofftxc += rd32(IGC_XOFFTXC);
+	adapter->stats.fcruc += rd32(IGC_FCRUC);
+	adapter->stats.gptc += rd32(IGC_GPTC);
+	adapter->stats.gotc += rd32(IGC_GOTCL);
+	rd32(IGC_GOTCH); /* clear GOTCL */
+	adapter->stats.rnbc += rd32(IGC_RNBC);
+	adapter->stats.ruc += rd32(IGC_RUC);
+	adapter->stats.rfc += rd32(IGC_RFC);
+	adapter->stats.rjc += rd32(IGC_RJC);
+	adapter->stats.tor += rd32(IGC_TORH);
+	adapter->stats.tot += rd32(IGC_TOTH);
+	adapter->stats.tpr += rd32(IGC_TPR);
+
+	adapter->stats.ptc64 += rd32(IGC_PTC64);
+	adapter->stats.ptc127 += rd32(IGC_PTC127);
+	adapter->stats.ptc255 += rd32(IGC_PTC255);
+	adapter->stats.ptc511 += rd32(IGC_PTC511);
+	adapter->stats.ptc1023 += rd32(IGC_PTC1023);
+	adapter->stats.ptc1522 += rd32(IGC_PTC1522);
+
+	adapter->stats.mptc += rd32(IGC_MPTC);
+	adapter->stats.bptc += rd32(IGC_BPTC);
+
+	adapter->stats.tpt += rd32(IGC_TPT);
+	adapter->stats.colc += rd32(IGC_COLC);
+
+	adapter->stats.algnerrc += rd32(IGC_ALGNERRC);
+
+	adapter->stats.tsctc += rd32(IGC_TSCTC);
+	adapter->stats.tsctfc += rd32(IGC_TSCTFC);
+
+	adapter->stats.iac += rd32(IGC_IAC);
+	adapter->stats.icrxoc += rd32(IGC_ICRXOC);
+	adapter->stats.icrxptc += rd32(IGC_ICRXPTC);
+	adapter->stats.icrxatc += rd32(IGC_ICRXATC);
+	adapter->stats.ictxptc += rd32(IGC_ICTXPTC);
+	adapter->stats.ictxatc += rd32(IGC_ICTXATC);
+	adapter->stats.ictxqec += rd32(IGC_ICTXQEC);
+	adapter->stats.ictxqmtc += rd32(IGC_ICTXQMTC);
+	adapter->stats.icrxdmtc += rd32(IGC_ICRXDMTC);
+
+	/* Fill out the OS statistics structure */
+	net_stats->multicast = adapter->stats.mprc;
+	net_stats->collisions = adapter->stats.colc;
+
+	/* Rx Errors */
+
+	/* RLEC on some newer hardware can be incorrect so build
+	 * our own version based on RUC and ROC
+	 */
+	net_stats->rx_errors = adapter->stats.rxerrc +
+		adapter->stats.crcerrs + adapter->stats.algnerrc +
+		adapter->stats.ruc + adapter->stats.roc +
+		adapter->stats.cexterr;
+	net_stats->rx_length_errors = adapter->stats.ruc +
+				      adapter->stats.roc;
+	net_stats->rx_crc_errors = adapter->stats.crcerrs;
+	net_stats->rx_frame_errors = adapter->stats.algnerrc;
+	net_stats->rx_missed_errors = adapter->stats.mpc;
+
+	/* Tx Errors */
+	net_stats->tx_errors = adapter->stats.ecol +
+			       adapter->stats.latecol;
+	net_stats->tx_aborted_errors = adapter->stats.ecol;
+	net_stats->tx_window_errors = adapter->stats.latecol;
+	net_stats->tx_carrier_errors = adapter->stats.tncrs;
+
+	/* Tx Dropped needs to be maintained elsewhere */
+
+	/* Management Stats */
+	adapter->stats.mgptc += rd32(IGC_MGTPTC);
+	adapter->stats.mgprc += rd32(IGC_MGTPRC);
+	adapter->stats.mgpdc += rd32(IGC_MGTPDC);
 }
 
 static void igc_nfc_filter_exit(struct igc_adapter *adapter)
 {
+	struct igc_nfc_filter *rule;
+
+	spin_lock(&adapter->nfc_lock);
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
+		igc_erase_filter(adapter, rule);
+
+	hlist_for_each_entry(rule, &adapter->cls_flower_list, nfc_node)
+		igc_erase_filter(adapter, rule);
+
+	spin_unlock(&adapter->nfc_lock);
+}
+
+static void igc_nfc_filter_restore(struct igc_adapter *adapter)
+{
+	struct igc_nfc_filter *rule;
+
+	spin_lock(&adapter->nfc_lock);
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
+		igc_add_filter(adapter, rule);
+
+	spin_unlock(&adapter->nfc_lock);
 }
 
 /**
  * igc_down - Close the interface
  * @adapter: board private structure
  */
-static void igc_down(struct igc_adapter *adapter)
+void igc_down(struct igc_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct igc_hw *hw = &adapter->hw;
@@ -1810,7 +2065,7 @@ static void igc_down(struct igc_adapter *adapter)
 	igc_clean_all_rx_rings(adapter);
 }
 
-static void igc_reinit_locked(struct igc_adapter *adapter)
+void igc_reinit_locked(struct igc_adapter *adapter)
 {
 	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
@@ -1888,6 +2143,86 @@ static struct net_device_stats *igc_get_stats(struct net_device *netdev)
 	return &netdev->stats;
 }
 
+static netdev_features_t igc_fix_features(struct net_device *netdev,
+					  netdev_features_t features)
+{
+	/* Since there is no support for separate Rx/Tx vlan accel
+	 * enable/disable make sure Tx flag is always in same state as Rx.
+	 */
+	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		features |= NETIF_F_HW_VLAN_CTAG_TX;
+	else
+		features &= ~NETIF_F_HW_VLAN_CTAG_TX;
+
+	return features;
+}
+
+static int igc_set_features(struct net_device *netdev,
+			    netdev_features_t features)
+{
+	netdev_features_t changed = netdev->features ^ features;
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	/* Add VLAN support */
+	if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE)))
+		return 0;
+
+	if (!(features & NETIF_F_NTUPLE)) {
+		struct hlist_node *node2;
+		struct igc_nfc_filter *rule;
+
+		spin_lock(&adapter->nfc_lock);
+		hlist_for_each_entry_safe(rule, node2,
+					  &adapter->nfc_filter_list, nfc_node) {
+			igc_erase_filter(adapter, rule);
+			hlist_del(&rule->nfc_node);
+			kfree(rule);
+		}
+		spin_unlock(&adapter->nfc_lock);
+		adapter->nfc_filter_count = 0;
+	}
+
+	netdev->features = features;
+
+	if (netif_running(netdev))
+		igc_reinit_locked(adapter);
+	else
+		igc_reset(adapter);
+
+	return 1;
+}
+
+static netdev_features_t
+igc_features_check(struct sk_buff *skb, struct net_device *dev,
+		   netdev_features_t features)
+{
+	unsigned int network_hdr_len, mac_hdr_len;
+
+	/* Make certain the headers can be described by a context descriptor */
+	mac_hdr_len = skb_network_header(skb) - skb->data;
+	if (unlikely(mac_hdr_len > IGC_MAX_MAC_HDR_LEN))
+		return features & ~(NETIF_F_HW_CSUM |
+				    NETIF_F_SCTP_CRC |
+				    NETIF_F_HW_VLAN_CTAG_TX |
+				    NETIF_F_TSO |
+				    NETIF_F_TSO6);
+
+	network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb);
+	if (unlikely(network_hdr_len >  IGC_MAX_NETWORK_HDR_LEN))
+		return features & ~(NETIF_F_HW_CSUM |
+				    NETIF_F_SCTP_CRC |
+				    NETIF_F_TSO |
+				    NETIF_F_TSO6);
+
+	/* We can only support IPv4 TSO in tunnels if we can mangle the
+	 * inner IP ID field, so strip TSO if MANGLEID is not supported.
+	 */
+	if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID))
+		features &= ~NETIF_F_TSO;
+
+	return features;
+}
+
 /**
  * igc_configure - configure the hardware for RX and TX
  * @adapter: private board structure
@@ -1904,6 +2239,7 @@ static void igc_configure(struct igc_adapter *adapter)
 	igc_setup_mrqc(adapter);
 	igc_setup_rctl(adapter);
 
+	igc_nfc_filter_restore(adapter);
 	igc_configure_tx(adapter);
 	igc_configure_rx(adapter);
 
@@ -1922,7 +2258,7 @@ static void igc_configure(struct igc_adapter *adapter)
 
 /**
  * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
- * @adapter: Pointer to adapter structure
+ * @adapter: address of board private structure
  * @index: Index of the RAR entry which need to be synced with MAC table
  */
 static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
@@ -1965,6 +2301,127 @@ static void igc_set_default_mac_filter(struct igc_adapter *adapter)
 	igc_rar_set_index(adapter, 0);
 }
 
+/* If the filter to be added and an already existing filter express
+ * the same address and address type, it should be possible to only
+ * override the other configurations, for example the queue to steer
+ * traffic.
+ */
+static bool igc_mac_entry_can_be_used(const struct igc_mac_addr *entry,
+				      const u8 *addr, const u8 flags)
+{
+	if (!(entry->state & IGC_MAC_STATE_IN_USE))
+		return true;
+
+	if ((entry->state & IGC_MAC_STATE_SRC_ADDR) !=
+	    (flags & IGC_MAC_STATE_SRC_ADDR))
+		return false;
+
+	if (!ether_addr_equal(addr, entry->addr))
+		return false;
+
+	return true;
+}
+
+/* Add a MAC filter for 'addr' directing matching traffic to 'queue',
+ * 'flags' is used to indicate what kind of match is made, match is by
+ * default for the destination address, if matching by source address
+ * is desired the flag IGC_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igc_add_mac_filter_flags(struct igc_adapter *adapter,
+				    const u8 *addr, const u8 queue,
+				    const u8 flags)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int rar_entries = hw->mac.rar_entry_count;
+	int i;
+
+	if (is_zero_ether_addr(addr))
+		return -EINVAL;
+
+	/* Search for the first empty entry in the MAC table.
+	 * Do not touch entries at the end of the table reserved for the VF MAC
+	 * addresses.
+	 */
+	for (i = 0; i < rar_entries; i++) {
+		if (!igc_mac_entry_can_be_used(&adapter->mac_table[i],
+					       addr, flags))
+			continue;
+
+		ether_addr_copy(adapter->mac_table[i].addr, addr);
+		adapter->mac_table[i].queue = queue;
+		adapter->mac_table[i].state |= IGC_MAC_STATE_IN_USE | flags;
+
+		igc_rar_set_index(adapter, i);
+		return i;
+	}
+
+	return -ENOSPC;
+}
+
+int igc_add_mac_steering_filter(struct igc_adapter *adapter,
+				const u8 *addr, u8 queue, u8 flags)
+{
+	return igc_add_mac_filter_flags(adapter, addr, queue,
+					IGC_MAC_STATE_QUEUE_STEERING | flags);
+}
+
+/* Remove a MAC filter for 'addr' directing matching traffic to
+ * 'queue', 'flags' is used to indicate what kind of match need to be
+ * removed, match is by default for the destination address, if
+ * matching by source address is to be removed the flag
+ * IGC_MAC_STATE_SRC_ADDR can be used.
+ */
+static int igc_del_mac_filter_flags(struct igc_adapter *adapter,
+				    const u8 *addr, const u8 queue,
+				    const u8 flags)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int rar_entries = hw->mac.rar_entry_count;
+	int i;
+
+	if (is_zero_ether_addr(addr))
+		return -EINVAL;
+
+	/* Search for matching entry in the MAC table based on given address
+	 * and queue. Do not touch entries at the end of the table reserved
+	 * for the VF MAC addresses.
+	 */
+	for (i = 0; i < rar_entries; i++) {
+		if (!(adapter->mac_table[i].state & IGC_MAC_STATE_IN_USE))
+			continue;
+		if ((adapter->mac_table[i].state & flags) != flags)
+			continue;
+		if (adapter->mac_table[i].queue != queue)
+			continue;
+		if (!ether_addr_equal(adapter->mac_table[i].addr, addr))
+			continue;
+
+		/* When a filter for the default address is "deleted",
+		 * we return it to its initial configuration
+		 */
+		if (adapter->mac_table[i].state & IGC_MAC_STATE_DEFAULT) {
+			adapter->mac_table[i].state =
+				IGC_MAC_STATE_DEFAULT | IGC_MAC_STATE_IN_USE;
+		} else {
+			adapter->mac_table[i].state = 0;
+			adapter->mac_table[i].queue = 0;
+			memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+		}
+
+		igc_rar_set_index(adapter, i);
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+int igc_del_mac_steering_filter(struct igc_adapter *adapter,
+				const u8 *addr, u8 queue, u8 flags)
+{
+	return igc_del_mac_filter_flags(adapter, addr, queue,
+					IGC_MAC_STATE_QUEUE_STEERING | flags);
+}
+
 /**
  * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set
  * @netdev: network interface device structure
@@ -2298,7 +2755,7 @@ static void igc_update_phy_info(struct timer_list *t)
  * igc_has_link - check shared code for link and determine up/down
  * @adapter: pointer to driver private info
  */
-static bool igc_has_link(struct igc_adapter *adapter)
+bool igc_has_link(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 	bool link_active = false;
@@ -2956,22 +3413,21 @@ static int igc_alloc_q_vector(struct igc_adapter *adapter,
 {
 	struct igc_q_vector *q_vector;
 	struct igc_ring *ring;
-	int ring_count, size;
+	int ring_count;
 
 	/* igc only supports 1 Tx and/or 1 Rx queue per vector */
 	if (txr_count > 1 || rxr_count > 1)
 		return -ENOMEM;
 
 	ring_count = txr_count + rxr_count;
-	size = sizeof(struct igc_q_vector) +
-		(sizeof(struct igc_ring) * ring_count);
 
 	/* allocate q_vector and rings */
 	q_vector = adapter->q_vector[v_idx];
 	if (!q_vector)
-		q_vector = kzalloc(size, GFP_KERNEL);
+		q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
+				   GFP_KERNEL);
 	else
-		memset(q_vector, 0, size);
+		memset(q_vector, 0, struct_size(q_vector, ring, ring_count));
 	if (!q_vector)
 		return -ENOMEM;
 
@@ -3433,6 +3889,9 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_set_mac_address	= igc_set_mac,
 	.ndo_change_mtu		= igc_change_mtu,
 	.ndo_get_stats		= igc_get_stats,
+	.ndo_fix_features	= igc_fix_features,
+	.ndo_set_features	= igc_set_features,
+	.ndo_features_check	= igc_features_check,
 };
 
 /* PCIe configuration access */
@@ -3496,11 +3955,63 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 		hw->hw_addr = NULL;
 		netif_device_detach(netdev);
 		netdev_err(netdev, "PCIe link lost, device now detached\n");
+		WARN(1, "igc: Failed to read reg 0x%x!\n", reg);
 	}
 
 	return value;
 }
 
+int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct igc_mac_info *mac = &adapter->hw.mac;
+
+	mac->autoneg = 0;
+
+	/* Make sure dplx is at most 1 bit and lsb of speed is not set
+	 * for the switch() below to work
+	 */
+	if ((spd & 1) || (dplx & ~1))
+		goto err_inval;
+
+	switch (spd + dplx) {
+	case SPEED_10 + DUPLEX_HALF:
+		mac->forced_speed_duplex = ADVERTISE_10_HALF;
+		break;
+	case SPEED_10 + DUPLEX_FULL:
+		mac->forced_speed_duplex = ADVERTISE_10_FULL;
+		break;
+	case SPEED_100 + DUPLEX_HALF:
+		mac->forced_speed_duplex = ADVERTISE_100_HALF;
+		break;
+	case SPEED_100 + DUPLEX_FULL:
+		mac->forced_speed_duplex = ADVERTISE_100_FULL;
+		break;
+	case SPEED_1000 + DUPLEX_FULL:
+		mac->autoneg = 1;
+		adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL;
+		break;
+	case SPEED_1000 + DUPLEX_HALF: /* not supported */
+		goto err_inval;
+	case SPEED_2500 + DUPLEX_FULL:
+		mac->autoneg = 1;
+		adapter->hw.phy.autoneg_advertised = ADVERTISE_2500_FULL;
+		break;
+	case SPEED_2500 + DUPLEX_HALF: /* not supported */
+	default:
+		goto err_inval;
+	}
+
+	/* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+	adapter->hw.phy.mdix = AUTO_ALL_MODES;
+
+	return 0;
+
+err_inval:
+	dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n");
+	return -EINVAL;
+}
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -3568,7 +4079,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw = &adapter->hw;
 	hw->back = adapter;
 	adapter->port_num = hw->bus.func;
-	adapter->msg_enable = GENMASK(debug - 1, 0);
+	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 	err = pci_save_state(pdev);
 	if (err)
@@ -3584,7 +4095,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igc_netdev_ops;
-
+	igc_set_ethtool_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
 	netdev->mem_start = pci_resource_start(pdev, 0);
@@ -3611,6 +4122,9 @@ static int igc_probe(struct pci_dev *pdev,
 	if (err)
 		goto err_sw_init;
 
+	/* copy netdev features into list of user selectable features */
+	netdev->hw_features |= NETIF_F_NTUPLE;
+
 	/* MTU range: 68 - 9216 */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
@@ -3744,8 +4258,8 @@ static struct pci_driver igc_driver = {
 	.remove   = igc_remove,
 };
 
-static void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
-				     const u32 max_rss_queues)
+void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+			      const u32 max_rss_queues)
 {
 	/* Determine if we need to pair queues. */
 	/* If rss_queues > half of max_rss_queues, pair the queues in
@@ -3757,7 +4271,7 @@ static void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
 		adapter->flags &= ~IGC_FLAG_QUEUE_PAIRS;
 }
 
-static unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
+unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
 {
 	unsigned int max_rss_queues;
 
@@ -3837,6 +4351,32 @@ static int igc_sw_init(struct igc_adapter *adapter)
 }
 
 /**
+ * igc_reinit_queues - return error
+ * @adapter: pointer to adapter structure
+ */
+int igc_reinit_queues(struct igc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	int err = 0;
+
+	if (netif_running(netdev))
+		igc_close(netdev);
+
+	igc_reset_interrupt_capability(adapter);
+
+	if (igc_init_interrupt_scheme(adapter, true)) {
+		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		return -ENOMEM;
+	}
+
+	if (netif_running(netdev))
+		err = igc_open(netdev);
+
+	return err;
+}
+
+/**
  * igc_get_hw_dev - return device
  * @hw: pointer to hardware structure
  *
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 38e43e6fc1c7..4c8f96a9a148 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -152,7 +152,6 @@ void igc_power_down_phy_copper(struct igc_hw *hw)
 s32 igc_check_downshift(struct igc_hw *hw)
 {
 	struct igc_phy_info *phy = &hw->phy;
-	u16 phy_data, offset, mask;
 	s32 ret_val;
 
 	switch (phy->type) {
@@ -161,15 +160,8 @@ s32 igc_check_downshift(struct igc_hw *hw)
 		/* speed downshift not supported */
 		phy->speed_downgraded = false;
 		ret_val = 0;
-		goto out;
 	}
 
-	ret_val = phy->ops.read_reg(hw, offset, &phy_data);
-
-	if (!ret_val)
-		phy->speed_downgraded = (phy_data & mask) ? true : false;
-
-out:
 	return ret_val;
 }
 
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index a1bd3216c906..50d7c04dccf5 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -80,6 +80,24 @@
 /* MSI-X Table Register Descriptions */
 #define IGC_PBACL		0x05B68  /* MSIx PBA Clear - R/W 1 to clear */
 
+/* RSS registers */
+#define IGC_MRQC		0x05818 /* Multiple Receive Control - RW */
+
+/* Filtering Registers */
+#define IGC_ETQF(_n)		(0x05CB0 + (4 * (_n))) /* EType Queue Fltr */
+
+/* ETQF register bit definitions */
+#define IGC_ETQF_FILTER_ENABLE	BIT(26)
+#define IGC_ETQF_QUEUE_ENABLE	BIT(31)
+#define IGC_ETQF_QUEUE_SHIFT	16
+#define IGC_ETQF_QUEUE_MASK	0x00070000
+#define IGC_ETQF_ETYPE_MASK	0x0000FFFF
+
+/* Redirection Table - RW Array */
+#define IGC_RETA(_i)		(0x05C00 + ((_i) * 4))
+/* RSS Random Key - RW Array */
+#define IGC_RSSRK(_i)		(0x05C80 + ((_i) * 4))
+
 /* Receive Register Descriptions */
 #define IGC_RCTL		0x00100  /* Rx Control - RW */
 #define IGC_SRRCTL(_n)		(0x0C00C + ((_n) * 0x40))
@@ -98,6 +116,7 @@
 #define IGC_UTA			0x0A000  /* Unicast Table Array - RW */
 #define IGC_RAL(_n)		(0x05400 + ((_n) * 0x08))
 #define IGC_RAH(_n)		(0x05404 + ((_n) * 0x08))
+#define IGC_VLAPQF		0x055B0  /* VLAN Priority Queue Filter VLAPQF */
 
 /* Transmit Register Descriptions */
 #define IGC_TCTL		0x00400  /* Tx Control - RW */
@@ -188,7 +207,6 @@
 #define IGC_HGOTCL	0x04130  /* Host Good Octets Transmit Count Low */
 #define IGC_HGOTCH	0x04134  /* Host Good Octets Transmit Count High */
 #define IGC_LENERRS	0x04138  /* Length Errors Count */
-#define IGC_SCVPC	0x04228  /* SerDes/SGMII Code Violation Pkt Count */
 #define IGC_HRMPC	0x0A018  /* Header Redirection Missed Packet Count */
 
 /* Management registers */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 08d85e336bd4..39e73ad60352 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -50,8 +50,6 @@
 #define IXGBE_MAX_RXD			   4096
 #define IXGBE_MIN_RXD			     64
 
-#define IXGBE_ETH_P_LLDP		 0x88CC
-
 /* flow control */
 #define IXGBE_MIN_FCRTL			   0x40
 #define IXGBE_MAX_FCRTL			0x7FF80
@@ -635,6 +633,7 @@ struct ixgbe_adapter {
 	/* XDP */
 	int num_xdp_queues;
 	struct ixgbe_ring *xdp_ring[MAX_XDP_QUEUES];
+	unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled rings */
 
 	/* TX */
 	struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp;
@@ -774,11 +773,6 @@ struct ixgbe_adapter {
 #ifdef CONFIG_IXGBE_IPSEC
 	struct ixgbe_ipsec *ipsec;
 #endif /* CONFIG_IXGBE_IPSEC */
-
-	/* AF_XDP zero-copy */
-	struct xdp_umem **xsk_umems;
-	u16 num_xsk_umems_used;
-	u16 num_xsk_umems;
 };
 
 static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
@@ -1039,4 +1033,10 @@ static inline int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter,
 static inline int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter,
 					u32 *mbuf, u32 vf) { return -EACCES; }
 #endif /* CONFIG_IXGBE_IPSEC */
+
+static inline bool ixgbe_enabled_xdp_adapter(struct ixgbe_adapter *adapter)
+{
+	return !!adapter->xdp_prog;
+}
+
 #endif /* _IXGBE_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 1e49716f52bc..109f8de5a1c2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -1048,7 +1048,7 @@ mac_reset_top:
 	 * clear the multicast table.  Also reset num_rar_entries to 128,
 	 * since we modify this value when programming the SAN MAC address.
 	 */
-	hw->mac.num_rar_entries = 128;
+	hw->mac.num_rar_entries = IXGBE_82599_RAR_ENTRIES;
 	hw->mac.ops.init_rx_addrs(hw);
 
 	/* Store the permanent SAN mac address */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index acba067cc15a..7c52ae8ac005 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -3226,7 +3226,8 @@ static int ixgbe_get_module_info(struct net_device *dev,
 		page_swap = true;
 	}
 
-	if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap) {
+	if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap ||
+	    !(addr_mode & IXGBE_SFF_DDM_IMPLEMENTED)) {
 		/* We have a SFP, but it does not support SFF-8472 */
 		modinfo->type = ETH_MODULE_SFF_8079;
 		modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index ff85ce5791a3..31629fc7e820 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -842,6 +842,9 @@ void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf)
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	int i;
 
+	if (!ipsec)
+		return;
+
 	/* search rx sa table */
 	for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_rx_sa; i++) {
 		if (!ipsec->rx_tbl[i].used)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 62e6499e4146..cc3196ae5aea 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -836,12 +836,10 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	struct ixgbe_ring *ring;
 	int node = NUMA_NO_NODE;
 	int cpu = -1;
-	int ring_count, size;
+	int ring_count;
 	u8 tcs = adapter->hw_tcs;
 
 	ring_count = txr_count + rxr_count + xdp_count;
-	size = sizeof(struct ixgbe_q_vector) +
-	       (sizeof(struct ixgbe_ring) * ring_count);
 
 	/* customize cpu for Flow Director mapping */
 	if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) {
@@ -855,9 +853,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	}
 
 	/* allocate q_vector and rings */
-	q_vector = kzalloc_node(size, GFP_KERNEL, node);
+	q_vector = kzalloc_node(struct_size(q_vector, ring, ring_count),
+				GFP_KERNEL, node);
 	if (!q_vector)
-		q_vector = kzalloc(size, GFP_KERNEL);
+		q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
+				   GFP_KERNEL);
 	if (!q_vector)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index daff8183534b..cbaf712d6529 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -27,6 +27,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/atomic.h>
+#include <linux/numa.h>
 #include <scsi/fc/fc_fcoe.h>
 #include <net/udp_tunnel.h>
 #include <net/pkt_cls.h>
@@ -1799,7 +1800,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
 	 * we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE);
+	pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
@@ -3953,8 +3954,11 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
 			else
 				mrqc = IXGBE_MRQC_VMDQRSS64EN;
 
-			/* Enable L3/L4 for Tx Switched packets */
-			mrqc |= IXGBE_MRQC_L3L4TXSWEN;
+			/* Enable L3/L4 for Tx Switched packets only for X550,
+			 * older devices do not support this feature
+			 */
+			if (hw->mac.type >= ixgbe_mac_X550)
+				mrqc |= IXGBE_MRQC_L3L4TXSWEN;
 		} else {
 			if (tcs > 4)
 				mrqc = IXGBE_MRQC_RTRSS8TCEN;
@@ -6284,6 +6288,10 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 	if (ixgbe_init_rss_key(adapter))
 		return -ENOMEM;
 
+	adapter->af_xdp_zc_qps = bitmap_zalloc(MAX_XDP_QUEUES, GFP_KERNEL);
+	if (!adapter->af_xdp_zc_qps)
+		return -ENOMEM;
+
 	/* Set MAC specific capability flags and exceptions */
 	switch (hw->mac.type) {
 	case ixgbe_mac_82598EB:
@@ -6415,7 +6423,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
 	int orig_node = dev_to_node(dev);
-	int ring_node = -1;
+	int ring_node = NUMA_NO_NODE;
 	int size;
 
 	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
@@ -6509,7 +6517,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 {
 	struct device *dev = rx_ring->dev;
 	int orig_node = dev_to_node(dev);
-	int ring_node = -1;
+	int ring_node = NUMA_NO_NODE;
 	int size;
 
 	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
@@ -8293,13 +8301,8 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 
 	ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
@@ -8479,8 +8482,7 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 
 #ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      struct net_device *sb_dev,
-			      select_queue_fallback_t fallback)
+			      struct net_device *sb_dev)
 {
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
@@ -8510,7 +8512,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 			break;
 		/* fall through */
 	default:
-		return fallback(dev, skb, sb_dev);
+		return netdev_pick_tx(dev, skb, sb_dev);
 	}
 
 	f = &adapter->ring_feature[RING_F_FCOE];
@@ -9605,27 +9607,6 @@ static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int ixgbe_setup_tc_block(struct net_device *dev,
-				struct tc_block_offload *f)
-{
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
-					     adapter, adapter, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
-					adapter);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int ixgbe_setup_tc_mqprio(struct net_device *dev,
 				 struct tc_mqprio_qopt *mqprio)
 {
@@ -9633,12 +9614,19 @@ static int ixgbe_setup_tc_mqprio(struct net_device *dev,
 	return ixgbe_setup_tc(dev, mqprio->num_tc);
 }
 
+static LIST_HEAD(ixgbe_block_cb_list);
+
 static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			    void *type_data)
 {
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return ixgbe_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &ixgbe_block_cb_list,
+						  ixgbe_setup_tc_block_cb,
+						  adapter, adapter, true);
 	case TC_SETUP_QDISC_MQPRIO:
 		return ixgbe_setup_tc_mqprio(dev, type_data);
 	default:
@@ -9792,7 +9780,7 @@ static int ixgbe_set_features(struct net_device *netdev,
 			    NETIF_F_HW_VLAN_CTAG_FILTER))
 		ixgbe_set_rx_mode(netdev);
 
-	return 0;
+	return 1;
 }
 
 /**
@@ -9910,7 +9898,8 @@ static void ixgbe_del_udp_tunnel_port(struct net_device *dev,
 static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			     struct net_device *dev,
 			     const unsigned char *addr, u16 vid,
-			     u16 flags)
+			     u16 flags,
+			     struct netlink_ext_ack *extack)
 {
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
@@ -10225,6 +10214,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct bpf_prog *old_prog;
+	bool need_reset;
 
 	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
 		return -EINVAL;
@@ -10247,9 +10237,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 		return -ENOMEM;
 
 	old_prog = xchg(&adapter->xdp_prog, prog);
+	need_reset = (!!prog != !!old_prog);
 
 	/* If transitioning XDP modes reconfigure rings */
-	if (!!prog != !!old_prog) {
+	if (need_reset) {
 		int err = ixgbe_setup_tc(dev, adapter->hw_tcs);
 
 		if (err) {
@@ -10265,6 +10256,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	/* Kick start the NAPI context if there is an AF_XDP socket open
+	 * on that queue id. This so that receiving will start.
+	 */
+	if (need_reset && prog)
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			if (adapter->xdp_ring[i]->xsk_umem)
+				(void)ixgbe_xsk_async_xmit(adapter->netdev, i);
+
 	return 0;
 }
 
@@ -10279,9 +10278,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		xdp->prog_id = adapter->xdp_prog ?
 			adapter->xdp_prog->aux->id : 0;
 		return 0;
-	case XDP_QUERY_XSK_UMEM:
-		return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem,
-					    xdp->xsk.queue_id);
 	case XDP_SETUP_XSK_UMEM:
 		return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem,
 					    xdp->xsk.queue_id);
@@ -11155,6 +11151,7 @@ err_sw_init:
 	kfree(adapter->jump_tables[0]);
 	kfree(adapter->mac_table);
 	kfree(adapter->rss_key);
+	bitmap_free(adapter->af_xdp_zc_qps);
 err_ioremap:
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
@@ -11243,6 +11240,7 @@ static void ixgbe_remove(struct pci_dev *pdev)
 
 	kfree(adapter->mac_table);
 	kfree(adapter->rss_key);
+	bitmap_free(adapter->af_xdp_zc_qps);
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index cc4907f9ff02..2fb97967961c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -905,13 +905,12 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw)
 	struct pci_dev *pdev = adapter->pdev;
 	struct device *dev = &adapter->netdev->dev;
 	struct mii_bus *bus;
+	int err = -ENODEV;
 
-	adapter->mii_bus = devm_mdiobus_alloc(dev);
-	if (!adapter->mii_bus)
+	bus = devm_mdiobus_alloc(dev);
+	if (!bus)
 		return -ENOMEM;
 
-	bus = adapter->mii_bus;
-
 	switch (hw->device_id) {
 	/* C3000 SoCs */
 	case IXGBE_DEV_ID_X550EM_A_KR:
@@ -949,12 +948,15 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw)
 	 */
 	hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22;
 
-	return mdiobus_register(bus);
+	err = mdiobus_register(bus);
+	if (!err) {
+		adapter->mii_bus = bus;
+		return 0;
+	}
 
 ixgbe_no_mii_bus:
 	devm_mdiobus_free(dev, bus);
-	adapter->mii_bus = NULL;
-	return -ENODEV;
+	return err;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 214b01085718..6544c4539c0d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -45,6 +45,7 @@
 #define IXGBE_SFF_SOFT_RS_SELECT_10G		0x8
 #define IXGBE_SFF_SOFT_RS_SELECT_1G		0x0
 #define IXGBE_SFF_ADDRESSING_MODE		0x4
+#define IXGBE_SFF_DDM_IMPLEMENTED		0x40
 #define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE		0x1
 #define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE		0x8
 #define IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE	0x23
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index d81a50dc9535..0be13a90ff79 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -72,13 +72,13 @@
 #define IXGBE_INCPER_SHIFT_82599 24
 
 #define IXGBE_OVERFLOW_PERIOD    (HZ * 30)
-#define IXGBE_PTP_TX_TIMEOUT     (HZ * 15)
+#define IXGBE_PTP_TX_TIMEOUT     (HZ)
 
-/* half of a one second clock period, for use with PPS signal. We have to use
- * this instead of something pre-defined like IXGBE_PTP_PPS_HALF_SECOND, in
- * order to force at least 64bits of precision for shifting
+/* We use our own definitions instead of NSEC_PER_SEC because we want to mark
+ * the value as a ULL to force precision when bit shifting.
  */
-#define IXGBE_PTP_PPS_HALF_SECOND 500000000ULL
+#define NS_PER_SEC      1000000000ULL
+#define NS_PER_HALF_SEC  500000000ULL
 
 /* In contrast, the X550 controller has two registers, SYSTIMEH and SYSTIMEL
  * which contain measurements of seconds and nanoseconds respectively. This
@@ -141,23 +141,26 @@
 #define MAX_TIMADJ	0x7FFFFFFF
 
 /**
- * ixgbe_ptp_setup_sdp_x540
+ * ixgbe_ptp_setup_sdp_X540
  * @adapter: private adapter structure
  *
  * this function enables or disables the clock out feature on SDP0 for
- * the X540 device. It will create a 1second periodic output that can
+ * the X540 device. It will create a 1 second periodic output that can
  * be used as the PPS (via an interrupt).
  *
- * It calculates when the systime will be on an exact second, and then
- * aligns the start of the PPS signal to that value. The shift is
- * necessary because it can change based on the link speed.
+ * It calculates when the system time will be on an exact second, and then
+ * aligns the start of the PPS signal to that value.
+ *
+ * This works by using the cycle counter shift and mult values in reverse, and
+ * assumes that the values we're shifting will not overflow.
  */
-static void ixgbe_ptp_setup_sdp_x540(struct ixgbe_adapter *adapter)
+static void ixgbe_ptp_setup_sdp_X540(struct ixgbe_adapter *adapter)
 {
+	struct cyclecounter *cc = &adapter->hw_cc;
 	struct ixgbe_hw *hw = &adapter->hw;
-	int shift = adapter->hw_cc.shift;
 	u32 esdp, tsauxc, clktiml, clktimh, trgttiml, trgttimh, rem;
-	u64 ns = 0, clock_edge = 0;
+	u64 ns = 0, clock_edge = 0, clock_period;
+	unsigned long flags;
 
 	/* disable the pin first */
 	IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0);
@@ -177,26 +180,33 @@ static void ixgbe_ptp_setup_sdp_x540(struct ixgbe_adapter *adapter)
 	/* enable the Clock Out feature on SDP0, and allow
 	 * interrupts to occur when the pin changes
 	 */
-	tsauxc = IXGBE_TSAUXC_EN_CLK |
-		 IXGBE_TSAUXC_SYNCLK |
-		 IXGBE_TSAUXC_SDP0_INT;
+	tsauxc = (IXGBE_TSAUXC_EN_CLK |
+		  IXGBE_TSAUXC_SYNCLK |
+		  IXGBE_TSAUXC_SDP0_INT);
 
-	/* clock period (or pulse length) */
-	clktiml = (u32)(IXGBE_PTP_PPS_HALF_SECOND << shift);
-	clktimh = (u32)((IXGBE_PTP_PPS_HALF_SECOND << shift) >> 32);
-
-	/* Account for the cyclecounter wrap-around value by
-	 * using the converted ns value of the current time to
-	 * check for when the next aligned second would occur.
+	/* Determine the clock time period to use. This assumes that the
+	 * cycle counter shift is small enough to avoid overflow.
 	 */
-	clock_edge |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIML);
-	clock_edge |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32;
-	ns = timecounter_cyc2time(&adapter->hw_tc, clock_edge);
+	clock_period = div_u64((NS_PER_HALF_SEC << cc->shift), cc->mult);
+	clktiml = (u32)(clock_period);
+	clktimh = (u32)(clock_period >> 32);
 
-	div_u64_rem(ns, IXGBE_PTP_PPS_HALF_SECOND, &rem);
-	clock_edge += ((IXGBE_PTP_PPS_HALF_SECOND - (u64)rem) << shift);
+	/* Read the current clock time, and save the cycle counter value */
+	spin_lock_irqsave(&adapter->tmreg_lock, flags);
+	ns = timecounter_read(&adapter->hw_tc);
+	clock_edge = adapter->hw_tc.cycle_last;
+	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
+	/* Figure out how many seconds to add in order to round up */
+	div_u64_rem(ns, NS_PER_SEC, &rem);
+
+	/* Figure out how many nanoseconds to add to round the clock edge up
+	 * to the next full second
+	 */
+	rem = (NS_PER_SEC - rem);
 
-	/* specify the initial clock start time */
+	/* Adjust the clock edge to align with the next full second. */
+	clock_edge += div_u64(((u64)rem << cc->shift), cc->mult);
 	trgttiml = (u32)clock_edge;
 	trgttimh = (u32)(clock_edge >> 32);
 
@@ -212,8 +222,100 @@ static void ixgbe_ptp_setup_sdp_x540(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_ptp_setup_sdp_X550
+ * @adapter: private adapter structure
+ *
+ * Enable or disable a clock output signal on SDP 0 for X550 hardware.
+ *
+ * Use the target time feature to align the output signal on the next full
+ * second.
+ *
+ * This works by using the cycle counter shift and mult values in reverse, and
+ * assumes that the values we're shifting will not overflow.
+ */
+static void ixgbe_ptp_setup_sdp_X550(struct ixgbe_adapter *adapter)
+{
+	u32 esdp, tsauxc, freqout, trgttiml, trgttimh, rem, tssdp;
+	struct cyclecounter *cc = &adapter->hw_cc;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u64 ns = 0, clock_edge = 0;
+	struct timespec64 ts;
+	unsigned long flags;
+
+	/* disable the pin first */
+	IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0);
+	IXGBE_WRITE_FLUSH(hw);
+
+	if (!(adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED))
+		return;
+
+	esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
+
+	/* enable the SDP0 pin as output, and connected to the
+	 * native function for Timesync (ClockOut)
+	 */
+	esdp |= IXGBE_ESDP_SDP0_DIR |
+		IXGBE_ESDP_SDP0_NATIVE;
+
+	/* enable the Clock Out feature on SDP0, and use Target Time 0 to
+	 * enable generation of interrupts on the clock change.
+	 */
+#define IXGBE_TSAUXC_DIS_TS_CLEAR 0x40000000
+	tsauxc = (IXGBE_TSAUXC_EN_CLK | IXGBE_TSAUXC_ST0 |
+		  IXGBE_TSAUXC_EN_TT0 | IXGBE_TSAUXC_SDP0_INT |
+		  IXGBE_TSAUXC_DIS_TS_CLEAR);
+
+	tssdp = (IXGBE_TSSDP_TS_SDP0_EN |
+		 IXGBE_TSSDP_TS_SDP0_CLK0);
+
+	/* Determine the clock time period to use. This assumes that the
+	 * cycle counter shift is small enough to avoid overflowing a 32bit
+	 * value.
+	 */
+	freqout = div_u64(NS_PER_HALF_SEC << cc->shift,  cc->mult);
+
+	/* Read the current clock time, and save the cycle counter value */
+	spin_lock_irqsave(&adapter->tmreg_lock, flags);
+	ns = timecounter_read(&adapter->hw_tc);
+	clock_edge = adapter->hw_tc.cycle_last;
+	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
+	/* Figure out how far past the next second we are */
+	div_u64_rem(ns, NS_PER_SEC, &rem);
+
+	/* Figure out how many nanoseconds to add to round the clock edge up
+	 * to the next full second
+	 */
+	rem = (NS_PER_SEC - rem);
+
+	/* Adjust the clock edge to align with the next full second. */
+	clock_edge += div_u64(((u64)rem << cc->shift), cc->mult);
+
+	/* X550 hardware stores the time in 32bits of 'billions of cycles' and
+	 * 32bits of 'cycles'. There's no guarantee that cycles represents
+	 * nanoseconds. However, we can use the math from a timespec64 to
+	 * convert into the hardware representation.
+	 *
+	 * See ixgbe_ptp_read_X550() for more details.
+	 */
+	ts = ns_to_timespec64(clock_edge);
+	trgttiml = (u32)ts.tv_nsec;
+	trgttimh = (u32)ts.tv_sec;
+
+	IXGBE_WRITE_REG(hw, IXGBE_FREQOUT0, freqout);
+	IXGBE_WRITE_REG(hw, IXGBE_TRGTTIML0, trgttiml);
+	IXGBE_WRITE_REG(hw, IXGBE_TRGTTIMH0, trgttimh);
+
+	IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp);
+	IXGBE_WRITE_REG(hw, IXGBE_TSSDP, tssdp);
+	IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, tsauxc);
+
+	IXGBE_WRITE_FLUSH(hw);
+}
+
+/**
  * ixgbe_ptp_read_X550 - read cycle counter value
- * @hw_cc: cyclecounter structure
+ * @cc: cyclecounter structure
  *
  * This function reads SYSTIME registers. It is called by the cyclecounter
  * structure to convert from internal representation into nanoseconds. We need
@@ -221,10 +323,10 @@ static void ixgbe_ptp_setup_sdp_x540(struct ixgbe_adapter *adapter)
  * result of SYSTIME is 32bits of "billions of cycles" and 32 bits of
  * "cycles", rather than seconds and nanoseconds.
  */
-static u64 ixgbe_ptp_read_X550(const struct cyclecounter *hw_cc)
+static u64 ixgbe_ptp_read_X550(const struct cyclecounter *cc)
 {
 	struct ixgbe_adapter *adapter =
-			container_of(hw_cc, struct ixgbe_adapter, hw_cc);
+		container_of(cc, struct ixgbe_adapter, hw_cc);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct timespec64 ts;
 
@@ -838,6 +940,15 @@ void ixgbe_ptp_rx_rgtstamp(struct ixgbe_q_vector *q_vector,
 	ixgbe_ptp_convert_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
 }
 
+/**
+ * ixgbe_ptp_get_ts_config - get current hardware timestamping configuration
+ * @adapter: pointer to adapter structure
+ * @ifr: ioctl data
+ *
+ * This function returns the current timestamping settings. Rather than
+ * attempt to deconstruct registers to fill in the values, simply keep a copy
+ * of the old settings around, and return a copy when requested.
+ */
 int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
 {
 	struct hwtstamp_config *config = &adapter->tstamp_config;
@@ -1253,7 +1364,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
-		adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_x540;
+		adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_X540;
 		break;
 	case ixgbe_mac_82599EB:
 		snprintf(adapter->ptp_caps.name,
@@ -1280,13 +1391,13 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.n_alarm = 0;
 		adapter->ptp_caps.n_ext_ts = 0;
 		adapter->ptp_caps.n_per_out = 0;
-		adapter->ptp_caps.pps = 0;
+		adapter->ptp_caps.pps = 1;
 		adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_X550;
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
 		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
-		adapter->ptp_setup_sdp = NULL;
+		adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_X550;
 		break;
 	default:
 		adapter->ptp_clock = NULL;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 345701af7749..537dfff585e0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -1645,7 +1645,7 @@ int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
 		IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_LLDP),
 				(IXGBE_ETQF_FILTER_EN    |
 				 IXGBE_ETQF_TX_ANTISPOOF |
-				 IXGBE_ETH_P_LLDP));
+				 ETH_P_LLDP));
 
 		IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FC),
 				(IXGBE_ETQF_FILTER_EN |
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index 53d4089f5644..d93a690aff74 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -30,8 +30,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring);
 
 struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
 				struct ixgbe_ring *ring);
-int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem,
-			 u16 qid);
 int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
 			 u16 qid);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 84f2dba39e36..2be1c4c72435 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -1067,6 +1067,7 @@ struct ixgbe_nvm_version {
 #define IXGBE_AUXSTMPL1  0x08C44 /* Auxiliary Time Stamp 1 register Low - RO */
 #define IXGBE_AUXSTMPH1  0x08C48 /* Auxiliary Time Stamp 1 register High - RO */
 #define IXGBE_TSIM       0x08C68 /* TimeSync Interrupt Mask Register - RW */
+#define IXGBE_TSSDP      0x0003C /* TimeSync SDP Configuration Register - RW */
 
 /* Diagnostic Registers */
 #define IXGBE_RDSTATCTL   0x02C20
@@ -2240,11 +2241,18 @@ enum {
 #define IXGBE_RXDCTL_RLPML_EN   0x00008000
 #define IXGBE_RXDCTL_VME        0x40000000  /* VLAN mode enable */
 
-#define IXGBE_TSAUXC_EN_CLK   0x00000004
-#define IXGBE_TSAUXC_SYNCLK   0x00000008
-#define IXGBE_TSAUXC_SDP0_INT 0x00000040
+#define IXGBE_TSAUXC_EN_CLK		0x00000004
+#define IXGBE_TSAUXC_SYNCLK		0x00000008
+#define IXGBE_TSAUXC_SDP0_INT		0x00000040
+#define IXGBE_TSAUXC_EN_TT0		0x00000001
+#define IXGBE_TSAUXC_EN_TT1		0x00000002
+#define IXGBE_TSAUXC_ST0		0x00000010
 #define IXGBE_TSAUXC_DISABLE_SYSTIME	0x80000000
 
+#define IXGBE_TSSDP_TS_SDP0_SEL_MASK	0x000000C0
+#define IXGBE_TSSDP_TS_SDP0_CLK0	0x00000080
+#define IXGBE_TSSDP_TS_SDP0_EN		0x00000100
+
 #define IXGBE_TSYNCTXCTL_VALID		0x00000001 /* Tx timestamp valid */
 #define IXGBE_TSYNCTXCTL_ENABLED	0x00000010 /* Tx timestamping enabled */
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 65c3e2c979d4..6b609553329f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -14,57 +14,10 @@ struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
 	bool xdp_on = READ_ONCE(adapter->xdp_prog);
 	int qid = ring->ring_idx;
 
-	if (!adapter->xsk_umems || !adapter->xsk_umems[qid] ||
-	    qid >= adapter->num_xsk_umems || !xdp_on)
+	if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps))
 		return NULL;
 
-	return adapter->xsk_umems[qid];
-}
-
-static int ixgbe_alloc_xsk_umems(struct ixgbe_adapter *adapter)
-{
-	if (adapter->xsk_umems)
-		return 0;
-
-	adapter->num_xsk_umems_used = 0;
-	adapter->num_xsk_umems = adapter->num_rx_queues;
-	adapter->xsk_umems = kcalloc(adapter->num_xsk_umems,
-				     sizeof(*adapter->xsk_umems),
-				     GFP_KERNEL);
-	if (!adapter->xsk_umems) {
-		adapter->num_xsk_umems = 0;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static int ixgbe_add_xsk_umem(struct ixgbe_adapter *adapter,
-			      struct xdp_umem *umem,
-			      u16 qid)
-{
-	int err;
-
-	err = ixgbe_alloc_xsk_umems(adapter);
-	if (err)
-		return err;
-
-	adapter->xsk_umems[qid] = umem;
-	adapter->num_xsk_umems_used++;
-
-	return 0;
-}
-
-static void ixgbe_remove_xsk_umem(struct ixgbe_adapter *adapter, u16 qid)
-{
-	adapter->xsk_umems[qid] = NULL;
-	adapter->num_xsk_umems_used--;
-
-	if (adapter->num_xsk_umems == 0) {
-		kfree(adapter->xsk_umems);
-		adapter->xsk_umems = NULL;
-		adapter->num_xsk_umems = 0;
-	}
+	return xdp_get_umem_from_qid(adapter->netdev, qid);
 }
 
 static int ixgbe_xsk_umem_dma_map(struct ixgbe_adapter *adapter,
@@ -113,6 +66,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 				 struct xdp_umem *umem,
 				 u16 qid)
 {
+	struct net_device *netdev = adapter->netdev;
 	struct xdp_umem_fq_reuse *reuseq;
 	bool if_running;
 	int err;
@@ -120,12 +74,9 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 	if (qid >= adapter->num_rx_queues)
 		return -EINVAL;
 
-	if (adapter->xsk_umems) {
-		if (qid >= adapter->num_xsk_umems)
-			return -EINVAL;
-		if (adapter->xsk_umems[qid])
-			return -EBUSY;
-	}
+	if (qid >= netdev->real_num_rx_queues ||
+	    qid >= netdev->real_num_tx_queues)
+		return -EINVAL;
 
 	reuseq = xsk_reuseq_prepare(adapter->rx_ring[0]->count);
 	if (!reuseq)
@@ -138,35 +89,42 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 		return err;
 
 	if_running = netif_running(adapter->netdev) &&
-		     READ_ONCE(adapter->xdp_prog);
+		     ixgbe_enabled_xdp_adapter(adapter);
 
 	if (if_running)
 		ixgbe_txrx_ring_disable(adapter, qid);
 
-	err = ixgbe_add_xsk_umem(adapter, umem, qid);
+	set_bit(qid, adapter->af_xdp_zc_qps);
 
-	if (if_running)
+	if (if_running) {
 		ixgbe_txrx_ring_enable(adapter, qid);
 
-	return err;
+		/* Kick start the NAPI context so that receiving will start */
+		err = ixgbe_xsk_async_xmit(adapter->netdev, qid);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
 {
+	struct xdp_umem *umem;
 	bool if_running;
 
-	if (!adapter->xsk_umems || qid >= adapter->num_xsk_umems ||
-	    !adapter->xsk_umems[qid])
+	umem = xdp_get_umem_from_qid(adapter->netdev, qid);
+	if (!umem)
 		return -EINVAL;
 
 	if_running = netif_running(adapter->netdev) &&
-		     READ_ONCE(adapter->xdp_prog);
+		     ixgbe_enabled_xdp_adapter(adapter);
 
 	if (if_running)
 		ixgbe_txrx_ring_disable(adapter, qid);
 
-	ixgbe_xsk_umem_dma_unmap(adapter, adapter->xsk_umems[qid]);
-	ixgbe_remove_xsk_umem(adapter, qid);
+	clear_bit(qid, adapter->af_xdp_zc_qps);
+	ixgbe_xsk_umem_dma_unmap(adapter, umem);
 
 	if (if_running)
 		ixgbe_txrx_ring_enable(adapter, qid);
@@ -174,23 +132,6 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
 	return 0;
 }
 
-int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem,
-			 u16 qid)
-{
-	if (qid >= adapter->num_rx_queues)
-		return -EINVAL;
-
-	if (adapter->xsk_umems) {
-		if (qid >= adapter->num_xsk_umems)
-			return -EINVAL;
-		*umem = adapter->xsk_umems[qid];
-		return 0;
-	}
-
-	*umem = NULL;
-	return 0;
-}
-
 int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
 			 u16 qid)
 {
@@ -630,24 +571,29 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	union ixgbe_adv_tx_desc *tx_desc = NULL;
 	struct ixgbe_tx_buffer *tx_bi;
 	bool work_done = true;
-	u32 len, cmd_type;
+	struct xdp_desc desc;
 	dma_addr_t dma;
+	u32 cmd_type;
 
 	while (budget-- > 0) {
-		if (unlikely(!ixgbe_desc_unused(xdp_ring))) {
+		if (unlikely(!ixgbe_desc_unused(xdp_ring)) ||
+		    !netif_carrier_ok(xdp_ring->netdev)) {
 			work_done = false;
 			break;
 		}
 
-		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len))
+		if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc))
 			break;
 
-		dma_sync_single_for_device(xdp_ring->dev, dma, len,
+		dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr);
+
+		dma_sync_single_for_device(xdp_ring->dev, dma, desc.len,
 					   DMA_BIDIRECTIONAL);
 
 		tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use];
-		tx_bi->bytecount = len;
+		tx_bi->bytecount = desc.len;
 		tx_bi->xdpf = NULL;
+		tx_bi->gso_segs = 1;
 
 		tx_desc = IXGBE_TX_DESC(xdp_ring, xdp_ring->next_to_use);
 		tx_desc->read.buffer_addr = cpu_to_le64(dma);
@@ -656,10 +602,10 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 		cmd_type = IXGBE_ADVTXD_DTYP_DATA |
 			   IXGBE_ADVTXD_DCMD_DEXT |
 			   IXGBE_ADVTXD_DCMD_IFCS;
-		cmd_type |= len | IXGBE_TXD_CMD;
+		cmd_type |= desc.len | IXGBE_TXD_CMD;
 		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
 		tx_desc->read.olinfo_status =
-			cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT);
+			cpu_to_le32(desc.len << IXGBE_ADVTXD_PAYLEN_SHIFT);
 
 		xdp_ring->next_to_use++;
 		if (xdp_ring->next_to_use == xdp_ring->count)
@@ -712,7 +658,6 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 			xsk_frames++;
 
 		tx_bi->xdpf = NULL;
-		total_bytes += tx_bi->bytecount;
 
 		tx_bi++;
 		tx_desc++;
@@ -761,7 +706,7 @@ int ixgbe_xsk_async_xmit(struct net_device *dev, u32 qid)
 	if (qid >= adapter->num_xdp_queues)
 		return -ENXIO;
 
-	if (!adapter->xsk_umems || !adapter->xsk_umems[qid])
+	if (!adapter->xdp_ring[qid]->xsk_umem)
 		return -ENXIO;
 
 	ring = adapter->xdp_ring[qid];
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 5399787e07af..54459b69c948 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -85,22 +85,16 @@ static int ixgbevf_get_link_ksettings(struct net_device *netdev,
 				      struct ethtool_link_ksettings *cmd)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
-	struct ixgbe_hw *hw = &adapter->hw;
-	u32 link_speed = 0;
-	bool link_up;
 
 	ethtool_link_ksettings_zero_link_mode(cmd, supported);
 	ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full);
 	cmd->base.autoneg = AUTONEG_DISABLE;
 	cmd->base.port = -1;
 
-	hw->mac.get_link_status = 1;
-	hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
-
-	if (link_up) {
+	if (adapter->link_up) {
 		__u32 speed = SPEED_10000;
 
-		switch (link_speed) {
+		switch (adapter->link_speed) {
 		case IXGBE_LINK_SPEED_10GB_FULL:
 			speed = SPEED_10000;
 			break;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 49e23afa05a2..d2b41f9f87f8 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -895,7 +895,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IXGBEVF_RX_HDR_SIZE)
-		headlen = eth_get_headlen(xdp->data, IXGBEVF_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, xdp->data,
+					  IXGBEVF_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), xdp->data,
@@ -1422,6 +1423,9 @@ static void ixgbevf_update_itr(struct ixgbevf_q_vector *q_vector,
 	 */
 	/* what was last interrupt timeslice? */
 	timepassed_us = q_vector->itr >> 2;
+	if (timepassed_us == 0)
+		return;
+
 	bytes_perint = bytes / timepassed_us; /* bytes/usec */
 
 	switch (itr_setting) {
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index cd3b81300cc7..d5ce49636548 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -508,9 +508,8 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw,
 		vector_list[i++] = ixgbevf_mta_vector(hw, ha->addr);
 	}
 
-	ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, IXGBE_VFMAILBOX_SIZE);
-
-	return 0;
+	return ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf,
+			IXGBE_VFMAILBOX_SIZE);
 }
 
 /**
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index a5ab6f3403ae..76b7b7b85e35 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * JMicron JMC2x0 series PCIe Ethernet Linux Device Driver
  *
@@ -6,20 +7,6 @@
  * Copyright (c) 2009 - 2010 Guo-Fu Tseng <cooldavid@cooldavid.org>
  *
  * Author: Guo-Fu Tseng <cooldavid@cooldavid.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -2034,10 +2021,9 @@ static void jme_drop_tx_map(struct jme_adapter *jme, int startidx, int count)
 				ctxbi->len,
 				PCI_DMA_TODEVICE);
 
-				ctxbi->mapping = 0;
-				ctxbi->len = 0;
+		ctxbi->mapping = 0;
+		ctxbi->len = 0;
 	}
-
 }
 
 static int
diff --git a/drivers/net/ethernet/jme.h b/drivers/net/ethernet/jme.h
index 89535c019f04..2bba5ce20289 100644
--- a/drivers/net/ethernet/jme.h
+++ b/drivers/net/ethernet/jme.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * JMicron JMC2x0 series PCIe Ethernet Linux Device Driver
  *
@@ -6,20 +7,6 @@
  * Copyright (c) 2009 - 2010 Guo-Fu Tseng <cooldavid@cooldavid.org>
  *
  * Author: Guo-Fu Tseng <cooldavid@cooldavid.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
  */
 
 #ifndef __JME_H_INCLUDED__
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 32ac9045cdae..6e73ffe6f928 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -1,15 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
- *   This program is free software; you can redistribute it and/or modify it
- *   under the terms of the GNU General Public License version 2 as published
- *   by the Free Software Foundation.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, see <http://www.gnu.org/licenses/>.
  *
  *   Copyright (C) 2011 John Crispin <blogic@openwrt.org>
  */
@@ -112,10 +102,12 @@ struct ltq_etop_priv {
 static int
 ltq_etop_alloc_skb(struct ltq_etop_chan *ch)
 {
+	struct ltq_etop_priv *priv = netdev_priv(ch->netdev);
+
 	ch->skb[ch->dma.desc] = netdev_alloc_skb(ch->netdev, MAX_DMA_DATA_LEN);
 	if (!ch->skb[ch->dma.desc])
 		return -ENOMEM;
-	ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(NULL,
+	ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(&priv->pdev->dev,
 		ch->skb[ch->dma.desc]->data, MAX_DMA_DATA_LEN,
 		DMA_FROM_DEVICE);
 	ch->dma.desc_base[ch->dma.desc].addr =
@@ -487,7 +479,7 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev)
 	netif_trans_update(dev);
 
 	spin_lock_irqsave(&priv->lock, flags);
-	desc->addr = ((unsigned int) dma_map_single(NULL, skb->data, len,
+	desc->addr = ((unsigned int) dma_map_single(&priv->pdev->dev, skb->data, len,
 						DMA_TO_DEVICE)) - byte_offset;
 	wmb();
 	desc->ctl = LTQ_DMA_OWN | LTQ_DMA_SOP | LTQ_DMA_EOP |
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 2d4d10a017e5..cda641ef89af 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -335,7 +335,6 @@ static const struct net_device_ops xrx200_netdev_ops = {
 	.ndo_start_xmit		= xrx200_start_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_change_mtu		= eth_change_mtu,
 };
 
 static irqreturn_t xrx200_dma_irq(int irq, void *ptr)
@@ -479,7 +478,7 @@ static int xrx200_probe(struct platform_device *pdev)
 	}
 
 	mac = of_get_mac_address(np);
-	if (mac && is_valid_ether_addr(mac))
+	if (!IS_ERR(mac))
 		ether_addr_copy(net_dev->dev_addr, mac);
 	else
 		eth_hw_addr_random(net_dev);
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index 3238aa7f5dac..fb942167ee54 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Marvell device configuration
 #
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 2f427271a793..88ea5ac83c93 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Driver for Marvell Discovery (MV643XX) and Marvell Orion ethernet ports
  * Copyright (C) 2002 Matthew Dharm <mdharm@momenco.com>
@@ -21,19 +22,6 @@
  *			   Lennert Buytenhek <buytenh@marvell.com>
  *
  * Copyright (C) 2013 Michael Stapelberg <michael@stapelberg.de>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -2749,8 +2737,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev,
 	}
 
 	mac_addr = of_get_mac_address(pnp);
-	if (mac_addr)
-		memcpy(ppd.mac_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(ppd.mac_addr, mac_addr);
 
 	mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size);
 	mv643xx_eth_property(pnp, "tx-sram-addr", ppd.tx_sram_addr);
@@ -2879,7 +2867,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev)
 
 	ret = mv643xx_eth_shared_of_probe(pdev);
 	if (ret)
-		return ret;
+		goto err_put_clk;
 	pd = dev_get_platdata(&pdev->dev);
 
 	msp->tx_csum_limit = (pd != NULL && pd->tx_csum_limit) ?
@@ -2887,6 +2875,11 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev)
 	infer_hw_params(msp);
 
 	return 0;
+
+err_put_clk:
+	if (!IS_ERR(msp->clk))
+		clk_disable_unprepare(msp->clk);
+	return ret;
 }
 
 static int mv643xx_eth_shared_remove(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index c5dac6bd2be4..f660cc2b8258 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -64,7 +64,7 @@
 
 struct orion_mdio_dev {
 	void __iomem *regs;
-	struct clk *clk[3];
+	struct clk *clk[4];
 	/*
 	 * If we have access to the error interrupt pin (which is
 	 * somewhat misnamed as it not only reflects internal errors
@@ -321,11 +321,19 @@ static int orion_mdio_probe(struct platform_device *pdev)
 
 	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
 		dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
+		if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto out_clk;
+		}
 		if (IS_ERR(dev->clk[i]))
 			break;
 		clk_prepare_enable(dev->clk[i]);
 	}
 
+	if (!IS_ERR(of_clk_get(pdev->dev.of_node, ARRAY_SIZE(dev->clk))))
+		dev_warn(&pdev->dev, "unsupported number of clocks, limiting to the first "
+			 __stringify(ARRAY_SIZE(dev->clk)) "\n");
+
 	dev->err_interrupt = platform_get_irq(pdev, 0);
 	if (dev->err_interrupt > 0 &&
 	    resource_size(r) < MVMDIO_ERR_INT_MASK + 4) {
@@ -362,6 +370,7 @@ out_mdio:
 	if (dev->err_interrupt > 0)
 		writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
 
+out_clk:
 	for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
 		if (IS_ERR(dev->clk[i]))
 			break;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 9d4568eb2297..895bfed26a8a 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -27,6 +27,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
+#include <linux/phy/phy.h>
 #include <linux/phy.h>
 #include <linux/phylink.h>
 #include <linux/platform_device.h>
@@ -436,6 +437,8 @@ struct mvneta_port {
 	struct device_node *dn;
 	unsigned int tx_csum_limit;
 	struct phylink *phylink;
+	struct phylink_config phylink_config;
+	struct phy *comphy;
 
 	struct mvneta_bm *bm_priv;
 	struct mvneta_bm_pool *pool_long;
@@ -1116,7 +1119,7 @@ static void mvneta_bm_update_mtu(struct mvneta_port *pp, int mtu)
 			SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(bm_pool->pkt_size));
 
 	/* Fill entire long pool */
-	num = hwbm_pool_add(hwbm_pool, hwbm_pool->size, GFP_ATOMIC);
+	num = hwbm_pool_add(hwbm_pool, hwbm_pool->size);
 	if (num != hwbm_pool->size) {
 		WARN(1, "pool %d: %d of %d allocated\n",
 		     bm_pool->id, num, hwbm_pool->size);
@@ -2146,7 +2149,7 @@ err_drop_frame:
 			if (unlikely(!skb))
 				goto err_drop_frame_ret_pool;
 
-			dma_sync_single_range_for_cpu(dev->dev.parent,
+			dma_sync_single_range_for_cpu(&pp->bm_priv->pdev->dev,
 			                              rx_desc->buf_phys_addr,
 			                              MVNETA_MH_SIZE + NET_SKB_PAD,
 			                              rx_bytes,
@@ -2465,7 +2468,7 @@ out:
 		if (txq->count >= txq->tx_stop_threshold)
 			netif_tx_stop_queue(nq);
 
-		if (!skb->xmit_more || netif_xmit_stopped(nq) ||
+		if (!netdev_xmit_more() || netif_xmit_stopped(nq) ||
 		    txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
 			mvneta_txq_pend_desc_add(pp, txq, frags);
 		else
@@ -3147,10 +3150,27 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
 	return 0;
 }
 
+static int mvneta_comphy_init(struct mvneta_port *pp)
+{
+	int ret;
+
+	if (!pp->comphy)
+		return 0;
+
+	ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET,
+			       pp->phy_interface);
+	if (ret)
+		return ret;
+
+	return phy_power_on(pp->comphy);
+}
+
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
 	int cpu;
 
+	WARN_ON(mvneta_comphy_init(pp));
+
 	mvneta_max_rx_size_set(pp, pp->pkt_size);
 	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
 
@@ -3213,6 +3233,8 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 
 	mvneta_tx_reset(pp);
 	mvneta_rx_reset(pp);
+
+	WARN_ON(phy_power_off(pp->comphy));
 }
 
 static void mvneta_percpu_enable(void *arg)
@@ -3335,9 +3357,12 @@ static int mvneta_set_mac_addr(struct net_device *dev, void *addr)
 	return 0;
 }
 
-static void mvneta_validate(struct net_device *ndev, unsigned long *supported,
+static void mvneta_validate(struct phylink_config *config,
+			    unsigned long *supported,
 			    struct phylink_link_state *state)
 {
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct mvneta_port *pp = netdev_priv(ndev);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 
 	/* We only support QSGMII, SGMII, 802.3z and RGMII modes */
@@ -3358,8 +3383,14 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported,
 	phylink_set(mask, Pause);
 
 	/* Half-duplex at speeds higher than 100Mbit is unsupported */
-	phylink_set(mask, 1000baseT_Full);
-	phylink_set(mask, 1000baseX_Full);
+	if (pp->comphy || state->interface != PHY_INTERFACE_MODE_2500BASEX) {
+		phylink_set(mask, 1000baseT_Full);
+		phylink_set(mask, 1000baseX_Full);
+	}
+	if (pp->comphy || state->interface == PHY_INTERFACE_MODE_2500BASEX) {
+		phylink_set(mask, 2500baseT_Full);
+		phylink_set(mask, 2500baseX_Full);
+	}
 
 	if (!phy_interface_mode_is_8023z(state->interface)) {
 		/* 10M and 100M are only supported in non-802.3z mode */
@@ -3373,18 +3404,26 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported,
 		   __ETHTOOL_LINK_MODE_MASK_NBITS);
 	bitmap_and(state->advertising, state->advertising, mask,
 		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+	/* We can only operate at 2500BaseX or 1000BaseX.  If requested
+	 * to advertise both, only report advertising at 2500BaseX.
+	 */
+	phylink_helper_basex_speed(state);
 }
 
-static int mvneta_mac_link_state(struct net_device *ndev,
+static int mvneta_mac_link_state(struct phylink_config *config,
 				 struct phylink_link_state *state)
 {
+	struct net_device *ndev = to_net_dev(config->dev);
 	struct mvneta_port *pp = netdev_priv(ndev);
 	u32 gmac_stat;
 
 	gmac_stat = mvreg_read(pp, MVNETA_GMAC_STATUS);
 
 	if (gmac_stat & MVNETA_GMAC_SPEED_1000)
-		state->speed = SPEED_1000;
+		state->speed =
+			state->interface == PHY_INTERFACE_MODE_2500BASEX ?
+			SPEED_2500 : SPEED_1000;
 	else if (gmac_stat & MVNETA_GMAC_SPEED_100)
 		state->speed = SPEED_100;
 	else
@@ -3403,8 +3442,9 @@ static int mvneta_mac_link_state(struct net_device *ndev,
 	return 1;
 }
 
-static void mvneta_mac_an_restart(struct net_device *ndev)
+static void mvneta_mac_an_restart(struct phylink_config *config)
 {
+	struct net_device *ndev = to_net_dev(config->dev);
 	struct mvneta_port *pp = netdev_priv(ndev);
 	u32 gmac_an = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
 
@@ -3414,9 +3454,10 @@ static void mvneta_mac_an_restart(struct net_device *ndev)
 		    gmac_an & ~MVNETA_GMAC_INBAND_RESTART_AN);
 }
 
-static void mvneta_mac_config(struct net_device *ndev, unsigned int mode,
-	const struct phylink_link_state *state)
+static void mvneta_mac_config(struct phylink_config *config, unsigned int mode,
+			      const struct phylink_link_state *state)
 {
+	struct net_device *ndev = to_net_dev(config->dev);
 	struct mvneta_port *pp = netdev_priv(ndev);
 	u32 new_ctrl0, gmac_ctrl0 = mvreg_read(pp, MVNETA_GMAC_CTRL_0);
 	u32 new_ctrl2, gmac_ctrl2 = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
@@ -3499,12 +3540,23 @@ static void mvneta_mac_config(struct net_device *ndev, unsigned int mode,
 			    MVNETA_GMAC_FORCE_LINK_DOWN);
 	}
 
+
 	/* When at 2.5G, the link partner can send frames with shortened
 	 * preambles.
 	 */
 	if (state->speed == SPEED_2500)
 		new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE;
 
+	if (pp->comphy && pp->phy_interface != state->interface &&
+	    (state->interface == PHY_INTERFACE_MODE_SGMII ||
+	     state->interface == PHY_INTERFACE_MODE_1000BASEX ||
+	     state->interface == PHY_INTERFACE_MODE_2500BASEX)) {
+		pp->phy_interface = state->interface;
+
+		WARN_ON(phy_power_off(pp->comphy));
+		WARN_ON(mvneta_comphy_init(pp));
+	}
+
 	if (new_ctrl0 != gmac_ctrl0)
 		mvreg_write(pp, MVNETA_GMAC_CTRL_0, new_ctrl0);
 	if (new_ctrl2 != gmac_ctrl2)
@@ -3535,9 +3587,10 @@ static void mvneta_set_eee(struct mvneta_port *pp, bool enable)
 	mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi_ctl1);
 }
 
-static void mvneta_mac_link_down(struct net_device *ndev, unsigned int mode,
-				 phy_interface_t interface)
+static void mvneta_mac_link_down(struct phylink_config *config,
+				 unsigned int mode, phy_interface_t interface)
 {
+	struct net_device *ndev = to_net_dev(config->dev);
 	struct mvneta_port *pp = netdev_priv(ndev);
 	u32 val;
 
@@ -3554,10 +3607,11 @@ static void mvneta_mac_link_down(struct net_device *ndev, unsigned int mode,
 	mvneta_set_eee(pp, false);
 }
 
-static void mvneta_mac_link_up(struct net_device *ndev, unsigned int mode,
+static void mvneta_mac_link_up(struct phylink_config *config, unsigned int mode,
 			       phy_interface_t interface,
 			       struct phy_device *phy)
 {
+	struct net_device *ndev = to_net_dev(config->dev);
 	struct mvneta_port *pp = netdev_priv(ndev);
 	u32 val;
 
@@ -4404,7 +4458,7 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	if (phy_mode == PHY_INTERFACE_MODE_QSGMII)
 		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO);
 	else if (phy_mode == PHY_INTERFACE_MODE_SGMII ||
-		 phy_mode == PHY_INTERFACE_MODE_1000BASEX)
+		 phy_interface_mode_is_8023z(phy_mode))
 		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
 	else if (!phy_interface_mode_is_rgmii(phy_mode))
 		return -EINVAL;
@@ -4421,6 +4475,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	struct mvneta_port *pp;
 	struct net_device *dev;
 	struct phylink *phylink;
+	struct phy *comphy;
 	const char *dt_mac_addr;
 	char hw_mac_addr[ETH_ALEN];
 	const char *mac_from;
@@ -4429,15 +4484,14 @@ static int mvneta_probe(struct platform_device *pdev)
 	int err;
 	int cpu;
 
-	dev = alloc_etherdev_mqs(sizeof(struct mvneta_port), txq_number, rxq_number);
+	dev = devm_alloc_etherdev_mqs(&pdev->dev, sizeof(struct mvneta_port),
+				      txq_number, rxq_number);
 	if (!dev)
 		return -ENOMEM;
 
 	dev->irq = irq_of_parse_and_map(dn, 0);
-	if (dev->irq == 0) {
-		err = -EINVAL;
-		goto err_free_netdev;
-	}
+	if (dev->irq == 0)
+		return -EINVAL;
 
 	phy_mode = of_get_phy_mode(dn);
 	if (phy_mode < 0) {
@@ -4446,8 +4500,22 @@ static int mvneta_probe(struct platform_device *pdev)
 		goto err_free_irq;
 	}
 
-	phylink = phylink_create(dev, pdev->dev.fwnode, phy_mode,
-				 &mvneta_phylink_ops);
+	comphy = devm_of_phy_get(&pdev->dev, dn, NULL);
+	if (comphy == ERR_PTR(-EPROBE_DEFER)) {
+		err = -EPROBE_DEFER;
+		goto err_free_irq;
+	} else if (IS_ERR(comphy)) {
+		comphy = NULL;
+	}
+
+	pp = netdev_priv(dev);
+	spin_lock_init(&pp->lock);
+
+	pp->phylink_config.dev = &dev->dev;
+	pp->phylink_config.type = PHYLINK_NETDEV;
+
+	phylink = phylink_create(&pp->phylink_config, pdev->dev.fwnode,
+				 phy_mode, &mvneta_phylink_ops);
 	if (IS_ERR(phylink)) {
 		err = PTR_ERR(phylink);
 		goto err_free_irq;
@@ -4459,9 +4527,8 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	dev->ethtool_ops = &mvneta_eth_tool_ops;
 
-	pp = netdev_priv(dev);
-	spin_lock_init(&pp->lock);
 	pp->phylink = phylink;
+	pp->comphy = comphy;
 	pp->phy_interface = phy_mode;
 	pp->dn = dn;
 
@@ -4508,9 +4575,9 @@ static int mvneta_probe(struct platform_device *pdev)
 	}
 
 	dt_mac_addr = of_get_mac_address(dn);
-	if (dt_mac_addr) {
+	if (!IS_ERR(dt_mac_addr)) {
 		mac_from = "device tree";
-		memcpy(dev->dev_addr, dt_mac_addr, ETH_ALEN);
+		ether_addr_copy(dev->dev_addr, dt_mac_addr);
 	} else {
 		mvneta_get_mac_addr(pp, hw_mac_addr);
 		if (is_valid_ether_addr(hw_mac_addr)) {
@@ -4619,7 +4686,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	err = register_netdev(dev);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register\n");
-		goto err_free_stats;
+		goto err_netdev;
 	}
 
 	netdev_info(dev, "Using %s mac address %pM\n", mac_from,
@@ -4630,14 +4697,12 @@ static int mvneta_probe(struct platform_device *pdev)
 	return 0;
 
 err_netdev:
-	unregister_netdev(dev);
 	if (pp->bm_priv) {
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short,
 				       1 << pp->id);
 		mvneta_bm_put(pp->bm_priv);
 	}
-err_free_stats:
 	free_percpu(pp->stats);
 err_free_ports:
 	free_percpu(pp->ports);
@@ -4649,8 +4714,6 @@ err_free_phylink:
 		phylink_destroy(pp->phylink);
 err_free_irq:
 	irq_dispose_mapping(dev->irq);
-err_free_netdev:
-	free_netdev(dev);
 	return err;
 }
 
@@ -4667,7 +4730,6 @@ static int mvneta_remove(struct platform_device *pdev)
 	free_percpu(pp->stats);
 	irq_dispose_mapping(dev->irq);
 	phylink_destroy(pp->phylink);
-	free_netdev(dev);
 
 	if (pp->bm_priv) {
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c
index de468e1bdba9..82ee2bcca6fd 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.c
+++ b/drivers/net/ethernet/marvell/mvneta_bm.c
@@ -190,7 +190,7 @@ struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		hwbm_pool->construct = mvneta_bm_construct;
 		hwbm_pool->priv = new_pool;
-		spin_lock_init(&hwbm_pool->lock);
+		mutex_init(&hwbm_pool->buf_lock);
 
 		/* Create new pool */
 		err = mvneta_bm_pool_create(priv, new_pool);
@@ -201,7 +201,7 @@ struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
 		}
 
 		/* Allocate buffers for this pool */
-		num = hwbm_pool_add(hwbm_pool, hwbm_pool->size, GFP_ATOMIC);
+		num = hwbm_pool_add(hwbm_pool, hwbm_pool->size);
 		if (num != hwbm_pool->size) {
 			WARN(1, "pool %d: %d of %d allocated\n",
 			     new_pool->id, num, hwbm_pool->size);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 398328f10743..4d9564ba68f6 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -14,6 +14,7 @@
 #include <linux/netdevice.h>
 #include <linux/phy.h>
 #include <linux/phylink.h>
+#include <net/flow_offload.h>
 
 /* Fifo Registers */
 #define MVPP2_RX_DATA_FIFO_SIZE_REG(port)	(0x00 + 4 * (port))
@@ -101,6 +102,7 @@
 #define MVPP2_CLS_FLOW_TBL1_REG			0x1828
 #define     MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK	0x7
 #define     MVPP2_CLS_FLOW_TBL1_N_FIELDS(x)	(x)
+#define     MVPP2_CLS_FLOW_TBL1_LU_TYPE(lu)	(((lu) & 0x3f) << 3)
 #define     MVPP2_CLS_FLOW_TBL1_PRIO_MASK	0x3f
 #define     MVPP2_CLS_FLOW_TBL1_PRIO(x)		((x) << 9)
 #define     MVPP2_CLS_FLOW_TBL1_SEQ_MASK	0x7
@@ -123,13 +125,18 @@
 #define MVPP22_CLS_C2_TCAM_DATA2		0x1b18
 #define MVPP22_CLS_C2_TCAM_DATA3		0x1b1c
 #define MVPP22_CLS_C2_TCAM_DATA4		0x1b20
+#define     MVPP22_CLS_C2_LU_TYPE(lu)		((lu) & 0x3f)
 #define     MVPP22_CLS_C2_PORT_ID(port)		((port) << 8)
+#define     MVPP22_CLS_C2_PORT_MASK		(0xff << 8)
+#define MVPP22_CLS_C2_TCAM_INV			0x1b24
+#define     MVPP22_CLS_C2_TCAM_INV_BIT		BIT(31)
 #define MVPP22_CLS_C2_HIT_CTR			0x1b50
 #define MVPP22_CLS_C2_ACT			0x1b60
 #define     MVPP22_CLS_C2_ACT_RSS_EN(act)	(((act) & 0x3) << 19)
 #define     MVPP22_CLS_C2_ACT_FWD(act)		(((act) & 0x7) << 13)
 #define     MVPP22_CLS_C2_ACT_QHIGH(act)	(((act) & 0x3) << 11)
 #define     MVPP22_CLS_C2_ACT_QLOW(act)		(((act) & 0x3) << 9)
+#define     MVPP22_CLS_C2_ACT_COLOR(act)	((act) & 0x7)
 #define MVPP22_CLS_C2_ATTR0			0x1b64
 #define     MVPP22_CLS_C2_ATTR0_QHIGH(qh)	(((qh) & 0x1f) << 24)
 #define     MVPP22_CLS_C2_ATTR0_QHIGH_MASK	0x1f
@@ -141,6 +148,8 @@
 #define MVPP22_CLS_C2_ATTR2			0x1b6c
 #define     MVPP22_CLS_C2_ATTR2_RSS_EN		BIT(30)
 #define MVPP22_CLS_C2_ATTR3			0x1b70
+#define MVPP22_CLS_C2_TCAM_CTRL			0x1b90
+#define     MVPP22_CLS_C2_TCAM_BYPASS_FIFO	BIT(0)
 
 /* Descriptor Manager Top Registers */
 #define MVPP2_RXQ_NUM_REG			0x2040
@@ -320,8 +329,26 @@
 #define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK	0xff00
 #define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT	8
 
+/* Packet Processor per-port counters */
+#define MVPP2_OVERRUN_ETH_DROP			0x7000
+#define MVPP2_CLS_ETH_DROP			0x7020
+
 /* Hit counters registers */
 #define MVPP2_CTRS_IDX				0x7040
+#define     MVPP22_CTRS_TX_CTR(port, txq)	((txq) | ((port) << 3) | BIT(7))
+#define MVPP2_TX_DESC_ENQ_CTR			0x7100
+#define MVPP2_TX_DESC_ENQ_TO_DDR_CTR		0x7104
+#define MVPP2_TX_BUFF_ENQ_TO_DDR_CTR		0x7108
+#define MVPP2_TX_DESC_ENQ_HW_FWD_CTR		0x710c
+#define MVPP2_RX_DESC_ENQ_CTR			0x7120
+#define MVPP2_TX_PKTS_DEQ_CTR			0x7130
+#define MVPP2_TX_PKTS_FULL_QUEUE_DROP_CTR	0x7200
+#define MVPP2_TX_PKTS_EARLY_DROP_CTR		0x7204
+#define MVPP2_TX_PKTS_BM_DROP_CTR		0x7208
+#define MVPP2_TX_PKTS_BM_MC_DROP_CTR		0x720c
+#define MVPP2_RX_PKTS_FULL_QUEUE_DROP_CTR	0x7220
+#define MVPP2_RX_PKTS_EARLY_DROP_CTR		0x7224
+#define MVPP2_RX_PKTS_BM_DROP_CTR		0x7228
 #define MVPP2_CLS_DEC_TBL_HIT_CTR		0x7700
 #define MVPP2_CLS_FLOW_TBL_HIT_CTR		0x7704
 
@@ -389,7 +416,7 @@
 #define     MVPP2_GMAC_IN_BAND_AUTONEG		BIT(2)
 #define     MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS	BIT(3)
 #define     MVPP2_GMAC_IN_BAND_RESTART_AN	BIT(4)
-#define     MVPP2_GMAC_CONFIG_MII_SPEED	BIT(5)
+#define     MVPP2_GMAC_CONFIG_MII_SPEED		BIT(5)
 #define     MVPP2_GMAC_CONFIG_GMII_SPEED	BIT(6)
 #define     MVPP2_GMAC_AN_SPEED_EN		BIT(7)
 #define     MVPP2_GMAC_FC_ADV_EN		BIT(9)
@@ -402,8 +429,8 @@
 #define     MVPP2_GMAC_STATUS0_GMII_SPEED	BIT(1)
 #define     MVPP2_GMAC_STATUS0_MII_SPEED	BIT(2)
 #define     MVPP2_GMAC_STATUS0_FULL_DUPLEX	BIT(3)
-#define     MVPP2_GMAC_STATUS0_RX_PAUSE		BIT(6)
-#define     MVPP2_GMAC_STATUS0_TX_PAUSE		BIT(7)
+#define     MVPP2_GMAC_STATUS0_RX_PAUSE		BIT(4)
+#define     MVPP2_GMAC_STATUS0_TX_PAUSE		BIT(5)
 #define     MVPP2_GMAC_STATUS0_AN_COMPLETE	BIT(11)
 #define MVPP2_GMAC_PORT_FIFO_CFG_1_REG		0x1c
 #define     MVPP2_GMAC_TX_FIFO_MIN_TH_OFFS	6
@@ -430,6 +457,8 @@
 #define MVPP22_XLG_CTRL0_REG			0x100
 #define     MVPP22_XLG_CTRL0_PORT_EN		BIT(0)
 #define     MVPP22_XLG_CTRL0_MAC_RESET_DIS	BIT(1)
+#define     MVPP22_XLG_CTRL0_FORCE_LINK_DOWN	BIT(2)
+#define     MVPP22_XLG_CTRL0_FORCE_LINK_PASS	BIT(3)
 #define     MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN	BIT(7)
 #define     MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN	BIT(8)
 #define     MVPP22_XLG_CTRL0_MIB_CNT_DIS	BIT(14)
@@ -481,6 +510,7 @@
 /* XPCS registers. PPv2.2 only */
 #define MVPP22_XPCS_BASE(port)			(0x7400 + (port) * 0x1000)
 #define MVPP22_XPCS_CFG0			0x0
+#define     MVPP22_XPCS_CFG0_RESET_DIS		BIT(0)
 #define     MVPP22_XPCS_CFG0_PCS_MODE(n)	((n) << 3)
 #define     MVPP22_XPCS_CFG0_ACTIVE_LANE(n)	((n) << 5)
 
@@ -549,8 +579,8 @@
 #define MVPP2_MAX_TSO_SEGS		300
 #define MVPP2_MAX_SKB_DESCS		(MVPP2_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
 
-/* Dfault number of RXQs in use */
-#define MVPP2_DEFAULT_RXQ		1
+/* Max number of RXQs per port */
+#define MVPP2_PORT_MAX_RXQ		32
 
 /* Max number of Rx descriptors */
 #define MVPP2_MAX_RXD_MAX		1024
@@ -607,7 +637,14 @@
 #define MVPP2_BIT_TO_WORD(bit)		((bit) / 32)
 #define MVPP2_BIT_IN_WORD(bit)		((bit) % 32)
 
+#define MVPP2_N_PRS_FLOWS		52
+#define MVPP2_N_RFS_ENTRIES_PER_FLOW	4
+
+/* There are 7 supported high-level flows */
+#define MVPP2_N_RFS_RULES		(MVPP2_N_RFS_ENTRIES_PER_FLOW * 7)
+
 /* RSS constants */
+#define MVPP22_N_RSS_TABLES		8
 #define MVPP22_RSS_TABLE_ENTRIES	32
 
 /* IPv6 max L3 address size */
@@ -707,6 +744,11 @@ enum mvpp2_prs_l3_cast {
 #define MVPP2_DESC_DMA_MASK	DMA_BIT_MASK(40)
 
 /* Definitions */
+struct mvpp2_dbgfs_entries;
+
+struct mvpp2_rss_table {
+	u32 indir[MVPP22_RSS_TABLE_ENTRIES];
+};
 
 /* Shared Packet Processor resources */
 struct mvpp2 {
@@ -768,6 +810,12 @@ struct mvpp2 {
 
 	/* Debugfs root entry */
 	struct dentry *dbgfs_dir;
+
+	/* Debugfs entries private data */
+	struct mvpp2_dbgfs_entries *dbgfs_entries;
+
+	/* RSS Indirection tables */
+	struct mvpp2_rss_table *rss_tables[MVPP22_N_RSS_TABLES];
 };
 
 struct mvpp2_pcpu_stats {
@@ -799,11 +847,42 @@ struct mvpp2_queue_vector {
 	struct cpumask *mask;
 };
 
+/* Internal represention of a Flow Steering rule */
+struct mvpp2_rfs_rule {
+	/* Rule location inside the flow*/
+	int loc;
+
+	/* Flow type, such as TCP_V4_FLOW, IP6_FLOW, etc. */
+	int flow_type;
+
+	/* Index of the C2 TCAM entry handling this rule */
+	int c2_index;
+
+	/* Header fields that needs to be extracted to match this flow */
+	u16 hek_fields;
+
+	/* CLS engine : only c2 is supported for now. */
+	u8 engine;
+
+	/* TCAM key and mask for C2-based steering. These fields should be
+	 * encapsulated in a union should we add more engines.
+	 */
+	u64 c2_tcam;
+	u64 c2_tcam_mask;
+
+	struct flow_rule *flow;
+};
+
+struct mvpp2_ethtool_fs {
+	struct mvpp2_rfs_rule rule;
+	struct ethtool_rxnfc rxnfc;
+};
+
 struct mvpp2_port {
 	u8 id;
 
 	/* Index of the port from the "group of ports" complex point
-	 * of view
+	 * of view. This is specific to PPv2.2.
 	 */
 	int gop_id;
 
@@ -854,6 +933,7 @@ struct mvpp2_port {
 
 	phy_interface_t phy_interface;
 	struct phylink *phylink;
+	struct phylink_config phylink_config;
 	struct phy *comphy;
 
 	struct mvpp2_bm_pool *pool_long;
@@ -868,8 +948,14 @@ struct mvpp2_port {
 
 	u32 tx_time_coal;
 
-	/* RSS indirection table */
-	u32 indir[MVPP22_RSS_TABLE_ENTRIES];
+	/* List of steering rules active on that port */
+	struct mvpp2_ethtool_fs *rfs_rules[MVPP2_N_RFS_ENTRIES_PER_FLOW];
+	int n_rfs_rules;
+
+	/* Each port has its own view of the rss contexts, so that it can number
+	 * them from 0
+	 */
+	int rss_ctx[MVPP22_N_RSS_TABLES];
 };
 
 /* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index efdb7a656835..35478cba2aa5 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -22,302 +22,302 @@
 	}							\
 }
 
-static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
+static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
 	/* TCP over IPv4 flows, Not fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP4_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP4_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP4_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* TCP over IPv4 flows, Not fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
-		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
-		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
-		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* TCP over IPv4 flows, fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* TCP over IPv4 flows, fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* UDP over IPv4 flows, Not fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP4_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP4_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP4_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* UDP over IPv4 flows, Not fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
-		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
-		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
-		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* UDP over IPv4 flows, fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* UDP over IPv4 flows, fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* TCP over IPv6 flows, not fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP6_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP6_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* TCP over IPv6 flows, not fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
-		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
-		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* TCP over IPv6 flows, fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP6_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
 		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP6_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
 		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* TCP over IPv6 flows, fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
 		       MVPP2_PRS_RI_L4_TCP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* UDP over IPv6 flows, not fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP6_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_UNTAG,
 		       MVPP22_CLS_HEK_IP6_5T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* UDP over IPv6 flows, not fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
-		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
-		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* UDP over IPv6 flows, fragmented, no vlan tag */
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP6_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
 		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
 		       MVPP22_CLS_HEK_IP6_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
 		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
 
 	/* UDP over IPv6 flows, fragmented, with vlan tag */
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
-	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
-		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
 		       MVPP2_PRS_RI_L4_UDP,
 		       MVPP2_PRS_IP_MASK),
 
 	/* IPv4 flows, no vlan tag */
-	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4,
 		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
-	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT,
 		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
-	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_UNTAG,
 		       MVPP22_CLS_HEK_IP4_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER,
 		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
 
 	/* IPv4 flows, with vlan tag */
-	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4,
 		       MVPP2_PRS_RI_L3_PROTO_MASK),
-	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OPT,
 		       MVPP2_PRS_RI_L3_PROTO_MASK),
-	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
-		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP4_OTHER,
 		       MVPP2_PRS_RI_L3_PROTO_MASK),
 
 	/* IPv6 flows, no vlan tag */
-	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_UNTAG,
 		       MVPP22_CLS_HEK_IP6_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
 		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
-	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_UNTAG,
 		       MVPP22_CLS_HEK_IP6_2T,
 		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
 		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
 
 	/* IPv6 flows, with vlan tag */
-	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
-		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6,
 		       MVPP2_PRS_RI_L3_PROTO_MASK),
-	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
-		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
 		       MVPP2_PRS_RI_L3_IP6,
 		       MVPP2_PRS_RI_L3_PROTO_MASK),
 
 	/* Non IP flow, no vlan tag */
-	MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_UNTAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_UNTAG,
 		       0,
 		       MVPP2_PRS_RI_VLAN_NONE,
 		       MVPP2_PRS_RI_VLAN_MASK),
 	/* Non IP flow, with vlan tag */
-	MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_TAG,
+	MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
 		       MVPP22_CLS_HEK_OPT_VLAN,
 		       0, 0),
 };
@@ -344,9 +344,9 @@ static void mvpp2_cls_flow_write(struct mvpp2 *priv,
 				 struct mvpp2_cls_flow_entry *fe)
 {
 	mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, fe->index);
-	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL0_REG,  fe->data[0]);
-	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL1_REG,  fe->data[1]);
-	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL2_REG,  fe->data[2]);
+	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL0_REG, fe->data[0]);
+	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL1_REG, fe->data[1]);
+	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL2_REG, fe->data[2]);
 }
 
 u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index)
@@ -429,12 +429,6 @@ static void mvpp2_cls_flow_port_id_sel(struct mvpp2_cls_flow_entry *fe,
 		fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
 }
 
-static void mvpp2_cls_flow_seq_set(struct mvpp2_cls_flow_entry *fe, u32 seq)
-{
-	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_SEQ(MVPP2_CLS_FLOW_TBL1_SEQ_MASK);
-	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_SEQ(seq);
-}
-
 static void mvpp2_cls_flow_last_set(struct mvpp2_cls_flow_entry *fe,
 				    bool is_last)
 {
@@ -454,9 +448,22 @@ static void mvpp2_cls_flow_port_add(struct mvpp2_cls_flow_entry *fe,
 	fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
 }
 
+static void mvpp2_cls_flow_port_remove(struct mvpp2_cls_flow_entry *fe,
+				       u32 port)
+{
+	fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
+}
+
+static void mvpp2_cls_flow_lu_type_set(struct mvpp2_cls_flow_entry *fe,
+				       u8 lu_type)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_LU_TYPE(MVPP2_CLS_LU_TYPE_MASK);
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_LU_TYPE(lu_type);
+}
+
 /* Initialize the parser entry for the given flow */
 static void mvpp2_cls_flow_prs_init(struct mvpp2 *priv,
-				    struct mvpp2_cls_flow *flow)
+				    const struct mvpp2_cls_flow *flow)
 {
 	mvpp2_prs_add_flow(priv, flow->flow_id, flow->prs_ri.ri,
 			   flow->prs_ri.ri_mask);
@@ -464,7 +471,7 @@ static void mvpp2_cls_flow_prs_init(struct mvpp2 *priv,
 
 /* Initialize the Lookup Id table entry for the given flow */
 static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv,
-				    struct mvpp2_cls_flow *flow)
+				    const struct mvpp2_cls_flow *flow)
 {
 	struct mvpp2_cls_lookup_entry le;
 
@@ -477,7 +484,7 @@ static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv,
 	/* We point on the first lookup in the sequence for the flow, that is
 	 * the C2 lookup.
 	 */
-	le.data |= MVPP2_CLS_LKP_FLOW_PTR(MVPP2_FLOW_C2_ENTRY(flow->flow_id));
+	le.data |= MVPP2_CLS_LKP_FLOW_PTR(MVPP2_CLS_FLT_FIRST(flow->flow_id));
 
 	/* CLS is always enabled, RSS is enabled/disabled in C2 lookup */
 	le.data |= MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK;
@@ -485,21 +492,113 @@ static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv,
 	mvpp2_cls_lookup_write(priv, &le);
 }
 
+static void mvpp2_cls_c2_write(struct mvpp2 *priv,
+			       struct mvpp2_cls_c2_entry *c2)
+{
+	u32 val;
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2->index);
+
+	val = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_INV);
+	if (c2->valid)
+		val &= ~MVPP22_CLS_C2_TCAM_INV_BIT;
+	else
+		val |= MVPP22_CLS_C2_TCAM_INV_BIT;
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_INV, val);
+
+	mvpp2_write(priv, MVPP22_CLS_C2_ACT, c2->act);
+
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR0, c2->attr[0]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR1, c2->attr[1]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR2, c2->attr[2]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
+
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA0, c2->tcam[0]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA1, c2->tcam[1]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA2, c2->tcam[2]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA3, c2->tcam[3]);
+	/* Writing TCAM_DATA4 flushes writes to TCAM_DATA0-4 and INV to HW */
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA4, c2->tcam[4]);
+}
+
+void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+		       struct mvpp2_cls_c2_entry *c2)
+{
+	u32 val;
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
+
+	c2->index = index;
+
+	c2->tcam[0] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA0);
+	c2->tcam[1] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA1);
+	c2->tcam[2] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA2);
+	c2->tcam[3] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA3);
+	c2->tcam[4] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA4);
+
+	c2->act = mvpp2_read(priv, MVPP22_CLS_C2_ACT);
+
+	c2->attr[0] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR0);
+	c2->attr[1] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR1);
+	c2->attr[2] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR2);
+	c2->attr[3] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR3);
+
+	val = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_INV);
+	c2->valid = !(val & MVPP22_CLS_C2_TCAM_INV_BIT);
+}
+
+static int mvpp2_cls_ethtool_flow_to_type(int flow_type)
+{
+	switch (flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
+	case ETHER_FLOW:
+		return MVPP22_FLOW_ETHERNET;
+	case TCP_V4_FLOW:
+		return MVPP22_FLOW_TCP4;
+	case TCP_V6_FLOW:
+		return MVPP22_FLOW_TCP6;
+	case UDP_V4_FLOW:
+		return MVPP22_FLOW_UDP4;
+	case UDP_V6_FLOW:
+		return MVPP22_FLOW_UDP6;
+	case IPV4_FLOW:
+		return MVPP22_FLOW_IP4;
+	case IPV6_FLOW:
+		return MVPP22_FLOW_IP6;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mvpp2_cls_c2_port_flow_index(struct mvpp2_port *port, int loc)
+{
+	return MVPP22_CLS_C2_RFS_LOC(port->id, loc);
+}
+
 /* Initialize the flow table entries for the given flow */
-static void mvpp2_cls_flow_init(struct mvpp2 *priv, struct mvpp2_cls_flow *flow)
+static void mvpp2_cls_flow_init(struct mvpp2 *priv,
+				const struct mvpp2_cls_flow *flow)
 {
 	struct mvpp2_cls_flow_entry fe;
-	int i;
+	int i, pri = 0;
 
-	/* C2 lookup */
-	memset(&fe, 0, sizeof(fe));
-	fe.index = MVPP2_FLOW_C2_ENTRY(flow->flow_id);
+	/* Assign default values to all entries in the flow */
+	for (i = MVPP2_CLS_FLT_FIRST(flow->flow_id);
+	     i <= MVPP2_CLS_FLT_LAST(flow->flow_id); i++) {
+		memset(&fe, 0, sizeof(fe));
+		fe.index = i;
+		mvpp2_cls_flow_pri_set(&fe, pri++);
+
+		if (i == MVPP2_CLS_FLT_LAST(flow->flow_id))
+			mvpp2_cls_flow_last_set(&fe, 1);
+
+		mvpp2_cls_flow_write(priv, &fe);
+	}
+
+	/* RSS config C2 lookup */
+	mvpp2_cls_flow_read(priv, MVPP2_CLS_FLT_C2_RSS_ENTRY(flow->flow_id),
+			    &fe);
 
 	mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
 	mvpp2_cls_flow_port_id_sel(&fe, true);
-	mvpp2_cls_flow_last_set(&fe, 0);
-	mvpp2_cls_flow_pri_set(&fe, 0);
-	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_FIRST1);
+	mvpp2_cls_flow_lu_type_set(&fe, MVPP22_CLS_LU_TYPE_ALL);
 
 	/* Add all ports */
 	for (i = 0; i < MVPP2_MAX_PORTS; i++)
@@ -509,22 +608,19 @@ static void mvpp2_cls_flow_init(struct mvpp2 *priv, struct mvpp2_cls_flow *flow)
 
 	/* C3Hx lookups */
 	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
-		memset(&fe, 0, sizeof(fe));
-		fe.index = MVPP2_PORT_FLOW_HASH_ENTRY(i, flow->flow_id);
+		mvpp2_cls_flow_read(priv,
+				    MVPP2_CLS_FLT_HASH_ENTRY(i, flow->flow_id),
+				    &fe);
 
+		/* Set a default engine. Will be overwritten when setting the
+		 * real HEK parameters
+		 */
+		mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C3HA);
 		mvpp2_cls_flow_port_id_sel(&fe, true);
-		mvpp2_cls_flow_pri_set(&fe, i + 1);
-		mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_MIDDLE);
 		mvpp2_cls_flow_port_add(&fe, BIT(i));
 
 		mvpp2_cls_flow_write(priv, &fe);
 	}
-
-	/* Update the last entry */
-	mvpp2_cls_flow_last_set(&fe, 1);
-	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
-
-	mvpp2_cls_flow_write(priv, &fe);
 }
 
 /* Adds a field to the Header Extracted Key generation parameters*/
@@ -555,9 +651,15 @@ static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
 
 	for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
 		switch (BIT(i)) {
+		case MVPP22_CLS_HEK_OPT_MAC_DA:
+			field_id = MVPP22_CLS_FIELD_MAC_DA;
+			break;
 		case MVPP22_CLS_HEK_OPT_VLAN:
 			field_id = MVPP22_CLS_FIELD_VLAN;
 			break;
+		case MVPP22_CLS_HEK_OPT_VLAN_PRI:
+			field_id = MVPP22_CLS_FIELD_VLAN_PRI;
+			break;
 		case MVPP22_CLS_HEK_OPT_IP4SA:
 			field_id = MVPP22_CLS_FIELD_IP4SA;
 			break;
@@ -586,9 +688,33 @@ static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
 	return 0;
 }
 
-struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
+/* Returns the size, in bits, of the corresponding HEK field */
+static int mvpp2_cls_hek_field_size(u32 field)
 {
-	if (flow >= MVPP2_N_FLOWS)
+	switch (field) {
+	case MVPP22_CLS_HEK_OPT_MAC_DA:
+		return 48;
+	case MVPP22_CLS_HEK_OPT_VLAN:
+		return 12;
+	case MVPP22_CLS_HEK_OPT_VLAN_PRI:
+		return 3;
+	case MVPP22_CLS_HEK_OPT_IP4SA:
+	case MVPP22_CLS_HEK_OPT_IP4DA:
+		return 32;
+	case MVPP22_CLS_HEK_OPT_IP6SA:
+	case MVPP22_CLS_HEK_OPT_IP6DA:
+		return 128;
+	case MVPP22_CLS_HEK_OPT_L4SIP:
+	case MVPP22_CLS_HEK_OPT_L4DIP:
+		return 16;
+	default:
+		return -1;
+	}
+}
+
+const struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
+{
+	if (flow >= MVPP2_N_PRS_FLOWS)
 		return NULL;
 
 	return &cls_flows[flow];
@@ -608,21 +734,17 @@ struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
 static int mvpp2_port_rss_hash_opts_set(struct mvpp2_port *port, int flow_type,
 					u16 requested_opts)
 {
+	const struct mvpp2_cls_flow *flow;
 	struct mvpp2_cls_flow_entry fe;
-	struct mvpp2_cls_flow *flow;
 	int i, engine, flow_index;
 	u16 hash_opts;
 
-	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+	for_each_cls_flow_id_with_type(i, flow_type) {
 		flow = mvpp2_cls_flow_get(i);
 		if (!flow)
 			return -EINVAL;
 
-		if (flow->flow_type != flow_type)
-			continue;
-
-		flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
-							flow->flow_id);
+		flow_index = MVPP2_CLS_FLT_HASH_ENTRY(port->id, flow->flow_id);
 
 		mvpp2_cls_flow_read(port->priv, flow_index, &fe);
 
@@ -664,6 +786,9 @@ u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
 		case MVPP22_CLS_FIELD_VLAN:
 			hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
 			break;
+		case MVPP22_CLS_FIELD_VLAN_PRI:
+			hash_opts |= MVPP22_CLS_HEK_OPT_VLAN_PRI;
+			break;
 		case MVPP22_CLS_FIELD_L3_PROTO:
 			hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
 			break;
@@ -697,21 +822,17 @@ u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
  */
 static u16 mvpp2_port_rss_hash_opts_get(struct mvpp2_port *port, int flow_type)
 {
+	const struct mvpp2_cls_flow *flow;
 	struct mvpp2_cls_flow_entry fe;
-	struct mvpp2_cls_flow *flow;
 	int i, flow_index;
 	u16 hash_opts = 0;
 
-	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+	for_each_cls_flow_id_with_type(i, flow_type) {
 		flow = mvpp2_cls_flow_get(i);
 		if (!flow)
 			return 0;
 
-		if (flow->flow_type != flow_type)
-			continue;
-
-		flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
-							flow->flow_id);
+		flow_index = MVPP2_CLS_FLT_HASH_ENTRY(port->id, flow->flow_id);
 
 		mvpp2_cls_flow_read(port->priv, flow_index, &fe);
 
@@ -723,10 +844,10 @@ static u16 mvpp2_port_rss_hash_opts_get(struct mvpp2_port *port, int flow_type)
 
 static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
 {
-	struct mvpp2_cls_flow *flow;
+	const struct mvpp2_cls_flow *flow;
 	int i;
 
-	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+	for (i = 0; i < MVPP2_N_PRS_FLOWS; i++) {
 		flow = mvpp2_cls_flow_get(i);
 		if (!flow)
 			break;
@@ -737,47 +858,6 @@ static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
 	}
 }
 
-static void mvpp2_cls_c2_write(struct mvpp2 *priv,
-			       struct mvpp2_cls_c2_entry *c2)
-{
-	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2->index);
-
-	/* Write TCAM */
-	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA0, c2->tcam[0]);
-	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA1, c2->tcam[1]);
-	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA2, c2->tcam[2]);
-	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA3, c2->tcam[3]);
-	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA4, c2->tcam[4]);
-
-	mvpp2_write(priv, MVPP22_CLS_C2_ACT, c2->act);
-
-	mvpp2_write(priv, MVPP22_CLS_C2_ATTR0, c2->attr[0]);
-	mvpp2_write(priv, MVPP22_CLS_C2_ATTR1, c2->attr[1]);
-	mvpp2_write(priv, MVPP22_CLS_C2_ATTR2, c2->attr[2]);
-	mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
-}
-
-void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
-		       struct mvpp2_cls_c2_entry *c2)
-{
-	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
-
-	c2->index = index;
-
-	c2->tcam[0] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA0);
-	c2->tcam[1] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA1);
-	c2->tcam[2] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA2);
-	c2->tcam[3] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA3);
-	c2->tcam[4] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA4);
-
-	c2->act = mvpp2_read(priv, MVPP22_CLS_C2_ACT);
-
-	c2->attr[0] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR0);
-	c2->attr[1] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR1);
-	c2->attr[2] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR2);
-	c2->attr[3] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR3);
-}
-
 static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
 {
 	struct mvpp2_cls_c2_entry c2;
@@ -791,6 +871,10 @@ static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
 	c2.tcam[4] = MVPP22_CLS_C2_PORT_ID(pmap);
 	c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_PORT_ID(pmap));
 
+	/* Match on Lookup Type */
+	c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_LU_TYPE(MVPP2_CLS_LU_TYPE_MASK));
+	c2.tcam[4] |= MVPP22_CLS_C2_LU_TYPE(MVPP22_CLS_LU_TYPE_ALL);
+
 	/* Update RSS status after matching this entry */
 	c2.act = MVPP22_CLS_C2_ACT_RSS_EN(MVPP22_C2_UPD_LOCK);
 
@@ -809,6 +893,8 @@ static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
 	c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
 		      MVPP22_CLS_C2_ATTR0_QLOW(ql);
 
+	c2.valid = true;
+
 	mvpp2_cls_c2_write(port->priv, &c2);
 }
 
@@ -817,6 +903,7 @@ void mvpp2_cls_init(struct mvpp2 *priv)
 {
 	struct mvpp2_cls_lookup_entry le;
 	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_c2_entry c2;
 	int index;
 
 	/* Enable classifier */
@@ -840,6 +927,20 @@ void mvpp2_cls_init(struct mvpp2 *priv)
 		mvpp2_cls_lookup_write(priv, &le);
 	}
 
+	/* Clear C2 TCAM engine table */
+	memset(&c2, 0, sizeof(c2));
+	c2.valid = false;
+	for (index = 0; index < MVPP22_CLS_C2_N_ENTRIES; index++) {
+		c2.index = index;
+		mvpp2_cls_c2_write(priv, &c2);
+	}
+
+	/* Disable the FIFO stages in C2 engine, which are only used in BIST
+	 * mode
+	 */
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_CTRL,
+		    MVPP22_CLS_C2_TCAM_BYPASS_FIFO);
+
 	mvpp2_cls_port_init_flows(priv);
 }
 
@@ -880,12 +981,22 @@ u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index)
 	return mvpp2_read(priv, MVPP22_CLS_C2_HIT_CTR);
 }
 
-static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port)
+static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port, u32 ctx)
 {
 	struct mvpp2_cls_c2_entry c2;
+	u8 qh, ql;
 
 	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
 
+	/* The RxQ number is used to select the RSS table. It that case, we set
+	 * it to be the ctx number.
+	 */
+	qh = (ctx >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+	ql = ctx & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+	c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
+		     MVPP22_CLS_C2_ATTR0_QLOW(ql);
+
 	c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
 
 	mvpp2_cls_c2_write(port->priv, &c2);
@@ -894,22 +1005,57 @@ static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port)
 static void mvpp2_rss_port_c2_disable(struct mvpp2_port *port)
 {
 	struct mvpp2_cls_c2_entry c2;
+	u8 qh, ql;
 
 	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
 
+	/* Reset the default destination RxQ to the port's first rx queue. */
+	qh = (port->first_rxq >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+	ql = port->first_rxq & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+	c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
+		      MVPP22_CLS_C2_ATTR0_QLOW(ql);
+
 	c2.attr[2] &= ~MVPP22_CLS_C2_ATTR2_RSS_EN;
 
 	mvpp2_cls_c2_write(port->priv, &c2);
 }
 
-void mvpp22_rss_enable(struct mvpp2_port *port)
+static inline int mvpp22_rss_ctx(struct mvpp2_port *port, int port_rss_ctx)
+{
+	return port->rss_ctx[port_rss_ctx];
+}
+
+int mvpp22_port_rss_enable(struct mvpp2_port *port)
 {
-	mvpp2_rss_port_c2_enable(port);
+	if (mvpp22_rss_ctx(port, 0) < 0)
+		return -EINVAL;
+
+	mvpp2_rss_port_c2_enable(port, mvpp22_rss_ctx(port, 0));
+
+	return 0;
 }
 
-void mvpp22_rss_disable(struct mvpp2_port *port)
+int mvpp22_port_rss_disable(struct mvpp2_port *port)
 {
+	if (mvpp22_rss_ctx(port, 0) < 0)
+		return -EINVAL;
+
 	mvpp2_rss_port_c2_disable(port);
+
+	return 0;
+}
+
+static void mvpp22_port_c2_lookup_disable(struct mvpp2_port *port, int entry)
+{
+	struct mvpp2_cls_c2_entry c2;
+
+	mvpp2_cls_c2_read(port->priv, entry, &c2);
+
+	/* Clear the port map so that the entry doesn't match anymore */
+	c2.tcam[4] &= ~(MVPP22_CLS_C2_PORT_ID(BIT(port->id)));
+
+	mvpp2_cls_c2_write(port->priv, &c2);
 }
 
 /* Set CPU queue number for oversize packets */
@@ -928,6 +1074,370 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 	mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
 }
 
+static int mvpp2_port_c2_tcam_rule_add(struct mvpp2_port *port,
+				       struct mvpp2_rfs_rule *rule)
+{
+	struct flow_action_entry *act;
+	struct mvpp2_cls_c2_entry c2;
+	u8 qh, ql, pmap;
+	int index, ctx;
+
+	memset(&c2, 0, sizeof(c2));
+
+	index = mvpp2_cls_c2_port_flow_index(port, rule->loc);
+	if (index < 0)
+		return -EINVAL;
+	c2.index = index;
+
+	act = &rule->flow->action.entries[0];
+
+	rule->c2_index = c2.index;
+
+	c2.tcam[3] = (rule->c2_tcam & 0xffff) |
+		     ((rule->c2_tcam_mask & 0xffff) << 16);
+	c2.tcam[2] = ((rule->c2_tcam >> 16) & 0xffff) |
+		     (((rule->c2_tcam_mask >> 16) & 0xffff) << 16);
+	c2.tcam[1] = ((rule->c2_tcam >> 32) & 0xffff) |
+		     (((rule->c2_tcam_mask >> 32) & 0xffff) << 16);
+	c2.tcam[0] = ((rule->c2_tcam >> 48) & 0xffff) |
+		     (((rule->c2_tcam_mask >> 48) & 0xffff) << 16);
+
+	pmap = BIT(port->id);
+	c2.tcam[4] = MVPP22_CLS_C2_PORT_ID(pmap);
+	c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_PORT_ID(pmap));
+
+	/* Match on Lookup Type */
+	c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_LU_TYPE(MVPP2_CLS_LU_TYPE_MASK));
+	c2.tcam[4] |= MVPP22_CLS_C2_LU_TYPE(rule->loc);
+
+	if (act->id == FLOW_ACTION_DROP) {
+		c2.act = MVPP22_CLS_C2_ACT_COLOR(MVPP22_C2_COL_RED_LOCK);
+	} else {
+		/* We want to keep the default color derived from the Header
+		 * Parser drop entries, for VLAN and MAC filtering. This will
+		 * assign a default color of Green or Red, and we want matches
+		 * with a non-drop action to keep that color.
+		 */
+		c2.act = MVPP22_CLS_C2_ACT_COLOR(MVPP22_C2_COL_NO_UPD_LOCK);
+
+		/* Update RSS status after matching this entry */
+		if (act->queue.ctx)
+			c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+		/* Always lock the RSS_EN decision. We might have high prio
+		 * rules steering to an RXQ, and a lower one steering to RSS,
+		 * we don't want the low prio RSS rule overwriting this flag.
+		 */
+		c2.act = MVPP22_CLS_C2_ACT_RSS_EN(MVPP22_C2_UPD_LOCK);
+
+		/* Mark packet as "forwarded to software", needed for RSS */
+		c2.act |= MVPP22_CLS_C2_ACT_FWD(MVPP22_C2_FWD_SW_LOCK);
+
+		c2.act |= MVPP22_CLS_C2_ACT_QHIGH(MVPP22_C2_UPD_LOCK) |
+			   MVPP22_CLS_C2_ACT_QLOW(MVPP22_C2_UPD_LOCK);
+
+		if (act->queue.ctx) {
+			/* Get the global ctx number */
+			ctx = mvpp22_rss_ctx(port, act->queue.ctx);
+			if (ctx < 0)
+				return -EINVAL;
+
+			qh = (ctx >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+			ql = ctx & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+		} else {
+			qh = ((act->queue.index + port->first_rxq) >> 3) &
+			      MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+			ql = (act->queue.index + port->first_rxq) &
+			      MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+		}
+
+		c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
+			      MVPP22_CLS_C2_ATTR0_QLOW(ql);
+	}
+
+	c2.valid = true;
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+
+	return 0;
+}
+
+static int mvpp2_port_c2_rfs_rule_insert(struct mvpp2_port *port,
+					 struct mvpp2_rfs_rule *rule)
+{
+	return mvpp2_port_c2_tcam_rule_add(port, rule);
+}
+
+static int mvpp2_port_cls_rfs_rule_remove(struct mvpp2_port *port,
+					  struct mvpp2_rfs_rule *rule)
+{
+	const struct mvpp2_cls_flow *flow;
+	struct mvpp2_cls_flow_entry fe;
+	int index, i;
+
+	for_each_cls_flow_id_containing_type(i, rule->flow_type) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			return 0;
+
+		index = MVPP2_CLS_FLT_C2_RFS(port->id, flow->flow_id, rule->loc);
+
+		mvpp2_cls_flow_read(port->priv, index, &fe);
+		mvpp2_cls_flow_port_remove(&fe, BIT(port->id));
+		mvpp2_cls_flow_write(port->priv, &fe);
+	}
+
+	if (rule->c2_index >= 0)
+		mvpp22_port_c2_lookup_disable(port, rule->c2_index);
+
+	return 0;
+}
+
+static int mvpp2_port_flt_rfs_rule_insert(struct mvpp2_port *port,
+					  struct mvpp2_rfs_rule *rule)
+{
+	const struct mvpp2_cls_flow *flow;
+	struct mvpp2 *priv = port->priv;
+	struct mvpp2_cls_flow_entry fe;
+	int index, ret, i;
+
+	if (rule->engine != MVPP22_CLS_ENGINE_C2)
+		return -EOPNOTSUPP;
+
+	ret = mvpp2_port_c2_rfs_rule_insert(port, rule);
+	if (ret)
+		return ret;
+
+	for_each_cls_flow_id_containing_type(i, rule->flow_type) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			return 0;
+
+		if ((rule->hek_fields & flow->supported_hash_opts) != rule->hek_fields)
+			continue;
+
+		index = MVPP2_CLS_FLT_C2_RFS(port->id, flow->flow_id, rule->loc);
+
+		mvpp2_cls_flow_read(priv, index, &fe);
+		mvpp2_cls_flow_eng_set(&fe, rule->engine);
+		mvpp2_cls_flow_port_id_sel(&fe, true);
+		mvpp2_flow_set_hek_fields(&fe, rule->hek_fields);
+		mvpp2_cls_flow_lu_type_set(&fe, rule->loc);
+		mvpp2_cls_flow_port_add(&fe, 0xf);
+
+		mvpp2_cls_flow_write(priv, &fe);
+	}
+
+	return 0;
+}
+
+static int mvpp2_cls_c2_build_match(struct mvpp2_rfs_rule *rule)
+{
+	struct flow_rule *flow = rule->flow;
+	int offs = 0;
+
+	/* The order of insertion in C2 tcam must match the order in which
+	 * the fields are found in the header
+	 */
+	if (flow_rule_match_key(flow, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(flow, &match);
+		if (match.mask->vlan_id) {
+			rule->hek_fields |= MVPP22_CLS_HEK_OPT_VLAN;
+
+			rule->c2_tcam |= ((u64)match.key->vlan_id) << offs;
+			rule->c2_tcam_mask |= ((u64)match.mask->vlan_id) << offs;
+
+			/* Don't update the offset yet */
+		}
+
+		if (match.mask->vlan_priority) {
+			rule->hek_fields |= MVPP22_CLS_HEK_OPT_VLAN_PRI;
+
+			/* VLAN pri is always at offset 13 relative to the
+			 * current offset
+			 */
+			rule->c2_tcam |= ((u64)match.key->vlan_priority) <<
+				(offs + 13);
+			rule->c2_tcam_mask |= ((u64)match.mask->vlan_priority) <<
+				(offs + 13);
+		}
+
+		if (match.mask->vlan_dei)
+			return -EOPNOTSUPP;
+
+		/* vlan id and prio always seem to take a full 16-bit slot in
+		 * the Header Extracted Key.
+		 */
+		offs += 16;
+	}
+
+	if (flow_rule_match_key(flow, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(flow, &match);
+		if (match.mask->src) {
+			rule->hek_fields |= MVPP22_CLS_HEK_OPT_L4SIP;
+
+			rule->c2_tcam |= ((u64)ntohs(match.key->src)) << offs;
+			rule->c2_tcam_mask |= ((u64)ntohs(match.mask->src)) << offs;
+			offs += mvpp2_cls_hek_field_size(MVPP22_CLS_HEK_OPT_L4SIP);
+		}
+
+		if (match.mask->dst) {
+			rule->hek_fields |= MVPP22_CLS_HEK_OPT_L4DIP;
+
+			rule->c2_tcam |= ((u64)ntohs(match.key->dst)) << offs;
+			rule->c2_tcam_mask |= ((u64)ntohs(match.mask->dst)) << offs;
+			offs += mvpp2_cls_hek_field_size(MVPP22_CLS_HEK_OPT_L4DIP);
+		}
+	}
+
+	if (hweight16(rule->hek_fields) > MVPP2_FLOW_N_FIELDS)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int mvpp2_cls_rfs_parse_rule(struct mvpp2_rfs_rule *rule)
+{
+	struct flow_rule *flow = rule->flow;
+	struct flow_action_entry *act;
+
+	act = &flow->action.entries[0];
+	if (act->id != FLOW_ACTION_QUEUE && act->id != FLOW_ACTION_DROP)
+		return -EOPNOTSUPP;
+
+	/* When both an RSS context and an queue index are set, the index
+	 * is considered as an offset to be added to the indirection table
+	 * entries. We don't support this, so reject this rule.
+	 */
+	if (act->queue.ctx && act->queue.index)
+		return -EOPNOTSUPP;
+
+	/* For now, only use the C2 engine which has a HEK size limited to 64
+	 * bits for TCAM matching.
+	 */
+	rule->engine = MVPP22_CLS_ENGINE_C2;
+
+	if (mvpp2_cls_c2_build_match(rule))
+		return -EINVAL;
+
+	return 0;
+}
+
+int mvpp2_ethtool_cls_rule_get(struct mvpp2_port *port,
+			       struct ethtool_rxnfc *rxnfc)
+{
+	struct mvpp2_ethtool_fs *efs;
+
+	if (rxnfc->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
+		return -EINVAL;
+
+	efs = port->rfs_rules[rxnfc->fs.location];
+	if (!efs)
+		return -ENOENT;
+
+	memcpy(rxnfc, &efs->rxnfc, sizeof(efs->rxnfc));
+
+	return 0;
+}
+
+int mvpp2_ethtool_cls_rule_ins(struct mvpp2_port *port,
+			       struct ethtool_rxnfc *info)
+{
+	struct ethtool_rx_flow_spec_input input = {};
+	struct ethtool_rx_flow_rule *ethtool_rule;
+	struct mvpp2_ethtool_fs *efs, *old_efs;
+	int ret = 0;
+
+	if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
+		return -EINVAL;
+
+	efs = kzalloc(sizeof(*efs), GFP_KERNEL);
+	if (!efs)
+		return -ENOMEM;
+
+	input.fs = &info->fs;
+
+	/* We need to manually set the rss_ctx, since this info isn't present
+	 * in info->fs
+	 */
+	if (info->fs.flow_type & FLOW_RSS)
+		input.rss_ctx = info->rss_context;
+
+	ethtool_rule = ethtool_rx_flow_rule_create(&input);
+	if (IS_ERR(ethtool_rule)) {
+		ret = PTR_ERR(ethtool_rule);
+		goto clean_rule;
+	}
+
+	efs->rule.flow = ethtool_rule->rule;
+	efs->rule.flow_type = mvpp2_cls_ethtool_flow_to_type(info->fs.flow_type);
+	if (efs->rule.flow_type < 0) {
+		ret = efs->rule.flow_type;
+		goto clean_rule;
+	}
+
+	ret = mvpp2_cls_rfs_parse_rule(&efs->rule);
+	if (ret)
+		goto clean_eth_rule;
+
+	efs->rule.loc = info->fs.location;
+
+	/* Replace an already existing rule */
+	if (port->rfs_rules[efs->rule.loc]) {
+		old_efs = port->rfs_rules[efs->rule.loc];
+		ret = mvpp2_port_cls_rfs_rule_remove(port, &old_efs->rule);
+		if (ret)
+			goto clean_eth_rule;
+		kfree(old_efs);
+		port->n_rfs_rules--;
+	}
+
+	ret = mvpp2_port_flt_rfs_rule_insert(port, &efs->rule);
+	if (ret)
+		goto clean_eth_rule;
+
+	ethtool_rx_flow_rule_destroy(ethtool_rule);
+	efs->rule.flow = NULL;
+
+	memcpy(&efs->rxnfc, info, sizeof(*info));
+	port->rfs_rules[efs->rule.loc] = efs;
+	port->n_rfs_rules++;
+
+	return ret;
+
+clean_eth_rule:
+	ethtool_rx_flow_rule_destroy(ethtool_rule);
+clean_rule:
+	kfree(efs);
+	return ret;
+}
+
+int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port,
+			       struct ethtool_rxnfc *info)
+{
+	struct mvpp2_ethtool_fs *efs;
+	int ret;
+
+	efs = port->rfs_rules[info->fs.location];
+	if (!efs)
+		return -EINVAL;
+
+	/* Remove the rule from the engines. */
+	ret = mvpp2_port_cls_rfs_rule_remove(port, &efs->rule);
+	if (ret)
+		return ret;
+
+	port->n_rfs_rules--;
+	port->rfs_rules[info->fs.location] = NULL;
+	kfree(efs);
+
+	return 0;
+}
+
 static inline u32 mvpp22_rxfh_indir(struct mvpp2_port *port, u32 rxq)
 {
 	int nrxqs, cpu, cpus = num_possible_cpus();
@@ -947,37 +1457,181 @@ static inline u32 mvpp22_rxfh_indir(struct mvpp2_port *port, u32 rxq)
 	return port->first_rxq + ((rxq * nrxqs + rxq / cpus) % port->nrxqs);
 }
 
-void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
+static void mvpp22_rss_fill_table(struct mvpp2_port *port,
+				  struct mvpp2_rss_table *table,
+				  u32 rss_ctx)
 {
 	struct mvpp2 *priv = port->priv;
 	int i;
 
 	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
-		u32 sel = MVPP22_RSS_INDEX_TABLE(table) |
+		u32 sel = MVPP22_RSS_INDEX_TABLE(rss_ctx) |
 			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
 		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
 
 		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY,
-			    mvpp22_rxfh_indir(port, port->indir[i]));
+			    mvpp22_rxfh_indir(port, table->indir[i]));
 	}
 }
 
+static int mvpp22_rss_context_create(struct mvpp2_port *port, u32 *rss_ctx)
+{
+	struct mvpp2 *priv = port->priv;
+	u32 ctx;
+
+	/* Find the first free RSS table */
+	for (ctx = 0; ctx < MVPP22_N_RSS_TABLES; ctx++) {
+		if (!priv->rss_tables[ctx])
+			break;
+	}
+
+	if (ctx == MVPP22_N_RSS_TABLES)
+		return -EINVAL;
+
+	priv->rss_tables[ctx] = kzalloc(sizeof(*priv->rss_tables[ctx]),
+					GFP_KERNEL);
+	if (!priv->rss_tables[ctx])
+		return -ENOMEM;
+
+	*rss_ctx = ctx;
+
+	/* Set the table width: replace the whole classifier Rx queue number
+	 * with the ones configured in RSS table entries.
+	 */
+	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(ctx));
+	mvpp2_write(priv, MVPP22_RSS_WIDTH, 8);
+
+	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(ctx));
+	mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE, MVPP22_RSS_TABLE_POINTER(ctx));
+
+	return 0;
+}
+
+int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *port_ctx)
+{
+	u32 rss_ctx;
+	int ret, i;
+
+	ret = mvpp22_rss_context_create(port, &rss_ctx);
+	if (ret)
+		return ret;
+
+	/* Find the first available context number in the port, starting from 1.
+	 * Context 0 on each port is reserved for the default context.
+	 */
+	for (i = 1; i < MVPP22_N_RSS_TABLES; i++) {
+		if (port->rss_ctx[i] < 0)
+			break;
+	}
+
+	if (i == MVPP22_N_RSS_TABLES)
+		return -EINVAL;
+
+	port->rss_ctx[i] = rss_ctx;
+	*port_ctx = i;
+
+	return 0;
+}
+
+static struct mvpp2_rss_table *mvpp22_rss_table_get(struct mvpp2 *priv,
+						    int rss_ctx)
+{
+	if (rss_ctx < 0 || rss_ctx >= MVPP22_N_RSS_TABLES)
+		return NULL;
+
+	return priv->rss_tables[rss_ctx];
+}
+
+int mvpp22_port_rss_ctx_delete(struct mvpp2_port *port, u32 port_ctx)
+{
+	struct mvpp2 *priv = port->priv;
+	struct ethtool_rxnfc *rxnfc;
+	int i, rss_ctx, ret;
+
+	rss_ctx = mvpp22_rss_ctx(port, port_ctx);
+
+	if (rss_ctx < 0 || rss_ctx >= MVPP22_N_RSS_TABLES)
+		return -EINVAL;
+
+	/* Invalidate any active classification rule that use this context */
+	for (i = 0; i < MVPP2_N_RFS_ENTRIES_PER_FLOW; i++) {
+		if (!port->rfs_rules[i])
+			continue;
+
+		rxnfc = &port->rfs_rules[i]->rxnfc;
+		if (!(rxnfc->fs.flow_type & FLOW_RSS) ||
+		    rxnfc->rss_context != port_ctx)
+			continue;
+
+		ret = mvpp2_ethtool_cls_rule_del(port, rxnfc);
+		if (ret) {
+			netdev_warn(port->dev,
+				    "couldn't remove classification rule %d associated to this context",
+				    rxnfc->fs.location);
+		}
+	}
+
+	kfree(priv->rss_tables[rss_ctx]);
+
+	priv->rss_tables[rss_ctx] = NULL;
+	port->rss_ctx[port_ctx] = -1;
+
+	return 0;
+}
+
+int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 port_ctx,
+				  const u32 *indir)
+{
+	int rss_ctx = mvpp22_rss_ctx(port, port_ctx);
+	struct mvpp2_rss_table *rss_table = mvpp22_rss_table_get(port->priv,
+								 rss_ctx);
+
+	if (!rss_table)
+		return -EINVAL;
+
+	memcpy(rss_table->indir, indir,
+	       MVPP22_RSS_TABLE_ENTRIES * sizeof(rss_table->indir[0]));
+
+	mvpp22_rss_fill_table(port, rss_table, rss_ctx);
+
+	return 0;
+}
+
+int mvpp22_port_rss_ctx_indir_get(struct mvpp2_port *port, u32 port_ctx,
+				  u32 *indir)
+{
+	int rss_ctx =  mvpp22_rss_ctx(port, port_ctx);
+	struct mvpp2_rss_table *rss_table = mvpp22_rss_table_get(port->priv,
+								 rss_ctx);
+
+	if (!rss_table)
+		return -EINVAL;
+
+	memcpy(indir, rss_table->indir,
+	       MVPP22_RSS_TABLE_ENTRIES * sizeof(rss_table->indir[0]));
+
+	return 0;
+}
+
 int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
 {
 	u16 hash_opts = 0;
+	u32 flow_type;
 
-	switch (info->flow_type) {
-	case TCP_V4_FLOW:
-	case UDP_V4_FLOW:
-	case TCP_V6_FLOW:
-	case UDP_V6_FLOW:
+	flow_type = mvpp2_cls_ethtool_flow_to_type(info->flow_type);
+
+	switch (flow_type) {
+	case MVPP22_FLOW_TCP4:
+	case MVPP22_FLOW_UDP4:
+	case MVPP22_FLOW_TCP6:
+	case MVPP22_FLOW_UDP6:
 		if (info->data & RXH_L4_B_0_1)
 			hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
 		if (info->data & RXH_L4_B_2_3)
 			hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
 		/* Fallthrough */
-	case IPV4_FLOW:
-	case IPV6_FLOW:
+	case MVPP22_FLOW_IP4:
+	case MVPP22_FLOW_IP6:
 		if (info->data & RXH_L2DA)
 			hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
 		if (info->data & RXH_VLAN)
@@ -994,15 +1648,18 @@ int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
 	default: return -EOPNOTSUPP;
 	}
 
-	return mvpp2_port_rss_hash_opts_set(port, info->flow_type, hash_opts);
+	return mvpp2_port_rss_hash_opts_set(port, flow_type, hash_opts);
 }
 
 int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info)
 {
 	unsigned long hash_opts;
+	u32 flow_type;
 	int i;
 
-	hash_opts = mvpp2_port_rss_hash_opts_get(port, info->flow_type);
+	flow_type = mvpp2_cls_ethtool_flow_to_type(info->flow_type);
+
+	hash_opts = mvpp2_port_rss_hash_opts_get(port, flow_type);
 	info->data = 0;
 
 	for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
@@ -1037,38 +1694,40 @@ int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info)
 	return 0;
 }
 
-void mvpp22_rss_port_init(struct mvpp2_port *port)
+int mvpp22_port_rss_init(struct mvpp2_port *port)
 {
-	struct mvpp2 *priv = port->priv;
-	int i;
+	struct mvpp2_rss_table *table;
+	u32 context = 0;
+	int i, ret;
 
-	/* Set the table width: replace the whole classifier Rx queue number
-	 * with the ones configured in RSS table entries.
-	 */
-	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(port->id));
-	mvpp2_write(priv, MVPP22_RSS_WIDTH, 8);
+	for (i = 0; i < MVPP22_N_RSS_TABLES; i++)
+		port->rss_ctx[i] = -1;
 
-	/* The default RxQ is used as a key to select the RSS table to use.
-	 * We use one RSS table per port.
-	 */
-	mvpp2_write(priv, MVPP22_RSS_INDEX,
-		    MVPP22_RSS_INDEX_QUEUE(port->first_rxq));
-	mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
-		    MVPP22_RSS_TABLE_POINTER(port->id));
+	ret = mvpp22_rss_context_create(port, &context);
+	if (ret)
+		return ret;
+
+	table = mvpp22_rss_table_get(port->priv, context);
+	if (!table)
+		return -EINVAL;
+
+	port->rss_ctx[0] = context;
 
 	/* Configure the first table to evenly distribute the packets across
 	 * real Rx Queues. The table entries map a hash to a port Rx Queue.
 	 */
 	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++)
-		port->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
+		table->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
 
-	mvpp22_rss_fill_table(port, port->id);
+	mvpp22_rss_fill_table(port, table, mvpp22_rss_ctx(port, 0));
 
 	/* Configure default flows */
-	mvpp2_port_rss_hash_opts_set(port, IPV4_FLOW, MVPP22_CLS_HEK_IP4_2T);
-	mvpp2_port_rss_hash_opts_set(port, IPV6_FLOW, MVPP22_CLS_HEK_IP6_2T);
-	mvpp2_port_rss_hash_opts_set(port, TCP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
-	mvpp2_port_rss_hash_opts_set(port, TCP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
-	mvpp2_port_rss_hash_opts_set(port, UDP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
-	mvpp2_port_rss_hash_opts_set(port, UDP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
+	mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_IP4, MVPP22_CLS_HEK_IP4_2T);
+	mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_IP6, MVPP22_CLS_HEK_IP6_2T);
+	mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_TCP4, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_TCP6, MVPP22_CLS_HEK_IP6_5T);
+	mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_UDP4, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_UDP6, MVPP22_CLS_HEK_IP6_5T);
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 089f05f29891..8867f25afab4 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -33,15 +33,16 @@ enum mvpp2_cls_engine {
 };
 
 #define MVPP22_CLS_HEK_OPT_MAC_DA	BIT(0)
-#define MVPP22_CLS_HEK_OPT_VLAN		BIT(1)
-#define MVPP22_CLS_HEK_OPT_L3_PROTO	BIT(2)
-#define MVPP22_CLS_HEK_OPT_IP4SA	BIT(3)
-#define MVPP22_CLS_HEK_OPT_IP4DA	BIT(4)
-#define MVPP22_CLS_HEK_OPT_IP6SA	BIT(5)
-#define MVPP22_CLS_HEK_OPT_IP6DA	BIT(6)
-#define MVPP22_CLS_HEK_OPT_L4SIP	BIT(7)
-#define MVPP22_CLS_HEK_OPT_L4DIP	BIT(8)
-#define MVPP22_CLS_HEK_N_FIELDS		9
+#define MVPP22_CLS_HEK_OPT_VLAN_PRI	BIT(1)
+#define MVPP22_CLS_HEK_OPT_VLAN		BIT(2)
+#define MVPP22_CLS_HEK_OPT_L3_PROTO	BIT(3)
+#define MVPP22_CLS_HEK_OPT_IP4SA	BIT(4)
+#define MVPP22_CLS_HEK_OPT_IP4DA	BIT(5)
+#define MVPP22_CLS_HEK_OPT_IP6SA	BIT(6)
+#define MVPP22_CLS_HEK_OPT_IP6DA	BIT(7)
+#define MVPP22_CLS_HEK_OPT_L4SIP	BIT(8)
+#define MVPP22_CLS_HEK_OPT_L4DIP	BIT(9)
+#define MVPP22_CLS_HEK_N_FIELDS		10
 
 #define MVPP22_CLS_HEK_L4_OPTS	(MVPP22_CLS_HEK_OPT_L4SIP | \
 				 MVPP22_CLS_HEK_OPT_L4DIP)
@@ -59,8 +60,12 @@ enum mvpp2_cls_engine {
 #define MVPP22_CLS_HEK_IP6_5T	(MVPP22_CLS_HEK_IP6_2T | \
 				 MVPP22_CLS_HEK_L4_OPTS)
 
+#define MVPP22_CLS_HEK_TAGGED	(MVPP22_CLS_HEK_OPT_VLAN | \
+				 MVPP22_CLS_HEK_OPT_VLAN_PRI)
+
 enum mvpp2_cls_field_id {
 	MVPP22_CLS_FIELD_MAC_DA = 0x03,
+	MVPP22_CLS_FIELD_VLAN_PRI = 0x05,
 	MVPP22_CLS_FIELD_VLAN = 0x06,
 	MVPP22_CLS_FIELD_L3_PROTO = 0x0f,
 	MVPP22_CLS_FIELD_IP4SA = 0x10,
@@ -71,14 +76,6 @@ enum mvpp2_cls_field_id {
 	MVPP22_CLS_FIELD_L4DIP = 0x1e,
 };
 
-enum mvpp2_cls_flow_seq {
-	MVPP2_CLS_FLOW_SEQ_NORMAL = 0,
-	MVPP2_CLS_FLOW_SEQ_FIRST1,
-	MVPP2_CLS_FLOW_SEQ_FIRST2,
-	MVPP2_CLS_FLOW_SEQ_LAST,
-	MVPP2_CLS_FLOW_SEQ_MIDDLE
-};
-
 /* Classifier C2 engine constants */
 #define MVPP22_CLS_C2_TCAM_EN(data)		((data) << 16)
 
@@ -100,39 +97,62 @@ enum mvpp22_cls_c2_fwd_action {
 	MVPP22_C2_FWD_HW_LOW_LAT_LOCK,
 };
 
+enum mvpp22_cls_c2_color_action {
+	MVPP22_C2_COL_NO_UPD = 0,
+	MVPP22_C2_COL_NO_UPD_LOCK,
+	MVPP22_C2_COL_GREEN,
+	MVPP22_C2_COL_GREEN_LOCK,
+	MVPP22_C2_COL_YELLOW,
+	MVPP22_C2_COL_YELLOW_LOCK,
+	MVPP22_C2_COL_RED,		/* Drop */
+	MVPP22_C2_COL_RED_LOCK,		/* Drop */
+};
+
 #define MVPP2_CLS_C2_TCAM_WORDS			5
 #define MVPP2_CLS_C2_ATTR_WORDS			5
 
 struct mvpp2_cls_c2_entry {
 	u32 index;
+	/* TCAM lookup key */
 	u32 tcam[MVPP2_CLS_C2_TCAM_WORDS];
+	/* Actions to perform upon TCAM match */
 	u32 act;
+	/* Attributes relative to the actions to perform */
 	u32 attr[MVPP2_CLS_C2_ATTR_WORDS];
+	/* Entry validity */
+	u8 valid;
 };
 
+#define MVPP22_FLOW_ETHER_BIT	BIT(0)
+#define MVPP22_FLOW_IP4_BIT	BIT(1)
+#define MVPP22_FLOW_IP6_BIT	BIT(2)
+#define MVPP22_FLOW_TCP_BIT	BIT(3)
+#define MVPP22_FLOW_UDP_BIT	BIT(4)
+
+#define MVPP22_FLOW_TCP4	(MVPP22_FLOW_ETHER_BIT | MVPP22_FLOW_IP4_BIT | MVPP22_FLOW_TCP_BIT)
+#define MVPP22_FLOW_TCP6	(MVPP22_FLOW_ETHER_BIT | MVPP22_FLOW_IP6_BIT | MVPP22_FLOW_TCP_BIT)
+#define MVPP22_FLOW_UDP4	(MVPP22_FLOW_ETHER_BIT | MVPP22_FLOW_IP4_BIT | MVPP22_FLOW_UDP_BIT)
+#define MVPP22_FLOW_UDP6	(MVPP22_FLOW_ETHER_BIT | MVPP22_FLOW_IP6_BIT | MVPP22_FLOW_UDP_BIT)
+#define MVPP22_FLOW_IP4		(MVPP22_FLOW_ETHER_BIT | MVPP22_FLOW_IP4_BIT)
+#define MVPP22_FLOW_IP6		(MVPP22_FLOW_ETHER_BIT | MVPP22_FLOW_IP6_BIT)
+#define MVPP22_FLOW_ETHERNET	(MVPP22_FLOW_ETHER_BIT)
+
 /* Classifier C2 engine entries */
-#define MVPP22_CLS_C2_RSS_ENTRY(port)	(port)
-#define MVPP22_CLS_C2_N_ENTRIES		MVPP2_MAX_PORTS
+#define MVPP22_CLS_C2_N_ENTRIES		256
 
-/* RSS flow entries in the flow table. We have 2 entries per port for RSS.
- *
- * The first performs a lookup using the C2 TCAM engine, to tag the
- * packet for software forwarding (needed for RSS), enable or disable RSS, and
- * assign the default rx queue.
- *
- * The second configures the hash generation, by specifying which fields of the
- * packet header are used to generate the hash, and specifies the relevant hash
- * engine to use.
+/* Number of per-port dedicated entries in the C2 TCAM */
+#define MVPP22_CLS_C2_PORT_N_FLOWS	MVPP2_N_RFS_ENTRIES_PER_FLOW
+
+/* Each port has oen range per flow type + one entry controling the global RSS
+ * setting and the default rx queue
  */
-#define MVPP22_RSS_FLOW_C2_OFFS		0
-#define MVPP22_RSS_FLOW_HASH_OFFS	1
-#define MVPP22_RSS_FLOW_SIZE		(MVPP22_RSS_FLOW_HASH_OFFS + 1)
+#define MVPP22_CLS_C2_PORT_RANGE	(MVPP22_CLS_C2_PORT_N_FLOWS + 1)
+#define MVPP22_CLS_C2_PORT_FIRST(p)	((p) * MVPP22_CLS_C2_PORT_RANGE)
+#define MVPP22_CLS_C2_RSS_ENTRY(p)	(MVPP22_CLS_C2_PORT_FIRST((p) + 1) - 1)
+
+#define MVPP22_CLS_C2_PORT_FLOW_FIRST(p)	(MVPP22_CLS_C2_PORT_FIRST(p))
 
-#define MVPP22_RSS_FLOW_C2(port)	((port) * MVPP22_RSS_FLOW_SIZE + \
-					 MVPP22_RSS_FLOW_C2_OFFS)
-#define MVPP22_RSS_FLOW_HASH(port)	((port) * MVPP22_RSS_FLOW_SIZE + \
-					 MVPP22_RSS_FLOW_HASH_OFFS)
-#define MVPP22_RSS_FLOW_FIRST(port)	MVPP22_RSS_FLOW_C2(port)
+#define MVPP22_CLS_C2_RFS_LOC(p, loc)	(MVPP22_CLS_C2_PORT_FLOW_FIRST(p) + (loc))
 
 /* Packet flow ID */
 enum mvpp2_prs_flow {
@@ -162,6 +182,16 @@ enum mvpp2_prs_flow {
 	MVPP2_FL_LAST,
 };
 
+/* LU Type defined for all engines, and specified in the flow table */
+#define MVPP2_CLS_LU_TYPE_MASK			0x3f
+
+enum mvpp2_cls_lu_type {
+	/* rule->loc is used as a lu-type for the entries 0 - 62. */
+	MVPP22_CLS_LU_TYPE_ALL = 63,
+};
+
+#define MVPP2_N_FLOWS		(MVPP2_FL_LAST - MVPP2_FL_START)
+
 struct mvpp2_cls_flow {
 	/* The L2-L4 traffic flow type */
 	int flow_type;
@@ -176,12 +206,48 @@ struct mvpp2_cls_flow {
 	struct mvpp2_prs_result_info prs_ri;
 };
 
-#define MVPP2_N_FLOWS	52
+#define MVPP2_CLS_FLT_ENTRIES_PER_FLOW		(MVPP2_MAX_PORTS + 1 + 16)
+#define MVPP2_CLS_FLT_FIRST(id)			(((id) - MVPP2_FL_START) * \
+						 MVPP2_CLS_FLT_ENTRIES_PER_FLOW)
+
+#define MVPP2_CLS_FLT_C2_RFS(port, id, rfs_n)	(MVPP2_CLS_FLT_FIRST(id) + \
+						 ((port) * MVPP2_MAX_PORTS) + \
+						 (rfs_n))
+
+#define MVPP2_CLS_FLT_C2_RSS_ENTRY(id)		(MVPP2_CLS_FLT_C2_RFS(MVPP2_MAX_PORTS, id, 0))
+#define MVPP2_CLS_FLT_HASH_ENTRY(port, id)	(MVPP2_CLS_FLT_C2_RSS_ENTRY(id) + 1 + (port))
+#define MVPP2_CLS_FLT_LAST(id)			(MVPP2_CLS_FLT_FIRST(id) + \
+						 MVPP2_CLS_FLT_ENTRIES_PER_FLOW - 1)
+
+/* Iterate on each classifier flow id. Sets 'i' to be the index of the first
+ * entry in the cls_flows table for each different flow_id.
+ * This relies on entries having the same flow_id in the cls_flows table being
+ * contiguous.
+ */
+#define for_each_cls_flow_id(i)						      \
+	for ((i) = 0; (i) < MVPP2_N_PRS_FLOWS; (i)++)			      \
+		if ((i) > 0 &&						      \
+		    cls_flows[(i)].flow_id == cls_flows[(i) - 1].flow_id)       \
+			continue;					      \
+		else
+
+/* Iterate on each classifier flow that has a given flow_type. Sets 'i' to be
+ * the index of the first entry in the cls_flow table for each different flow_id
+ * that has the given flow_type. This allows to operate on all flows that
+ * matches a given ethtool flow type.
+ */
+#define for_each_cls_flow_id_with_type(i, type)				      \
+	for_each_cls_flow_id((i))					      \
+		if (cls_flows[(i)].flow_type != (type))			      \
+			continue;					      \
+		else
+
+#define for_each_cls_flow_id_containing_type(i, type)			      \
+	for_each_cls_flow_id((i))					      \
+		if ((cls_flows[(i)].flow_type & (type)) != (type))	      \
+			continue;					      \
+		else
 
-#define MVPP2_ENTRIES_PER_FLOW			(MVPP2_MAX_PORTS + 1)
-#define MVPP2_FLOW_C2_ENTRY(id)			((id) * MVPP2_ENTRIES_PER_FLOW)
-#define MVPP2_PORT_FLOW_HASH_ENTRY(port, id)	((id) * MVPP2_ENTRIES_PER_FLOW + \
-						(port) + 1)
 struct mvpp2_cls_flow_entry {
 	u32 index;
 	u32 data[MVPP2_CLS_FLOWS_TBL_DATA_WORDS];
@@ -193,12 +259,18 @@ struct mvpp2_cls_lookup_entry {
 	u32 data;
 };
 
-void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table);
+int mvpp22_port_rss_init(struct mvpp2_port *port);
+
+int mvpp22_port_rss_enable(struct mvpp2_port *port);
+int mvpp22_port_rss_disable(struct mvpp2_port *port);
 
-void mvpp22_rss_port_init(struct mvpp2_port *port);
+int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *rss_ctx);
+int mvpp22_port_rss_ctx_delete(struct mvpp2_port *port, u32 rss_ctx);
 
-void mvpp22_rss_enable(struct mvpp2_port *port);
-void mvpp22_rss_disable(struct mvpp2_port *port);
+int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 rss_ctx,
+				  const u32 *indir);
+int mvpp22_port_rss_ctx_indir_get(struct mvpp2_port *port, u32 rss_ctx,
+				  u32 *indir);
 
 int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info);
 int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info);
@@ -213,7 +285,7 @@ int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe);
 
 u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe);
 
-struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow);
+const struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow);
 
 u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index);
 
@@ -230,4 +302,13 @@ u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index);
 void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
 		       struct mvpp2_cls_c2_entry *c2);
 
+int mvpp2_ethtool_cls_rule_get(struct mvpp2_port *port,
+			       struct ethtool_rxnfc *rxnfc);
+
+int mvpp2_ethtool_cls_rule_ins(struct mvpp2_port *port,
+			       struct ethtool_rxnfc *info);
+
+int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port,
+			       struct ethtool_rxnfc *info);
+
 #endif
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
index f9744a61e5dd..274fb07362cb 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -18,22 +18,48 @@ struct mvpp2_dbgfs_prs_entry {
 	struct mvpp2 *priv;
 };
 
+struct mvpp2_dbgfs_c2_entry {
+	int id;
+	struct mvpp2 *priv;
+};
+
 struct mvpp2_dbgfs_flow_entry {
 	int flow;
 	struct mvpp2 *priv;
 };
 
+struct mvpp2_dbgfs_flow_tbl_entry {
+	int id;
+	struct mvpp2 *priv;
+};
+
 struct mvpp2_dbgfs_port_flow_entry {
 	struct mvpp2_port *port;
 	struct mvpp2_dbgfs_flow_entry *dbg_fe;
 };
 
+struct mvpp2_dbgfs_entries {
+	/* Entries for Header Parser debug info */
+	struct mvpp2_dbgfs_prs_entry prs_entries[MVPP2_PRS_TCAM_SRAM_SIZE];
+
+	/* Entries for Classifier C2 engine debug info */
+	struct mvpp2_dbgfs_c2_entry c2_entries[MVPP22_CLS_C2_N_ENTRIES];
+
+	/* Entries for Classifier Flow Table debug info */
+	struct mvpp2_dbgfs_flow_tbl_entry flt_entries[MVPP2_CLS_FLOWS_TBL_SIZE];
+
+	/* Entries for Classifier flows debug info */
+	struct mvpp2_dbgfs_flow_entry flow_entries[MVPP2_N_PRS_FLOWS];
+
+	/* Entries for per-port flows debug info */
+	struct mvpp2_dbgfs_port_flow_entry port_flow_entries[MVPP2_MAX_PORTS];
+};
+
 static int mvpp2_dbgfs_flow_flt_hits_show(struct seq_file *s, void *unused)
 {
-	struct mvpp2_dbgfs_flow_entry *entry = s->private;
-	int id = MVPP2_FLOW_C2_ENTRY(entry->flow);
+	struct mvpp2_dbgfs_flow_tbl_entry *entry = s->private;
 
-	u32 hits = mvpp2_cls_flow_hits(entry->priv, id);
+	u32 hits = mvpp2_cls_flow_hits(entry->priv, entry->id);
 
 	seq_printf(s, "%u\n", hits);
 
@@ -58,7 +84,7 @@ DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_dec_hits);
 static int mvpp2_dbgfs_flow_type_show(struct seq_file *s, void *unused)
 {
 	struct mvpp2_dbgfs_flow_entry *entry = s->private;
-	struct mvpp2_cls_flow *f;
+	const struct mvpp2_cls_flow *f;
 	const char *flow_name;
 
 	f = mvpp2_cls_flow_get(entry->flow);
@@ -93,30 +119,12 @@ static int mvpp2_dbgfs_flow_type_show(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int mvpp2_dbgfs_flow_type_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mvpp2_dbgfs_flow_type_show, inode->i_private);
-}
-
-static int mvpp2_dbgfs_flow_type_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq = file->private_data;
-	struct mvpp2_dbgfs_flow_entry *flow_entry = seq->private;
-
-	kfree(flow_entry);
-	return single_release(inode, file);
-}
-
-static const struct file_operations mvpp2_dbgfs_flow_type_fops = {
-	.open = mvpp2_dbgfs_flow_type_open,
-	.read = seq_read,
-	.release = mvpp2_dbgfs_flow_type_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_type);
 
 static int mvpp2_dbgfs_flow_id_show(struct seq_file *s, void *unused)
 {
-	struct mvpp2_dbgfs_flow_entry *entry = s->private;
-	struct mvpp2_cls_flow *f;
+	const struct mvpp2_dbgfs_flow_entry *entry = s->private;
+	const struct mvpp2_cls_flow *f;
 
 	f = mvpp2_cls_flow_get(entry->flow);
 	if (!f)
@@ -134,7 +142,7 @@ static int mvpp2_dbgfs_port_flow_hash_opt_show(struct seq_file *s, void *unused)
 	struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
 	struct mvpp2_port *port = entry->port;
 	struct mvpp2_cls_flow_entry fe;
-	struct mvpp2_cls_flow *f;
+	const struct mvpp2_cls_flow *f;
 	int flow_index;
 	u16 hash_opts;
 
@@ -142,7 +150,7 @@ static int mvpp2_dbgfs_port_flow_hash_opt_show(struct seq_file *s, void *unused)
 	if (!f)
 		return -EINVAL;
 
-	flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+	flow_index = MVPP2_CLS_FLT_HASH_ENTRY(entry->port->id, f->flow_id);
 
 	mvpp2_cls_flow_read(port->priv, flow_index, &fe);
 
@@ -153,42 +161,21 @@ static int mvpp2_dbgfs_port_flow_hash_opt_show(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int mvpp2_dbgfs_port_flow_hash_opt_open(struct inode *inode,
-					       struct file *file)
-{
-	return single_open(file, mvpp2_dbgfs_port_flow_hash_opt_show,
-			   inode->i_private);
-}
-
-static int mvpp2_dbgfs_port_flow_hash_opt_release(struct inode *inode,
-						  struct file *file)
-{
-	struct seq_file *seq = file->private_data;
-	struct mvpp2_dbgfs_port_flow_entry *flow_entry = seq->private;
-
-	kfree(flow_entry);
-	return single_release(inode, file);
-}
-
-static const struct file_operations mvpp2_dbgfs_port_flow_hash_opt_fops = {
-	.open = mvpp2_dbgfs_port_flow_hash_opt_open,
-	.read = seq_read,
-	.release = mvpp2_dbgfs_port_flow_hash_opt_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_flow_hash_opt);
 
 static int mvpp2_dbgfs_port_flow_engine_show(struct seq_file *s, void *unused)
 {
 	struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
 	struct mvpp2_port *port = entry->port;
 	struct mvpp2_cls_flow_entry fe;
-	struct mvpp2_cls_flow *f;
+	const struct mvpp2_cls_flow *f;
 	int flow_index, engine;
 
 	f = mvpp2_cls_flow_get(entry->dbg_fe->flow);
 	if (!f)
 		return -EINVAL;
 
-	flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+	flow_index = MVPP2_CLS_FLT_HASH_ENTRY(entry->port->id, f->flow_id);
 
 	mvpp2_cls_flow_read(port->priv, flow_index, &fe);
 
@@ -203,11 +190,10 @@ DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_flow_engine);
 
 static int mvpp2_dbgfs_flow_c2_hits_show(struct seq_file *s, void *unused)
 {
-	struct mvpp2_port *port = s->private;
+	struct mvpp2_dbgfs_c2_entry *entry = s->private;
 	u32 hits;
 
-	hits = mvpp2_cls_c2_hit_count(port->priv,
-				      MVPP22_CLS_C2_RSS_ENTRY(port->id));
+	hits = mvpp2_cls_c2_hit_count(entry->priv, entry->id);
 
 	seq_printf(s, "%u\n", hits);
 
@@ -218,11 +204,11 @@ DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_hits);
 
 static int mvpp2_dbgfs_flow_c2_rxq_show(struct seq_file *s, void *unused)
 {
-	struct mvpp2_port *port = s->private;
+	struct mvpp2_dbgfs_c2_entry *entry = s->private;
 	struct mvpp2_cls_c2_entry c2;
 	u8 qh, ql;
 
-	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+	mvpp2_cls_c2_read(entry->priv, entry->id, &c2);
 
 	qh = (c2.attr[0] >> MVPP22_CLS_C2_ATTR0_QHIGH_OFFS) &
 	     MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
@@ -239,11 +225,11 @@ DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_rxq);
 
 static int mvpp2_dbgfs_flow_c2_enable_show(struct seq_file *s, void *unused)
 {
-	struct mvpp2_port *port = s->private;
+	struct mvpp2_dbgfs_c2_entry *entry = s->private;
 	struct mvpp2_cls_c2_entry c2;
 	int enabled;
 
-	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+	mvpp2_cls_c2_read(entry->priv, entry->id, &c2);
 
 	enabled = !!(c2.attr[2] & MVPP22_CLS_C2_ATTR2_RSS_EN);
 
@@ -456,25 +442,7 @@ static int mvpp2_dbgfs_prs_valid_show(struct seq_file *s, void *unused)
 	return 0;
 }
 
-static int mvpp2_dbgfs_prs_valid_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, mvpp2_dbgfs_prs_valid_show, inode->i_private);
-}
-
-static int mvpp2_dbgfs_prs_valid_release(struct inode *inode, struct file *file)
-{
-	struct seq_file *seq = file->private_data;
-	struct mvpp2_dbgfs_prs_entry *entry = seq->private;
-
-	kfree(entry);
-	return single_release(inode, file);
-}
-
-static const struct file_operations mvpp2_dbgfs_prs_valid_fops = {
-	.open = mvpp2_dbgfs_prs_valid_open,
-	.read = seq_read,
-	.release = mvpp2_dbgfs_prs_valid_release,
-};
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_valid);
 
 static int mvpp2_dbgfs_flow_port_init(struct dentry *parent,
 				      struct mvpp2_port *port,
@@ -487,10 +455,7 @@ static int mvpp2_dbgfs_flow_port_init(struct dentry *parent,
 	if (IS_ERR(port_dir))
 		return PTR_ERR(port_dir);
 
-	/* This will be freed by 'hash_opts' release op */
-	port_entry = kmalloc(sizeof(*port_entry), GFP_KERNEL);
-	if (!port_entry)
-		return -ENOMEM;
+	port_entry = &port->priv->dbgfs_entries->port_flow_entries[port->id];
 
 	port_entry->port = port;
 	port_entry->dbg_fe = entry;
@@ -518,17 +483,11 @@ static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent,
 	if (!flow_entry_dir)
 		return -ENOMEM;
 
-	/* This will be freed by 'type' release op */
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		return -ENOMEM;
+	entry = &priv->dbgfs_entries->flow_entries[flow];
 
 	entry->flow = flow;
 	entry->priv = priv;
 
-	debugfs_create_file("flow_hits", 0444, flow_entry_dir, entry,
-			    &mvpp2_dbgfs_flow_flt_hits_fops);
-
 	debugfs_create_file("dec_hits", 0444, flow_entry_dir, entry,
 			    &mvpp2_dbgfs_flow_dec_hits_fops);
 
@@ -545,6 +504,7 @@ static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent,
 		if (ret)
 			return ret;
 	}
+
 	return 0;
 }
 
@@ -557,7 +517,7 @@ static int mvpp2_dbgfs_flow_init(struct dentry *parent, struct mvpp2 *priv)
 	if (!flow_dir)
 		return -ENOMEM;
 
-	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+	for (i = 0; i < MVPP2_N_PRS_FLOWS; i++) {
 		ret = mvpp2_dbgfs_flow_entry_init(flow_dir, priv, i);
 		if (ret)
 			return ret;
@@ -582,10 +542,7 @@ static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent,
 	if (!prs_entry_dir)
 		return -ENOMEM;
 
-	/* The 'valid' entry's ops will free that */
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		return -ENOMEM;
+	entry = &priv->dbgfs_entries->prs_entries[tid];
 
 	entry->tid = tid;
 	entry->priv = priv;
@@ -609,6 +566,9 @@ static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent,
 	debugfs_create_file("hits", 0444, prs_entry_dir, entry,
 			    &mvpp2_dbgfs_prs_hits_fops);
 
+	debugfs_create_file("pmap", 0444, prs_entry_dir, entry,
+			     &mvpp2_dbgfs_prs_pmap_fops);
+
 	return 0;
 }
 
@@ -630,6 +590,98 @@ static int mvpp2_dbgfs_prs_init(struct dentry *parent, struct mvpp2 *priv)
 	return 0;
 }
 
+static int mvpp2_dbgfs_c2_entry_init(struct dentry *parent,
+				     struct mvpp2 *priv, int id)
+{
+	struct mvpp2_dbgfs_c2_entry *entry;
+	struct dentry *c2_entry_dir;
+	char c2_entry_name[10];
+
+	if (id >= MVPP22_CLS_C2_N_ENTRIES)
+		return -EINVAL;
+
+	sprintf(c2_entry_name, "%03d", id);
+
+	c2_entry_dir = debugfs_create_dir(c2_entry_name, parent);
+	if (!c2_entry_dir)
+		return -ENOMEM;
+
+	entry = &priv->dbgfs_entries->c2_entries[id];
+
+	entry->id = id;
+	entry->priv = priv;
+
+	debugfs_create_file("hits", 0444, c2_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_c2_hits_fops);
+
+	debugfs_create_file("default_rxq", 0444, c2_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_c2_rxq_fops);
+
+	debugfs_create_file("rss_enable", 0444, c2_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_c2_enable_fops);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_flow_tbl_entry_init(struct dentry *parent,
+					   struct mvpp2 *priv, int id)
+{
+	struct mvpp2_dbgfs_flow_tbl_entry *entry;
+	struct dentry *flow_tbl_entry_dir;
+	char flow_tbl_entry_name[10];
+
+	if (id >= MVPP2_CLS_FLOWS_TBL_SIZE)
+		return -EINVAL;
+
+	sprintf(flow_tbl_entry_name, "%03d", id);
+
+	flow_tbl_entry_dir = debugfs_create_dir(flow_tbl_entry_name, parent);
+	if (!flow_tbl_entry_dir)
+		return -ENOMEM;
+
+	entry = &priv->dbgfs_entries->flt_entries[id];
+
+	entry->id = id;
+	entry->priv = priv;
+
+	debugfs_create_file("hits", 0444, flow_tbl_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_flt_hits_fops);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_cls_init(struct dentry *parent, struct mvpp2 *priv)
+{
+	struct dentry *cls_dir, *c2_dir, *flow_tbl_dir;
+	int i, ret;
+
+	cls_dir = debugfs_create_dir("classifier", parent);
+	if (!cls_dir)
+		return -ENOMEM;
+
+	c2_dir = debugfs_create_dir("c2", cls_dir);
+	if (!c2_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < MVPP22_CLS_C2_N_ENTRIES; i++) {
+		ret = mvpp2_dbgfs_c2_entry_init(c2_dir, priv, i);
+		if (ret)
+			return ret;
+	}
+
+	flow_tbl_dir = debugfs_create_dir("flow_table", cls_dir);
+	if (!flow_tbl_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < MVPP2_CLS_FLOWS_TBL_SIZE; i++) {
+		ret = mvpp2_dbgfs_flow_tbl_entry_init(flow_tbl_dir, priv, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int mvpp2_dbgfs_port_init(struct dentry *parent,
 				 struct mvpp2_port *port)
 {
@@ -648,21 +700,14 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent,
 	debugfs_create_file("vid_filter", 0444, port_dir, port,
 			    &mvpp2_dbgfs_port_vid_fops);
 
-	debugfs_create_file("c2_hits", 0444, port_dir, port,
-			    &mvpp2_dbgfs_flow_c2_hits_fops);
-
-	debugfs_create_file("default_rxq", 0444, port_dir, port,
-			    &mvpp2_dbgfs_flow_c2_rxq_fops);
-
-	debugfs_create_file("rss_enable", 0444, port_dir, port,
-			    &mvpp2_dbgfs_flow_c2_enable_fops);
-
 	return 0;
 }
 
 void mvpp2_dbgfs_cleanup(struct mvpp2 *priv)
 {
 	debugfs_remove_recursive(priv->dbgfs_dir);
+
+	kfree(priv->dbgfs_entries);
 }
 
 void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name)
@@ -682,11 +727,18 @@ void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name)
 		return;
 
 	priv->dbgfs_dir = mvpp2_dir;
+	priv->dbgfs_entries = kzalloc(sizeof(*priv->dbgfs_entries), GFP_KERNEL);
+	if (!priv->dbgfs_entries)
+		goto err;
 
 	ret = mvpp2_dbgfs_prs_init(mvpp2_dir, priv);
 	if (ret)
 		goto err;
 
+	ret = mvpp2_dbgfs_cls_init(mvpp2_dir, priv);
+	if (ret)
+		goto err;
+
 	for (i = 0; i < priv->port_count; i++) {
 		ret = mvpp2_dbgfs_port_init(mvpp2_dir, priv->port_list[i]);
 		if (ret)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 16066c2d5b3a..c51f1d5b550b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -56,9 +56,9 @@ static struct {
 /* The prototype is added here to be used in start_dev when using ACPI. This
  * will be removed once phylink is used for all modes (dt+ACPI).
  */
-static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
+static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode,
 			     const struct phylink_link_state *state);
-static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode,
+static void mvpp2_mac_link_up(struct phylink_config *config, unsigned int mode,
 			      phy_interface_t interface, struct phy_device *phy);
 
 /* Queue modes */
@@ -965,6 +965,11 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask)
 }
 
 /* Port configuration routines */
+static bool mvpp2_is_xlg(phy_interface_t interface)
+{
+	return interface == PHY_INTERFACE_MODE_10GKR ||
+	       interface == PHY_INTERFACE_MODE_XAUI;
+}
 
 static void mvpp22_gop_init_rgmii(struct mvpp2_port *port)
 {
@@ -1010,27 +1015,20 @@ static void mvpp22_gop_init_10gkr(struct mvpp2_port *port)
 	void __iomem *xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
 	u32 val;
 
-	/* XPCS */
 	val = readl(xpcs + MVPP22_XPCS_CFG0);
 	val &= ~(MVPP22_XPCS_CFG0_PCS_MODE(0x3) |
 		 MVPP22_XPCS_CFG0_ACTIVE_LANE(0x3));
 	val |= MVPP22_XPCS_CFG0_ACTIVE_LANE(2);
 	writel(val, xpcs + MVPP22_XPCS_CFG0);
 
-	/* MPCS */
 	val = readl(mpcs + MVPP22_MPCS_CTRL);
 	val &= ~MVPP22_MPCS_CTRL_FWD_ERR_CONN;
 	writel(val, mpcs + MVPP22_MPCS_CTRL);
 
 	val = readl(mpcs + MVPP22_MPCS_CLK_RESET);
-	val &= ~(MVPP22_MPCS_CLK_RESET_DIV_RATIO(0x7) | MAC_CLK_RESET_MAC |
-		 MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX);
+	val &= ~MVPP22_MPCS_CLK_RESET_DIV_RATIO(0x7);
 	val |= MVPP22_MPCS_CLK_RESET_DIV_RATIO(1);
 	writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
-
-	val &= ~MVPP22_MPCS_CLK_RESET_DIV_SET;
-	val |= MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX;
-	writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
 }
 
 static int mvpp22_gop_init(struct mvpp2_port *port)
@@ -1090,9 +1088,8 @@ static void mvpp22_gop_unmask_irq(struct mvpp2_port *port)
 	u32 val;
 
 	if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-	    port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+	    phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		/* Enable the GMAC link status irq for this port */
 		val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK);
 		val |= MVPP22_GMAC_INT_SUM_MASK_LINK_STAT;
@@ -1102,7 +1099,7 @@ static void mvpp22_gop_unmask_irq(struct mvpp2_port *port)
 	if (port->gop_id == 0) {
 		/* Enable the XLG/GIG irqs for this port */
 		val = readl(port->base + MVPP22_XLG_EXT_INT_MASK);
-		if (port->phy_interface == PHY_INTERFACE_MODE_10GKR)
+		if (mvpp2_is_xlg(port->phy_interface))
 			val |= MVPP22_XLG_EXT_INT_MASK_XLG;
 		else
 			val |= MVPP22_XLG_EXT_INT_MASK_GIG;
@@ -1122,9 +1119,8 @@ static void mvpp22_gop_mask_irq(struct mvpp2_port *port)
 	}
 
 	if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-	    port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+	    phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK);
 		val &= ~MVPP22_GMAC_INT_SUM_MASK_LINK_STAT;
 		writel(val, port->base + MVPP22_GMAC_INT_SUM_MASK);
@@ -1135,10 +1131,10 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port)
 {
 	u32 val;
 
-	if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-	    port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+	if (port->phylink ||
+	    phy_interface_mode_is_rgmii(port->phy_interface) ||
+	    phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		val = readl(port->base + MVPP22_GMAC_INT_MASK);
 		val |= MVPP22_GMAC_INT_MASK_LINK_STAT;
 		writel(val, port->base + MVPP22_GMAC_INT_MASK);
@@ -1183,12 +1179,9 @@ static void mvpp2_port_enable(struct mvpp2_port *port)
 	u32 val;
 
 	/* Only GOP port 0 has an XLG MAC */
-	if (port->gop_id == 0 &&
-	    (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-	     port->phy_interface == PHY_INTERFACE_MODE_10GKR)) {
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) {
 		val = readl(port->base + MVPP22_XLG_CTRL0_REG);
-		val |= MVPP22_XLG_CTRL0_PORT_EN |
-		       MVPP22_XLG_CTRL0_MAC_RESET_DIS;
+		val |= MVPP22_XLG_CTRL0_PORT_EN;
 		val &= ~MVPP22_XLG_CTRL0_MIB_CNT_DIS;
 		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
 	} else {
@@ -1204,21 +1197,15 @@ static void mvpp2_port_disable(struct mvpp2_port *port)
 	u32 val;
 
 	/* Only GOP port 0 has an XLG MAC */
-	if (port->gop_id == 0 &&
-	    (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-	     port->phy_interface == PHY_INTERFACE_MODE_10GKR)) {
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) {
 		val = readl(port->base + MVPP22_XLG_CTRL0_REG);
 		val &= ~MVPP22_XLG_CTRL0_PORT_EN;
 		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
-
-		/* Disable & reset should be done separately */
-		val &= ~MVPP22_XLG_CTRL0_MAC_RESET_DIS;
-		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
-	} else {
-		val = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
-		val &= ~(MVPP2_GMAC_PORT_EN_MASK);
-		writel(val, port->base + MVPP2_GMAC_CTRL_0_REG);
 	}
+
+	val = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
+	val &= ~(MVPP2_GMAC_PORT_EN_MASK);
+	writel(val, port->base + MVPP2_GMAC_CTRL_0_REG);
 }
 
 /* Set IEEE 802.3x Flow Control Xon Packet Transmission Mode */
@@ -1244,9 +1231,8 @@ static void mvpp2_port_loopback_set(struct mvpp2_port *port,
 	else
 		val &= ~MVPP2_GMAC_GMII_LB_EN_MASK;
 
-	if (port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX)
+	if (phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII)
 		val |= MVPP2_GMAC_PCS_LB_EN_MASK;
 	else
 		val &= ~MVPP2_GMAC_PCS_LB_EN_MASK;
@@ -1272,6 +1258,17 @@ static u64 mvpp2_read_count(struct mvpp2_port *port,
 	return val;
 }
 
+/* Some counters are accessed indirectly by first writing an index to
+ * MVPP2_CTRS_IDX. The index can represent various resources depending on the
+ * register we access, it can be a hit counter for some classification tables,
+ * a counter specific to a rxq, a txq or a buffer pool.
+ */
+static u32 mvpp2_read_index(struct mvpp2 *priv, u32 index, u32 reg)
+{
+	mvpp2_write(priv, MVPP2_CTRS_IDX, index);
+	return mvpp2_read(priv, reg);
+}
+
 /* Due to the fact that software statistics and hardware statistics are, by
  * design, incremented at different moments in the chain of packet processing,
  * it is very likely that incoming packets could have been dropped after being
@@ -1281,7 +1278,7 @@ static u64 mvpp2_read_count(struct mvpp2_port *port,
  * Hence, statistics gathered from userspace with ifconfig (software) and
  * ethtool (hardware) cannot be compared.
  */
-static const struct mvpp2_ethtool_counter mvpp2_ethtool_regs[] = {
+static const struct mvpp2_ethtool_counter mvpp2_ethtool_mib_regs[] = {
 	{ MVPP2_MIB_GOOD_OCTETS_RCVD, "good_octets_received", true },
 	{ MVPP2_MIB_BAD_OCTETS_RCVD, "bad_octets_received" },
 	{ MVPP2_MIB_CRC_ERRORS_SENT, "crc_errors_sent" },
@@ -1311,16 +1308,103 @@ static const struct mvpp2_ethtool_counter mvpp2_ethtool_regs[] = {
 	{ MVPP2_MIB_LATE_COLLISION, "late_collision" },
 };
 
+static const struct mvpp2_ethtool_counter mvpp2_ethtool_port_regs[] = {
+	{ MVPP2_OVERRUN_ETH_DROP, "rx_fifo_or_parser_overrun_drops" },
+	{ MVPP2_CLS_ETH_DROP, "rx_classifier_drops" },
+};
+
+static const struct mvpp2_ethtool_counter mvpp2_ethtool_txq_regs[] = {
+	{ MVPP2_TX_DESC_ENQ_CTR, "txq_%d_desc_enqueue" },
+	{ MVPP2_TX_DESC_ENQ_TO_DDR_CTR, "txq_%d_desc_enqueue_to_ddr" },
+	{ MVPP2_TX_BUFF_ENQ_TO_DDR_CTR, "txq_%d_buff_euqueue_to_ddr" },
+	{ MVPP2_TX_DESC_ENQ_HW_FWD_CTR, "txq_%d_desc_hardware_forwarded" },
+	{ MVPP2_TX_PKTS_DEQ_CTR, "txq_%d_packets_dequeued" },
+	{ MVPP2_TX_PKTS_FULL_QUEUE_DROP_CTR, "txq_%d_queue_full_drops" },
+	{ MVPP2_TX_PKTS_EARLY_DROP_CTR, "txq_%d_packets_early_drops" },
+	{ MVPP2_TX_PKTS_BM_DROP_CTR, "txq_%d_packets_bm_drops" },
+	{ MVPP2_TX_PKTS_BM_MC_DROP_CTR, "txq_%d_packets_rep_bm_drops" },
+};
+
+static const struct mvpp2_ethtool_counter mvpp2_ethtool_rxq_regs[] = {
+	{ MVPP2_RX_DESC_ENQ_CTR, "rxq_%d_desc_enqueue" },
+	{ MVPP2_RX_PKTS_FULL_QUEUE_DROP_CTR, "rxq_%d_queue_full_drops" },
+	{ MVPP2_RX_PKTS_EARLY_DROP_CTR, "rxq_%d_packets_early_drops" },
+	{ MVPP2_RX_PKTS_BM_DROP_CTR, "rxq_%d_packets_bm_drops" },
+};
+
+#define MVPP2_N_ETHTOOL_STATS(ntxqs, nrxqs)	(ARRAY_SIZE(mvpp2_ethtool_mib_regs) + \
+						 ARRAY_SIZE(mvpp2_ethtool_port_regs) + \
+						 (ARRAY_SIZE(mvpp2_ethtool_txq_regs) * (ntxqs)) + \
+						 (ARRAY_SIZE(mvpp2_ethtool_rxq_regs) * (nrxqs)))
+
 static void mvpp2_ethtool_get_strings(struct net_device *netdev, u32 sset,
 				      u8 *data)
 {
-	if (sset == ETH_SS_STATS) {
-		int i;
+	struct mvpp2_port *port = netdev_priv(netdev);
+	int i, q;
+
+	if (sset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_mib_regs); i++) {
+		strscpy(data, mvpp2_ethtool_mib_regs[i].string,
+			ETH_GSTRING_LEN);
+		data += ETH_GSTRING_LEN;
+	}
 
-		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++)
-			memcpy(data + i * ETH_GSTRING_LEN,
-			       &mvpp2_ethtool_regs[i].string, ETH_GSTRING_LEN);
+	for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_port_regs); i++) {
+		strscpy(data, mvpp2_ethtool_port_regs[i].string,
+			ETH_GSTRING_LEN);
+		data += ETH_GSTRING_LEN;
 	}
+
+	for (q = 0; q < port->ntxqs; q++) {
+		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_txq_regs); i++) {
+			snprintf(data, ETH_GSTRING_LEN,
+				 mvpp2_ethtool_txq_regs[i].string, q);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+
+	for (q = 0; q < port->nrxqs; q++) {
+		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_rxq_regs); i++) {
+			snprintf(data, ETH_GSTRING_LEN,
+				 mvpp2_ethtool_rxq_regs[i].string,
+				 q);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+}
+
+static void mvpp2_read_stats(struct mvpp2_port *port)
+{
+	u64 *pstats;
+	int i, q;
+
+	pstats = port->ethtool_stats;
+
+	for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_mib_regs); i++)
+		*pstats++ += mvpp2_read_count(port, &mvpp2_ethtool_mib_regs[i]);
+
+	for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_port_regs); i++)
+		*pstats++ += mvpp2_read(port->priv,
+					mvpp2_ethtool_port_regs[i].offset +
+					4 * port->id);
+
+	for (q = 0; q < port->ntxqs; q++)
+		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_txq_regs); i++)
+			*pstats++ += mvpp2_read_index(port->priv,
+						      MVPP22_CTRS_TX_CTR(port->id, i),
+						      mvpp2_ethtool_txq_regs[i].offset);
+
+	/* Rxqs are numbered from 0 from the user standpoint, but not from the
+	 * driver's. We need to add the  port->first_rxq offset.
+	 */
+	for (q = 0; q < port->nrxqs; q++)
+		for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_rxq_regs); i++)
+			*pstats++ += mvpp2_read_index(port->priv,
+						      port->first_rxq + i,
+						      mvpp2_ethtool_rxq_regs[i].offset);
 }
 
 static void mvpp2_gather_hw_statistics(struct work_struct *work)
@@ -1328,14 +1412,10 @@ static void mvpp2_gather_hw_statistics(struct work_struct *work)
 	struct delayed_work *del_work = to_delayed_work(work);
 	struct mvpp2_port *port = container_of(del_work, struct mvpp2_port,
 					       stats_work);
-	u64 *pstats;
-	int i;
 
 	mutex_lock(&port->gather_stats_lock);
 
-	pstats = port->ethtool_stats;
-	for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++)
-		*pstats++ += mvpp2_read_count(port, &mvpp2_ethtool_regs[i]);
+	mvpp2_read_stats(port);
 
 	/* No need to read again the counters right after this function if it
 	 * was called asynchronously by the user (ie. use of ethtool).
@@ -1359,34 +1439,84 @@ static void mvpp2_ethtool_get_stats(struct net_device *dev,
 
 	mutex_lock(&port->gather_stats_lock);
 	memcpy(data, port->ethtool_stats,
-	       sizeof(u64) * ARRAY_SIZE(mvpp2_ethtool_regs));
+	       sizeof(u64) * MVPP2_N_ETHTOOL_STATS(port->ntxqs, port->nrxqs));
 	mutex_unlock(&port->gather_stats_lock);
 }
 
 static int mvpp2_ethtool_get_sset_count(struct net_device *dev, int sset)
 {
+	struct mvpp2_port *port = netdev_priv(dev);
+
 	if (sset == ETH_SS_STATS)
-		return ARRAY_SIZE(mvpp2_ethtool_regs);
+		return MVPP2_N_ETHTOOL_STATS(port->ntxqs, port->nrxqs);
 
 	return -EOPNOTSUPP;
 }
 
-static void mvpp2_port_reset(struct mvpp2_port *port)
+static void mvpp2_mac_reset_assert(struct mvpp2_port *port)
 {
 	u32 val;
-	unsigned int i;
-
-	/* Read the GOP statistics to reset the hardware counters */
-	for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++)
-		mvpp2_read_count(port, &mvpp2_ethtool_regs[i]);
 
-	val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) &
-		    ~MVPP2_GMAC_PORT_RESET_MASK;
+	val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) |
+	      MVPP2_GMAC_PORT_RESET_MASK;
 	writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
 
-	while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) &
-	       MVPP2_GMAC_PORT_RESET_MASK)
-		continue;
+	if (port->priv->hw_version == MVPP22 && port->gop_id == 0) {
+		val = readl(port->base + MVPP22_XLG_CTRL0_REG) &
+		      ~MVPP22_XLG_CTRL0_MAC_RESET_DIS;
+		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+	}
+}
+
+static void mvpp22_pcs_reset_assert(struct mvpp2_port *port)
+{
+	struct mvpp2 *priv = port->priv;
+	void __iomem *mpcs, *xpcs;
+	u32 val;
+
+	if (port->priv->hw_version != MVPP22 || port->gop_id != 0)
+		return;
+
+	mpcs = priv->iface_base + MVPP22_MPCS_BASE(port->gop_id);
+	xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
+
+	val = readl(mpcs + MVPP22_MPCS_CLK_RESET);
+	val &= ~(MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX);
+	val |= MVPP22_MPCS_CLK_RESET_DIV_SET;
+	writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
+
+	val = readl(xpcs + MVPP22_XPCS_CFG0);
+	writel(val & ~MVPP22_XPCS_CFG0_RESET_DIS, xpcs + MVPP22_XPCS_CFG0);
+}
+
+static void mvpp22_pcs_reset_deassert(struct mvpp2_port *port)
+{
+	struct mvpp2 *priv = port->priv;
+	void __iomem *mpcs, *xpcs;
+	u32 val;
+
+	if (port->priv->hw_version != MVPP22 || port->gop_id != 0)
+		return;
+
+	mpcs = priv->iface_base + MVPP22_MPCS_BASE(port->gop_id);
+	xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
+
+	switch (port->phy_interface) {
+	case PHY_INTERFACE_MODE_10GKR:
+		val = readl(mpcs + MVPP22_MPCS_CLK_RESET);
+		val |= MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX |
+		       MAC_CLK_RESET_SD_TX;
+		val &= ~MVPP22_MPCS_CLK_RESET_DIV_SET;
+		writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
+		break;
+	case PHY_INTERFACE_MODE_XAUI:
+	case PHY_INTERFACE_MODE_RXAUI:
+		val = readl(xpcs + MVPP22_XPCS_CFG0);
+		writel(val | MVPP22_XPCS_CFG0_RESET_DIS, xpcs + MVPP22_XPCS_CFG0);
+		break;
+	default:
+		break;
+	}
 }
 
 /* Change maximum receive size of the port */
@@ -1416,7 +1546,7 @@ static inline void mvpp2_xlg_max_rx_size_set(struct mvpp2_port *port)
 /* Set defaults to the MVPP2 port */
 static void mvpp2_defaults_set(struct mvpp2_port *port)
 {
-	int tx_port_num, val, queue, ptxq, lrxq;
+	int tx_port_num, val, queue, lrxq;
 
 	if (port->priv->hw_version == MVPP21) {
 		/* Update TX FIFO MIN Threshold */
@@ -1437,11 +1567,9 @@ static void mvpp2_defaults_set(struct mvpp2_port *port)
 	mvpp2_write(port->priv, MVPP2_TXP_SCHED_FIXED_PRIO_REG, 0);
 
 	/* Close bandwidth for all queues */
-	for (queue = 0; queue < MVPP2_MAX_TXQ; queue++) {
-		ptxq = mvpp2_txq_phys(port->id, queue);
+	for (queue = 0; queue < MVPP2_MAX_TXQ; queue++)
 		mvpp2_write(port->priv,
-			    MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(ptxq), 0);
-	}
+			    MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(queue), 0);
 
 	/* Set refill period to 1 usec, refill tokens
 	 * and bucket size to maximum
@@ -2297,7 +2425,7 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port,
 	txq->descs_dma         = 0;
 
 	/* Set minimum bandwidth for disabled TXQs */
-	mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->id), 0);
+	mvpp2_write(port->priv, MVPP2_TXQ_SCHED_TOKEN_CNTR_REG(txq->log_id), 0);
 
 	/* Set Tx descriptors queue starting address and size */
 	thread = mvpp2_cpu_to_thread(port->priv, get_cpu());
@@ -2462,8 +2590,7 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id)
 
 	mvpp22_gop_mask_irq(port);
 
-	if (port->gop_id == 0 &&
-	    port->phy_interface == PHY_INTERFACE_MODE_10GKR) {
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) {
 		val = readl(port->base + MVPP22_XLG_INT_STAT);
 		if (val & MVPP22_XLG_INT_STAT_LINK) {
 			event = true;
@@ -2472,9 +2599,8 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id)
 				link = true;
 		}
 	} else if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-		   port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-		   port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-		   port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+		   phy_interface_mode_is_8023z(port->phy_interface) ||
+		   port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		val = readl(port->base + MVPP22_GMAC_INT_STAT);
 		if (val & MVPP22_GMAC_INT_STAT_LINK) {
 			event = true;
@@ -3143,19 +3269,26 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port)
 {
 	u32 ctrl3;
 
+	/* Set the GMAC & XLG MAC in reset */
+	mvpp2_mac_reset_assert(port);
+
+	/* Set the MPCS and XPCS in reset */
+	mvpp22_pcs_reset_assert(port);
+
 	/* comphy reconfiguration */
 	mvpp22_comphy_init(port);
 
 	/* gop reconfiguration */
 	mvpp22_gop_init(port);
 
+	mvpp22_pcs_reset_deassert(port);
+
 	/* Only GOP port 0 has an XLG MAC */
 	if (port->gop_id == 0) {
 		ctrl3 = readl(port->base + MVPP22_XLG_CTRL3_REG);
 		ctrl3 &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
 
-		if (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-		    port->phy_interface == PHY_INTERFACE_MODE_10GKR)
+		if (mvpp2_is_xlg(port->phy_interface))
 			ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_10G;
 		else
 			ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC;
@@ -3163,9 +3296,7 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port)
 		writel(ctrl3, port->base + MVPP22_XLG_CTRL3_REG);
 	}
 
-	if (port->gop_id == 0 &&
-	    (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-	     port->phy_interface == PHY_INTERFACE_MODE_10GKR))
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface))
 		mvpp2_xlg_max_rx_size_set(port);
 	else
 		mvpp2_gmac_max_rx_size_set(port);
@@ -3197,9 +3328,9 @@ static void mvpp2_start_dev(struct mvpp2_port *port)
 		struct phylink_link_state state = {
 			.interface = port->phy_interface,
 		};
-		mvpp2_mac_config(port->dev, MLO_AN_INBAND, &state);
-		mvpp2_mac_link_up(port->dev, MLO_AN_INBAND, port->phy_interface,
-				  NULL);
+		mvpp2_mac_config(&port->phylink_config, MLO_AN_INBAND, &state);
+		mvpp2_mac_link_up(&port->phylink_config, MLO_AN_INBAND,
+				  port->phy_interface, NULL);
 	}
 
 	netif_tx_start_all_queues(port->dev);
@@ -3483,6 +3614,9 @@ static int mvpp2_stop(struct net_device *dev)
 
 	cancel_delayed_work_sync(&port->stats_work);
 
+	mvpp2_mac_reset_assert(port);
+	mvpp22_pcs_reset_assert(port);
+
 	return 0;
 }
 
@@ -3696,9 +3830,9 @@ static int mvpp2_set_features(struct net_device *dev,
 
 	if (changed & NETIF_F_RXHASH) {
 		if (features & NETIF_F_RXHASH)
-			mvpp22_rss_enable(port);
+			mvpp22_port_rss_enable(port);
 		else
-			mvpp22_rss_disable(port);
+			mvpp22_port_rss_disable(port);
 	}
 
 	return 0;
@@ -3892,7 +4026,7 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 				   struct ethtool_rxnfc *info, u32 *rules)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
-	int ret = 0;
+	int ret = 0, i, loc = 0;
 
 	if (!mvpp22_rss_is_supported())
 		return -EOPNOTSUPP;
@@ -3904,6 +4038,18 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 	case ETHTOOL_GRXRINGS:
 		info->data = port->nrxqs;
 		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		info->rule_cnt = port->n_rfs_rules;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		ret = mvpp2_ethtool_cls_rule_get(port, info);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		for (i = 0; i < MVPP2_N_RFS_ENTRIES_PER_FLOW; i++) {
+			if (port->rfs_rules[i])
+				rules[loc++] = i;
+		}
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -3924,6 +4070,12 @@ static int mvpp2_ethtool_set_rxnfc(struct net_device *dev,
 	case ETHTOOL_SRXFH:
 		ret = mvpp2_ethtool_rxfh_set(port, info);
 		break;
+	case ETHTOOL_SRXCLSRLINS:
+		ret = mvpp2_ethtool_cls_rule_ins(port, info);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = mvpp2_ethtool_cls_rule_del(port, info);
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3939,24 +4091,25 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
 				  u8 *hfunc)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
 
 	if (!mvpp22_rss_is_supported())
 		return -EOPNOTSUPP;
 
 	if (indir)
-		memcpy(indir, port->indir,
-		       ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
+		ret = mvpp22_port_rss_ctx_indir_get(port, 0, indir);
 
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_CRC32;
 
-	return 0;
+	return ret;
 }
 
 static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
 				  const u8 *key, const u8 hfunc)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
 
 	if (!mvpp22_rss_is_supported())
 		return -EOPNOTSUPP;
@@ -3967,15 +4120,58 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
 	if (key)
 		return -EOPNOTSUPP;
 
-	if (indir) {
-		memcpy(port->indir, indir,
-		       ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
-		mvpp22_rss_fill_table(port, port->id);
-	}
+	if (indir)
+		ret = mvpp22_port_rss_ctx_indir_set(port, 0, indir);
 
-	return 0;
+	return ret;
 }
 
+static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir,
+					  u8 *key, u8 *hfunc, u32 rss_context)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_CRC32;
+
+	if (indir)
+		ret = mvpp22_port_rss_ctx_indir_get(port, rss_context, indir);
+
+	return ret;
+}
+
+static int mvpp2_ethtool_set_rxfh_context(struct net_device *dev,
+					  const u32 *indir, const u8 *key,
+					  const u8 hfunc, u32 *rss_context,
+					  bool delete)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+	int ret;
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
+		return -EOPNOTSUPP;
+
+	if (key)
+		return -EOPNOTSUPP;
+
+	if (delete)
+		return mvpp22_port_rss_ctx_delete(port, *rss_context);
+
+	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
+		ret = mvpp22_port_rss_ctx_create(port, rss_context);
+		if (ret)
+			return ret;
+	}
+
+	return mvpp22_port_rss_ctx_indir_set(port, *rss_context, indir);
+}
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -4012,7 +4208,8 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= mvpp2_ethtool_get_rxfh,
 	.set_rxfh		= mvpp2_ethtool_set_rxfh,
-
+	.get_rxfh_context	= mvpp2_ethtool_get_rxfh_context,
+	.set_rxfh_context	= mvpp2_ethtool_set_rxfh_context,
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
@@ -4072,8 +4269,8 @@ static int mvpp2_multi_queue_vectors_init(struct mvpp2_port *port,
 			snprintf(irqname, sizeof(irqname), "hif%d", i);
 
 		if (queue_mode == MVPP2_QDIST_MULTI_MODE) {
-			v->first_rxq = i * MVPP2_DEFAULT_RXQ;
-			v->nrxqs = MVPP2_DEFAULT_RXQ;
+			v->first_rxq = i;
+			v->nrxqs = 1;
 		} else if (queue_mode == MVPP2_QDIST_SINGLE_MODE &&
 			   i == (port->nqvecs - 1)) {
 			v->first_rxq = 0;
@@ -4166,8 +4363,7 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	    MVPP2_MAX_PORTS * priv->max_port_rxqs)
 		return -EINVAL;
 
-	if (port->nrxqs % MVPP2_DEFAULT_RXQ ||
-	    port->nrxqs > priv->max_port_rxqs || port->ntxqs > MVPP2_MAX_TXQ)
+	if (port->nrxqs > priv->max_port_rxqs || port->ntxqs > MVPP2_MAX_TXQ)
 		return -EINVAL;
 
 	/* Disable port */
@@ -4257,7 +4453,7 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	mvpp2_cls_port_config(port);
 
 	if (mvpp22_rss_is_supported())
-		mvpp22_rss_port_init(port);
+		mvpp22_port_rss_init(port);
 
 	/* Provide an initial Rx packet size */
 	port->pkt_size = MVPP2_RX_PKT_SIZE(port->dev->mtu);
@@ -4267,6 +4463,11 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	if (err)
 		goto err_free_percpu;
 
+	/* Clear all port stats */
+	mvpp2_read_stats(port);
+	memset(port->ethtool_stats, 0,
+	       MVPP2_N_ETHTOOL_STATS(port->ntxqs, port->nrxqs) * sizeof(u64));
+
 	return 0;
 
 err_free_percpu:
@@ -4356,11 +4557,12 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv,
 	eth_hw_addr_random(dev);
 }
 
-static void mvpp2_phylink_validate(struct net_device *dev,
+static void mvpp2_phylink_validate(struct phylink_config *config,
 				   unsigned long *supported,
 				   struct phylink_link_state *state)
 {
-	struct mvpp2_port *port = netdev_priv(dev);
+	struct mvpp2_port *port = container_of(config, struct mvpp2_port,
+					       phylink_config);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 
 	/* Invalid combinations */
@@ -4374,7 +4576,7 @@ static void mvpp2_phylink_validate(struct net_device *dev,
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
-		if (port->gop_id == 0)
+		if (port->priv->hw_version == MVPP22 && port->gop_id == 0)
 			goto empty_set;
 		break;
 	default:
@@ -4414,6 +4616,7 @@ static void mvpp2_phylink_validate(struct net_device *dev,
 	case PHY_INTERFACE_MODE_2500BASEX:
 		phylink_set(mask, 1000baseT_Full);
 		phylink_set(mask, 1000baseX_Full);
+		phylink_set(mask, 2500baseT_Full);
 		phylink_set(mask, 2500baseX_Full);
 		break;
 	default:
@@ -4483,10 +4686,11 @@ static void mvpp2_gmac_link_state(struct mvpp2_port *port,
 		state->pause |= MLO_PAUSE_TX;
 }
 
-static int mvpp2_phylink_mac_link_state(struct net_device *dev,
+static int mvpp2_phylink_mac_link_state(struct phylink_config *config,
 					struct phylink_link_state *state)
 {
-	struct mvpp2_port *port = netdev_priv(dev);
+	struct mvpp2_port *port = container_of(config, struct mvpp2_port,
+					       phylink_config);
 
 	if (port->priv->hw_version == MVPP22 && port->gop_id == 0) {
 		u32 mode = readl(port->base + MVPP22_XLG_CTRL3_REG);
@@ -4502,134 +4706,203 @@ static int mvpp2_phylink_mac_link_state(struct net_device *dev,
 	return 1;
 }
 
-static void mvpp2_mac_an_restart(struct net_device *dev)
+static void mvpp2_mac_an_restart(struct phylink_config *config)
 {
-	struct mvpp2_port *port = netdev_priv(dev);
-	u32 val;
-
-	if (port->phy_interface != PHY_INTERFACE_MODE_SGMII)
-		return;
+	struct mvpp2_port *port = container_of(config, struct mvpp2_port,
+					       phylink_config);
+	u32 val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
 
-	val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-	/* The RESTART_AN bit is cleared by the h/w after restarting the AN
-	 * process.
-	 */
-	val |= MVPP2_GMAC_IN_BAND_RESTART_AN | MVPP2_GMAC_IN_BAND_AUTONEG;
-	writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	writel(val | MVPP2_GMAC_IN_BAND_RESTART_AN,
+	       port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	writel(val & ~MVPP2_GMAC_IN_BAND_RESTART_AN,
+	       port->base + MVPP2_GMAC_AUTONEG_CONFIG);
 }
 
 static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode,
 			     const struct phylink_link_state *state)
 {
-	u32 ctrl0, ctrl4;
+	u32 old_ctrl0, ctrl0;
+	u32 old_ctrl4, ctrl4;
+
+	old_ctrl0 = ctrl0 = readl(port->base + MVPP22_XLG_CTRL0_REG);
+	old_ctrl4 = ctrl4 = readl(port->base + MVPP22_XLG_CTRL4_REG);
 
-	ctrl0 = readl(port->base + MVPP22_XLG_CTRL0_REG);
-	ctrl4 = readl(port->base + MVPP22_XLG_CTRL4_REG);
+	ctrl0 |= MVPP22_XLG_CTRL0_MAC_RESET_DIS;
 
 	if (state->pause & MLO_PAUSE_TX)
 		ctrl0 |= MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN;
+	else
+		ctrl0 &= ~MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN;
+
 	if (state->pause & MLO_PAUSE_RX)
 		ctrl0 |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;
+	else
+		ctrl0 &= ~MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;
 
 	ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC;
 	ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC |
 		 MVPP22_XLG_CTRL4_EN_IDLE_CHECK;
 
-	writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG);
-	writel(ctrl4, port->base + MVPP22_XLG_CTRL4_REG);
+	if (old_ctrl0 != ctrl0)
+		writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG);
+	if (old_ctrl4 != ctrl4)
+		writel(ctrl4, port->base + MVPP22_XLG_CTRL4_REG);
+
+	if (!(old_ctrl0 & MVPP22_XLG_CTRL0_MAC_RESET_DIS)) {
+		while (!(readl(port->base + MVPP22_XLG_CTRL0_REG) &
+			 MVPP22_XLG_CTRL0_MAC_RESET_DIS))
+			continue;
+	}
 }
 
 static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode,
 			      const struct phylink_link_state *state)
 {
-	u32 an, ctrl0, ctrl2, ctrl4;
-
-	an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-	ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
-	ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
-	ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
+	u32 old_an, an;
+	u32 old_ctrl0, ctrl0;
+	u32 old_ctrl2, ctrl2;
+	u32 old_ctrl4, ctrl4;
 
-	/* Force link down */
-	an &= ~MVPP2_GMAC_FORCE_LINK_PASS;
-	an |= MVPP2_GMAC_FORCE_LINK_DOWN;
-	writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-
-	/* Set the GMAC in a reset state */
-	ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK;
-	writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+	old_an = an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	old_ctrl0 = ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
+	old_ctrl2 = ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
+	old_ctrl4 = ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
 
 	an &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED |
 		MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN |
 		MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG |
 		MVPP2_GMAC_CONFIG_FULL_DUPLEX | MVPP2_GMAC_AN_DUPLEX_EN |
-		MVPP2_GMAC_FORCE_LINK_DOWN);
+		MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS);
 	ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK;
-	ctrl2 &= ~(MVPP2_GMAC_PORT_RESET_MASK | MVPP2_GMAC_PCS_ENABLE_MASK);
-
-	if (state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    state->interface == PHY_INTERFACE_MODE_2500BASEX) {
-		/* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can
-		 * they negotiate duplex: they are always operating with a fixed
-		 * speed of 1000/2500Mbps in full duplex, so force 1000/2500
-		 * speed and full duplex here.
-		 */
-		ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK;
-		an |= MVPP2_GMAC_CONFIG_GMII_SPEED |
-		      MVPP2_GMAC_CONFIG_FULL_DUPLEX;
-	} else if (!phy_interface_mode_is_rgmii(state->interface)) {
-		an |= MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG;
+	ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PORT_RESET_MASK |
+		   MVPP2_GMAC_PCS_ENABLE_MASK);
+	ctrl4 &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN);
+
+	/* Configure port type */
+	if (phy_interface_mode_is_8023z(state->interface)) {
+		ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK;
+		ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+		ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS |
+			 MVPP22_CTRL4_DP_CLK_SEL |
+			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+	} else if (state->interface == PHY_INTERFACE_MODE_SGMII) {
+		ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK | MVPP2_GMAC_INBAND_AN_MASK;
+		ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+		ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS |
+			 MVPP22_CTRL4_DP_CLK_SEL |
+			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+	} else if (phy_interface_mode_is_rgmii(state->interface)) {
+		ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL;
+		ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
+			 MVPP22_CTRL4_SYNC_BYPASS_DIS |
+			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
 	}
 
-	if (state->duplex)
-		an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX;
+	/* Configure advertisement bits */
 	if (phylink_test(state->advertising, Pause))
 		an |= MVPP2_GMAC_FC_ADV_EN;
 	if (phylink_test(state->advertising, Asym_Pause))
 		an |= MVPP2_GMAC_FC_ADV_ASM_EN;
 
-	if (state->interface == PHY_INTERFACE_MODE_SGMII ||
-	    state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    state->interface == PHY_INTERFACE_MODE_2500BASEX) {
-		an |= MVPP2_GMAC_IN_BAND_AUTONEG;
-		ctrl2 |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK;
+	/* Configure negotiation style */
+	if (!phylink_autoneg_inband(mode)) {
+		/* Phy or fixed speed - no in-band AN */
+		if (state->duplex)
+			an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX;
 
-		ctrl4 &= ~(MVPP22_CTRL4_EXT_PIN_GMII_SEL |
-			   MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN);
-		ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS |
-			 MVPP22_CTRL4_DP_CLK_SEL |
-			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+		if (state->speed == SPEED_1000 || state->speed == SPEED_2500)
+			an |= MVPP2_GMAC_CONFIG_GMII_SPEED;
+		else if (state->speed == SPEED_100)
+			an |= MVPP2_GMAC_CONFIG_MII_SPEED;
 
 		if (state->pause & MLO_PAUSE_TX)
 			ctrl4 |= MVPP22_CTRL4_TX_FC_EN;
 		if (state->pause & MLO_PAUSE_RX)
 			ctrl4 |= MVPP22_CTRL4_RX_FC_EN;
-	} else if (phy_interface_mode_is_rgmii(state->interface)) {
-		an |= MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS;
+	} else if (state->interface == PHY_INTERFACE_MODE_SGMII) {
+		/* SGMII in-band mode receives the speed and duplex from
+		 * the PHY. Flow control information is not received. */
+		an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS);
+		an |= MVPP2_GMAC_IN_BAND_AUTONEG |
+		      MVPP2_GMAC_AN_SPEED_EN |
+		      MVPP2_GMAC_AN_DUPLEX_EN;
 
-		if (state->speed == SPEED_1000)
-			an |= MVPP2_GMAC_CONFIG_GMII_SPEED;
-		else if (state->speed == SPEED_100)
-			an |= MVPP2_GMAC_CONFIG_MII_SPEED;
+		if (state->pause & MLO_PAUSE_TX)
+			ctrl4 |= MVPP22_CTRL4_TX_FC_EN;
+		if (state->pause & MLO_PAUSE_RX)
+			ctrl4 |= MVPP22_CTRL4_RX_FC_EN;
+	} else if (phy_interface_mode_is_8023z(state->interface)) {
+		/* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can
+		 * they negotiate duplex: they are always operating with a fixed
+		 * speed of 1000/2500Mbps in full duplex, so force 1000/2500
+		 * speed and full duplex here.
+		 */
+		ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK;
+		an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS);
+		an |= MVPP2_GMAC_IN_BAND_AUTONEG |
+		      MVPP2_GMAC_CONFIG_GMII_SPEED |
+		      MVPP2_GMAC_CONFIG_FULL_DUPLEX;
 
-		ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL;
-		ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
-			 MVPP22_CTRL4_SYNC_BYPASS_DIS |
-			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+		if (state->pause & MLO_PAUSE_AN && state->an_enabled) {
+			an |= MVPP2_GMAC_FLOW_CTRL_AUTONEG;
+		} else {
+			if (state->pause & MLO_PAUSE_TX)
+				ctrl4 |= MVPP22_CTRL4_TX_FC_EN;
+			if (state->pause & MLO_PAUSE_RX)
+				ctrl4 |= MVPP22_CTRL4_RX_FC_EN;
+		}
 	}
 
-	writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG);
-	writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
-	writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG);
-	writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+/* Some fields of the auto-negotiation register require the port to be down when
+ * their value is updated.
+ */
+#define MVPP2_GMAC_AN_PORT_DOWN_MASK	\
+		(MVPP2_GMAC_IN_BAND_AUTONEG | \
+		 MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS | \
+		 MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED | \
+		 MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_CONFIG_FULL_DUPLEX | \
+		 MVPP2_GMAC_AN_DUPLEX_EN)
+
+	if ((old_ctrl0 ^ ctrl0) & MVPP2_GMAC_PORT_TYPE_MASK ||
+	    (old_ctrl2 ^ ctrl2) & MVPP2_GMAC_INBAND_AN_MASK ||
+	    (old_an ^ an) & MVPP2_GMAC_AN_PORT_DOWN_MASK) {
+		/* Force link down */
+		old_an &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+		old_an |= MVPP2_GMAC_FORCE_LINK_DOWN;
+		writel(old_an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+
+		/* Set the GMAC in a reset state - do this in a way that
+		 * ensures we clear it below.
+		 */
+		old_ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK;
+		writel(old_ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+	}
+
+	if (old_ctrl0 != ctrl0)
+		writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG);
+	if (old_ctrl2 != ctrl2)
+		writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+	if (old_ctrl4 != ctrl4)
+		writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG);
+	if (old_an != an)
+		writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+
+	if (old_ctrl2 & MVPP2_GMAC_PORT_RESET_MASK) {
+		while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) &
+		       MVPP2_GMAC_PORT_RESET_MASK)
+			continue;
+	}
 }
 
-static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
+static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode,
 			     const struct phylink_link_state *state)
 {
+	struct net_device *dev = to_net_dev(config->dev);
 	struct mvpp2_port *port = netdev_priv(dev);
+	bool change_interface = port->phy_interface != state->interface;
 
 	/* Check for invalid configuration */
-	if (state->interface == PHY_INTERFACE_MODE_10GKR && port->gop_id != 0) {
+	if (mvpp2_is_xlg(state->interface) && port->gop_id != 0) {
 		netdev_err(dev, "Invalid mode on %s\n", dev->name);
 		return;
 	}
@@ -4637,8 +4910,9 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 	/* Make sure the port is disabled when reconfiguring the mode */
 	mvpp2_port_disable(port);
 
-	if (port->priv->hw_version == MVPP22 &&
-	    port->phy_interface != state->interface) {
+	if (port->priv->hw_version == MVPP22 && change_interface) {
+		mvpp22_gop_mask_irq(port);
+
 		port->phy_interface = state->interface;
 
 		/* Reconfigure the serdes lanes */
@@ -4647,33 +4921,41 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 	}
 
 	/* mac (re)configuration */
-	if (state->interface == PHY_INTERFACE_MODE_10GKR)
+	if (mvpp2_is_xlg(state->interface))
 		mvpp2_xlg_config(port, mode, state);
 	else if (phy_interface_mode_is_rgmii(state->interface) ||
-		 state->interface == PHY_INTERFACE_MODE_SGMII ||
-		 state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-		 state->interface == PHY_INTERFACE_MODE_2500BASEX)
+		 phy_interface_mode_is_8023z(state->interface) ||
+		 state->interface == PHY_INTERFACE_MODE_SGMII)
 		mvpp2_gmac_config(port, mode, state);
 
 	if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK)
 		mvpp2_port_loopback_set(port, state);
 
+	if (port->priv->hw_version == MVPP22 && change_interface)
+		mvpp22_gop_unmask_irq(port);
+
 	mvpp2_port_enable(port);
 }
 
-static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode,
+static void mvpp2_mac_link_up(struct phylink_config *config, unsigned int mode,
 			      phy_interface_t interface, struct phy_device *phy)
 {
+	struct net_device *dev = to_net_dev(config->dev);
 	struct mvpp2_port *port = netdev_priv(dev);
 	u32 val;
 
-	if (!phylink_autoneg_inband(mode) &&
-	    interface != PHY_INTERFACE_MODE_10GKR) {
-		val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-		val &= ~MVPP2_GMAC_FORCE_LINK_DOWN;
-		if (phy_interface_mode_is_rgmii(interface))
+	if (!phylink_autoneg_inband(mode)) {
+		if (mvpp2_is_xlg(interface)) {
+			val = readl(port->base + MVPP22_XLG_CTRL0_REG);
+			val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_DOWN;
+			val |= MVPP22_XLG_CTRL0_FORCE_LINK_PASS;
+			writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+		} else {
+			val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+			val &= ~MVPP2_GMAC_FORCE_LINK_DOWN;
 			val |= MVPP2_GMAC_FORCE_LINK_PASS;
-		writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+			writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+		}
 	}
 
 	mvpp2_port_enable(port);
@@ -4683,31 +4965,31 @@ static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode,
 	netif_tx_wake_all_queues(dev);
 }
 
-static void mvpp2_mac_link_down(struct net_device *dev, unsigned int mode,
-				phy_interface_t interface)
+static void mvpp2_mac_link_down(struct phylink_config *config,
+				unsigned int mode, phy_interface_t interface)
 {
+	struct net_device *dev = to_net_dev(config->dev);
 	struct mvpp2_port *port = netdev_priv(dev);
 	u32 val;
 
-	if (!phylink_autoneg_inband(mode) &&
-	    interface != PHY_INTERFACE_MODE_10GKR) {
-		val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-		val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
-		val |= MVPP2_GMAC_FORCE_LINK_DOWN;
-		writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	if (!phylink_autoneg_inband(mode)) {
+		if (mvpp2_is_xlg(interface)) {
+			val = readl(port->base + MVPP22_XLG_CTRL0_REG);
+			val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_PASS;
+			val |= MVPP22_XLG_CTRL0_FORCE_LINK_DOWN;
+			writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+		} else {
+			val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+			val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+			val |= MVPP2_GMAC_FORCE_LINK_DOWN;
+			writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+		}
 	}
 
 	netif_tx_stop_all_queues(dev);
 	mvpp2_egress_disable(port);
 	mvpp2_ingress_disable(port);
 
-	/* When using link interrupts to notify phylink of a MAC state change,
-	 * we do not want the port to be disabled (we want to receive further
-	 * interrupts, to be notified when the port will have a link later).
-	 */
-	if (!port->has_phy)
-		return;
-
 	mvpp2_port_disable(port);
 }
 
@@ -4729,6 +5011,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	struct mvpp2_port *port;
 	struct mvpp2_port_pcpu *port_pcpu;
 	struct device_node *port_node = to_of_node(port_fwnode);
+	netdev_features_t features;
 	struct net_device *dev;
 	struct resource *res;
 	struct phylink *phylink;
@@ -4737,7 +5020,6 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	unsigned long flags = 0;
 	bool has_tx_irqs;
 	u32 id;
-	int features;
 	int phy_mode;
 	int err, i;
 
@@ -4749,10 +5031,18 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	}
 
 	ntxqs = MVPP2_MAX_TXQ;
-	if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_MULTI_MODE)
-		nrxqs = MVPP2_DEFAULT_RXQ * num_possible_cpus();
-	else
-		nrxqs = MVPP2_DEFAULT_RXQ;
+	if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_SINGLE_MODE) {
+		nrxqs = 1;
+	} else {
+		/* According to the PPv2.2 datasheet and our experiments on
+		 * PPv2.1, RX queues have an allocation granularity of 4 (when
+		 * more than a single one on PPv2.2).
+		 * Round up to nearest multiple of 4.
+		 */
+		nrxqs = (num_possible_cpus() + 3) & ~0x3;
+		if (nrxqs > MVPP2_PORT_MAX_RXQ)
+			nrxqs = MVPP2_PORT_MAX_RXQ;
+	}
 
 	dev = alloc_etherdev_mqs(sizeof(*port), ntxqs, nrxqs);
 	if (!dev)
@@ -4859,7 +5149,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	}
 
 	port->ethtool_stats = devm_kcalloc(&pdev->dev,
-					   ARRAY_SIZE(mvpp2_ethtool_regs),
+					   MVPP2_N_ETHTOOL_STATS(ntxqs, nrxqs),
 					   sizeof(u64), GFP_KERNEL);
 	if (!port->ethtool_stats) {
 		err = -ENOMEM;
@@ -4883,7 +5173,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 
 	mvpp2_port_periodic_xon_disable(port);
 
-	mvpp2_port_reset(port);
+	mvpp2_mac_reset_assert(port);
+	mvpp22_pcs_reset_assert(port);
 
 	port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
 	if (!port->pcpu) {
@@ -4912,8 +5203,10 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO |
 			    NETIF_F_HW_VLAN_CTAG_FILTER;
 
-	if (mvpp22_rss_is_supported())
+	if (mvpp22_rss_is_supported()) {
 		dev->hw_features |= NETIF_F_RXHASH;
+		dev->features |= NETIF_F_NTUPLE;
+	}
 
 	if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) {
 		dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
@@ -4932,8 +5225,11 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 
 	/* Phylink isn't used w/ ACPI as of now */
 	if (port_node) {
-		phylink = phylink_create(dev, port_fwnode, phy_mode,
-					 &mvpp2_phylink_ops);
+		port->phylink_config.dev = &dev->dev;
+		port->phylink_config.type = PHYLINK_NETDEV;
+
+		phylink = phylink_create(&port->phylink_config, port_fwnode,
+					 phy_mode, &mvpp2_phylink_ops);
 		if (IS_ERR(phylink)) {
 			err = PTR_ERR(phylink);
 			goto err_free_port_pcpu;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 392fd895f278..5692c6087bbb 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -312,7 +312,8 @@ static void mvpp2_prs_sram_shift_set(struct mvpp2_prs_entry *pe, int shift,
 	}
 
 	/* Set value */
-	pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] = shift & MVPP2_PRS_SRAM_SHIFT_MASK;
+	pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] |=
+		shift & MVPP2_PRS_SRAM_SHIFT_MASK;
 
 	/* Reset and set operation */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_SHIFT_OFFS,
@@ -1905,8 +1906,7 @@ static int mvpp2_prs_ip6_init(struct mvpp2 *priv)
 }
 
 /* Find tcam entry with matched pair <vid,port> */
-static int mvpp2_prs_vid_range_find(struct mvpp2 *priv, int pmap, u16 vid,
-				    u16 mask)
+static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask)
 {
 	unsigned char byte[2], enable[2];
 	struct mvpp2_prs_entry pe;
@@ -1914,13 +1914,13 @@ static int mvpp2_prs_vid_range_find(struct mvpp2 *priv, int pmap, u16 vid,
 	int tid;
 
 	/* Go through the all entries with MVPP2_PRS_LU_VID */
-	for (tid = MVPP2_PE_VID_FILT_RANGE_START;
-	     tid <= MVPP2_PE_VID_FILT_RANGE_END; tid++) {
-		if (!priv->prs_shadow[tid].valid ||
-		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
+	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
+	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
+		if (!port->priv->prs_shadow[tid].valid ||
+		    port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
 
 		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
 		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
@@ -1950,7 +1950,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 	memset(&pe, 0, sizeof(pe));
 
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, mask);
+	tid = mvpp2_prs_vid_range_find(port, vid, mask);
 
 	reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id));
 	if (reg_val & MVPP2_DSA_EXTENDED)
@@ -2008,7 +2008,7 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid)
 	int tid;
 
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(priv, (1 << port->id), vid, 0xfff);
+	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
 
 	/* No such entry */
 	if (tid < 0)
@@ -2026,8 +2026,10 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 
 	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
 	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
-		if (priv->prs_shadow[tid].valid)
-			mvpp2_prs_vid_entry_remove(port, tid);
+		if (priv->prs_shadow[tid].valid) {
+			mvpp2_prs_hw_inv(priv, tid);
+			priv->prs_shadow[tid].valid = false;
+		}
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig
index 35827bdf1878..711ada7139d3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/Kconfig
+++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Marvell OcteonTX2 drivers configuration
 #
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index f8a6d6e3cb7a..3aa998797bc1 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * PXA168 ethernet driver.
  * Most of the code is derived from mv643xx ethernet driver.
@@ -7,19 +8,6 @@
  *		Zhangfei Gao <zgao6@marvell.com>
  *		Philip Rakity <prakity@marvell.com>
  *		Mark Brown <markb@marvell.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/bitops.h>
@@ -201,6 +189,7 @@ struct tx_desc {
 };
 
 struct pxa168_eth_private {
+	struct platform_device *pdev;
 	int port_num;		/* User Ethernet port number    */
 	int phy_addr;
 	int phy_speed;
@@ -331,7 +320,7 @@ static void rxq_refill(struct net_device *dev)
 		used_rx_desc = pep->rx_used_desc_q;
 		p_used_rx_desc = &pep->p_rx_desc_area[used_rx_desc];
 		size = skb_end_pointer(skb) - skb->data;
-		p_used_rx_desc->buf_ptr = dma_map_single(NULL,
+		p_used_rx_desc->buf_ptr = dma_map_single(&pep->pdev->dev,
 							 skb->data,
 							 size,
 							 DMA_FROM_DEVICE);
@@ -743,7 +732,7 @@ static int txq_reclaim(struct net_device *dev, int force)
 				netdev_err(dev, "Error in TX\n");
 			dev->stats.tx_errors++;
 		}
-		dma_unmap_single(NULL, addr, count, DMA_TO_DEVICE);
+		dma_unmap_single(&pep->pdev->dev, addr, count, DMA_TO_DEVICE);
 		if (skb)
 			dev_kfree_skb_irq(skb);
 		released++;
@@ -805,7 +794,7 @@ static int rxq_process(struct net_device *dev, int budget)
 		if (rx_next_curr_desc == rx_used_desc)
 			pep->rx_resource_err = 1;
 		pep->rx_desc_count--;
-		dma_unmap_single(NULL, rx_desc->buf_ptr,
+		dma_unmap_single(&pep->pdev->dev, rx_desc->buf_ptr,
 				 rx_desc->buf_size,
 				 DMA_FROM_DEVICE);
 		received_packets++;
@@ -1274,7 +1263,8 @@ pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	length = skb->len;
 	pep->tx_skb[tx_index] = skb;
 	desc->byte_cnt = length;
-	desc->buf_ptr = dma_map_single(NULL, skb->data, length, DMA_TO_DEVICE);
+	desc->buf_ptr = dma_map_single(&pep->pdev->dev, skb->data, length,
+					DMA_TO_DEVICE);
 
 	skb_tx_timestamp(skb);
 
@@ -1459,7 +1449,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	if (pdev->dev.of_node)
 		mac_addr = of_get_mac_address(pdev->dev.of_node);
 
-	if (mac_addr && is_valid_ether_addr(mac_addr)) {
+	if (!IS_ERR_OR_NULL(mac_addr)) {
 		ether_addr_copy(dev->dev_addr, mac_addr);
 	} else {
 		/* try reading the mac address, if set by the bootloader */
@@ -1528,6 +1518,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	if (err)
 		goto err_free_mdio;
 
+	pep->pdev = pdev;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 	pxa168_init_hw(pep);
 	err = register_netdev(dev);
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 654ac534b10e..35a92fd2cf39 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * New driver for Marvell Yukon chipset and SysKonnect Gigabit
  * Ethernet adapters. Based on earlier sk98lin, e100 and
@@ -8,19 +9,6 @@
  * those should be done at higher levels.
  *
  * Copyright (C) 2004, 2005 Stephen Hemminger <shemminger@osdl.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index f3a5fa84860f..fe518c854d1f 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * New driver for Marvell Yukon 2 chipset.
  * Based on earlier sk98lin, and skge driver.
@@ -7,19 +8,6 @@
  * those should be done at higher levels.
  *
  * Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -46,6 +34,7 @@
 #include <linux/mii.h>
 #include <linux/of_device.h>
 #include <linux/of_net.h>
+#include <linux/dmi.h>
 
 #include <asm/irq.h>
 
@@ -93,7 +82,7 @@ static int copybreak __read_mostly = 128;
 module_param(copybreak, int, 0);
 MODULE_PARM_DESC(copybreak, "Receive copy threshold");
 
-static int disable_msi = 0;
+static int disable_msi = -1;
 module_param(disable_msi, int, 0);
 MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
 
@@ -1138,9 +1127,6 @@ static inline void sky2_put_idx(struct sky2_hw *hw, unsigned q, u16 idx)
 	/* Make sure write' to descriptors are complete before we tell hardware */
 	wmb();
 	sky2_write16(hw, Y2_QADDR(q, PREF_UNIT_PUT_IDX), idx);
-
-	/* Synchronize I/O on since next processor may write to tail */
-	mmiowb();
 }
 
 
@@ -1353,7 +1339,6 @@ stopped:
 
 	/* reset the Rx prefetch unit */
 	sky2_write32(hw, Y2_QADDR(rxq, PREF_UNIT_CTRL), PREF_UNIT_RST_SET);
-	mmiowb();
 }
 
 /* Clean out receive buffer area, assumes receiver hardware stopped */
@@ -4807,8 +4792,8 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port,
 	 * 2) from internal registers set by bootloader
 	 */
 	iap = of_get_mac_address(hw->pdev->dev.of_node);
-	if (iap)
-		memcpy(dev->dev_addr, iap, ETH_ALEN);
+	if (!IS_ERR(iap))
+		ether_addr_copy(dev->dev_addr, iap);
 	else
 		memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8,
 			      ETH_ALEN);
@@ -4917,6 +4902,24 @@ static const char *sky2_name(u8 chipid, char *buf, int sz)
 	return buf;
 }
 
+static const struct dmi_system_id msi_blacklist[] = {
+	{
+		.ident = "Dell Inspiron 1545",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1545"),
+		},
+	},
+	{
+		.ident = "Gateway P-79",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Gateway"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P-79"),
+		},
+	},
+	{}
+};
+
 static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *dev, *dev1;
@@ -5028,6 +5031,9 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_free_pci;
 	}
 
+	if (disable_msi == -1)
+		disable_msi = !!dmi_check_system(msi_blacklist);
+
 	if (!disable_msi && pci_enable_msi(pdev) == 0) {
 		err = sky2_test_msi(hw);
 		if (err) {
@@ -5073,7 +5079,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 200;
+	pdev->d3_delay = 300;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index f9149d2a4694..263cd0909fe0 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -1,6 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config NET_VENDOR_MEDIATEK
 	bool "MediaTek ethernet driver"
-	depends on ARCH_MEDIATEK
+	depends on ARCH_MEDIATEK || SOC_MT7621
 	---help---
 	  If you have a Mediatek SoC with ethernet, say Y.
 
diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index aa3f1c8ccd4a..2d8362f9341b 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -1,5 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Mediatek SoCs built-in ethernet macs
 #
 
-obj-$(CONFIG_NET_MEDIATEK_SOC)			+= mtk_eth_soc.o
+obj-$(CONFIG_NET_MEDIATEK_SOC)                 += mtk_eth.o
+mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c
new file mode 100644
index 000000000000..7f05880cf9ef
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018-2019 MediaTek Inc.
+
+/* A library for configuring path from GMAC/GDM to target PHY
+ *
+ * Author: Sean Wang <sean.wang@mediatek.com>
+ *
+ */
+
+#include <linux/phy.h>
+#include <linux/regmap.h>
+
+#include "mtk_eth_soc.h"
+
+struct mtk_eth_muxc {
+	const char	*name;
+	int		cap_bit;
+	int		(*set_path)(struct mtk_eth *eth, int path);
+};
+
+static const char *mtk_eth_path_name(int path)
+{
+	switch (path) {
+	case MTK_ETH_PATH_GMAC1_RGMII:
+		return "gmac1_rgmii";
+	case MTK_ETH_PATH_GMAC1_TRGMII:
+		return "gmac1_trgmii";
+	case MTK_ETH_PATH_GMAC1_SGMII:
+		return "gmac1_sgmii";
+	case MTK_ETH_PATH_GMAC2_RGMII:
+		return "gmac2_rgmii";
+	case MTK_ETH_PATH_GMAC2_SGMII:
+		return "gmac2_sgmii";
+	case MTK_ETH_PATH_GMAC2_GEPHY:
+		return "gmac2_gephy";
+	case MTK_ETH_PATH_GDM1_ESW:
+		return "gdm1_esw";
+	default:
+		return "unknown path";
+	}
+}
+
+static int set_mux_gdm1_to_gmac1_esw(struct mtk_eth *eth, int path)
+{
+	bool updated = true;
+	u32 val, mask, set;
+
+	switch (path) {
+	case MTK_ETH_PATH_GMAC1_SGMII:
+		mask = ~(u32)MTK_MUX_TO_ESW;
+		set = 0;
+		break;
+	case MTK_ETH_PATH_GDM1_ESW:
+		mask = ~(u32)MTK_MUX_TO_ESW;
+		set = MTK_MUX_TO_ESW;
+		break;
+	default:
+		updated = false;
+		break;
+	};
+
+	if (updated) {
+		val = mtk_r32(eth, MTK_MAC_MISC);
+		val = (val & mask) | set;
+		mtk_w32(eth, val, MTK_MAC_MISC);
+	}
+
+	dev_dbg(eth->dev, "path %s in %s updated = %d\n",
+		mtk_eth_path_name(path), __func__, updated);
+
+	return 0;
+}
+
+static int set_mux_gmac2_gmac0_to_gephy(struct mtk_eth *eth, int path)
+{
+	unsigned int val = 0;
+	bool updated = true;
+
+	switch (path) {
+	case MTK_ETH_PATH_GMAC2_GEPHY:
+		val = ~(u32)GEPHY_MAC_SEL;
+		break;
+	default:
+		updated = false;
+		break;
+	}
+
+	if (updated)
+		regmap_update_bits(eth->infra, INFRA_MISC2, GEPHY_MAC_SEL, val);
+
+	dev_dbg(eth->dev, "path %s in %s updated = %d\n",
+		mtk_eth_path_name(path), __func__, updated);
+
+	return 0;
+}
+
+static int set_mux_u3_gmac2_to_qphy(struct mtk_eth *eth, int path)
+{
+	unsigned int val = 0;
+	bool updated = true;
+
+	switch (path) {
+	case MTK_ETH_PATH_GMAC2_SGMII:
+		val = CO_QPHY_SEL;
+		break;
+	default:
+		updated = false;
+		break;
+	}
+
+	if (updated)
+		regmap_update_bits(eth->infra, INFRA_MISC2, CO_QPHY_SEL, val);
+
+	dev_dbg(eth->dev, "path %s in %s updated = %d\n",
+		mtk_eth_path_name(path), __func__, updated);
+
+	return 0;
+}
+
+static int set_mux_gmac1_gmac2_to_sgmii_rgmii(struct mtk_eth *eth, int path)
+{
+	unsigned int val = 0;
+	bool updated = true;
+
+	switch (path) {
+	case MTK_ETH_PATH_GMAC1_SGMII:
+		val = SYSCFG0_SGMII_GMAC1;
+		break;
+	case MTK_ETH_PATH_GMAC2_SGMII:
+		val = SYSCFG0_SGMII_GMAC2;
+		break;
+	case MTK_ETH_PATH_GMAC1_RGMII:
+	case MTK_ETH_PATH_GMAC2_RGMII:
+		regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val);
+		val &= SYSCFG0_SGMII_MASK;
+
+		if ((path == MTK_GMAC1_RGMII && val == SYSCFG0_SGMII_GMAC1) ||
+		    (path == MTK_GMAC2_RGMII && val == SYSCFG0_SGMII_GMAC2))
+			val = 0;
+		else
+			updated = false;
+		break;
+	default:
+		updated = false;
+		break;
+	};
+
+	if (updated)
+		regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0,
+				   SYSCFG0_SGMII_MASK, val);
+
+	dev_dbg(eth->dev, "path %s in %s updated = %d\n",
+		mtk_eth_path_name(path), __func__, updated);
+
+	return 0;
+}
+
+static int set_mux_gmac12_to_gephy_sgmii(struct mtk_eth *eth, int path)
+{
+	unsigned int val = 0;
+	bool updated = true;
+
+	regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val);
+
+	switch (path) {
+	case MTK_ETH_PATH_GMAC1_SGMII:
+		val |= SYSCFG0_SGMII_GMAC1_V2;
+		break;
+	case MTK_ETH_PATH_GMAC2_GEPHY:
+		val &= ~(u32)SYSCFG0_SGMII_GMAC2_V2;
+		break;
+	case MTK_ETH_PATH_GMAC2_SGMII:
+		val |= SYSCFG0_SGMII_GMAC2_V2;
+		break;
+	default:
+		updated = false;
+	};
+
+	if (updated)
+		regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0,
+				   SYSCFG0_SGMII_MASK, val);
+
+	dev_dbg(eth->dev, "path %s in %s updated = %d\n",
+		mtk_eth_path_name(path), __func__, updated);
+
+	return 0;
+}
+
+static const struct mtk_eth_muxc mtk_eth_muxc[] = {
+	{
+		.name = "mux_gdm1_to_gmac1_esw",
+		.cap_bit = MTK_ETH_MUX_GDM1_TO_GMAC1_ESW,
+		.set_path = set_mux_gdm1_to_gmac1_esw,
+	}, {
+		.name = "mux_gmac2_gmac0_to_gephy",
+		.cap_bit = MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY,
+		.set_path = set_mux_gmac2_gmac0_to_gephy,
+	}, {
+		.name = "mux_u3_gmac2_to_qphy",
+		.cap_bit = MTK_ETH_MUX_U3_GMAC2_TO_QPHY,
+		.set_path = set_mux_u3_gmac2_to_qphy,
+	}, {
+		.name = "mux_gmac1_gmac2_to_sgmii_rgmii",
+		.cap_bit = MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII,
+		.set_path = set_mux_gmac1_gmac2_to_sgmii_rgmii,
+	}, {
+		.name = "mux_gmac12_to_gephy_sgmii",
+		.cap_bit = MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII,
+		.set_path = set_mux_gmac12_to_gephy_sgmii,
+	},
+};
+
+static int mtk_eth_mux_setup(struct mtk_eth *eth, int path)
+{
+	int i, err = 0;
+
+	if (!MTK_HAS_CAPS(eth->soc->caps, path)) {
+		dev_err(eth->dev, "path %s isn't support on the SoC\n",
+			mtk_eth_path_name(path));
+		return -EINVAL;
+	}
+
+	if (!MTK_HAS_CAPS(eth->soc->caps, MTK_MUX))
+		return 0;
+
+	/* Setup MUX in path fabric */
+	for (i = 0; i < ARRAY_SIZE(mtk_eth_muxc); i++) {
+		if (MTK_HAS_CAPS(eth->soc->caps, mtk_eth_muxc[i].cap_bit)) {
+			err = mtk_eth_muxc[i].set_path(eth, path);
+			if (err)
+				goto out;
+		} else {
+			dev_dbg(eth->dev, "mux %s isn't present on the SoC\n",
+				mtk_eth_muxc[i].name);
+		}
+	}
+
+out:
+	return err;
+}
+
+static int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id)
+{
+	unsigned int val = 0;
+	int sid, err, path;
+
+	path = (mac_id == 0) ?  MTK_ETH_PATH_GMAC1_SGMII :
+				MTK_ETH_PATH_GMAC2_SGMII;
+
+	/* Setup proper MUXes along the path */
+	err = mtk_eth_mux_setup(eth, path);
+	if (err)
+		return err;
+
+	/* The path GMAC to SGMII will be enabled once the SGMIISYS is being
+	 * setup done.
+	 */
+	regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val);
+
+	regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0,
+			   SYSCFG0_SGMII_MASK, ~(u32)SYSCFG0_SGMII_MASK);
+
+	/* Decide how GMAC and SGMIISYS be mapped */
+	sid = (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_SGMII)) ? 0 : mac_id;
+
+	/* Setup SGMIISYS with the determined property */
+	if (MTK_HAS_FLAGS(eth->sgmii->flags[sid], MTK_SGMII_PHYSPEED_AN))
+		err = mtk_sgmii_setup_mode_an(eth->sgmii, sid);
+	else
+		err = mtk_sgmii_setup_mode_force(eth->sgmii, sid);
+
+	if (err)
+		return err;
+
+	regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0,
+			   SYSCFG0_SGMII_MASK, val);
+
+	return 0;
+}
+
+static int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id)
+{
+	int err, path = 0;
+
+	if (mac_id == 1)
+		path = MTK_ETH_PATH_GMAC2_GEPHY;
+
+	if (!path)
+		return -EINVAL;
+
+	/* Setup proper MUXes along the path */
+	err = mtk_eth_mux_setup(eth, path);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id)
+{
+	int err, path;
+
+	path = (mac_id == 0) ?  MTK_ETH_PATH_GMAC1_RGMII :
+				MTK_ETH_PATH_GMAC2_RGMII;
+
+	/* Setup proper MUXes along the path */
+	err = mtk_eth_mux_setup(eth, path);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+int mtk_setup_hw_path(struct mtk_eth *eth, int mac_id, int phymode)
+{
+	int err;
+
+	switch (phymode) {
+	case PHY_INTERFACE_MODE_TRGMII:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_REVMII:
+	case PHY_INTERFACE_MODE_RMII:
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_RGMII)) {
+			err = mtk_gmac_rgmii_path_setup(eth, mac_id);
+			if (err)
+				return err;
+		}
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII)) {
+			err = mtk_gmac_sgmii_path_setup(eth, mac_id);
+			if (err)
+				return err;
+		}
+		break;
+	case PHY_INTERFACE_MODE_GMII:
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_GEPHY)) {
+			err = mtk_gmac_gephy_path_setup(eth, mac_id);
+			if (err)
+				return err;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 49f926b7a91c..b20b3a5a1ebb 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1,11 +1,5 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
+// SPDX-License-Identifier: GPL-2.0-only
+/*
  *
  *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
  *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
@@ -54,8 +48,10 @@ static const struct mtk_ethtool_stats {
 };
 
 static const char * const mtk_clks_source_name[] = {
-	"ethif", "esw", "gp0", "gp1", "gp2", "trgpll", "sgmii_tx250m",
-	"sgmii_rx250m", "sgmii_cdr_ref", "sgmii_cdr_fb", "sgmii_ck", "eth2pll"
+	"ethif", "sgmiitop", "esw", "gp0", "gp1", "gp2", "fe", "trgpll",
+	"sgmii_tx250m", "sgmii_rx250m", "sgmii_cdr_ref", "sgmii_cdr_fb",
+	"sgmii2_tx250m", "sgmii2_rx250m", "sgmii2_cdr_ref", "sgmii2_cdr_fb",
+	"sgmii_ck", "eth2pll",
 };
 
 void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg)
@@ -138,6 +134,31 @@ static int mtk_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg)
 	return _mtk_mdio_read(eth, phy_addr, phy_reg);
 }
 
+static int mt7621_gmac0_rgmii_adjust(struct mtk_eth *eth,
+				     phy_interface_t interface)
+{
+	u32 val;
+
+	/* Check DDR memory type.
+	 * Currently TRGMII mode with DDR2 memory is not supported.
+	 */
+	regmap_read(eth->ethsys, ETHSYS_SYSCFG, &val);
+	if (interface == PHY_INTERFACE_MODE_TRGMII &&
+	    val & SYSCFG_DRAM_TYPE_DDR2) {
+		dev_err(eth->dev,
+			"TRGMII mode with DDR2 memory is not supported!\n");
+		return -EOPNOTSUPP;
+	}
+
+	val = (interface == PHY_INTERFACE_MODE_TRGMII) ?
+		ETHSYS_TRGMII_MT7621_DDR_PLL : 0;
+
+	regmap_update_bits(eth->ethsys, ETHSYS_CLKCFG0,
+			   ETHSYS_TRGMII_MT7621_MASK, val);
+
+	return 0;
+}
+
 static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed)
 {
 	u32 val;
@@ -165,47 +186,6 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed)
 	mtk_w32(eth, val, TRGMII_TCK_CTRL);
 }
 
-static void mtk_gmac_sgmii_hw_setup(struct mtk_eth *eth, int mac_id)
-{
-	u32 val;
-
-	/* Setup the link timer and QPHY power up inside SGMIISYS */
-	regmap_write(eth->sgmiisys, SGMSYS_PCS_LINK_TIMER,
-		     SGMII_LINK_TIMER_DEFAULT);
-
-	regmap_read(eth->sgmiisys, SGMSYS_SGMII_MODE, &val);
-	val |= SGMII_REMOTE_FAULT_DIS;
-	regmap_write(eth->sgmiisys, SGMSYS_SGMII_MODE, val);
-
-	regmap_read(eth->sgmiisys, SGMSYS_PCS_CONTROL_1, &val);
-	val |= SGMII_AN_RESTART;
-	regmap_write(eth->sgmiisys, SGMSYS_PCS_CONTROL_1, val);
-
-	regmap_read(eth->sgmiisys, SGMSYS_QPHY_PWR_STATE_CTRL, &val);
-	val &= ~SGMII_PHYA_PWD;
-	regmap_write(eth->sgmiisys, SGMSYS_QPHY_PWR_STATE_CTRL, val);
-
-	/* Determine MUX for which GMAC uses the SGMII interface */
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_DUAL_GMAC_SHARED_SGMII)) {
-		regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val);
-		val &= ~SYSCFG0_SGMII_MASK;
-		val |= !mac_id ? SYSCFG0_SGMII_GMAC1 : SYSCFG0_SGMII_GMAC2;
-		regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val);
-
-		dev_info(eth->dev, "setup shared sgmii for gmac=%d\n",
-			 mac_id);
-	}
-
-	/* Setup the GMAC1 going through SGMII path when SoC also support
-	 * ESW on GMAC1
-	 */
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC1_ESW | MTK_GMAC1_SGMII) &&
-	    !mac_id) {
-		mtk_w32(eth, 0, MTK_MAC_MISC);
-		dev_info(eth->dev, "setup gmac1 going through sgmii");
-	}
-}
-
 static void mtk_phy_link_adjust(struct net_device *dev)
 {
 	struct mtk_mac *mac = netdev_priv(dev);
@@ -226,11 +206,19 @@ static void mtk_phy_link_adjust(struct net_device *dev)
 	case SPEED_100:
 		mcr |= MAC_MCR_SPEED_100;
 		break;
-	};
+	}
 
-	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GMAC1_TRGMII) &&
-	    !mac->id && !mac->trgmii)
-		mtk_gmac0_rgmii_adjust(mac->hw, dev->phydev->speed);
+	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GMAC1_TRGMII) && !mac->id) {
+		if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_TRGMII_MT7621_CLK)) {
+			if (mt7621_gmac0_rgmii_adjust(mac->hw,
+						      dev->phydev->interface))
+				return;
+		} else {
+			if (!mac->trgmii)
+				mtk_gmac0_rgmii_adjust(mac->hw,
+						       dev->phydev->speed);
+		}
+	}
 
 	if (dev->phydev->link)
 		mcr |= MAC_MCR_FORCE_LINK;
@@ -295,6 +283,7 @@ static int mtk_phy_connect(struct net_device *dev)
 	struct mtk_eth *eth;
 	struct device_node *np;
 	u32 val;
+	int err;
 
 	eth = mac->hw;
 	np = of_parse_phandle(mac->of_node, "phy-handle", 0);
@@ -304,6 +293,10 @@ static int mtk_phy_connect(struct net_device *dev)
 	if (!np)
 		return -ENODEV;
 
+	err = mtk_setup_hw_path(eth, mac->id, of_get_phy_mode(np));
+	if (err)
+		goto err_phy;
+
 	mac->ge_mode = 0;
 	switch (of_get_phy_mode(np)) {
 	case PHY_INTERFACE_MODE_TRGMII:
@@ -312,12 +305,10 @@ static int mtk_phy_connect(struct net_device *dev)
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII:
-		break;
 	case PHY_INTERFACE_MODE_SGMII:
-		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII))
-			mtk_gmac_sgmii_hw_setup(eth, mac->id);
 		break;
 	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_GMII:
 		mac->ge_mode = 1;
 		break;
 	case PHY_INTERFACE_MODE_REVMII:
@@ -767,7 +758,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	 */
 	wmb();
 
-	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
+	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) ||
+	    !netdev_xmit_more())
 		mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR);
 
 	return 0;
@@ -1745,6 +1737,22 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t mtk_handle_irq(int irq, void *_eth)
+{
+	struct mtk_eth *eth = _eth;
+
+	if (mtk_r32(eth, MTK_PDMA_INT_MASK) & MTK_RX_DONE_INT) {
+		if (mtk_r32(eth, MTK_PDMA_INT_STATUS) & MTK_RX_DONE_INT)
+			mtk_handle_irq_rx(irq, _eth);
+	}
+	if (mtk_r32(eth, MTK_QDMA_INT_MASK) & MTK_TX_DONE_INT) {
+		if (mtk_r32(eth, MTK_QMTK_INT_STATUS) & MTK_TX_DONE_INT)
+			mtk_handle_irq_tx(irq, _eth);
+	}
+
+	return IRQ_HANDLED;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void mtk_poll_controller(struct net_device *dev)
 {
@@ -1761,6 +1769,7 @@ static void mtk_poll_controller(struct net_device *dev)
 
 static int mtk_start_dma(struct mtk_eth *eth)
 {
+	u32 rx_2b_offset = (NET_IP_ALIGN == 2) ? MTK_RX_2B_OFFSET : 0;
 	int err;
 
 	err = mtk_dma_init(eth);
@@ -1777,7 +1786,7 @@ static int mtk_start_dma(struct mtk_eth *eth)
 		MTK_QDMA_GLO_CFG);
 
 	mtk_w32(eth,
-		MTK_RX_DMA_EN | MTK_RX_2B_OFFSET |
+		MTK_RX_DMA_EN | rx_2b_offset |
 		MTK_RX_BT_32DWORDS | MTK_MULTI_EN,
 		MTK_PDMA_GLO_CFG);
 
@@ -2011,7 +2020,7 @@ static int __init mtk_init(struct net_device *dev)
 	const char *mac_addr;
 
 	mac_addr = of_get_mac_address(mac->of_node);
-	if (mac_addr)
+	if (!IS_ERR(mac_addr))
 		ether_addr_copy(dev->dev_addr, mac_addr);
 
 	/* If the mac address is invalid, use random mac address  */
@@ -2281,13 +2290,13 @@ static int mtk_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
-		if (dev->features & NETIF_F_LRO) {
+		if (dev->hw_features & NETIF_F_LRO) {
 			cmd->data = MTK_MAX_RX_RING_NUM;
 			ret = 0;
 		}
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
-		if (dev->features & NETIF_F_LRO) {
+		if (dev->hw_features & NETIF_F_LRO) {
 			struct mtk_mac *mac = netdev_priv(dev);
 
 			cmd->rule_cnt = mac->hwlro_ip_cnt;
@@ -2295,11 +2304,11 @@ static int mtk_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		}
 		break;
 	case ETHTOOL_GRXCLSRULE:
-		if (dev->features & NETIF_F_LRO)
+		if (dev->hw_features & NETIF_F_LRO)
 			ret = mtk_hwlro_get_fdir_entry(dev, cmd);
 		break;
 	case ETHTOOL_GRXCLSRLALL:
-		if (dev->features & NETIF_F_LRO)
+		if (dev->hw_features & NETIF_F_LRO)
 			ret = mtk_hwlro_get_fdir_all(dev, cmd,
 						     rule_locs);
 		break;
@@ -2316,11 +2325,11 @@ static int mtk_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 
 	switch (cmd->cmd) {
 	case ETHTOOL_SRXCLSRLINS:
-		if (dev->features & NETIF_F_LRO)
+		if (dev->hw_features & NETIF_F_LRO)
 			ret = mtk_hwlro_add_ipaddr(dev, cmd);
 		break;
 	case ETHTOOL_SRXCLSRLDEL:
-		if (dev->features & NETIF_F_LRO)
+		if (dev->hw_features & NETIF_F_LRO)
 			ret = mtk_hwlro_del_ipaddr(dev, cmd);
 		break;
 	default:
@@ -2465,16 +2474,28 @@ static int mtk_probe(struct platform_device *pdev)
 		return PTR_ERR(eth->ethsys);
 	}
 
-	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII)) {
-		eth->sgmiisys =
-		syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
-						"mediatek,sgmiisys");
-		if (IS_ERR(eth->sgmiisys)) {
-			dev_err(&pdev->dev, "no sgmiisys regmap found\n");
-			return PTR_ERR(eth->sgmiisys);
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_INFRA)) {
+		eth->infra = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+							     "mediatek,infracfg");
+		if (IS_ERR(eth->infra)) {
+			dev_err(&pdev->dev, "no infracfg regmap found\n");
+			return PTR_ERR(eth->infra);
 		}
 	}
 
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII)) {
+		eth->sgmii = devm_kzalloc(eth->dev, sizeof(*eth->sgmii),
+					  GFP_KERNEL);
+		if (!eth->sgmii)
+			return -ENOMEM;
+
+		err = mtk_sgmii_init(eth->sgmii, pdev->dev.of_node,
+				     eth->soc->ana_rgc3);
+
+		if (err)
+			return err;
+	}
+
 	if (eth->soc->required_pctl) {
 		eth->pctl = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
 							    "mediatek,pctl");
@@ -2485,7 +2506,10 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < 3; i++) {
-		eth->irq[i] = platform_get_irq(pdev, i);
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT) && i > 0)
+			eth->irq[i] = eth->irq[0];
+		else
+			eth->irq[i] = platform_get_irq(pdev, i);
 		if (eth->irq[i] < 0) {
 			dev_err(&pdev->dev, "no IRQ%d resource found\n", i);
 			return -ENXIO;
@@ -2528,13 +2552,21 @@ static int mtk_probe(struct platform_device *pdev)
 			goto err_deinit_hw;
 	}
 
-	err = devm_request_irq(eth->dev, eth->irq[1], mtk_handle_irq_tx, 0,
-			       dev_name(eth->dev), eth);
-	if (err)
-		goto err_free_dev;
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT)) {
+		err = devm_request_irq(eth->dev, eth->irq[0],
+				       mtk_handle_irq, 0,
+				       dev_name(eth->dev), eth);
+	} else {
+		err = devm_request_irq(eth->dev, eth->irq[1],
+				       mtk_handle_irq_tx, 0,
+				       dev_name(eth->dev), eth);
+		if (err)
+			goto err_free_dev;
 
-	err = devm_request_irq(eth->dev, eth->irq[2], mtk_handle_irq_rx, 0,
-			       dev_name(eth->dev), eth);
+		err = devm_request_irq(eth->dev, eth->irq[2],
+				       mtk_handle_irq_rx, 0,
+				       dev_name(eth->dev), eth);
+	}
 	if (err)
 		goto err_free_dev;
 
@@ -2602,27 +2634,43 @@ static int mtk_remove(struct platform_device *pdev)
 }
 
 static const struct mtk_soc_data mt2701_data = {
-	.caps = MTK_GMAC1_TRGMII | MTK_HWLRO,
+	.caps = MT7623_CAPS | MTK_HWLRO,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 };
 
+static const struct mtk_soc_data mt7621_data = {
+	.caps = MT7621_CAPS,
+	.required_clks = MT7621_CLKS_BITMAP,
+	.required_pctl = false,
+};
+
 static const struct mtk_soc_data mt7622_data = {
-	.caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW | MTK_HWLRO,
+	.ana_rgc3 = 0x2028,
+	.caps = MT7622_CAPS | MTK_HWLRO,
 	.required_clks = MT7622_CLKS_BITMAP,
 	.required_pctl = false,
 };
 
 static const struct mtk_soc_data mt7623_data = {
-	.caps = MTK_GMAC1_TRGMII | MTK_HWLRO,
+	.caps = MT7623_CAPS | MTK_HWLRO,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 };
 
+static const struct mtk_soc_data mt7629_data = {
+	.ana_rgc3 = 0x128,
+	.caps = MT7629_CAPS | MTK_HWLRO,
+	.required_clks = MT7629_CLKS_BITMAP,
+	.required_pctl = false,
+};
+
 const struct of_device_id of_mtk_match[] = {
 	{ .compatible = "mediatek,mt2701-eth", .data = &mt2701_data},
+	{ .compatible = "mediatek,mt7621-eth", .data = &mt7621_data},
 	{ .compatible = "mediatek,mt7622-eth", .data = &mt7622_data},
 	{ .compatible = "mediatek,mt7623-eth", .data = &mt7623_data},
+	{ .compatible = "mediatek,mt7629-eth", .data = &mt7629_data},
 	{},
 };
 MODULE_DEVICE_TABLE(of, of_mtk_match);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 46819297fc3e..bab94f763e2c 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -1,11 +1,5 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
  *
  *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
  *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
@@ -15,6 +9,10 @@
 #ifndef MTK_ETH_H
 #define MTK_ETH_H
 
+#include <linux/dma-mapping.h>
+#include <linux/netdevice.h>
+#include <linux/of_net.h>
+#include <linux/u64_stats_sync.h>
 #include <linux/refcount.h>
 
 #define MTK_QDMA_PAGE_SIZE	2048
@@ -363,18 +361,29 @@
 #define ETHSYS_CHIPID4_7	0x4
 #define MT7623_ETH		7623
 #define MT7622_ETH		7622
+#define MT7621_ETH		7621
+
+/* ethernet system control register */
+#define ETHSYS_SYSCFG		0x10
+#define SYSCFG_DRAM_TYPE_DDR2	BIT(4)
 
 /* ethernet subsystem config register */
 #define ETHSYS_SYSCFG0		0x14
 #define SYSCFG0_GE_MASK		0x3
 #define SYSCFG0_GE_MODE(x, y)	(x << (12 + (y * 2)))
-#define SYSCFG0_SGMII_MASK	(3 << 8)
-#define SYSCFG0_SGMII_GMAC1	((2 << 8) & GENMASK(9, 8))
-#define SYSCFG0_SGMII_GMAC2	((3 << 8) & GENMASK(9, 8))
+#define SYSCFG0_SGMII_MASK     GENMASK(9, 8)
+#define SYSCFG0_SGMII_GMAC1    ((2 << 8) & SYSCFG0_SGMII_MASK)
+#define SYSCFG0_SGMII_GMAC2    ((3 << 8) & SYSCFG0_SGMII_MASK)
+#define SYSCFG0_SGMII_GMAC1_V2 BIT(9)
+#define SYSCFG0_SGMII_GMAC2_V2 BIT(8)
+
 
 /* ethernet subsystem clock register */
 #define ETHSYS_CLKCFG0		0x2c
 #define ETHSYS_TRGMII_CLK_SEL362_5	BIT(11)
+#define ETHSYS_TRGMII_MT7621_MASK	(BIT(5) | BIT(6))
+#define ETHSYS_TRGMII_MT7621_APLL	BIT(6)
+#define ETHSYS_TRGMII_MT7621_DDR_PLL	BIT(5)
 
 /* ethernet reset control register */
 #define ETHSYS_RSTCTRL		0x34
@@ -398,6 +407,11 @@
 #define SGMSYS_QPHY_PWR_STATE_CTRL 0xe8
 #define	SGMII_PHYA_PWD		BIT(4)
 
+/* Infrasys subsystem config registers */
+#define INFRA_MISC2            0x70c
+#define CO_QPHY_SEL            BIT(0)
+#define GEPHY_MAC_SEL          BIT(1)
+
 struct mtk_rx_dma {
 	unsigned int rxd1;
 	unsigned int rxd2;
@@ -462,15 +476,21 @@ enum mtk_tx_flags {
  */
 enum mtk_clks_map {
 	MTK_CLK_ETHIF,
+	MTK_CLK_SGMIITOP,
 	MTK_CLK_ESW,
 	MTK_CLK_GP0,
 	MTK_CLK_GP1,
 	MTK_CLK_GP2,
+	MTK_CLK_FE,
 	MTK_CLK_TRGPLL,
 	MTK_CLK_SGMII_TX_250M,
 	MTK_CLK_SGMII_RX_250M,
 	MTK_CLK_SGMII_CDR_REF,
 	MTK_CLK_SGMII_CDR_FB,
+	MTK_CLK_SGMII2_TX_250M,
+	MTK_CLK_SGMII2_RX_250M,
+	MTK_CLK_SGMII2_CDR_REF,
+	MTK_CLK_SGMII2_CDR_FB,
 	MTK_CLK_SGMII_CK,
 	MTK_CLK_ETH2PLL,
 	MTK_CLK_MAX
@@ -488,6 +508,21 @@ enum mtk_clks_map {
 				 BIT(MTK_CLK_SGMII_CDR_FB) | \
 				 BIT(MTK_CLK_SGMII_CK) | \
 				 BIT(MTK_CLK_ETH2PLL))
+#define MT7621_CLKS_BITMAP	(0)
+#define MT7629_CLKS_BITMAP	(BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) |  \
+				 BIT(MTK_CLK_GP0) | BIT(MTK_CLK_GP1) | \
+				 BIT(MTK_CLK_GP2) | BIT(MTK_CLK_FE) | \
+				 BIT(MTK_CLK_SGMII_TX_250M) | \
+				 BIT(MTK_CLK_SGMII_RX_250M) | \
+				 BIT(MTK_CLK_SGMII_CDR_REF) | \
+				 BIT(MTK_CLK_SGMII_CDR_FB) | \
+				 BIT(MTK_CLK_SGMII2_TX_250M) | \
+				 BIT(MTK_CLK_SGMII2_RX_250M) | \
+				 BIT(MTK_CLK_SGMII2_CDR_REF) | \
+				 BIT(MTK_CLK_SGMII2_CDR_FB) | \
+				 BIT(MTK_CLK_SGMII_CK) | \
+				 BIT(MTK_CLK_ETH2PLL) | BIT(MTK_CLK_SGMIITOP))
+
 enum mtk_dev_state {
 	MTK_HW_INIT,
 	MTK_RESETTING
@@ -557,20 +592,120 @@ struct mtk_rx_ring {
 	u32 crx_idx_reg;
 };
 
-#define MTK_TRGMII			BIT(0)
-#define MTK_GMAC1_TRGMII		(BIT(1) | MTK_TRGMII)
-#define MTK_ESW				BIT(4)
-#define MTK_GMAC1_ESW			(BIT(5) | MTK_ESW)
-#define MTK_SGMII			BIT(8)
-#define MTK_GMAC1_SGMII			(BIT(9) | MTK_SGMII)
-#define MTK_GMAC2_SGMII			(BIT(10) | MTK_SGMII)
-#define MTK_DUAL_GMAC_SHARED_SGMII	(BIT(11) | MTK_GMAC1_SGMII | \
-					 MTK_GMAC2_SGMII)
-#define MTK_HWLRO			BIT(12)
+enum mkt_eth_capabilities {
+	MTK_RGMII_BIT = 0,
+	MTK_TRGMII_BIT,
+	MTK_SGMII_BIT,
+	MTK_ESW_BIT,
+	MTK_GEPHY_BIT,
+	MTK_MUX_BIT,
+	MTK_INFRA_BIT,
+	MTK_SHARED_SGMII_BIT,
+	MTK_HWLRO_BIT,
+	MTK_SHARED_INT_BIT,
+	MTK_TRGMII_MT7621_CLK_BIT,
+
+	/* MUX BITS*/
+	MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT,
+	MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT,
+	MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT,
+	MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT,
+	MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII_BIT,
+
+	/* PATH BITS */
+	MTK_ETH_PATH_GMAC1_RGMII_BIT,
+	MTK_ETH_PATH_GMAC1_TRGMII_BIT,
+	MTK_ETH_PATH_GMAC1_SGMII_BIT,
+	MTK_ETH_PATH_GMAC2_RGMII_BIT,
+	MTK_ETH_PATH_GMAC2_SGMII_BIT,
+	MTK_ETH_PATH_GMAC2_GEPHY_BIT,
+	MTK_ETH_PATH_GDM1_ESW_BIT,
+};
+
+/* Supported hardware group on SoCs */
+#define MTK_RGMII		BIT(MTK_RGMII_BIT)
+#define MTK_TRGMII		BIT(MTK_TRGMII_BIT)
+#define MTK_SGMII		BIT(MTK_SGMII_BIT)
+#define MTK_ESW			BIT(MTK_ESW_BIT)
+#define MTK_GEPHY		BIT(MTK_GEPHY_BIT)
+#define MTK_MUX			BIT(MTK_MUX_BIT)
+#define MTK_INFRA		BIT(MTK_INFRA_BIT)
+#define MTK_SHARED_SGMII	BIT(MTK_SHARED_SGMII_BIT)
+#define MTK_HWLRO		BIT(MTK_HWLRO_BIT)
+#define MTK_SHARED_INT		BIT(MTK_SHARED_INT_BIT)
+#define MTK_TRGMII_MT7621_CLK	BIT(MTK_TRGMII_MT7621_CLK_BIT)
+
+#define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW		\
+	BIT(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT)
+#define MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY	\
+	BIT(MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY_BIT)
+#define MTK_ETH_MUX_U3_GMAC2_TO_QPHY		\
+	BIT(MTK_ETH_MUX_U3_GMAC2_TO_QPHY_BIT)
+#define MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII	\
+	BIT(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII_BIT)
+#define MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII	\
+	BIT(MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII_BIT)
+
+/* Supported path present on SoCs */
+#define MTK_ETH_PATH_GMAC1_RGMII	BIT(MTK_ETH_PATH_GMAC1_RGMII_BIT)
+#define MTK_ETH_PATH_GMAC1_TRGMII	BIT(MTK_ETH_PATH_GMAC1_TRGMII_BIT)
+#define MTK_ETH_PATH_GMAC1_SGMII	BIT(MTK_ETH_PATH_GMAC1_SGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_RGMII	BIT(MTK_ETH_PATH_GMAC2_RGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_SGMII	BIT(MTK_ETH_PATH_GMAC2_SGMII_BIT)
+#define MTK_ETH_PATH_GMAC2_GEPHY	BIT(MTK_ETH_PATH_GMAC2_GEPHY_BIT)
+#define MTK_ETH_PATH_GDM1_ESW		BIT(MTK_ETH_PATH_GDM1_ESW_BIT)
+
+#define MTK_GMAC1_RGMII		(MTK_ETH_PATH_GMAC1_RGMII | MTK_RGMII)
+#define MTK_GMAC1_TRGMII	(MTK_ETH_PATH_GMAC1_TRGMII | MTK_TRGMII)
+#define MTK_GMAC1_SGMII		(MTK_ETH_PATH_GMAC1_SGMII | MTK_SGMII)
+#define MTK_GMAC2_RGMII		(MTK_ETH_PATH_GMAC2_RGMII | MTK_RGMII)
+#define MTK_GMAC2_SGMII		(MTK_ETH_PATH_GMAC2_SGMII | MTK_SGMII)
+#define MTK_GMAC2_GEPHY		(MTK_ETH_PATH_GMAC2_GEPHY | MTK_GEPHY)
+#define MTK_GDM1_ESW		(MTK_ETH_PATH_GDM1_ESW | MTK_ESW)
+
+/* MUXes present on SoCs */
+/* 0: GDM1 -> GMAC1, 1: GDM1 -> ESW */
+#define MTK_MUX_GDM1_TO_GMAC1_ESW (MTK_ETH_MUX_GDM1_TO_GMAC1_ESW | MTK_MUX)
+
+/* 0: GMAC2 -> GEPHY, 1: GMAC0 -> GePHY */
+#define MTK_MUX_GMAC2_GMAC0_TO_GEPHY    \
+	(MTK_ETH_MUX_GMAC2_GMAC0_TO_GEPHY | MTK_MUX | MTK_INFRA)
+
+/* 0: U3 -> QPHY, 1: GMAC2 -> QPHY */
+#define MTK_MUX_U3_GMAC2_TO_QPHY        \
+	(MTK_ETH_MUX_U3_GMAC2_TO_QPHY | MTK_MUX | MTK_INFRA)
+
+/* 2: GMAC1 -> SGMII, 3: GMAC2 -> SGMII */
+#define MTK_MUX_GMAC1_GMAC2_TO_SGMII_RGMII      \
+	(MTK_ETH_MUX_GMAC1_GMAC2_TO_SGMII_RGMII | MTK_MUX | \
+	MTK_SHARED_SGMII)
+
+/* 0: GMACx -> GEPHY, 1: GMACx -> SGMII where x is 1 or 2 */
+#define MTK_MUX_GMAC12_TO_GEPHY_SGMII   \
+	(MTK_ETH_MUX_GMAC12_TO_GEPHY_SGMII | MTK_MUX)
+
 #define MTK_HAS_CAPS(caps, _x)		(((caps) & (_x)) == (_x))
 
+#define MT7621_CAPS  (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | \
+		      MTK_GMAC2_RGMII | MTK_SHARED_INT | MTK_TRGMII_MT7621_CLK)
+
+#define MT7622_CAPS  (MTK_GMAC1_RGMII | MTK_GMAC1_SGMII | MTK_GMAC2_RGMII | \
+		      MTK_GMAC2_SGMII | MTK_GDM1_ESW | \
+		      MTK_MUX_GDM1_TO_GMAC1_ESW | \
+		      MTK_MUX_GMAC1_GMAC2_TO_SGMII_RGMII)
+
+#define MT7623_CAPS  (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | MTK_GMAC2_RGMII)
+
+#define MT7629_CAPS  (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | MTK_GMAC2_GEPHY | \
+		      MTK_GDM1_ESW | MTK_MUX_GDM1_TO_GMAC1_ESW | \
+		      MTK_MUX_GMAC2_GMAC0_TO_GEPHY | \
+		      MTK_MUX_U3_GMAC2_TO_QPHY | \
+		      MTK_MUX_GMAC12_TO_GEPHY_SGMII)
+
 /* struct mtk_eth_data -	This is the structure holding all differences
  *				among various plaforms
+ * @ana_rgc3:                   The offset for register ANA_RGC3 related to
+ *				sgmiisys syscon
  * @caps			Flags shown the extra capability for the SoC
  * @required_clks		Flags shown the bitmap for required clocks on
  *				the target SoC
@@ -578,6 +713,7 @@ struct mtk_rx_ring {
  *				the extra setup for those pins used by GMAC.
  */
 struct mtk_soc_data {
+	u32             ana_rgc3;
 	u32		caps;
 	u32		required_clks;
 	bool		required_pctl;
@@ -586,6 +722,26 @@ struct mtk_soc_data {
 /* currently no SoC has more than 2 macs */
 #define MTK_MAX_DEVS			2
 
+#define MTK_SGMII_PHYSPEED_AN          BIT(31)
+#define MTK_SGMII_PHYSPEED_MASK        GENMASK(2, 0)
+#define MTK_SGMII_PHYSPEED_1000        BIT(0)
+#define MTK_SGMII_PHYSPEED_2500        BIT(1)
+#define MTK_HAS_FLAGS(flags, _x)       (((flags) & (_x)) == (_x))
+
+/* struct mtk_sgmii -  This is the structure holding sgmii regmap and its
+ *                     characteristics
+ * @regmap:            The register map pointing at the range used to setup
+ *                     SGMII modes
+ * @flags:             The enum refers to which mode the sgmii wants to run on
+ * @ana_rgc3:          The offset refers to register ANA_RGC3 related to regmap
+ */
+
+struct mtk_sgmii {
+	struct regmap   *regmap[MTK_MAX_DEVS];
+	u32             flags[MTK_MAX_DEVS];
+	u32             ana_rgc3;
+};
+
 /* struct mtk_eth -	This is the main datasructure for holding the state
  *			of the driver
  * @dev:		The device pointer
@@ -601,8 +757,8 @@ struct mtk_soc_data {
  * @msg_enable:		Ethtool msg level
  * @ethsys:		The register map pointing at the range used to setup
  *			MII modes
- * @sgmiisys:		The register map pointing at the range used to setup
- *			SGMII modes
+ * @infra:              The register map pointing at the range used to setup
+ *                      SGMII and GePHY path
  * @pctl:		The register map pointing at the range used to setup
  *			GMAC port drive/slew values
  * @dma_refcnt:		track how many netdevs are using the DMA engine
@@ -634,7 +790,8 @@ struct mtk_eth {
 	u32				msg_enable;
 	unsigned long			sysclk;
 	struct regmap			*ethsys;
-	struct regmap			*sgmiisys;
+	struct regmap                   *infra;
+	struct mtk_sgmii                *sgmii;
 	struct regmap			*pctl;
 	bool				hwlro;
 	refcount_t			dma_refcnt;
@@ -685,4 +842,10 @@ void mtk_stats_update_mac(struct mtk_mac *mac);
 void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg);
 u32 mtk_r32(struct mtk_eth *eth, unsigned reg);
 
+int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *np,
+		   u32 ana_rgc3);
+int mtk_sgmii_setup_mode_an(struct mtk_sgmii *ss, int id);
+int mtk_sgmii_setup_mode_force(struct mtk_sgmii *ss, int id);
+int mtk_setup_hw_path(struct mtk_eth *eth, int mac_id, int phymode);
+
 #endif /* MTK_ETH_H */
diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c
new file mode 100644
index 000000000000..ff509d42d818
--- /dev/null
+++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018-2019 MediaTek Inc.
+
+/* A library for MediaTek SGMII circuit
+ *
+ * Author: Sean Wang <sean.wang@mediatek.com>
+ *
+ */
+
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+
+#include "mtk_eth_soc.h"
+
+int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3)
+{
+	struct device_node *np;
+	const char *str;
+	int i, err;
+
+	ss->ana_rgc3 = ana_rgc3;
+
+	for (i = 0; i < MTK_MAX_DEVS; i++) {
+		np = of_parse_phandle(r, "mediatek,sgmiisys", i);
+		if (!np)
+			break;
+
+		ss->regmap[i] = syscon_node_to_regmap(np);
+		if (IS_ERR(ss->regmap[i]))
+			return PTR_ERR(ss->regmap[i]);
+
+		err = of_property_read_string(np, "mediatek,physpeed", &str);
+		if (err)
+			return err;
+
+		if (!strcmp(str, "2500"))
+			ss->flags[i] |= MTK_SGMII_PHYSPEED_2500;
+		else if (!strcmp(str, "1000"))
+			ss->flags[i] |= MTK_SGMII_PHYSPEED_1000;
+		else if (!strcmp(str, "auto"))
+			ss->flags[i] |= MTK_SGMII_PHYSPEED_AN;
+		else
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mtk_sgmii_setup_mode_an(struct mtk_sgmii *ss, int id)
+{
+	unsigned int val;
+
+	if (!ss->regmap[id])
+		return -EINVAL;
+
+	/* Setup the link timer and QPHY power up inside SGMIISYS */
+	regmap_write(ss->regmap[id], SGMSYS_PCS_LINK_TIMER,
+		     SGMII_LINK_TIMER_DEFAULT);
+
+	regmap_read(ss->regmap[id], SGMSYS_SGMII_MODE, &val);
+	val |= SGMII_REMOTE_FAULT_DIS;
+	regmap_write(ss->regmap[id], SGMSYS_SGMII_MODE, val);
+
+	regmap_read(ss->regmap[id], SGMSYS_PCS_CONTROL_1, &val);
+	val |= SGMII_AN_RESTART;
+	regmap_write(ss->regmap[id], SGMSYS_PCS_CONTROL_1, val);
+
+	regmap_read(ss->regmap[id], SGMSYS_QPHY_PWR_STATE_CTRL, &val);
+	val &= ~SGMII_PHYA_PWD;
+	regmap_write(ss->regmap[id], SGMSYS_QPHY_PWR_STATE_CTRL, val);
+
+	return 0;
+}
+
+int mtk_sgmii_setup_mode_force(struct mtk_sgmii *ss, int id)
+{
+	unsigned int val;
+	int mode;
+
+	if (!ss->regmap[id])
+		return -EINVAL;
+
+	regmap_read(ss->regmap[id], ss->ana_rgc3, &val);
+	val &= ~GENMASK(3, 2);
+	mode = ss->flags[id] & MTK_SGMII_PHYSPEED_MASK;
+	val |= (mode == MTK_SGMII_PHYSPEED_1000) ? 0 : BIT(2);
+	regmap_write(ss->regmap[id], ss->ana_rgc3, val);
+
+	/* Disable SGMII AN */
+	regmap_read(ss->regmap[id], SGMSYS_PCS_CONTROL_1, &val);
+	val &= ~BIT(12);
+	regmap_write(ss->regmap[id], SGMSYS_PCS_CONTROL_1, val);
+
+	/* SGMII force mode setting */
+	val = 0x31120019;
+	regmap_write(ss->regmap[id], SGMSYS_SGMII_MODE, val);
+
+	/* Release PHYA power down state */
+	regmap_read(ss->regmap[id], SGMSYS_QPHY_PWR_STATE_CTRL, &val);
+	val &= ~SGMII_PHYA_PWD;
+	regmap_write(ss->regmap[id], SGMSYS_QPHY_PWR_STATE_CTRL, val);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/Kconfig b/drivers/net/ethernet/mellanox/Kconfig
index 872548cd9431..23cf7917a0c9 100644
--- a/drivers/net/ethernet/mellanox/Kconfig
+++ b/drivers/net/ethernet/mellanox/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Mellanox driver configuration
 #
diff --git a/drivers/net/ethernet/mellanox/Makefile b/drivers/net/ethernet/mellanox/Makefile
index 016aa263bc04..79773ac331ee 100644
--- a/drivers/net/ethernet/mellanox/Makefile
+++ b/drivers/net/ethernet/mellanox/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Mellanox device drivers.
 #
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index f200b8c420d5..e69c3c31e701 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -1,10 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Mellanox driver configuration
 #
 
 config MLX4_EN
 	tristate "Mellanox Technologies 1/10/40Gbit Ethernet support"
-	depends on MAY_USE_DEVLINK
 	depends on PCI && NETDEVICES && ETHERNET && INET
 	select MLX4_CORE
 	imply PTP_1588_CLOCK
@@ -27,6 +27,7 @@ config MLX4_EN_DCB
 config MLX4_CORE
 	tristate
 	depends on PCI
+	select NET_DEVLINK
 	default n
 
 config MLX4_DEBUG
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index dbc483e4a2ef..b330020dc0d6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -185,8 +185,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
 	bitmap->avail = num - reserved_top - reserved_bot;
 	bitmap->effective_len = bitmap->avail;
 	spin_lock_init(&bitmap->lock);
-	bitmap->table = kcalloc(BITS_TO_LONGS(bitmap->max), sizeof(long),
-				GFP_KERNEL);
+	bitmap->table = bitmap_zalloc(bitmap->max, GFP_KERNEL);
 	if (!bitmap->table)
 		return -ENOMEM;
 
@@ -197,7 +196,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
 
 void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap)
 {
-	kfree(bitmap->table);
+	bitmap_free(bitmap->table);
 }
 
 struct mlx4_zone_allocator {
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index c81d15bf259c..87e90b5d4d7d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -129,10 +129,6 @@ static int mlx4_reset_slave(struct mlx4_dev *dev)
 	comm_flags = rst_req << COM_CHAN_RST_REQ_OFFSET;
 	__raw_writel((__force u32)cpu_to_be32(comm_flags),
 		     (__iomem char *)priv->mfunc.comm + MLX4_COMM_CHAN_FLAGS);
-	/* Make sure that our comm channel write doesn't
-	 * get mixed in with writes from another CPU.
-	 */
-	mmiowb();
 
 	end = msecs_to_jiffies(MLX4_COMM_TIME) + jiffies;
 	while (time_before(jiffies, end)) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e65bc3c95630..c678344d22a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -281,7 +281,6 @@ static int mlx4_comm_cmd_post(struct mlx4_dev *dev, u8 cmd, u16 param)
 	val = param | (cmd << 16) | (priv->cmd.comm_toggle << 31);
 	__raw_writel((__force u32) cpu_to_be32(val),
 		     &priv->mfunc.comm->slave_write);
-	mmiowb();
 	mutex_unlock(&dev->persist->device_state_mutex);
 	return 0;
 }
@@ -496,12 +495,6 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 					       (op_modifier << HCR_OPMOD_SHIFT) |
 					       op), hcr + 6);
 
-	/*
-	 * Make sure that our HCR writes don't get mixed in with
-	 * writes from another CPU starting a FW command.
-	 */
-	mmiowb();
-
 	cmd->toggle = cmd->toggle ^ 1;
 
 	ret = 0;
@@ -2206,7 +2199,6 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 	}
 	__raw_writel((__force u32) cpu_to_be32(reply),
 		     &priv->mfunc.comm[slave].slave_read);
-	mmiowb();
 
 	return;
 
@@ -2410,7 +2402,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 				     &priv->mfunc.comm[i].slave_write);
 			__raw_writel((__force u32) 0,
 				     &priv->mfunc.comm[i].slave_read);
-			mmiowb();
 			for (port = 1; port <= MLX4_MAX_PORTS; port++) {
 				struct mlx4_vport_state *admin_vport;
 				struct mlx4_vport_state *oper_vport;
@@ -2576,10 +2567,6 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev)
 		slave_read |= (u32)COMM_CHAN_EVENT_INTERNAL_ERR;
 		__raw_writel((__force u32)cpu_to_be32(slave_read),
 			     &priv->mfunc.comm[slave].slave_read);
-		/* Make sure that our comm channel write doesn't
-		 * get mixed in with writes from another CPU.
-		 */
-		mmiowb();
 	}
 }
 
@@ -2645,6 +2632,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	if (!priv->cmd.context)
 		return -ENOMEM;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	for (i = 0; i < priv->cmd.max_cmds; ++i) {
 		priv->cmd.context[i].token = i;
@@ -2670,6 +2659,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	down(&priv->cmd.poll_sem);
 	priv->cmd.use_events = 1;
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 
 	return err;
 }
@@ -2682,6 +2673,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	priv->cmd.use_events = 0;
 
@@ -2689,9 +2682,12 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 		down(&priv->cmd.event_sem);
 
 	kfree(priv->cmd.context);
+	priv->cmd.context = NULL;
 
 	up(&priv->cmd.poll_sem);
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 }
 
 struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
@@ -3274,7 +3270,7 @@ int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_stat
 		mlx4_warn(dev, "unknown value for link_state %02x on slave %d port %d\n",
 			  link_state, slave, port);
 		return -EINVAL;
-	};
+	}
 	s_info = &priv->mfunc.master.vf_admin[slave].vport[port];
 	s_info->link_state = link_state;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index d290f0787dfb..94c59939a8cf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -2010,6 +2010,8 @@ static int mlx4_en_set_tunable(struct net_device *dev,
 	return ret;
 }
 
+#define MLX4_EEPROM_PAGE_LEN 256
+
 static int mlx4_en_get_module_info(struct net_device *dev,
 				   struct ethtool_modinfo *modinfo)
 {
@@ -2044,7 +2046,7 @@ static int mlx4_en_get_module_info(struct net_device *dev,
 		break;
 	case MLX4_MODULE_ID_SFP:
 		modinfo->type = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX4_EEPROM_PAGE_LEN;
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 6b88881b8e35..c1438ae52a11 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3360,7 +3360,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	dev->addr_len = ETH_ALEN;
 	mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]);
 	if (!is_valid_ether_addr(dev->dev_addr)) {
-		en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n",
+		en_err(priv, "Port: %d, invalid mac burned: %pM, quitting\n",
 		       priv->port, dev->dev_addr);
 		err = -EINVAL;
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 9a0881cb7f51..6c01314e87b0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -617,6 +617,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 }
 #endif
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 /* We reach this function only after checking that any of
  * the (IPv4 | IPv6) bits are set in cqe->status.
  */
@@ -624,9 +626,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
+	void *hdr;
+
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to skip
+	 * checksum complete.
+	 */
+	if (short_frame(skb->len))
+		return -EINVAL;
 
-	void *hdr = (u8 *)va + sizeof(struct ethhdr);
-
+	hdr = (u8 *)va + sizeof(struct ethhdr);
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
 	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) &&
@@ -819,6 +832,11 @@ xdp_drop_no_cnt:
 		skb_record_rx_queue(skb, cq_ring);
 
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			/* TODO: For IP non TCP/UDP packets when csum complete is
+			 * not an option (not supported or any other reason) we can
+			 * actually check cqe IPOK status bit and report
+			 * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE
+			 */
 			if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						       MLX4_CQE_STATUS_UDP)) &&
 			    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 2cbd2bd7c67c..36a92b19e613 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -685,16 +685,15 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
 }
 
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 struct net_device *sb_dev,
-			 select_queue_fallback_t fallback)
+			 struct net_device *sb_dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
 
 	if (netdev_get_num_tc(dev))
-		return fallback(dev, skb, NULL);
+		return netdev_pick_tx(dev, skb, NULL);
 
-	return fallback(dev, skb, NULL) % rings_p_up;
+	return netdev_pick_tx(dev, skb, NULL) % rings_p_up;
 }
 
 static void mlx4_bf_copy(void __iomem *dst, const void *src,
@@ -1043,7 +1042,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	send_doorbell = __netdev_tx_sent_queue(ring->tx_queue,
 					       tx_info->nr_bytes,
-					       skb->xmit_more);
+					       netdev_xmit_more());
 
 	real_size = (real_size / 16) & 0x3f;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 2df92dbd38e1..a5be27772b8e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -100,7 +100,7 @@ static void eq_set_ci(struct mlx4_eq *eq, int req_not)
 					       req_not << 31),
 		     eq->doorbell);
 	/* We still want ordering, just not swabbing, so add a barrier */
-	mb();
+	wmb();
 }
 
 static struct mlx4_eqe *get_eqe(struct mlx4_eq *eq, u32 entry, u8 eqe_factor,
@@ -558,6 +558,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n",
 				 __func__, be32_to_cpu(eqe->event.srq.srqn),
 				 eq->eqn);
+			/* fall through */
 		case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
 			if (mlx4_is_master(dev)) {
 				/* forward only to slave owning the SRQ */
@@ -820,7 +821,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				  !!(eqe->owner & 0x80) ^
 				  !!(eq->cons_index & eq->nent) ? "HW" : "SW");
 			break;
-		};
+		}
 
 		++eq->cons_index;
 		eqes_found = 1;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index bdb8dd161923..1f6e16d5ea6b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3981,6 +3981,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto err_params_unregister;
 
+	devlink_params_publish(devlink);
 	pci_save_state(pdev);
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index ffed2d4c9403..9c481823b3e8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1492,7 +1492,7 @@ int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port,
 	rule.port = port;
 	rule.qpn = qpn;
 	INIT_LIST_HEAD(&rule.list);
-	mlx4_err(dev, "going promisc on %x\n", port);
+	mlx4_info(dev, "going promisc on %x\n", port);
 
 	return  mlx4_flow_attach(dev, &rule, regid_p);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 8137454e2534..630f15977f09 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -698,8 +698,7 @@ void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 struct net_device *sb_dev,
-			 select_queue_fallback_t fallback);
+			 struct net_device *sb_dev);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 10fcc22f4590..ba6ac31a339d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -2077,11 +2077,6 @@ int mlx4_get_module_info(struct mlx4_dev *dev, u8 port,
 		size -= offset + size - I2C_PAGE_SIZE;
 
 	i2c_addr = I2C_ADDR_LOW;
-	if (offset >= I2C_PAGE_SIZE) {
-		/* Reset offset to high page */
-		i2c_addr = I2C_ADDR_HIGH;
-		offset -= I2C_PAGE_SIZE;
-	}
 
 	cable_info = (struct mlx4_cable_info *)inmad->data;
 	cable_info->dev_mem_address = cpu_to_be16(offset);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index eb13d3618162..4356f3a58002 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2719,13 +2719,13 @@ static int qp_get_mtt_size(struct mlx4_qp_context *qpc)
 	int total_pages;
 	int total_mem;
 	int page_offset = (be32_to_cpu(qpc->params2) >> 6) & 0x3f;
+	int tot;
 
 	sq_size = 1 << (log_sq_size + log_sq_sride + 4);
 	rq_size = (srq|rss|xrc) ? 0 : (1 << (log_rq_size + log_rq_stride + 4));
 	total_mem = sq_size + rq_size;
-	total_pages =
-		roundup_pow_of_two((total_mem + (page_offset << 6)) >>
-				   page_shift);
+	tot = (total_mem + (page_offset << 6)) >> page_shift;
+	total_pages = !tot ? 1 : roundup_pow_of_two(tot);
 
 	return total_pages;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 37a551436e4a..37fef8cd25e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -1,13 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Mellanox driver configuration
 #
 
 config MLX5_CORE
 	tristate "Mellanox 5th generation network adapters (ConnectX series) core driver"
-	depends on MAY_USE_DEVLINK
 	depends on PCI
+	select NET_DEVLINK
 	imply PTP_1588_CLOCK
 	imply VXLAN
+	imply MLXFW
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
@@ -32,6 +34,7 @@ config MLX5_CORE_EN
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	depends on IPV6=y || IPV6=n || MLX5_CORE=m
 	select PAGE_POOL
+	select DIMLIB
 	default n
 	---help---
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
@@ -94,26 +97,60 @@ config MLX5_CORE_IPOIB
 	---help---
 	  MLX5 IPoIB offloads & acceleration support.
 
+config MLX5_FPGA_IPSEC
+	bool "Mellanox Technologies IPsec Innova support"
+	depends on MLX5_CORE
+	depends on MLX5_FPGA
+	default n
+	help
+	Build IPsec support for the Innova family of network cards by Mellanox
+	Technologies. Innova network cards are comprised of a ConnectX chip
+	and an FPGA chip on one board. If you select this option, the
+	mlx5_core driver will include the Innova FPGA core and allow building
+	sandbox-specific client drivers.
+
 config MLX5_EN_IPSEC
 	bool "IPSec XFRM cryptography-offload accelaration"
-	depends on MLX5_ACCEL
 	depends on MLX5_CORE_EN
 	depends on XFRM_OFFLOAD
 	depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD
+	depends on MLX5_FPGA_IPSEC
 	default n
-	---help---
+	help
 	  Build support for IPsec cryptography-offload accelaration in the NIC.
 	  Note: Support for hardware with this capability needs to be selected
 	  for this option to become available.
 
-config MLX5_EN_TLS
-	bool "TLS cryptography-offload accelaration"
+config MLX5_FPGA_TLS
+	bool "Mellanox Technologies TLS Innova support"
+	depends on TLS_DEVICE
+	depends on TLS=y || MLX5_CORE=m
+	depends on MLX5_FPGA
+	default n
+	help
+	Build TLS support for the Innova family of network cards by Mellanox
+	Technologies. Innova network cards are comprised of a ConnectX chip
+	and an FPGA chip on one board. If you select this option, the
+	mlx5_core driver will include the Innova FPGA core and allow building
+	sandbox-specific client drivers.
+
+config MLX5_TLS
+	bool "Mellanox Technologies TLS Connect-X support"
 	depends on MLX5_CORE_EN
 	depends on TLS_DEVICE
 	depends on TLS=y || MLX5_CORE=m
-	depends on MLX5_ACCEL
+	select MLX5_ACCEL
 	default n
-	---help---
-	  Build support for TLS cryptography-offload accelaration in the NIC.
-	  Note: Support for hardware with this capability needs to be selected
-	  for this option to become available.
+	help
+	Build TLS support for the Connect-X family of network cards by Mellanox
+	Technologies.
+
+config MLX5_EN_TLS
+	bool "TLS cryptography-offload accelaration"
+	depends on MLX5_CORE_EN
+	depends on MLX5_FPGA_TLS || MLX5_TLS
+	default y
+	help
+	Build support for TLS cryptography-offload accelaration in the NIC.
+	Note: Support for hardware with this capability needs to be selected
+	for this option to become available.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9de9abacf7f6..57d2cc666fe3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -13,16 +13,18 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 #
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
-		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
+		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
-		lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o
+		lib/devcom.o lib/pci_vsc.o diag/fs_tracepoint.o \
+		diag/fw_tracer.o diag/crdump.o devlink.o
 
 #
 # Netdev basic
 #
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_selftest.o en/port.o en/monitor_stats.o
+		en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \
+		en/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o
 
 #
 # Netdev extra
@@ -30,12 +32,15 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o \
+					lib/geneve.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
+					en/tc_tun_geneve.o
 
 #
 # Core extra
 #
-mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o eswitch_offloads_termtbl.o \
+				      ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
@@ -48,14 +53,14 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib
 #
 # Accelerations & FPGA
 #
-mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
+mlx5_core-$(CONFIG_MLX5_FPGA_IPSEC) += fpga/ipsec.o
+mlx5_core-$(CONFIG_MLX5_FPGA_TLS)   += fpga/tls.o
+mlx5_core-$(CONFIG_MLX5_ACCEL)      += lib/crypto.o accel/tls.o accel/ipsec.o
 
-mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
-				 fpga/ipsec.o fpga/tls.o
+mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
 				     en_accel/ipsec_stats.o
 
-mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
-
-CFLAGS_tracepoint.o := -I$(src)
+mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o \
+				   en_accel/ktls.o en_accel/ktls_tx.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/accel/Makefile
index d8e17110f25d..c78512eed8d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
index 9f1b1939716a..eddc34e4a762 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.c
@@ -31,6 +31,8 @@
  *
  */
 
+#ifdef CONFIG_MLX5_FPGA_IPSEC
+
 #include <linux/mlx5/device.h>
 
 #include "accel/ipsec.h"
@@ -74,6 +76,11 @@ int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
 	return mlx5_fpga_ipsec_init(mdev);
 }
 
+void mlx5_accel_ipsec_build_fs_cmds(void)
+{
+	mlx5_fpga_ipsec_build_fs_cmds();
+}
+
 void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
 {
 	mlx5_fpga_ipsec_cleanup(mdev);
@@ -107,3 +114,5 @@ int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 	return mlx5_fpga_esp_modify_xfrm(xfrm, attrs);
 }
 EXPORT_SYMBOL_GPL(mlx5_accel_esp_modify_xfrm);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
index 024dbd22a89b..530e428d46ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/ipsec.h
@@ -37,7 +37,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/accel.h>
 
-#ifdef CONFIG_MLX5_ACCEL
+#ifdef CONFIG_MLX5_FPGA_IPSEC
 
 #define MLX5_IPSEC_DEV(mdev) (mlx5_accel_ipsec_device_caps(mdev) & \
 			      MLX5_ACCEL_IPSEC_CAP_DEVICE)
@@ -54,6 +54,7 @@ void *mlx5_accel_esp_create_hw_context(struct mlx5_core_dev *mdev,
 void mlx5_accel_esp_free_hw_context(void *context);
 
 int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev);
+void mlx5_accel_ipsec_build_fs_cmds(void);
 void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev);
 
 #else
@@ -79,6 +80,10 @@ static inline int mlx5_accel_ipsec_init(struct mlx5_core_dev *mdev)
 	return 0;
 }
 
+static inline void mlx5_accel_ipsec_build_fs_cmds(void)
+{
+}
+
 static inline void mlx5_accel_ipsec_cleanup(struct mlx5_core_dev *mdev)
 {
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
index da7bd26368f9..cab708af3422 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
@@ -35,6 +35,9 @@
 
 #include "accel/tls.h"
 #include "mlx5_core.h"
+#include "lib/mlx5.h"
+
+#ifdef CONFIG_MLX5_FPGA_TLS
 #include "fpga/tls.h"
 
 int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
@@ -61,7 +64,8 @@ int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
 {
-	return mlx5_fpga_is_tls_device(mdev);
+	return mlx5_fpga_is_tls_device(mdev) ||
+		mlx5_accel_is_ktls_device(mdev);
 }
 
 u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev)
@@ -78,3 +82,42 @@ void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev)
 {
 	mlx5_fpga_tls_cleanup(mdev);
 }
+#endif
+
+#ifdef CONFIG_MLX5_TLS
+int mlx5_ktls_create_key(struct mlx5_core_dev *mdev,
+			 struct tls_crypto_info *crypto_info,
+			 u32 *p_key_id)
+{
+	u32 sz_bytes;
+	void *key;
+
+	switch (crypto_info->cipher_type) {
+	case TLS_CIPHER_AES_GCM_128: {
+		struct tls12_crypto_info_aes_gcm_128 *info =
+			(struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
+
+		key      = info->key;
+		sz_bytes = sizeof(info->key);
+		break;
+	}
+	case TLS_CIPHER_AES_GCM_256: {
+		struct tls12_crypto_info_aes_gcm_256 *info =
+			(struct tls12_crypto_info_aes_gcm_256 *)crypto_info;
+
+		key      = info->key;
+		sz_bytes = sizeof(info->key);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+
+	return mlx5_create_encryption_key(mdev, key, sz_bytes, p_key_id);
+}
+
+void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id)
+{
+	mlx5_destroy_encryption_key(mdev, key_id);
+}
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index def4093ebfae..d787bc0a4155 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -37,7 +37,49 @@
 #include <linux/mlx5/driver.h>
 #include <linux/tls.h>
 
-#ifdef CONFIG_MLX5_ACCEL
+#ifdef CONFIG_MLX5_TLS
+int mlx5_ktls_create_key(struct mlx5_core_dev *mdev,
+			 struct tls_crypto_info *crypto_info,
+			 u32 *p_key_id);
+void mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id);
+
+static inline bool mlx5_accel_is_ktls_device(struct mlx5_core_dev *mdev)
+{
+	if (!MLX5_CAP_GEN(mdev, tls))
+		return false;
+
+	if (!MLX5_CAP_GEN(mdev, log_max_dek))
+		return false;
+
+	return MLX5_CAP_TLS(mdev, tls_1_2_aes_gcm_128);
+}
+
+static inline bool mlx5e_ktls_type_check(struct mlx5_core_dev *mdev,
+					 struct tls_crypto_info *crypto_info)
+{
+	switch (crypto_info->cipher_type) {
+	case TLS_CIPHER_AES_GCM_128:
+		if (crypto_info->version == TLS_1_2_VERSION)
+			return MLX5_CAP_TLS(mdev,  tls_1_2_aes_gcm_128);
+		break;
+	}
+
+	return false;
+}
+#else
+static inline int
+mlx5_ktls_create_key(struct mlx5_core_dev *mdev,
+		     struct tls_crypto_info *crypto_info,
+		     u32 *p_key_id) { return -ENOTSUPP; }
+static inline void
+mlx5_ktls_destroy_key(struct mlx5_core_dev *mdev, u32 key_id) {}
+
+static inline bool
+mlx5_accel_is_ktls_device(struct mlx5_core_dev *mdev) { return false; }
+static inline bool
+mlx5e_ktls_type_check(struct mlx5_core_dev *mdev,
+		      struct tls_crypto_info *crypto_info) { return false; }
+#endif
 
 enum {
 	MLX5_ACCEL_TLS_TX = BIT(0),
@@ -60,6 +102,7 @@ struct mlx5_ifc_tls_flow_bits {
 	u8         reserved_at_2[0x1e];
 };
 
+#ifdef CONFIG_MLX5_FPGA_TLS
 int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
 			    struct tls_crypto_info *crypto_info,
 			    u32 start_offload_tcp_sn, u32 *p_swid,
@@ -84,11 +127,13 @@ static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 					   bool direction_sx) { }
 static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle,
 					   u32 seq, u64 rcd_sn) { return 0; }
-static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; }
+static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
+{
+	return mlx5_accel_is_ktls_device(mdev);
+}
 static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; }
 static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; }
 static inline void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev) { }
-
 #endif
 
 #endif	/* __MLX5_ACCEL_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 421b9c3c8bf7..549f962cd86e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -57,15 +57,16 @@ static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev,
 					   int node)
 {
 	struct mlx5_priv *priv = &dev->priv;
+	struct device *device = dev->device;
 	int original_node;
 	void *cpu_handle;
 
 	mutex_lock(&priv->alloc_mutex);
-	original_node = dev_to_node(&dev->pdev->dev);
-	set_dev_node(&dev->pdev->dev, node);
-	cpu_handle = dma_alloc_coherent(&dev->pdev->dev, size, dma_handle,
+	original_node = dev_to_node(device);
+	set_dev_node(device, node);
+	cpu_handle = dma_alloc_coherent(device, size, dma_handle,
 					GFP_KERNEL);
-	set_dev_node(&dev->pdev->dev, original_node);
+	set_dev_node(device, original_node);
 	mutex_unlock(&priv->alloc_mutex);
 	return cpu_handle;
 }
@@ -110,7 +111,7 @@ EXPORT_SYMBOL(mlx5_buf_alloc);
 
 void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
 {
-	dma_free_coherent(&dev->pdev->dev, buf->size, buf->frags->buf,
+	dma_free_coherent(dev->device, buf->size, buf->frags->buf,
 			  buf->frags->map);
 
 	kfree(buf->frags);
@@ -139,7 +140,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 		if (!frag->buf)
 			goto err_free_buf;
 		if (frag->map & ((1 << buf->page_shift) - 1)) {
-			dma_free_coherent(&dev->pdev->dev, frag_sz,
+			dma_free_coherent(dev->device, frag_sz,
 					  buf->frags[i].buf, buf->frags[i].map);
 			mlx5_core_warn(dev, "unexpected map alignment: %pad, page_shift=%d\n",
 				       &frag->map, buf->page_shift);
@@ -152,7 +153,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 
 err_free_buf:
 	while (i--)
-		dma_free_coherent(&dev->pdev->dev, PAGE_SIZE, buf->frags[i].buf,
+		dma_free_coherent(dev->device, PAGE_SIZE, buf->frags[i].buf,
 				  buf->frags[i].map);
 	kfree(buf->frags);
 err_out:
@@ -168,7 +169,7 @@ void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
 	for (i = 0; i < buf->npages; i++) {
 		int frag_sz = min_t(int, size, PAGE_SIZE);
 
-		dma_free_coherent(&dev->pdev->dev, frag_sz, buf->frags[i].buf,
+		dma_free_coherent(dev->device, frag_sz, buf->frags[i].buf,
 				  buf->frags[i].map);
 		size -= frag_sz;
 	}
@@ -186,10 +187,7 @@ static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
 	if (!pgdir)
 		return NULL;
 
-	pgdir->bitmap = kcalloc(BITS_TO_LONGS(db_per_page),
-				sizeof(unsigned long),
-				GFP_KERNEL);
-
+	pgdir->bitmap = bitmap_zalloc(db_per_page, GFP_KERNEL);
 	if (!pgdir->bitmap) {
 		kfree(pgdir);
 		return NULL;
@@ -200,7 +198,7 @@ static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
 	pgdir->db_page = mlx5_dma_zalloc_coherent_node(dev, PAGE_SIZE,
 						       &pgdir->db_dma, node);
 	if (!pgdir->db_page) {
-		kfree(pgdir->bitmap);
+		bitmap_free(pgdir->bitmap);
 		kfree(pgdir);
 		return NULL;
 	}
@@ -277,10 +275,10 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 	__set_bit(db->index, db->u.pgdir->bitmap);
 
 	if (bitmap_full(db->u.pgdir->bitmap, db_per_page)) {
-		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+		dma_free_coherent(dev->device, PAGE_SIZE,
 				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
 		list_del(&db->u.pgdir->list);
-		kfree(db->u.pgdir->bitmap);
+		bitmap_free(db->u.pgdir->bitmap);
 		kfree(db->u.pgdir);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3e0fa8a8077b..8cdd7e66f8df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -316,6 +316,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
 	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
+	case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -440,6 +441,10 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_GENERAL_OBJECT:
 	case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_QUERY_GENERAL_OBJECT:
+	case MLX5_CMD_OP_CREATE_UCTX:
+	case MLX5_CMD_OP_DESTROY_UCTX:
+	case MLX5_CMD_OP_CREATE_UMEM:
+	case MLX5_CMD_OP_DESTROY_UMEM:
 	case MLX5_CMD_OP_ALLOC_MEMIC:
 		*status = MLX5_DRIVER_STATUS_ABORTED;
 		*synd = MLX5_DRIVER_SYND;
@@ -627,6 +632,11 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT);
 	MLX5_COMMAND_STR_CASE(ALLOC_MEMIC);
 	MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC);
+	MLX5_COMMAND_STR_CASE(QUERY_ESW_FUNCTIONS);
+	MLX5_COMMAND_STR_CASE(CREATE_UCTX);
+	MLX5_COMMAND_STR_CASE(DESTROY_UCTX);
+	MLX5_COMMAND_STR_CASE(CREATE_UMEM);
+	MLX5_COMMAND_STR_CASE(DESTROY_UMEM);
 	default: return "unknown command opcode";
 	}
 }
@@ -915,7 +925,6 @@ static void cmd_work_handler(struct work_struct *work)
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
-	mmiowb();
 	/* if not in polling don't use ent after this point */
 	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);
@@ -1345,7 +1354,7 @@ static void set_wqname(struct mlx5_core_dev *dev)
 	struct mlx5_cmd *cmd = &dev->cmd;
 
 	snprintf(cmd->wq_name, sizeof(cmd->wq_name), "mlx5_cmd_%s",
-		 dev_name(&dev->pdev->dev));
+		 dev_name(dev->device));
 }
 
 static void clean_debug_files(struct mlx5_core_dev *dev)
@@ -1583,9 +1592,47 @@ no_trig:
 	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
 }
 
+void mlx5_cmd_flush(struct mlx5_core_dev *dev)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+	int i;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		while (down_trylock(&cmd->sem))
+			mlx5_cmd_trigger_completions(dev);
+
+	while (down_trylock(&cmd->pages_sem))
+		mlx5_cmd_trigger_completions(dev);
+
+	/* Unlock cmdif */
+	up(&cmd->pages_sem);
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		up(&cmd->sem);
+}
+
 static int status_to_err(u8 status)
 {
-	return status ? -1 : 0; /* TBD more meaningful codes */
+	switch (status) {
+	case MLX5_CMD_DELIVERY_STAT_OK:
+	case MLX5_DRIVER_STATUS_ABORTED:
+		return 0;
+	case MLX5_CMD_DELIVERY_STAT_SIGNAT_ERR:
+	case MLX5_CMD_DELIVERY_STAT_TOK_ERR:
+		return -EBADR;
+	case MLX5_CMD_DELIVERY_STAT_BAD_BLK_NUM_ERR:
+	case MLX5_CMD_DELIVERY_STAT_OUT_PTR_ALIGN_ERR:
+	case MLX5_CMD_DELIVERY_STAT_IN_PTR_ALIGN_ERR:
+		return -EFAULT; /* Bad address */
+	case MLX5_CMD_DELIVERY_STAT_IN_LENGTH_ERR:
+	case MLX5_CMD_DELIVERY_STAT_OUT_LENGTH_ERR:
+	case MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR:
+	case MLX5_CMD_DELIVERY_STAT_RES_FLD_NOT_CLR_ERR:
+		return -ENOMSG;
+	case MLX5_CMD_DELIVERY_STAT_FW_ERR:
+		return -EIO;
+	default:
+		return -EINVAL;
+	}
 }
 
 static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
@@ -1711,12 +1758,57 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 }
 EXPORT_SYMBOL(mlx5_cmd_exec);
 
-int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size,
-		     void *out, int out_size, mlx5_cmd_cbk_t callback,
-		     void *context)
+void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev,
+			     struct mlx5_async_ctx *ctx)
+{
+	ctx->dev = dev;
+	/* Starts at 1 to avoid doing wake_up if we are not cleaning up */
+	atomic_set(&ctx->num_inflight, 1);
+	init_waitqueue_head(&ctx->wait);
+}
+EXPORT_SYMBOL(mlx5_cmd_init_async_ctx);
+
+/**
+ * mlx5_cmd_cleanup_async_ctx - Clean up an async_ctx
+ * @ctx: The ctx to clean
+ *
+ * Upon return all callbacks given to mlx5_cmd_exec_cb() have been called. The
+ * caller must ensure that mlx5_cmd_exec_cb() is not called during or after
+ * the call mlx5_cleanup_async_ctx().
+ */
+void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx)
+{
+	atomic_dec(&ctx->num_inflight);
+	wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0);
+}
+EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx);
+
+static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 {
-	return cmd_exec(dev, in, in_size, out, out_size, callback, context,
-			false);
+	struct mlx5_async_work *work = _work;
+	struct mlx5_async_ctx *ctx = work->ctx;
+
+	work->user_callback(status, work);
+	if (atomic_dec_and_test(&ctx->num_inflight))
+		wake_up(&ctx->wait);
+}
+
+int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
+		     void *out, int out_size, mlx5_async_cbk_t callback,
+		     struct mlx5_async_work *work)
+{
+	int ret;
+
+	work->ctx = ctx;
+	work->user_callback = callback;
+	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
+		return -EIO;
+	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
+		       mlx5_cmd_exec_cb_handler, work, false);
+	if (ret && atomic_dec_and_test(&ctx->num_inflight))
+		wake_up(&ctx->wait);
+
+	return ret;
 }
 EXPORT_SYMBOL(mlx5_cmd_exec_cb);
 
@@ -1787,7 +1879,7 @@ static void create_msg_cache(struct mlx5_core_dev *dev)
 
 static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 {
-	struct device *ddev = &dev->pdev->dev;
+	struct device *ddev = dev->device;
 
 	cmd->cmd_alloc_buf = dma_alloc_coherent(ddev, MLX5_ADAPTER_PAGE_SIZE,
 						&cmd->alloc_dma, GFP_KERNEL);
@@ -1818,7 +1910,7 @@ static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 
 static void free_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 {
-	struct device *ddev = &dev->pdev->dev;
+	struct device *ddev = dev->device;
 
 	dma_free_coherent(ddev, cmd->alloc_size, cmd->cmd_alloc_buf,
 			  cmd->alloc_dma);
@@ -1837,14 +1929,13 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	memset(cmd, 0, sizeof(*cmd));
 	cmd_if_rev = cmdif_rev(dev);
 	if (cmd_if_rev != CMD_IF_REV) {
-		dev_err(&dev->pdev->dev,
-			"Driver cmdif rev(%d) differs from firmware's(%d)\n",
-			CMD_IF_REV, cmd_if_rev);
+		mlx5_core_err(dev,
+			      "Driver cmdif rev(%d) differs from firmware's(%d)\n",
+			      CMD_IF_REV, cmd_if_rev);
 		return -EINVAL;
 	}
 
-	cmd->pool = dma_pool_create("mlx5_cmd", &dev->pdev->dev, size, align,
-				    0);
+	cmd->pool = dma_pool_create("mlx5_cmd", dev->device, size, align, 0);
 	if (!cmd->pool)
 		return -ENOMEM;
 
@@ -1856,14 +1947,14 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	cmd->log_sz = cmd_l >> 4 & 0xf;
 	cmd->log_stride = cmd_l & 0xf;
 	if (1 << cmd->log_sz > MLX5_MAX_COMMANDS) {
-		dev_err(&dev->pdev->dev, "firmware reports too many outstanding commands %d\n",
-			1 << cmd->log_sz);
+		mlx5_core_err(dev, "firmware reports too many outstanding commands %d\n",
+			      1 << cmd->log_sz);
 		err = -EINVAL;
 		goto err_free_page;
 	}
 
 	if (cmd->log_sz + cmd->log_stride > MLX5_ADAPTER_PAGE_SHIFT) {
-		dev_err(&dev->pdev->dev, "command queue size overflow\n");
+		mlx5_core_err(dev, "command queue size overflow\n");
 		err = -EINVAL;
 		goto err_free_page;
 	}
@@ -1874,8 +1965,8 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 
 	cmd->cmdif_rev = ioread32be(&dev->iseg->cmdif_rev_fw_sub) >> 16;
 	if (cmd->cmdif_rev > CMD_IF_REV) {
-		dev_err(&dev->pdev->dev, "driver does not support command interface version. driver %d, firmware %d\n",
-			CMD_IF_REV, cmd->cmdif_rev);
+		mlx5_core_err(dev, "driver does not support command interface version. driver %d, firmware %d\n",
+			      CMD_IF_REV, cmd->cmdif_rev);
 		err = -EOPNOTSUPP;
 		goto err_free_page;
 	}
@@ -1891,7 +1982,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	cmd_h = (u32)((u64)(cmd->dma) >> 32);
 	cmd_l = (u32)(cmd->dma);
 	if (cmd_l & 0xfff) {
-		dev_err(&dev->pdev->dev, "invalid command queue address\n");
+		mlx5_core_err(dev, "invalid command queue address\n");
 		err = -ENOMEM;
 		goto err_free_page;
 	}
@@ -1911,7 +2002,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	set_wqname(dev);
 	cmd->wq = create_singlethread_workqueue(cmd->wq_name);
 	if (!cmd->wq) {
-		dev_err(&dev->pdev->dev, "failed to create command workqueue\n");
+		mlx5_core_err(dev, "failed to create command workqueue\n");
 		err = -ENOMEM;
 		goto err_cache;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 713a17ee3751..818edc63e428 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -58,7 +58,7 @@ void mlx5_cq_tasklet_cb(unsigned long data)
 	list_for_each_entry_safe(mcq, temp, &ctx->process_list,
 				 tasklet_ctx.list) {
 		list_del_init(&mcq->tasklet_ctx.list);
-		mcq->tasklet_ctx.comp(mcq);
+		mcq->tasklet_ctx.comp(mcq, NULL);
 		mlx5_cq_put(mcq);
 		if (time_after(jiffies, end))
 			break;
@@ -68,7 +68,8 @@ void mlx5_cq_tasklet_cb(unsigned long data)
 		tasklet_schedule(&ctx->task);
 }
 
-static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq)
+static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq,
+				   struct mlx5_eqe *eqe)
 {
 	unsigned long flags;
 	struct mlx5_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
@@ -87,11 +88,10 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq)
 }
 
 int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
-			u32 *in, int inlen)
+			u32 *in, int inlen, u32 *out, int outlen)
 {
 	int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), c_eqn);
 	u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)];
-	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)];
 	struct mlx5_eq_comp *eq;
 	int err;
@@ -100,9 +100,9 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	if (IS_ERR(eq))
 		return PTR_ERR(eq);
 
-	memset(out, 0, sizeof(out));
+	memset(out, 0, outlen);
 	MLX5_SET(create_cq_in, in, opcode, MLX5_CMD_OP_CREATE_CQ);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
 	if (err)
 		return err;
 
@@ -158,13 +158,8 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0};
 	int err;
 
-	err = mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
-	if (err)
-		return err;
-
-	err = mlx5_eq_del_cq(&cq->eq->core, cq);
-	if (err)
-		return err;
+	mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
+	mlx5_eq_del_cq(&cq->eq->core, cq);
 
 	MLX5_SET(destroy_cq_in, in, opcode, MLX5_CMD_OP_DESTROY_CQ);
 	MLX5_SET(destroy_cq_in, in, cqn, cq->cqn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index ebc046fa97d3..5bb6a26ea267 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -248,11 +248,32 @@ void mlx5_unregister_interface(struct mlx5_interface *intf)
 }
 EXPORT_SYMBOL(mlx5_unregister_interface);
 
+/* Must be called with intf_mutex held */
+static bool mlx5_has_added_dev_by_protocol(struct mlx5_core_dev *mdev, int protocol)
+{
+	struct mlx5_device_context *dev_ctx;
+	struct mlx5_interface *intf;
+	bool found = false;
+
+	list_for_each_entry(intf, &intf_list, list) {
+		if (intf->protocol == protocol) {
+			dev_ctx = mlx5_get_device(intf, &mdev->priv);
+			if (dev_ctx && test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
+				found = true;
+			break;
+		}
+	}
+
+	return found;
+}
+
 void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol)
 {
 	mutex_lock(&mlx5_intf_mutex);
-	mlx5_remove_dev_by_protocol(mdev, protocol);
-	mlx5_add_dev_by_protocol(mdev, protocol);
+	if (mlx5_has_added_dev_by_protocol(mdev, protocol)) {
+		mlx5_remove_dev_by_protocol(mdev, protocol);
+		mlx5_add_dev_by_protocol(mdev, protocol);
+	}
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
@@ -290,13 +311,20 @@ static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev)
 /* Must be called with intf_mutex held */
 struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 {
-	u32 pci_id = mlx5_gen_pci_id(dev);
 	struct mlx5_core_dev *res = NULL;
 	struct mlx5_core_dev *tmp_dev;
 	struct mlx5_priv *priv;
+	u32 pci_id;
 
+	if (!mlx5_core_is_pf(dev))
+		return NULL;
+
+	pci_id = mlx5_gen_pci_id(dev);
 	list_for_each_entry(priv, &mlx5_dev_list, dev_list) {
 		tmp_dev = container_of(priv, struct mlx5_core_dev, priv);
+		if (!mlx5_core_is_pf(tmp_dev))
+			continue;
+
 		if ((dev != tmp_dev) && (mlx5_gen_pci_id(tmp_dev) == pci_id)) {
 			res = tmp_dev;
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
new file mode 100644
index 000000000000..a400f4430c28
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <devlink.h>
+
+#include "mlx5_core.h"
+#include "eswitch.h"
+
+static int mlx5_devlink_flash_update(struct devlink *devlink,
+				     const char *file_name,
+				     const char *component,
+				     struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	const struct firmware *fw;
+	int err;
+
+	if (component)
+		return -EOPNOTSUPP;
+
+	err = request_firmware_direct(&fw, file_name, &dev->pdev->dev);
+	if (err)
+		return err;
+
+	return mlx5_firmware_flash(dev, fw, extack);
+}
+
+static u8 mlx5_fw_ver_major(u32 version)
+{
+	return (version >> 24) & 0xff;
+}
+
+static u8 mlx5_fw_ver_minor(u32 version)
+{
+	return (version >> 16) & 0xff;
+}
+
+static u16 mlx5_fw_ver_subminor(u32 version)
+{
+	return version & 0xffff;
+}
+
+#define DEVLINK_FW_STRING_LEN 32
+
+static int
+mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
+		      struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	char version_str[DEVLINK_FW_STRING_LEN];
+	u32 running_fw, stored_fw;
+	int err;
+
+	err = devlink_info_driver_name_put(req, DRIVER_NAME);
+	if (err)
+		return err;
+
+	err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id);
+	if (err)
+		return err;
+
+	err = mlx5_fw_version_query(dev, &running_fw, &stored_fw);
+	if (err)
+		return err;
+
+	snprintf(version_str, sizeof(version_str), "%d.%d.%04d",
+		 mlx5_fw_ver_major(running_fw), mlx5_fw_ver_minor(running_fw),
+		 mlx5_fw_ver_subminor(running_fw));
+	err = devlink_info_version_running_put(req, "fw.version", version_str);
+	if (err)
+		return err;
+
+	/* no pending version, return running (stored) version */
+	if (stored_fw == 0)
+		stored_fw = running_fw;
+
+	snprintf(version_str, sizeof(version_str), "%d.%d.%04d",
+		 mlx5_fw_ver_major(stored_fw), mlx5_fw_ver_minor(stored_fw),
+		 mlx5_fw_ver_subminor(stored_fw));
+	err = devlink_info_version_stored_put(req, "fw.version", version_str);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static const struct devlink_ops mlx5_devlink_ops = {
+#ifdef CONFIG_MLX5_ESWITCH
+	.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
+	.eswitch_mode_get = mlx5_devlink_eswitch_mode_get,
+	.eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set,
+	.eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get,
+	.eswitch_encap_mode_set = mlx5_devlink_eswitch_encap_mode_set,
+	.eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get,
+#endif
+	.flash_update = mlx5_devlink_flash_update,
+	.info_get = mlx5_devlink_info_get,
+};
+
+struct devlink *mlx5_devlink_alloc(void)
+{
+	return devlink_alloc(&mlx5_devlink_ops, sizeof(struct mlx5_core_dev));
+}
+
+void mlx5_devlink_free(struct devlink *devlink)
+{
+	devlink_free(devlink);
+}
+
+int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
+{
+	return devlink_register(devlink, dev);
+}
+
+void mlx5_devlink_unregister(struct devlink *devlink)
+{
+	devlink_unregister(devlink);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
new file mode 100644
index 000000000000..d0ba03774ddf
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019, Mellanox Technologies */
+
+#ifndef __MLX5_DEVLINK_H__
+#define __MLX5_DEVLINK_H__
+
+#include <net/devlink.h>
+
+struct devlink *mlx5_devlink_alloc(void);
+void mlx5_devlink_free(struct devlink *devlink);
+int mlx5_devlink_register(struct devlink *devlink, struct device *dev);
+void mlx5_devlink_unregister(struct devlink *devlink);
+
+#endif /* __MLX5_DEVLINK_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/diag/Makefile
index d8e17110f25d..c78512eed8d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
new file mode 100644
index 000000000000..28d02749d3c4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/crdump.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "lib/pci_vsc.h"
+#include "lib/mlx5.h"
+
+#define BAD_ACCESS			0xBADACCE5
+#define MLX5_PROTECTED_CR_SCAN_CRSPACE	0x7
+
+static bool mlx5_crdump_enabled(struct mlx5_core_dev *dev)
+{
+	return !!dev->priv.health.crdump_size;
+}
+
+static int mlx5_crdump_fill(struct mlx5_core_dev *dev, u32 *cr_data)
+{
+	u32 crdump_size = dev->priv.health.crdump_size;
+	int i, ret;
+
+	for (i = 0; i < (crdump_size / 4); i++)
+		cr_data[i] = BAD_ACCESS;
+
+	ret = mlx5_vsc_gw_read_block_fast(dev, cr_data, crdump_size);
+	if (ret <= 0) {
+		if (ret == 0)
+			return -EIO;
+		return ret;
+	}
+
+	if (crdump_size != ret) {
+		mlx5_core_warn(dev, "failed to read full dump, read %d out of %u\n",
+			       ret, crdump_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data)
+{
+	int ret;
+
+	if (!mlx5_crdump_enabled(dev))
+		return -ENODEV;
+
+	ret = mlx5_vsc_gw_lock(dev);
+	if (ret) {
+		mlx5_core_warn(dev, "crdump: failed to lock vsc gw err %d\n",
+			       ret);
+		return ret;
+	}
+	/* Verify no other PF is running cr-dump or sw reset */
+	ret = mlx5_vsc_sem_set_space(dev, MLX5_SEMAPHORE_SW_RESET,
+				     MLX5_VSC_LOCK);
+	if (ret) {
+		mlx5_core_warn(dev, "Failed to lock SW reset semaphore\n");
+		goto unlock_gw;
+	}
+
+	ret = mlx5_vsc_gw_set_space(dev, MLX5_VSC_SPACE_SCAN_CRSPACE, NULL);
+	if (ret)
+		goto unlock_sem;
+
+	ret = mlx5_crdump_fill(dev, cr_data);
+
+unlock_sem:
+	mlx5_vsc_sem_set_space(dev, MLX5_SEMAPHORE_SW_RESET, MLX5_VSC_UNLOCK);
+unlock_gw:
+	mlx5_vsc_gw_unlock(dev);
+	return ret;
+}
+
+int mlx5_crdump_enable(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	u32 space_size;
+	int ret;
+
+	if (!mlx5_core_is_pf(dev) || !mlx5_vsc_accessible(dev) ||
+	    mlx5_crdump_enabled(dev))
+		return 0;
+
+	ret = mlx5_vsc_gw_lock(dev);
+	if (ret)
+		return ret;
+
+	/* Check if space is supported and get space size */
+	ret = mlx5_vsc_gw_set_space(dev, MLX5_VSC_SPACE_SCAN_CRSPACE,
+				    &space_size);
+	if (ret) {
+		/* Unlock and mask error since space is not supported */
+		mlx5_vsc_gw_unlock(dev);
+		return 0;
+	}
+
+	if (!space_size) {
+		mlx5_core_warn(dev, "Invalid Crspace size, zero\n");
+		mlx5_vsc_gw_unlock(dev);
+		return -EINVAL;
+	}
+
+	ret = mlx5_vsc_gw_unlock(dev);
+	if (ret)
+		return ret;
+
+	priv->health.crdump_size = space_size;
+	return 0;
+}
+
+void mlx5_crdump_disable(struct mlx5_core_dev *dev)
+{
+	dev->priv.health.crdump_size = 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index 424457ff9759..8ecac81a385d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -258,6 +258,8 @@ const char *parse_fs_dst(struct trace_seq *p,
 	return ret;
 }
 
+EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_add_ft);
+EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_del_ft);
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_add_fg);
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_del_fg);
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_set_fte);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index d027ce00c8ce..ddf1b87f1bc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -61,6 +61,41 @@ const char *parse_fs_dst(struct trace_seq *p,
 			 const struct mlx5_flow_destination *dst,
 			 u32 counter_id);
 
+TRACE_EVENT(mlx5_fs_add_ft,
+	    TP_PROTO(const struct mlx5_flow_table *ft),
+	    TP_ARGS(ft),
+	    TP_STRUCT__entry(
+		__field(const struct mlx5_flow_table *, ft)
+		__field(u32, id)
+		__field(u32, level)
+		__field(u32, type)
+	    ),
+	    TP_fast_assign(
+			   __entry->ft = ft;
+			   __entry->id = ft->id;
+			   __entry->level = ft->level;
+			   __entry->type = ft->type;
+	    ),
+	    TP_printk("ft=%p id=%u level=%u type=%u \n",
+		      __entry->ft, __entry->id, __entry->level, __entry->type)
+	    );
+
+TRACE_EVENT(mlx5_fs_del_ft,
+	    TP_PROTO(const struct mlx5_flow_table *ft),
+	    TP_ARGS(ft),
+	    TP_STRUCT__entry(
+		__field(const struct mlx5_flow_table *, ft)
+		__field(u32, id)
+	    ),
+	    TP_fast_assign(
+			   __entry->ft = ft;
+			   __entry->id = ft->id;
+
+	    ),
+	    TP_printk("ft=%p id=%u\n",
+		      __entry->ft, __entry->id)
+	    );
+
 TRACE_EVENT(mlx5_fs_add_fg,
 	    TP_PROTO(const struct mlx5_flow_group *fg),
 	    TP_ARGS(fg),
@@ -152,6 +187,7 @@ TRACE_EVENT(mlx5_fs_set_fte,
 		__field(u32, index)
 		__field(u32, action)
 		__field(u32, flow_tag)
+		__field(u32, flow_source)
 		__field(u8,  mask_enable)
 		__field(int, new_fte)
 		__array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4))
@@ -169,7 +205,8 @@ TRACE_EVENT(mlx5_fs_set_fte,
 			   __entry->index = fte->index;
 			   __entry->action = fte->action.action;
 			   __entry->mask_enable = __entry->fg->mask.match_criteria_enable;
-			   __entry->flow_tag = fte->action.flow_tag;
+			   __entry->flow_tag = fte->flow_context.flow_tag;
+			   __entry->flow_source = fte->flow_context.flow_source;
 			   memcpy(__entry->mask_outer,
 				  MLX5_ADDR_OF(fte_match_param,
 					       &__entry->fg->mask.match_criteria,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 6999f4486e9e..8a4930c8bf62 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -243,6 +243,19 @@ free_strings_db:
 	return -ENOMEM;
 }
 
+static void
+mlx5_fw_tracer_init_saved_traces_array(struct mlx5_fw_tracer *tracer)
+{
+	tracer->st_arr.saved_traces_index = 0;
+	mutex_init(&tracer->st_arr.lock);
+}
+
+static void
+mlx5_fw_tracer_clean_saved_traces_array(struct mlx5_fw_tracer *tracer)
+{
+	mutex_destroy(&tracer->st_arr.lock);
+}
+
 static void mlx5_tracer_read_strings_db(struct work_struct *work)
 {
 	struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer,
@@ -522,6 +535,24 @@ static void mlx5_fw_tracer_clean_ready_list(struct mlx5_fw_tracer *tracer)
 		list_del(&str_frmt->list);
 }
 
+static void mlx5_fw_tracer_save_trace(struct mlx5_fw_tracer *tracer,
+				      u64 timestamp, bool lost,
+				      u8 event_id, char *msg)
+{
+	struct mlx5_fw_trace_data *trace_data;
+
+	mutex_lock(&tracer->st_arr.lock);
+	trace_data = &tracer->st_arr.straces[tracer->st_arr.saved_traces_index];
+	trace_data->timestamp = timestamp;
+	trace_data->lost = lost;
+	trace_data->event_id = event_id;
+	strncpy(trace_data->msg, msg, TRACE_STR_MSG);
+
+	tracer->st_arr.saved_traces_index =
+		(tracer->st_arr.saved_traces_index + 1) & (SAVED_TRACES_NUM - 1);
+	mutex_unlock(&tracer->st_arr.lock);
+}
+
 static void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt,
 				    struct mlx5_core_dev *dev,
 				    u64 trace_timestamp)
@@ -540,6 +571,9 @@ static void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt,
 	trace_mlx5_fw(dev->tracer, trace_timestamp, str_frmt->lost,
 		      str_frmt->event_id, tmp);
 
+	mlx5_fw_tracer_save_trace(dev->tracer, trace_timestamp,
+				  str_frmt->lost, str_frmt->event_id, tmp);
+
 	/* remove it from hash */
 	mlx5_tracer_clean_message(str_frmt);
 }
@@ -786,6 +820,109 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
 	mlx5_fw_tracer_start(tracer);
 }
 
+static int mlx5_fw_tracer_set_core_dump_reg(struct mlx5_core_dev *dev,
+					    u32 *in, int size_in)
+{
+	u32 out[MLX5_ST_SZ_DW(core_dump_reg)] = {};
+
+	if (!MLX5_CAP_DEBUG(dev, core_dump_general) &&
+	    !MLX5_CAP_DEBUG(dev, core_dump_qp))
+		return -EOPNOTSUPP;
+
+	return mlx5_core_access_reg(dev, in, size_in, out, sizeof(out),
+				    MLX5_REG_CORE_DUMP, 0, 1);
+}
+
+int mlx5_fw_tracer_trigger_core_dump_general(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_tracer *tracer = dev->tracer;
+	u32 in[MLX5_ST_SZ_DW(core_dump_reg)] = {};
+	int err;
+
+	if (!MLX5_CAP_DEBUG(dev, core_dump_general) || !tracer)
+		return -EOPNOTSUPP;
+	if (!tracer->owner)
+		return -EPERM;
+
+	MLX5_SET(core_dump_reg, in, core_dump_type, 0x0);
+
+	err =  mlx5_fw_tracer_set_core_dump_reg(dev, in, sizeof(in));
+	if (err)
+		return err;
+	queue_work(tracer->work_queue, &tracer->handle_traces_work);
+	flush_workqueue(tracer->work_queue);
+	return 0;
+}
+
+static int
+mlx5_devlink_fmsg_fill_trace(struct devlink_fmsg *fmsg,
+			     struct mlx5_fw_trace_data *trace_data)
+{
+	int err;
+
+	err = devlink_fmsg_obj_nest_start(fmsg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u64_pair_put(fmsg, "timestamp", trace_data->timestamp);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_bool_pair_put(fmsg, "lost", trace_data->lost);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "event_id", trace_data->event_id);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_string_pair_put(fmsg, "msg", trace_data->msg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_obj_nest_end(fmsg);
+	if (err)
+		return err;
+	return 0;
+}
+
+int mlx5_fw_tracer_get_saved_traces_objects(struct mlx5_fw_tracer *tracer,
+					    struct devlink_fmsg *fmsg)
+{
+	struct mlx5_fw_trace_data *straces = tracer->st_arr.straces;
+	u32 index, start_index, end_index;
+	u32 saved_traces_index;
+	int err;
+
+	if (!straces[0].timestamp)
+		return -ENOMSG;
+
+	mutex_lock(&tracer->st_arr.lock);
+	saved_traces_index = tracer->st_arr.saved_traces_index;
+	if (straces[saved_traces_index].timestamp)
+		start_index = saved_traces_index;
+	else
+		start_index = 0;
+	end_index = (saved_traces_index - 1) & (SAVED_TRACES_NUM - 1);
+
+	err = devlink_fmsg_arr_pair_nest_start(fmsg, "dump fw traces");
+	if (err)
+		goto unlock;
+	index = start_index;
+	while (index != end_index) {
+		err = mlx5_devlink_fmsg_fill_trace(fmsg, &straces[index]);
+		if (err)
+			goto unlock;
+
+		index = (index + 1) & (SAVED_TRACES_NUM - 1);
+	}
+
+	err = devlink_fmsg_arr_pair_nest_end(fmsg);
+unlock:
+	mutex_unlock(&tracer->st_arr.lock);
+	return err;
+}
+
 /* Create software resources (Buffers, etc ..) */
 struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 {
@@ -833,6 +970,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 		goto free_log_buf;
 	}
 
+	mlx5_fw_tracer_init_saved_traces_array(tracer);
 	mlx5_core_dbg(dev, "FWTracer: Tracer created\n");
 
 	return tracer;
@@ -917,6 +1055,7 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	cancel_work_sync(&tracer->read_fw_strings_work);
 	mlx5_fw_tracer_clean_ready_list(tracer);
 	mlx5_fw_tracer_clean_print_hash(tracer);
+	mlx5_fw_tracer_clean_saved_traces_array(tracer);
 	mlx5_fw_tracer_free_strings_db(tracer);
 	mlx5_fw_tracer_destroy_log_buf(tracer);
 	flush_workqueue(tracer->work_queue);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index a8b8747f2b61..40601fba80ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -46,6 +46,9 @@
 #define TRACER_BLOCK_SIZE_BYTE 256
 #define TRACES_PER_BLOCK 32
 
+#define TRACE_STR_MSG 256
+#define SAVED_TRACES_NUM 8192
+
 #define TRACER_MAX_PARAMS 7
 #define MESSAGE_HASH_BITS 6
 #define MESSAGE_HASH_SIZE BIT(MESSAGE_HASH_BITS)
@@ -53,6 +56,13 @@
 #define MASK_52_7 (0x1FFFFFFFFFFF80)
 #define MASK_6_0  (0x7F)
 
+struct mlx5_fw_trace_data {
+	u64 timestamp;
+	bool lost;
+	u8 event_id;
+	char msg[TRACE_STR_MSG];
+};
+
 struct mlx5_fw_tracer {
 	struct mlx5_core_dev *dev;
 	struct mlx5_nb        nb;
@@ -83,6 +93,13 @@ struct mlx5_fw_tracer {
 		u32 consumer_index;
 	} buff;
 
+	/* Saved Traces Array */
+	struct {
+		struct mlx5_fw_trace_data straces[SAVED_TRACES_NUM];
+		u32 saved_traces_index;
+		struct mutex lock; /* Protect st_arr access */
+	} st_arr;
+
 	u64 last_timestamp;
 	struct work_struct handle_traces_work;
 	struct hlist_head hash[MESSAGE_HASH_SIZE];
@@ -171,5 +188,8 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
 int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
+int mlx5_fw_tracer_trigger_core_dump_general(struct mlx5_core_dev *dev);
+int mlx5_fw_tracer_get_saved_traces_objects(struct mlx5_fw_tracer *tracer,
+					    struct devlink_fmsg *fmsg);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
index 83f90e9aff45..3038be575923 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
@@ -47,7 +47,7 @@ TRACE_EVENT(mlx5_fw,
 	TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
 
 	TP_STRUCT__entry(
-		__string(dev_name, dev_name(&tracer->dev->pdev->dev))
+		__string(dev_name, dev_name(tracer->dev->device))
 		__field(u64, trace_timestamp)
 		__field(bool, lost)
 		__field(u8, event_id)
@@ -55,7 +55,8 @@ TRACE_EVENT(mlx5_fw,
 	),
 
 	TP_fast_assign(
-		__assign_str(dev_name, dev_name(&tracer->dev->pdev->dev));
+		__assign_str(dev_name,
+			     dev_name(tracer->dev->device));
 		__entry->trace_timestamp = trace_timestamp;
 		__entry->lost = lost;
 		__entry->event_id = event_id;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
new file mode 100644
index 000000000000..d2228e37450f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "ecpf.h"
+
+bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev)
+{
+	return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1;
+}
+
+static int mlx5_peer_pf_enable_hca(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(enable_hca_in)]   = {};
+
+	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
+	MLX5_SET(enable_hca_in, in, function_id, 0);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+}
+
+static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(disable_hca_in)]   = {};
+
+	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
+	MLX5_SET(disable_hca_in, in, function_id, 0);
+	MLX5_SET(disable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_peer_pf_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_peer_pf_enable_hca(dev);
+	if (err)
+		mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n",
+			      err);
+
+	return err;
+}
+
+static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_peer_pf_disable_hca(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n",
+			      err);
+		return;
+	}
+
+	err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages);
+	if (err)
+		mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n",
+			       err);
+}
+
+int mlx5_ec_init(struct mlx5_core_dev *dev)
+{
+	int err = 0;
+
+	if (!mlx5_core_is_ecpf(dev))
+		return 0;
+
+	/* ECPF shall enable HCA for peer PF in the same way a PF
+	 * does this for its VFs.
+	 */
+	err = mlx5_peer_pf_init(dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
+{
+	if (!mlx5_core_is_ecpf(dev))
+		return;
+
+	mlx5_peer_pf_cleanup(dev);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
new file mode 100644
index 000000000000..d3d7a00a02ac
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_ECPF_H__
+#define __MLX5_ECPF_H__
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+enum {
+	MLX5_ECPU_BIT_NUM = 23,
+};
+
+bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev);
+int mlx5_ec_init(struct mlx5_core_dev *dev);
+void mlx5_ec_cleanup(struct mlx5_core_dev *dev);
+
+#else  /* CONFIG_MLX5_ESWITCH */
+
+static inline bool
+mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; }
+static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; }
+static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+
+#endif /* __MLX5_ECPF_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8fa8fdd30b85..79d93d6c7d7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -48,7 +48,7 @@
 #include <linux/rhashtable.h>
 #include <net/switchdev.h>
 #include <net/xdp.h>
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 #include <linux/bits.h>
 #include "wq.h"
 #include "mlx5_core.h"
@@ -76,15 +76,14 @@ struct page_pool;
 #define MLX5_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
 				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
+#define MLX5E_RX_MAX_HEAD (256)
+
 #define MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev) \
 	(6 + MLX5_CAP_GEN(mdev, cache_line_128byte)) /* HW restriction */
 #define MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, req) \
 	max_t(u32, MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev), req)
-#define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev)       MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 6)
-#define MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 8)
-#define MLX5E_MPWQE_STRIDE_SZ(mdev, cqe_cmprs) \
-	(cqe_cmprs ? MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : \
-	MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev))
+#define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) \
+	MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, order_base_2(MLX5E_RX_MAX_HEAD))
 
 #define MLX5_MPWRQ_LOG_WQE_SZ			18
 #define MLX5_MPWRQ_WQE_PAGE_ORDER  (MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT > 0 ? \
@@ -119,8 +118,6 @@ struct page_pool;
 
 #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW            0x2
 
-#define MLX5E_RX_MAX_HEAD (256)
-
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32
 #define MLX5E_LRO_TIMEOUT_ARR_SIZE                      4
@@ -140,6 +137,7 @@ struct page_pool;
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
+#define MLX5E_TX_XSK_POLL_BUDGET       64
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
 #define MLX5E_UMR_WQE_INLINE_SZ \
@@ -158,6 +156,11 @@ do {                                                            \
 			    ##__VA_ARGS__);                     \
 } while (0)
 
+enum mlx5e_rq_group {
+	MLX5E_RQ_GROUP_REGULAR,
+	MLX5E_RQ_GROUP_XSK,
+	MLX5E_NUM_RQ_GROUPS /* Keep last. */
+};
 
 static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
 {
@@ -182,7 +185,8 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 /* Use this function to get max num channels after netdev was created */
 static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev)
 {
-	return min_t(unsigned int, netdev->num_rx_queues,
+	return min_t(unsigned int,
+		     netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS,
 		     netdev->num_tx_queues);
 }
 
@@ -205,7 +209,10 @@ struct mlx5e_umr_wqe {
 	struct mlx5_wqe_ctrl_seg       ctrl;
 	struct mlx5_wqe_umr_ctrl_seg   uctrl;
 	struct mlx5_mkey_seg           mkc;
-	struct mlx5_mtt                inline_mtts[0];
+	union {
+		struct mlx5_mtt        inline_mtts[0];
+		u8                     tls_static_params_ctx[0];
+	};
 };
 
 extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
@@ -241,10 +248,10 @@ struct mlx5e_params {
 	u16 num_channels;
 	u8  num_tc;
 	bool rx_cqe_compress_def;
-	struct net_dim_cq_moder rx_cq_moderation;
-	struct net_dim_cq_moder tx_cq_moderation;
+	bool tunneled_offload_en;
+	struct dim_cq_moder rx_cq_moderation;
+	struct dim_cq_moder tx_cq_moderation;
 	bool lro_en;
-	u32 lro_wqe_sz;
 	u8  tx_min_inline_mode;
 	bool vlan_strip_disable;
 	bool scatter_fcs_en;
@@ -253,6 +260,7 @@ struct mlx5e_params {
 	u32 lro_timeout;
 	u32 pflags;
 	struct bpf_prog *xdp_prog;
+	struct mlx5e_xsk *xsk;
 	unsigned int sw_mtu;
 	int hard_mtu;
 };
@@ -297,6 +305,7 @@ enum {
 	MLX5E_RQ_STATE_ENABLED,
 	MLX5E_RQ_STATE_AM,
 	MLX5E_RQ_STATE_NO_CSUM_COMPLETE,
+	MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */
 };
 
 struct mlx5e_cq {
@@ -309,16 +318,18 @@ struct mlx5e_cq {
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_channel      *channel;
 
+	/* control */
+	struct mlx5_core_dev      *mdev;
+	struct mlx5_wq_ctrl        wq_ctrl;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_cq_decomp {
 	/* cqe decompression */
 	struct mlx5_cqe64          title;
 	struct mlx5_mini_cqe8      mini_arr[MLX5_MINI_CQE_ARRAY_SIZE];
 	u8                         mini_arr_idx;
-	u16                        decmprs_left;
-	u16                        decmprs_wqe_counter;
-
-	/* control */
-	struct mlx5_core_dev      *mdev;
-	struct mlx5_wq_ctrl        wq_ctrl;
+	u16                        left;
+	u16                        wqe_counter;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_tx_wqe_info {
@@ -326,6 +337,9 @@ struct mlx5e_tx_wqe_info {
 	u32 num_bytes;
 	u8  num_wqebbs;
 	u8  num_dma;
+#ifdef CONFIG_MLX5_EN_TLS
+	skb_frag_t *resync_dump_frag;
+#endif
 };
 
 enum mlx5e_dma_map_type {
@@ -349,6 +363,13 @@ enum {
 
 struct mlx5e_sq_wqe_info {
 	u8  opcode;
+
+	/* Auxiliary data for different opcodes. */
+	union {
+		struct {
+			struct mlx5e_rq *rq;
+		} umr;
+	};
 };
 
 struct mlx5e_txqsq {
@@ -357,7 +378,7 @@ struct mlx5e_txqsq {
 	/* dirtied @completion */
 	u16                        cc;
 	u32                        dma_fifo_cc;
-	struct net_dim             dim; /* Adaptive Moderation */
+	struct dim                 dim; /* Adaptive Moderation */
 
 	/* dirtied @xmit */
 	u16                        pc ____cacheline_aligned_in_smp;
@@ -376,6 +397,7 @@ struct mlx5e_txqsq {
 	void __iomem              *uar_map;
 	struct netdev_queue       *txq;
 	u32                        sqn;
+	u16                        stop_room;
 	u8                         min_inline_mode;
 	struct device             *pdev;
 	__be32                     mkey_be;
@@ -386,23 +408,62 @@ struct mlx5e_txqsq {
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
 	struct mlx5e_channel      *channel;
+	int                        ch_ix;
 	int                        txq_ix;
 	u32                        rate_limit;
-	struct mlx5e_txqsq_recover {
-		struct work_struct         recover_work;
-		u64                        last_recover;
-	} recover;
+	struct work_struct         recover_work;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_dma_info {
-	struct page     *page;
-	dma_addr_t      addr;
+	dma_addr_t addr;
+	union {
+		struct page *page;
+		struct {
+			u64 handle;
+			void *data;
+		} xsk;
+	};
+};
+
+/* XDP packets can be transmitted in different ways. On completion, we need to
+ * distinguish between them to clean up things in a proper way.
+ */
+enum mlx5e_xdp_xmit_mode {
+	/* An xdp_frame was transmitted due to either XDP_REDIRECT from another
+	 * device or XDP_TX from an XSK RQ. The frame has to be unmapped and
+	 * returned.
+	 */
+	MLX5E_XDP_XMIT_MODE_FRAME,
+
+	/* The xdp_frame was created in place as a result of XDP_TX from a
+	 * regular RQ. No DMA remapping happened, and the page belongs to us.
+	 */
+	MLX5E_XDP_XMIT_MODE_PAGE,
+
+	/* No xdp_frame was created at all, the transmit happened from a UMEM
+	 * page. The UMEM Completion Ring producer pointer has to be increased.
+	 */
+	MLX5E_XDP_XMIT_MODE_XSK,
 };
 
 struct mlx5e_xdp_info {
-	struct xdp_frame      *xdpf;
-	dma_addr_t            dma_addr;
-	struct mlx5e_dma_info di;
+	enum mlx5e_xdp_xmit_mode mode;
+	union {
+		struct {
+			struct xdp_frame *xdpf;
+			dma_addr_t dma_addr;
+		} frame;
+		struct {
+			struct mlx5e_rq *rq;
+			struct mlx5e_dma_info di;
+		} page;
+	};
+};
+
+struct mlx5e_xdp_xmit_data {
+	dma_addr_t  dma_addr;
+	void       *data;
+	u32         len;
 };
 
 struct mlx5e_xdp_info_fifo {
@@ -414,26 +475,32 @@ struct mlx5e_xdp_info_fifo {
 
 struct mlx5e_xdp_wqe_info {
 	u8 num_wqebbs;
-	u8 num_ds;
+	u8 num_pkts;
 };
 
 struct mlx5e_xdp_mpwqe {
 	/* Current MPWQE session */
 	struct mlx5e_tx_wqe *wqe;
 	u8                   ds_count;
+	u8                   pkt_count;
 	u8                   max_ds_count;
+	u8                   complete;
+	u8                   inline_on;
 };
 
 struct mlx5e_xdpsq;
-typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq*,
-					struct mlx5e_xdp_info*);
+typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *);
+typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *,
+					struct mlx5e_xdp_xmit_data *,
+					struct mlx5e_xdp_info *,
+					int);
+
 struct mlx5e_xdpsq {
 	/* data path */
 
 	/* dirtied @completion */
 	u32                        xdpi_fifo_cc;
 	u16                        cc;
-	bool                       redirect_flush;
 
 	/* dirtied @xmit */
 	u32                        xdpi_fifo_pc ____cacheline_aligned_in_smp;
@@ -444,8 +511,10 @@ struct mlx5e_xdpsq {
 	struct mlx5e_cq            cq;
 
 	/* read only */
+	struct xdp_umem           *umem;
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
+	mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check;
 	mlx5e_fp_xmit_xdp_frame    xmit_xdp_frame;
 	struct {
 		struct mlx5e_xdp_wqe_info *wqe_info;
@@ -466,10 +535,10 @@ struct mlx5e_xdpsq {
 
 struct mlx5e_icosq {
 	/* data path */
+	u16                        cc;
+	u16                        pc;
 
-	/* dirtied @xmit */
-	u16                        pc ____cacheline_aligned_in_smp;
-
+	struct mlx5_wqe_ctrl_seg  *doorbell_cseg;
 	struct mlx5e_cq            cq;
 
 	/* write@xmit, read@completion */
@@ -488,12 +557,6 @@ struct mlx5e_icosq {
 	struct mlx5e_channel      *channel;
 } ____cacheline_aligned_in_smp;
 
-static inline bool
-mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
-{
-	return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
-}
-
 struct mlx5e_wqe_frag_info {
 	struct mlx5e_dma_info *di;
 	u32 offset;
@@ -536,7 +599,8 @@ typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
 typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
 
 enum mlx5e_rq_flag {
-	MLX5E_RQ_FLAG_XDP_XMIT = BIT(0),
+	MLX5E_RQ_FLAG_XDP_XMIT,
+	MLX5E_RQ_FLAG_XDP_REDIRECT,
 };
 
 struct mlx5e_rq_frag_info {
@@ -567,11 +631,15 @@ struct mlx5e_rq {
 			struct mlx5e_mpw_info *info;
 			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
 			u16                    num_strides;
+			u16                    actual_wq_head;
 			u8                     log_stride_sz;
-			bool                   umr_in_progress;
+			u8                     umr_in_progress;
+			u8                     umr_last_bulk;
+			u8                     umr_completed;
 		} mpwqe;
 	};
 	struct {
+		u16            umem_headroom;
 		u16            headroom;
 		u8             map_dir;   /* dma map direction */
 	} buff;
@@ -581,6 +649,7 @@ struct mlx5e_rq {
 	struct net_device     *netdev;
 	struct mlx5e_rq_stats *stats;
 	struct mlx5e_cq        cq;
+	struct mlx5e_cq_decomp cqd;
 	struct mlx5e_page_cache page_cache;
 	struct hwtstamp_config *tstamp;
 	struct mlx5_clock      *clock;
@@ -593,14 +662,18 @@ struct mlx5e_rq {
 	int                    ix;
 	unsigned int           hw_mtu;
 
-	struct net_dim         dim; /* Dynamic Interrupt Moderation */
+	struct dim         dim; /* Dynamic Interrupt Moderation */
 
 	/* XDP */
 	struct bpf_prog       *xdp_prog;
-	struct mlx5e_xdpsq     xdpsq;
+	struct mlx5e_xdpsq    *xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
 
+	/* AF_XDP zero-copy */
+	struct zero_copy_allocator zca;
+	struct xdp_umem       *umem;
+
 	/* control */
 	struct mlx5_wq_ctrl    wq_ctrl;
 	__be32                 mkey_be;
@@ -613,9 +686,15 @@ struct mlx5e_rq {
 	struct xdp_rxq_info    xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
+enum mlx5e_channel_state {
+	MLX5E_CHANNEL_STATE_XSK,
+	MLX5E_CHANNEL_NUM_STATES
+};
+
 struct mlx5e_channel {
 	/* data path */
 	struct mlx5e_rq            rq;
+	struct mlx5e_xdpsq         rq_xdpsq;
 	struct mlx5e_txqsq         sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_icosq         icosq;   /* internal control operations */
 	bool                       xdp;
@@ -628,6 +707,13 @@ struct mlx5e_channel {
 	/* XDP_REDIRECT */
 	struct mlx5e_xdpsq         xdpsq;
 
+	/* AF_XDP zero-copy */
+	struct mlx5e_rq            xskrq;
+	struct mlx5e_xdpsq         xsksq;
+	struct mlx5e_icosq         xskicosq;
+	/* xskicosq can be accessed from any CPU - the spinlock protects it. */
+	spinlock_t                 xskicosq_lock;
+
 	/* data path - accessed per napi poll */
 	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
@@ -636,8 +722,10 @@ struct mlx5e_channel {
 	struct mlx5e_priv         *priv;
 	struct mlx5_core_dev      *mdev;
 	struct hwtstamp_config    *tstamp;
+	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
 	int                        cpu;
+	cpumask_var_t              xps_cpumask;
 };
 
 struct mlx5e_channels {
@@ -650,13 +738,17 @@ struct mlx5e_channel_stats {
 	struct mlx5e_ch_stats ch;
 	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
+	struct mlx5e_rq_stats xskrq;
 	struct mlx5e_xdpsq_stats rq_xdpsq;
 	struct mlx5e_xdpsq_stats xdpsq;
+	struct mlx5e_xdpsq_stats xsksq;
 } ____cacheline_aligned_in_smp;
 
 enum {
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
+	MLX5E_STATE_XDP_TX_ENABLED,
+	MLX5E_STATE_XDP_OPEN,
 };
 
 struct mlx5e_rqt {
@@ -682,6 +774,24 @@ struct mlx5e_rss_params {
 	u8	hfunc;
 };
 
+struct mlx5e_modify_sq_param {
+	int curr_state;
+	int next_state;
+	int rl_update;
+	int rl_index;
+};
+
+struct mlx5e_xsk {
+	/* UMEMs are stored separately from channels, because we don't want to
+	 * lose them when channels are recreated. The kernel also stores UMEMs,
+	 * but it doesn't distinguish between zero-copy and non-zero-copy UMEMs,
+	 * so rely on our mechanism.
+	 */
+	struct xdp_umem **umems;
+	u16 refcnt;
+	bool ever_used;
+};
+
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
@@ -702,6 +812,7 @@ struct mlx5e_priv {
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
+	struct mlx5e_tir           xsk_tir[MLX5E_MAX_NUM_CHANNELS];
 	struct mlx5e_rss_params    rss_params;
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
@@ -737,6 +848,8 @@ struct mlx5e_priv {
 #ifdef CONFIG_MLX5_EN_TLS
 	struct mlx5e_tls          *tls;
 #endif
+	struct devlink_health_reporter *tx_reporter;
+	struct mlx5e_xsk           xsk;
 };
 
 struct mlx5e_profile {
@@ -750,6 +863,7 @@ struct mlx5e_profile {
 	void	(*cleanup_tx)(struct mlx5e_priv *priv);
 	void	(*enable)(struct mlx5e_priv *priv);
 	void	(*disable)(struct mlx5e_priv *priv);
+	int	(*update_rx)(struct mlx5e_priv *priv);
 	void	(*update_stats)(struct mlx5e_priv *priv);
 	void	(*update_carrier)(struct mlx5e_priv *priv);
 	struct {
@@ -762,13 +876,13 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback);
+		       struct net_device *sb_dev);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5e_tx_wqe *wqe, u16 pi);
+			  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
 
-void mlx5e_completion_event(struct mlx5_core_cq *mcq);
+void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
+void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
@@ -780,11 +894,13 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params);
 
 void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
-void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
-			bool recycle);
+void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
+				struct mlx5e_dma_info *dma_info,
+				bool recycle);
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
+void mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
@@ -803,6 +919,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
+void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
 
 void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
@@ -839,6 +956,30 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
 void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
 struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt);
 
+struct mlx5e_xsk_param;
+
+struct mlx5e_rq_param;
+int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		  struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk,
+		  struct xdp_umem *umem, struct mlx5e_rq *rq);
+int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time);
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
+void mlx5e_close_rq(struct mlx5e_rq *rq);
+
+struct mlx5e_sq_param;
+int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
+void mlx5e_close_icosq(struct mlx5e_icosq *sq);
+int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		     struct mlx5e_sq_param *param, struct xdp_umem *umem,
+		     struct mlx5e_xdpsq *sq, bool is_redirect);
+void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq);
+
+struct mlx5e_cq_param;
+int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder,
+		  struct mlx5e_cq_param *param, struct mlx5e_cq *cq);
+void mlx5e_close_cq(struct mlx5e_cq *cq);
+
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
 
@@ -850,9 +991,10 @@ void mlx5e_close_channels(struct mlx5e_channels *chs);
  * switching channels
  */
 typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
-void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
-				struct mlx5e_channels *new_chs,
-				mlx5e_fp_hw_modify hw_modify);
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
+int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
+			       struct mlx5e_channels *new_chs,
+			       mlx5e_fp_hw_modify hw_modify);
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
 
@@ -866,65 +1008,21 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params);
 
+int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+		    struct mlx5e_modify_sq_param *p);
+void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq);
+void mlx5e_tx_disable_queue(struct netdev_queue *txq);
+
 static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev)
 {
 	return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) &&
 		MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version));
 }
 
-static inline void mlx5e_sq_fetch_wqe(struct mlx5e_txqsq *sq,
-				      struct mlx5e_tx_wqe **wqe,
-				      u16 *pi)
+static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_wq_cyc *wq = &sq->wq;
-
-	*pi  = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	*wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
-	memset(*wqe, 0, sizeof(**wqe));
-}
-
-static inline
-struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
-{
-	u16                         pi   = mlx5_wq_cyc_ctr2ix(wq, *pc);
-	struct mlx5e_tx_wqe        *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-	struct mlx5_wqe_ctrl_seg   *cseg = &wqe->ctrl;
-
-	memset(cseg, 0, sizeof(*cseg));
-
-	cseg->opmod_idx_opcode = cpu_to_be32((*pc << 8) | MLX5_OPCODE_NOP);
-	cseg->qpn_ds           = cpu_to_be32((sqn << 8) | 0x01);
-
-	(*pc)++;
-
-	return wqe;
-}
-
-static inline
-void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc,
-		     void __iomem *uar_map,
-		     struct mlx5_wqe_ctrl_seg *ctrl)
-{
-	ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
-	/* ensure wqe is visible to device before updating doorbell record */
-	dma_wmb();
-
-	*wq->db = cpu_to_be32(pc);
-
-	/* ensure doorbell record is visible to device before ringing the
-	 * doorbell
-	 */
-	wmb();
-
-	mlx5_write64((__be32 *)ctrl, uar_map, NULL);
-}
-
-static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
-{
-	struct mlx5_core_cq *mcq;
-
-	mcq = &cq->mcq;
-	mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, cq->wq.cc);
+	return MLX5_CAP_ETH(mdev, swp) &&
+		MLX5_CAP_ETH(mdev, swp_csum) && MLX5_CAP_ETH(mdev, swp_lso);
 }
 
 extern const struct ethtool_ops mlx5e_ethtool_ops;
@@ -956,17 +1054,17 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
 int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
 void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc);
 
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
-void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv);
-int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
-void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
+void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
+int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
+void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs);
 void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
 
-int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
-		     u32 underlay_qpn, u32 *tisn);
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
 int mlx5e_create_tises(struct mlx5e_priv *priv);
+int mlx5e_update_nic_rx(struct mlx5e_priv *priv);
 void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
@@ -1008,8 +1106,6 @@ u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv);
 u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info);
-int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
-			       struct ethtool_flash *flash);
 void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
 				  struct ethtool_pauseparam *pauseparam);
 int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
@@ -1028,7 +1124,9 @@ mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *prof
 int mlx5e_attach_netdev(struct mlx5e_priv *priv);
 void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
+void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_xsk *xsk,
 			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
 			    u16 max_channels, u16 mtu);
@@ -1045,6 +1143,7 @@ void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti)
 netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 				       struct net_device *netdev,
 				       netdev_features_t features);
+int mlx5e_set_features(struct net_device *netdev, netdev_features_t features);
 #ifdef CONFIG_MLX5_ESWITCH
 int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
 int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/en/Makefile
index d8e17110f25d..c78512eed8d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
index 2ce420851e77..7cd5b02e0f10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -66,7 +66,7 @@ static int mlx5e_monitor_event_handler(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-void mlx5e_monitor_counter_start(struct mlx5e_priv *priv)
+static void mlx5e_monitor_counter_start(struct mlx5e_priv *priv)
 {
 	MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler,
 		     MONITOR_COUNTER);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
new file mode 100644
index 000000000000..79301d116667
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "en/params.h"
+
+static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params,
+				   struct mlx5e_xsk_param *xsk)
+{
+	return params->xdp_prog || xsk;
+}
+
+u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params,
+				 struct mlx5e_xsk_param *xsk)
+{
+	u16 headroom = NET_IP_ALIGN;
+
+	if (mlx5e_rx_is_xdp(params, xsk)) {
+		headroom += XDP_PACKET_HEADROOM;
+		if (xsk)
+			headroom += xsk->headroom;
+	} else {
+		headroom += MLX5_RX_HEADROOM;
+	}
+
+	return headroom;
+}
+
+u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params,
+				struct mlx5e_xsk_param *xsk)
+{
+	u32 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	u16 linear_rq_headroom = mlx5e_get_linear_rq_headroom(params, xsk);
+	u32 frag_sz = linear_rq_headroom + hw_mtu;
+
+	/* AF_XDP doesn't build SKBs in place. */
+	if (!xsk)
+		frag_sz = MLX5_SKB_FRAG_SZ(frag_sz);
+
+	/* XDP in mlx5e doesn't support multiple packets per page. */
+	if (mlx5e_rx_is_xdp(params, xsk))
+		frag_sz = max_t(u32, frag_sz, PAGE_SIZE);
+
+	/* Even if we can go with a smaller fragment size, we must not put
+	 * multiple packets into a single frame.
+	 */
+	if (xsk)
+		frag_sz = max_t(u32, frag_sz, xsk->chunk_size);
+
+	return frag_sz;
+}
+
+u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params,
+				struct mlx5e_xsk_param *xsk)
+{
+	u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk);
+
+	return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
+}
+
+bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params,
+			    struct mlx5e_xsk_param *xsk)
+{
+	/* AF_XDP allocates SKBs on XDP_PASS - ensure they don't occupy more
+	 * than one page. For this, check both with and without xsk.
+	 */
+	u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk),
+				 mlx5e_rx_get_linear_frag_sz(params, NULL));
+
+	return !params->lro_en && linear_frag_sz <= PAGE_SIZE;
+}
+
+#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \
+					  MLX5_MPWQE_LOG_STRIDE_SZ_BASE)
+bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
+				  struct mlx5e_params *params,
+				  struct mlx5e_xsk_param *xsk)
+{
+	u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk);
+	s8 signed_log_num_strides_param;
+	u8 log_num_strides;
+
+	if (!mlx5e_rx_is_linear_skb(params, xsk))
+		return false;
+
+	if (order_base_2(linear_frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
+		return false;
+
+	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
+		return true;
+
+	log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
+	signed_log_num_strides_param =
+		(s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
+
+	return signed_log_num_strides_param >= 0;
+}
+
+u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params,
+			       struct mlx5e_xsk_param *xsk)
+{
+	u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params, xsk);
+
+	/* Numbers are unsigned, don't subtract to avoid underflow. */
+	if (params->log_rq_mtu_frames <
+	    log_pkts_per_wqe + MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW)
+		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
+
+	return params->log_rq_mtu_frames - log_pkts_per_wqe;
+}
+
+u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params,
+				   struct mlx5e_xsk_param *xsk)
+{
+	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk))
+		return order_base_2(mlx5e_rx_get_linear_frag_sz(params, xsk));
+
+	return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
+}
+
+u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params,
+				   struct mlx5e_xsk_param *xsk)
+{
+	return MLX5_MPWRQ_LOG_WQE_SZ -
+		mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+}
+
+u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
+			  struct mlx5e_params *params,
+			  struct mlx5e_xsk_param *xsk)
+{
+	bool is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
+		mlx5e_rx_is_linear_skb(params, xsk) :
+		mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk);
+
+	return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
new file mode 100644
index 000000000000..bd882b5ee9a7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_PARAMS_H__
+#define __MLX5_EN_PARAMS_H__
+
+#include "en.h"
+
+struct mlx5e_xsk_param {
+	u16 headroom;
+	u16 chunk_size;
+};
+
+struct mlx5e_rq_param {
+	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
+	struct mlx5_wq_param       wq;
+	struct mlx5e_rq_frags_info frags_info;
+};
+
+struct mlx5e_sq_param {
+	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
+	struct mlx5_wq_param       wq;
+	bool                       is_mpw;
+};
+
+struct mlx5e_cq_param {
+	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
+	struct mlx5_wq_param       wq;
+	u16                        eq_ix;
+	u8                         cq_period_mode;
+};
+
+struct mlx5e_channel_param {
+	struct mlx5e_rq_param      rq;
+	struct mlx5e_sq_param      sq;
+	struct mlx5e_sq_param      xdp_sq;
+	struct mlx5e_sq_param      icosq;
+	struct mlx5e_cq_param      rx_cq;
+	struct mlx5e_cq_param      tx_cq;
+	struct mlx5e_cq_param      icosq_cq;
+};
+
+static inline bool mlx5e_qid_get_ch_if_in_group(struct mlx5e_params *params,
+						u16 qid,
+						enum mlx5e_rq_group group,
+						u16 *ix)
+{
+	int nch = params->num_channels;
+	int ch = qid - nch * group;
+
+	if (ch < 0 || ch >= nch)
+		return false;
+
+	*ix = ch;
+	return true;
+}
+
+static inline void mlx5e_qid_get_ch_and_group(struct mlx5e_params *params,
+					      u16 qid,
+					      u16 *ix,
+					      enum mlx5e_rq_group *group)
+{
+	u16 nch = params->num_channels;
+
+	*ix = qid % nch;
+	*group = qid / nch;
+}
+
+static inline bool mlx5e_qid_validate(struct mlx5e_params *params, u64 qid)
+{
+	return qid < params->num_channels * MLX5E_NUM_RQ_GROUPS;
+}
+
+/* Parameter calculations */
+
+u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params,
+				 struct mlx5e_xsk_param *xsk);
+u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params,
+				struct mlx5e_xsk_param *xsk);
+u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params,
+				struct mlx5e_xsk_param *xsk);
+bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params,
+			    struct mlx5e_xsk_param *xsk);
+bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
+				  struct mlx5e_params *params,
+				  struct mlx5e_xsk_param *xsk);
+u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params,
+			       struct mlx5e_xsk_param *xsk);
+u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params,
+				   struct mlx5e_xsk_param *xsk);
+u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
+				   struct mlx5e_params *params,
+				   struct mlx5e_xsk_param *xsk);
+u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
+			  struct mlx5e_params *params,
+			  struct mlx5e_xsk_param *xsk);
+
+/* Build queue parameters */
+
+void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+			  struct mlx5e_params *params,
+			  struct mlx5e_xsk_param *xsk,
+			  struct mlx5e_rq_param *param);
+void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
+				 struct mlx5e_sq_param *param);
+void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_xsk_param *xsk,
+			     struct mlx5e_cq_param *param);
+void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_cq_param *param);
+void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
+			      u8 log_wq_size,
+			      struct mlx5e_cq_param *param);
+void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
+			     u8 log_wq_size,
+			     struct mlx5e_sq_param *param);
+void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_sq_param *param);
+
+#endif /* __MLX5_EN_PARAMS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 4a37713023be..d5e5afbdca6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -63,66 +63,165 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
 	[MLX5E_50GBASE_KR2]       = 50000,
 };
 
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper)
+static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
+	[MLX5E_SGMII_100M]			= 100,
+	[MLX5E_1000BASE_X_SGMII]		= 1000,
+	[MLX5E_5GBASE_R]			= 5000,
+	[MLX5E_10GBASE_XFI_XAUI_1]		= 10000,
+	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= 40000,
+	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= 25000,
+	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2]	= 50000,
+	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= 50000,
+	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= 100000,
+	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= 200000,
+	[MLX5E_400GAUI_8]			= 400000,
+};
+
+static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
+				     const u32 **arr, u32 *size)
+{
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+
+	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
+		      ARRAY_SIZE(mlx5e_link_speed);
+	*arr  = ext ? mlx5e_ext_link_speed : mlx5e_link_speed;
+}
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5e_port_eth_proto *eproto)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	if (!eproto)
+		return -EINVAL;
+
+	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port);
+	if (err)
+		return err;
+
+	eproto->cap   = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					   eth_proto_capability);
+	eproto->admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin);
+	eproto->oper  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
+	return 0;
+}
+
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+				 u8 *an_disable_cap, u8 *an_disable_admin)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+
+	*an_status = 0;
+	*an_disable_cap = 0;
+	*an_disable_admin = 0;
+
+	if (mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, 1))
+		return;
+
+	*an_status = MLX5_GET(ptys_reg, out, an_status);
+	*an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
+	*an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
+}
+
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+			   u32 proto_admin, bool ext)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
+	u8 an_disable_admin;
+	u8 an_disable_cap;
+	u8 an_status;
+
+	mlx5_port_query_eth_autoneg(dev, &an_status, &an_disable_cap,
+				    &an_disable_admin);
+	if (!an_disable_cap && an_disable)
+		return -EPERM;
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(ptys_reg, in, local_port, 1);
+	MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
+	MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN);
+	if (ext)
+		MLX5_SET(ptys_reg, in, ext_eth_proto_admin, proto_admin);
+	else
+		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out,
+			    sizeof(out), MLX5_REG_PTYS, 0, 1);
+}
+
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
 {
 	unsigned long temp = eth_proto_oper;
+	const u32 *table;
 	u32 speed = 0;
+	u32 max_size;
 	int i;
 
-	i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER);
-	if (i < MLX5E_LINK_MODES_NUMBER)
-		speed = mlx5e_link_speed[i];
-
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	i = find_first_bit(&temp, max_size);
+	if (i < max_size)
+		speed = table[i];
 	return speed;
 }
 
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {};
-	u32 eth_proto_oper;
+	struct mlx5e_port_eth_proto eproto;
+	bool ext;
 	int err;
 
-	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
-		return err;
+		goto out;
 
-	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	*speed = mlx5e_port_ptys2speed(eth_proto_oper);
+	*speed = mlx5e_port_ptys2speed(mdev, eproto.oper);
 	if (!(*speed))
 		err = -EINVAL;
 
+out:
 	return err;
 }
 
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
+	struct mlx5e_port_eth_proto eproto;
 	u32 max_speed = 0;
-	u32 proto_cap;
+	const u32 *table;
+	u32 max_size;
+	bool ext;
 	int err;
 	int i;
 
-	err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN);
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		return err;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i)
-		if (proto_cap & MLX5E_PROT_MASK(i))
-			max_speed = max(max_speed, mlx5e_link_speed[i]);
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	for (i = 0; i < max_size; ++i)
+		if (eproto.cap & MLX5E_PROT_MASK(i))
+			max_speed = max(max_speed, table[i]);
 
 	*speed = max_speed;
 	return 0;
 }
 
-u32 mlx5e_port_speed2linkmodes(u32 speed)
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed)
 {
 	u32 link_modes = 0;
+	const u32 *table;
+	u32 max_size;
 	int i;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (mlx5e_link_speed[i] == speed)
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	for (i = 0; i < max_size; ++i) {
+		if (table[i] == speed)
 			link_modes |= MLX5E_PROT_MASK(i);
 	}
-
 	return link_modes;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index cd2160b8c9bf..70f536ec51c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -36,10 +36,22 @@
 #include <linux/mlx5/driver.h>
 #include "en.h"
 
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper);
+struct mlx5e_port_eth_proto {
+	u32 cap;
+	u32 admin;
+	u32 oper;
+};
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5e_port_eth_proto *eproto);
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+				 u8 *an_disable_cap, u8 *an_disable_admin);
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+			   u32 proto_admin, bool ext);
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper);
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-u32 mlx5e_port_speed2linkmodes(u32 speed);
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed);
 
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index eac245a93f91..633b117eb13e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -122,7 +122,9 @@ out:
 	return err;
 }
 
-/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */
+/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B])
+ * minimum speed value is 40Gbps
+ */
 static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 {
 	u32 speed;
@@ -130,10 +132,9 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
-		return 0;
-	}
+	if (err)
+		speed = SPEED_40000;
+	speed = max_t(u32, speed, SPEED_40000);
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 
@@ -142,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 }
 
 static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
-				 u32 xoff, unsigned int mtu)
+				 u32 xoff, unsigned int max_mtu)
 {
 	int i;
 
@@ -154,36 +155,37 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
 			return -ENOMEM;
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
-		port_buffer->buffer[i].xon  = port_buffer->buffer[i].xoff - mtu;
+		port_buffer->buffer[i].xon  =
+			port_buffer->buffer[i].xoff - max_mtu;
 	}
 
 	return 0;
 }
 
 /**
- * update_buffer_lossy()
- *   mtu: device's MTU
- *   pfc_en: <input> current pfc configuration
- *   buffer: <input> current prio to buffer mapping
- *   xoff:   <input> xoff value
- *   port_buffer: <output> port receive buffer configuration
- *   change: <output>
+ *	update_buffer_lossy	- Update buffer configuration based on pfc
+ *	@max_mtu: netdev's max_mtu
+ *	@pfc_en: <input> current pfc configuration
+ *	@buffer: <input> current prio to buffer mapping
+ *	@xoff:   <input> xoff value
+ *	@port_buffer: <output> port receive buffer configuration
+ *	@change: <output>
  *
- *   Update buffer configuration based on pfc configuraiton and priority
- *   to buffer mapping.
- *   Buffer's lossy bit is changed to:
- *     lossless if there is at least one PFC enabled priority mapped to this buffer
- *     lossy if all priorities mapped to this buffer are PFC disabled
+ *	Update buffer configuration based on pfc configuraiton and
+ *	priority to buffer mapping.
+ *	Buffer's lossy bit is changed to:
+ *		lossless if there is at least one PFC enabled priority
+ *		mapped to this buffer lossy if all priorities mapped to
+ *		this buffer are PFC disabled
  *
- *   Return:
- *     Return 0 if no error.
- *     Set change to true if buffer configuration is modified.
+ *	@return: 0 if no error,
+ *	sets change to true if buffer configuration was modified.
  */
-static int update_buffer_lossy(unsigned int mtu,
+static int update_buffer_lossy(unsigned int max_mtu,
 			       u8 pfc_en, u8 *buffer, u32 xoff,
 			       struct mlx5e_port_buffer *port_buffer,
 			       bool *change)
@@ -220,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	}
 
 	if (changed) {
-		err = update_xoff_threshold(port_buffer, xoff, mtu);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 
@@ -230,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	return 0;
 }
 
+#define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
@@ -241,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	bool update_prio2buffer = false;
 	u8 buffer[MLX5E_MAX_PRIORITY];
 	bool update_buffer = false;
+	unsigned int max_mtu;
 	u32 total_used = 0;
 	u8 curr_pfc_en;
 	int err;
 	int i;
 
 	mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change);
+	max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);
 
 	err = mlx5e_port_query_buffer(priv, &port_buffer);
 	if (err)
@@ -254,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_CABLE_LEN) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -264,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff,
+		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff,
 					  &port_buffer, &update_buffer);
 		if (err)
 			return err;
@@ -276,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff,
-					  &port_buffer, &update_buffer);
+		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer,
+					  xoff, &port_buffer, &update_buffer);
 		if (err)
 			return err;
 	}
@@ -301,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return -EINVAL;
 
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -309,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	/* Need to update buffer configuration if xoff value is changed */
 	if (!update_buffer && xoff != priv->dcbx.xoff) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
new file mode 100644
index 000000000000..e78e92753d73
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5E_EN_REPORTER_H
+#define __MLX5E_EN_REPORTER_H
+
+#include <linux/mlx5/driver.h>
+#include "en.h"
+
+int mlx5e_tx_reporter_create(struct mlx5e_priv *priv);
+void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv);
+void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq);
+int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
new file mode 100644
index 000000000000..f3d98748b211
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -0,0 +1,312 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <net/devlink.h>
+#include "reporter.h"
+#include "lib/eq.h"
+
+#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256
+
+struct mlx5e_tx_err_ctx {
+	int (*recover)(struct mlx5e_txqsq *sq);
+	struct mlx5e_txqsq *sq;
+};
+
+static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
+{
+	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+
+	while (time_before(jiffies, exp_time)) {
+		if (sq->cc == sq->pc)
+			return 0;
+
+		msleep(20);
+	}
+
+	netdev_err(sq->channel->netdev,
+		   "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n",
+		   sq->sqn, sq->cc, sq->pc);
+
+	return -ETIMEDOUT;
+}
+
+static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
+{
+	WARN_ONCE(sq->cc != sq->pc,
+		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
+		  sq->sqn, sq->cc, sq->pc);
+	sq->cc = 0;
+	sq->dma_fifo_cc = 0;
+	sq->pc = 0;
+}
+
+static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
+{
+	struct mlx5_core_dev *mdev = sq->channel->mdev;
+	struct net_device *dev = sq->channel->netdev;
+	struct mlx5e_modify_sq_param msp = {0};
+	int err;
+
+	msp.curr_state = curr_state;
+	msp.next_state = MLX5_SQC_STATE_RST;
+
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
+		return err;
+	}
+
+	memset(&msp, 0, sizeof(msp));
+	msp.curr_state = MLX5_SQC_STATE_RST;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
+		return err;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_core_dev *mdev = sq->channel->mdev;
+	struct net_device *dev = sq->channel->netdev;
+	u8 state;
+	int err;
+
+	if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+		return 0;
+
+	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
+	if (err) {
+		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
+			   sq->sqn, err);
+		return err;
+	}
+
+	if (state != MLX5_SQC_STATE_ERR) {
+		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
+		return -EINVAL;
+	}
+
+	mlx5e_tx_disable_queue(sq->txq);
+
+	err = mlx5e_wait_for_sq_flush(sq);
+	if (err)
+		return err;
+
+	/* At this point, no new packets will arrive from the stack as TXQ is
+	 * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
+	 * pending WQEs. SQ can safely reset the SQ.
+	 */
+
+	err = mlx5e_sq_to_ready(sq, state);
+	if (err)
+		return err;
+
+	mlx5e_reset_txqsq_cc_pc(sq);
+	sq->stats->recover++;
+	mlx5e_activate_txqsq(sq);
+
+	return 0;
+}
+
+static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
+				 char *err_str,
+				 struct mlx5e_tx_err_ctx *err_ctx)
+{
+	if (IS_ERR_OR_NULL(tx_reporter)) {
+		netdev_err(err_ctx->sq->channel->netdev, err_str);
+		return err_ctx->recover(err_ctx->sq);
+	}
+
+	return devlink_health_report(tx_reporter, err_str, err_ctx);
+}
+
+void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
+{
+	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
+	struct mlx5e_tx_err_ctx err_ctx = {0};
+
+	err_ctx.sq       = sq;
+	err_ctx.recover  = mlx5e_tx_reporter_err_cqe_recover;
+	sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn);
+
+	mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
+			      &err_ctx);
+}
+
+static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
+	u32 eqe_count;
+
+	netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
+		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
+
+	eqe_count = mlx5_eq_poll_irq_disabled(eq);
+	if (!eqe_count) {
+		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+		return -EIO;
+	}
+
+	netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n",
+		   eqe_count, eq->core.eqn);
+	sq->channel->stats->eq_rearm++;
+	return 0;
+}
+
+int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
+{
+	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
+	struct mlx5e_tx_err_ctx err_ctx;
+
+	err_ctx.sq       = sq;
+	err_ctx.recover  = mlx5e_tx_reporter_timeout_recover;
+	sprintf(err_str,
+		"TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
+		sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
+		jiffies_to_usecs(jiffies - sq->txq->trans_start));
+
+	return mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
+				     &err_ctx);
+}
+
+/* state lock cannot be grabbed within this function.
+ * It can cause a dead lock or a read-after-free.
+ */
+static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
+{
+	return err_ctx->recover(err_ctx->sq);
+}
+
+static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
+{
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
+	err = mlx5e_safe_reopen_channels(priv);
+
+out:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+
+	return err;
+}
+
+static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
+				     void *context)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	struct mlx5e_tx_err_ctx *err_ctx = context;
+
+	return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) :
+			 mlx5e_tx_reporter_recover_all(priv);
+}
+
+static int
+mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg,
+					u32 sqn, u8 state, bool stopped)
+{
+	int err;
+
+	err = devlink_fmsg_obj_nest_start(fmsg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "HW state", state);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_bool_pair_put(fmsg, "stopped", stopped);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_obj_nest_end(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	int i, err = 0;
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs");
+	if (err)
+		goto unlock;
+
+	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc;
+	     i++) {
+		struct mlx5e_txqsq *sq = priv->txq2sq[i];
+		u8 state;
+
+		err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
+		if (err)
+			goto unlock;
+
+		err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
+							      state,
+							      netif_xmit_stopped(sq->txq));
+		if (err)
+			goto unlock;
+	}
+	err = devlink_fmsg_arr_pair_nest_end(fmsg);
+	if (err)
+		goto unlock;
+
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
+		.name = "tx",
+		.recover = mlx5e_tx_reporter_recover,
+		.diagnose = mlx5e_tx_reporter_diagnose,
+};
+
+#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500
+
+int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct devlink *devlink = priv_to_devlink(mdev);
+
+	priv->tx_reporter =
+		devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
+					       MLX5_REPORTER_TX_GRACEFUL_PERIOD,
+					       true, priv);
+	if (IS_ERR(priv->tx_reporter))
+		netdev_warn(priv->netdev,
+			    "Failed to create tx reporter, err = %ld\n",
+			    PTR_ERR(priv->tx_reporter));
+	return IS_ERR_OR_NULL(priv->tx_reporter);
+}
+
+void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
+{
+	if (IS_ERR_OR_NULL(priv->tx_reporter))
+		return;
+
+	devlink_health_reporter_destroy(priv->tx_reporter);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index f3c7ab6faea5..a6a52806be45 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -3,42 +3,62 @@
 
 #include <net/vxlan.h>
 #include <net/gre.h>
-#include "lib/vxlan.h"
+#include <net/geneve.h>
 #include "en/tc_tun.h"
+#include "en_tc.h"
+
+struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
+{
+	if (netif_is_vxlan(tunnel_dev))
+		return &vxlan_tunnel;
+	else if (netif_is_geneve(tunnel_dev))
+		return &geneve_tunnel;
+	else if (netif_is_gretap(tunnel_dev) ||
+		 netif_is_ip6gretap(tunnel_dev))
+		return &gre_tunnel;
+	else
+		return NULL;
+}
 
 static int get_route_and_out_devs(struct mlx5e_priv *priv,
 				  struct net_device *dev,
 				  struct net_device **route_dev,
 				  struct net_device **out_dev)
 {
+	struct net_device *uplink_dev, *uplink_upper, *real_dev;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct net_device *uplink_dev, *uplink_upper;
 	bool dst_is_lag_dev;
 
+	real_dev = is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : dev;
 	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
 	dst_is_lag_dev = (uplink_upper &&
 			  netif_is_lag_master(uplink_upper) &&
-			  dev == uplink_upper &&
+			  real_dev == uplink_upper &&
 			  mlx5_lag_is_sriov(priv->mdev));
 
 	/* if the egress device isn't on the same HW e-switch or
 	 * it's a LAG device, use the uplink
 	 */
-	if (!switchdev_port_same_parent_id(priv->netdev, dev) ||
+	if (!netdev_port_same_parent_id(priv->netdev, real_dev) ||
 	    dst_is_lag_dev) {
-		*route_dev = uplink_dev;
-		*out_dev = *route_dev;
+		*route_dev = dev;
+		*out_dev = uplink_dev;
 	} else {
 		*route_dev = dev;
 		if (is_vlan_dev(*route_dev))
 			*out_dev = uplink_dev;
-		else if (mlx5e_eswitch_rep(dev))
+		else if (mlx5e_eswitch_rep(dev) &&
+			 mlx5e_is_valid_eswitch_fwd_dev(priv, dev))
 			*out_dev = *route_dev;
 		else
 			return -EOPNOTSUPP;
 	}
 
+	if (!(mlx5e_eswitch_rep(*out_dev) &&
+	      mlx5e_is_uplink_rep(netdev_priv(*out_dev))))
+		return -EOPNOTSUPP;
+
 	return 0;
 }
 
@@ -54,12 +74,24 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	struct neighbour *n = NULL;
 
 #if IS_ENABLED(CONFIG_INET)
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct net_device *uplink_dev;
 	int ret;
 
+	if (mlx5_lag_is_multipath(mdev)) {
+		struct mlx5_eswitch *esw = mdev->priv.eswitch;
+
+		uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+		fl4->flowi4_oif = uplink_dev->ifindex;
+	}
+
 	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
 	ret = PTR_ERR_OR_ZERO(rt);
 	if (ret)
 		return ret;
+
+	if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET)
+		return -ENETUNREACH;
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -84,7 +116,7 @@ static const char *mlx5e_netdev_kind(struct net_device *dev)
 	if (dev->rtnl_link_ops)
 		return dev->rtnl_link_ops->kind;
 	else
-		return "";
+		return "unknown";
 }
 
 static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
@@ -125,63 +157,15 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
-{
-	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
-	struct udphdr *udp = (struct udphdr *)(buf);
-	struct vxlanhdr *vxh = (struct vxlanhdr *)
-			       ((char *)udp + sizeof(struct udphdr));
-
-	udp->dest = tun_key->tp_dst;
-	vxh->vx_flags = VXLAN_HF_VNI;
-	vxh->vx_vni = vxlan_vni_field(tun_id);
-
-	return 0;
-}
-
-static int mlx5e_gen_gre_header(char buf[], struct ip_tunnel_key *tun_key)
-{
-	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
-	int hdr_len;
-	struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf);
-
-	/* the HW does not calculate GRE csum or sequences */
-	if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ))
-		return -EOPNOTSUPP;
-
-	greh->protocol = htons(ETH_P_TEB);
-
-	/* GRE key */
-	hdr_len = gre_calc_hlen(tun_key->tun_flags);
-	greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags);
-	if (tun_key->tun_flags & TUNNEL_KEY) {
-		__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
-
-		*ptr = tun_id;
-	}
-
-	return 0;
-}
-
 static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
 				      struct mlx5e_encap_entry *e)
 {
-	int err = 0;
-	struct ip_tunnel_key *key = &e->tun_info.key;
-
-	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		*ip_proto = IPPROTO_UDP;
-		err = mlx5e_gen_vxlan_header(buf, key);
-	} else if  (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
-		*ip_proto = IPPROTO_GRE;
-		err = mlx5e_gen_gre_header(buf, key);
-	} else {
-		pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n"
-			, e->tunnel_type);
-		err = -EOPNOTSUPP;
+	if (!e->tunnel) {
+		pr_warn("mlx5: Cannot generate tunnel header for this tunnel\n");
+		return -EOPNOTSUPP;
 	}
 
-	return err;
+	return e->tunnel->generate_ip_tun_hdr(buf, ip_proto, e);
 }
 
 static char *gen_eth_tnl_hdr(char *buf, struct net_device *dev,
@@ -213,7 +197,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 				    struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
 	struct net_device *out_dev, *route_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
@@ -237,7 +221,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	ipv4_encap_size =
 		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
 		sizeof(struct iphdr) +
-		e->tunnel_hlen;
+		e->tunnel->calc_hlen(e);
 
 	if (max_encap_size < ipv4_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -295,7 +279,9 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(n, NULL);
-		err = -EAGAIN;
+		/* the encap entry will be made valid on neigh update event
+		 * and not used before that.
+		 */
 		goto out;
 	}
 
@@ -327,7 +313,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct mlx5e_encap_entry *e)
 {
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
 	struct net_device *out_dev, *route_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
@@ -351,7 +337,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	ipv6_encap_size =
 		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
 		sizeof(struct ipv6hdr) +
-		e->tunnel_hlen;
+		e->tunnel->calc_hlen(e);
 
 	if (max_encap_size < ipv6_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -408,7 +394,9 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 
 	if (!(nud_state & NUD_VALID)) {
 		neigh_event_send(n, NULL);
-		err = -EAGAIN;
+		/* the encap entry will be made valid on neigh update event
+		 * and not used before that.
+		 */
 		goto out;
 	}
 
@@ -435,27 +423,12 @@ out:
 	return err;
 }
 
-int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev)
-{
-	if (netif_is_vxlan(tunnel_dev))
-		return MLX5E_TC_TUNNEL_TYPE_VXLAN;
-	else if (netif_is_gretap(tunnel_dev) ||
-		 netif_is_ip6gretap(tunnel_dev))
-		return MLX5E_TC_TUNNEL_TYPE_GRETAP;
-	else
-		return MLX5E_TC_TUNNEL_TYPE_UNKNOWN;
-}
-
 bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 				    struct net_device *netdev)
 {
-	int tunnel_type = mlx5e_tc_tun_get_type(netdev);
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(netdev);
 
-	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN &&
-	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
-		return true;
-	else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP &&
-		 MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap))
+	if (tunnel && tunnel->can_offload(priv))
 		return true;
 	else
 		return false;
@@ -466,173 +439,104 @@ int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
 				 struct mlx5e_encap_entry *e,
 				 struct netlink_ext_ack *extack)
 {
-	e->tunnel_type = mlx5e_tc_tun_get_type(tunnel_dev);
-
-	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		int dst_port =  be16_to_cpu(e->tun_info.key.tp_dst);
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(tunnel_dev);
 
-		if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "vxlan udp dport was not registered with the HW");
-			netdev_warn(priv->netdev,
-				    "%d isn't an offloaded vxlan udp dport\n",
-				    dst_port);
-			return -EOPNOTSUPP;
-		}
-		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
-		e->tunnel_hlen = VXLAN_HLEN;
-	} else if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
-		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_NVGRE;
-		e->tunnel_hlen = gre_calc_hlen(e->tun_info.key.tun_flags);
-	} else {
+	if (!tunnel) {
 		e->reformat_type = -1;
-		e->tunnel_hlen = -1;
 		return -EOPNOTSUPP;
 	}
-	return 0;
+
+	return tunnel->init_encap_attr(tunnel_dev, priv, e, extack);
 }
 
-static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
-				    struct mlx5_flow_spec *spec,
-				    struct tc_cls_flower_offload *f,
-				    void *headers_c,
-				    void *headers_v)
+int mlx5e_tc_tun_parse(struct net_device *filter_dev,
+		       struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct flow_cls_offload *f,
+		       void *headers_c,
+		       void *headers_v, u8 *match_level)
+{
+	struct mlx5e_tc_tunnel *tunnel = mlx5e_get_tc_tun(filter_dev);
+	int err = 0;
+
+	if (!tunnel) {
+		netdev_warn(priv->netdev,
+			    "decapsulation offload is not supported for %s net device\n",
+			    mlx5e_netdev_kind(filter_dev));
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	*match_level = tunnel->match_level;
+
+	if (tunnel->parse_udp_ports) {
+		err = tunnel->parse_udp_ports(priv, spec, f,
+					      headers_c, headers_v);
+		if (err)
+			goto out;
+	}
+
+	if (tunnel->parse_tunnel) {
+		err = tunnel->parse_tunnel(priv, spec, f,
+					   headers_c, headers_v);
+		if (err)
+			goto out;
+	}
+
+out:
+	return err;
+}
+
+int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv,
+				 struct mlx5_flow_spec *spec,
+				 struct flow_cls_offload *f,
+				 void *headers_c,
+				 void *headers_v)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
-	struct flow_dissector_key_ports *key =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_ENC_PORTS,
-					  f->key);
-	struct flow_dissector_key_ports *mask =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_ENC_PORTS,
-					  f->mask);
-	void *misc_c = MLX5_ADDR_OF(fte_match_param,
-				    spec->match_criteria,
-				    misc_parameters);
-	void *misc_v = MLX5_ADDR_OF(fte_match_param,
-				    spec->match_value,
-				    misc_parameters);
+	struct flow_match_ports enc_ports;
 
 	/* Full udp dst port must be given */
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) ||
-	    memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) {
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "VXLAN decap filter must include enc_dst_port condition");
+				   "UDP tunnel decap filter must include enc_dst_port condition");
 		netdev_warn(priv->netdev,
-			    "VXLAN decap filter must include enc_dst_port condition\n");
+			    "UDP tunnel decap filter must include enc_dst_port condition\n");
 		return -EOPNOTSUPP;
 	}
 
-	/* udp dst port must be knonwn as a VXLAN port */
-	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) {
+	flow_rule_match_enc_ports(rule, &enc_ports);
+
+	if (memchr_inv(&enc_ports.mask->dst, 0xff,
+		       sizeof(enc_ports.mask->dst))) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Matched UDP port is not registered as a VXLAN port");
+				   "UDP tunnel decap filter must match enc_dst_port fully");
 		netdev_warn(priv->netdev,
-			    "UDP port %d is not registered as a VXLAN port\n",
-			    be16_to_cpu(key->dst));
+			    "UDP tunnel decap filter must match enc_dst_port fully\n");
 		return -EOPNOTSUPP;
 	}
 
-	/* dst UDP port is valid here */
+	/* match on UDP protocol and dst port number */
+
 	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
 	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP);
 
-	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst));
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst));
-
-	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src));
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src));
-
-	/* match on VNI */
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->key);
-		struct flow_dissector_key_keyid *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->mask);
-		MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
-			 be32_to_cpu(mask->keyid));
-		MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
-			 be32_to_cpu(key->keyid));
-	}
-	return 0;
-}
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport,
+		 ntohs(enc_ports.mask->dst));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport,
+		 ntohs(enc_ports.key->dst));
 
-static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv,
-				     struct mlx5_flow_spec *spec,
-				     struct tc_cls_flower_offload *f,
-				     void *outer_headers_c,
-				     void *outer_headers_v)
-{
-	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    misc_parameters);
-	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-				    misc_parameters);
-
-	if (!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap)) {
-		NL_SET_ERR_MSG_MOD(f->common.extack,
-				   "GRE HW offloading is not supported");
-		netdev_warn(priv->netdev, "GRE HW offloading is not supported\n");
-		return -EOPNOTSUPP;
-	}
+	/* UDP src port on outer header is generated by HW,
+	 * so it is probably a bad idea to request matching it.
+	 * Nonetheless, it is allowed.
+	 */
 
-	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol);
-	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-		 ip_protocol, IPPROTO_GRE);
-
-	/* gre protocol*/
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, gre_protocol);
-	MLX5_SET(fte_match_set_misc, misc_v, gre_protocol, ETH_P_TEB);
-
-	/* gre key */
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *mask = NULL;
-		struct flow_dissector_key_keyid *key = NULL;
-
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_ENC_KEYID,
-						 f->mask);
-		MLX5_SET(fte_match_set_misc, misc_c,
-			 gre_key.key, be32_to_cpu(mask->keyid));
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_ENC_KEYID,
-						f->key);
-		MLX5_SET(fte_match_set_misc, misc_v,
-			 gre_key.key, be32_to_cpu(key->keyid));
-	}
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport,
+		 ntohs(enc_ports.mask->src));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport,
+		 ntohs(enc_ports.key->src));
 
 	return 0;
 }
-
-int mlx5e_tc_tun_parse(struct net_device *filter_dev,
-		       struct mlx5e_priv *priv,
-		       struct mlx5_flow_spec *spec,
-		       struct tc_cls_flower_offload *f,
-		       void *headers_c,
-		       void *headers_v, u8 *match_level)
-{
-	int tunnel_type;
-	int err = 0;
-
-	tunnel_type = mlx5e_tc_tun_get_type(filter_dev);
-	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
-		*match_level = MLX5_MATCH_L4;
-		err = mlx5e_tc_tun_parse_vxlan(priv, spec, f,
-					       headers_c, headers_v);
-	} else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
-		*match_level = MLX5_MATCH_L3;
-		err = mlx5e_tc_tun_parse_gretap(priv, spec, f,
-						headers_c, headers_v);
-	} else {
-		netdev_warn(priv->netdev,
-			    "decapsulation offload is not supported for %s net device (%d)\n",
-			    mlx5e_netdev_kind(filter_dev), tunnel_type);
-		return -EOPNOTSUPP;
-	}
-	return err;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index b63f15de899d..c362b9225dc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -14,9 +14,41 @@
 enum {
 	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
 	MLX5E_TC_TUNNEL_TYPE_VXLAN,
-	MLX5E_TC_TUNNEL_TYPE_GRETAP
+	MLX5E_TC_TUNNEL_TYPE_GENEVE,
+	MLX5E_TC_TUNNEL_TYPE_GRETAP,
 };
 
+struct mlx5e_tc_tunnel {
+	int tunnel_type;
+	enum mlx5_flow_match_level match_level;
+
+	bool (*can_offload)(struct mlx5e_priv *priv);
+	int (*calc_hlen)(struct mlx5e_encap_entry *e);
+	int (*init_encap_attr)(struct net_device *tunnel_dev,
+			       struct mlx5e_priv *priv,
+			       struct mlx5e_encap_entry *e,
+			       struct netlink_ext_ack *extack);
+	int (*generate_ip_tun_hdr)(char buf[],
+				   __u8 *ip_proto,
+				   struct mlx5e_encap_entry *e);
+	int (*parse_udp_ports)(struct mlx5e_priv *priv,
+			       struct mlx5_flow_spec *spec,
+			       struct flow_cls_offload *f,
+			       void *headers_c,
+			       void *headers_v);
+	int (*parse_tunnel)(struct mlx5e_priv *priv,
+			    struct mlx5_flow_spec *spec,
+			    struct flow_cls_offload *f,
+			    void *headers_c,
+			    void *headers_v);
+};
+
+extern struct mlx5e_tc_tunnel vxlan_tunnel;
+extern struct mlx5e_tc_tunnel geneve_tunnel;
+extern struct mlx5e_tc_tunnel gre_tunnel;
+
+struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev);
+
 int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
 				 struct mlx5e_priv *priv,
 				 struct mlx5e_encap_entry *e,
@@ -30,15 +62,20 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct net_device *mirred_dev,
 				    struct mlx5e_encap_entry *e);
 
-int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev);
 bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 				    struct net_device *netdev);
 
 int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 		       struct mlx5e_priv *priv,
 		       struct mlx5_flow_spec *spec,
-		       struct tc_cls_flower_offload *f,
+		       struct flow_cls_offload *f,
 		       void *headers_c,
 		       void *headers_v, u8 *match_level);
 
+int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv,
+				 struct mlx5_flow_spec *spec,
+				 struct flow_cls_offload *f,
+				 void *headers_c,
+				 void *headers_v);
+
 #endif //__MLX5_EN_TC_TUNNEL_H__
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
new file mode 100644
index 000000000000..951ea26d96bc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/geneve.h>
+#include "lib/geneve.h"
+#include "en/tc_tun.h"
+
+#define MLX5E_GENEVE_VER 0
+
+static bool mlx5e_tc_tun_can_offload_geneve(struct mlx5e_priv *priv)
+{
+	return !!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & MLX5_FLEX_PROTO_GENEVE);
+}
+
+static int mlx5e_tc_tun_calc_hlen_geneve(struct mlx5e_encap_entry *e)
+{
+	return sizeof(struct udphdr) +
+	       sizeof(struct genevehdr) +
+	       e->tun_info->options_len;
+}
+
+static int mlx5e_tc_tun_check_udp_dport_geneve(struct mlx5e_priv *priv,
+					       struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_match_ports enc_ports;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS))
+		return -EOPNOTSUPP;
+
+	flow_rule_match_enc_ports(rule, &enc_ports);
+
+	/* Currently we support only default GENEVE
+	 * port, so udp dst port must match.
+	 */
+	if (be16_to_cpu(enc_ports.key->dst) != GENEVE_UDP_PORT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matched UDP dst port is not registered as a GENEVE port");
+		netdev_warn(priv->netdev,
+			    "UDP port %d is not registered as a GENEVE port\n",
+			    be16_to_cpu(enc_ports.key->dst));
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_udp_ports_geneve(struct mlx5e_priv *priv,
+					       struct mlx5_flow_spec *spec,
+					       struct flow_cls_offload *f,
+					       void *headers_c,
+					       void *headers_v)
+{
+	int err;
+
+	err = mlx5e_tc_tun_parse_udp_ports(priv, spec, f, headers_c, headers_v);
+	if (err)
+		return err;
+
+	return mlx5e_tc_tun_check_udp_dport_geneve(priv, f);
+}
+
+static int mlx5e_tc_tun_init_encap_attr_geneve(struct net_device *tunnel_dev,
+					       struct mlx5e_priv *priv,
+					       struct mlx5e_encap_entry *e,
+					       struct netlink_ext_ack *extack)
+{
+	e->tunnel = &geneve_tunnel;
+
+	/* Reformat type for GENEVE encap is similar to VXLAN:
+	 * in both cases the HW adds in the same place a
+	 * defined encapsulation header that the SW provides.
+	 */
+	e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
+	return 0;
+}
+
+static void mlx5e_tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	vni[0] = (__force __u8)(tun_id >> 16);
+	vni[1] = (__force __u8)(tun_id >> 8);
+	vni[2] = (__force __u8)tun_id;
+#else
+	vni[0] = (__force __u8)((__force u64)tun_id >> 40);
+	vni[1] = (__force __u8)((__force u64)tun_id >> 48);
+	vni[2] = (__force __u8)((__force u64)tun_id >> 56);
+#endif
+}
+
+static int mlx5e_gen_ip_tunnel_header_geneve(char buf[],
+					     __u8 *ip_proto,
+					     struct mlx5e_encap_entry *e)
+{
+	const struct ip_tunnel_info *tun_info = e->tun_info;
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct genevehdr *geneveh;
+
+	geneveh = (struct genevehdr *)((char *)udp + sizeof(struct udphdr));
+
+	*ip_proto = IPPROTO_UDP;
+
+	udp->dest = tun_info->key.tp_dst;
+
+	memset(geneveh, 0, sizeof(*geneveh));
+	geneveh->ver = MLX5E_GENEVE_VER;
+	geneveh->opt_len = tun_info->options_len / 4;
+	geneveh->oam = !!(tun_info->key.tun_flags & TUNNEL_OAM);
+	geneveh->critical = !!(tun_info->key.tun_flags & TUNNEL_CRIT_OPT);
+	mlx5e_tunnel_id_to_vni(tun_info->key.tun_id, geneveh->vni);
+	geneveh->proto_type = htons(ETH_P_TEB);
+
+	if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+		if (!geneveh->opt_len)
+			return -EOPNOTSUPP;
+		ip_tunnel_info_opts_get(geneveh->options, tun_info);
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_geneve_vni(struct mlx5e_priv *priv,
+					 struct mlx5_flow_spec *spec,
+					 struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_match_enc_keyid enc_keyid;
+	void *misc_c, *misc_v;
+
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
+		return 0;
+
+	flow_rule_match_enc_keyid(rule, &enc_keyid);
+
+	if (!enc_keyid.mask->keyid)
+		return 0;
+
+	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, ft_field_support.outer_geneve_vni)) {
+		NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE VNI is not supported");
+		netdev_warn(priv->netdev, "Matching on GENEVE VNI is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	MLX5_SET(fte_match_set_misc, misc_c, geneve_vni, be32_to_cpu(enc_keyid.mask->keyid));
+	MLX5_SET(fte_match_set_misc, misc_v, geneve_vni, be32_to_cpu(enc_keyid.key->keyid));
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv,
+					     struct mlx5_flow_spec *spec,
+					     struct flow_cls_offload *f)
+{
+	u8 max_tlv_option_data_len = MLX5_CAP_GEN(priv->mdev, max_geneve_tlv_option_data_len);
+	u8 max_tlv_options = MLX5_CAP_GEN(priv->mdev, max_geneve_tlv_options);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	void *misc_c, *misc_v, *misc_3_c, *misc_3_v;
+	struct geneve_opt *option_key, *option_mask;
+	__be32 opt_data_key = 0, opt_data_mask = 0;
+	struct flow_match_enc_opts enc_opts;
+	int res = 0;
+
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+	misc_3_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_3);
+	misc_3_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_3);
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS))
+		return 0;
+
+	flow_rule_match_enc_opts(rule, &enc_opts);
+
+	if (memchr_inv(&enc_opts.mask->data, 0, sizeof(enc_opts.mask->data)) &&
+	    !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+					ft_field_support.geneve_tlv_option_0_data)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on GENEVE options is not supported");
+		netdev_warn(priv->netdev,
+			    "Matching on GENEVE options is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* make sure that we're talking about GENEVE options */
+
+	if (enc_opts.key->dst_opt_type != TUNNEL_GENEVE_OPT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on GENEVE options: option type is not GENEVE");
+		netdev_warn(priv->netdev,
+			    "Matching on GENEVE options: option type is not GENEVE\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (enc_opts.mask->len &&
+	    !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+					ft_field_support.outer_geneve_opt_len)) {
+		NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE options len is not supported");
+		netdev_warn(priv->netdev,
+			    "Matching on GENEVE options len is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* max_geneve_tlv_option_data_len comes in multiples of 4 bytes, and it
+	 * doesn't include the TLV option header. 'geneve_opt_len' is a total
+	 * len of all the options, including the headers, also multiples of 4
+	 * bytes. Len that comes from the dissector is in bytes.
+	 */
+
+	if ((enc_opts.key->len / 4) > ((max_tlv_option_data_len + 1) * max_tlv_options)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on GENEVE options: unsupported options len");
+		netdev_warn(priv->netdev,
+			    "Matching on GENEVE options: unsupported options len (len=%d)\n",
+			    enc_opts.key->len);
+		return -EOPNOTSUPP;
+	}
+
+	MLX5_SET(fte_match_set_misc, misc_c, geneve_opt_len, enc_opts.mask->len / 4);
+	MLX5_SET(fte_match_set_misc, misc_v, geneve_opt_len, enc_opts.key->len / 4);
+
+	/* we support matching on one option only, so just get it */
+	option_key = (struct geneve_opt *)&enc_opts.key->data[0];
+	option_mask = (struct geneve_opt *)&enc_opts.mask->data[0];
+
+	if (option_key->length > max_tlv_option_data_len) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on GENEVE options: unsupported option len");
+		netdev_warn(priv->netdev,
+			    "Matching on GENEVE options: unsupported option len (key=%d, mask=%d)\n",
+			    option_key->length, option_mask->length);
+		return -EOPNOTSUPP;
+	}
+
+	/* data can't be all 0 - fail to offload such rule */
+	if (!memchr_inv(option_key->opt_data, 0, option_key->length * 4)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on GENEVE options: can't match on 0 data field");
+		netdev_warn(priv->netdev,
+			    "Matching on GENEVE options: can't match on 0 data field\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* add new GENEVE TLV options object */
+	res = mlx5_geneve_tlv_option_add(priv->mdev->geneve, option_key);
+	if (res) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on GENEVE options: failed creating TLV opt object");
+		netdev_warn(priv->netdev,
+			    "Matching on GENEVE options: failed creating TLV opt object (class:type:len = 0x%x:0x%x:%d)\n",
+			    be16_to_cpu(option_key->opt_class),
+			    option_key->type, option_key->length);
+		return res;
+	}
+
+	/* In general, after creating the object, need to query it
+	 * in order to check which option data to set in misc3.
+	 * But we support only geneve_tlv_option_0_data, so no
+	 * point querying at this stage.
+	 */
+
+	memcpy(&opt_data_key, option_key->opt_data, option_key->length * 4);
+	memcpy(&opt_data_mask, option_mask->opt_data, option_mask->length * 4);
+	MLX5_SET(fte_match_set_misc3, misc_3_v,
+		 geneve_tlv_option_0_data, be32_to_cpu(opt_data_key));
+	MLX5_SET(fte_match_set_misc3, misc_3_c,
+		 geneve_tlv_option_0_data, be32_to_cpu(opt_data_mask));
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_geneve_params(struct mlx5e_priv *priv,
+					    struct mlx5_flow_spec *spec,
+					    struct flow_cls_offload *f)
+{
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,  misc_parameters);
+	struct netlink_ext_ack *extack = f->common.extack;
+
+	/* match on OAM - packets with OAM bit on should NOT be offloaded */
+
+	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, ft_field_support.outer_geneve_oam)) {
+		NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE OAM is not supported");
+		netdev_warn(priv->netdev, "Matching on GENEVE OAM is not supported\n");
+		return -EOPNOTSUPP;
+	}
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, geneve_oam);
+	MLX5_SET(fte_match_set_misc, misc_v, geneve_oam, 0);
+
+	/* Match on GENEVE protocol. We support only Transparent Eth Bridge. */
+
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+				       ft_field_support.outer_geneve_protocol_type)) {
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, geneve_protocol_type);
+		MLX5_SET(fte_match_set_misc, misc_v, geneve_protocol_type, ETH_P_TEB);
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv,
+				     struct mlx5_flow_spec *spec,
+				     struct flow_cls_offload *f,
+				     void *headers_c,
+				     void *headers_v)
+{
+	int err;
+
+	err = mlx5e_tc_tun_parse_geneve_params(priv, spec, f);
+	if (err)
+		return err;
+
+	err = mlx5e_tc_tun_parse_geneve_vni(priv, spec, f);
+	if (err)
+		return err;
+
+	return mlx5e_tc_tun_parse_geneve_options(priv, spec, f);
+}
+
+struct mlx5e_tc_tunnel geneve_tunnel = {
+	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_GENEVE,
+	.match_level          = MLX5_MATCH_L4,
+	.can_offload          = mlx5e_tc_tun_can_offload_geneve,
+	.calc_hlen            = mlx5e_tc_tun_calc_hlen_geneve,
+	.init_encap_attr      = mlx5e_tc_tun_init_encap_attr_geneve,
+	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_geneve,
+	.parse_udp_ports      = mlx5e_tc_tun_parse_udp_ports_geneve,
+	.parse_tunnel         = mlx5e_tc_tun_parse_geneve,
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
new file mode 100644
index 000000000000..58b13192df23
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/gre.h>
+#include "en/tc_tun.h"
+
+static bool mlx5e_tc_tun_can_offload_gretap(struct mlx5e_priv *priv)
+{
+	return !!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap);
+}
+
+static int mlx5e_tc_tun_calc_hlen_gretap(struct mlx5e_encap_entry *e)
+{
+	return gre_calc_hlen(e->tun_info->key.tun_flags);
+}
+
+static int mlx5e_tc_tun_init_encap_attr_gretap(struct net_device *tunnel_dev,
+					       struct mlx5e_priv *priv,
+					       struct mlx5e_encap_entry *e,
+					       struct netlink_ext_ack *extack)
+{
+	e->tunnel = &gre_tunnel;
+	e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_NVGRE;
+	return 0;
+}
+
+static int mlx5e_gen_ip_tunnel_header_gretap(char buf[],
+					     __u8 *ip_proto,
+					     struct mlx5e_encap_entry *e)
+{
+	const struct ip_tunnel_key *tun_key  = &e->tun_info->key;
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf);
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	int hdr_len;
+
+	*ip_proto = IPPROTO_GRE;
+
+	/* the HW does not calculate GRE csum or sequences */
+	if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ))
+		return -EOPNOTSUPP;
+
+	greh->protocol = htons(ETH_P_TEB);
+
+	/* GRE key */
+	hdr_len	= mlx5e_tc_tun_calc_hlen_gretap(e);
+	greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags);
+	if (tun_key->tun_flags & TUNNEL_KEY) {
+		__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
+		*ptr = tun_id;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv,
+				     struct mlx5_flow_spec *spec,
+				     struct flow_cls_offload *f,
+				     void *headers_c,
+				     void *headers_v)
+{
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_GRE);
+
+	/* gre protocol */
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, gre_protocol);
+	MLX5_SET(fte_match_set_misc, misc_v, gre_protocol, ETH_P_TEB);
+
+	/* gre key */
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid enc_keyid;
+
+		flow_rule_match_enc_keyid(rule, &enc_keyid);
+		MLX5_SET(fte_match_set_misc, misc_c,
+			 gre_key.key, be32_to_cpu(enc_keyid.mask->keyid));
+		MLX5_SET(fte_match_set_misc, misc_v,
+			 gre_key.key, be32_to_cpu(enc_keyid.key->keyid));
+	}
+
+	return 0;
+}
+
+struct mlx5e_tc_tunnel gre_tunnel = {
+	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_GRETAP,
+	.match_level          = MLX5_MATCH_L3,
+	.can_offload          = mlx5e_tc_tun_can_offload_gretap,
+	.calc_hlen            = mlx5e_tc_tun_calc_hlen_gretap,
+	.init_encap_attr      = mlx5e_tc_tun_init_encap_attr_gretap,
+	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_gretap,
+	.parse_udp_ports      = NULL,
+	.parse_tunnel         = mlx5e_tc_tun_parse_gretap,
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
new file mode 100644
index 000000000000..37b176801bcc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/vxlan.h>
+#include "lib/vxlan.h"
+#include "en/tc_tun.h"
+
+static bool mlx5e_tc_tun_can_offload_vxlan(struct mlx5e_priv *priv)
+{
+	return !!MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap);
+}
+
+static int mlx5e_tc_tun_calc_hlen_vxlan(struct mlx5e_encap_entry *e)
+{
+	return VXLAN_HLEN;
+}
+
+static int mlx5e_tc_tun_check_udp_dport_vxlan(struct mlx5e_priv *priv,
+					      struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_match_ports enc_ports;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS))
+		return -EOPNOTSUPP;
+
+	flow_rule_match_enc_ports(rule, &enc_ports);
+
+	/* check the UDP destination port validity */
+
+	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan,
+				    be16_to_cpu(enc_ports.key->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matched UDP dst port is not registered as a VXLAN port");
+		netdev_warn(priv->netdev,
+			    "UDP port %d is not registered as a VXLAN port\n",
+			    be16_to_cpu(enc_ports.key->dst));
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_udp_ports_vxlan(struct mlx5e_priv *priv,
+					      struct mlx5_flow_spec *spec,
+					      struct flow_cls_offload *f,
+					      void *headers_c,
+					      void *headers_v)
+{
+	int err = 0;
+
+	err = mlx5e_tc_tun_parse_udp_ports(priv, spec, f, headers_c, headers_v);
+	if (err)
+		return err;
+
+	return mlx5e_tc_tun_check_udp_dport_vxlan(priv, f);
+}
+
+static int mlx5e_tc_tun_init_encap_attr_vxlan(struct net_device *tunnel_dev,
+					      struct mlx5e_priv *priv,
+					      struct mlx5e_encap_entry *e,
+					      struct netlink_ext_ack *extack)
+{
+	int dst_port = be16_to_cpu(e->tun_info->key.tp_dst);
+
+	e->tunnel = &vxlan_tunnel;
+
+	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "vxlan udp dport was not registered with the HW");
+		netdev_warn(priv->netdev,
+			    "%d isn't an offloaded vxlan udp dport\n",
+			    dst_port);
+		return -EOPNOTSUPP;
+	}
+
+	e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
+	return 0;
+}
+
+static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
+					    __u8 *ip_proto,
+					    struct mlx5e_encap_entry *e)
+{
+	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct vxlanhdr *vxh;
+
+	vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
+	*ip_proto = IPPROTO_UDP;
+
+	udp->dest = tun_key->tp_dst;
+	vxh->vx_flags = VXLAN_HF_VNI;
+	vxh->vx_vni = vxlan_vni_field(tun_id);
+
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
+				    struct mlx5_flow_spec *spec,
+				    struct flow_cls_offload *f,
+				    void *headers_c,
+				    void *headers_v)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct flow_match_enc_keyid enc_keyid;
+	void *misc_c, *misc_v;
+
+	misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID))
+		return 0;
+
+	flow_rule_match_enc_keyid(rule, &enc_keyid);
+
+	if (!enc_keyid.mask->keyid)
+		return 0;
+
+	/* match on VNI is required */
+
+	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+					ft_field_support.outer_vxlan_vni)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matching on VXLAN VNI is not supported");
+		netdev_warn(priv->netdev,
+			    "Matching on VXLAN VNI is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
+		 be32_to_cpu(enc_keyid.mask->keyid));
+	MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
+		 be32_to_cpu(enc_keyid.key->keyid));
+
+	return 0;
+}
+
+struct mlx5e_tc_tunnel vxlan_tunnel = {
+	.tunnel_type          = MLX5E_TC_TUNNEL_TYPE_VXLAN,
+	.match_level          = MLX5_MATCH_L4,
+	.can_offload          = mlx5e_tc_tun_can_offload_vxlan,
+	.calc_hlen            = mlx5e_tc_tun_calc_hlen_vxlan,
+	.init_encap_attr      = mlx5e_tc_tun_init_encap_attr_vxlan,
+	.generate_ip_tun_hdr  = mlx5e_gen_ip_tunnel_header_vxlan,
+	.parse_udp_ports      = mlx5e_tc_tun_parse_udp_ports_vxlan,
+	.parse_tunnel         = mlx5e_tc_tun_parse_vxlan,
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
new file mode 100644
index 000000000000..ddfe19adb3d9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -0,0 +1,208 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_TXRX_H___
+#define __MLX5_EN_TXRX_H___
+
+#include "en.h"
+
+#define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
+#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
+			    MLX5E_SQ_NOPS_ROOM)
+
+#ifndef CONFIG_MLX5_EN_TLS
+#define MLX5E_SQ_TLS_ROOM (0)
+#else
+/* TLS offload requires additional stop_room for:
+ *  - a resync SKB.
+ * kTLS offload requires additional stop_room for:
+ * - static params WQE,
+ * - progress params WQE, and
+ * - resync DUMP per frag.
+ */
+#define MLX5E_SQ_TLS_ROOM  \
+	(MLX5_SEND_WQE_MAX_WQEBBS + \
+	 MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS + \
+	 MAX_SKB_FRAGS * MLX5E_KTLS_MAX_DUMP_WQEBBS)
+#endif
+
+#define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
+
+static inline bool
+mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
+{
+	return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
+}
+
+static inline void *
+mlx5e_sq_fetch_wqe(struct mlx5e_txqsq *sq, size_t size, u16 *pi)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	void *wqe;
+
+	*pi  = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	wqe = mlx5_wq_cyc_get_wqe(wq, *pi);
+	memset(wqe, 0, size);
+
+	return wqe;
+}
+
+static inline struct mlx5e_tx_wqe *
+mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
+{
+	u16                         pi   = mlx5_wq_cyc_ctr2ix(wq, *pc);
+	struct mlx5e_tx_wqe        *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+	struct mlx5_wqe_ctrl_seg   *cseg = &wqe->ctrl;
+
+	memset(cseg, 0, sizeof(*cseg));
+
+	cseg->opmod_idx_opcode = cpu_to_be32((*pc << 8) | MLX5_OPCODE_NOP);
+	cseg->qpn_ds           = cpu_to_be32((sqn << 8) | 0x01);
+
+	(*pc)++;
+
+	return wqe;
+}
+
+static inline struct mlx5e_tx_wqe *
+mlx5e_post_nop_fence(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc)
+{
+	u16                         pi   = mlx5_wq_cyc_ctr2ix(wq, *pc);
+	struct mlx5e_tx_wqe        *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+	struct mlx5_wqe_ctrl_seg   *cseg = &wqe->ctrl;
+
+	memset(cseg, 0, sizeof(*cseg));
+
+	cseg->opmod_idx_opcode = cpu_to_be32((*pc << 8) | MLX5_OPCODE_NOP);
+	cseg->qpn_ds           = cpu_to_be32((sqn << 8) | 0x01);
+	cseg->fm_ce_se         = MLX5_FENCE_MODE_INITIATOR_SMALL;
+
+	(*pc)++;
+
+	return wqe;
+}
+
+static inline void
+mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, struct mlx5_wq_cyc *wq,
+			u16 pi, u16 nnops)
+{
+	struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
+
+	edge_wi = wi + nnops;
+
+	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
+	for (; wi < edge_wi; wi++) {
+		wi->skb        = NULL;
+		wi->num_wqebbs = 1;
+		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+	}
+	sq->stats->nop += nnops;
+}
+
+static inline void
+mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,
+		struct mlx5_wqe_ctrl_seg *ctrl)
+{
+	ctrl->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
+	/* ensure wqe is visible to device before updating doorbell record */
+	dma_wmb();
+
+	*wq->db = cpu_to_be32(pc);
+
+	/* ensure doorbell record is visible to device before ringing the
+	 * doorbell
+	 */
+	wmb();
+
+	mlx5_write64((__be32 *)ctrl, uar_map);
+}
+
+static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe)
+{
+	return !!wqe->ctrl.tisn;
+}
+
+static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
+{
+	struct mlx5_core_cq *mcq;
+
+	mcq = &cq->mcq;
+	mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, cq->wq.cc);
+}
+
+static inline struct mlx5e_sq_dma *
+mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
+{
+	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+}
+
+static inline void
+mlx5e_dma_push(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size,
+	       enum mlx5e_dma_map_type map_type)
+{
+	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
+
+	dma->addr = addr;
+	dma->size = size;
+	dma->type = map_type;
+}
+
+static inline void
+mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
+{
+	switch (dma->type) {
+	case MLX5E_DMA_MAP_SINGLE:
+		dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
+		break;
+	case MLX5E_DMA_MAP_PAGE:
+		dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
+		break;
+	default:
+		WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n");
+	}
+}
+
+/* SW parser related functions */
+
+struct mlx5e_swp_spec {
+	__be16 l3_proto;
+	u8 l4_proto;
+	u8 is_tun;
+	__be16 tun_l3_proto;
+	u8 tun_l4_proto;
+};
+
+static inline void
+mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
+		   struct mlx5e_swp_spec *swp_spec)
+{
+	/* SWP offsets are in 2-bytes words */
+	eseg->swp_outer_l3_offset = skb_network_offset(skb) / 2;
+	if (swp_spec->l3_proto == htons(ETH_P_IPV6))
+		eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L3_IPV6;
+	if (swp_spec->l4_proto) {
+		eseg->swp_outer_l4_offset = skb_transport_offset(skb) / 2;
+		if (swp_spec->l4_proto == IPPROTO_UDP)
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L4_UDP;
+	}
+
+	if (swp_spec->is_tun) {
+		eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
+		if (swp_spec->tun_l3_proto == htons(ETH_P_IPV6))
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
+	} else { /* typically for ipsec when xfrm mode != XFRM_MODE_TUNNEL */
+		eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2;
+		if (swp_spec->l3_proto == htons(ETH_P_IPV6))
+			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
+	}
+	switch (swp_spec->tun_l4_proto) {
+	case IPPROTO_UDP:
+		eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
+		/* fall through */
+	case IPPROTO_TCP:
+		eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
+		break;
+	}
+}
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 3740177eed09..b0b982cf69bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -31,28 +31,95 @@
  */
 
 #include <linux/bpf_trace.h>
+#include <net/xdp_sock.h>
 #include "en/xdp.h"
+#include "en/params.h"
+
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk)
+{
+	int hr = mlx5e_get_linear_rq_headroom(params, xsk);
+
+	/* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
+	 * The condition checked in mlx5e_rx_is_linear_skb is:
+	 *   SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE         (1)
+	 *   (Note that hw_mtu == sw_mtu + hard_mtu.)
+	 * What is returned from this function is:
+	 *   max_mtu = PAGE_SIZE - S - hr - hard_mtu                         (2)
+	 * After assigning sw_mtu := max_mtu, the left side of (1) turns to
+	 * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE,
+	 * because both PAGE_SIZE and S are already aligned. Any number greater
+	 * than max_mtu would make the left side of (1) greater than PAGE_SIZE,
+	 * so max_mtu is the maximum MTU allowed.
+	 */
+
+	return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr));
+}
 
 static inline bool
-mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
-		    struct xdp_buff *xdp)
+mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
+		    struct mlx5e_dma_info *di, struct xdp_buff *xdp)
 {
+	struct mlx5e_xdp_xmit_data xdptxd;
 	struct mlx5e_xdp_info xdpi;
+	struct xdp_frame *xdpf;
+	dma_addr_t dma_addr;
 
-	xdpi.xdpf = convert_to_xdp_frame(xdp);
-	if (unlikely(!xdpi.xdpf))
+	xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpf))
 		return false;
-	xdpi.dma_addr = di->addr + (xdpi.xdpf->data - (void *)xdpi.xdpf);
-	dma_sync_single_for_device(sq->pdev, xdpi.dma_addr,
-				   xdpi.xdpf->len, PCI_DMA_TODEVICE);
-	xdpi.di = *di;
 
-	return sq->xmit_xdp_frame(sq, &xdpi);
+	xdptxd.data = xdpf->data;
+	xdptxd.len  = xdpf->len;
+
+	if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) {
+		/* The xdp_buff was in the UMEM and was copied into a newly
+		 * allocated page. The UMEM page was returned via the ZCA, and
+		 * this new page has to be mapped at this point and has to be
+		 * unmapped and returned via xdp_return_frame on completion.
+		 */
+
+		/* Prevent double recycling of the UMEM page. Even in case this
+		 * function returns false, the xdp_buff shouldn't be recycled,
+		 * as it was already done in xdp_convert_zc_to_xdp_frame.
+		 */
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
+
+		xdpi.mode = MLX5E_XDP_XMIT_MODE_FRAME;
+
+		dma_addr = dma_map_single(sq->pdev, xdptxd.data, xdptxd.len,
+					  DMA_TO_DEVICE);
+		if (dma_mapping_error(sq->pdev, dma_addr)) {
+			xdp_return_frame(xdpf);
+			return false;
+		}
+
+		xdptxd.dma_addr     = dma_addr;
+		xdpi.frame.xdpf     = xdpf;
+		xdpi.frame.dma_addr = dma_addr;
+	} else {
+		/* Driver assumes that convert_to_xdp_frame returns an xdp_frame
+		 * that points to the same memory region as the original
+		 * xdp_buff. It allows to map the memory only once and to use
+		 * the DMA_BIDIRECTIONAL mode.
+		 */
+
+		xdpi.mode = MLX5E_XDP_XMIT_MODE_PAGE;
+
+		dma_addr = di->addr + (xdpf->data - (void *)xdpf);
+		dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len,
+					   DMA_TO_DEVICE);
+
+		xdptxd.dma_addr = dma_addr;
+		xdpi.page.rq    = rq;
+		xdpi.page.di    = *di;
+	}
+
+	return sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0);
 }
 
 /* returns true if packet was consumed by xdp */
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
-		      void *va, u16 *rx_headroom, u32 *len)
+		      void *va, u16 *rx_headroom, u32 *len, bool xsk)
 {
 	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
 	struct xdp_buff xdp;
@@ -66,16 +133,20 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 	xdp_set_data_meta_invalid(&xdp);
 	xdp.data_end = xdp.data + *len;
 	xdp.data_hard_start = va;
+	if (xsk)
+		xdp.handle = di->xsk.handle;
 	xdp.rxq = &rq->xdp_rxq;
 
 	act = bpf_prog_run_xdp(prog, &xdp);
+	if (xsk)
+		xdp.handle += xdp.data - xdp.data_hard_start;
 	switch (act) {
 	case XDP_PASS:
 		*rx_headroom = xdp.data - xdp.data_hard_start;
 		*len = xdp.data_end - xdp.data;
 		return false;
 	case XDP_TX:
-		if (unlikely(!mlx5e_xmit_xdp_buff(&rq->xdpsq, di, &xdp)))
+		if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, di, &xdp)))
 			goto xdp_abort;
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
 		return true;
@@ -85,8 +156,9 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		if (unlikely(err))
 			goto xdp_abort;
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
-		rq->xdpsq.redirect_flush = true;
-		mlx5e_page_dma_unmap(rq, di);
+		__set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags);
+		if (!xsk)
+			mlx5e_page_dma_unmap(rq, di);
 		rq->stats->xdp_redirect++;
 		return true;
 	default:
@@ -105,6 +177,7 @@ xdp_abort:
 static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	u8  wqebbs;
 	u16 pi;
@@ -112,7 +185,9 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 	mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
 
 	prefetchw(session->wqe->data);
-	session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->pkt_count = 0;
+	session->complete  = 0;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
@@ -131,9 +206,13 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 		       MLX5E_XDP_MPW_MAX_WQEBBS);
 
 	session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
+
+	mlx5e_xdp_update_inline_state(sq);
+
+	stats->mpwqe++;
 }
 
-static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
+void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5_wq_cyc       *wq    = &sq->wq;
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
@@ -147,7 +226,7 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
 	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_count);
 
 	wi->num_wqebbs = DIV_ROUND_UP(ds_count, MLX5_SEND_WQEBB_NUM_DS);
-	wi->num_ds     = ds_count - MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	wi->num_pkts   = session->pkt_count;
 
 	sq->pc += wi->num_wqebbs;
 
@@ -156,36 +235,58 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
 	session->wqe = NULL; /* Close session */
 }
 
+enum {
+	MLX5E_XDP_CHECK_OK = 1,
+	MLX5E_XDP_CHECK_START_MPWQE = 2,
+};
+
+static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
+{
+	if (unlikely(!sq->mpwqe.wqe)) {
+		if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
+						     MLX5_SEND_WQE_MAX_WQEBBS))) {
+			/* SQ is full, ring doorbell */
+			mlx5e_xmit_xdp_doorbell(sq);
+			sq->stats->full++;
+			return -EBUSY;
+		}
+
+		return MLX5E_XDP_CHECK_START_MPWQE;
+	}
+
+	return MLX5E_XDP_CHECK_OK;
+}
+
 static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
-				       struct mlx5e_xdp_info *xdpi)
+				       struct mlx5e_xdp_xmit_data *xdptxd,
+				       struct mlx5e_xdp_info *xdpi,
+				       int check_result)
 {
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
-	dma_addr_t dma_addr    = xdpi->dma_addr;
-	struct xdp_frame *xdpf = xdpi->xdpf;
-	unsigned int dma_len   = xdpf->len;
-
-	if (unlikely(sq->hw_mtu < dma_len)) {
+	if (unlikely(xdptxd->len > sq->hw_mtu)) {
 		stats->err++;
 		return false;
 	}
 
-	if (unlikely(!session->wqe)) {
-		if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
-						     MLX5_SEND_WQE_MAX_WQEBBS))) {
-			/* SQ is full, ring doorbell */
-			mlx5e_xmit_xdp_doorbell(sq);
-			stats->full++;
-			return false;
-		}
+	if (!check_result)
+		check_result = mlx5e_xmit_xdp_frame_check_mpwqe(sq);
+	if (unlikely(check_result < 0))
+		return false;
 
+	if (check_result == MLX5E_XDP_CHECK_START_MPWQE) {
+		/* Start the session when nothing can fail, so it's guaranteed
+		 * that if there is an active session, it has at least one dseg,
+		 * and it's safe to complete it at any time.
+		 */
 		mlx5e_xdp_mpwqe_session_start(sq);
 	}
 
-	mlx5e_xdp_mpwqe_add_dseg(sq, dma_addr, dma_len);
+	mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats);
 
-	if (unlikely(session->ds_count == session->max_ds_count))
+	if (unlikely(session->complete ||
+		     session->ds_count == session->max_ds_count))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
@@ -193,7 +294,22 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 	return true;
 }
 
-static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
+static int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
+{
+	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
+		/* SQ is full, ring doorbell */
+		mlx5e_xmit_xdp_doorbell(sq);
+		sq->stats->full++;
+		return -EBUSY;
+	}
+
+	return MLX5E_XDP_CHECK_OK;
+}
+
+static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
+				 struct mlx5e_xdp_xmit_data *xdptxd,
+				 struct mlx5e_xdp_info *xdpi,
+				 int check_result)
 {
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
 	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
@@ -203,9 +319,8 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *
 	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
 	struct mlx5_wqe_data_seg *dseg = wqe->data;
 
-	struct xdp_frame *xdpf = xdpi->xdpf;
-	dma_addr_t dma_addr  = xdpi->dma_addr;
-	unsigned int dma_len = xdpf->len;
+	dma_addr_t dma_addr = xdptxd->dma_addr;
+	u32 dma_len = xdptxd->len;
 
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
@@ -216,18 +331,16 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *
 		return false;
 	}
 
-	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
-		/* SQ is full, ring doorbell */
-		mlx5e_xmit_xdp_doorbell(sq);
-		stats->full++;
+	if (!check_result)
+		check_result = mlx5e_xmit_xdp_frame_check(sq);
+	if (unlikely(check_result < 0))
 		return false;
-	}
 
 	cseg->fm_ce_se = 0;
 
 	/* copy the inline part if required */
 	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE);
+		memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE);
 		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
 		dma_len  -= MLX5E_XDP_MIN_INLINE;
 		dma_addr += MLX5E_XDP_MIN_INLINE;
@@ -249,12 +362,43 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *
 	return true;
 }
 
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
+static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
+				  struct mlx5e_xdp_wqe_info *wi,
+				  u32 *xsk_frames,
+				  bool recycle)
+{
+	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
+	u16 i;
+
+	for (i = 0; i < wi->num_pkts; i++) {
+		struct mlx5e_xdp_info xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
+
+		switch (xdpi.mode) {
+		case MLX5E_XDP_XMIT_MODE_FRAME:
+			/* XDP_TX from the XSK RQ and XDP_REDIRECT */
+			dma_unmap_single(sq->pdev, xdpi.frame.dma_addr,
+					 xdpi.frame.xdpf->len, DMA_TO_DEVICE);
+			xdp_return_frame(xdpi.frame.xdpf);
+			break;
+		case MLX5E_XDP_XMIT_MODE_PAGE:
+			/* XDP_TX from the regular RQ */
+			mlx5e_page_release_dynamic(xdpi.page.rq, &xdpi.page.di, recycle);
+			break;
+		case MLX5E_XDP_XMIT_MODE_XSK:
+			/* AF_XDP send */
+			(*xsk_frames)++;
+			break;
+		default:
+			WARN_ON_ONCE(true);
+		}
+	}
+}
+
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 {
-	struct mlx5e_xdp_info_fifo *xdpi_fifo;
 	struct mlx5e_xdpsq *sq;
 	struct mlx5_cqe64 *cqe;
-	bool is_redirect;
+	u32 xsk_frames = 0;
 	u16 sqcc;
 	int i;
 
@@ -267,9 +411,6 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 	if (!cqe)
 		return false;
 
-	is_redirect = !rq;
-	xdpi_fifo = &sq->db.xdpi_fifo;
-
 	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
 	 * otherwise a cq overrun may occur
 	 */
@@ -291,7 +432,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 
 		do {
 			struct mlx5e_xdp_wqe_info *wi;
-			u16 ci, j;
+			u16 ci;
 
 			last_wqe = (sqcc == wqe_counter);
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
@@ -299,22 +440,13 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 
 			sqcc += wi->num_wqebbs;
 
-			for (j = 0; j < wi->num_ds; j++) {
-				struct mlx5e_xdp_info xdpi =
-					mlx5e_xdpi_fifo_pop(xdpi_fifo);
-
-				if (is_redirect) {
-					xdp_return_frame(xdpi.xdpf);
-					dma_unmap_single(sq->pdev, xdpi.dma_addr,
-							 xdpi.xdpf->len, DMA_TO_DEVICE);
-				} else {
-					/* Recycle RX page */
-					mlx5e_page_release(rq, &xdpi.di, true);
-				}
-			}
+			mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true);
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	if (xsk_frames)
+		xsk_umem_complete_tx(sq->umem, xsk_frames);
+
 	sq->stats->cqes += i;
 
 	mlx5_cqwq_update_db_record(&cq->wq);
@@ -326,34 +458,24 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
 
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 {
-	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
-	bool is_redirect = !rq;
+	u32 xsk_frames = 0;
 
 	while (sq->cc != sq->pc) {
 		struct mlx5e_xdp_wqe_info *wi;
-		u16 ci, i;
+		u16 ci;
 
 		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
 		wi = &sq->db.wqe_info[ci];
 
 		sq->cc += wi->num_wqebbs;
 
-		for (i = 0; i < wi->num_ds; i++) {
-			struct mlx5e_xdp_info xdpi =
-				mlx5e_xdpi_fifo_pop(xdpi_fifo);
-
-			if (is_redirect) {
-				xdp_return_frame(xdpi.xdpf);
-				dma_unmap_single(sq->pdev, xdpi.dma_addr,
-						 xdpi.xdpf->len, DMA_TO_DEVICE);
-			} else {
-				/* Recycle RX page */
-				mlx5e_page_release(rq, &xdpi.di, false);
-			}
-		}
+		mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false);
 	}
+
+	if (xsk_frames)
+		xsk_umem_complete_tx(sq->umem, xsk_frames);
 }
 
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
@@ -365,7 +487,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	int sq_num;
 	int i;
 
-	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+	/* this flag is sufficient, no need to test internal sq state */
+	if (unlikely(!mlx5e_xdp_tx_is_enabled(priv)))
 		return -ENETDOWN;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -378,26 +501,29 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	sq = &priv->channels.c[sq_num]->xdpsq;
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return -ENETDOWN;
-
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
+		struct mlx5e_xdp_xmit_data xdptxd;
 		struct mlx5e_xdp_info xdpi;
 
-		xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len,
-					       DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) {
+		xdptxd.data = xdpf->data;
+		xdptxd.len = xdpf->len;
+		xdptxd.dma_addr = dma_map_single(sq->pdev, xdptxd.data,
+						 xdptxd.len, DMA_TO_DEVICE);
+
+		if (unlikely(dma_mapping_error(sq->pdev, xdptxd.dma_addr))) {
 			xdp_return_frame_rx_napi(xdpf);
 			drops++;
 			continue;
 		}
 
-		xdpi.xdpf = xdpf;
+		xdpi.mode           = MLX5E_XDP_XMIT_MODE_FRAME;
+		xdpi.frame.xdpf     = xdpf;
+		xdpi.frame.dma_addr = xdptxd.dma_addr;
 
-		if (unlikely(!sq->xmit_xdp_frame(sq, &xdpi))) {
-			dma_unmap_single(sq->pdev, xdpi.dma_addr,
-					 xdpf->len, DMA_TO_DEVICE);
+		if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0))) {
+			dma_unmap_single(sq->pdev, xdptxd.dma_addr,
+					 xdptxd.len, DMA_TO_DEVICE);
 			xdp_return_frame_rx_napi(xdpf);
 			drops++;
 		}
@@ -414,21 +540,23 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
 {
-	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
+	struct mlx5e_xdpsq *xdpsq = rq->xdpsq;
 
 	if (xdpsq->mpwqe.wqe)
 		mlx5e_xdp_mpwqe_complete(xdpsq);
 
 	mlx5e_xmit_xdp_doorbell(xdpsq);
 
-	if (xdpsq->redirect_flush) {
+	if (test_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags)) {
 		xdp_do_flush_map();
-		xdpsq->redirect_flush = false;
+		__clear_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags);
 	}
 }
 
 void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw)
 {
+	sq->xmit_xdp_frame_check = is_mpw ?
+		mlx5e_xmit_xdp_frame_check_mpwqe : mlx5e_xmit_xdp_frame_check;
 	sq->xmit_xdp_frame = is_mpw ?
 		mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 3a67cb3cd179..b90923932668 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -33,23 +33,57 @@
 #define __MLX5_EN_XDP_H__
 
 #include "en.h"
+#include "en/txrx.h"
 
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
-				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 #define MLX5E_XDP_TX_EMPTY_DS_COUNT \
 	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
+struct mlx5e_xsk_param;
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
-		      void *va, u16 *rx_headroom, u32 *len);
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq);
+		      void *va, u16 *rx_headroom, u32 *len, bool xsk);
+void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
 void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw);
 void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
+static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv)
+{
+	clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+	/* let other device's napi(s) see our new state */
+	synchronize_rcu();
+}
+
+static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv)
+{
+	return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
+static inline void mlx5e_xdp_set_open(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
+}
+
+static inline void mlx5e_xdp_set_closed(struct mlx5e_priv *priv)
+{
+	clear_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
+}
+
+static inline bool mlx5e_xdp_is_open(struct mlx5e_priv *priv)
+{
+	return test_bit(MLX5E_STATE_XDP_OPEN, &priv->state);
+}
+
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
 	if (sq->doorbell_cseg) {
@@ -58,16 +92,67 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 	}
 }
 
+/* Enable inline WQEs to shift some load from a congested HCA (HW) to
+ * a less congested cpu (SW).
+ */
+static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
+{
+	u16 outstanding = sq->xdpi_fifo_pc - sq->xdpi_fifo_cc;
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+
+#define MLX5E_XDP_INLINE_WATERMARK_LOW	10
+#define MLX5E_XDP_INLINE_WATERMARK_HIGH 128
+
+	if (session->inline_on) {
+		if (outstanding <= MLX5E_XDP_INLINE_WATERMARK_LOW)
+			session->inline_on = 0;
+		return;
+	}
+
+	/* inline is false */
+	if (outstanding >= MLX5E_XDP_INLINE_WATERMARK_HIGH)
+		session->inline_on = 1;
+}
+
 static inline void
-mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, dma_addr_t dma_addr, u16 dma_len)
+mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq,
+			 struct mlx5e_xdp_xmit_data *xdptxd,
+			 struct mlx5e_xdpsq_stats *stats)
 {
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 	struct mlx5_wqe_data_seg *dseg =
-		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count++;
+		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count;
+	u32 dma_len = xdptxd->len;
 
-	dseg->addr       = cpu_to_be64(dma_addr);
+	session->pkt_count++;
+
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
+
+	if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) {
+		struct mlx5_wqe_inline_seg *inline_dseg =
+			(struct mlx5_wqe_inline_seg *)dseg;
+		u16 ds_len = sizeof(*inline_dseg) + dma_len;
+		u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS);
+
+		if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) {
+			/* Not enough space for inline wqe, send with memory pointer */
+			session->complete = true;
+			goto no_inline;
+		}
+
+		inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG);
+		memcpy(inline_dseg->data, xdptxd->data, dma_len);
+
+		session->ds_count += ds_cnt;
+		stats->inlnw++;
+		return;
+	}
+
+no_inline:
+	dseg->addr       = cpu_to_be64(xdptxd->dma_addr);
 	dseg->byte_count = cpu_to_be32(dma_len);
 	dseg->lkey       = sq->mkey_be;
+	session->ds_count++;
 }
 
 static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
@@ -94,5 +179,4 @@ mlx5e_xdpi_fifo_pop(struct mlx5e_xdp_info_fifo *fifo)
 {
 	return fifo->xi[(*fifo->cc)++ & fifo->mask];
 }
-
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile
new file mode 100644
index 000000000000..5ee42991900a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile
@@ -0,0 +1 @@
+subdir-ccflags-y += -I$(src)/../..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
new file mode 100644
index 000000000000..6a55573ec8f2
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "rx.h"
+#include "en/xdp.h"
+#include <net/xdp_sock.h>
+
+/* RX data path */
+
+bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count)
+{
+	/* Check in advance that we have enough frames, instead of allocating
+	 * one-by-one, failing and moving frames to the Reuse Ring.
+	 */
+	return xsk_umem_has_addrs_rq(rq->umem, count);
+}
+
+int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
+			      struct mlx5e_dma_info *dma_info)
+{
+	struct xdp_umem *umem = rq->umem;
+	u64 handle;
+
+	if (!xsk_umem_peek_addr_rq(umem, &handle))
+		return -ENOMEM;
+
+	dma_info->xsk.handle = handle + rq->buff.umem_headroom;
+	dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle);
+
+	/* No need to add headroom to the DMA address. In striding RQ case, we
+	 * just provide pages for UMR, and headroom is counted at the setup
+	 * stage when creating a WQE. In non-striding RQ case, headroom is
+	 * accounted in mlx5e_alloc_rx_wqe.
+	 */
+	dma_info->addr = xdp_umem_get_dma(umem, handle);
+
+	xsk_umem_discard_addr_rq(umem);
+
+	dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE,
+				   DMA_BIDIRECTIONAL);
+
+	return 0;
+}
+
+static inline void mlx5e_xsk_recycle_frame(struct mlx5e_rq *rq, u64 handle)
+{
+	xsk_umem_fq_reuse(rq->umem, handle & rq->umem->chunk_mask);
+}
+
+/* XSKRQ uses pages from UMEM, they must not be released. They are returned to
+ * the userspace if possible, and if not, this function is called to reuse them
+ * in the driver.
+ */
+void mlx5e_xsk_page_release(struct mlx5e_rq *rq,
+			    struct mlx5e_dma_info *dma_info)
+{
+	mlx5e_xsk_recycle_frame(rq, dma_info->xsk.handle);
+}
+
+/* Return a frame back to the hardware to fill in again. It is used by XDP when
+ * the XDP program returns XDP_TX or XDP_REDIRECT not to an XSKMAP.
+ */
+void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle)
+{
+	struct mlx5e_rq *rq = container_of(zca, struct mlx5e_rq, zca);
+
+	mlx5e_xsk_recycle_frame(rq, handle);
+}
+
+static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data,
+					       u32 cqe_bcnt)
+{
+	struct sk_buff *skb;
+
+	skb = napi_alloc_skb(rq->cq.napi, cqe_bcnt);
+	if (unlikely(!skb)) {
+		rq->stats->buff_alloc_err++;
+		return NULL;
+	}
+
+	skb_put_data(skb, data, cqe_bcnt);
+
+	return skb;
+}
+
+struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
+						    struct mlx5e_mpw_info *wi,
+						    u16 cqe_bcnt,
+						    u32 head_offset,
+						    u32 page_idx)
+{
+	struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx];
+	u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
+	u32 cqe_bcnt32 = cqe_bcnt;
+	void *va, *data;
+	u32 frag_size;
+	bool consumed;
+
+	/* Check packet size. Note LRO doesn't use linear SKB */
+	if (unlikely(cqe_bcnt > rq->hw_mtu)) {
+		rq->stats->oversize_pkts_sw_drop++;
+		return NULL;
+	}
+
+	/* head_offset is not used in this function, because di->xsk.data and
+	 * di->addr point directly to the necessary place. Furthermore, in the
+	 * current implementation, one page = one packet = one frame, so
+	 * head_offset should always be 0.
+	 */
+	WARN_ON_ONCE(head_offset);
+
+	va             = di->xsk.data;
+	data           = va + rx_headroom;
+	frag_size      = rq->buff.headroom + cqe_bcnt32;
+
+	dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
+	prefetch(data);
+
+	rcu_read_lock();
+	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, true);
+	rcu_read_unlock();
+
+	/* Possible flows:
+	 * - XDP_REDIRECT to XSKMAP:
+	 *   The page is owned by the userspace from now.
+	 * - XDP_TX and other XDP_REDIRECTs:
+	 *   The page was returned by ZCA and recycled.
+	 * - XDP_DROP:
+	 *   Recycle the page.
+	 * - XDP_PASS:
+	 *   Allocate an SKB, copy the data and recycle the page.
+	 *
+	 * Pages to be recycled go to the Reuse Ring on MPWQE deallocation. Its
+	 * size is the same as the Driver RX Ring's size, and pages for WQEs are
+	 * allocated first from the Reuse Ring, so it has enough space.
+	 */
+
+	if (likely(consumed)) {
+		if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)))
+			__set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */
+		return NULL; /* page/packet was consumed by XDP */
+	}
+
+	/* XDP_PASS: copy the data from the UMEM to a new SKB and reuse the
+	 * frame. On SKB allocation failure, NULL is returned.
+	 */
+	return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt32);
+}
+
+struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
+					      struct mlx5_cqe64 *cqe,
+					      struct mlx5e_wqe_frag_info *wi,
+					      u32 cqe_bcnt)
+{
+	struct mlx5e_dma_info *di = wi->di;
+	u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom;
+	void *va, *data;
+	bool consumed;
+	u32 frag_size;
+
+	/* wi->offset is not used in this function, because di->xsk.data and
+	 * di->addr point directly to the necessary place. Furthermore, in the
+	 * current implementation, one page = one packet = one frame, so
+	 * wi->offset should always be 0.
+	 */
+	WARN_ON_ONCE(wi->offset);
+
+	va             = di->xsk.data;
+	data           = va + rx_headroom;
+	frag_size      = rq->buff.headroom + cqe_bcnt;
+
+	dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL);
+	prefetch(data);
+
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
+		rq->stats->wqe_err++;
+		return NULL;
+	}
+
+	rcu_read_lock();
+	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, true);
+	rcu_read_unlock();
+
+	if (likely(consumed))
+		return NULL; /* page/packet was consumed by XDP */
+
+	/* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse
+	 * will be handled by mlx5e_put_rx_frag.
+	 * On SKB allocation failure, NULL is returned.
+	 */
+	return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
new file mode 100644
index 000000000000..307b923a1361
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_XSK_RX_H__
+#define __MLX5_EN_XSK_RX_H__
+
+#include "en.h"
+
+/* RX data path */
+
+bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count);
+int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq,
+			      struct mlx5e_dma_info *dma_info);
+void mlx5e_xsk_page_release(struct mlx5e_rq *rq,
+			    struct mlx5e_dma_info *dma_info);
+void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle);
+struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq,
+						    struct mlx5e_mpw_info *wi,
+						    u16 cqe_bcnt,
+						    u32 head_offset,
+						    u32 page_idx);
+struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq,
+					      struct mlx5_cqe64 *cqe,
+					      struct mlx5e_wqe_frag_info *wi,
+					      u32 cqe_bcnt);
+
+#endif /* __MLX5_EN_XSK_RX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
new file mode 100644
index 000000000000..aaffa6f68dc0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "setup.h"
+#include "en/params.h"
+
+bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
+			      struct mlx5e_xsk_param *xsk,
+			      struct mlx5_core_dev *mdev)
+{
+	/* AF_XDP doesn't support frames larger than PAGE_SIZE, and the current
+	 * mlx5e XDP implementation doesn't support multiple packets per page.
+	 */
+	if (xsk->chunk_size != PAGE_SIZE)
+		return false;
+
+	/* Current MTU and XSK headroom don't allow packets to fit the frames. */
+	if (mlx5e_rx_get_linear_frag_sz(params, xsk) > xsk->chunk_size)
+		return false;
+
+	/* frag_sz is different for regular and XSK RQs, so ensure that linear
+	 * SKB mode is possible.
+	 */
+	switch (params->rq_wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk);
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		return mlx5e_rx_is_linear_skb(params, xsk);
+	}
+}
+
+static void mlx5e_build_xskicosq_param(struct mlx5e_priv *priv,
+				       u8 log_wq_size,
+				       struct mlx5e_sq_param *param)
+{
+	void *sqc = param->sqc;
+	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+	mlx5e_build_sq_param_common(priv, param);
+
+	MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
+}
+
+static void mlx5e_build_xsk_cparam(struct mlx5e_priv *priv,
+				   struct mlx5e_params *params,
+				   struct mlx5e_xsk_param *xsk,
+				   struct mlx5e_channel_param *cparam)
+{
+	const u8 xskicosq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+
+	mlx5e_build_rq_param(priv, params, xsk, &cparam->rq);
+	mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
+	mlx5e_build_xskicosq_param(priv, xskicosq_size, &cparam->icosq);
+	mlx5e_build_rx_cq_param(priv, params, xsk, &cparam->rx_cq);
+	mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
+	mlx5e_build_ico_cq_param(priv, xskicosq_size, &cparam->icosq_cq);
+}
+
+int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
+		   struct mlx5e_xsk_param *xsk, struct xdp_umem *umem,
+		   struct mlx5e_channel *c)
+{
+	struct mlx5e_channel_param cparam = {};
+	struct dim_cq_moder icocq_moder = {};
+	int err;
+
+	if (!mlx5e_validate_xsk_param(params, xsk, priv->mdev))
+		return -EINVAL;
+
+	mlx5e_build_xsk_cparam(priv, params, xsk, &cparam);
+
+	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam.rx_cq, &c->xskrq.cq);
+	if (unlikely(err))
+		return err;
+
+	err = mlx5e_open_rq(c, params, &cparam.rq, xsk, umem, &c->xskrq);
+	if (unlikely(err))
+		goto err_close_rx_cq;
+
+	err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam.tx_cq, &c->xsksq.cq);
+	if (unlikely(err))
+		goto err_close_rq;
+
+	/* Create a separate SQ, so that when the UMEM is disabled, we could
+	 * close this SQ safely and stop receiving CQEs. In other case, e.g., if
+	 * the XDPSQ was used instead, we might run into trouble when the UMEM
+	 * is disabled and then reenabled, but the SQ continues receiving CQEs
+	 * from the old UMEM.
+	 */
+	err = mlx5e_open_xdpsq(c, params, &cparam.xdp_sq, umem, &c->xsksq, true);
+	if (unlikely(err))
+		goto err_close_tx_cq;
+
+	err = mlx5e_open_cq(c, icocq_moder, &cparam.icosq_cq, &c->xskicosq.cq);
+	if (unlikely(err))
+		goto err_close_sq;
+
+	/* Create a dedicated SQ for posting NOPs whenever we need an IRQ to be
+	 * triggered and NAPI to be called on the correct CPU.
+	 */
+	err = mlx5e_open_icosq(c, params, &cparam.icosq, &c->xskicosq);
+	if (unlikely(err))
+		goto err_close_icocq;
+
+	spin_lock_init(&c->xskicosq_lock);
+
+	set_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
+
+	return 0;
+
+err_close_icocq:
+	mlx5e_close_cq(&c->xskicosq.cq);
+
+err_close_sq:
+	mlx5e_close_xdpsq(&c->xsksq);
+
+err_close_tx_cq:
+	mlx5e_close_cq(&c->xsksq.cq);
+
+err_close_rq:
+	mlx5e_close_rq(&c->xskrq);
+
+err_close_rx_cq:
+	mlx5e_close_cq(&c->xskrq.cq);
+
+	return err;
+}
+
+void mlx5e_close_xsk(struct mlx5e_channel *c)
+{
+	clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
+	napi_synchronize(&c->napi);
+
+	mlx5e_close_rq(&c->xskrq);
+	mlx5e_close_cq(&c->xskrq.cq);
+	mlx5e_close_icosq(&c->xskicosq);
+	mlx5e_close_cq(&c->xskicosq.cq);
+	mlx5e_close_xdpsq(&c->xsksq);
+	mlx5e_close_cq(&c->xsksq.cq);
+}
+
+void mlx5e_activate_xsk(struct mlx5e_channel *c)
+{
+	set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
+	/* TX queue is created active. */
+	mlx5e_trigger_irq(&c->xskicosq);
+}
+
+void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
+{
+	mlx5e_deactivate_rq(&c->xskrq);
+	/* TX queue is disabled on close. */
+}
+
+static int mlx5e_redirect_xsk_rqt(struct mlx5e_priv *priv, u16 ix, u32 rqn)
+{
+	struct mlx5e_redirect_rqt_param direct_rrp = {
+		.is_rss = false,
+		{
+			.rqn = rqn,
+		},
+	};
+
+	u32 rqtn = priv->xsk_tir[ix].rqt.rqtn;
+
+	return mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp);
+}
+
+int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c)
+{
+	return mlx5e_redirect_xsk_rqt(priv, c->ix, c->xskrq.rqn);
+}
+
+int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix)
+{
+	return mlx5e_redirect_xsk_rqt(priv, ix, priv->drop_rq.rqn);
+}
+
+int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs)
+{
+	int err, i;
+
+	if (!priv->xsk.refcnt)
+		return 0;
+
+	for (i = 0; i < chs->num; i++) {
+		struct mlx5e_channel *c = chs->c[i];
+
+		if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+			continue;
+
+		err = mlx5e_xsk_redirect_rqt_to_channel(priv, c);
+		if (unlikely(err))
+			goto err_stop;
+	}
+
+	return 0;
+
+err_stop:
+	for (i--; i >= 0; i--) {
+		if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state))
+			continue;
+
+		mlx5e_xsk_redirect_rqt_to_drop(priv, i);
+	}
+
+	return err;
+}
+
+void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs)
+{
+	int i;
+
+	if (!priv->xsk.refcnt)
+		return;
+
+	for (i = 0; i < chs->num; i++) {
+		if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state))
+			continue;
+
+		mlx5e_xsk_redirect_rqt_to_drop(priv, i);
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
new file mode 100644
index 000000000000..0dd11b81c046
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_XSK_SETUP_H__
+#define __MLX5_EN_XSK_SETUP_H__
+
+#include "en.h"
+
+struct mlx5e_xsk_param;
+
+bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
+			      struct mlx5e_xsk_param *xsk,
+			      struct mlx5_core_dev *mdev);
+int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
+		   struct mlx5e_xsk_param *xsk, struct xdp_umem *umem,
+		   struct mlx5e_channel *c);
+void mlx5e_close_xsk(struct mlx5e_channel *c);
+void mlx5e_activate_xsk(struct mlx5e_channel *c);
+void mlx5e_deactivate_xsk(struct mlx5e_channel *c);
+int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c);
+int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix);
+int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs);
+void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs);
+
+#endif /* __MLX5_EN_XSK_SETUP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
new file mode 100644
index 000000000000..35e188cf4ea4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "tx.h"
+#include "umem.h"
+#include "en/xdp.h"
+#include "en/params.h"
+#include <net/xdp_sock.h>
+
+int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_params *params = &priv->channels.params;
+	struct mlx5e_channel *c;
+	u16 ix;
+
+	if (unlikely(!mlx5e_xdp_is_open(priv)))
+		return -ENETDOWN;
+
+	if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
+		return -EINVAL;
+
+	c = priv->channels.c[ix];
+
+	if (unlikely(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)))
+		return -ENXIO;
+
+	if (!napi_if_scheduled_mark_missed(&c->napi)) {
+		spin_lock(&c->xskicosq_lock);
+		mlx5e_trigger_irq(&c->xskicosq);
+		spin_unlock(&c->xskicosq_lock);
+	}
+
+	return 0;
+}
+
+/* When TX fails (because of the size of the packet), we need to get completions
+ * in order, so post a NOP to get a CQE. Since AF_XDP doesn't distinguish
+ * between successful TX and errors, handling in mlx5e_poll_xdpsq_cq is the
+ * same.
+ */
+static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq,
+				  struct mlx5e_xdp_info *xdpi)
+{
+	u16 pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc);
+	struct mlx5e_xdp_wqe_info *wi = &sq->db.wqe_info[pi];
+	struct mlx5e_tx_wqe *nopwqe;
+
+	wi->num_wqebbs = 1;
+	wi->num_pkts = 1;
+
+	nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc);
+	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
+	sq->doorbell_cseg = &nopwqe->ctrl;
+}
+
+bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
+{
+	struct xdp_umem *umem = sq->umem;
+	struct mlx5e_xdp_info xdpi;
+	struct mlx5e_xdp_xmit_data xdptxd;
+	bool work_done = true;
+	bool flush = false;
+
+	xdpi.mode = MLX5E_XDP_XMIT_MODE_XSK;
+
+	for (; budget; budget--) {
+		int check_result = sq->xmit_xdp_frame_check(sq);
+		struct xdp_desc desc;
+
+		if (unlikely(check_result < 0)) {
+			work_done = false;
+			break;
+		}
+
+		if (!xsk_umem_consume_tx(umem, &desc)) {
+			/* TX will get stuck until something wakes it up by
+			 * triggering NAPI. Currently it's expected that the
+			 * application calls sendto() if there are consumed, but
+			 * not completed frames.
+			 */
+			break;
+		}
+
+		xdptxd.dma_addr = xdp_umem_get_dma(umem, desc.addr);
+		xdptxd.data = xdp_umem_get_data(umem, desc.addr);
+		xdptxd.len = desc.len;
+
+		dma_sync_single_for_device(sq->pdev, xdptxd.dma_addr,
+					   xdptxd.len, DMA_BIDIRECTIONAL);
+
+		if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, check_result))) {
+			if (sq->mpwqe.wqe)
+				mlx5e_xdp_mpwqe_complete(sq);
+
+			mlx5e_xsk_tx_post_err(sq, &xdpi);
+		}
+
+		flush = true;
+	}
+
+	if (flush) {
+		if (sq->mpwqe.wqe)
+			mlx5e_xdp_mpwqe_complete(sq);
+		mlx5e_xmit_xdp_doorbell(sq);
+
+		xsk_umem_consume_tx_done(umem);
+	}
+
+	return !(budget && work_done);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
new file mode 100644
index 000000000000..7add18bf78d8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_XSK_TX_H__
+#define __MLX5_EN_XSK_TX_H__
+
+#include "en.h"
+
+/* TX data path */
+
+int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid);
+
+bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget);
+
+#endif /* __MLX5_EN_XSK_TX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
new file mode 100644
index 000000000000..4baaa5788320
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c
@@ -0,0 +1,267 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <net/xdp_sock.h>
+#include "umem.h"
+#include "setup.h"
+#include "en/params.h"
+
+static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv,
+			      struct xdp_umem *umem)
+{
+	struct device *dev = priv->mdev->device;
+	u32 i;
+
+	for (i = 0; i < umem->npgs; i++) {
+		dma_addr_t dma = dma_map_page(dev, umem->pgs[i], 0, PAGE_SIZE,
+					      DMA_BIDIRECTIONAL);
+
+		if (unlikely(dma_mapping_error(dev, dma)))
+			goto err_unmap;
+		umem->pages[i].dma = dma;
+	}
+
+	return 0;
+
+err_unmap:
+	while (i--) {
+		dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
+		umem->pages[i].dma = 0;
+	}
+
+	return -ENOMEM;
+}
+
+static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv,
+				 struct xdp_umem *umem)
+{
+	struct device *dev = priv->mdev->device;
+	u32 i;
+
+	for (i = 0; i < umem->npgs; i++) {
+		dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
+		umem->pages[i].dma = 0;
+	}
+}
+
+static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk)
+{
+	if (!xsk->umems) {
+		xsk->umems = kcalloc(MLX5E_MAX_NUM_CHANNELS,
+				     sizeof(*xsk->umems), GFP_KERNEL);
+		if (unlikely(!xsk->umems))
+			return -ENOMEM;
+	}
+
+	xsk->refcnt++;
+	xsk->ever_used = true;
+
+	return 0;
+}
+
+static void mlx5e_xsk_put_umems(struct mlx5e_xsk *xsk)
+{
+	if (!--xsk->refcnt) {
+		kfree(xsk->umems);
+		xsk->umems = NULL;
+	}
+}
+
+static int mlx5e_xsk_add_umem(struct mlx5e_xsk *xsk, struct xdp_umem *umem, u16 ix)
+{
+	int err;
+
+	err = mlx5e_xsk_get_umems(xsk);
+	if (unlikely(err))
+		return err;
+
+	xsk->umems[ix] = umem;
+	return 0;
+}
+
+static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix)
+{
+	xsk->umems[ix] = NULL;
+
+	mlx5e_xsk_put_umems(xsk);
+}
+
+static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem)
+{
+	return umem->headroom <= 0xffff && umem->chunk_size_nohr <= 0xffff;
+}
+
+void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk)
+{
+	xsk->headroom = umem->headroom;
+	xsk->chunk_size = umem->chunk_size_nohr + umem->headroom;
+}
+
+static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
+				   struct xdp_umem *umem, u16 ix)
+{
+	struct mlx5e_params *params = &priv->channels.params;
+	struct mlx5e_xsk_param xsk;
+	struct mlx5e_channel *c;
+	int err;
+
+	if (unlikely(mlx5e_xsk_get_umem(&priv->channels.params, &priv->xsk, ix)))
+		return -EBUSY;
+
+	if (unlikely(!mlx5e_xsk_is_umem_sane(umem)))
+		return -EINVAL;
+
+	err = mlx5e_xsk_map_umem(priv, umem);
+	if (unlikely(err))
+		return err;
+
+	err = mlx5e_xsk_add_umem(&priv->xsk, umem, ix);
+	if (unlikely(err))
+		goto err_unmap_umem;
+
+	mlx5e_build_xsk_param(umem, &xsk);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		/* XSK objects will be created on open. */
+		goto validate_closed;
+	}
+
+	if (!params->xdp_prog) {
+		/* XSK objects will be created when an XDP program is set,
+		 * and the channels are reopened.
+		 */
+		goto validate_closed;
+	}
+
+	c = priv->channels.c[ix];
+
+	err = mlx5e_open_xsk(priv, params, &xsk, umem, c);
+	if (unlikely(err))
+		goto err_remove_umem;
+
+	mlx5e_activate_xsk(c);
+
+	/* Don't wait for WQEs, because the newer xdpsock sample doesn't provide
+	 * any Fill Ring entries at the setup stage.
+	 */
+
+	err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]);
+	if (unlikely(err))
+		goto err_deactivate;
+
+	return 0;
+
+err_deactivate:
+	mlx5e_deactivate_xsk(c);
+	mlx5e_close_xsk(c);
+
+err_remove_umem:
+	mlx5e_xsk_remove_umem(&priv->xsk, ix);
+
+err_unmap_umem:
+	mlx5e_xsk_unmap_umem(priv, umem);
+
+	return err;
+
+validate_closed:
+	/* Check the configuration in advance, rather than fail at a later stage
+	 * (in mlx5e_xdp_set or on open) and end up with no channels.
+	 */
+	if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) {
+		err = -EINVAL;
+		goto err_remove_umem;
+	}
+
+	return 0;
+}
+
+static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
+{
+	struct xdp_umem *umem = mlx5e_xsk_get_umem(&priv->channels.params,
+						   &priv->xsk, ix);
+	struct mlx5e_channel *c;
+
+	if (unlikely(!umem))
+		return -EINVAL;
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto remove_umem;
+
+	/* XSK RQ and SQ are only created if XDP program is set. */
+	if (!priv->channels.params.xdp_prog)
+		goto remove_umem;
+
+	c = priv->channels.c[ix];
+	mlx5e_xsk_redirect_rqt_to_drop(priv, ix);
+	mlx5e_deactivate_xsk(c);
+	mlx5e_close_xsk(c);
+
+remove_umem:
+	mlx5e_xsk_remove_umem(&priv->xsk, ix);
+	mlx5e_xsk_unmap_umem(priv, umem);
+
+	return 0;
+}
+
+static int mlx5e_xsk_enable_umem(struct mlx5e_priv *priv, struct xdp_umem *umem,
+				 u16 ix)
+{
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_xsk_enable_locked(priv, umem, ix);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+static int mlx5e_xsk_disable_umem(struct mlx5e_priv *priv, u16 ix)
+{
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_xsk_disable_locked(priv, ix);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_params *params = &priv->channels.params;
+	u16 ix;
+
+	if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix)))
+		return -EINVAL;
+
+	return umem ? mlx5e_xsk_enable_umem(priv, umem, ix) :
+		      mlx5e_xsk_disable_umem(priv, ix);
+}
+
+int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries)
+{
+	struct xdp_umem_fq_reuse *reuseq;
+
+	reuseq = xsk_reuseq_prepare(nentries);
+	if (unlikely(!reuseq))
+		return -ENOMEM;
+	xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq));
+
+	return 0;
+}
+
+u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk)
+{
+	u16 res = xsk->refcnt ? params->num_channels : 0;
+
+	while (res) {
+		if (mlx5e_xsk_get_umem(params, xsk, res - 1))
+			break;
+		--res;
+	}
+
+	return res;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h
new file mode 100644
index 000000000000..25b4cbe58b54
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_XSK_UMEM_H__
+#define __MLX5_EN_XSK_UMEM_H__
+
+#include "en.h"
+
+static inline struct xdp_umem *mlx5e_xsk_get_umem(struct mlx5e_params *params,
+						  struct mlx5e_xsk *xsk, u16 ix)
+{
+	if (!xsk || !xsk->umems)
+		return NULL;
+
+	if (unlikely(ix >= params->num_channels))
+		return NULL;
+
+	return xsk->umems[ix];
+}
+
+struct mlx5e_xsk_param;
+void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk);
+
+/* .ndo_bpf callback. */
+int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid);
+
+int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries);
+
+u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk);
+
+#endif /* __MLX5_EN_XSK_UMEM_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/Makefile
index d8e17110f25d..c78512eed8d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 1dd225380a66..3022463f2284 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -39,6 +39,58 @@
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
 #include "en.h"
+#include "en/txrx.h"
+
+#if IS_ENABLED(CONFIG_GENEVE)
+static inline bool mlx5_geneve_tx_allowed(struct mlx5_core_dev *mdev)
+{
+	return mlx5_tx_swp_supported(mdev);
+}
+
+static inline void
+mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+{
+	struct mlx5e_swp_spec swp_spec = {};
+	unsigned int offset = 0;
+	__be16 l3_proto;
+	u8 l4_proto;
+
+	l3_proto = vlan_get_protocol(skb);
+	switch (l3_proto) {
+	case htons(ETH_P_IP):
+		l4_proto = ip_hdr(skb)->protocol;
+		break;
+	case htons(ETH_P_IPV6):
+		l4_proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL);
+		break;
+	default:
+		return;
+	}
+
+	if (l4_proto != IPPROTO_UDP ||
+	    udp_hdr(skb)->dest != cpu_to_be16(GENEVE_UDP_PORT))
+		return;
+	swp_spec.l3_proto = l3_proto;
+	swp_spec.l4_proto = l4_proto;
+	swp_spec.is_tun = true;
+	if (inner_ip_hdr(skb)->version == 6) {
+		swp_spec.tun_l3_proto = htons(ETH_P_IPV6);
+		swp_spec.tun_l4_proto = inner_ipv6_hdr(skb)->nexthdr;
+	} else {
+		swp_spec.tun_l3_proto = htons(ETH_P_IP);
+		swp_spec.tun_l4_proto = inner_ip_hdr(skb)->protocol;
+	}
+
+	mlx5e_set_eseg_swp(skb, eseg, &swp_spec);
+}
+
+#else
+static inline bool mlx5_geneve_tx_allowed(struct mlx5_core_dev *mdev)
+{
+	return false;
+}
+
+#endif /* CONFIG_GENEVE */
 
 static inline void
 mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 53608afd39b6..0dd17514caae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -136,7 +136,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 				struct mlx5_wqe_eth_seg *eseg, u8 mode,
 				struct xfrm_offload *xo)
 {
-	u8 proto;
+	struct mlx5e_swp_spec swp_spec = {};
 
 	/* Tunnel Mode:
 	 * SWP:      OutL3       InL3  InL4
@@ -146,35 +146,23 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 	 * SWP:      OutL3       InL4
 	 *           InL3
 	 * Pkt: MAC  IP     ESP  L4
-	 *
-	 * Offsets are in 2-byte words, counting from start of frame
 	 */
-	eseg->swp_outer_l3_offset = skb_network_offset(skb) / 2;
-	if (skb->protocol == htons(ETH_P_IPV6))
-		eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L3_IPV6;
-
-	if (mode == XFRM_MODE_TUNNEL) {
-		eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
+	swp_spec.l3_proto = skb->protocol;
+	swp_spec.is_tun = mode == XFRM_MODE_TUNNEL;
+	if (swp_spec.is_tun) {
 		if (xo->proto == IPPROTO_IPV6) {
-			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
-			proto = inner_ipv6_hdr(skb)->nexthdr;
+			swp_spec.tun_l3_proto = htons(ETH_P_IPV6);
+			swp_spec.tun_l4_proto = inner_ipv6_hdr(skb)->nexthdr;
 		} else {
-			proto = inner_ip_hdr(skb)->protocol;
+			swp_spec.tun_l3_proto = htons(ETH_P_IP);
+			swp_spec.tun_l4_proto = inner_ip_hdr(skb)->protocol;
 		}
 	} else {
-		eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2;
-		if (skb->protocol == htons(ETH_P_IPV6))
-			eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
-		proto = xo->proto;
-	}
-	switch (proto) {
-	case IPPROTO_UDP:
-		eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
-		/* Fall through */
-	case IPPROTO_TCP:
-		eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
-		break;
+		swp_spec.tun_l3_proto = skb->protocol;
+		swp_spec.tun_l4_proto = xo->proto;
 	}
+
+	mlx5e_set_eseg_swp(skb, eseg, &swp_spec);
 }
 
 void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index ca47c0540904..db84500b024f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -39,6 +39,7 @@
 #include <linux/skbuff.h>
 #include <net/xfrm.h>
 #include "en.h"
+#include "en/txrx.h"
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 					  struct sk_buff *skb, u32 *cqe_bcnt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
new file mode 100644
index 000000000000..d2ff74d52720
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include "en.h"
+#include "en_accel/ktls.h"
+
+static int mlx5e_ktls_create_tis(struct mlx5_core_dev *mdev, u32 *tisn)
+{
+	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+	void *tisc;
+
+	tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+	MLX5_SET(tisc, tisc, tls_en, 1);
+
+	return mlx5e_create_tis(mdev, in, tisn);
+}
+
+static int mlx5e_ktls_add(struct net_device *netdev, struct sock *sk,
+			  enum tls_offload_ctx_dir direction,
+			  struct tls_crypto_info *crypto_info,
+			  u32 start_offload_tcp_sn)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_ktls_offload_context_tx *tx_priv;
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int err;
+
+	if (WARN_ON(direction != TLS_OFFLOAD_CTX_DIR_TX))
+		return -EINVAL;
+
+	if (WARN_ON(!mlx5e_ktls_type_check(mdev, crypto_info)))
+		return -EOPNOTSUPP;
+
+	tx_priv = kvzalloc(sizeof(*tx_priv), GFP_KERNEL);
+	if (!tx_priv)
+		return -ENOMEM;
+
+	tx_priv->expected_seq = start_offload_tcp_sn;
+	tx_priv->crypto_info  = crypto_info;
+	mlx5e_set_ktls_tx_priv_ctx(tls_ctx, tx_priv);
+
+	/* tc and underlay_qpn values are not in use for tls tis */
+	err = mlx5e_ktls_create_tis(mdev, &tx_priv->tisn);
+	if (err)
+		goto create_tis_fail;
+
+	err = mlx5_ktls_create_key(mdev, crypto_info, &tx_priv->key_id);
+	if (err)
+		goto encryption_key_create_fail;
+
+	mlx5e_ktls_tx_offload_set_pending(tx_priv);
+
+	return 0;
+
+encryption_key_create_fail:
+	mlx5e_destroy_tis(priv->mdev, tx_priv->tisn);
+create_tis_fail:
+	kvfree(tx_priv);
+	return err;
+}
+
+static void mlx5e_ktls_del(struct net_device *netdev,
+			   struct tls_context *tls_ctx,
+			   enum tls_offload_ctx_dir direction)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_ktls_offload_context_tx *tx_priv =
+		mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
+
+	mlx5_ktls_destroy_key(priv->mdev, tx_priv->key_id);
+	mlx5e_destroy_tis(priv->mdev, tx_priv->tisn);
+	kvfree(tx_priv);
+}
+
+static const struct tlsdev_ops mlx5e_ktls_ops = {
+	.tls_dev_add = mlx5e_ktls_add,
+	.tls_dev_del = mlx5e_ktls_del,
+};
+
+void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+
+	if (!mlx5_accel_is_ktls_device(priv->mdev))
+		return;
+
+	netdev->hw_features |= NETIF_F_HW_TLS_TX;
+	netdev->features    |= NETIF_F_HW_TLS_TX;
+
+	netdev->tlsdev_ops = &mlx5e_ktls_ops;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
new file mode 100644
index 000000000000..407da83474ef
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5E_KTLS_H__
+#define __MLX5E_KTLS_H__
+
+#include "en.h"
+
+#ifdef CONFIG_MLX5_EN_TLS
+#include <net/tls.h>
+#include "accel/tls.h"
+
+#define MLX5E_KTLS_STATIC_UMR_WQE_SZ \
+	(sizeof(struct mlx5e_umr_wqe) + MLX5_ST_SZ_BYTES(tls_static_params))
+#define MLX5E_KTLS_STATIC_WQEBBS \
+	(DIV_ROUND_UP(MLX5E_KTLS_STATIC_UMR_WQE_SZ, MLX5_SEND_WQE_BB))
+
+#define MLX5E_KTLS_PROGRESS_WQE_SZ \
+	(sizeof(struct mlx5e_tx_wqe) + MLX5_ST_SZ_BYTES(tls_progress_params))
+#define MLX5E_KTLS_PROGRESS_WQEBBS \
+	(DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_BB))
+#define MLX5E_KTLS_MAX_DUMP_WQEBBS 2
+
+enum {
+	MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD     = 0,
+	MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_OFFLOAD        = 1,
+	MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_AUTHENTICATION = 2,
+};
+
+enum {
+	MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_START     = 0,
+	MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_SEARCHING = 1,
+	MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_TRACKING  = 2,
+};
+
+struct mlx5e_ktls_offload_context_tx {
+	struct tls_offload_context_tx *tx_ctx;
+	struct tls_crypto_info *crypto_info;
+	u32 expected_seq;
+	u32 tisn;
+	u32 key_id;
+	bool ctx_post_pending;
+};
+
+struct mlx5e_ktls_offload_context_tx_shadow {
+	struct tls_offload_context_tx         tx_ctx;
+	struct mlx5e_ktls_offload_context_tx *priv_tx;
+};
+
+static inline void
+mlx5e_set_ktls_tx_priv_ctx(struct tls_context *tls_ctx,
+			   struct mlx5e_ktls_offload_context_tx *priv_tx)
+{
+	struct tls_offload_context_tx *tx_ctx = tls_offload_ctx_tx(tls_ctx);
+	struct mlx5e_ktls_offload_context_tx_shadow *shadow;
+
+	BUILD_BUG_ON(sizeof(*shadow) > TLS_OFFLOAD_CONTEXT_SIZE_TX);
+
+	shadow = (struct mlx5e_ktls_offload_context_tx_shadow *)tx_ctx;
+
+	shadow->priv_tx = priv_tx;
+	priv_tx->tx_ctx = tx_ctx;
+}
+
+static inline struct mlx5e_ktls_offload_context_tx *
+mlx5e_get_ktls_tx_priv_ctx(struct tls_context *tls_ctx)
+{
+	struct tls_offload_context_tx *tx_ctx = tls_offload_ctx_tx(tls_ctx);
+	struct mlx5e_ktls_offload_context_tx_shadow *shadow;
+
+	BUILD_BUG_ON(sizeof(*shadow) > TLS_OFFLOAD_CONTEXT_SIZE_TX);
+
+	shadow = (struct mlx5e_ktls_offload_context_tx_shadow *)tx_ctx;
+
+	return shadow->priv_tx;
+}
+
+void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv);
+void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx);
+
+struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
+					 struct mlx5e_txqsq *sq,
+					 struct sk_buff *skb,
+					 struct mlx5e_tx_wqe **wqe, u16 *pi);
+void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
+					   struct mlx5e_tx_wqe_info *wi,
+					   struct mlx5e_sq_dma *dma);
+
+#else
+
+static inline void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv)
+{
+}
+
+#endif
+
+#endif /* __MLX5E_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
new file mode 100644
index 000000000000..ea032f54197e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -0,0 +1,448 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include <linux/tls.h>
+#include "en.h"
+#include "en/txrx.h"
+#include "en_accel/ktls.h"
+
+enum {
+	MLX5E_STATIC_PARAMS_CONTEXT_TLS_1_2 = 0x2,
+};
+
+enum {
+	MLX5E_ENCRYPTION_STANDARD_TLS = 0x1,
+};
+
+#define EXTRACT_INFO_FIELDS do { \
+	salt    = info->salt;    \
+	rec_seq = info->rec_seq; \
+	salt_sz    = sizeof(info->salt);    \
+	rec_seq_sz = sizeof(info->rec_seq); \
+} while (0)
+
+static void
+fill_static_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx)
+{
+	struct tls_crypto_info *crypto_info = priv_tx->crypto_info;
+	struct tls12_crypto_info_aes_gcm_128 *info;
+	char *initial_rn, *gcm_iv;
+	u16 salt_sz, rec_seq_sz;
+	char *salt, *rec_seq;
+	u8 tls_version;
+
+	if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128))
+		return;
+
+	info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
+	EXTRACT_INFO_FIELDS;
+
+	gcm_iv      = MLX5_ADDR_OF(tls_static_params, ctx, gcm_iv);
+	initial_rn  = MLX5_ADDR_OF(tls_static_params, ctx, initial_record_number);
+
+	memcpy(gcm_iv,      salt,    salt_sz);
+	memcpy(initial_rn,  rec_seq, rec_seq_sz);
+
+	tls_version = MLX5E_STATIC_PARAMS_CONTEXT_TLS_1_2;
+
+	MLX5_SET(tls_static_params, ctx, tls_version, tls_version);
+	MLX5_SET(tls_static_params, ctx, const_1, 1);
+	MLX5_SET(tls_static_params, ctx, const_2, 2);
+	MLX5_SET(tls_static_params, ctx, encryption_standard,
+		 MLX5E_ENCRYPTION_STANDARD_TLS);
+	MLX5_SET(tls_static_params, ctx, dek_index, priv_tx->key_id);
+}
+
+static void
+build_static_params(struct mlx5e_umr_wqe *wqe, u16 pc, u32 sqn,
+		    struct mlx5e_ktls_offload_context_tx *priv_tx,
+		    bool fence)
+{
+	struct mlx5_wqe_ctrl_seg     *cseg  = &wqe->ctrl;
+	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
+
+#define STATIC_PARAMS_DS_CNT \
+	DIV_ROUND_UP(MLX5E_KTLS_STATIC_UMR_WQE_SZ, MLX5_SEND_WQE_DS)
+
+	cseg->opmod_idx_opcode = cpu_to_be32((pc << 8) | MLX5_OPCODE_UMR |
+					     (MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS << 24));
+	cseg->qpn_ds           = cpu_to_be32((sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
+					     STATIC_PARAMS_DS_CNT);
+	cseg->fm_ce_se         = fence ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
+	cseg->imm              = cpu_to_be32(priv_tx->tisn);
+
+	ucseg->flags = MLX5_UMR_INLINE;
+	ucseg->bsf_octowords = cpu_to_be16(MLX5_ST_SZ_BYTES(tls_static_params) / 16);
+
+	fill_static_params_ctx(wqe->tls_static_params_ctx, priv_tx);
+}
+
+static void
+fill_progress_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx)
+{
+	MLX5_SET(tls_progress_params, ctx, pd, priv_tx->tisn);
+	MLX5_SET(tls_progress_params, ctx, record_tracker_state,
+		 MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_START);
+	MLX5_SET(tls_progress_params, ctx, auth_state,
+		 MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD);
+}
+
+static void
+build_progress_params(struct mlx5e_tx_wqe *wqe, u16 pc, u32 sqn,
+		      struct mlx5e_ktls_offload_context_tx *priv_tx,
+		      bool fence)
+{
+	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+
+#define PROGRESS_PARAMS_DS_CNT \
+	DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_DS)
+
+	cseg->opmod_idx_opcode =
+		cpu_to_be32((pc << 8) | MLX5_OPCODE_SET_PSV |
+			    (MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS << 24));
+	cseg->qpn_ds           = cpu_to_be32((sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
+					     PROGRESS_PARAMS_DS_CNT);
+	cseg->fm_ce_se         = fence ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
+
+	fill_progress_params_ctx(wqe->data, priv_tx);
+}
+
+static void tx_fill_wi(struct mlx5e_txqsq *sq,
+		       u16 pi, u8 num_wqebbs,
+		       skb_frag_t *resync_dump_frag)
+{
+	struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi];
+
+	wi->skb              = NULL;
+	wi->num_wqebbs       = num_wqebbs;
+	wi->resync_dump_frag = resync_dump_frag;
+}
+
+void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx)
+{
+	priv_tx->ctx_post_pending = true;
+}
+
+static bool
+mlx5e_ktls_tx_offload_test_and_clear_pending(struct mlx5e_ktls_offload_context_tx *priv_tx)
+{
+	bool ret = priv_tx->ctx_post_pending;
+
+	priv_tx->ctx_post_pending = false;
+
+	return ret;
+}
+
+static void
+post_static_params(struct mlx5e_txqsq *sq,
+		   struct mlx5e_ktls_offload_context_tx *priv_tx,
+		   bool fence)
+{
+	struct mlx5e_umr_wqe *umr_wqe;
+	u16 pi;
+
+	umr_wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_STATIC_UMR_WQE_SZ, &pi);
+	build_static_params(umr_wqe, sq->pc, sq->sqn, priv_tx, fence);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, NULL);
+	sq->pc += MLX5E_KTLS_STATIC_WQEBBS;
+}
+
+static void
+post_progress_params(struct mlx5e_txqsq *sq,
+		     struct mlx5e_ktls_offload_context_tx *priv_tx,
+		     bool fence)
+{
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi;
+
+	wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_PROGRESS_WQE_SZ, &pi);
+	build_progress_params(wqe, sq->pc, sq->sqn, priv_tx, fence);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, NULL);
+	sq->pc += MLX5E_KTLS_PROGRESS_WQEBBS;
+}
+
+static void
+mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
+			      struct mlx5e_ktls_offload_context_tx *priv_tx,
+			      bool skip_static_post, bool fence_first_post)
+{
+	bool progress_fence = skip_static_post || !fence_first_post;
+
+	if (!skip_static_post)
+		post_static_params(sq, priv_tx, fence_first_post);
+
+	post_progress_params(sq, priv_tx, progress_fence);
+}
+
+struct tx_sync_info {
+	u64 rcd_sn;
+	s32 sync_len;
+	int nr_frags;
+	skb_frag_t *frags[MAX_SKB_FRAGS];
+};
+
+static bool tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
+			     u32 tcp_seq, struct tx_sync_info *info)
+{
+	struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx;
+	struct tls_record_info *record;
+	int remaining, i = 0;
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&tx_ctx->lock, flags);
+	record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn);
+
+	if (unlikely(!record)) {
+		ret = false;
+		goto out;
+	}
+
+	if (unlikely(tcp_seq < tls_record_start_seq(record))) {
+		if (!tls_record_is_start_marker(record))
+			ret = false;
+		goto out;
+	}
+
+	info->sync_len = tcp_seq - tls_record_start_seq(record);
+	remaining = info->sync_len;
+	while (remaining > 0) {
+		skb_frag_t *frag = &record->frags[i];
+
+		__skb_frag_ref(frag);
+		remaining -= skb_frag_size(frag);
+		info->frags[i++] = frag;
+	}
+	/* reduce the part which will be sent with the original SKB */
+	if (remaining < 0)
+		skb_frag_size_add(info->frags[i - 1], remaining);
+	info->nr_frags = i;
+out:
+	spin_unlock_irqrestore(&tx_ctx->lock, flags);
+	return ret;
+}
+
+static void
+tx_post_resync_params(struct mlx5e_txqsq *sq,
+		      struct mlx5e_ktls_offload_context_tx *priv_tx,
+		      u64 rcd_sn)
+{
+	struct tls_crypto_info *crypto_info = priv_tx->crypto_info;
+	struct tls12_crypto_info_aes_gcm_128 *info;
+	__be64 rn_be = cpu_to_be64(rcd_sn);
+	bool skip_static_post;
+	u16 rec_seq_sz;
+	char *rec_seq;
+
+	if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128))
+		return;
+
+	info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
+	rec_seq = info->rec_seq;
+	rec_seq_sz = sizeof(info->rec_seq);
+
+	skip_static_post = !memcmp(rec_seq, &rn_be, rec_seq_sz);
+	if (!skip_static_post)
+		memcpy(rec_seq, &rn_be, rec_seq_sz);
+
+	mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, skip_static_post, true);
+}
+
+static int
+tx_post_resync_dump(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		    skb_frag_t *frag, u32 tisn, bool first)
+{
+	struct mlx5_wqe_ctrl_seg *cseg;
+	struct mlx5_wqe_eth_seg  *eseg;
+	struct mlx5_wqe_data_seg *dseg;
+	struct mlx5e_tx_wqe *wqe;
+	dma_addr_t dma_addr = 0;
+	u16 ds_cnt, ds_cnt_inl;
+	u8  num_wqebbs;
+	u16 pi, ihs;
+	int fsz;
+
+	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
+	ihs    = eth_get_headlen(skb->dev, skb->data, skb_headlen(skb));
+	ds_cnt_inl = DIV_ROUND_UP(ihs - INL_HDR_START_SZ, MLX5_SEND_WQE_DS);
+	ds_cnt += ds_cnt_inl;
+	ds_cnt += 1; /* one frag */
+
+	wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
+
+	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
+
+	cseg = &wqe->ctrl;
+	eseg = &wqe->eth;
+	dseg =  wqe->data;
+
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8)  | MLX5_OPCODE_DUMP);
+	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+	cseg->imm              = cpu_to_be32(tisn);
+	cseg->fm_ce_se         = first ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
+
+	eseg->inline_hdr.sz = cpu_to_be16(ihs);
+	memcpy(eseg->inline_hdr.start, skb->data, ihs);
+	dseg += ds_cnt_inl;
+
+	fsz = skb_frag_size(frag);
+	dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
+				    DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
+		return -ENOMEM;
+
+	dseg->addr       = cpu_to_be64(dma_addr);
+	dseg->lkey       = sq->mkey_be;
+	dseg->byte_count = cpu_to_be32(fsz);
+	mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE);
+
+	tx_fill_wi(sq, pi, num_wqebbs, frag);
+	sq->pc += num_wqebbs;
+
+	WARN(num_wqebbs > MLX5E_KTLS_MAX_DUMP_WQEBBS,
+	     "unexpected DUMP num_wqebbs, %d > %d",
+	     num_wqebbs, MLX5E_KTLS_MAX_DUMP_WQEBBS);
+
+	return 0;
+}
+
+void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
+					   struct mlx5e_tx_wqe_info *wi,
+					   struct mlx5e_sq_dma *dma)
+{
+	struct mlx5e_sq_stats *stats = sq->stats;
+
+	mlx5e_tx_dma_unmap(sq->pdev, dma);
+	__skb_frag_unref(wi->resync_dump_frag);
+	stats->tls_dump_packets++;
+	stats->tls_dump_bytes += wi->num_bytes;
+}
+
+static void tx_post_fence_nop(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+
+	tx_fill_wi(sq, pi, 1, NULL);
+
+	mlx5e_post_nop_fence(wq, sq->sqn, &sq->pc);
+}
+
+static struct sk_buff *
+mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
+			 struct mlx5e_txqsq *sq,
+			 struct sk_buff *skb,
+			 u32 seq)
+{
+	struct mlx5e_sq_stats *stats = sq->stats;
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	struct tx_sync_info info = {};
+	u16 contig_wqebbs_room, pi;
+	u8 num_wqebbs;
+	int i;
+
+	if (!tx_sync_info_get(priv_tx, seq, &info)) {
+		/* We might get here if a retransmission reaches the driver
+		 * after the relevant record is acked.
+		 * It should be safe to drop the packet in this case
+		 */
+		stats->tls_drop_no_sync_data++;
+		goto err_out;
+	}
+
+	if (unlikely(info.sync_len < 0)) {
+		u32 payload;
+		int headln;
+
+		headln = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		payload = skb->len - headln;
+		if (likely(payload <= -info.sync_len))
+			return skb;
+
+		stats->tls_drop_bypass_req++;
+		goto err_out;
+	}
+
+	stats->tls_ooo++;
+
+	num_wqebbs = MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS +
+		(info.nr_frags ? info.nr_frags * MLX5E_KTLS_MAX_DUMP_WQEBBS : 1);
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs_room < num_wqebbs))
+		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
+
+	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
+
+	for (i = 0; i < info.nr_frags; i++)
+		if (tx_post_resync_dump(sq, skb, info.frags[i],
+					priv_tx->tisn, !i))
+			goto err_out;
+
+	/* If no dump WQE was sent, we need to have a fence NOP WQE before the
+	 * actual data xmit.
+	 */
+	if (!info.nr_frags)
+		tx_post_fence_nop(sq);
+
+	return skb;
+
+err_out:
+	dev_kfree_skb_any(skb);
+	return NULL;
+}
+
+struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
+					 struct mlx5e_txqsq *sq,
+					 struct sk_buff *skb,
+					 struct mlx5e_tx_wqe **wqe, u16 *pi)
+{
+	struct mlx5e_ktls_offload_context_tx *priv_tx;
+	struct mlx5e_sq_stats *stats = sq->stats;
+	struct mlx5_wqe_ctrl_seg *cseg;
+	struct tls_context *tls_ctx;
+	int datalen;
+	u32 seq;
+
+	if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
+		goto out;
+
+	datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
+	if (!datalen)
+		goto out;
+
+	tls_ctx = tls_get_ctx(skb->sk);
+	if (unlikely(tls_ctx->netdev != netdev))
+		goto err_out;
+
+	priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
+
+	if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) {
+		mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, false, false);
+		*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
+		stats->tls_ctx++;
+	}
+
+	seq = ntohl(tcp_hdr(skb)->seq);
+	if (unlikely(priv_tx->expected_seq != seq)) {
+		skb = mlx5e_ktls_tx_handle_ooo(priv_tx, sq, skb, seq);
+		if (unlikely(!skb))
+			goto out;
+		*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
+	}
+
+	priv_tx->expected_seq = seq + datalen;
+
+	cseg = &(*wqe)->ctrl;
+	cseg->imm = cpu_to_be32(priv_tx->tisn);
+
+	stats->tls_encrypted_packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
+	stats->tls_encrypted_bytes   += datalen;
+
+out:
+	return skb;
+
+err_out:
+	dev_kfree_skb_any(skb);
+	return NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index e88340e196f7..fba561ffe1d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -160,25 +160,31 @@ static void mlx5e_tls_del(struct net_device *netdev,
 				direction == TLS_OFFLOAD_CTX_DIR_TX);
 }
 
-static void mlx5e_tls_resync_rx(struct net_device *netdev, struct sock *sk,
-				u32 seq, u64 rcd_sn)
+static int mlx5e_tls_resync(struct net_device *netdev, struct sock *sk,
+			    u32 seq, u8 *rcd_sn_data,
+			    enum tls_offload_ctx_dir direction)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_tls_offload_context_rx *rx_ctx;
+	u64 rcd_sn = *(u64 *)rcd_sn_data;
 
+	if (WARN_ON_ONCE(direction != TLS_OFFLOAD_CTX_DIR_RX))
+		return -EINVAL;
 	rx_ctx = mlx5e_get_tls_rx_context(tls_ctx);
 
 	netdev_info(netdev, "resyncing seq %d rcd %lld\n", seq,
 		    be64_to_cpu(rcd_sn));
 	mlx5_accel_tls_resync_rx(priv->mdev, rx_ctx->handle, seq, rcd_sn);
 	atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_reply);
+
+	return 0;
 }
 
 static const struct tlsdev_ops mlx5e_tls_ops = {
 	.tls_dev_add = mlx5e_tls_add,
 	.tls_dev_del = mlx5e_tls_del,
-	.tls_dev_resync_rx = mlx5e_tls_resync_rx,
+	.tls_dev_resync = mlx5e_tls_resync,
 };
 
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
@@ -186,6 +192,11 @@ void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 	struct net_device *netdev = priv->netdev;
 	u32 caps;
 
+	if (mlx5_accel_is_ktls_device(priv->mdev)) {
+		mlx5e_ktls_build_netdev(priv);
+		return;
+	}
+
 	if (!mlx5_accel_is_tls_device(priv->mdev))
 		return;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index 3f5d72163b56..9015f3f7792d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -33,8 +33,10 @@
 #ifndef __MLX5E_TLS_H__
 #define __MLX5E_TLS_H__
 
-#ifdef CONFIG_MLX5_EN_TLS
+#include "accel/tls.h"
+#include "en_accel/ktls.h"
 
+#ifdef CONFIG_MLX5_EN_TLS
 #include <net/tls.h>
 #include "en.h"
 
@@ -94,7 +96,12 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data);
 
 #else
 
-static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) { }
+static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
+{
+	if (mlx5_accel_is_ktls_device(priv->mdev))
+		mlx5e_ktls_build_netdev(priv);
+}
+
 static inline int mlx5e_tls_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tls_cleanup(struct mlx5e_priv *priv) { }
 static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index be137d4a9169..71384ad1a443 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -181,7 +181,6 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 	 */
 	nskb->ip_summed = CHECKSUM_PARTIAL;
 
-	nskb->xmit_more = 1;
 	nskb->queue_mapping = skb->queue_mapping;
 }
 
@@ -248,8 +247,8 @@ mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 	sq->stats->tls_resync_bytes += nskb->len;
 	mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln,
 				    cpu_to_be64(info.rcd_sn));
-	mlx5e_sq_xmit(sq, nskb, *wqe, *pi);
-	mlx5e_sq_fetch_wqe(sq, wqe, pi);
+	mlx5e_sq_xmit(sq, nskb, *wqe, *pi, true);
+	*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
 	return skb;
 
 err_out:
@@ -270,6 +269,11 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 	int datalen;
 	u32 skb_seq;
 
+	if (MLX5_CAP_GEN(sq->channel->mdev, tls)) {
+		skb = mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
+		goto out;
+	}
+
 	if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
 		goto out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 311667ec71b8..90bc1f2384c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -38,6 +38,7 @@
 
 #include <linux/skbuff.h>
 #include "en.h"
+#include "en/txrx.h"
 
 struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 					struct mlx5e_txqsq *sq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 3078491cc0d0..1539cf3de5dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 }
@@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir)
 {
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	mlx5_core_destroy_tir(mdev, tir->tirn);
 	list_del(&tir->list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 }
 
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
@@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	}
 
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+	mutex_init(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 
@@ -141,15 +146,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	int err  = -ENOMEM;
+	int err  = 0;
 	u32 tirn = 0;
 	int inlen;
 	void *in;
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	if (!in) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -157,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
 		tirn = tir->tirn;
 		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
@@ -168,6 +176,7 @@ out:
 	kvfree(in);
 	if (err)
 		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 722998d68564..8dd31b5c740c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -680,7 +680,7 @@ static void mlx5e_dcbnl_getpermhwaddr(struct net_device *netdev,
 
 	memset(perm_addr, 0xff, MAX_ADDR_LEN);
 
-	mlx5_query_nic_vport_mac_address(priv->mdev, 0, perm_addr);
+	mlx5_query_mac_address(priv->mdev, perm_addr);
 }
 
 static void mlx5e_dcbnl_setpgtccfgtx(struct net_device *netdev,
@@ -1126,9 +1126,7 @@ static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv)
 	    priv->channels.params.tx_min_inline_mode)
 		goto out;
 
-	if (mlx5e_open_channels(priv, &new_channels))
-		goto out;
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 out:
 	mutex_unlock(&priv->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
index d67adf70a97b..ca9cfbf57d8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
@@ -30,22 +30,22 @@
  * SOFTWARE.
  */
 
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 #include "en.h"
 
 static void
-mlx5e_complete_dim_work(struct net_dim *dim, struct net_dim_cq_moder moder,
+mlx5e_complete_dim_work(struct dim *dim, struct dim_cq_moder moder,
 			struct mlx5_core_dev *mdev, struct mlx5_core_cq *mcq)
 {
 	mlx5_core_modify_cq_moderation(mdev, mcq, moder.usec, moder.pkts);
-	dim->state = NET_DIM_START_MEASURE;
+	dim->state = DIM_START_MEASURE;
 }
 
 void mlx5e_rx_dim_work(struct work_struct *work)
 {
-	struct net_dim *dim = container_of(work, struct net_dim, work);
+	struct dim *dim = container_of(work, struct dim, work);
 	struct mlx5e_rq *rq = container_of(dim, struct mlx5e_rq, dim);
-	struct net_dim_cq_moder cur_moder =
+	struct dim_cq_moder cur_moder =
 		net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
 
 	mlx5e_complete_dim_work(dim, cur_moder, rq->mdev, &rq->cq.mcq);
@@ -53,9 +53,9 @@ void mlx5e_rx_dim_work(struct work_struct *work)
 
 void mlx5e_tx_dim_work(struct work_struct *work)
 {
-	struct net_dim *dim = container_of(work, struct net_dim, work);
+	struct dim *dim = container_of(work, struct dim, work);
 	struct mlx5e_txqsq *sq = container_of(dim, struct mlx5e_txqsq, dim);
-	struct net_dim_cq_moder cur_moder =
+	struct dim_cq_moder cur_moder =
 		net_dim_get_tx_moderation(dim->mode, dim->profile_ix);
 
 	mlx5e_complete_dim_work(dim, cur_moder, sq->cq.mdev, &sq->cq.mcq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 3bbccead2f63..126ec4181286 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,6 +32,7 @@
 
 #include "en.h"
 #include "en/port.h"
+#include "en/xsk/umem.h"
 #include "lib/clock.h"
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
@@ -46,7 +47,7 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 		 "%d.%d.%04d (%.16s)",
 		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev),
 		 mdev->board_id);
-	strlcpy(drvinfo->bus_info, pci_name(mdev->pdev),
+	strlcpy(drvinfo->bus_info, dev_name(mdev->device),
 		sizeof(drvinfo->bus_info));
 }
 
@@ -63,76 +64,147 @@ struct ptys2ethtool_config {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertised);
 };
 
-static struct ptys2ethtool_config ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER];
+static
+struct ptys2ethtool_config ptys2legacy_ethtool_table[MLX5E_LINK_MODES_NUMBER];
+static
+struct ptys2ethtool_config ptys2ext_ethtool_table[MLX5E_EXT_LINK_MODES_NUMBER];
 
-#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, ...)                       \
+#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, table, ...)                  \
 	({                                                              \
 		struct ptys2ethtool_config *cfg;                        \
 		const unsigned int modes[] = { __VA_ARGS__ };           \
-		unsigned int i;                                         \
-		cfg = &ptys2ethtool_table[reg_];                        \
+		unsigned int i, bit, idx;                               \
+		cfg = &ptys2##table##_ethtool_table[reg_];		\
 		bitmap_zero(cfg->supported,                             \
 			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
 		bitmap_zero(cfg->advertised,                            \
 			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
 		for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) {             \
-			__set_bit(modes[i], cfg->supported);            \
-			__set_bit(modes[i], cfg->advertised);           \
+			bit = modes[i] % 64;                            \
+			idx = modes[i] / 64;                            \
+			__set_bit(bit, &cfg->supported[idx]);           \
+			__set_bit(bit, &cfg->advertised[idx]);          \
 		}                                                       \
 	})
 
 void mlx5e_build_ptys2ethtool_map(void)
 {
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII,
+	memset(ptys2legacy_ethtool_table, 0, sizeof(ptys2legacy_ethtool_table));
+	memset(ptys2ext_ethtool_table, 0, sizeof(ptys2ext_ethtool_table));
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII, legacy,
 				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX, legacy,
 				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2, legacy,
 				       ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4, legacy,
 				       ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2, legacy,
 				       ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, legacy,
 				       ETHTOOL_LINK_MODE_10000baseT_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, legacy,
 				       ETHTOOL_LINK_MODE_25000baseCR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR, legacy,
 				       ETHTOOL_LINK_MODE_25000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR, legacy,
 				       ETHTOOL_LINK_MODE_25000baseSR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2, legacy,
 				       ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2, legacy,
 				       ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_SGMII_100M, ext,
+				       ETHTOOL_LINK_MODE_100baseT_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_X_SGMII, ext,
+				       ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+				       ETHTOOL_LINK_MODE_1000baseX_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_5GBASE_R, ext,
+				       ETHTOOL_LINK_MODE_5000baseT_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_XFI_XAUI_1, ext,
+				       ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+				       ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseER_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_XLAUI_4_XLPPI_4, ext,
+				       ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GAUI_1_25GBASE_CR_KR, ext,
+				       ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_25000baseSR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2,
+				       ext,
+				       ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR, ext,
+				       ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseDR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_CAUI_4_100GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_2_100GBASE_CR2_KR2, ext,
+				       ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_4_200GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT);
+}
+
+static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
+					struct ptys2ethtool_config **arr,
+					u32 *size)
+{
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+
+	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
+	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
+		      ARRAY_SIZE(ptys2legacy_ethtool_table);
 }
 
 typedef int (*mlx5e_pflag_handler)(struct net_device *netdev, bool enable);
@@ -298,11 +370,7 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 		goto unlock;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto unlock;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 unlock:
 	mutex_unlock(&priv->state_lock);
@@ -321,8 +389,17 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv,
 				struct ethtool_channels *ch)
 {
+	mutex_lock(&priv->state_lock);
+
 	ch->max_combined   = mlx5e_get_netdev_max_channels(priv->netdev);
 	ch->combined_count = priv->channels.params.num_channels;
+	if (priv->xsk.refcnt) {
+		/* The upper half are XSK queues. */
+		ch->max_combined *= 2;
+		ch->combined_count *= 2;
+	}
+
+	mutex_unlock(&priv->state_lock);
 }
 
 static void mlx5e_get_channels(struct net_device *dev,
@@ -336,6 +413,7 @@ static void mlx5e_get_channels(struct net_device *dev,
 int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 			       struct ethtool_channels *ch)
 {
+	struct mlx5e_params *cur_params = &priv->channels.params;
 	unsigned int count = ch->combined_count;
 	struct mlx5e_channels new_channels = {};
 	bool arfs_enabled;
@@ -347,39 +425,49 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 		return -EINVAL;
 	}
 
-	if (priv->channels.params.num_channels == count)
+	if (cur_params->num_channels == count)
 		return 0;
 
 	mutex_lock(&priv->state_lock);
 
+	/* Don't allow changing the number of channels if there is an active
+	 * XSK, because the numeration of the XSK and regular RQs will change.
+	 */
+	if (priv->xsk.refcnt) {
+		err = -EINVAL;
+		netdev_err(priv->netdev, "%s: AF_XDP is active, cannot change the number of channels\n",
+			   __func__);
+		goto out;
+	}
+
 	new_channels.params = priv->channels.params;
 	new_channels.params.num_channels = count;
-	if (!netif_is_rxfh_configured(priv->netdev))
-		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
-					      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		priv->channels.params = new_channels.params;
+		*cur_params = new_channels.params;
+		if (!netif_is_rxfh_configured(priv->netdev))
+			mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+						      MLX5E_INDIR_RQT_SIZE, count);
 		goto out;
 	}
 
-	/* Create fresh channels with new parameters */
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
-
 	arfs_enabled = priv->netdev->features & NETIF_F_NTUPLE;
 	if (arfs_enabled)
 		mlx5e_arfs_disable(priv);
 
+	if (!netif_is_rxfh_configured(priv->netdev))
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, count);
+
 	/* Switch to new channels, set new parameters and close old ones */
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 	if (arfs_enabled) {
-		err = mlx5e_arfs_enable(priv);
-		if (err)
+		int err2 = mlx5e_arfs_enable(priv);
+
+		if (err2)
 			netdev_err(priv->netdev, "%s: mlx5e_arfs_enable failed: %d\n",
-				   __func__, err);
+				   __func__, err2);
 	}
 
 out:
@@ -399,7 +487,7 @@ static int mlx5e_set_channels(struct net_device *dev,
 int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal)
 {
-	struct net_dim_cq_moder *rx_moder, *tx_moder;
+	struct dim_cq_moder *rx_moder, *tx_moder;
 
 	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
 		return -EOPNOTSUPP;
@@ -454,7 +542,7 @@ mlx5e_set_priv_channels_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesc
 int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal)
 {
-	struct net_dim_cq_moder *rx_moder, *tx_moder;
+	struct dim_cq_moder *rx_moder, *tx_moder;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_channels new_channels = {};
 	int err = 0;
@@ -505,12 +593,7 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	/* open fresh channels with new coal parameters */
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 out:
 	mutex_unlock(&priv->state_lock);
@@ -525,27 +608,37 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	return mlx5e_ethtool_set_coalesce(priv, coal);
 }
 
-static void ptys2ethtool_supported_link(unsigned long *supported_modes,
+static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev,
+					unsigned long *supported_modes,
 					u32 eth_proto_cap)
 {
 	unsigned long proto_cap = eth_proto_cap;
+	struct ptys2ethtool_config *table;
+	u32 max_size;
 	int proto;
 
-	for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
+	mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size);
+	for_each_set_bit(proto, &proto_cap, max_size)
 		bitmap_or(supported_modes, supported_modes,
-			  ptys2ethtool_table[proto].supported,
+			  table[proto].supported,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
 static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
-				    u32 eth_proto_cap)
+				    u32 eth_proto_cap, bool ext)
 {
 	unsigned long proto_cap = eth_proto_cap;
+	struct ptys2ethtool_config *table;
+	u32 max_size;
 	int proto;
 
-	for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
+	table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
+	max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
+			 ARRAY_SIZE(ptys2legacy_ethtool_table);
+
+	for_each_set_bit(proto, &proto_cap, max_size)
 		bitmap_or(advertising_modes, advertising_modes,
-			  ptys2ethtool_table[proto].advertised,
+			  table[proto].advertised,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
@@ -695,13 +788,14 @@ static void get_speed_duplex(struct net_device *netdev,
 			     u32 eth_proto_oper,
 			     struct ethtool_link_ksettings *link_ksettings)
 {
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u32 speed = SPEED_UNKNOWN;
 	u8 duplex = DUPLEX_UNKNOWN;
 
 	if (!netif_carrier_ok(netdev))
 		goto out;
 
-	speed = mlx5e_port_ptys2speed(eth_proto_oper);
+	speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper);
 	if (!speed) {
 		speed = SPEED_UNKNOWN;
 		goto out;
@@ -714,22 +808,22 @@ out:
 	link_ksettings->base.duplex = duplex;
 }
 
-static void get_supported(u32 eth_proto_cap,
+static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 			  struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *supported = link_ksettings->link_modes.supported;
+	ptys2ethtool_supported_link(mdev, supported, eth_proto_cap);
 
-	ptys2ethtool_supported_link(supported, eth_proto_cap);
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }
 
-static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
-			    u8 rx_pause,
-			    struct ethtool_link_ksettings *link_ksettings)
+static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
+			    struct ethtool_link_ksettings *link_ksettings,
+			    bool ext)
 {
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
+	ptys2ethtool_adver_link(advertising, eth_proto_cap, ext);
 
-	ptys2ethtool_adver_link(advertising, eth_proto_cap);
 	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
@@ -779,12 +873,13 @@ static u8 get_connector_port(u32 eth_proto, u8 connector_type)
 	return PORT_OTHER;
 }
 
-static void get_lp_advertising(u32 eth_proto_lp,
+static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 			       struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
 
-	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp);
+	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
 }
 
 int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
@@ -801,6 +896,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	u8 an_disable_admin;
 	u8 an_status;
 	u8 connector_type;
+	bool admin_ext;
+	bool ext;
 	int err;
 
 	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
@@ -809,22 +906,39 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 			   __func__, err);
 		goto err_query_regs;
 	}
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	eth_proto_cap    = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					      eth_proto_capability);
+	eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					      eth_proto_admin);
+	/* Fields: eth_proto_admin and ext_eth_proto_admin  are
+	 * mutually exclusive. Hence try reading legacy advertising
+	 * when extended advertising is zero.
+	 * admin_ext indicates how eth_proto_admin should be
+	 * interpreted
+	 */
+	admin_ext = ext;
+	if (ext && !eth_proto_admin) {
+		eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, false,
+						      eth_proto_admin);
+		admin_ext = false;
+	}
 
-	eth_proto_cap    = MLX5_GET(ptys_reg, out, eth_proto_capability);
-	eth_proto_admin  = MLX5_GET(ptys_reg, out, eth_proto_admin);
-	eth_proto_oper   = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	eth_proto_lp     = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
-	an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
-	an_status        = MLX5_GET(ptys_reg, out, an_status);
-	connector_type   = MLX5_GET(ptys_reg, out, connector_type);
+	eth_proto_oper   = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					      eth_proto_oper);
+	eth_proto_lp	    = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
+	an_disable_admin    = MLX5_GET(ptys_reg, out, an_disable_admin);
+	an_status	    = MLX5_GET(ptys_reg, out, an_status);
+	connector_type	    = MLX5_GET(ptys_reg, out, connector_type);
 
 	mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
 
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
 
-	get_supported(eth_proto_cap, link_ksettings);
-	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
+	get_supported(mdev, eth_proto_cap, link_ksettings);
+	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
+			admin_ext);
 	get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
@@ -833,7 +947,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 						       connector_type);
 	ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin,
 					       connector_type);
-	get_lp_advertising(eth_proto_lp, link_ksettings);
+	get_lp_advertising(mdev, eth_proto_lp, link_ksettings);
 
 	if (an_status == MLX5_AN_COMPLETE)
 		ethtool_link_ksettings_add_link_mode(link_ksettings,
@@ -872,7 +986,9 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 	u32 i, ptys_modes = 0;
 
 	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (bitmap_intersects(ptys2ethtool_table[i].advertised,
+		if (*ptys2legacy_ethtool_table[i].advertised == 0)
+			continue;
+		if (bitmap_intersects(ptys2legacy_ethtool_table[i].advertised,
 				      link_modes,
 				      __ETHTOOL_LINK_MODE_MASK_NBITS))
 			ptys_modes |= MLX5E_PROT_MASK(i);
@@ -881,13 +997,34 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 	return ptys_modes;
 }
 
+static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes)
+{
+	u32 i, ptys_modes = 0;
+	unsigned long modes[2];
+
+	for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) {
+		if (*ptys2ext_ethtool_table[i].advertised == 0)
+			continue;
+		memset(modes, 0, sizeof(modes));
+		bitmap_and(modes, ptys2ext_ethtool_table[i].advertised,
+			   link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+		if (modes[0] == ptys2ext_ethtool_table[i].advertised[0] &&
+		    modes[1] == ptys2ext_ethtool_table[i].advertised[1])
+			ptys_modes |= MLX5E_PROT_MASK(i);
+	}
+	return ptys_modes;
+}
+
 int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 				     const struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 eth_proto_cap, eth_proto_admin;
+	struct mlx5e_port_eth_proto eproto;
 	bool an_changes = false;
 	u8 an_disable_admin;
+	bool ext_supported;
+	bool ext_requested;
 	u8 an_disable_cap;
 	bool an_disable;
 	u32 link_modes;
@@ -895,20 +1032,31 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	u32 speed;
 	int err;
 
-	speed = link_ksettings->base.speed;
+	u32 (*ethtool2ptys_adver_func)(const unsigned long *adver);
 
-	link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
-		mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) :
-		mlx5e_port_speed2linkmodes(speed);
+#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1)
+
+	ext_requested = !!(link_ksettings->link_modes.advertising[0] >
+			MLX5E_PTYS_EXT ||
+			link_ksettings->link_modes.advertising[1]);
+	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext_requested &= ext_supported;
 
-	err = mlx5_query_port_proto_cap(mdev, &eth_proto_cap, MLX5_PTYS_EN);
+	speed = link_ksettings->base.speed;
+	ethtool2ptys_adver_func = ext_requested ?
+				  mlx5e_ethtool2ptys_ext_adver_link :
+				  mlx5e_ethtool2ptys_adver_link;
+	err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto);
 	if (err) {
-		netdev_err(priv->netdev, "%s: query port eth proto cap failed: %d\n",
+		netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
 			   __func__, err);
 		goto out;
 	}
+	link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
+		ethtool2ptys_adver_func(link_ksettings->link_modes.advertising) :
+		mlx5e_port_speed2linkmodes(mdev, speed);
 
-	link_modes = link_modes & eth_proto_cap;
+	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {
 		netdev_err(priv->netdev, "%s: Not supported link mode(s) requested",
 			   __func__);
@@ -916,24 +1064,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5_query_port_proto_admin(mdev, &eth_proto_admin, MLX5_PTYS_EN);
-	if (err) {
-		netdev_err(priv->netdev, "%s: query port eth proto admin failed: %d\n",
-			   __func__, err);
-		goto out;
-	}
-
-	mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status,
-				&an_disable_cap, &an_disable_admin);
+	mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap,
+				    &an_disable_admin);
 
 	an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE;
 	an_changes = ((!an_disable && an_disable_admin) ||
 		      (an_disable && !an_disable_admin));
 
-	if (!an_changes && link_modes == eth_proto_admin)
+	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN);
+	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested);
 	mlx5_toggle_port_link(mdev);
 
 out:
@@ -1441,7 +1582,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *dev = priv->mdev;
 	int size_read = 0;
-	u8 data[4];
+	u8 data[4] = {0};
 
 	size_read = mlx5_query_module_eeprom(dev, 0, 2, data);
 	if (size_read < 2)
@@ -1451,22 +1592,22 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 	switch (data[0]) {
 	case MLX5_MODULE_ID_QSFP:
 		modinfo->type       = ETH_MODULE_SFF_8436;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
 		break;
 	case MLX5_MODULE_ID_QSFP_PLUS:
 	case MLX5_MODULE_ID_QSFP28:
 		/* data[1] = revision id */
 		if (data[0] == MLX5_MODULE_ID_QSFP28 || data[1] >= 0x3) {
 			modinfo->type       = ETH_MODULE_SFF_8636;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN;
 		} else {
 			modinfo->type       = ETH_MODULE_SFF_8436;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
 		}
 		break;
 	case MLX5_MODULE_ID_SFP:
 		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
 		break;
 	default:
 		netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
@@ -1521,7 +1662,6 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 	struct mlx5e_channels new_channels = {};
 	bool mode_changed;
 	u8 cq_period_mode, current_cq_period_mode;
-	int err = 0;
 
 	cq_period_mode = enable ?
 		MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
@@ -1549,12 +1689,7 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 		return 0;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		return err;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
-	return 0;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 }
 
 static int set_pflag_tx_cqe_based_moder(struct net_device *netdev, bool enable)
@@ -1587,11 +1722,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val
 		return 0;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 	if (err)
 		return err;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 	mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n",
 		  MLX5E_GET_PFLAG(&priv->channels.params,
 				  MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF");
@@ -1624,7 +1758,6 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_channels new_channels = {};
-	int err;
 
 	if (enable) {
 		if (!mlx5e_check_fragmented_striding_rq_cap(mdev))
@@ -1646,12 +1779,7 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 		return 0;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		return err;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
-	return 0;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 }
 
 static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
@@ -1661,7 +1789,8 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	struct mlx5e_channel *c;
 	int i;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) ||
+	    priv->channels.params.xdp_prog)
 		return 0;
 
 	for (i = 0; i < channels->num; i++) {
@@ -1694,12 +1823,8 @@ static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable)
 		return 0;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		return err;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
-	return 0;
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+	return err;
 }
 
 static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = {
@@ -1763,39 +1888,21 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 	return priv->channels.params.pflags;
 }
 
-int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
-			       struct ethtool_flash *flash)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct net_device *dev = priv->netdev;
-	const struct firmware *fw;
-	int err;
-
-	if (flash->region != ETHTOOL_FLASH_ALL_REGIONS)
-		return -EOPNOTSUPP;
-
-	err = request_firmware_direct(&fw, flash->data, &dev->dev);
-	if (err)
-		return err;
-
-	dev_hold(dev);
-	rtnl_unlock();
-
-	err = mlx5_firmware_flash(mdev, fw);
-	release_firmware(fw);
-
-	rtnl_lock();
-	dev_put(dev);
-	return err;
-}
-
-static int mlx5e_flash_device(struct net_device *dev,
-			      struct ethtool_flash *flash)
+#ifndef CONFIG_MLX5_EN_RXNFC
+/* When CONFIG_MLX5_EN_RXNFC=n we only support ETHTOOL_GRXRINGS
+ * otherwise this function will be defined from en_fs_ethtool.c
+ */
+static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-	return mlx5e_ethtool_flash_device(priv, flash);
+	if (info->cmd != ETHTOOL_GRXRINGS)
+		return -EOPNOTSUPP;
+	/* ring_count is needed by ethtool -x */
+	info->data = priv->channels.params.num_channels;
+	return 0;
 }
+#endif
 
 const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_drvinfo       = mlx5e_get_drvinfo,
@@ -1815,11 +1922,10 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
-#ifdef CONFIG_MLX5_EN_RXNFC
 	.get_rxnfc         = mlx5e_get_rxnfc,
+#ifdef CONFIG_MLX5_EN_RXNFC
 	.set_rxnfc         = mlx5e_set_rxnfc,
 #endif
-	.flash_device      = mlx5e_flash_device,
 	.get_tunable       = mlx5e_get_tunable,
 	.set_tunable       = mlx5e_set_tunable,
 	.get_pauseparam    = mlx5e_get_pauseparam,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 4421c10f58ae..ea3a490b569a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -32,6 +32,8 @@
 
 #include <linux/mlx5/fs.h>
 #include "en.h"
+#include "en/params.h"
+#include "en/xsk/umem.h"
 
 struct mlx5e_ethtool_rule {
 	struct list_head             list;
@@ -414,6 +416,14 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC) {
 		flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
 	} else {
+		struct mlx5e_params *params = &priv->channels.params;
+		enum mlx5e_rq_group group;
+		struct mlx5e_tir *tir;
+		u16 ix;
+
+		mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group);
+		tir = group == MLX5E_RQ_GROUP_XSK ? priv->xsk_tir : priv->direct_tir;
+
 		dst = kzalloc(sizeof(*dst), GFP_KERNEL);
 		if (!dst) {
 			err = -ENOMEM;
@@ -421,12 +431,12 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 		}
 
 		dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
-		dst->tir_num = priv->direct_tir[fs->ring_cookie].tirn;
+		dst->tir_num = tir[ix].tirn;
 		flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	}
 
 	spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
-	flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+	spec->flow_context.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, dst ? 1 : 0);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -600,9 +610,9 @@ static int validate_flow(struct mlx5e_priv *priv,
 	if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
 		return -ENOSPC;
 
-	if (fs->ring_cookie >= priv->channels.params.num_channels &&
-	    fs->ring_cookie != RX_CLS_FLOW_DISC)
-		return -EINVAL;
+	if (fs->ring_cookie != RX_CLS_FLOW_DISC)
+		if (!mlx5e_qid_validate(&priv->channels.params, fs->ring_cookie))
+			return -EINVAL;
 
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
 	case ETHER_FLOW:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 01819e5c9975..47eea6b3a1c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -34,14 +34,19 @@
 #include <net/pkt_cls.h>
 #include <linux/mlx5/fs.h>
 #include <net/vxlan.h>
+#include <net/geneve.h>
 #include <linux/bpf.h>
+#include <linux/if_bridge.h>
 #include <net/page_pool.h>
+#include <net/xdp_sock.h>
 #include "eswitch.h"
 #include "en.h"
+#include "en/txrx.h"
 #include "en_tc.h"
 #include "en_rep.h"
 #include "en_accel/ipsec.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "en_accel/en_accel.h"
 #include "en_accel/tls.h"
 #include "accel/ipsec.h"
 #include "accel/tls.h"
@@ -51,35 +56,13 @@
 #include "en/xdp.h"
 #include "lib/eq.h"
 #include "en/monitor_stats.h"
+#include "en/reporter.h"
+#include "en/params.h"
+#include "en/xsk/umem.h"
+#include "en/xsk/setup.h"
+#include "en/xsk/rx.h"
+#include "en/xsk/tx.h"
 
-struct mlx5e_rq_param {
-	u32			rqc[MLX5_ST_SZ_DW(rqc)];
-	struct mlx5_wq_param	wq;
-	struct mlx5e_rq_frags_info frags_info;
-};
-
-struct mlx5e_sq_param {
-	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
-	struct mlx5_wq_param       wq;
-	bool                       is_mpw;
-};
-
-struct mlx5e_cq_param {
-	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
-	struct mlx5_wq_param       wq;
-	u16                        eq_ix;
-	u8                         cq_period_mode;
-};
-
-struct mlx5e_channel_param {
-	struct mlx5e_rq_param      rq;
-	struct mlx5e_sq_param      sq;
-	struct mlx5e_sq_param      xdp_sq;
-	struct mlx5e_sq_param      icosq;
-	struct mlx5e_cq_param      rx_cq;
-	struct mlx5e_cq_param      tx_cq;
-	struct mlx5e_cq_param      icosq_cq;
-};
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
@@ -99,109 +82,9 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 	return true;
 }
 
-static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
-{
-	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	u16 linear_rq_headroom = params->xdp_prog ?
-		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
-	u32 frag_sz;
-
-	linear_rq_headroom += NET_IP_ALIGN;
-
-	frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
-
-	if (params->xdp_prog && frag_sz < PAGE_SIZE)
-		frag_sz = PAGE_SIZE;
-
-	return frag_sz;
-}
-
-static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
-{
-	u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-
-	return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz);
-}
-
-static bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params)
-{
-	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-
-	return !params->lro_en && frag_sz <= PAGE_SIZE;
-}
-
-#define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \
-					  MLX5_MPWQE_LOG_STRIDE_SZ_BASE)
-static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev,
-					 struct mlx5e_params *params)
-{
-	u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params);
-	s8 signed_log_num_strides_param;
-	u8 log_num_strides;
-
-	if (!mlx5e_rx_is_linear_skb(mdev, params))
-		return false;
-
-	if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ)
-		return false;
-
-	if (MLX5_CAP_GEN(mdev, ext_stride_num_range))
-		return true;
-
-	log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz);
-	signed_log_num_strides_param =
-		(s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE;
-
-	return signed_log_num_strides_param >= 0;
-}
-
-static u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params)
-{
-	if (params->log_rq_mtu_frames <
-	    mlx5e_mpwqe_log_pkts_per_wqe(params) + MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW)
-		return MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW;
-
-	return params->log_rq_mtu_frames - mlx5e_mpwqe_log_pkts_per_wqe(params);
-}
-
-static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
-					  struct mlx5e_params *params)
-{
-	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
-		return order_base_2(mlx5e_rx_get_linear_frag_sz(params));
-
-	return MLX5E_MPWQE_STRIDE_SZ(mdev,
-		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
-}
-
-static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
-					  struct mlx5e_params *params)
-{
-	return MLX5_MPWRQ_LOG_WQE_SZ -
-		mlx5e_mpwqe_get_log_stride_size(mdev, params);
-}
-
-static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
-				 struct mlx5e_params *params)
-{
-	u16 linear_rq_headroom = params->xdp_prog ?
-		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
-	bool is_linear_skb;
-
-	linear_rq_headroom += NET_IP_ALIGN;
-
-	is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ?
-		mlx5e_rx_is_linear_skb(mdev, params) :
-		mlx5e_rx_mpwqe_is_linear_skb(mdev, params);
-
-	return is_linear_skb ? linear_rq_headroom : 0;
-}
-
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params)
 {
-	params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
 	params->log_rq_mtu_frames = is_kdump_kernel() ?
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
@@ -209,18 +92,31 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 	mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n",
 		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ,
 		       params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
-		       BIT(mlx5e_mpwqe_get_log_rq_size(params)) :
+		       BIT(mlx5e_mpwqe_get_log_rq_size(params, NULL)) :
 		       BIT(params->log_rq_mtu_frames),
-		       BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)),
+		       BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL)),
 		       MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
 }
 
 bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params)
 {
-	return mlx5e_check_fragmented_striding_rq_cap(mdev) &&
-		!MLX5_IPSEC_DEV(mdev) &&
-		!(params->xdp_prog && !mlx5e_rx_mpwqe_is_linear_skb(mdev, params));
+	if (!mlx5e_check_fragmented_striding_rq_cap(mdev))
+		return false;
+
+	if (MLX5_IPSEC_DEV(mdev))
+		return false;
+
+	if (params->xdp_prog) {
+		/* XSK params are not considered here. If striding RQ is in use,
+		 * and an XSK is being opened, mlx5e_rx_mpwqe_is_linear_skb will
+		 * be called with the known XSK params.
+		 */
+		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
+			return false;
+	}
+
+	return true;
 }
 
 void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
@@ -468,7 +364,6 @@ static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
 }
 
 static int mlx5e_init_di_list(struct mlx5e_rq *rq,
-			      struct mlx5e_params *params,
 			      int wq_sz, int cpu)
 {
 	int len = wq_sz << rq->wqe.info.log_num_frags;
@@ -490,6 +385,8 @@ static void mlx5e_free_di_list(struct mlx5e_rq *rq)
 
 static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			  struct mlx5e_params *params,
+			  struct mlx5e_xsk_param *xsk,
+			  struct xdp_umem *umem,
 			  struct mlx5e_rq_param *rqp,
 			  struct mlx5e_rq *rq)
 {
@@ -497,6 +394,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->mdev;
 	void *rqc = rqp->rqc;
 	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
+	u32 num_xsk_frames = 0;
+	u32 rq_xdp_ix;
 	u32 pool_size;
 	int wq_sz;
 	int err;
@@ -513,7 +412,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
 	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	rq->stats   = &c->priv->channel_stats[c->ix].rq;
+	rq->xdpsq   = &c->rq_xdpsq;
+	rq->umem    = umem;
+
+	if (rq->umem)
+		rq->stats = &c->priv->channel_stats[c->ix].xskrq;
+	else
+		rq->stats = &c->priv->channel_stats[c->ix].rq;
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
 	if (IS_ERR(rq->xdp_prog)) {
@@ -522,12 +427,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		goto err_rq_wq_destroy;
 	}
 
-	err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix);
+	rq_xdp_ix = rq->ix;
+	if (xsk)
+		rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK;
+	err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix);
 	if (err < 0)
 		goto err_rq_wq_destroy;
 
 	rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
-	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params);
+	rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk);
+	rq->buff.umem_headroom = xsk ? xsk->headroom : 0;
 	pool_size = 1 << params->log_rq_mtu_frames;
 
 	switch (rq->wq_type) {
@@ -541,7 +450,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-		pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params);
+		if (xsk)
+			num_xsk_frames = wq_sz <<
+				mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
+
+		pool_size = MLX5_MPWRQ_PAGES_PER_WQE <<
+			mlx5e_mpwqe_get_log_rq_size(params, xsk);
 
 		rq->post_wqes = mlx5e_post_rx_mpwqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
@@ -560,12 +474,15 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_rq_wq_destroy;
 		}
 
-		rq->mpwqe.skb_from_cqe_mpwrq =
-			mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ?
-			mlx5e_skb_from_cqe_mpwrq_linear :
-			mlx5e_skb_from_cqe_mpwrq_nonlinear;
-		rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params);
-		rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params));
+		rq->mpwqe.skb_from_cqe_mpwrq = xsk ?
+			mlx5e_xsk_skb_from_cqe_mpwrq_linear :
+			mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ?
+				mlx5e_skb_from_cqe_mpwrq_linear :
+				mlx5e_skb_from_cqe_mpwrq_nonlinear;
+
+		rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
+		rq->mpwqe.num_strides =
+			BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
 
 		err = mlx5e_create_rq_umr_mkey(mdev, rq);
 		if (err)
@@ -586,6 +503,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 		wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq);
 
+		if (xsk)
+			num_xsk_frames = wq_sz << rq->wqe.info.log_num_frags;
+
 		rq->wqe.info = rqp->frags_info;
 		rq->wqe.frags =
 			kvzalloc_node(array_size(sizeof(*rq->wqe.frags),
@@ -596,9 +516,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_free;
 		}
 
-		err = mlx5e_init_di_list(rq, params, wq_sz, c->cpu);
+		err = mlx5e_init_di_list(rq, wq_sz, c->cpu);
 		if (err)
 			goto err_free;
+
 		rq->post_wqes = mlx5e_post_rx_wqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
@@ -614,33 +535,49 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 			goto err_free;
 		}
 
-		rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(mdev, params) ?
-			mlx5e_skb_from_cqe_linear :
-			mlx5e_skb_from_cqe_nonlinear;
+		rq->wqe.skb_from_cqe = xsk ?
+			mlx5e_xsk_skb_from_cqe_linear :
+			mlx5e_rx_is_linear_skb(params, NULL) ?
+				mlx5e_skb_from_cqe_linear :
+				mlx5e_skb_from_cqe_nonlinear;
 		rq->mkey_be = c->mkey_be;
 	}
 
-	/* Create a page_pool and register it with rxq */
-	pp_params.order     = 0;
-	pp_params.flags     = 0; /* No-internal DMA mapping in page_pool */
-	pp_params.pool_size = pool_size;
-	pp_params.nid       = cpu_to_node(c->cpu);
-	pp_params.dev       = c->pdev;
-	pp_params.dma_dir   = rq->buff.map_dir;
-
-	/* page_pool can be used even when there is no rq->xdp_prog,
-	 * given page_pool does not handle DMA mapping there is no
-	 * required state to clear. And page_pool gracefully handle
-	 * elevated refcnt.
-	 */
-	rq->page_pool = page_pool_create(&pp_params);
-	if (IS_ERR(rq->page_pool)) {
-		err = PTR_ERR(rq->page_pool);
-		rq->page_pool = NULL;
-		goto err_free;
+	if (xsk) {
+		err = mlx5e_xsk_resize_reuseq(umem, num_xsk_frames);
+		if (unlikely(err)) {
+			mlx5_core_err(mdev, "Unable to allocate the Reuse Ring for %u frames\n",
+				      num_xsk_frames);
+			goto err_free;
+		}
+
+		rq->zca.free = mlx5e_xsk_zca_free;
+		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+						 MEM_TYPE_ZERO_COPY,
+						 &rq->zca);
+	} else {
+		/* Create a page_pool and register it with rxq */
+		pp_params.order     = 0;
+		pp_params.flags     = 0; /* No-internal DMA mapping in page_pool */
+		pp_params.pool_size = pool_size;
+		pp_params.nid       = cpu_to_node(c->cpu);
+		pp_params.dev       = c->pdev;
+		pp_params.dma_dir   = rq->buff.map_dir;
+
+		/* page_pool can be used even when there is no rq->xdp_prog,
+		 * given page_pool does not handle DMA mapping there is no
+		 * required state to clear. And page_pool gracefully handle
+		 * elevated refcnt.
+		 */
+		rq->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(rq->page_pool)) {
+			err = PTR_ERR(rq->page_pool);
+			rq->page_pool = NULL;
+			goto err_free;
+		}
+		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+						 MEM_TYPE_PAGE_POOL, rq->page_pool);
 	}
-	err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
-					 MEM_TYPE_PAGE_POOL, rq->page_pool);
 	if (err)
 		goto err_free;
 
@@ -680,11 +617,11 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 
 	switch (params->rx_cq_moderation.cq_period_mode) {
 	case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
-		rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE;
+		rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE;
 		break;
 	case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
 	default:
-		rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		rq->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 	}
 
 	rq->page_cache.head = 0;
@@ -707,8 +644,7 @@ err_rq_wq_destroy:
 	if (rq->xdp_prog)
 		bpf_prog_put(rq->xdp_prog);
 	xdp_rxq_info_unreg(&rq->xdp_rxq);
-	if (rq->page_pool)
-		page_pool_destroy(rq->page_pool);
+	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
 
 	return err;
@@ -721,10 +657,6 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 	if (rq->xdp_prog)
 		bpf_prog_put(rq->xdp_prog);
 
-	xdp_rxq_info_unreg(&rq->xdp_rxq);
-	if (rq->page_pool)
-		page_pool_destroy(rq->page_pool);
-
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		kvfree(rq->mpwqe.info);
@@ -739,8 +671,15 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 	     i = (i + 1) & (MLX5E_CACHE_SIZE - 1)) {
 		struct mlx5e_dma_info *dma_info = &rq->page_cache.page_cache[i];
 
-		mlx5e_page_release(rq, dma_info, false);
+		/* With AF_XDP, page_cache is not used, so this loop is not
+		 * entered, and it's safe to call mlx5e_page_release_dynamic
+		 * directly.
+		 */
+		mlx5e_page_release_dynamic(rq, dma_info, false);
 	}
+
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
+	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
 }
 
@@ -874,7 +813,7 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
 	mlx5_core_destroy_rq(rq->mdev, rq->rqn);
 }
 
-static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
+int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time)
 {
 	unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time);
 	struct mlx5e_channel *c = rq->channel;
@@ -901,10 +840,14 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
+		u16 head = wq->head;
+		int i;
 
-		/* UMR WQE (if in progress) is always at wq->head */
-		if (rq->mpwqe.umr_in_progress)
-			rq->dealloc_wqe(rq, wq->head);
+		/* Outstanding UMR WQEs (in progress) start at wq->head */
+		for (i = 0; i < rq->mpwqe.umr_in_progress; i++) {
+			rq->dealloc_wqe(rq, head);
+			head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+		}
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
@@ -928,14 +871,13 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 }
 
-static int mlx5e_open_rq(struct mlx5e_channel *c,
-			 struct mlx5e_params *params,
-			 struct mlx5e_rq_param *param,
-			 struct mlx5e_rq *rq)
+int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		  struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk,
+		  struct xdp_umem *umem, struct mlx5e_rq *rq)
 {
 	int err;
 
-	err = mlx5e_alloc_rq(c, params, param, rq);
+	err = mlx5e_alloc_rq(c, params, xsk, umem, param, rq);
 	if (err)
 		return err;
 
@@ -947,10 +889,17 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (err)
 		goto err_destroy_rq;
 
+	if (MLX5_CAP_ETH(c->mdev, cqe_checksum_full))
+		__set_bit(MLX5E_RQ_STATE_CSUM_FULL, &c->rq.state);
+
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
-	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE))
+	/* We disable csum_complete when XDP is enabled since
+	 * XDP programs might manipulate packets which will render
+	 * skb->checksum incorrect.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
 
 	return 0;
@@ -965,25 +914,17 @@ err_free_rq:
 
 static void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
-	struct mlx5e_icosq *sq = &rq->channel->icosq;
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *nopwqe;
-
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	sq->db.ico_wqe[pi].opcode     = MLX5_OPCODE_NOP;
-	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+	mlx5e_trigger_irq(&rq->channel->icosq);
 }
 
-static void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
+void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 {
 	clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
 	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
 }
 
-static void mlx5e_close_rq(struct mlx5e_rq *rq)
+void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
 	cancel_work_sync(&rq->dim.work);
 	mlx5e_destroy_rq(rq);
@@ -1036,6 +977,7 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 
 static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
+			     struct xdp_umem *umem,
 			     struct mlx5e_sq_param *param,
 			     struct mlx5e_xdpsq *sq,
 			     bool is_redirect)
@@ -1051,9 +993,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	sq->stats     = is_redirect ?
-		&c->priv->channel_stats[c->ix].xdpsq :
-		&c->priv->channel_stats[c->ix].rq_xdpsq;
+	sq->umem      = umem;
+
+	sq->stats = sq->umem ?
+		&c->priv->channel_stats[c->ix].xsksq :
+		is_redirect ?
+			&c->priv->channel_stats[c->ix].xdpsq :
+			&c->priv->channel_stats[c->ix].rq_xdpsq;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1086,7 +1032,7 @@ static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
-	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
 	sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
 						  sizeof(*sq->db.ico_wqe)),
@@ -1160,7 +1106,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	return 0;
 }
 
-static void mlx5e_sq_recover(struct work_struct *work);
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
 static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 			     int txq_ix,
 			     struct mlx5e_params *params,
@@ -1178,15 +1124,19 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->clock     = &mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->channel   = c;
+	sq->ch_ix     = c->ix;
 	sq->txq_ix    = txq_ix;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
-	INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover);
+	sq->stop_room = MLX5E_SQ_STOP_ROOM;
+	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
-	if (mlx5_accel_is_tls_device(c->priv->mdev))
+	if (mlx5_accel_is_tls_device(c->priv->mdev)) {
 		set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
+		sq->stop_room += MLX5E_SQ_TLS_ROOM;
+	}
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1270,15 +1220,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
 	return err;
 }
 
-struct mlx5e_modify_sq_param {
-	int curr_state;
-	int next_state;
-	bool rl_update;
-	int rl_index;
-};
-
-static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
-			   struct mlx5e_modify_sq_param *p)
+int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+		    struct mlx5e_modify_sq_param *p)
 {
 	void *in;
 	void *sqc;
@@ -1376,17 +1319,7 @@ err_free_txqsq:
 	return err;
 }
 
-static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
-{
-	WARN_ONCE(sq->cc != sq->pc,
-		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
-		  sq->sqn, sq->cc, sq->pc);
-	sq->cc = 0;
-	sq->dma_fifo_cc = 0;
-	sq->pc = 0;
-}
-
-static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 {
 	sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
@@ -1395,7 +1328,7 @@ static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 	netif_tx_start_queue(sq->txq);
 }
 
-static inline void netif_tx_disable_queue(struct netdev_queue *txq)
+void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 {
 	__netif_tx_lock_bh(txq);
 	netif_tx_stop_queue(txq);
@@ -1411,7 +1344,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	/* prevent netif_tx_wake_queue */
 	napi_synchronize(&c->napi);
 
-	netif_tx_disable_queue(sq->txq);
+	mlx5e_tx_disable_queue(sq->txq);
 
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
@@ -1431,6 +1364,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	struct mlx5_rate_limit rl = {0};
 
 	cancel_work_sync(&sq->dim.work);
+	cancel_work_sync(&sq->recover_work);
 	mlx5e_destroy_sq(mdev, sq->sqn);
 	if (sq->rate_limit) {
 		rl.rate = sq->rate_limit;
@@ -1440,111 +1374,16 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	mlx5e_free_txqsq(sq);
 }
 
-static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
-{
-	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
-
-	while (time_before(jiffies, exp_time)) {
-		if (sq->cc == sq->pc)
-			return 0;
-
-		msleep(20);
-	}
-
-	netdev_err(sq->channel->netdev,
-		   "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n",
-		   sq->sqn, sq->cc, sq->pc);
-
-	return -ETIMEDOUT;
-}
-
-static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 {
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	struct mlx5e_modify_sq_param msp = {0};
-	int err;
-
-	msp.curr_state = curr_state;
-	msp.next_state = MLX5_SQC_STATE_RST;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
-		return err;
-	}
-
-	memset(&msp, 0, sizeof(msp));
-	msp.curr_state = MLX5_SQC_STATE_RST;
-	msp.next_state = MLX5_SQC_STATE_RDY;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
-		return err;
-	}
-
-	return 0;
-}
-
-static void mlx5e_sq_recover(struct work_struct *work)
-{
-	struct mlx5e_txqsq_recover *recover =
-		container_of(work, struct mlx5e_txqsq_recover,
-			     recover_work);
-	struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq,
-					      recover);
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	u8 state;
-	int err;
-
-	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
-	if (err) {
-		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
-			   sq->sqn, err);
-		return;
-	}
+	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
+					      recover_work);
 
-	if (state != MLX5_RQC_STATE_ERR) {
-		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
-		return;
-	}
-
-	netif_tx_disable_queue(sq->txq);
-
-	if (mlx5e_wait_for_sq_flush(sq))
-		return;
-
-	/* If the interval between two consecutive recovers per SQ is too
-	 * short, don't recover to avoid infinite loop of ERR_CQE -> recover.
-	 * If we reached this state, there is probably a bug that needs to be
-	 * fixed. let's keep the queue close and let tx timeout cleanup.
-	 */
-	if (jiffies_to_msecs(jiffies - recover->last_recover) <
-	    MLX5E_SQ_RECOVER_MIN_INTERVAL) {
-		netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n",
-			   sq->sqn);
-		return;
-	}
-
-	/* At this point, no new packets will arrive from the stack as TXQ is
-	 * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
-	 * pending WQEs.  SQ can safely reset the SQ.
-	 */
-	if (mlx5e_sq_to_ready(sq, state))
-		return;
-
-	mlx5e_reset_txqsq_cc_pc(sq);
-	sq->stats->recover++;
-	recover->last_recover = jiffies;
-	mlx5e_activate_txqsq(sq);
+	mlx5e_tx_reporter_err_cqe(sq);
 }
 
-static int mlx5e_open_icosq(struct mlx5e_channel *c,
-			    struct mlx5e_params *params,
-			    struct mlx5e_sq_param *param,
-			    struct mlx5e_icosq *sq)
+int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq)
 {
 	struct mlx5e_create_sq_param csp = {};
 	int err;
@@ -1570,7 +1409,7 @@ err_free_icosq:
 	return err;
 }
 
-static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
@@ -1581,16 +1420,14 @@ static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 	mlx5e_free_icosq(sq);
 }
 
-static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
-			    struct mlx5e_params *params,
-			    struct mlx5e_sq_param *param,
-			    struct mlx5e_xdpsq *sq,
-			    bool is_redirect)
+int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
+		     struct mlx5e_sq_param *param, struct xdp_umem *umem,
+		     struct mlx5e_xdpsq *sq, bool is_redirect)
 {
 	struct mlx5e_create_sq_param csp = {};
 	int err;
 
-	err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
+	err = mlx5e_alloc_xdpsq(c, params, umem, param, sq, is_redirect);
 	if (err)
 		return err;
 
@@ -1631,7 +1468,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			dseg->lkey = sq->mkey_be;
 
 			wi->num_wqebbs = 1;
-			wi->num_ds     = 1;
+			wi->num_pkts   = 1;
 		}
 	}
 
@@ -1644,7 +1481,7 @@ err_free_xdpsq:
 	return err;
 }
 
-static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
+void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
@@ -1652,7 +1489,7 @@ static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 	napi_synchronize(&c->napi);
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
-	mlx5e_free_xdpsq_descs(sq, rq);
+	mlx5e_free_xdpsq_descs(sq);
 	mlx5e_free_xdpsq(sq);
 }
 
@@ -1722,6 +1559,7 @@ static void mlx5e_free_cq(struct mlx5e_cq *cq)
 
 static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 {
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	struct mlx5_core_dev *mdev = cq->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 
@@ -1756,7 +1594,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
 
-	err = mlx5_core_create_cq(mdev, mcq, in, inlen);
+	err = mlx5_core_create_cq(mdev, mcq, in, inlen, out, sizeof(out));
 
 	kvfree(in);
 
@@ -1773,10 +1611,8 @@ static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
 	mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
 }
 
-static int mlx5e_open_cq(struct mlx5e_channel *c,
-			 struct net_dim_cq_moder moder,
-			 struct mlx5e_cq_param *param,
-			 struct mlx5e_cq *cq)
+int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder,
+		  struct mlx5e_cq_param *param, struct mlx5e_cq *cq)
 {
 	struct mlx5_core_dev *mdev = c->mdev;
 	int err;
@@ -1799,7 +1635,7 @@ err_free_cq:
 	return err;
 }
 
-static void mlx5e_close_cq(struct mlx5e_cq *cq)
+void mlx5e_close_cq(struct mlx5e_cq *cq)
 {
 	mlx5e_destroy_cq(cq);
 	mlx5e_free_cq(cq);
@@ -1950,46 +1786,39 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	return err;
 }
 
-static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
-			      struct mlx5e_params *params,
-			      struct mlx5e_channel_param *cparam,
-			      struct mlx5e_channel **cp)
+static int mlx5e_alloc_xps_cpumask(struct mlx5e_channel *c,
+				   struct mlx5e_params *params)
 {
-	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
-	struct net_dim_cq_moder icocq_moder = {0, 0};
-	struct net_device *netdev = priv->netdev;
-	struct mlx5e_channel *c;
-	unsigned int irq;
-	int err;
-	int eqn;
-
-	err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
-	if (err)
-		return err;
+	int num_comp_vectors = mlx5_comp_vectors_count(c->mdev);
+	int irq;
 
-	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
-	if (!c)
+	if (!zalloc_cpumask_var(&c->xps_cpumask, GFP_KERNEL))
 		return -ENOMEM;
 
-	c->priv     = priv;
-	c->mdev     = priv->mdev;
-	c->tstamp   = &priv->tstamp;
-	c->ix       = ix;
-	c->cpu      = cpu;
-	c->pdev     = &priv->mdev->pdev->dev;
-	c->netdev   = priv->netdev;
-	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
-	c->num_tc   = params->num_tc;
-	c->xdp      = !!params->xdp_prog;
-	c->stats    = &priv->channel_stats[ix].ch;
+	for (irq = c->ix; irq < num_comp_vectors; irq += params->num_channels) {
+		int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(c->mdev, irq));
 
-	c->irq_desc = irq_to_desc(irq);
+		cpumask_set_cpu(cpu, c->xps_cpumask);
+	}
 
-	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
+	return 0;
+}
+
+static void mlx5e_free_xps_cpumask(struct mlx5e_channel *c)
+{
+	free_cpumask_var(c->xps_cpumask);
+}
+
+static int mlx5e_open_queues(struct mlx5e_channel *c,
+			     struct mlx5e_params *params,
+			     struct mlx5e_channel_param *cparam)
+{
+	struct dim_cq_moder icocq_moder = {0, 0};
+	int err;
 
 	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
 	if (err)
-		goto err_napi_del;
+		return err;
 
 	err = mlx5e_open_tx_cqs(c, params, cparam);
 	if (err)
@@ -2005,7 +1834,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 
 	/* XDP SQ CQ params are same as normal TXQ sq CQ params */
 	err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
-				     &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
+				     &cparam->tx_cq, &c->rq_xdpsq.cq) : 0;
 	if (err)
 		goto err_close_rx_cq;
 
@@ -2019,20 +1848,21 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq;
 
-	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0;
-	if (err)
-		goto err_close_sqs;
+	if (c->xdp) {
+		err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL,
+				       &c->rq_xdpsq, false);
+		if (err)
+			goto err_close_sqs;
+	}
 
-	err = mlx5e_open_rq(c, params, &cparam->rq, &c->rq);
+	err = mlx5e_open_rq(c, params, &cparam->rq, NULL, NULL, &c->rq);
 	if (err)
 		goto err_close_xdp_sq;
 
-	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true);
+	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->xdpsq, true);
 	if (err)
 		goto err_close_rq;
 
-	*cp = c;
-
 	return 0;
 
 err_close_rq:
@@ -2040,7 +1870,7 @@ err_close_rq:
 
 err_close_xdp_sq:
 	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
+		mlx5e_close_xdpsq(&c->rq_xdpsq);
 
 err_close_sqs:
 	mlx5e_close_sqs(c);
@@ -2050,8 +1880,9 @@ err_close_icosq:
 
 err_disable_napi:
 	napi_disable(&c->napi);
+
 	if (c->xdp)
-		mlx5e_close_cq(&c->rq.xdpsq.cq);
+		mlx5e_close_cq(&c->rq_xdpsq.cq);
 
 err_close_rx_cq:
 	mlx5e_close_cq(&c->rq.cq);
@@ -2065,8 +1896,90 @@ err_close_tx_cqs:
 err_close_icosq_cq:
 	mlx5e_close_cq(&c->icosq.cq);
 
+	return err;
+}
+
+static void mlx5e_close_queues(struct mlx5e_channel *c)
+{
+	mlx5e_close_xdpsq(&c->xdpsq);
+	mlx5e_close_rq(&c->rq);
+	if (c->xdp)
+		mlx5e_close_xdpsq(&c->rq_xdpsq);
+	mlx5e_close_sqs(c);
+	mlx5e_close_icosq(&c->icosq);
+	napi_disable(&c->napi);
+	if (c->xdp)
+		mlx5e_close_cq(&c->rq_xdpsq.cq);
+	mlx5e_close_cq(&c->rq.cq);
+	mlx5e_close_cq(&c->xdpsq.cq);
+	mlx5e_close_tx_cqs(c);
+	mlx5e_close_cq(&c->icosq.cq);
+}
+
+static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
+			      struct mlx5e_params *params,
+			      struct mlx5e_channel_param *cparam,
+			      struct xdp_umem *umem,
+			      struct mlx5e_channel **cp)
+{
+	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
+	struct net_device *netdev = priv->netdev;
+	struct mlx5e_xsk_param xsk;
+	struct mlx5e_channel *c;
+	unsigned int irq;
+	int err;
+	int eqn;
+
+	err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq);
+	if (err)
+		return err;
+
+	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	if (!c)
+		return -ENOMEM;
+
+	c->priv     = priv;
+	c->mdev     = priv->mdev;
+	c->tstamp   = &priv->tstamp;
+	c->ix       = ix;
+	c->cpu      = cpu;
+	c->pdev     = priv->mdev->device;
+	c->netdev   = priv->netdev;
+	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
+	c->num_tc   = params->num_tc;
+	c->xdp      = !!params->xdp_prog;
+	c->stats    = &priv->channel_stats[ix].ch;
+	c->irq_desc = irq_to_desc(irq);
+
+	err = mlx5e_alloc_xps_cpumask(c, params);
+	if (err)
+		goto err_free_channel;
+
+	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
+
+	err = mlx5e_open_queues(c, params, cparam);
+	if (unlikely(err))
+		goto err_napi_del;
+
+	if (umem) {
+		mlx5e_build_xsk_param(umem, &xsk);
+		err = mlx5e_open_xsk(priv, params, &xsk, umem, c);
+		if (unlikely(err))
+			goto err_close_queues;
+	}
+
+	*cp = c;
+
+	return 0;
+
+err_close_queues:
+	mlx5e_close_queues(c);
+
 err_napi_del:
 	netif_napi_del(&c->napi);
+	mlx5e_free_xps_cpumask(c);
+
+err_free_channel:
 	kvfree(c);
 
 	return err;
@@ -2079,13 +1992,19 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+	netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix);
+
+	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		mlx5e_activate_xsk(c);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 {
 	int tc;
 
+	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		mlx5e_deactivate_xsk(c);
+
 	mlx5e_deactivate_rq(&c->rq);
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_deactivate_txqsq(&c->sq[tc]);
@@ -2093,20 +2012,11 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
-	mlx5e_close_xdpsq(&c->xdpsq, NULL);
-	mlx5e_close_rq(&c->rq);
-	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
-	mlx5e_close_sqs(c);
-	mlx5e_close_icosq(&c->icosq);
-	napi_disable(&c->napi);
-	if (c->xdp)
-		mlx5e_close_cq(&c->rq.xdpsq.cq);
-	mlx5e_close_cq(&c->rq.cq);
-	mlx5e_close_cq(&c->xdpsq.cq);
-	mlx5e_close_tx_cqs(c);
-	mlx5e_close_cq(&c->icosq.cq);
+	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+		mlx5e_close_xsk(c);
+	mlx5e_close_queues(c);
 	netif_napi_del(&c->napi);
+	mlx5e_free_xps_cpumask(c);
 
 	kvfree(c);
 }
@@ -2115,6 +2025,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 
 static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
 				      struct mlx5e_params *params,
+				      struct mlx5e_xsk_param *xsk,
 				      struct mlx5e_rq_frags_info *info)
 {
 	u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu);
@@ -2127,10 +2038,10 @@ static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev,
 		byte_count += MLX5E_METADATA_ETHER_LEN;
 #endif
 
-	if (mlx5e_rx_is_linear_skb(mdev, params)) {
+	if (mlx5e_rx_is_linear_skb(params, xsk)) {
 		int frag_stride;
 
-		frag_stride = mlx5e_rx_get_linear_frag_sz(params);
+		frag_stride = mlx5e_rx_get_linear_frag_sz(params, xsk);
 		frag_stride = roundup_pow_of_two(frag_stride);
 
 		info->arr[0].frag_size = byte_count;
@@ -2181,9 +2092,17 @@ static inline u8 mlx5e_get_rqwq_log_stride(u8 wq_type, int ndsegs)
 	return order_base_2(sz);
 }
 
-static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
-				 struct mlx5e_params *params,
-				 struct mlx5e_rq_param *param)
+static u8 mlx5e_get_rq_log_wq_sz(void *rqc)
+{
+	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+
+	return MLX5_GET(wq, wq, log_wq_sz);
+}
+
+void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+			  struct mlx5e_params *params,
+			  struct mlx5e_xsk_param *xsk,
+			  struct mlx5e_rq_param *param)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *rqc = param->rqc;
@@ -2193,16 +2112,16 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
 		MLX5_SET(wq, wq, log_wqe_num_of_strides,
-			 mlx5e_mpwqe_get_log_num_strides(mdev, params) -
+			 mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk) -
 			 MLX5_MPWQE_LOG_NUM_STRIDES_BASE);
 		MLX5_SET(wq, wq, log_wqe_stride_size,
-			 mlx5e_mpwqe_get_log_stride_size(mdev, params) -
+			 mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk) -
 			 MLX5_MPWQE_LOG_STRIDE_SZ_BASE);
-		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params));
+		MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params, xsk));
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames);
-		mlx5e_build_rq_frags_info(mdev, params, &param->frags_info);
+		mlx5e_build_rq_frags_info(mdev, params, xsk, &param->frags_info);
 		ndsegs = param->frags_info.num_frags;
 	}
 
@@ -2215,7 +2134,7 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
 	MLX5_SET(rqc, rqc, vsd,            params->vlan_strip_disable);
 	MLX5_SET(rqc, rqc, scatter_fcs,    params->scatter_fcs_en);
 
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mdev->device);
 }
 
 static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
@@ -2230,11 +2149,11 @@ static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv,
 		 mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1));
 	MLX5_SET(rqc, rqc, counter_set_id, priv->drop_rq_q_counter);
 
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mdev->device);
 }
 
-static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
-					struct mlx5e_sq_param *param)
+void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
+				 struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -2242,7 +2161,7 @@ static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv,
 	MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
 	MLX5_SET(wq, wq, pd,            priv->mdev->mlx5e_res.pdn);
 
-	param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(priv->mdev->device);
 }
 
 static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
@@ -2251,10 +2170,13 @@ static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+	bool allow_swp;
 
+	allow_swp = mlx5_geneve_tx_allowed(priv->mdev) ||
+		    !!MLX5_IPSEC_DEV(priv->mdev);
 	mlx5e_build_sq_param_common(priv, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
-	MLX5_SET(sqc, sqc, allow_swp, !!MLX5_IPSEC_DEV(priv->mdev));
+	MLX5_SET(sqc, sqc, allow_swp, allow_swp);
 }
 
 static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
@@ -2267,9 +2189,10 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
 		MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);
 }
 
-static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_params *params,
-				    struct mlx5e_cq_param *param)
+void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_xsk_param *xsk,
+			     struct mlx5e_cq_param *param)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	void *cqc = param->cqc;
@@ -2277,8 +2200,8 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 
 	switch (params->rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) +
-			mlx5e_mpwqe_get_log_num_strides(mdev, params);
+		log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) +
+			mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		log_cq_size = params->log_rq_mtu_frames;
@@ -2294,9 +2217,9 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
 	param->cq_period_mode = params->rx_cq_moderation.cq_period_mode;
 }
 
-static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_params *params,
-				    struct mlx5e_cq_param *param)
+void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
@@ -2306,9 +2229,9 @@ static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
 	param->cq_period_mode = params->tx_cq_moderation.cq_period_mode;
 }
 
-static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
-				     u8 log_wq_size,
-				     struct mlx5e_cq_param *param)
+void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
+			      u8 log_wq_size,
+			      struct mlx5e_cq_param *param)
 {
 	void *cqc = param->cqc;
 
@@ -2316,12 +2239,12 @@ static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv,
 
 	mlx5e_build_common_cq_param(priv, param);
 
-	param->cq_period_mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+	param->cq_period_mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
-static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
-				    u8 log_wq_size,
-				    struct mlx5e_sq_param *param)
+void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
+			     u8 log_wq_size,
+			     struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -2332,9 +2255,9 @@ static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
 	MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
 }
 
-static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
-				    struct mlx5e_params *params,
-				    struct mlx5e_sq_param *param)
+void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
+			     struct mlx5e_params *params,
+			     struct mlx5e_sq_param *param)
 {
 	void *sqc = param->sqc;
 	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
@@ -2344,17 +2267,32 @@ static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
 	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
 }
 
+static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params,
+				      struct mlx5e_rq_param *rqp)
+{
+	switch (params->rq_wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		return order_base_2(MLX5E_UMR_WQEBBS) +
+			mlx5e_get_rq_log_wq_sz(rqp->rqc);
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	}
+}
+
 static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
 				      struct mlx5e_params *params,
 				      struct mlx5e_channel_param *cparam)
 {
-	u8 icosq_log_wq_sz = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
+	u8 icosq_log_wq_sz;
+
+	mlx5e_build_rq_param(priv, params, NULL, &cparam->rq);
+
+	icosq_log_wq_sz = mlx5e_build_icosq_log_wq_sz(params, &cparam->rq);
 
-	mlx5e_build_rq_param(priv, params, &cparam->rq);
 	mlx5e_build_sq_param(priv, params, &cparam->sq);
 	mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
 	mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
-	mlx5e_build_rx_cq_param(priv, params, &cparam->rx_cq);
+	mlx5e_build_rx_cq_param(priv, params, NULL, &cparam->rx_cq);
 	mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq);
 	mlx5e_build_ico_cq_param(priv, icosq_log_wq_sz, &cparam->icosq_cq);
 }
@@ -2375,11 +2313,20 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 
 	mlx5e_build_channel_param(priv, &chs->params, cparam);
 	for (i = 0; i < chs->num; i++) {
-		err = mlx5e_open_channel(priv, i, &chs->params, cparam, &chs->c[i]);
+		struct xdp_umem *umem = NULL;
+
+		if (chs->params.xdp_prog)
+			umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, i);
+
+		err = mlx5e_open_channel(priv, i, &chs->params, cparam, umem, &chs->c[i]);
 		if (err)
 			goto err_close_channels;
 	}
 
+	if (!IS_ERR_OR_NULL(priv->tx_reporter))
+		devlink_health_reporter_state_update(priv->tx_reporter,
+						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+
 	kvfree(cparam);
 	return 0;
 
@@ -2402,14 +2349,22 @@ static void mlx5e_activate_channels(struct mlx5e_channels *chs)
 		mlx5e_activate_channel(chs->c[i]);
 }
 
+#define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */
+
 static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs)
 {
 	int err = 0;
 	int i;
 
-	for (i = 0; i < chs->num; i++)
-		err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq,
-						  err ? 0 : 20000);
+	for (i = 0; i < chs->num; i++) {
+		int timeout = err ? 0 : MLX5E_RQ_WQES_TIMEOUT;
+
+		err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq, timeout);
+
+		/* Don't wait on the XSK RQ, because the newer xdpsock sample
+		 * doesn't provide any Fill Ring entries at the setup stage.
+		 */
+	}
 
 	return err ? -ETIMEDOUT : 0;
 }
@@ -2481,35 +2436,35 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv)
 	return err;
 }
 
-int mlx5e_create_direct_rqts(struct mlx5e_priv *priv)
+int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
-	struct mlx5e_rqt *rqt;
+	const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
 	int err;
 	int ix;
 
-	for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) {
-		rqt = &priv->direct_tir[ix].rqt;
-		err = mlx5e_create_rqt(priv, 1 /*size */, rqt);
-		if (err)
+	for (ix = 0; ix < max_nch; ix++) {
+		err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt);
+		if (unlikely(err))
 			goto err_destroy_rqts;
 	}
 
 	return 0;
 
 err_destroy_rqts:
-	mlx5_core_warn(priv->mdev, "create direct rqts failed, %d\n", err);
+	mlx5_core_warn(priv->mdev, "create rqts failed, %d\n", err);
 	for (ix--; ix >= 0; ix--)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt);
+		mlx5e_destroy_rqt(priv, &tirs[ix].rqt);
 
 	return err;
 }
 
-void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv)
+void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
+	const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
 	int i;
 
-	for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++)
-		mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt);
+	for (i = 0; i < max_nch; i++)
+		mlx5e_destroy_rqt(priv, &tirs[i].rqt);
 }
 
 static int mlx5e_rx_hash_fn(int hfunc)
@@ -2706,7 +2661,7 @@ static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
 		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
-		 (params->lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
 }
 
@@ -2816,22 +2771,6 @@ free_in:
 	return err;
 }
 
-static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
-					    enum mlx5e_traffic_types tt,
-					    u32 *tirc)
-{
-	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
-
-	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
-
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	MLX5_SET(tirc, tirc, tunneled_offload_en, 0x1);
-
-	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
-				       &tirc_default_config[tt], tirc, true);
-}
-
 static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params, u16 mtu)
 {
@@ -2881,6 +2820,21 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 	return 0;
 }
 
+void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv)
+{
+	struct mlx5e_params *params = &priv->channels.params;
+	struct net_device *netdev   = priv->netdev;
+	struct mlx5_core_dev *mdev  = priv->mdev;
+	u16 max_mtu;
+
+	/* MTU range: 68 - hw-specific max */
+	netdev->min_mtu = ETH_MIN_MTU;
+
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->max_mtu = min_t(unsigned int, MLX5E_HW2SW_MTU(params, max_mtu),
+				ETH_MAX_MTU);
+}
+
 static void mlx5e_netdev_set_tcs(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -2930,14 +2884,16 @@ static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv)
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 {
 	int num_txqs = priv->channels.num * priv->channels.params.num_tc;
+	int num_rxqs = priv->channels.num * MLX5E_NUM_RQ_GROUPS;
 	struct net_device *netdev = priv->netdev;
 
 	mlx5e_netdev_set_tcs(netdev);
 	netif_set_real_num_tx_queues(netdev, num_txqs);
-	netif_set_real_num_rx_queues(netdev, priv->channels.num);
+	netif_set_real_num_rx_queues(netdev, num_rxqs);
 
 	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
+	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
 
 	if (mlx5e_is_vport_rep(priv))
@@ -2945,10 +2901,14 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
 	mlx5e_redirect_rqts_to_channels(priv, &priv->channels);
+
+	mlx5e_xsk_redirect_rqts_to_channels(priv, &priv->channels);
 }
 
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
+	mlx5e_xsk_redirect_rqts_to_drop(priv, &priv->channels);
+
 	mlx5e_redirect_rqts_to_drop(priv);
 
 	if (mlx5e_is_vport_rep(priv))
@@ -2959,16 +2919,18 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	 */
 	netif_tx_stop_all_queues(priv->netdev);
 	netif_tx_disable(priv->netdev);
+	mlx5e_xdp_tx_disable(priv);
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
-void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
-				struct mlx5e_channels *new_chs,
-				mlx5e_fp_hw_modify hw_modify)
+static void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				       struct mlx5e_channels *new_chs,
+				       mlx5e_fp_hw_modify hw_modify)
 {
 	struct net_device *netdev = priv->netdev;
 	int new_num_txqs;
 	int carrier_ok;
+
 	new_num_txqs = new_chs->num * new_chs->params.num_tc;
 
 	carrier_ok = netif_carrier_ok(netdev);
@@ -2986,7 +2948,7 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 	if (hw_modify)
 		hw_modify(priv);
 
-	mlx5e_refresh_tirs(priv, false);
+	priv->profile->update_rx(priv);
 	mlx5e_activate_priv_channels(priv);
 
 	/* return carrier back if needed */
@@ -2994,6 +2956,28 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 		netif_carrier_on(netdev);
 }
 
+int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
+			       struct mlx5e_channels *new_chs,
+			       mlx5e_fp_hw_modify hw_modify)
+{
+	int err;
+
+	err = mlx5e_open_channels(priv, new_chs);
+	if (err)
+		return err;
+
+	mlx5e_switch_priv_channels(priv, new_chs, hw_modify);
+	return 0;
+}
+
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channels new_channels = {};
+
+	new_channels.params = priv->channels.params;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+}
+
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 {
 	priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
@@ -3003,15 +2987,18 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 int mlx5e_open_locked(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	bool is_xdp = priv->channels.params.xdp_prog;
 	int err;
 
 	set_bit(MLX5E_STATE_OPENED, &priv->state);
+	if (is_xdp)
+		mlx5e_xdp_set_open(priv);
 
 	err = mlx5e_open_channels(priv, &priv->channels);
 	if (err)
 		goto err_clear_state_opened_flag;
 
-	mlx5e_refresh_tirs(priv, false);
+	priv->profile->update_rx(priv);
 	mlx5e_activate_priv_channels(priv);
 	if (priv->profile->update_carrier)
 		priv->profile->update_carrier(priv);
@@ -3020,6 +3007,8 @@ int mlx5e_open_locked(struct net_device *netdev)
 	return 0;
 
 err_clear_state_opened_flag:
+	if (is_xdp)
+		mlx5e_xdp_set_closed(priv);
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 	return err;
 }
@@ -3051,6 +3040,8 @@ int mlx5e_close_locked(struct net_device *netdev)
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return 0;
 
+	if (priv->channels.params.xdp_prog)
+		mlx5e_xdp_set_closed(priv);
 	clear_bit(MLX5E_STATE_OPENED, &priv->state);
 
 	netif_carrier_off(priv->netdev);
@@ -3103,8 +3094,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
 			       struct mlx5e_cq *cq,
 			       struct mlx5e_cq_param *param)
 {
-	param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev);
-	param->wq.db_numa_node  = dev_to_node(&mdev->pdev->dev);
+	param->wq.buf_numa_node = dev_to_node(mdev->device);
+	param->wq.db_numa_node  = dev_to_node(mdev->device);
 
 	return mlx5e_alloc_cq_common(mdev, param, cq);
 }
@@ -3162,20 +3153,19 @@ void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
 	mlx5e_free_cq(&drop_rq->cq);
 }
 
-int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
-		     u32 underlay_qpn, u32 *tisn)
+int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn)
 {
-	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {0};
 	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
 
-	MLX5_SET(tisc, tisc, prio, tc << 1);
-	MLX5_SET(tisc, tisc, underlay_qpn, underlay_qpn);
 	MLX5_SET(tisc, tisc, transport_domain, mdev->mlx5e_res.td.tdn);
 
+	if (MLX5_GET(tisc, tisc, tls_en))
+		MLX5_SET(tisc, tisc, pd, mdev->mlx5e_res.pdn);
+
 	if (mlx5_lag_is_lacp_owner(mdev))
 		MLX5_SET(tisc, tisc, strict_lag_tx_port_affinity, 1);
 
-	return mlx5_core_create_tis(mdev, in, sizeof(in), tisn);
+	return mlx5_core_create_tis(mdev, in, MLX5_ST_SZ_BYTES(create_tis_in), tisn);
 }
 
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn)
@@ -3189,7 +3179,14 @@ int mlx5e_create_tises(struct mlx5e_priv *priv)
 	int tc;
 
 	for (tc = 0; tc < priv->profile->max_tc; tc++) {
-		err = mlx5e_create_tis(priv->mdev, tc, 0, &priv->tisn[tc]);
+		u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+		void *tisc;
+
+		tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+		MLX5_SET(tisc, tisc, prio, tc << 1);
+
+		err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[tc]);
 		if (err)
 			goto err_close_tises;
 	}
@@ -3207,36 +3204,47 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
 	int tc;
 
+	mlx5e_tx_reporter_destroy(priv);
 	for (tc = 0; tc < priv->profile->max_tc; tc++)
 		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 }
 
-static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
-				      enum mlx5e_traffic_types tt,
-				      u32 *tirc)
+static void mlx5e_build_indir_tir_ctx_common(struct mlx5e_priv *priv,
+					     u32 rqtn, u32 *tirc)
 {
 	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
+	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
+	MLX5_SET(tirc, tirc, indirect_table, rqtn);
+	MLX5_SET(tirc, tirc, tunneled_offload_en,
+		 priv->channels.params.tunneled_offload_en);
 
 	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
+}
 
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-
+static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
+				      enum mlx5e_traffic_types tt,
+				      u32 *tirc)
+{
+	mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc);
 	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
 				       &tirc_default_config[tt], tirc, false);
 }
 
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
 {
-	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
-
-	mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc);
-
-	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
-	MLX5_SET(tirc, tirc, indirect_table, rqtn);
+	mlx5e_build_indir_tir_ctx_common(priv, rqtn, tirc);
 	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
 }
 
+static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
+					    enum mlx5e_traffic_types tt,
+					    u32 *tirc)
+{
+	mlx5e_build_indir_tir_ctx_common(priv, priv->indir_rqt.rqtn, tirc);
+	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
+				       &tirc_default_config[tt], tirc, true);
+}
+
 int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
 {
 	struct mlx5e_tir *tir;
@@ -3296,13 +3304,13 @@ err_destroy_inner_tirs:
 	return err;
 }
 
-int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
+int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
-	int nch = mlx5e_get_netdev_max_channels(priv->netdev);
+	const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
 	struct mlx5e_tir *tir;
 	void *tirc;
 	int inlen;
-	int err;
+	int err = 0;
 	u32 *in;
 	int ix;
 
@@ -3311,25 +3319,24 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv)
 	if (!in)
 		return -ENOMEM;
 
-	for (ix = 0; ix < nch; ix++) {
+	for (ix = 0; ix < max_nch; ix++) {
 		memset(in, 0, inlen);
-		tir = &priv->direct_tir[ix];
+		tir = &tirs[ix];
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
-		mlx5e_build_direct_tir_ctx(priv, priv->direct_tir[ix].rqt.rqtn, tirc);
+		mlx5e_build_direct_tir_ctx(priv, tir->rqt.rqtn, tirc);
 		err = mlx5e_create_tir(priv->mdev, tir, in, inlen);
-		if (err)
+		if (unlikely(err))
 			goto err_destroy_ch_tirs;
 	}
 
-	kvfree(in);
-
-	return 0;
+	goto out;
 
 err_destroy_ch_tirs:
-	mlx5_core_warn(priv->mdev, "create direct tirs failed, %d\n", err);
+	mlx5_core_warn(priv->mdev, "create tirs failed, %d\n", err);
 	for (ix--; ix >= 0; ix--)
-		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[ix]);
+		mlx5e_destroy_tir(priv->mdev, &tirs[ix]);
 
+out:
 	kvfree(in);
 
 	return err;
@@ -3349,13 +3356,13 @@ void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc)
 		mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]);
 }
 
-void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv)
+void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
 {
-	int nch = mlx5e_get_netdev_max_channels(priv->netdev);
+	const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
 	int i;
 
-	for (i = 0; i < nch; i++)
-		mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]);
+	for (i = 0; i < max_nch; i++)
+		mlx5e_destroy_tir(priv->mdev, &tirs[i]);
 }
 
 static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
@@ -3386,10 +3393,9 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
 	return 0;
 }
 
-static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
+static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 				 struct tc_mqprio_qopt *mqprio)
 {
-	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_channels new_channels = {};
 	u8 tc = mqprio->num_tc;
 	int err = 0;
@@ -3409,13 +3415,12 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 	if (err)
 		goto out;
 
 	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
 				    new_channels.params.num_tc);
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3423,17 +3428,17 @@ out:
 
 #ifdef CONFIG_MLX5_ESWITCH
 static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
-				     struct tc_cls_flower_offload *cls_flower,
+				     struct flow_cls_offload *cls_flower,
 				     int flags)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
 					      flags);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
 					   flags);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
 					  flags);
 	default:
@@ -3454,49 +3459,57 @@ static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 		return -EOPNOTSUPP;
 	}
 }
-
-static int mlx5e_setup_tc_block(struct net_device *dev,
-				struct tc_block_offload *f)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
-					     priv, priv, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
-					priv);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
 #endif
 
+static LIST_HEAD(mlx5e_block_cb_list);
+
 static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			  void *type_data)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
 	switch (type) {
 #ifdef CONFIG_MLX5_ESWITCH
 	case TC_SETUP_BLOCK:
-		return mlx5e_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &mlx5e_block_cb_list,
+						  mlx5e_setup_tc_block_cb,
+						  priv, priv, true);
 #endif
 	case TC_SETUP_QDISC_MQPRIO:
-		return mlx5e_setup_tc_mqprio(dev, type_data);
+		return mlx5e_setup_tc_mqprio(priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
+void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
+{
+	int i;
+
+	for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) {
+		struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
+		struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
+		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
+		int j;
+
+		s->rx_packets   += rq_stats->packets + xskrq_stats->packets;
+		s->rx_bytes     += rq_stats->bytes + xskrq_stats->bytes;
+
+		for (j = 0; j < priv->max_opened_tc; j++) {
+			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
+
+			s->tx_packets    += sq_stats->packets;
+			s->tx_bytes      += sq_stats->bytes;
+			s->tx_dropped    += sq_stats->dropped;
+		}
+	}
+}
+
 void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sw_stats *sstats = &priv->stats.sw;
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
@@ -3511,12 +3524,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
 		stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
 	} else {
-		mlx5e_grp_sw_update_stats(priv);
-		stats->rx_packets = sstats->rx_packets;
-		stats->rx_bytes   = sstats->rx_bytes;
-		stats->tx_packets = sstats->tx_packets;
-		stats->tx_bytes   = sstats->tx_bytes;
-		stats->tx_dropped = sstats->tx_queue_dropped;
+		mlx5e_fold_sw_stats64(priv, stats);
 	}
 
 	stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer;
@@ -3585,6 +3593,13 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 
 	mutex_lock(&priv->state_lock);
 
+	if (enable && priv->xsk.refcnt) {
+		netdev_warn(netdev, "LRO is incompatible with AF_XDP (%hu XSKs are active)\n",
+			    priv->xsk.refcnt);
+		err = -EINVAL;
+		goto out;
+	}
+
 	old_params = &priv->channels.params;
 	if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) {
 		netdev_warn(netdev, "can't set LRO with legacy RQ\n");
@@ -3598,8 +3613,8 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 	new_channels.params.lro_en = enable;
 
 	if (old_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) {
-		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) ==
-		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params))
+		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params, NULL) ==
+		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params, NULL))
 			reset = false;
 	}
 
@@ -3609,11 +3624,7 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3731,8 +3742,7 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 	return 0;
 }
 
-static int mlx5e_set_features(struct net_device *netdev,
-			      netdev_features_t features)
+int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	netdev_features_t oper_features = netdev->features;
 	int err = 0;
@@ -3783,11 +3793,54 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 			netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n");
 	}
 
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) {
+		features &= ~NETIF_F_RXHASH;
+		if (netdev->features & NETIF_F_RXHASH)
+			netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n");
+	}
+
 	mutex_unlock(&priv->state_lock);
 
 	return features;
 }
 
+static bool mlx5e_xsk_validate_mtu(struct net_device *netdev,
+				   struct mlx5e_channels *chs,
+				   struct mlx5e_params *new_params,
+				   struct mlx5_core_dev *mdev)
+{
+	u16 ix;
+
+	for (ix = 0; ix < chs->params.num_channels; ix++) {
+		struct xdp_umem *umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, ix);
+		struct mlx5e_xsk_param xsk;
+
+		if (!umem)
+			continue;
+
+		mlx5e_build_xsk_param(umem, &xsk);
+
+		if (!mlx5e_validate_xsk_param(new_params, &xsk, mdev)) {
+			u32 hr = mlx5e_get_linear_rq_headroom(new_params, &xsk);
+			int max_mtu_frame, max_mtu_page, max_mtu;
+
+			/* Two criteria must be met:
+			 * 1. HW MTU + all headrooms <= XSK frame size.
+			 * 2. Size of SKBs allocated on XDP_PASS <= PAGE_SIZE.
+			 */
+			max_mtu_frame = MLX5E_HW2SW_MTU(new_params, xsk.chunk_size - hr);
+			max_mtu_page = mlx5e_xdp_max_mtu(new_params, &xsk);
+			max_mtu = min(max_mtu_frame, max_mtu_page);
+
+			netdev_err(netdev, "MTU %d is too big for an XSK running on channel %hu. Try MTU <= %d\n",
+				   new_params->sw_mtu, ix, max_mtu);
+			return false;
+		}
+	}
+
+	return true;
+}
+
 int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		     change_hw_mtu_cb set_mtu_cb)
 {
@@ -3808,18 +3861,31 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	new_channels.params.sw_mtu = new_mtu;
 
 	if (params->xdp_prog &&
-	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+	    !mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) {
 		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
-			   new_mtu, MLX5E_XDP_MAX_MTU);
+			   new_mtu, mlx5e_xdp_max_mtu(params, NULL));
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (priv->xsk.refcnt &&
+	    !mlx5e_xsk_validate_mtu(netdev, &priv->channels,
+				    &new_channels.params, priv->mdev)) {
 		err = -EINVAL;
 		goto out;
 	}
 
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, &new_channels.params);
-		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
-		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
+		bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev,
+							      &new_channels.params,
+							      NULL);
+		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params, NULL);
+		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params, NULL);
+
+		/* If XSK is active, XSK RQs are linear. */
+		is_linear |= priv->xsk.refcnt;
 
+		/* Always reset in linear mode - hw_mtu is used in data path. */
 		reset = reset && (is_linear || (ppw_old != ppw_new));
 	}
 
@@ -3831,11 +3897,10 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, set_mtu_cb);
 	if (err)
 		goto out;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb);
 	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
@@ -3909,6 +3974,9 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	memcpy(&priv->tstamp, &config, sizeof(config));
 	mutex_unlock(&priv->state_lock);
 
+	/* might need to fix some features */
+	netdev_update_features(priv->netdev);
+
 	return copy_to_user(ifr->ifr_data, &config,
 			    sizeof(config)) ? -EFAULT : 0;
 }
@@ -4149,6 +4217,12 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		/* Verify if UDP port is being offloaded by HW */
 		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port))
 			return features;
+
+#if IS_ENABLED(CONFIG_GENEVE)
+		/* Support Geneve offload for default UDP port */
+		if (port == GENEVE_UDP_PORT && mlx5_geneve_tx_allowed(priv->mdev))
+			return features;
+#endif
 	}
 
 out:
@@ -4178,31 +4252,13 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
-static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
-					struct mlx5e_txqsq *sq)
-{
-	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
-	u32 eqe_count;
-
-	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
-
-	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	if (!eqe_count)
-		return false;
-
-	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn);
-	sq->channel->stats->eq_rearm++;
-	return true;
-}
-
 static void mlx5e_tx_timeout_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
 					       tx_timeout_work);
-	struct net_device *dev = priv->netdev;
-	bool reopen_channels = false;
-	int i, err;
+	bool report_failed = false;
+	int err;
+	int i;
 
 	rtnl_lock();
 	mutex_lock(&priv->state_lock);
@@ -4211,34 +4267,24 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 		goto unlock;
 
 	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
-		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i);
+		struct netdev_queue *dev_queue =
+			netdev_get_tx_queue(priv->netdev, i);
 		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
 		if (!netif_xmit_stopped(dev_queue))
 			continue;
 
-		netdev_err(dev,
-			   "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
-			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
-			   jiffies_to_usecs(jiffies - dev_queue->trans_start));
-
-		/* If we recover a lost interrupt, most likely TX timeout will
-		 * be resolved, skip reopening channels
-		 */
-		if (!mlx5e_tx_timeout_eq_recover(dev, sq)) {
-			clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-			reopen_channels = true;
-		}
+		if (mlx5e_tx_reporter_timeout(sq))
+			report_failed = true;
 	}
 
-	if (!reopen_channels)
+	if (!report_failed)
 		goto unlock;
 
-	mlx5e_close_locked(dev);
-	err = mlx5e_open_locked(dev);
+	err = mlx5e_safe_reopen_channels(priv);
 	if (err)
 		netdev_err(priv->netdev,
-			   "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n",
 			   err);
 
 unlock:
@@ -4272,15 +4318,29 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	new_channels.params = priv->channels.params;
 	new_channels.params.xdp_prog = prog;
 
-	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+	/* No XSK params: AF_XDP can't be enabled yet at the point of setting
+	 * the XDP program.
+	 */
+	if (!mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) {
 		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
-			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+			    new_channels.params.sw_mtu,
+			    mlx5e_xdp_max_mtu(&new_channels.params, NULL));
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
+static int mlx5e_xdp_update_state(struct mlx5e_priv *priv)
+{
+	if (priv->channels.params.xdp_prog)
+		mlx5e_xdp_set_open(priv);
+	else
+		mlx5e_xdp_set_closed(priv);
+
+	return 0;
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4301,8 +4361,6 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* no need for full reset when exchanging programs */
 	reset = (!priv->channels.params.xdp_prog || !prog);
 
-	if (was_opened && reset)
-		mlx5e_close_locked(netdev);
 	if (was_opened && !reset) {
 		/* num_channels is invariant here, so we can take the
 		 * batched reference right upfront.
@@ -4314,20 +4372,31 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 		}
 	}
 
-	/* exchange programs, extra prog reference we got from caller
-	 * as long as we don't fail from this point onwards.
-	 */
-	old_prog = xchg(&priv->channels.params.xdp_prog, prog);
+	if (was_opened && reset) {
+		struct mlx5e_channels new_channels = {};
+
+		new_channels.params = priv->channels.params;
+		new_channels.params.xdp_prog = prog;
+		mlx5e_set_rq_type(priv->mdev, &new_channels.params);
+		old_prog = priv->channels.params.xdp_prog;
+
+		err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_xdp_update_state);
+		if (err)
+			goto unlock;
+	} else {
+		/* exchange programs, extra prog reference we got from caller
+		 * as long as we don't fail from this point onwards.
+		 */
+		old_prog = xchg(&priv->channels.params.xdp_prog, prog);
+	}
+
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
-	if (reset) /* change RQ type according to priv->xdp_prog */
+	if (!was_opened && reset) /* change RQ type according to priv->xdp_prog */
 		mlx5e_set_rq_type(priv->mdev, &priv->channels.params);
 
-	if (was_opened && reset)
-		mlx5e_open_locked(netdev);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
+	if (!was_opened || reset)
 		goto unlock;
 
 	/* exchanging programs w/o reset, we update ref counts on behalf
@@ -4335,19 +4404,29 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	 */
 	for (i = 0; i < priv->channels.num; i++) {
 		struct mlx5e_channel *c = priv->channels.c[i];
+		bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
 
 		clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
+		if (xsk_open)
+			clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
 		napi_synchronize(&c->napi);
 		/* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */
 
 		old_prog = xchg(&c->rq.xdp_prog, prog);
+		if (old_prog)
+			bpf_prog_put(old_prog);
+
+		if (xsk_open) {
+			old_prog = xchg(&c->xskrq.xdp_prog, prog);
+			if (old_prog)
+				bpf_prog_put(old_prog);
+		}
 
 		set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state);
+		if (xsk_open)
+			set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
 		/* napi_schedule in case we have missed anything */
 		napi_schedule(&c->napi);
-
-		if (old_prog)
-			bpf_prog_put(old_prog);
 	}
 
 unlock:
@@ -4378,11 +4457,69 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx5e_xdp_query(dev);
 		return 0;
+	case XDP_SETUP_XSK_UMEM:
+		return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem,
+					    xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
 }
 
+#ifdef CONFIG_MLX5_ESWITCH
+static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+				struct net_device *dev, u32 filter_mask,
+				int nlflags)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 mode, setting;
+	int err;
+
+	err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting);
+	if (err)
+		return err;
+	mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB;
+	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
+				       mode,
+				       0, 0, nlflags, filter_mask, NULL);
+}
+
+static int mlx5e_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
+				u16 flags, struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct nlattr *attr, *br_spec;
+	u16 mode = BRIDGE_MODE_UNDEF;
+	u8 setting;
+	int rem;
+
+	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
+
+	nla_for_each_nested(attr, br_spec, rem) {
+		if (nla_type(attr) != IFLA_BRIDGE_MODE)
+			continue;
+
+		if (nla_len(attr) < sizeof(mode))
+			return -EINVAL;
+
+		mode = nla_get_u16(attr);
+		if (mode > BRIDGE_MODE_VEPA)
+			return -EINVAL;
+
+		break;
+	}
+
+	if (mode == BRIDGE_MODE_UNDEF)
+		return -EINVAL;
+
+	setting = (mode == BRIDGE_MODE_VEPA) ?  1 : 0;
+	return mlx5_eswitch_set_vepa(mdev->priv.eswitch, setting);
+}
+#endif
+
 const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
@@ -4405,10 +4542,14 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
 	.ndo_bpf		 = mlx5e_xdp,
 	.ndo_xdp_xmit            = mlx5e_xdp_xmit,
+	.ndo_xsk_async_xmit      = mlx5e_xsk_async_xmit,
 #ifdef CONFIG_MLX5_EN_ARFS
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
 #ifdef CONFIG_MLX5_ESWITCH
+	.ndo_bridge_setlink      = mlx5e_bridge_setlink,
+	.ndo_bridge_getlink      = mlx5e_bridge_getlink,
+
 	/* SRIOV E-Switch NDOs */
 	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
 	.ndo_set_vf_vlan         = mlx5e_set_vf_vlan,
@@ -4471,9 +4612,9 @@ static bool slow_pci_heuristic(struct mlx5_core_dev *mdev)
 		link_speed > MLX5E_SLOW_PCI_RATIO * pci_bw;
 }
 
-static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
+static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
 {
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 
 	moder.cq_period_mode = cq_period_mode;
 	moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
@@ -4484,9 +4625,9 @@ static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode)
 	return moder;
 }
 
-static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
+static struct dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
 {
-	struct net_dim_cq_moder moder;
+	struct dim_cq_moder moder;
 
 	moder.cq_period_mode = cq_period_mode;
 	moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
@@ -4500,8 +4641,8 @@ static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode)
 static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode)
 {
 	return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ?
-		NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE :
-		NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+		DIM_CQ_PERIOD_MODE_START_FROM_CQE :
+		DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 }
 
 void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode)
@@ -4553,11 +4694,13 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 	 * - Striding RQ configuration is not possible/supported.
 	 * - Slow PCI heuristic.
 	 * - Legacy RQ would use linear SKB while Striding RQ would use non-linear.
+	 *
+	 * No XSK params: checking the availability of striding RQ in general.
 	 */
 	if (!slow_pci_heuristic(mdev) &&
 	    mlx5e_striding_rq_possible(mdev, params) &&
-	    (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ||
-	     !mlx5e_rx_is_linear_skb(mdev, params)))
+	    (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ||
+	     !mlx5e_rx_is_linear_skb(params, NULL)))
 		MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true);
 	mlx5e_set_rq_type(mdev, params);
 	mlx5e_init_rq_type_params(mdev, params);
@@ -4568,7 +4711,7 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 {
 	enum mlx5e_traffic_types tt;
 
-	rss_params->hfunc = ETH_RSS_HASH_XOR;
+	rss_params->hfunc = ETH_RSS_HASH_TOP;
 	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
 			    sizeof(rss_params->toeplitz_hash_key));
 	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
@@ -4579,6 +4722,7 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 }
 
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_xsk *xsk,
 			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
 			    u16 max_channels, u16 mtu)
@@ -4614,9 +4758,11 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	/* HW LRO */
 
 	/* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */
-	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
+	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+		/* No XSK params: checking the availability of striding RQ in general. */
+		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
 			params->lro_en = !slow_pci_heuristic(mdev);
+	}
 	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
@@ -4633,13 +4779,18 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 
 	/* RSS */
 	mlx5e_build_rss_params(rss_params, params->num_channels);
+	params->tunneled_offload_en =
+		mlx5e_tunnel_inner_ft_supported(mdev);
+
+	/* AF_XDP */
+	params->xsk = xsk;
 }
 
 static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	mlx5_query_nic_vport_mac_address(priv->mdev, 0, netdev->dev_addr);
+	mlx5_query_mac_address(priv->mdev, netdev->dev_addr);
 	if (is_zero_ether_addr(netdev->dev_addr) &&
 	    !MLX5_CAP_GEN(priv->mdev, vport_group_manager)) {
 		eth_hw_addr_random(netdev);
@@ -4654,7 +4805,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	bool fcs_supported;
 	bool fcs_enabled;
 
-	SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
+	SET_NETDEV_DEV(netdev, mdev->device);
 
 	netdev->netdev_ops = &mlx5e_netdev_ops;
 
@@ -4668,14 +4819,18 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->ethtool_ops	  = &mlx5e_ethtool_ops;
 
 	netdev->vlan_features    |= NETIF_F_SG;
-	netdev->vlan_features    |= NETIF_F_IP_CSUM;
-	netdev->vlan_features    |= NETIF_F_IPV6_CSUM;
+	netdev->vlan_features    |= NETIF_F_HW_CSUM;
 	netdev->vlan_features    |= NETIF_F_GRO;
 	netdev->vlan_features    |= NETIF_F_TSO;
 	netdev->vlan_features    |= NETIF_F_TSO6;
 	netdev->vlan_features    |= NETIF_F_RXCSUM;
 	netdev->vlan_features    |= NETIF_F_RXHASH;
 
+	netdev->mpls_features    |= NETIF_F_SG;
+	netdev->mpls_features    |= NETIF_F_HW_CSUM;
+	netdev->mpls_features    |= NETIF_F_TSO;
+	netdev->mpls_features    |= NETIF_F_TSO6;
+
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_TX;
 	netdev->hw_enc_features  |= NETIF_F_HW_VLAN_CTAG_RX;
 
@@ -4689,15 +4844,15 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5_vxlan_allowed(mdev->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
-		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
-		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
+	if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev) ||
+	    MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
+		netdev->hw_enc_features |= NETIF_F_HW_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
 		netdev->hw_enc_features |= NETIF_F_TSO6;
 		netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
 	}
 
-	if (mlx5_vxlan_allowed(mdev->vxlan)) {
+	if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev)) {
 		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
 					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
 		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
@@ -4737,6 +4892,10 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	if (!priv->channels.params.scatter_fcs_en)
 		netdev->features  &= ~NETIF_F_RXFCS;
 
+	/* prefere CQE compression over rxhash */
+	if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS))
+		netdev->features &= ~NETIF_F_RXHASH;
+
 #define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f)
 	if (FT_CAP(flow_modify_en) &&
 	    FT_CAP(modify_root) &&
@@ -4800,7 +4959,7 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
-	mlx5e_build_nic_params(mdev, rss, &priv->channels.params,
+	mlx5e_build_nic_params(mdev, &priv->xsk, rss, &priv->channels.params,
 			       mlx5e_get_netdev_max_channels(netdev),
 			       netdev->mtu);
 
@@ -4842,7 +5001,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_close_drop_rq;
 
-	err = mlx5e_create_direct_rqts(priv);
+	err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_rqts;
 
@@ -4850,14 +5009,22 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_destroy_direct_rqts;
 
-	err = mlx5e_create_direct_tirs(priv);
+	err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_tirs;
 
+	err = mlx5e_create_direct_rqts(priv, priv->xsk_tir);
+	if (unlikely(err))
+		goto err_destroy_direct_tirs;
+
+	err = mlx5e_create_direct_tirs(priv, priv->xsk_tir);
+	if (unlikely(err))
+		goto err_destroy_xsk_rqts;
+
 	err = mlx5e_create_flow_steering(priv);
 	if (err) {
 		mlx5_core_warn(mdev, "create flow steering failed, %d\n", err);
-		goto err_destroy_direct_tirs;
+		goto err_destroy_xsk_tirs;
 	}
 
 	err = mlx5e_tc_nic_init(priv);
@@ -4868,12 +5035,16 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 
 err_destroy_flow_steering:
 	mlx5e_destroy_flow_steering(priv);
+err_destroy_xsk_tirs:
+	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
+err_destroy_xsk_rqts:
+	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
 err_destroy_direct_tirs:
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
 	mlx5e_destroy_indirect_tirs(priv, true);
 err_destroy_direct_rqts:
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 err_close_drop_rq:
@@ -4887,9 +5058,11 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
 {
 	mlx5e_tc_nic_cleanup(priv);
 	mlx5e_destroy_flow_steering(priv);
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->xsk_tir);
+	mlx5e_destroy_direct_rqts(priv, priv->xsk_tir);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 	mlx5e_destroy_indirect_tirs(priv, true);
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
 	mlx5e_destroy_q_counters(priv);
@@ -4908,6 +5081,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_initialize(priv);
 #endif
+	mlx5e_tx_reporter_create(priv);
 	return 0;
 }
 
@@ -4915,7 +5089,6 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_mtu;
 
 	mlx5e_init_l2_addr(priv);
 
@@ -4923,10 +5096,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	if (!netif_running(netdev))
 		mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN);
 
-	/* MTU range: 68 - hw-specific max */
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+	mlx5e_set_netdev_mtu_boundaries(priv);
 	mlx5e_set_dev_port_mtu(priv);
 
 	mlx5_lag_add(mdev, netdev);
@@ -4974,6 +5144,11 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 	mlx5_lag_remove(mdev);
 }
 
+int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
+{
+	return mlx5e_refresh_tirs(priv, false);
+}
+
 static const struct mlx5e_profile mlx5e_nic_profile = {
 	.init		   = mlx5e_nic_init,
 	.cleanup	   = mlx5e_nic_cleanup,
@@ -4983,6 +5158,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.cleanup_tx	   = mlx5e_cleanup_nic_tx,
 	.enable		   = mlx5e_nic_enable,
 	.disable	   = mlx5e_nic_disable,
+	.update_rx	   = mlx5e_update_nic_rx,
 	.update_stats	   = mlx5e_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
 	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe,
@@ -5042,7 +5218,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 
 	netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv),
 				    nch * profile->max_tc,
-				    nch);
+				    nch * MLX5E_NUM_RQ_GROUPS);
 	if (!netdev) {
 		mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
 		return NULL;
@@ -5155,6 +5331,11 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 	struct mlx5e_priv *priv = vpriv;
 	struct net_device *netdev = priv->netdev;
 
+#ifdef CONFIG_MLX5_ESWITCH
+	if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev)
+		return;
+#endif
+
 	if (!netif_device_present(netdev))
 		return;
 
@@ -5175,7 +5356,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 
 #ifdef CONFIG_MLX5_ESWITCH
 	if (MLX5_ESWITCH_MANAGER(mdev) &&
-	    mlx5_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+	    mlx5_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) {
 		mlx5e_rep_register_vport_reps(mdev);
 		return mdev;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index ef9e472daffb..7245d287633d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -37,6 +37,7 @@
 #include <net/act_api.h>
 #include <net/netevent.h>
 #include <net/arp.h>
+#include <net/devlink.h>
 
 #include "eswitch.h"
 #include "en.h"
@@ -44,6 +45,7 @@
 #include "en_tc.h"
 #include "en/tc_tun.h"
 #include "fs_core.h"
+#include "lib/port_tun.h"
 
 #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
         max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
@@ -64,9 +66,26 @@ static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 				  struct ethtool_drvinfo *drvinfo)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
 	strlcpy(drvinfo->driver, mlx5e_rep_driver_name,
 		sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "%d.%d.%04d (%.16s)",
+		 fw_rev_maj(mdev), fw_rev_min(mdev),
+		 fw_rev_sub(mdev), mdev->board_id);
+}
+
+static void mlx5e_uplink_rep_get_drvinfo(struct net_device *dev,
+					 struct ethtool_drvinfo *drvinfo)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	mlx5e_rep_get_drvinfo(dev, drvinfo);
+	strlcpy(drvinfo->bus_info, pci_name(priv->mdev->pdev),
+		sizeof(drvinfo->bus_info));
 }
 
 static const struct counter_desc sw_rep_stats_desc[] = {
@@ -110,7 +129,7 @@ static void mlx5e_rep_get_strings(struct net_device *dev,
 	}
 }
 
-static void mlx5e_vf_rep_update_hw_counters(struct mlx5e_priv *priv)
+static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -148,41 +167,19 @@ static void mlx5e_uplink_rep_update_hw_counters(struct mlx5e_priv *priv)
 	vport_stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
 }
 
-static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
-
-	if (rep->vport == FDB_UPLINK_VPORT)
-		mlx5e_uplink_rep_update_hw_counters(priv);
-	else
-		mlx5e_vf_rep_update_hw_counters(priv);
-}
-
 static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5e_sw_stats *s = &priv->stats.sw;
-	struct mlx5e_rq_stats *rq_stats;
-	struct mlx5e_sq_stats *sq_stats;
-	int i, j;
+	struct rtnl_link_stats64 stats64 = {};
 
 	memset(s, 0, sizeof(*s));
-	for (i = 0; i < priv->channels.num; i++) {
-		struct mlx5e_channel *c = priv->channels.c[i];
-
-		rq_stats = c->rq.stats;
+	mlx5e_fold_sw_stats64(priv, &stats64);
 
-		s->rx_packets	+= rq_stats->packets;
-		s->rx_bytes	+= rq_stats->bytes;
-
-		for (j = 0; j < priv->channels.params.num_tc; j++) {
-			sq_stats = c->sq[j].stats;
-
-			s->tx_packets		+= sq_stats->packets;
-			s->tx_bytes		+= sq_stats->bytes;
-			s->tx_queue_dropped	+= sq_stats->dropped;
-		}
-	}
+	s->rx_packets = stats64.rx_packets;
+	s->rx_bytes   = stats64.rx_bytes;
+	s->tx_packets = stats64.tx_packets;
+	s->tx_bytes   = stats64.tx_bytes;
+	s->tx_queue_dropped = stats64.tx_dropped;
 }
 
 static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
@@ -195,9 +192,8 @@ static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
 		return;
 
 	mutex_lock(&priv->state_lock);
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-		mlx5e_rep_update_sw_counters(priv);
-	mlx5e_rep_update_hw_counters(priv);
+	mlx5e_rep_update_sw_counters(priv);
+	priv->profile->update_stats(priv);
 	mutex_unlock(&priv->state_lock);
 
 	for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++)
@@ -357,7 +353,7 @@ static int mlx5e_uplink_rep_set_link_ksettings(struct net_device *netdev,
 	return mlx5e_ethtool_set_link_ksettings(priv, link_ksettings);
 }
 
-static const struct ethtool_ops mlx5e_vf_rep_ethtool_ops = {
+static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
 	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
 	.get_link	   = ethtool_op_get_link,
 	.get_strings       = mlx5e_rep_get_strings,
@@ -374,7 +370,7 @@ static const struct ethtool_ops mlx5e_vf_rep_ethtool_ops = {
 };
 
 static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = {
-	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
+	.get_drvinfo	   = mlx5e_uplink_rep_get_drvinfo,
 	.get_link	   = ethtool_op_get_link,
 	.get_strings       = mlx5e_rep_get_strings,
 	.get_sset_count    = mlx5e_rep_get_sset_count,
@@ -393,38 +389,22 @@ static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = {
 	.set_pauseparam    = mlx5e_uplink_rep_set_pauseparam,
 };
 
-static int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static int mlx5e_rep_get_port_parent_id(struct net_device *dev,
+					struct netdev_phys_item_id *ppid)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct net_device *uplink_upper = NULL;
-	struct mlx5e_priv *uplink_priv = NULL;
-	struct net_device *uplink_dev;
-
-	if (esw->mode == SRIOV_NONE)
-		return -EOPNOTSUPP;
-
-	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
-	if (uplink_dev) {
-		uplink_upper = netdev_master_upper_dev_get(uplink_dev);
-		uplink_priv = netdev_priv(uplink_dev);
-	}
+	struct mlx5_eswitch *esw;
+	struct mlx5e_priv *priv;
+	u64 parent_id;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = ETH_ALEN;
-		if (uplink_upper && mlx5_lag_is_sriov(uplink_priv->mdev)) {
-			ether_addr_copy(attr->u.ppid.id, uplink_upper->dev_addr);
-		} else {
-			struct mlx5e_rep_priv *rpriv = priv->ppriv;
-			struct mlx5_eswitch_rep *rep = rpriv->rep;
+	priv = netdev_priv(dev);
+	esw = priv->mdev->priv.eswitch;
 
-			ether_addr_copy(attr->u.ppid.id, rep->hw_id);
-		}
-		break;
-	default:
+	if (esw->mode == MLX5_ESWITCH_NONE)
 		return -EOPNOTSUPP;
-	}
+
+	parent_id = mlx5_query_nic_system_image_guid(priv->mdev);
+	ppid->id_len = sizeof(parent_id);
+	memcpy(ppid->id, &parent_id, sizeof(parent_id));
 
 	return 0;
 }
@@ -435,7 +415,7 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw,
 	struct mlx5e_rep_sq *rep_sq, *tmp;
 	struct mlx5e_rep_priv *rpriv;
 
-	if (esw->mode != SRIOV_OFFLOADS)
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return;
 
 	rpriv = mlx5e_rep_to_rep_priv(rep);
@@ -456,7 +436,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 	int err;
 	int i;
 
-	if (esw->mode != SRIOV_OFFLOADS)
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return 0;
 
 	rpriv = mlx5e_rep_to_rep_priv(rep);
@@ -676,7 +656,7 @@ static void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv)
 
 static int
 mlx5e_rep_indr_offload(struct net_device *netdev,
-		       struct tc_cls_flower_offload *flower,
+		       struct flow_cls_offload *flower,
 		       struct mlx5e_rep_indr_block_priv *indr_priv)
 {
 	struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev);
@@ -684,13 +664,13 @@ mlx5e_rep_indr_offload(struct net_device *netdev,
 	int err = 0;
 
 	switch (flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		err = mlx5e_configure_flower(netdev, priv, flower, flags);
 		break;
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		err = mlx5e_delete_flower(netdev, priv, flower, flags);
 		break;
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		err = mlx5e_stats_flower(netdev, priv, flower, flags);
 		break;
 	default:
@@ -713,23 +693,39 @@ static int mlx5e_rep_indr_setup_block_cb(enum tc_setup_type type,
 	}
 }
 
+static void mlx5e_rep_indr_tc_block_unbind(void *cb_priv)
+{
+	struct mlx5e_rep_indr_block_priv *indr_priv = cb_priv;
+
+	list_del(&indr_priv->list);
+	kfree(indr_priv);
+}
+
+static LIST_HEAD(mlx5e_block_cb_list);
+
 static int
 mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
 			      struct mlx5e_rep_priv *rpriv,
-			      struct tc_block_offload *f)
+			      struct flow_block_offload *f)
 {
 	struct mlx5e_rep_indr_block_priv *indr_priv;
-	int err = 0;
+	struct flow_block_cb *block_cb;
 
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	f->driver_block_list = &mlx5e_block_cb_list;
+
 	switch (f->command) {
-	case TC_BLOCK_BIND:
+	case FLOW_BLOCK_BIND:
 		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
 		if (indr_priv)
 			return -EEXIST;
 
+		if (flow_block_cb_is_busy(mlx5e_rep_indr_setup_block_cb,
+					  indr_priv, &mlx5e_block_cb_list))
+			return -EBUSY;
+
 		indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL);
 		if (!indr_priv)
 			return -ENOMEM;
@@ -739,26 +735,32 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
 		list_add(&indr_priv->list,
 			 &rpriv->uplink_priv.tc_indr_block_priv_list);
 
-		err = tcf_block_cb_register(f->block,
-					    mlx5e_rep_indr_setup_block_cb,
-					    indr_priv, indr_priv, f->extack);
-		if (err) {
+		block_cb = flow_block_cb_alloc(f->net,
+					       mlx5e_rep_indr_setup_block_cb,
+					       indr_priv, indr_priv,
+					       mlx5e_rep_indr_tc_block_unbind);
+		if (IS_ERR(block_cb)) {
 			list_del(&indr_priv->list);
 			kfree(indr_priv);
+			return PTR_ERR(block_cb);
 		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlx5e_block_cb_list);
 
-		return err;
-	case TC_BLOCK_UNBIND:
+		return 0;
+	case FLOW_BLOCK_UNBIND:
 		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
 		if (!indr_priv)
 			return -ENOENT;
 
-		tcf_block_cb_unregister(f->block,
-					mlx5e_rep_indr_setup_block_cb,
-					indr_priv);
-		list_del(&indr_priv->list);
-		kfree(indr_priv);
+		block_cb = flow_block_cb_lookup(f,
+						mlx5e_rep_indr_setup_block_cb,
+						indr_priv);
+		if (!block_cb)
+			return -ENOENT;
 
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -811,7 +813,8 @@ static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
 
-	if (!mlx5e_tc_tun_device_to_offload(priv, netdev))
+	if (!mlx5e_tc_tun_device_to_offload(priv, netdev) &&
+	    !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev))
 		return NOTIFY_OK;
 
 	switch (event) {
@@ -1061,14 +1064,23 @@ static void mlx5e_rep_neigh_entry_destroy(struct mlx5e_priv *priv,
 int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
 				 struct mlx5e_encap_entry *e)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
 	struct mlx5e_neigh_hash_entry *nhe;
 	int err;
 
+	err = mlx5_tun_entropy_refcount_inc(tun_entropy, e->reformat_type);
+	if (err)
+		return err;
 	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);
 	if (!nhe) {
 		err = mlx5e_rep_neigh_entry_create(priv, e, &nhe);
-		if (err)
+		if (err) {
+			mlx5_tun_entropy_refcount_dec(tun_entropy,
+						      e->reformat_type);
 			return err;
+		}
 	}
 	list_add(&e->encap_list, &nhe->encap_list);
 	return 0;
@@ -1077,6 +1089,9 @@ int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
 void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 				  struct mlx5e_encap_entry *e)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
 	struct mlx5e_neigh_hash_entry *nhe;
 
 	list_del(&e->encap_list);
@@ -1084,9 +1099,10 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 
 	if (list_empty(&nhe->encap_list))
 		mlx5e_rep_neigh_entry_destroy(priv, nhe);
+	mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type);
 }
 
-static int mlx5e_vf_rep_open(struct net_device *dev)
+static int mlx5e_rep_open(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -1100,7 +1116,8 @@ static int mlx5e_vf_rep_open(struct net_device *dev)
 
 	if (!mlx5_modify_vport_admin_state(priv->mdev,
 					   MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					   rep->vport, MLX5_VPORT_ADMIN_STATE_UP))
+					   rep->vport, 1,
+					   MLX5_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -1108,7 +1125,7 @@ unlock:
 	return err;
 }
 
-static int mlx5e_vf_rep_close(struct net_device *dev)
+static int mlx5e_rep_close(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -1118,47 +1135,25 @@ static int mlx5e_vf_rep_close(struct net_device *dev)
 	mutex_lock(&priv->state_lock);
 	mlx5_modify_vport_admin_state(priv->mdev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-				      rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN);
+				      rep->vport, 1,
+				      MLX5_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
 }
 
-static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
-					char *buf, size_t len)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
-	int ret, pf_num;
-
-	ret = mlx5_lag_get_pf_num(priv->mdev, &pf_num);
-	if (ret)
-		return ret;
-
-	if (rep->vport == FDB_UPLINK_VPORT)
-		ret = snprintf(buf, len, "p%d", pf_num);
-	else
-		ret = snprintf(buf, len, "pf%dvf%d", pf_num, rep->vport - 1);
-
-	if (ret >= len)
-		return -EOPNOTSUPP;
-
-	return 0;
-}
-
 static int
 mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
-			      struct tc_cls_flower_offload *cls_flower, int flags)
+			      struct flow_cls_offload *cls_flower, int flags)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
 					      flags);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
 					   flags);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
 					  flags);
 	default:
@@ -1180,32 +1175,19 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int mlx5e_rep_setup_tc_block(struct net_device *dev,
-				    struct tc_block_offload *f)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
-					     priv, priv, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(mlx5e_rep_block_cb_list);
 
 static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return mlx5e_rep_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &mlx5e_rep_block_cb_list,
+						  mlx5e_rep_setup_tc_cb,
+						  priv, priv, true);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1223,7 +1205,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 		return false;
 
 	rep = rpriv->rep;
-	return (rep->vport == FDB_UPLINK_VPORT);
+	return (rep->vport == MLX5_VPORT_UPLINK);
 }
 
 static bool mlx5e_rep_has_offload_stats(const struct net_device *dev, int attr_id)
@@ -1241,17 +1223,8 @@ mlx5e_get_sw_stats64(const struct net_device *dev,
 		     struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sw_stats *sstats = &priv->stats.sw;
-
-	mlx5e_rep_update_sw_counters(priv);
-
-	stats->rx_packets = sstats->rx_packets;
-	stats->rx_bytes   = sstats->rx_bytes;
-	stats->tx_packets = sstats->tx_packets;
-	stats->tx_bytes   = sstats->tx_bytes;
-
-	stats->tx_dropped = sstats->tx_queue_dropped;
 
+	mlx5e_fold_sw_stats64(priv, stats);
 	return 0;
 }
 
@@ -1267,7 +1240,7 @@ static int mlx5e_rep_get_offload_stats(int attr_id, const struct net_device *dev
 }
 
 static void
-mlx5e_vf_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
+mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
@@ -1276,7 +1249,7 @@ mlx5e_vf_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
 }
 
-static int mlx5e_vf_rep_change_mtu(struct net_device *netdev, int new_mtu)
+static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	return mlx5e_change_mtu(netdev, new_mtu, NULL);
 }
@@ -1309,20 +1282,24 @@ static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan
 	return 0;
 }
 
-static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
-	.switchdev_port_attr_get	= mlx5e_attr_get,
-};
+static struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+	return &rpriv->dl_port;
+}
 
-static const struct net_device_ops mlx5e_netdev_ops_vf_rep = {
-	.ndo_open                = mlx5e_vf_rep_open,
-	.ndo_stop                = mlx5e_vf_rep_close,
+static const struct net_device_ops mlx5e_netdev_ops_rep = {
+	.ndo_open                = mlx5e_rep_open,
+	.ndo_stop                = mlx5e_rep_close,
 	.ndo_start_xmit          = mlx5e_xmit,
-	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
-	.ndo_get_stats64         = mlx5e_vf_rep_get_stats,
+	.ndo_get_devlink_port = mlx5e_get_devlink_port,
+	.ndo_get_stats64         = mlx5e_rep_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
-	.ndo_change_mtu          = mlx5e_vf_rep_change_mtu,
+	.ndo_change_mtu          = mlx5e_rep_change_mtu,
 };
 
 static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
@@ -1330,8 +1307,8 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
 	.ndo_stop                = mlx5e_close,
 	.ndo_start_xmit          = mlx5e_xmit,
 	.ndo_set_mac_address     = mlx5e_uplink_rep_set_mac,
-	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
+	.ndo_get_devlink_port = mlx5e_get_devlink_port,
 	.ndo_get_stats64         = mlx5e_get_stats,
 	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
 	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
@@ -1344,11 +1321,12 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
 	.ndo_get_vf_config       = mlx5e_get_vf_config,
 	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
 	.ndo_set_vf_vlan         = mlx5e_uplink_rep_set_vf_vlan,
+	.ndo_set_features        = mlx5e_set_features,
 };
 
 bool mlx5e_eswitch_rep(struct net_device *netdev)
 {
-	if (netdev->netdev_ops == &mlx5e_netdev_ops_vf_rep ||
+	if (netdev->netdev_ops == &mlx5e_netdev_ops_rep ||
 	    netdev->netdev_ops == &mlx5e_netdev_ops_uplink_rep)
 		return true;
 
@@ -1372,7 +1350,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	params->sw_mtu      = netdev->mtu;
 
 	/* SQ */
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 	else
 		params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
@@ -1385,6 +1363,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
 
 	params->num_tc                = 1;
+	params->tunneled_offload_en = false;
 
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
@@ -1399,30 +1378,27 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	if (rep->vport == FDB_UPLINK_VPORT) {
-		SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev);
+	if (rep->vport == MLX5_VPORT_UPLINK) {
+		SET_NETDEV_DEV(netdev, mdev->device);
 		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
 		/* we want a persistent mac for the uplink rep */
-		mlx5_query_nic_vport_mac_address(mdev, 0, netdev->dev_addr);
+		mlx5_query_mac_address(mdev, netdev->dev_addr);
 		netdev->ethtool_ops = &mlx5e_uplink_rep_ethtool_ops;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 		if (MLX5_CAP_GEN(mdev, qos))
 			netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
 #endif
 	} else {
-		netdev->netdev_ops = &mlx5e_netdev_ops_vf_rep;
+		netdev->netdev_ops = &mlx5e_netdev_ops_rep;
 		eth_hw_addr_random(netdev);
-		netdev->ethtool_ops = &mlx5e_vf_rep_ethtool_ops;
+		netdev->ethtool_ops = &mlx5e_rep_ethtool_ops;
 	}
 
 	netdev->watchdog_timeo    = 15 * HZ;
 
+	netdev->features       |= NETIF_F_NETNS_LOCAL;
 
-	netdev->switchdev_ops = &mlx5e_rep_switchdev_ops;
-
-	netdev->features	 |= NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
-	netdev->hw_features      |= NETIF_F_HW_TC;
-
+	netdev->hw_features    |= NETIF_F_HW_TC;
 	netdev->hw_features    |= NETIF_F_SG;
 	netdev->hw_features    |= NETIF_F_IP_CSUM;
 	netdev->hw_features    |= NETIF_F_IPV6_CSUM;
@@ -1431,7 +1407,9 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	netdev->hw_features    |= NETIF_F_TSO6;
 	netdev->hw_features    |= NETIF_F_RXCSUM;
 
-	if (rep->vport != FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+	else
 		netdev->features |= NETIF_F_VLAN_CHALLENGED;
 
 	netdev->features |= netdev->hw_features;
@@ -1522,7 +1500,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_close_drop_rq;
 
-	err = mlx5e_create_direct_rqts(priv);
+	err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_rqts;
 
@@ -1530,7 +1508,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_destroy_direct_rqts;
 
-	err = mlx5e_create_direct_tirs(priv);
+	err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_tirs;
 
@@ -1547,11 +1525,11 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 err_destroy_ttc_table:
 	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
 err_destroy_direct_tirs:
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
 	mlx5e_destroy_indirect_tirs(priv, false);
 err_destroy_direct_rqts:
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 err_close_drop_rq:
@@ -1565,9 +1543,9 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 
 	mlx5_del_flow_rules(rpriv->vport_rx_rule);
 	mlx5e_destroy_ttc_table(priv, &priv->fs.ttc);
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 	mlx5e_destroy_indirect_tirs(priv, false);
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
 }
@@ -1584,14 +1562,18 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	if (rpriv->rep->vport == FDB_UPLINK_VPORT) {
+	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
 		uplink_priv = &rpriv->uplink_priv;
 
+		INIT_LIST_HEAD(&uplink_priv->unready_flows);
+
 		/* init shared tc flow table */
 		err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
 		if (err)
 			goto destroy_tises;
 
+		mlx5_init_port_tun_entropy(&uplink_priv->tun_entropy, priv->mdev);
+
 		/* init indirect block notifications */
 		INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
 		uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
@@ -1620,7 +1602,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 	for (tc = 0; tc < priv->profile->max_tc; tc++)
 		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 
-	if (rpriv->rep->vport == FDB_UPLINK_VPORT) {
+	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
 		/* clean indirect TC block notifications */
 		unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb);
 		mlx5e_rep_indr_clean_block_privs(rpriv);
@@ -1630,41 +1612,51 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
 	}
 }
 
-static void mlx5e_vf_rep_enable(struct mlx5e_priv *priv)
+static void mlx5e_rep_enable(struct mlx5e_priv *priv)
 {
-	struct net_device *netdev = priv->netdev;
-	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_mtu;
+	mlx5e_set_netdev_mtu_boundaries(priv);
+}
 
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+static int mlx5e_update_rep_rx(struct mlx5e_priv *priv)
+{
+	return 0;
 }
 
 static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event, void *data)
 {
 	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
-	struct mlx5_eqe   *eqe = data;
 
-	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
-		return NOTIFY_DONE;
+	if (event == MLX5_EVENT_TYPE_PORT_CHANGE) {
+		struct mlx5_eqe *eqe = data;
 
-	switch (eqe->sub_type) {
-	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-		queue_work(priv->wq, &priv->update_carrier_work);
-		break;
-	default:
-		return NOTIFY_DONE;
+		switch (eqe->sub_type) {
+		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+			queue_work(priv->wq, &priv->update_carrier_work);
+			break;
+		default:
+			return NOTIFY_DONE;
+		}
+
+		return NOTIFY_OK;
 	}
 
-	return NOTIFY_OK;
+	if (event == MLX5_DEV_EVENT_PORT_AFFINITY) {
+		struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+		queue_work(priv->wq, &rpriv->uplink_priv.reoffload_flows_work);
+
+		return NOTIFY_OK;
+	}
+
+	return NOTIFY_DONE;
 }
 
 static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 {
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	u16 max_mtu;
 
 	netdev->min_mtu = ETH_MIN_MTU;
@@ -1672,6 +1664,9 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
 	mlx5e_set_dev_port_mtu(priv);
 
+	INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work,
+		  mlx5e_tc_reoffload_flows_work);
+
 	mlx5_lag_add(mdev, netdev);
 	priv->events_nb.notifier_call = uplink_rep_async_event;
 	mlx5_notifier_register(mdev, &priv->events_nb);
@@ -1684,23 +1679,26 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
 #endif
 	mlx5_notifier_unregister(mdev, &priv->events_nb);
+	cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
 	mlx5_lag_remove(mdev);
 }
 
-static const struct mlx5e_profile mlx5e_vf_rep_profile = {
+static const struct mlx5e_profile mlx5e_rep_profile = {
 	.init			= mlx5e_init_rep,
 	.cleanup		= mlx5e_cleanup_rep,
 	.init_rx		= mlx5e_init_rep_rx,
 	.cleanup_rx		= mlx5e_cleanup_rep_rx,
 	.init_tx		= mlx5e_init_rep_tx,
 	.cleanup_tx		= mlx5e_cleanup_rep_tx,
-	.enable		        = mlx5e_vf_rep_enable,
-	.update_stats           = mlx5e_vf_rep_update_hw_counters,
+	.enable		        = mlx5e_rep_enable,
+	.update_rx		= mlx5e_update_rep_rx,
+	.update_stats           = mlx5e_rep_update_hw_counters,
 	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
 	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
 	.max_tc			= 1,
@@ -1715,6 +1713,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.cleanup_tx		= mlx5e_cleanup_rep_tx,
 	.enable		        = mlx5e_uplink_rep_enable,
 	.disable	        = mlx5e_uplink_rep_disable,
+	.update_rx		= mlx5e_update_rep_rx,
 	.update_stats           = mlx5e_uplink_rep_update_hw_counters,
 	.update_carrier	        = mlx5e_update_carrier,
 	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
@@ -1722,6 +1721,55 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.max_tc			= MLX5E_MAX_NUM_TC,
 };
 
+static bool
+is_devlink_port_supported(const struct mlx5_core_dev *dev,
+			  const struct mlx5e_rep_priv *rpriv)
+{
+	return rpriv->rep->vport == MLX5_VPORT_UPLINK ||
+	       rpriv->rep->vport == MLX5_VPORT_PF ||
+	       mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport);
+}
+
+static int register_devlink_port(struct mlx5_core_dev *dev,
+				 struct mlx5e_rep_priv *rpriv)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct netdev_phys_item_id ppid = {};
+	int ret;
+
+	if (!is_devlink_port_supported(dev, rpriv))
+		return 0;
+
+	ret = mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
+	if (ret)
+		return ret;
+
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		devlink_port_attrs_set(&rpriv->dl_port,
+				       DEVLINK_PORT_FLAVOUR_PHYSICAL,
+				       PCI_FUNC(dev->pdev->devfn), false, 0,
+				       &ppid.id[0], ppid.id_len);
+	else if (rep->vport == MLX5_VPORT_PF)
+		devlink_port_attrs_pci_pf_set(&rpriv->dl_port,
+					      &ppid.id[0], ppid.id_len,
+					      dev->pdev->devfn);
+	else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport))
+		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
+					      &ppid.id[0], ppid.id_len,
+					      dev->pdev->devfn,
+					      rep->vport - 1);
+
+	return devlink_port_register(devlink, &rpriv->dl_port, rep->vport);
+}
+
+static void unregister_devlink_port(struct mlx5_core_dev *dev,
+				    struct mlx5e_rep_priv *rpriv)
+{
+	if (is_devlink_port_supported(dev, rpriv))
+		devlink_port_unregister(&rpriv->dl_port);
+}
+
 /* e-Switch vport representors */
 static int
 mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
@@ -1739,7 +1787,8 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	rpriv->rep = rep;
 
 	nch = mlx5e_get_max_num_channels(dev);
-	profile = (rep->vport == FDB_UPLINK_VPORT) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile;
+	profile = (rep->vport == MLX5_VPORT_UPLINK) ?
+		  &mlx5e_uplink_rep_profile : &mlx5e_rep_profile;
 	netdev = mlx5e_create_netdev(dev, profile, nch, rpriv);
 	if (!netdev) {
 		pr_warn("Failed to create representor netdev for vport %d\n",
@@ -1749,10 +1798,10 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	}
 
 	rpriv->netdev = netdev;
-	rep->rep_if[REP_ETH].priv = rpriv;
+	rep->rep_data[REP_ETH].priv = rpriv;
 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
 
-	if (rep->vport == FDB_UPLINK_VPORT) {
+	if (rep->vport == MLX5_VPORT_UPLINK) {
 		err = mlx5e_create_mdev_resources(dev);
 		if (err)
 			goto err_destroy_netdev;
@@ -1772,15 +1821,27 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		goto err_detach_netdev;
 	}
 
+	err = register_devlink_port(dev, rpriv);
+	if (err) {
+		esw_warn(dev, "Failed to register devlink port %d\n",
+			 rep->vport);
+		goto err_neigh_cleanup;
+	}
+
 	err = register_netdev(netdev);
 	if (err) {
 		pr_warn("Failed to register representor netdev for vport %d\n",
 			rep->vport);
-		goto err_neigh_cleanup;
+		goto err_devlink_cleanup;
 	}
 
+	if (is_devlink_port_supported(dev, rpriv))
+		devlink_port_type_eth_set(&rpriv->dl_port, netdev);
 	return 0;
 
+err_devlink_cleanup:
+	unregister_devlink_port(dev, rpriv);
+
 err_neigh_cleanup:
 	mlx5e_rep_neigh_cleanup(rpriv);
 
@@ -1788,7 +1849,7 @@ err_detach_netdev:
 	mlx5e_detach_netdev(netdev_priv(netdev));
 
 err_destroy_mdev_resources:
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		mlx5e_destroy_mdev_resources(dev);
 
 err_destroy_netdev:
@@ -1803,12 +1864,16 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
 	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *dev = priv->mdev;
 	void *ppriv = priv->ppriv;
 
+	if (is_devlink_port_supported(dev, rpriv))
+		devlink_port_type_clear(&rpriv->dl_port);
 	unregister_netdev(netdev);
+	unregister_devlink_port(dev, rpriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
-	if (rep->vport == FDB_UPLINK_VPORT)
+	if (rep->vport == MLX5_VPORT_UPLINK)
 		mlx5e_destroy_mdev_resources(priv->mdev);
 	mlx5e_destroy_netdev(priv);
 	kfree(ppriv); /* mlx5e_rep_priv */
@@ -1823,28 +1888,22 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return rpriv->netdev;
 }
 
+static const struct mlx5_eswitch_rep_ops rep_ops = {
+	.load = mlx5e_vport_rep_load,
+	.unload = mlx5e_vport_rep_unload,
+	.get_proto_dev = mlx5e_vport_rep_get_proto_dev
+};
+
 void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
 
-	for (vport = 0; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep_if rep_if = {};
-
-		rep_if.load = mlx5e_vport_rep_load;
-		rep_if.unload = mlx5e_vport_rep_unload;
-		rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev;
-		mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH);
-	}
+	mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_ETH);
 }
 
 void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
 
-	for (vport = total_vfs - 1; vport >= 0; vport--)
-		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH);
+	mlx5_eswitch_unregister_vport_reps(esw, REP_ETH);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 36eafc877e6b..c56e6ee4350c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -37,6 +37,7 @@
 #include <linux/rhashtable.h>
 #include "eswitch.h"
 #include "en.h"
+#include "lib/port_tun.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
 struct mlx5e_neigh_update_table {
@@ -71,6 +72,11 @@ struct mlx5_rep_uplink_priv {
 	 */
 	struct list_head	    tc_indr_block_priv_list;
 	struct notifier_block	    netdevice_nb;
+
+	struct mlx5_tun_entropy tun_entropy;
+
+	struct list_head            unready_flows;
+	struct work_struct          reoffload_flows_work;
 };
 
 struct mlx5e_rep_priv {
@@ -80,12 +86,13 @@ struct mlx5e_rep_priv {
 	struct mlx5_flow_handle *vport_rx_rule;
 	struct list_head       vport_sqs_list;
 	struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */
+	struct devlink_port dl_port;
 };
 
 static inline
 struct mlx5e_rep_priv *mlx5e_rep_to_rep_priv(struct mlx5_eswitch_rep *rep)
 {
-	return (struct mlx5e_rep_priv *)rep->rep_if[REP_ETH].priv;
+	return rep->rep_data[REP_ETH].priv;
 }
 
 struct mlx5e_neigh {
@@ -144,13 +151,12 @@ struct mlx5e_encap_entry {
 	struct hlist_node encap_hlist;
 	struct list_head flows;
 	u32 encap_id;
-	struct ip_tunnel_info tun_info;
+	const struct ip_tunnel_info *tun_info;
 	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
 
 	struct net_device *out_dev;
 	struct net_device *route_dev;
-	int tunnel_type;
-	int tunnel_hlen;
+	struct mlx5e_tc_tunnel *tunnel;
 	int reformat_type;
 	u8 flags;
 	char *encap_header;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f86e4804e83e..ac6e586d403d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -34,6 +34,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
+#include <linux/indirect_call_wrapper.h>
 #include <net/ip6_checksum.h>
 #include <net/page_pool.h>
 #include <net/inet_ecn.h>
@@ -46,46 +47,52 @@
 #include "en_accel/tls_rxtx.h"
 #include "lib/clock.h"
 #include "en/xdp.h"
+#include "en/xsk/rx.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
 	return config->rx_filter == HWTSTAMP_FILTER_ALL;
 }
 
-static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc,
-				       void *data)
+static inline void mlx5e_read_cqe_slot(struct mlx5_cqwq *wq,
+				       u32 cqcc, void *data)
 {
-	u32 ci = mlx5_cqwq_ctr2ix(&cq->wq, cqcc);
+	u32 ci = mlx5_cqwq_ctr2ix(wq, cqcc);
 
-	memcpy(data, mlx5_cqwq_get_wqe(&cq->wq, ci), sizeof(struct mlx5_cqe64));
+	memcpy(data, mlx5_cqwq_get_wqe(wq, ci), sizeof(struct mlx5_cqe64));
 }
 
 static inline void mlx5e_read_title_slot(struct mlx5e_rq *rq,
-					 struct mlx5e_cq *cq, u32 cqcc)
+					 struct mlx5_cqwq *wq,
+					 u32 cqcc)
 {
-	mlx5e_read_cqe_slot(cq, cqcc, &cq->title);
-	cq->decmprs_left        = be32_to_cpu(cq->title.byte_cnt);
-	cq->decmprs_wqe_counter = be16_to_cpu(cq->title.wqe_counter);
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	struct mlx5_cqe64 *title = &cqd->title;
+
+	mlx5e_read_cqe_slot(wq, cqcc, title);
+	cqd->left        = be32_to_cpu(title->byte_cnt);
+	cqd->wqe_counter = be16_to_cpu(title->wqe_counter);
 	rq->stats->cqe_compress_blks++;
 }
 
-static inline void mlx5e_read_mini_arr_slot(struct mlx5e_cq *cq, u32 cqcc)
+static inline void mlx5e_read_mini_arr_slot(struct mlx5_cqwq *wq,
+					    struct mlx5e_cq_decomp *cqd,
+					    u32 cqcc)
 {
-	mlx5e_read_cqe_slot(cq, cqcc, cq->mini_arr);
-	cq->mini_arr_idx = 0;
+	mlx5e_read_cqe_slot(wq, cqcc, cqd->mini_arr);
+	cqd->mini_arr_idx = 0;
 }
 
-static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
+static inline void mlx5e_cqes_update_owner(struct mlx5_cqwq *wq, int n)
 {
-	struct mlx5_cqwq *wq = &cq->wq;
-
+	u32 cqcc   = wq->cc;
 	u8  op_own = mlx5_cqwq_get_ctr_wrap_cnt(wq, cqcc) & 1;
 	u32 ci     = mlx5_cqwq_ctr2ix(wq, cqcc);
 	u32 wq_sz  = mlx5_cqwq_get_size(wq);
 	u32 ci_top = min_t(u32, wq_sz, ci + n);
 
 	for (; ci < ci_top; ci++, n--) {
-		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, ci);
+		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(wq, ci);
 
 		cqe->op_own = op_own;
 	}
@@ -93,7 +100,7 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
 	if (unlikely(ci == wq_sz)) {
 		op_own = !op_own;
 		for (ci = 0; ci < n; ci++) {
-			struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, ci);
+			struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(wq, ci);
 
 			cqe->op_own = op_own;
 		}
@@ -101,68 +108,79 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
 }
 
 static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
-					struct mlx5e_cq *cq, u32 cqcc)
+					struct mlx5_cqwq *wq,
+					u32 cqcc)
 {
-	cq->title.byte_cnt     = cq->mini_arr[cq->mini_arr_idx].byte_cnt;
-	cq->title.check_sum    = cq->mini_arr[cq->mini_arr_idx].checksum;
-	cq->title.op_own      &= 0xf0;
-	cq->title.op_own      |= 0x01 & (cqcc >> cq->wq.fbc.log_sz);
-	cq->title.wqe_counter  = cpu_to_be16(cq->decmprs_wqe_counter);
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	struct mlx5_mini_cqe8 *mini_cqe = &cqd->mini_arr[cqd->mini_arr_idx];
+	struct mlx5_cqe64 *title = &cqd->title;
+
+	title->byte_cnt     = mini_cqe->byte_cnt;
+	title->check_sum    = mini_cqe->checksum;
+	title->op_own      &= 0xf0;
+	title->op_own      |= 0x01 & (cqcc >> wq->fbc.log_sz);
+	title->wqe_counter  = cpu_to_be16(cqd->wqe_counter);
 
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		cq->decmprs_wqe_counter +=
-			mpwrq_get_cqe_consumed_strides(&cq->title);
+		cqd->wqe_counter += mpwrq_get_cqe_consumed_strides(title);
 	else
-		cq->decmprs_wqe_counter =
-			mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, cq->decmprs_wqe_counter + 1);
+		cqd->wqe_counter =
+			mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, cqd->wqe_counter + 1);
 }
 
 static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq,
-						struct mlx5e_cq *cq, u32 cqcc)
+						struct mlx5_cqwq *wq,
+						u32 cqcc)
 {
-	mlx5e_decompress_cqe(rq, cq, cqcc);
-	cq->title.rss_hash_type   = 0;
-	cq->title.rss_hash_result = 0;
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+
+	mlx5e_decompress_cqe(rq, wq, cqcc);
+	cqd->title.rss_hash_type   = 0;
+	cqd->title.rss_hash_result = 0;
 }
 
 static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq,
-					     struct mlx5e_cq *cq,
+					     struct mlx5_cqwq *wq,
 					     int update_owner_only,
 					     int budget_rem)
 {
-	u32 cqcc = cq->wq.cc + update_owner_only;
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	u32 cqcc = wq->cc + update_owner_only;
 	u32 cqe_count;
 	u32 i;
 
-	cqe_count = min_t(u32, cq->decmprs_left, budget_rem);
+	cqe_count = min_t(u32, cqd->left, budget_rem);
 
 	for (i = update_owner_only; i < cqe_count;
-	     i++, cq->mini_arr_idx++, cqcc++) {
-		if (cq->mini_arr_idx == MLX5_MINI_CQE_ARRAY_SIZE)
-			mlx5e_read_mini_arr_slot(cq, cqcc);
+	     i++, cqd->mini_arr_idx++, cqcc++) {
+		if (cqd->mini_arr_idx == MLX5_MINI_CQE_ARRAY_SIZE)
+			mlx5e_read_mini_arr_slot(wq, cqd, cqcc);
 
-		mlx5e_decompress_cqe_no_hash(rq, cq, cqcc);
-		rq->handle_rx_cqe(rq, &cq->title);
+		mlx5e_decompress_cqe_no_hash(rq, wq, cqcc);
+		rq->handle_rx_cqe(rq, &cqd->title);
 	}
-	mlx5e_cqes_update_owner(cq, cq->wq.cc, cqcc - cq->wq.cc);
-	cq->wq.cc = cqcc;
-	cq->decmprs_left -= cqe_count;
+	mlx5e_cqes_update_owner(wq, cqcc - wq->cc);
+	wq->cc = cqcc;
+	cqd->left -= cqe_count;
 	rq->stats->cqe_compress_pkts += cqe_count;
 
 	return cqe_count;
 }
 
 static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
-					      struct mlx5e_cq *cq,
+					      struct mlx5_cqwq *wq,
 					      int budget_rem)
 {
-	mlx5e_read_title_slot(rq, cq, cq->wq.cc);
-	mlx5e_read_mini_arr_slot(cq, cq->wq.cc + 1);
-	mlx5e_decompress_cqe(rq, cq, cq->wq.cc);
-	rq->handle_rx_cqe(rq, &cq->title);
-	cq->mini_arr_idx++;
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	u32 cc = wq->cc;
+
+	mlx5e_read_title_slot(rq, wq, cc);
+	mlx5e_read_mini_arr_slot(wq, cqd, cc + 1);
+	mlx5e_decompress_cqe(rq, wq, cc);
+	rq->handle_rx_cqe(rq, &cqd->title);
+	cqd->mini_arr_idx++;
 
-	return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1;
+	return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1;
 }
 
 static inline bool mlx5e_page_is_reserved(struct page *page)
@@ -218,8 +236,8 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq,
 	return true;
 }
 
-static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
-					  struct mlx5e_dma_info *dma_info)
+static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq,
+					struct mlx5e_dma_info *dma_info)
 {
 	if (mlx5e_rx_cache_get(rq, dma_info))
 		return 0;
@@ -231,7 +249,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 	dma_info->addr = dma_map_page(rq->pdev, dma_info->page, 0,
 				      PAGE_SIZE, rq->buff.map_dir);
 	if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) {
-		put_page(dma_info->page);
+		page_pool_recycle_direct(rq->page_pool, dma_info->page);
 		dma_info->page = NULL;
 		return -ENOMEM;
 	}
@@ -239,13 +257,23 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 	return 0;
 }
 
+static inline int mlx5e_page_alloc(struct mlx5e_rq *rq,
+				   struct mlx5e_dma_info *dma_info)
+{
+	if (rq->umem)
+		return mlx5e_xsk_page_alloc_umem(rq, dma_info);
+	else
+		return mlx5e_page_alloc_pool(rq, dma_info);
+}
+
 void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info)
 {
 	dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir);
 }
 
-void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
-			bool recycle)
+void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
+				struct mlx5e_dma_info *dma_info,
+				bool recycle)
 {
 	if (likely(recycle)) {
 		if (mlx5e_rx_cache_put(rq, dma_info))
@@ -255,10 +283,25 @@ void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 		page_pool_recycle_direct(rq->page_pool, dma_info->page);
 	} else {
 		mlx5e_page_dma_unmap(rq, dma_info);
+		page_pool_release_page(rq->page_pool, dma_info->page);
 		put_page(dma_info->page);
 	}
 }
 
+static inline void mlx5e_page_release(struct mlx5e_rq *rq,
+				      struct mlx5e_dma_info *dma_info,
+				      bool recycle)
+{
+	if (rq->umem)
+		/* The `recycle` parameter is ignored, and the page is always
+		 * put into the Reuse Ring, because there is no way to return
+		 * the page to the userspace when the interface goes down.
+		 */
+		mlx5e_xsk_page_release(rq, dma_info);
+	else
+		mlx5e_page_release_dynamic(rq, dma_info, recycle);
+}
+
 static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 				    struct mlx5e_wqe_frag_info *frag)
 {
@@ -270,7 +313,7 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 		 * offset) should just use the new one without replenishing again
 		 * by themselves.
 		 */
-		err = mlx5e_page_alloc_mapped(rq, frag->di);
+		err = mlx5e_page_alloc(rq, frag->di);
 
 	return err;
 }
@@ -336,6 +379,13 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
 	int err;
 	int i;
 
+	if (rq->umem) {
+		int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags;
+
+		if (unlikely(!mlx5e_xsk_pages_enough_umem(rq, pages_desired)))
+			return -ENOMEM;
+	}
+
 	for (i = 0; i < wqe_bulk; i++) {
 		struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(wq, ix + i);
 
@@ -369,7 +419,7 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
 static inline void
 mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
 		      struct mlx5e_dma_info *dma_info,
-		      int offset_from, int offset_to, u32 headlen)
+		      int offset_from, u32 headlen)
 {
 	const void *from = page_address(dma_info->page) + offset_from;
 	/* Aligning len to sizeof(long) optimizes memcpy performance */
@@ -377,47 +427,37 @@ mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
 
 	dma_sync_single_for_cpu(pdev, dma_info->addr + offset_from, len,
 				DMA_FROM_DEVICE);
-	skb_copy_to_linear_data_offset(skb, offset_to, from, len);
-}
-
-static inline void
-mlx5e_copy_skb_header_mpwqe(struct device *pdev,
-			    struct sk_buff *skb,
-			    struct mlx5e_dma_info *dma_info,
-			    u32 offset, u32 headlen)
-{
-	u16 headlen_pg = min_t(u32, headlen, PAGE_SIZE - offset);
-
-	mlx5e_copy_skb_header(pdev, skb, dma_info, offset, 0, headlen_pg);
-
-	if (unlikely(offset + headlen > PAGE_SIZE)) {
-		dma_info++;
-		mlx5e_copy_skb_header(pdev, skb, dma_info, 0, headlen_pg,
-				      headlen - headlen_pg);
-	}
+	skb_copy_to_linear_data(skb, from, len);
 }
 
 static void
 mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle)
 {
-	const bool no_xdp_xmit =
-		bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
+	bool no_xdp_xmit;
 	struct mlx5e_dma_info *dma_info = wi->umr.dma_info;
 	int i;
 
+	/* A common case for AF_XDP. */
+	if (bitmap_full(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE))
+		return;
+
+	no_xdp_xmit = bitmap_empty(wi->xdp_xmit_bitmap,
+				   MLX5_MPWRQ_PAGES_PER_WQE);
+
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
 		if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
 			mlx5e_page_release(rq, &dma_info[i], recycle);
 }
 
-static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
+static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq, u8 n)
 {
 	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
-	struct mlx5e_rx_wqe_ll *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
 
-	rq->mpwqe.umr_in_progress = false;
+	do {
+		u16 next_wqe_index = mlx5_wq_ll_get_wqe_next_ix(wq, wq->head);
 
-	mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
+		mlx5_wq_ll_push(wq, next_wqe_index);
+	} while (--n);
 
 	/* ensure wqes are visible to device before updating doorbell record */
 	dma_wmb();
@@ -425,11 +465,6 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
 	mlx5_wq_ll_update_db_record(wq);
 }
 
-static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq)
-{
-	return sq->pc >> MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
-}
-
 static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq,
 					      struct mlx5_wq_cyc *wq,
 					      u16 pi, u16 nnops)
@@ -457,6 +492,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	int err;
 	int i;
 
+	if (rq->umem &&
+	    unlikely(!mlx5e_xsk_pages_enough_umem(rq, MLX5_MPWRQ_PAGES_PER_WQE))) {
+		err = -ENOMEM;
+		goto err;
+	}
+
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 	if (unlikely(contig_wqebbs_room < MLX5E_UMR_WQEBBS)) {
@@ -465,12 +506,10 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	}
 
 	umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi);
-	if (unlikely(mlx5e_icosq_wrap_cnt(sq) < 2))
-		memcpy(umr_wqe, &rq->mpwqe.umr_wqe,
-		       offsetof(struct mlx5e_umr_wqe, inline_mtts));
+	memcpy(umr_wqe, &rq->mpwqe.umr_wqe, offsetof(struct mlx5e_umr_wqe, inline_mtts));
 
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) {
-		err = mlx5e_page_alloc_mapped(rq, dma_info);
+		err = mlx5e_page_alloc(rq, dma_info);
 		if (unlikely(err))
 			goto err_unmap;
 		umr_wqe->inline_mtts[i].ptag = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
@@ -479,16 +518,16 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
 	wi->consumed_strides = 0;
 
-	rq->mpwqe.umr_in_progress = true;
-
 	umr_wqe->ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
 	umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
+	sq->db.ico_wqe[pi].umr.rq = rq;
 	sq->pc += MLX5E_UMR_WQEBBS;
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+
+	sq->doorbell_cseg = &umr_wqe->ctrl;
 
 	return 0;
 
@@ -497,6 +536,8 @@ err_unmap:
 		dma_info--;
 		mlx5e_page_release(rq, dma_info, true);
 	}
+
+err:
 	rq->stats->buff_alloc_err++;
 
 	return err;
@@ -543,37 +584,12 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 	return !!err;
 }
 
-static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq,
-					     struct mlx5e_icosq *sq,
-					     struct mlx5e_rq *rq,
-					     struct mlx5_cqe64 *cqe)
-{
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	u16 ci = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter));
-	struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci];
-
-	mlx5_cqwq_pop(&cq->wq);
-
-	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
-		netdev_WARN_ONCE(cq->channel->netdev,
-				 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
-		return;
-	}
-
-	if (likely(icowi->opcode == MLX5_OPCODE_UMR)) {
-		mlx5e_post_rx_mpwqe(rq);
-		return;
-	}
-
-	if (unlikely(icowi->opcode != MLX5_OPCODE_NOP))
-		netdev_WARN_ONCE(cq->channel->netdev,
-				 "Bad OPCODE in ICOSQ WQE info: 0x%x\n", icowi->opcode);
-}
-
-static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
+void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 {
 	struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq);
 	struct mlx5_cqe64 *cqe;
+	u16 sqcc;
+	int i;
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
 		return;
@@ -582,28 +598,105 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 	if (likely(!cqe))
 		return;
 
-	/* by design, there's only a single cqe */
-	mlx5e_poll_ico_single_cqe(cq, sq, rq, cqe);
+	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+	 * otherwise a cq overrun may occur
+	 */
+	sqcc = sq->cc;
+
+	i = 0;
+	do {
+		u16 wqe_counter;
+		bool last_wqe;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
+			netdev_WARN_ONCE(cq->channel->netdev,
+					 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
+			break;
+		}
+		do {
+			struct mlx5e_sq_wqe_info *wi;
+			u16 ci;
+
+			last_wqe = (sqcc == wqe_counter);
+
+			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			wi = &sq->db.ico_wqe[ci];
+
+			if (likely(wi->opcode == MLX5_OPCODE_UMR)) {
+				sqcc += MLX5E_UMR_WQEBBS;
+				wi->umr.rq->mpwqe.umr_completed++;
+			} else if (likely(wi->opcode == MLX5_OPCODE_NOP)) {
+				sqcc++;
+			} else {
+				netdev_WARN_ONCE(cq->channel->netdev,
+						 "Bad OPCODE in ICOSQ WQE info: 0x%x\n",
+						 wi->opcode);
+			}
+
+		} while (!last_wqe);
+
+	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+
+	sq->cc = sqcc;
 
 	mlx5_cqwq_update_db_record(&cq->wq);
 }
 
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 {
+	struct mlx5e_icosq *sq = &rq->channel->icosq;
 	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
+	u8  umr_completed = rq->mpwqe.umr_completed;
+	int alloc_err = 0;
+	u8  missing, i;
+	u16 head;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return false;
 
-	mlx5e_poll_ico_cq(&rq->channel->icosq.cq, rq);
+	if (umr_completed) {
+		mlx5e_post_rx_mpwqe(rq, umr_completed);
+		rq->mpwqe.umr_in_progress -= umr_completed;
+		rq->mpwqe.umr_completed = 0;
+	}
+
+	missing = mlx5_wq_ll_missing(wq) - rq->mpwqe.umr_in_progress;
 
-	if (mlx5_wq_ll_is_full(wq))
+	if (unlikely(rq->mpwqe.umr_in_progress > rq->mpwqe.umr_last_bulk))
+		rq->stats->congst_umr++;
+
+#define UMR_WQE_BULK (2)
+	if (likely(missing < UMR_WQE_BULK))
 		return false;
 
-	if (!rq->mpwqe.umr_in_progress)
-		mlx5e_alloc_rx_mpwqe(rq, wq->head);
-	else
-		rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2;
+	head = rq->mpwqe.actual_wq_head;
+	i = missing;
+	do {
+		alloc_err = mlx5e_alloc_rx_mpwqe(rq, head);
+
+		if (unlikely(alloc_err))
+			break;
+		head = mlx5_wq_ll_get_wqe_next_ix(wq, head);
+	} while (--i);
+
+	rq->mpwqe.umr_last_bulk    = missing - i;
+	if (sq->doorbell_cseg) {
+		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, sq->doorbell_cseg);
+		sq->doorbell_cseg = NULL;
+	}
+
+	rq->mpwqe.umr_in_progress += rq->mpwqe.umr_last_bulk;
+	rq->mpwqe.actual_wq_head   = head;
+
+	/* If XSK Fill Ring doesn't have enough frames, busy poll by
+	 * rescheduling the NAPI poll.
+	 */
+	if (unlikely(alloc_err == -ENOMEM && rq->umem))
+		return true;
 
 	return false;
 }
@@ -693,7 +786,14 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth,
 {
 	*proto = ((struct ethhdr *)skb->data)->h_proto;
 	*proto = __vlan_get_protocol(skb, *proto, network_depth);
-	return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+
+	if (*proto == htons(ETH_P_IP))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+	if (*proto == htons(ETH_P_IPV6))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+	return false;
 }
 
 static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
@@ -713,17 +813,6 @@ static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
 	rq->stats->ecn_mark += !!rc;
 }
 
-static u32 mlx5e_get_fcs(const struct sk_buff *skb)
-{
-	const void *fcs_bytes;
-	u32 _fcs_bytes;
-
-	fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
-				       ETH_FCS_LEN, &_fcs_bytes);
-
-	return __get_unaligned_cpu32(fcs_bytes);
-}
-
 static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 {
 	void *ip_p = skb->data + network_depth;
@@ -734,6 +823,68 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 
 #define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
 
+#define MAX_PADDING 8
+
+static void
+tail_padding_csum_slow(struct sk_buff *skb, int offset, int len,
+		       struct mlx5e_rq_stats *stats)
+{
+	stats->csum_complete_tail_slow++;
+	skb->csum = csum_block_add(skb->csum,
+				   skb_checksum(skb, offset, len, 0),
+				   offset);
+}
+
+static void
+tail_padding_csum(struct sk_buff *skb, int offset,
+		  struct mlx5e_rq_stats *stats)
+{
+	u8 tail_padding[MAX_PADDING];
+	int len = skb->len - offset;
+	void *tail;
+
+	if (unlikely(len > MAX_PADDING)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	tail = skb_header_pointer(skb, offset, len, tail_padding);
+	if (unlikely(!tail)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	stats->csum_complete_tail++;
+	skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset);
+}
+
+static void
+mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
+		       struct mlx5e_rq_stats *stats)
+{
+	struct ipv6hdr *ip6;
+	struct iphdr   *ip4;
+	int pkt_len;
+
+	switch (proto) {
+	case htons(ETH_P_IP):
+		ip4 = (struct iphdr *)(skb->data + network_depth);
+		pkt_len = network_depth + ntohs(ip4->tot_len);
+		break;
+	case htons(ETH_P_IPV6):
+		ip6 = (struct ipv6hdr *)(skb->data + network_depth);
+		pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len);
+		break;
+	default:
+		return;
+	}
+
+	if (likely(pkt_len >= skb->len))
+		return;
+
+	tail_padding_csum(skb, pkt_len, stats);
+}
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -753,7 +904,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
+	/* True when explicitly set via priv flag, or XDP prog is loaded */
+	if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
 		goto csum_unnecessary;
 
 	/* CQE csum doesn't cover padding octets in short ethernet
@@ -771,8 +923,14 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
 			goto csum_unnecessary;
 
+		stats->csum_complete++;
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+
+		if (test_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state))
+			return; /* CQE csum covers all received bytes */
+
+		/* csum might need some fixups ...*/
 		if (network_depth > ETH_HLEN)
 			/* CQE csum is calculated from the IP header and does
 			 * not cover VLAN headers (if present). This will add
@@ -781,18 +939,14 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum = csum_partial(skb->data + ETH_HLEN,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
-		if (unlikely(netdev->features & NETIF_F_RXFCS))
-			skb->csum = csum_block_add(skb->csum,
-						   (__force __wsum)mlx5e_get_fcs(skb),
-						   skb->len - ETH_FCS_LEN);
-		stats->csum_complete++;
+
+		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
 		return;
 	}
 
 csum_unnecessary:
 	if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
-		   ((cqe->hds_ip_ext & CQE_L4_OK) ||
-		    (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) {
+		   (cqe->hds_ip_ext & CQE_L4_OK))) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		if (cqe_is_tunneled(cqe)) {
 			skb->csum_level = 1;
@@ -917,7 +1071,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	}
 
 	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt);
+	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false);
 	rcu_read_unlock();
 	if (consumed)
 		return NULL; /* page/packet was consumed by XDP */
@@ -973,8 +1127,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	}
 
 	/* copy header */
-	mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset,
-			      0, headlen);
+	mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
 	skb->len  += headlen;
@@ -994,7 +1147,10 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	wi       = get_frag(rq, ci);
 	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
-	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
+			      mlx5e_skb_from_cqe_linear,
+			      mlx5e_skb_from_cqe_nonlinear,
+			      rq, cqe, wi, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
@@ -1096,8 +1252,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		di++;
 	}
 	/* copy header */
-	mlx5e_copy_skb_header_mpwqe(rq->pdev, skb, head_di,
-				    head_offset, headlen);
+	mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
 	skb->len  += headlen;
@@ -1133,7 +1288,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	prefetch(data);
 
 	rcu_read_lock();
-	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32);
+	consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, false);
 	rcu_read_unlock();
 	if (consumed) {
 		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
@@ -1182,8 +1337,10 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 	cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
 
-	skb = rq->mpwqe.skb_from_cqe_mpwrq(rq, wi, cqe_bcnt, head_offset,
-					   page_idx);
+	skb = INDIRECT_CALL_2(rq->mpwqe.skb_from_cqe_mpwrq,
+			      mlx5e_skb_from_cqe_mpwrq_linear,
+			      mlx5e_skb_from_cqe_mpwrq_nonlinear,
+			      rq, wi, cqe_bcnt, head_offset, page_idx);
 	if (!skb)
 		goto mpwrq_cqe_out;
 
@@ -1203,16 +1360,17 @@ mpwrq_cqe_out:
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 {
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
+	struct mlx5_cqwq *cqwq = &cq->wq;
 	struct mlx5_cqe64 *cqe;
 	int work_done = 0;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return 0;
 
-	if (cq->decmprs_left)
-		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
+	if (rq->cqd.left)
+		work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget);
 
-	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	cqe = mlx5_cqwq_get_cqe(cqwq);
 	if (!cqe) {
 		if (unlikely(work_done))
 			goto out;
@@ -1222,21 +1380,22 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	do {
 		if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) {
 			work_done +=
-				mlx5e_decompress_cqes_start(rq, cq,
+				mlx5e_decompress_cqes_start(rq, cqwq,
 							    budget - work_done);
 			continue;
 		}
 
-		mlx5_cqwq_pop(&cq->wq);
+		mlx5_cqwq_pop(cqwq);
 
-		rq->handle_rx_cqe(rq, cqe);
-	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+		INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
+				mlx5e_handle_rx_cqe, rq, cqe);
+	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
 
 out:
 	if (rq->xdp_prog)
 		mlx5e_xdp_rx_poll_complete(rq);
 
-	mlx5_cqwq_update_db_record(&cq->wq);
+	mlx5_cqwq_update_db_record(cqwq);
 
 	/* ensure cq space is freed before enabling more cqes */
 	wmb();
@@ -1297,8 +1456,14 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 
 	skb->protocol = *((__be16 *)(skb->data));
 
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+	if (netdev->features & NETIF_F_RXCSUM) {
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+		stats->csum_complete++;
+	} else {
+		skb->ip_summed = CHECKSUM_NONE;
+		stats->csum_none++;
+	}
 
 	if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
 		skb_hwtstamps(skb)->hwtstamp =
@@ -1317,7 +1482,6 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 
 	skb->dev = netdev;
 
-	stats->csum_complete++;
 	stats->packets++;
 	stats->bytes += cqe_bcnt;
 }
@@ -1334,7 +1498,10 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	wi       = get_frag(rq, ci);
 	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
-	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
+			      mlx5e_skb_from_cqe_linear,
+			      mlx5e_skb_from_cqe_nonlinear,
+			      rq, cqe, wi, cqe_bcnt);
 	if (!skb)
 		goto wq_free_wqe;
 
@@ -1366,7 +1533,10 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	wi       = get_frag(rq, ci);
 	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
-	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
+	skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe,
+			      mlx5e_skb_from_cqe_linear,
+			      mlx5e_skb_from_cqe_nonlinear,
+			      rq, cqe, wi, cqe_bcnt);
 	if (unlikely(!skb)) {
 		/* a DROP, save the page-reuse checks */
 		mlx5e_free_rx_wqe(rq, wi, true);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 4382ef85488c..840ec945ccba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -64,7 +64,7 @@ static int mlx5e_test_health_info(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_health *health = &priv->mdev->priv.health;
 
-	return health->sick ? 1 : 0;
+	return health->fatal_error ? 1 : 0;
 }
 
 static int mlx5e_test_link_state(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index d3fe48ff9da9..539b4d3656da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -48,8 +48,15 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) },
 
 #ifdef CONFIG_MLX5_EN_TLS
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_resync_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_no_sync_data) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_bypass_req) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) },
 #endif
 
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
@@ -59,10 +66,14 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
@@ -77,6 +88,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
@@ -87,7 +100,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_page_reuse) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_reuse) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
@@ -99,7 +111,33 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_force_irq) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_unnecessary) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_none) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_ecn_mark) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_removed_vlan_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_xdp_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_xdp_redirect) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_wqe_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_oversize_pkts_sw_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_buff_alloc_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_blks) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_pkts) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_congst_umr) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_arfs_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_mpwqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_inlnw) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_cqes) },
 };
 
 #define NUM_SW_COUNTERS			ARRAY_SIZE(sw_stats_desc)
@@ -127,9 +165,9 @@ static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
 	return idx;
 }
 
-void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
+static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 {
-	struct mlx5e_sw_stats temp, *s = &temp;
+	struct mlx5e_sw_stats *s = &priv->stats.sw;
 	int i;
 
 	memset(s, 0, sizeof(*s));
@@ -139,6 +177,8 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			&priv->channel_stats[i];
 		struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq;
 		struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq;
+		struct mlx5e_xdpsq_stats *xsksq_stats = &channel_stats->xsksq;
+		struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
 		struct mlx5e_ch_stats *ch_stats = &channel_stats->ch;
 		int j;
@@ -151,11 +191,15 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_complete_tail += rq_stats->csum_complete_tail;
+		s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop     += rq_stats->xdp_drop;
 		s->rx_xdp_redirect += rq_stats->xdp_redirect;
 		s->rx_xdp_tx_xmit  += xdpsq_stats->xmit;
+		s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe;
+		s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw;
 		s->rx_xdp_tx_full  += xdpsq_stats->full;
 		s->rx_xdp_tx_err   += xdpsq_stats->err;
 		s->rx_xdp_tx_cqe   += xdpsq_stats->cqes;
@@ -166,7 +210,6 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
-		s->rx_page_reuse  += rq_stats->page_reuse;
 		s->rx_cache_reuse += rq_stats->cache_reuse;
 		s->rx_cache_full  += rq_stats->cache_full;
 		s->rx_cache_empty += rq_stats->cache_empty;
@@ -178,12 +221,41 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->ch_poll        += ch_stats->poll;
 		s->ch_arm         += ch_stats->arm;
 		s->ch_aff_change  += ch_stats->aff_change;
+		s->ch_force_irq   += ch_stats->force_irq;
 		s->ch_eq_rearm    += ch_stats->eq_rearm;
 		/* xdp redirect */
 		s->tx_xdp_xmit    += xdpsq_red_stats->xmit;
+		s->tx_xdp_mpwqe   += xdpsq_red_stats->mpwqe;
+		s->tx_xdp_inlnw   += xdpsq_red_stats->inlnw;
 		s->tx_xdp_full    += xdpsq_red_stats->full;
 		s->tx_xdp_err     += xdpsq_red_stats->err;
 		s->tx_xdp_cqes    += xdpsq_red_stats->cqes;
+		/* AF_XDP zero-copy */
+		s->rx_xsk_packets                += xskrq_stats->packets;
+		s->rx_xsk_bytes                  += xskrq_stats->bytes;
+		s->rx_xsk_csum_complete          += xskrq_stats->csum_complete;
+		s->rx_xsk_csum_unnecessary       += xskrq_stats->csum_unnecessary;
+		s->rx_xsk_csum_unnecessary_inner += xskrq_stats->csum_unnecessary_inner;
+		s->rx_xsk_csum_none              += xskrq_stats->csum_none;
+		s->rx_xsk_ecn_mark               += xskrq_stats->ecn_mark;
+		s->rx_xsk_removed_vlan_packets   += xskrq_stats->removed_vlan_packets;
+		s->rx_xsk_xdp_drop               += xskrq_stats->xdp_drop;
+		s->rx_xsk_xdp_redirect           += xskrq_stats->xdp_redirect;
+		s->rx_xsk_wqe_err                += xskrq_stats->wqe_err;
+		s->rx_xsk_mpwqe_filler_cqes      += xskrq_stats->mpwqe_filler_cqes;
+		s->rx_xsk_mpwqe_filler_strides   += xskrq_stats->mpwqe_filler_strides;
+		s->rx_xsk_oversize_pkts_sw_drop  += xskrq_stats->oversize_pkts_sw_drop;
+		s->rx_xsk_buff_alloc_err         += xskrq_stats->buff_alloc_err;
+		s->rx_xsk_cqe_compress_blks      += xskrq_stats->cqe_compress_blks;
+		s->rx_xsk_cqe_compress_pkts      += xskrq_stats->cqe_compress_pkts;
+		s->rx_xsk_congst_umr             += xskrq_stats->congst_umr;
+		s->rx_xsk_arfs_err               += xskrq_stats->arfs_err;
+		s->tx_xsk_xmit                   += xsksq_stats->xmit;
+		s->tx_xsk_mpwqe                  += xsksq_stats->mpwqe;
+		s->tx_xsk_inlnw                  += xsksq_stats->inlnw;
+		s->tx_xsk_full                   += xsksq_stats->full;
+		s->tx_xsk_err                    += xsksq_stats->err;
+		s->tx_xsk_cqes                   += xsksq_stats->cqes;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -206,14 +278,19 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_csum_none		+= sq_stats->csum_none;
 			s->tx_csum_partial	+= sq_stats->csum_partial;
 #ifdef CONFIG_MLX5_EN_TLS
-			s->tx_tls_ooo		+= sq_stats->tls_ooo;
-			s->tx_tls_resync_bytes	+= sq_stats->tls_resync_bytes;
+			s->tx_tls_encrypted_packets += sq_stats->tls_encrypted_packets;
+			s->tx_tls_encrypted_bytes   += sq_stats->tls_encrypted_bytes;
+			s->tx_tls_ctx               += sq_stats->tls_ctx;
+			s->tx_tls_ooo               += sq_stats->tls_ooo;
+			s->tx_tls_resync_bytes      += sq_stats->tls_resync_bytes;
+			s->tx_tls_drop_no_sync_data += sq_stats->tls_drop_no_sync_data;
+			s->tx_tls_drop_bypass_req   += sq_stats->tls_drop_bypass_req;
+			s->tx_tls_dump_bytes        += sq_stats->tls_dump_bytes;
+			s->tx_tls_dump_packets      += sq_stats->tls_dump_packets;
 #endif
 			s->tx_cqes		+= sq_stats->cqes;
 		}
 	}
-
-	memcpy(&priv->stats.sw, s, sizeof(*s));
 }
 
 static const struct counter_desc q_stats_desc[] = {
@@ -1192,6 +1269,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
@@ -1208,7 +1287,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, page_reuse) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_reuse) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
@@ -1229,6 +1307,16 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_partial_inner) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, added_vlan_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) },
+#ifdef CONFIG_MLX5_EN_TLS
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_no_sync_data) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_bypass_req) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) },
+#endif
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
@@ -1241,6 +1329,8 @@ static const struct counter_desc sq_stats_desc[] = {
 
 static const struct counter_desc rq_xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
@@ -1248,16 +1338,50 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = {
 
 static const struct counter_desc xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
 };
 
+static const struct counter_desc xskrq_stats_desc[] = {
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, packets) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, bytes) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_none) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, ecn_mark) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, xdp_drop) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, xdp_redirect) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, wqe_err) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, oversize_pkts_sw_drop) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, congst_umr) },
+	{ MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, arfs_err) },
+};
+
+static const struct counter_desc xsksq_stats_desc[] = {
+	{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
+	{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
+	{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, full) },
+	{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, err) },
+	{ MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
+};
+
 static const struct counter_desc ch_stats_desc[] = {
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, force_irq) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) },
 };
 
@@ -1265,6 +1389,8 @@ static const struct counter_desc ch_stats_desc[] = {
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
 #define NUM_XDPSQ_STATS			ARRAY_SIZE(xdpsq_stats_desc)
 #define NUM_RQ_XDPSQ_STATS		ARRAY_SIZE(rq_xdpsq_stats_desc)
+#define NUM_XSKRQ_STATS			ARRAY_SIZE(xskrq_stats_desc)
+#define NUM_XSKSQ_STATS			ARRAY_SIZE(xsksq_stats_desc)
 #define NUM_CH_STATS			ARRAY_SIZE(ch_stats_desc)
 
 static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
@@ -1275,13 +1401,16 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
 	       (NUM_CH_STATS * max_nch) +
 	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc) +
 	       (NUM_RQ_XDPSQ_STATS * max_nch) +
-	       (NUM_XDPSQ_STATS * max_nch);
+	       (NUM_XDPSQ_STATS * max_nch) +
+	       (NUM_XSKRQ_STATS * max_nch * priv->xsk.ever_used) +
+	       (NUM_XSKSQ_STATS * max_nch * priv->xsk.ever_used);
 }
 
 static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 					   int idx)
 {
 	int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
+	bool is_xsk = priv->xsk.ever_used;
 	int i, j, tc;
 
 	for (i = 0; i < max_nch; i++)
@@ -1293,6 +1422,9 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				rq_stats_desc[j].format, i);
+		for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				xskrq_stats_desc[j].format, i);
 		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				rq_xdpsq_stats_desc[j].format, i);
@@ -1305,10 +1437,14 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 					sq_stats_desc[j].format,
 					priv->channel_tc2txq[i][tc]);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
+		for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				xsksq_stats_desc[j].format, i);
 		for (j = 0; j < NUM_XDPSQ_STATS; j++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				xdpsq_stats_desc[j].format, i);
+	}
 
 	return idx;
 }
@@ -1317,6 +1453,7 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 					 int idx)
 {
 	int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
+	bool is_xsk = priv->xsk.ever_used;
 	int i, j, tc;
 
 	for (i = 0; i < max_nch; i++)
@@ -1330,6 +1467,10 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 			data[idx++] =
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq,
 						     rq_stats_desc, j);
+		for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xskrq,
+						     xskrq_stats_desc, j);
 		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
 			data[idx++] =
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq,
@@ -1343,11 +1484,16 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 					MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc],
 							     sq_stats_desc, j);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
+		for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xsksq,
+						     xsksq_stats_desc, j);
 		for (j = 0; j < NUM_XDPSQ_STATS; j++)
 			data[idx++] =
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq,
 						     xdpsq_stats_desc, j);
+	}
 
 	return idx;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index fe91ec06e3c7..76ac111e14d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -46,6 +46,8 @@
 #define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_XDPSQ_STAT(type, fld) "tx%d_xdp_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_XSKRQ_STAT(type, fld) "rx%d_xsk_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_XSKSQ_STAT(type, fld) "tx%d_xsk_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld)
 
 struct counter_desc {
@@ -71,10 +73,14 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
 	u64 rx_csum_complete;
+	u64 rx_csum_complete_tail;
+	u64 rx_csum_complete_tail_slow;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_redirect;
 	u64 rx_xdp_tx_xmit;
+	u64 rx_xdp_tx_mpwqe;
+	u64 rx_xdp_tx_inlnw;
 	u64 rx_xdp_tx_full;
 	u64 rx_xdp_tx_err;
 	u64 rx_xdp_tx_cqe;
@@ -89,6 +95,8 @@ struct mlx5e_sw_stats {
 	u64 tx_queue_wake;
 	u64 tx_cqe_err;
 	u64 tx_xdp_xmit;
+	u64 tx_xdp_mpwqe;
+	u64 tx_xdp_inlnw;
 	u64 tx_xdp_full;
 	u64 tx_xdp_err;
 	u64 tx_xdp_cqes;
@@ -99,7 +107,6 @@ struct mlx5e_sw_stats {
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
-	u64 rx_page_reuse;
 	u64 rx_cache_reuse;
 	u64 rx_cache_full;
 	u64 rx_cache_empty;
@@ -111,12 +118,46 @@ struct mlx5e_sw_stats {
 	u64 ch_poll;
 	u64 ch_arm;
 	u64 ch_aff_change;
+	u64 ch_force_irq;
 	u64 ch_eq_rearm;
 
 #ifdef CONFIG_MLX5_EN_TLS
+	u64 tx_tls_encrypted_packets;
+	u64 tx_tls_encrypted_bytes;
+	u64 tx_tls_ctx;
 	u64 tx_tls_ooo;
 	u64 tx_tls_resync_bytes;
+	u64 tx_tls_drop_no_sync_data;
+	u64 tx_tls_drop_bypass_req;
+	u64 tx_tls_dump_packets;
+	u64 tx_tls_dump_bytes;
 #endif
+
+	u64 rx_xsk_packets;
+	u64 rx_xsk_bytes;
+	u64 rx_xsk_csum_complete;
+	u64 rx_xsk_csum_unnecessary;
+	u64 rx_xsk_csum_unnecessary_inner;
+	u64 rx_xsk_csum_none;
+	u64 rx_xsk_ecn_mark;
+	u64 rx_xsk_removed_vlan_packets;
+	u64 rx_xsk_xdp_drop;
+	u64 rx_xsk_xdp_redirect;
+	u64 rx_xsk_wqe_err;
+	u64 rx_xsk_mpwqe_filler_cqes;
+	u64 rx_xsk_mpwqe_filler_strides;
+	u64 rx_xsk_oversize_pkts_sw_drop;
+	u64 rx_xsk_buff_alloc_err;
+	u64 rx_xsk_cqe_compress_blks;
+	u64 rx_xsk_cqe_compress_pkts;
+	u64 rx_xsk_congst_umr;
+	u64 rx_xsk_arfs_err;
+	u64 tx_xsk_xmit;
+	u64 tx_xsk_mpwqe;
+	u64 tx_xsk_inlnw;
+	u64 tx_xsk_full;
+	u64 tx_xsk_err;
+	u64 tx_xsk_cqes;
 };
 
 struct mlx5e_qcounter_stats {
@@ -181,6 +222,8 @@ struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_complete_tail;
+	u64 csum_complete_tail_slow;
 	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;
@@ -197,7 +240,6 @@ struct mlx5e_rq_stats {
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
-	u64 page_reuse;
 	u64 cache_reuse;
 	u64 cache_full;
 	u64 cache_empty;
@@ -221,8 +263,15 @@ struct mlx5e_sq_stats {
 	u64 added_vlan_packets;
 	u64 nop;
 #ifdef CONFIG_MLX5_EN_TLS
+	u64 tls_encrypted_packets;
+	u64 tls_encrypted_bytes;
+	u64 tls_ctx;
 	u64 tls_ooo;
 	u64 tls_resync_bytes;
+	u64 tls_drop_no_sync_data;
+	u64 tls_drop_bypass_req;
+	u64 tls_dump_packets;
+	u64 tls_dump_bytes;
 #endif
 	/* less likely accessed in data path */
 	u64 csum_none;
@@ -237,6 +286,8 @@ struct mlx5e_sq_stats {
 
 struct mlx5e_xdpsq_stats {
 	u64 xmit;
+	u64 mpwqe;
+	u64 inlnw;
 	u64 full;
 	u64 err;
 	/* dirtied @completion */
@@ -248,6 +299,7 @@ struct mlx5e_ch_stats {
 	u64 poll;
 	u64 arm;
 	u64 aff_change;
+	u64 force_irq;
 	u64 eq_rearm;
 };
 
@@ -277,7 +329,6 @@ struct mlx5e_stats_grp {
 extern const struct mlx5e_stats_grp mlx5e_stats_grps[];
 extern const int mlx5e_num_stats_grps;
 
-void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv);
 void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv);
 
 #endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b5c1b039375a..2d6436257f9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -38,13 +38,13 @@
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/device.h>
 #include <linux/rhashtable.h>
-#include <net/switchdev.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_csum.h>
 #include <net/arp.h>
+#include <net/ipv6_stubs.h>
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
@@ -53,6 +53,7 @@
 #include "en/port.h"
 #include "en/tc_tun.h"
 #include "lib/devcom.h"
+#include "lib/geneve.h"
 
 struct mlx5_nic_flow_attr {
 	u32 action;
@@ -76,6 +77,7 @@ enum {
 	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 2),
 	MLX5E_TC_FLOW_SLOW	  = BIT(MLX5E_TC_FLOW_BASE + 3),
 	MLX5E_TC_FLOW_DUP         = BIT(MLX5E_TC_FLOW_BASE + 4),
+	MLX5E_TC_FLOW_NOT_READY   = BIT(MLX5E_TC_FLOW_BASE + 5),
 };
 
 #define MLX5E_TC_MAX_SPLITS 1
@@ -117,6 +119,7 @@ struct mlx5e_tc_flow {
 	struct list_head	mod_hdr; /* flows sharing the same mod hdr ID */
 	struct list_head	hairpin; /* flows sharing the same hairpin */
 	struct list_head	peer;    /* flows with peer flow */
+	struct list_head	unready; /* flows not ready to be offloaded (e.g due to missing route) */
 	union {
 		struct mlx5_esw_flow_attr esw_attr[0];
 		struct mlx5_nic_flow_attr nic_attr[0];
@@ -124,7 +127,7 @@ struct mlx5e_tc_flow {
 };
 
 struct mlx5e_tc_flow_parse_attr {
-	struct ip_tunnel_info tun_info[MLX5_MAX_FLOW_FWD_VPORTS];
+	const struct ip_tunnel_info *tun_info[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct net_device *filter_dev;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
@@ -662,7 +665,8 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 	}
 
 	netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n",
-		   hp->tirn, hp->pair->rqn[0], hp->pair->peer_mdev->priv.name,
+		   hp->tirn, hp->pair->rqn[0],
+		   dev_name(hp->pair->peer_mdev->device),
 		   hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets);
 
 	hpe->hp = hp;
@@ -699,7 +703,7 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv,
 		hpe = list_entry(next, struct mlx5e_hairpin_entry, flows);
 
 		netdev_dbg(priv->netdev, "del hairpin: peer %s\n",
-			   hpe->hp->pair->peer_mdev->priv.name);
+			   dev_name(hpe->hp->pair->peer_mdev->device));
 
 		mlx5e_hairpin_destroy(hpe->hp);
 		hash_del(&hpe->hairpin_hlist);
@@ -713,19 +717,22 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		      struct mlx5e_tc_flow *flow,
 		      struct netlink_ext_ack *extack)
 {
+	struct mlx5_flow_context *flow_context = &parse_attr->spec.flow_context;
 	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
 	struct mlx5_core_dev *dev = priv->mdev;
 	struct mlx5_flow_destination dest[2] = {};
 	struct mlx5_flow_act flow_act = {
 		.action = attr->action,
-		.flow_tag = attr->flow_tag,
 		.reformat_id = 0,
-		.flags    = FLOW_ACT_HAS_TAG | FLOW_ACT_NO_APPEND,
+		.flags    = FLOW_ACT_NO_APPEND,
 	};
 	struct mlx5_fc *counter = NULL;
 	bool table_created = false;
 	int err, dest_ix = 0;
 
+	flow_context->flags |= FLOW_CONTEXT_HAS_TAG;
+	flow_context->flow_tag = attr->flow_tag;
+
 	if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) {
 		err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack);
 		if (err) {
@@ -796,7 +803,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 	}
 
 	if (attr->match_level != MLX5_MATCH_NONE)
-		parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		parse_attr->spec.match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
 
 	flow->rule[0] = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec,
 					    &flow_act, dest, dest_ix);
@@ -851,12 +858,12 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 			       struct mlx5e_tc_flow *flow, int out_index);
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
-			      struct ip_tunnel_info *tun_info,
-			      struct net_device *mirred_dev,
-			      struct net_device **encap_dev,
 			      struct mlx5e_tc_flow *flow,
+			      struct net_device *mirred_dev,
+			      int out_index,
 			      struct netlink_ext_ack *extack,
-			      int out_index);
+			      struct net_device **encap_dev,
+			      bool *encap_valid);
 
 static struct mlx5_flow_handle *
 mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
@@ -928,21 +935,42 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
 	flow->flags &= ~MLX5E_TC_FLOW_SLOW;
 }
 
+static void add_unready_flow(struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5_eswitch *esw;
+
+	esw = flow->priv->mdev->priv.eswitch;
+	rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	uplink_priv = &rpriv->uplink_priv;
+
+	flow->flags |= MLX5E_TC_FLOW_NOT_READY;
+	list_add_tail(&flow->unready, &uplink_priv->unready_flows);
+}
+
+static void remove_unready_flow(struct mlx5e_tc_flow *flow)
+{
+	list_del(&flow->unready);
+	flow->flags &= ~MLX5E_TC_FLOW_NOT_READY;
+}
+
 static int
 mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
-		      struct mlx5e_tc_flow_parse_attr *parse_attr,
 		      struct mlx5e_tc_flow *flow,
 		      struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	u32 max_chain = mlx5_eswitch_get_chain_range(esw);
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
 	u16 max_prio = mlx5_eswitch_get_prio_range(esw);
 	struct net_device *out_dev, *encap_dev = NULL;
 	struct mlx5_fc *counter = NULL;
 	struct mlx5e_rep_priv *rpriv;
 	struct mlx5e_priv *out_priv;
-	int err = 0, encap_err = 0;
+	bool encap_valid = true;
+	int err = 0;
 	int out_index;
 
 	if (!mlx5_eswitch_prios_supported(esw) && attr->prio != 1) {
@@ -968,17 +996,14 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		if (!(attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
 			continue;
 
-		mirred_ifindex = attr->parse_attr->mirred_ifindex[out_index];
+		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
 		out_dev = __dev_get_by_index(dev_net(priv->netdev),
 					     mirred_ifindex);
-		err = mlx5e_attach_encap(priv,
-					 &parse_attr->tun_info[out_index],
-					 out_dev, &encap_dev, flow,
-					 extack, out_index);
-		if (err && err != -EAGAIN)
+		err = mlx5e_attach_encap(priv, flow, out_dev, out_index,
+					 extack, &encap_dev, &encap_valid);
+		if (err)
 			goto err_attach_encap;
-		if (err == -EAGAIN)
-			encap_err = err;
+
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
 		attr->dests[out_index].rep = rpriv->rep;
@@ -1006,10 +1031,11 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		attr->counter = counter;
 	}
 
-	/* we get here if (1) there's no error or when
-	 * (2) there's an encap action and we're on -EAGAIN (no valid neigh)
+	/* we get here if one of the following takes place:
+	 * (1) there's no error
+	 * (2) there's an encap action and we don't have valid neigh
 	 */
-	if (encap_err == -EAGAIN) {
+	if (!encap_valid) {
 		/* continue with goto slow path rule instead */
 		struct mlx5_esw_flow_attr slow_attr;
 
@@ -1041,6 +1067,19 @@ err_max_prio_chain:
 	return err;
 }
 
+static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_flow_spec *spec = &flow->esw_attr->parse_attr->spec;
+	void *headers_v = MLX5_ADDR_OF(fte_match_param,
+				       spec->match_value,
+				       misc_parameters_3);
+	u32 geneve_tlv_opt_0_data = MLX5_GET(fte_match_set_misc3,
+					     headers_v,
+					     geneve_tlv_option_0_data);
+
+	return !!geneve_tlv_opt_0_data;
+}
+
 static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 				  struct mlx5e_tc_flow *flow)
 {
@@ -1049,6 +1088,12 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr slow_attr;
 	int out_index;
 
+	if (flow->flags & MLX5E_TC_FLOW_NOT_READY) {
+		remove_unready_flow(flow);
+		kvfree(attr->parse_attr);
+		return;
+	}
+
 	if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 		if (flow->flags & MLX5E_TC_FLOW_SLOW)
 			mlx5e_tc_unoffload_from_slow_path(esw, flow, &slow_attr);
@@ -1056,6 +1101,9 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 			mlx5e_tc_unoffload_fdb_rules(esw, flow, attr);
 	}
 
+	if (mlx5_flow_has_geneve_opt(flow))
+		mlx5_geneve_tlv_option_del(priv->mdev->geneve);
+
 	mlx5_eswitch_del_vlan_action(esw, attr);
 
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
@@ -1302,7 +1350,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5_flow_spec *spec,
-			     struct tc_cls_flower_offload *f,
+			     struct flow_cls_offload *f,
 			     struct net_device *filter_dev, u8 *match_level)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -1310,12 +1358,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 				       outer_headers);
 	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				       outer_headers);
-
-	struct flow_dissector_key_control *enc_control =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-					  f->key);
-	int err = 0;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	int err;
 
 	err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f,
 				 headers_c, headers_v, match_level);
@@ -1325,79 +1369,68 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		return err;
 	}
 
-	if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_enc_ipv4_addrs(rule, &match);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 src_ipv4_src_ipv6.ipv4_layout.ipv4,
-			 ntohl(mask->src));
+			 ntohl(match.mask->src));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
 			 src_ipv4_src_ipv6.ipv4_layout.ipv4,
-			 ntohl(key->src));
+			 ntohl(match.key->src));
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
-			 ntohl(mask->dst));
+			 ntohl(match.mask->dst));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
 			 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
-			 ntohl(key->dst));
+			 ntohl(match.key->dst));
 
 		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP);
-	} else if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
-						  f->mask);
+	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match;
 
+		flow_rule_match_enc_ipv6_addrs(rule, &match);
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 
 		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
-		struct flow_dissector_key_ip *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IP,
-						  f->key);
-		struct flow_dissector_key_ip *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IP,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_match_ip match;
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3);
+		flow_rule_match_enc_ip(rule, &match);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn,
+			 match.mask->tos & 0x3);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn,
+			 match.key->tos & 0x3);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos  >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp,
+			 match.mask->tos >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp,
+			 match.key->tos  >> 2);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit,
+			 match.mask->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit,
+			 match.key->ttl);
 
-		if (mask->ttl &&
+		if (match.mask->ttl &&
 		    !MLX5_CAP_ESW_FLOWTABLE_FDB
 			(priv->mdev,
 			 ft_field_support.outer_ipv4_ttl)) {
@@ -1423,9 +1456,29 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static void *get_match_headers_criteria(u32 flags,
+					struct mlx5_flow_spec *spec)
+{
+	return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ?
+		MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			     inner_headers) :
+		MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			     outer_headers);
+}
+
+static void *get_match_headers_value(u32 flags,
+				     struct mlx5_flow_spec *spec)
+{
+	return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ?
+		MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			     inner_headers) :
+		MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			     outer_headers);
+}
+
 static int __parse_cls_flower(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
-			      struct tc_cls_flower_offload *f,
+			      struct flow_cls_offload *f,
 			      struct net_device *filter_dev,
 			      u8 *match_level, u8 *tunnel_match_level)
 {
@@ -1438,12 +1491,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				    misc_parameters);
 	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    misc_parameters);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 
 	*match_level = MLX5_MATCH_NONE;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -1459,70 +1514,64 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_TCP) |
 	      BIT(FLOW_DISSECTOR_KEY_IP)  |
-	      BIT(FLOW_DISSECTOR_KEY_ENC_IP))) {
+	      BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
+	      BIT(FLOW_DISSECTOR_KEY_ENC_OPTS))) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported key");
 		netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n",
-			    f->dissector->used_keys);
+			    dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if ((dissector_uses_key(f->dissector,
-				FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) ||
-	     dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) ||
-	     dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) &&
-	    dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-						  f->key);
-		switch (key->addr_type) {
-		case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
-		case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
-			if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level))
-				return -EOPNOTSUPP;
-			break;
-		default:
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) ||
+	    flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) ||
+	    flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID) ||
+	    flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) ||
+	    flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+		if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level))
 			return -EOPNOTSUPP;
-		}
 
 		/* In decap flow, header pointers should point to the inner
 		 * headers, outer header were already set by parse_tunnel_attr
 		 */
-		headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-					 inner_headers);
-		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-					 inner_headers);
-	}
-
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
+		headers_c = get_match_headers_criteria(MLX5_FLOW_CONTEXT_ACTION_DECAP,
+						       spec);
+		headers_v = get_match_headers_value(MLX5_FLOW_CONTEXT_ACTION_DECAP,
+						    spec);
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
-			 ntohs(mask->n_proto));
+			 ntohs(match.mask->n_proto));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-			 ntohs(key->n_proto));
+			 ntohs(match.key->n_proto));
 
-		if (mask->n_proto)
+		if (match.mask->n_proto)
 			*match_level = MLX5_MATCH_L2;
 	}
-
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
-		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
-			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN) ||
+	    is_vlan_dev(filter_dev)) {
+		struct flow_dissector_key_vlan filter_dev_mask;
+		struct flow_dissector_key_vlan filter_dev_key;
+		struct flow_match_vlan match;
+
+		if (is_vlan_dev(filter_dev)) {
+			match.key = &filter_dev_key;
+			match.key->vlan_id = vlan_dev_vlan_id(filter_dev);
+			match.key->vlan_tpid = vlan_dev_vlan_proto(filter_dev);
+			match.key->vlan_priority = 0;
+			match.mask = &filter_dev_mask;
+			memset(match.mask, 0xff, sizeof(*match.mask));
+			match.mask->vlan_priority = 0;
+		} else {
+			flow_rule_match_vlan(rule, &match);
+		}
+		if (match.mask->vlan_id ||
+		    match.mask->vlan_priority ||
+		    match.mask->vlan_tpid) {
+			if (match.key->vlan_tpid == htons(ETH_P_8021AD)) {
 				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 					 svlan_tag, 1);
 				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
@@ -1534,11 +1583,15 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 					 cvlan_tag, 1);
 			}
 
-			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid,
+				 match.mask->vlan_id);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid,
+				 match.key->vlan_id);
 
-			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio,
+				 match.mask->vlan_priority);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio,
+				 match.key->vlan_priority);
 
 			*match_level = MLX5_MATCH_L2;
 		}
@@ -1548,17 +1601,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		*match_level = MLX5_MATCH_L2;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CVLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CVLAN,
-						  f->mask);
-		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
-			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_cvlan(rule, &match);
+		if (match.mask->vlan_id ||
+		    match.mask->vlan_priority ||
+		    match.mask->vlan_tpid) {
+			if (match.key->vlan_tpid == htons(ETH_P_8021AD)) {
 				MLX5_SET(fte_match_set_misc, misc_c,
 					 outer_second_svlan_tag, 1);
 				MLX5_SET(fte_match_set_misc, misc_v,
@@ -1571,69 +1621,58 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			}
 
 			MLX5_SET(fte_match_set_misc, misc_c, outer_second_vid,
-				 mask->vlan_id);
+				 match.mask->vlan_id);
 			MLX5_SET(fte_match_set_misc, misc_v, outer_second_vid,
-				 key->vlan_id);
+				 match.key->vlan_id);
 			MLX5_SET(fte_match_set_misc, misc_c, outer_second_prio,
-				 mask->vlan_priority);
+				 match.mask->vlan_priority);
 			MLX5_SET(fte_match_set_misc, misc_v, outer_second_prio,
-				 key->vlan_priority);
+				 match.key->vlan_priority);
 
 			*match_level = MLX5_MATCH_L2;
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
+		flow_rule_match_eth_addrs(rule, &match);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 					     dmac_47_16),
-				mask->dst);
+				match.mask->dst);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 					     dmac_47_16),
-				key->dst);
+				match.key->dst);
 
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 					     smac_47_16),
-				mask->src);
+				match.mask->src);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 					     smac_47_16),
-				key->src);
+				match.key->src);
 
-		if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
+		if (!is_zero_ether_addr(match.mask->src) ||
+		    !is_zero_ether_addr(match.mask->dst))
 			*match_level = MLX5_MATCH_L2;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		struct flow_dissector_key_control *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->mask);
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 
 		/* the HW doesn't support frag first/later */
-		if (mask->flags & FLOW_DIS_FIRST_FRAG)
+		if (match.mask->flags & FLOW_DIS_FIRST_FRAG)
 			return -EOPNOTSUPP;
 
-		if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
+		if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
-				 key->flags & FLOW_DIS_IS_FRAGMENT);
+				 match.key->flags & FLOW_DIS_IS_FRAGMENT);
 
 			/* the HW doesn't need L3 inline to match on frag=no */
-			if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
+			if (!(match.key->flags & FLOW_DIS_IS_FRAGMENT))
 				*match_level = MLX5_MATCH_L2;
 	/* ***  L2 attributes parsing up to here *** */
 			else
@@ -1641,102 +1680,85 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
-		ip_proto = key->ip_proto;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		ip_proto = match.key->ip_proto;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
-			 mask->ip_proto);
+			 match.mask->ip_proto);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
-			 key->ip_proto);
+			 match.key->ip_proto);
 
-		if (mask->ip_proto)
+		if (match.mask->ip_proto)
 			*match_level = MLX5_MATCH_L3;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->mask);
+		struct flow_match_ipv4_addrs match;
 
+		flow_rule_match_ipv4_addrs(rule, &match);
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
-		       &mask->src, sizeof(mask->src));
+		       &match.mask->src, sizeof(match.mask->src));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
-		       &key->src, sizeof(key->src));
+		       &match.key->src, sizeof(match.key->src));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
-		       &mask->dst, sizeof(mask->dst));
+		       &match.mask->dst, sizeof(match.mask->dst));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
-		       &key->dst, sizeof(key->dst));
+		       &match.key->dst, sizeof(match.key->dst));
 
-		if (mask->src || mask->dst)
+		if (match.mask->src || match.mask->dst)
 			*match_level = MLX5_MATCH_L3;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->mask);
+		struct flow_match_ipv6_addrs match;
 
+		flow_rule_match_ipv6_addrs(rule, &match);
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &mask->src, sizeof(mask->src));
+		       &match.mask->src, sizeof(match.mask->src));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &key->src, sizeof(key->src));
+		       &match.key->src, sizeof(match.key->src));
 
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &mask->dst, sizeof(mask->dst));
+		       &match.mask->dst, sizeof(match.mask->dst));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &key->dst, sizeof(key->dst));
+		       &match.key->dst, sizeof(match.key->dst));
 
-		if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY ||
-		    ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY)
+		if (ipv6_addr_type(&match.mask->src) != IPV6_ADDR_ANY ||
+		    ipv6_addr_type(&match.mask->dst) != IPV6_ADDR_ANY)
 			*match_level = MLX5_MATCH_L3;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) {
-		struct flow_dissector_key_ip *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IP,
-						  f->key);
-		struct flow_dissector_key_ip *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IP,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_match_ip match;
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3);
+		flow_rule_match_ip(rule, &match);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn,
+			 match.mask->tos & 0x3);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn,
+			 match.key->tos & 0x3);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos  >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp,
+			 match.mask->tos >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp,
+			 match.key->tos  >> 2);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit,
+			 match.mask->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit,
+			 match.key->ttl);
 
-		if (mask->ttl &&
+		if (match.mask->ttl &&
 		    !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
 						ft_field_support.outer_ipv4_ttl)) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1744,44 +1766,39 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			return -EOPNOTSUPP;
 		}
 
-		if (mask->tos || mask->ttl)
+		if (match.mask->tos || match.mask->ttl)
 			*match_level = MLX5_MATCH_L3;
 	}
 
 	/* ***  L3 attributes parsing up to here *** */
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(rule, &match);
 		switch (ip_proto) {
 		case IPPROTO_TCP:
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 tcp_sport, ntohs(mask->src));
+				 tcp_sport, ntohs(match.mask->src));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 tcp_sport, ntohs(key->src));
+				 tcp_sport, ntohs(match.key->src));
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 tcp_dport, ntohs(mask->dst));
+				 tcp_dport, ntohs(match.mask->dst));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 tcp_dport, ntohs(key->dst));
+				 tcp_dport, ntohs(match.key->dst));
 			break;
 
 		case IPPROTO_UDP:
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 udp_sport, ntohs(mask->src));
+				 udp_sport, ntohs(match.mask->src));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 udp_sport, ntohs(key->src));
+				 udp_sport, ntohs(match.key->src));
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 udp_dport, ntohs(mask->dst));
+				 udp_dport, ntohs(match.mask->dst));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 udp_dport, ntohs(key->dst));
+				 udp_dport, ntohs(match.key->dst));
 			break;
 		default:
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1791,26 +1808,20 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			return -EINVAL;
 		}
 
-		if (mask->src || mask->dst)
+		if (match.mask->src || match.mask->dst)
 			*match_level = MLX5_MATCH_L4;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) {
-		struct flow_dissector_key_tcp *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_TCP,
-						  f->key);
-		struct flow_dissector_key_tcp *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_TCP,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
+		struct flow_match_tcp match;
 
+		flow_rule_match_tcp(rule, &match);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags,
-			 ntohs(mask->flags));
+			 ntohs(match.mask->flags));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_flags,
-			 ntohs(key->flags));
+			 ntohs(match.key->flags));
 
-		if (mask->flags)
+		if (match.mask->flags)
 			*match_level = MLX5_MATCH_L4;
 	}
 
@@ -1820,7 +1831,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 static int parse_cls_flower(struct mlx5e_priv *priv,
 			    struct mlx5e_tc_flow *flow,
 			    struct mlx5_flow_spec *spec,
-			    struct tc_cls_flower_offload *f,
+			    struct flow_cls_offload *f,
 			    struct net_device *filter_dev)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -1835,7 +1846,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 
 	if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
 		rep = rpriv->rep;
-		if (rep->vport != FDB_UPLINK_VPORT &&
+		if (rep->vport != MLX5_VPORT_UPLINK &&
 		    (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
 		    esw->offloads.inline_mode < match_level)) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1859,33 +1870,36 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 
 struct pedit_headers {
 	struct ethhdr  eth;
+	struct vlan_hdr vlan;
 	struct iphdr   ip4;
 	struct ipv6hdr ip6;
 	struct tcphdr  tcp;
 	struct udphdr  udp;
 };
 
+struct pedit_headers_action {
+	struct pedit_headers	vals;
+	struct pedit_headers	masks;
+	u32			pedits;
+};
+
 static int pedit_header_offsets[] = {
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp),
+	[FLOW_ACT_MANGLE_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth),
+	[FLOW_ACT_MANGLE_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4),
+	[FLOW_ACT_MANGLE_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6),
+	[FLOW_ACT_MANGLE_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp),
+	[FLOW_ACT_MANGLE_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp),
 };
 
 #define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype])
 
 static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset,
-			 struct pedit_headers *masks,
-			 struct pedit_headers *vals)
+			 struct pedit_headers_action *hdrs)
 {
 	u32 *curr_pmask, *curr_pval;
 
-	if (hdr_type >= __PEDIT_HDR_TYPE_MAX)
-		goto out_err;
-
-	curr_pmask = (u32 *)(pedit_header(masks, hdr_type) + offset);
-	curr_pval  = (u32 *)(pedit_header(vals, hdr_type) + offset);
+	curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset);
+	curr_pval  = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset);
 
 	if (*curr_pmask & mask)  /* disallow acting twice on the same location */
 		goto out_err;
@@ -1903,50 +1917,99 @@ struct mlx5_fields {
 	u8  field;
 	u8  size;
 	u32 offset;
+	u32 match_offset;
 };
 
-#define OFFLOAD(fw_field, size, field, off) \
-		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, offsetof(struct pedit_headers, field) + (off)}
+#define OFFLOAD(fw_field, size, field, off, match_field) \
+		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, \
+		 offsetof(struct pedit_headers, field) + (off), \
+		 MLX5_BYTE_OFF(fte_match_set_lyr_2_4, match_field)}
+
+/* masked values are the same and there are no rewrites that do not have a
+ * match.
+ */
+#define SAME_VAL_MASK(type, valp, maskp, matchvalp, matchmaskp) ({ \
+	type matchmaskx = *(type *)(matchmaskp); \
+	type matchvalx = *(type *)(matchvalp); \
+	type maskx = *(type *)(maskp); \
+	type valx = *(type *)(valp); \
+	\
+	(valx & maskx) == (matchvalx & matchmaskx) && !(maskx & (maskx ^ \
+								 matchmaskx)); \
+})
+
+static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp,
+			 void *matchmaskp, int size)
+{
+	bool same = false;
+
+	switch (size) {
+	case sizeof(u8):
+		same = SAME_VAL_MASK(u8, valp, maskp, matchvalp, matchmaskp);
+		break;
+	case sizeof(u16):
+		same = SAME_VAL_MASK(u16, valp, maskp, matchvalp, matchmaskp);
+		break;
+	case sizeof(u32):
+		same = SAME_VAL_MASK(u32, valp, maskp, matchvalp, matchmaskp);
+		break;
+	}
+
+	return same;
+}
 
 static struct mlx5_fields fields[] = {
-	OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0),
-	OFFLOAD(DMAC_15_0,  2, eth.h_dest[4], 0),
-	OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0),
-	OFFLOAD(SMAC_15_0,  2, eth.h_source[4], 0),
-	OFFLOAD(ETHERTYPE,  2, eth.h_proto, 0),
-
-	OFFLOAD(IP_TTL, 1, ip4.ttl,   0),
-	OFFLOAD(SIPV4,  4, ip4.saddr, 0),
-	OFFLOAD(DIPV4,  4, ip4.daddr, 0),
-
-	OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0),
-	OFFLOAD(SIPV6_95_64,  4, ip6.saddr.s6_addr32[1], 0),
-	OFFLOAD(SIPV6_63_32,  4, ip6.saddr.s6_addr32[2], 0),
-	OFFLOAD(SIPV6_31_0,   4, ip6.saddr.s6_addr32[3], 0),
-	OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0),
-	OFFLOAD(DIPV6_95_64,  4, ip6.daddr.s6_addr32[1], 0),
-	OFFLOAD(DIPV6_63_32,  4, ip6.daddr.s6_addr32[2], 0),
-	OFFLOAD(DIPV6_31_0,   4, ip6.daddr.s6_addr32[3], 0),
-	OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0),
-
-	OFFLOAD(TCP_SPORT, 2, tcp.source,  0),
-	OFFLOAD(TCP_DPORT, 2, tcp.dest,    0),
-	OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5),
-
-	OFFLOAD(UDP_SPORT, 2, udp.source, 0),
-	OFFLOAD(UDP_DPORT, 2, udp.dest,   0),
+	OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0, dmac_47_16),
+	OFFLOAD(DMAC_15_0,  2, eth.h_dest[4], 0, dmac_15_0),
+	OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0, smac_47_16),
+	OFFLOAD(SMAC_15_0,  2, eth.h_source[4], 0, smac_15_0),
+	OFFLOAD(ETHERTYPE,  2, eth.h_proto, 0, ethertype),
+	OFFLOAD(FIRST_VID,  2, vlan.h_vlan_TCI, 0, first_vid),
+
+	OFFLOAD(IP_TTL, 1, ip4.ttl,   0, ttl_hoplimit),
+	OFFLOAD(SIPV4,  4, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4),
+	OFFLOAD(DIPV4,  4, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+
+	OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[0]),
+	OFFLOAD(SIPV6_95_64,  4, ip6.saddr.s6_addr32[1], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[4]),
+	OFFLOAD(SIPV6_63_32,  4, ip6.saddr.s6_addr32[2], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[8]),
+	OFFLOAD(SIPV6_31_0,   4, ip6.saddr.s6_addr32[3], 0,
+		src_ipv4_src_ipv6.ipv6_layout.ipv6[12]),
+	OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[0]),
+	OFFLOAD(DIPV6_95_64,  4, ip6.daddr.s6_addr32[1], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[4]),
+	OFFLOAD(DIPV6_63_32,  4, ip6.daddr.s6_addr32[2], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[8]),
+	OFFLOAD(DIPV6_31_0,   4, ip6.daddr.s6_addr32[3], 0,
+		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
+	OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0, ttl_hoplimit),
+
+	OFFLOAD(TCP_SPORT, 2, tcp.source,  0, tcp_sport),
+	OFFLOAD(TCP_DPORT, 2, tcp.dest,    0, tcp_dport),
+	OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5, tcp_flags),
+
+	OFFLOAD(UDP_SPORT, 2, udp.source, 0, udp_sport),
+	OFFLOAD(UDP_DPORT, 2, udp.dest,   0, udp_dport),
 };
 
 /* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
  * max from the SW pedit action. On success, attr->num_mod_hdr_actions
  * says how many HW actions were actually parsed.
  */
-static int offload_pedit_fields(struct pedit_headers *masks,
-				struct pedit_headers *vals,
+static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
+				u32 *action_flags,
 				struct netlink_ext_ack *extack)
 {
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
+	void *headers_c = get_match_headers_criteria(*action_flags,
+						     &parse_attr->spec);
+	void *headers_v = get_match_headers_value(*action_flags,
+						  &parse_attr->spec);
 	int i, action_size, nactions, max_actions, first, last, next_z;
 	void *s_masks_p, *a_masks_p, *vals_p;
 	struct mlx5_fields *f;
@@ -1957,10 +2020,10 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	__be16 mask_be16;
 	void *action;
 
-	set_masks = &masks[TCA_PEDIT_KEY_EX_CMD_SET];
-	add_masks = &masks[TCA_PEDIT_KEY_EX_CMD_ADD];
-	set_vals = &vals[TCA_PEDIT_KEY_EX_CMD_SET];
-	add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
+	set_masks = &hdrs[0].masks;
+	add_masks = &hdrs[1].masks;
+	set_vals = &hdrs[0].vals;
+	add_vals = &hdrs[1].vals;
 
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
 	action = parse_attr->mod_hdr_actions +
@@ -1970,6 +2033,8 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	nactions = parse_attr->num_mod_hdr_actions;
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		bool skip;
+
 		f = &fields[i];
 		/* avoid seeing bits set from previous iterations */
 		s_mask = 0;
@@ -1998,19 +2063,34 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 			return -EOPNOTSUPP;
 		}
 
+		skip = false;
 		if (s_mask) {
+			void *match_mask = headers_c + f->match_offset;
+			void *match_val = headers_v + f->match_offset;
+
 			cmd  = MLX5_ACTION_TYPE_SET;
 			mask = s_mask;
 			vals_p = (void *)set_vals + f->offset;
+			/* don't rewrite if we have a match on the same value */
+			if (cmp_val_mask(vals_p, s_masks_p, match_val,
+					 match_mask, f->size))
+				skip = true;
 			/* clear to denote we consumed this field */
 			memset(s_masks_p, 0, f->size);
 		} else {
+			u32 zero = 0;
+
 			cmd  = MLX5_ACTION_TYPE_ADD;
 			mask = a_mask;
 			vals_p = (void *)add_vals + f->offset;
+			/* add 0 is no change */
+			if (!memcmp(vals_p, &zero, f->size))
+				skip = true;
 			/* clear to denote we consumed this field */
 			memset(a_masks_p, 0, f->size);
 		}
+		if (skip)
+			continue;
 
 		field_bsize = f->size * BITS_PER_BYTE;
 
@@ -2057,20 +2137,27 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	return 0;
 }
 
+static int mlx5e_flow_namespace_max_modify_action(struct mlx5_core_dev *mdev,
+						  int namespace)
+{
+	if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
+		return MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, max_modify_header_actions);
+	else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
+		return MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_modify_header_actions);
+}
+
 static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
-				 const struct tc_action *a, int namespace,
+				 struct pedit_headers_action *hdrs,
+				 int namespace,
 				 struct mlx5e_tc_flow_parse_attr *parse_attr)
 {
 	int nkeys, action_size, max_actions;
 
-	nkeys = tcf_pedit_nkeys(a);
+	nkeys = hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits +
+		hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits;
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
 
-	if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
-		max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, max_modify_header_actions);
-	else /* namespace is MLX5_FLOW_NAMESPACE_KERNEL - NIC offloading */
-		max_actions = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, max_modify_header_actions);
-
+	max_actions = mlx5e_flow_namespace_max_modify_action(priv->mdev, namespace);
 	/* can get up to crazingly 16 HW actions in 32 bits pedit SW key */
 	max_actions = min(max_actions, nkeys * 16);
 
@@ -2085,57 +2172,67 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
 static const struct pedit_headers zero_masks = {};
 
 static int parse_tc_pedit_action(struct mlx5e_priv *priv,
-				 const struct tc_action *a, int namespace,
+				 const struct flow_action_entry *act, int namespace,
 				 struct mlx5e_tc_flow_parse_attr *parse_attr,
+				 struct pedit_headers_action *hdrs,
 				 struct netlink_ext_ack *extack)
 {
-	struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks;
-	int nkeys, i, err = -EOPNOTSUPP;
+	u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1;
+	int err = -EOPNOTSUPP;
 	u32 mask, val, offset;
-	u8 cmd, htype;
+	u8 htype;
 
-	nkeys = tcf_pedit_nkeys(a);
+	htype = act->mangle.htype;
+	err = -EOPNOTSUPP; /* can't be all optimistic */
 
-	memset(masks, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
-	memset(vals,  0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+	if (htype == FLOW_ACT_MANGLE_UNSPEC) {
+		NL_SET_ERR_MSG_MOD(extack, "legacy pedit isn't offloaded");
+		goto out_err;
+	}
+
+	if (!mlx5e_flow_namespace_max_modify_action(priv->mdev, namespace)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "The pedit offload action is not supported");
+		goto out_err;
+	}
 
-	for (i = 0; i < nkeys; i++) {
-		htype = tcf_pedit_htype(a, i);
-		cmd = tcf_pedit_cmd(a, i);
-		err = -EOPNOTSUPP; /* can't be all optimistic */
+	mask = act->mangle.mask;
+	val = act->mangle.val;
+	offset = act->mangle.offset;
 
-		if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "legacy pedit isn't offloaded");
-			goto out_err;
-		}
+	err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd]);
+	if (err)
+		goto out_err;
 
-		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) {
-			NL_SET_ERR_MSG_MOD(extack, "pedit cmd isn't offloaded");
-			goto out_err;
-		}
+	hdrs[cmd].pedits++;
 
-		mask = tcf_pedit_mask(a, i);
-		val = tcf_pedit_val(a, i);
-		offset = tcf_pedit_offset(a, i);
+	return 0;
+out_err:
+	return err;
+}
 
-		err = set_pedit_val(htype, ~mask, val, offset, &masks[cmd], &vals[cmd]);
-		if (err)
-			goto out_err;
-	}
+static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr,
+				 struct pedit_headers_action *hdrs,
+				 u32 *action_flags,
+				 struct netlink_ext_ack *extack)
+{
+	struct pedit_headers *cmd_masks;
+	int err;
+	u8 cmd;
 
 	if (!parse_attr->mod_hdr_actions) {
-		err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
+		err = alloc_mod_hdr_actions(priv, hdrs, namespace, parse_attr);
 		if (err)
 			goto out_err;
 	}
 
-	err = offload_pedit_fields(masks, vals, parse_attr, extack);
+	err = offload_pedit_fields(hdrs, parse_attr, action_flags, extack);
 	if (err < 0)
 		goto out_dealloc_parsed_actions;
 
 	for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
-		cmd_masks = &masks[cmd];
+		cmd_masks = &hdrs[cmd].masks;
 		if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "attempt to offload an unsupported field");
@@ -2184,23 +2281,65 @@ static bool csum_offload_supported(struct mlx5e_priv *priv,
 	return true;
 }
 
+struct ip_ttl_word {
+	__u8	ttl;
+	__u8	protocol;
+	__sum16	check;
+};
+
+struct ipv6_hoplimit_word {
+	__be16	payload_len;
+	__u8	nexthdr;
+	__u8	hop_limit;
+};
+
+static bool is_action_keys_supported(const struct flow_action_entry *act)
+{
+	u32 mask, offset;
+	u8 htype;
+
+	htype = act->mangle.htype;
+	offset = act->mangle.offset;
+	mask = ~act->mangle.mask;
+	/* For IPv4 & IPv6 header check 4 byte word,
+	 * to determine that modified fields
+	 * are NOT ttl & hop_limit only.
+	 */
+	if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4) {
+		struct ip_ttl_word *ttl_word =
+			(struct ip_ttl_word *)&mask;
+
+		if (offset != offsetof(struct iphdr, ttl) ||
+		    ttl_word->protocol ||
+		    ttl_word->check) {
+			return true;
+		}
+	} else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) {
+		struct ipv6_hoplimit_word *hoplimit_word =
+			(struct ipv6_hoplimit_word *)&mask;
+
+		if (offset != offsetof(struct ipv6hdr, payload_len) ||
+		    hoplimit_word->payload_len ||
+		    hoplimit_word->nexthdr) {
+			return true;
+		}
+	}
+	return false;
+}
+
 static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
-					  struct tcf_exts *exts,
+					  struct flow_action *flow_action,
 					  u32 actions,
 					  struct netlink_ext_ack *extack)
 {
-	const struct tc_action *a;
+	const struct flow_action_entry *act;
 	bool modify_ip_header;
-	u8 htype, ip_proto;
 	void *headers_v;
 	u16 ethertype;
-	int nkeys, i;
-
-	if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)
-		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers);
-	else
-		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
+	u8 ip_proto;
+	int i;
 
+	headers_v = get_match_headers_value(actions, spec);
 	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
 
 	/* for non-IP we only re-write MACs, so we're okay */
@@ -2208,20 +2347,14 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 		goto out_ok;
 
 	modify_ip_header = false;
-	tcf_exts_for_each_action(i, a, exts) {
-		int k;
-
-		if (!is_tcf_pedit(a))
+	flow_action_for_each(i, act, flow_action) {
+		if (act->id != FLOW_ACTION_MANGLE &&
+		    act->id != FLOW_ACTION_ADD)
 			continue;
 
-		nkeys = tcf_pedit_nkeys(a);
-		for (k = 0; k < nkeys; k++) {
-			htype = tcf_pedit_htype(a, k);
-			if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 ||
-			    htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) {
-				modify_ip_header = true;
-				break;
-			}
+		if (is_action_keys_supported(act)) {
+			modify_ip_header = true;
+			break;
 		}
 	}
 
@@ -2239,7 +2372,7 @@ out_ok:
 }
 
 static bool actions_match_supported(struct mlx5e_priv *priv,
-				    struct tcf_exts *exts,
+				    struct flow_action *flow_action,
 				    struct mlx5e_tc_flow_parse_attr *parse_attr,
 				    struct mlx5e_tc_flow *flow,
 				    struct netlink_ext_ack *extack)
@@ -2252,12 +2385,14 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 		actions = flow->nic_attr->action;
 
 	if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
-	    !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+	    !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) ||
+	      (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)))
 		return false;
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
-		return modify_header_match_supported(&parse_attr->spec, exts,
-						     actions, extack);
+		return modify_header_match_supported(&parse_attr->spec,
+						     flow_action, actions,
+						     extack);
 
 	return true;
 }
@@ -2276,52 +2411,127 @@ static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 	return (fsystem_guid == psystem_guid);
 }
 
-static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
+static int add_vlan_rewrite_action(struct mlx5e_priv *priv, int namespace,
+				   const struct flow_action_entry *act,
+				   struct mlx5e_tc_flow_parse_attr *parse_attr,
+				   struct pedit_headers_action *hdrs,
+				   u32 *action, struct netlink_ext_ack *extack)
+{
+	u16 mask16 = VLAN_VID_MASK;
+	u16 val16 = act->vlan.vid & VLAN_VID_MASK;
+	const struct flow_action_entry pedit_act = {
+		.id = FLOW_ACTION_MANGLE,
+		.mangle.htype = FLOW_ACT_MANGLE_HDR_TYPE_ETH,
+		.mangle.offset = offsetof(struct vlan_ethhdr, h_vlan_TCI),
+		.mangle.mask = ~(u32)be16_to_cpu(*(__be16 *)&mask16),
+		.mangle.val = (u32)be16_to_cpu(*(__be16 *)&val16),
+	};
+	u8 match_prio_mask, match_prio_val;
+	void *headers_c, *headers_v;
+	int err;
+
+	headers_c = get_match_headers_criteria(*action, &parse_attr->spec);
+	headers_v = get_match_headers_value(*action, &parse_attr->spec);
+
+	if (!(MLX5_GET(fte_match_set_lyr_2_4, headers_c, cvlan_tag) &&
+	      MLX5_GET(fte_match_set_lyr_2_4, headers_v, cvlan_tag))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "VLAN rewrite action must have VLAN protocol match");
+		return -EOPNOTSUPP;
+	}
+
+	match_prio_mask = MLX5_GET(fte_match_set_lyr_2_4, headers_c, first_prio);
+	match_prio_val = MLX5_GET(fte_match_set_lyr_2_4, headers_v, first_prio);
+	if (act->vlan.prio != (match_prio_val & match_prio_mask)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Changing VLAN prio is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	err = parse_tc_pedit_action(priv, &pedit_act, namespace, parse_attr,
+				    hdrs, NULL);
+	*action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+
+	return err;
+}
+
+static int
+add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr,
+				 struct pedit_headers_action *hdrs,
+				 u32 *action, struct netlink_ext_ack *extack)
+{
+	const struct flow_action_entry prio_tag_act = {
+		.vlan.vid = 0,
+		.vlan.prio =
+			MLX5_GET(fte_match_set_lyr_2_4,
+				 get_match_headers_value(*action,
+							 &parse_attr->spec),
+				 first_prio) &
+			MLX5_GET(fte_match_set_lyr_2_4,
+				 get_match_headers_criteria(*action,
+							    &parse_attr->spec),
+				 first_prio),
+	};
+
+	return add_vlan_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB,
+				       &prio_tag_act, parse_attr, hdrs, action,
+				       extack);
+}
+
+static int parse_tc_nic_actions(struct mlx5e_priv *priv,
+				struct flow_action *flow_action,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow,
 				struct netlink_ext_ack *extack)
 {
 	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
-	const struct tc_action *a;
+	struct pedit_headers_action hdrs[2] = {};
+	const struct flow_action_entry *act;
 	u32 action = 0;
 	int err, i;
 
-	if (!tcf_exts_has_actions(exts))
+	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
 
 	attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 
-	tcf_exts_for_each_action(i, a, exts) {
-		if (is_tcf_gact_shot(a)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
 			action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
 			if (MLX5_CAP_FLOWTABLE(priv->mdev,
 					       flow_table_properties_nic_receive.flow_counter))
 				action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
-			continue;
-		}
-
-		if (is_tcf_pedit(a)) {
-			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL,
-						    parse_attr, extack);
+			break;
+		case FLOW_ACTION_MANGLE:
+		case FLOW_ACTION_ADD:
+			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_KERNEL,
+						    parse_attr, hdrs, extack);
 			if (err)
 				return err;
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
 				  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-			continue;
-		}
+			break;
+		case FLOW_ACTION_VLAN_MANGLE:
+			err = add_vlan_rewrite_action(priv,
+						      MLX5_FLOW_NAMESPACE_KERNEL,
+						      act, parse_attr, hdrs,
+						      &action, extack);
+			if (err)
+				return err;
 
-		if (is_tcf_csum(a)) {
+			break;
+		case FLOW_ACTION_CSUM:
 			if (csum_offload_supported(priv, action,
-						   tcf_csum_update_flags(a),
+						   act->csum_flags,
 						   extack))
-				continue;
+				break;
 
 			return -EOPNOTSUPP;
-		}
-
-		if (is_tcf_mirred_egress_redirect(a)) {
-			struct net_device *peer_dev = tcf_mirred_dev(a);
+		case FLOW_ACTION_REDIRECT: {
+			struct net_device *peer_dev = act->dev;
 
 			if (priv->netdev->netdev_ops == peer_dev->netdev_ops &&
 			    same_hw_devs(priv, netdev_priv(peer_dev))) {
@@ -2336,11 +2546,10 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 					    peer_dev->name);
 				return -EINVAL;
 			}
-			continue;
-		}
-
-		if (is_tcf_skbedit_mark(a)) {
-			u32 mark = tcf_skbedit_mark(a);
+			}
+			break;
+		case FLOW_ACTION_MARK: {
+			u32 mark = act->mark;
 
 			if (mark & ~MLX5E_TC_FLOW_ID_MASK) {
 				NL_SET_ERR_MSG_MOD(extack,
@@ -2350,28 +2559,52 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 
 			attr->flow_tag = mark;
 			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-			continue;
+			}
+			break;
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
+			return -EOPNOTSUPP;
 		}
+	}
 
-		return -EINVAL;
+	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
+	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
+		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL,
+					    parse_attr, hdrs, &action, extack);
+		if (err)
+			return err;
+		/* in case all pedit actions are skipped, remove the MOD_HDR
+		 * flag.
+		 */
+		if (parse_attr->num_mod_hdr_actions == 0) {
+			action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+			kfree(parse_attr->mod_hdr_actions);
+		}
 	}
 
 	attr->action = action;
-	if (!actions_match_supported(priv, exts, parse_attr, flow, extack))
+	if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
 
 	return 0;
 }
 
-static inline int cmp_encap_info(struct ip_tunnel_key *a,
-				 struct ip_tunnel_key *b)
+struct encap_key {
+	const struct ip_tunnel_key *ip_tun_key;
+	struct mlx5e_tc_tunnel *tc_tunnel;
+};
+
+static inline int cmp_encap_info(struct encap_key *a,
+				 struct encap_key *b)
 {
-	return memcmp(a, b, sizeof(*a));
+	return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) ||
+	       a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type;
 }
 
-static inline int hash_encap_info(struct ip_tunnel_key *key)
+static inline int hash_encap_info(struct encap_key *key)
 {
-	return jhash(key, sizeof(*key), 0);
+	return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
+		     key->tc_tunnel->tunnel_type);
 }
 
 
@@ -2383,36 +2616,45 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 	peer_priv = netdev_priv(peer_netdev);
 
 	return (MLX5_CAP_ESW(priv->mdev, merged_eswitch) &&
-		(priv->netdev->netdev_ops == peer_netdev->netdev_ops) &&
-		same_hw_devs(priv, peer_priv) &&
-		MLX5_VPORT_MANAGER(peer_priv->mdev) &&
-		(peer_priv->mdev->priv.eswitch->mode == SRIOV_OFFLOADS));
+		mlx5e_eswitch_rep(priv->netdev) &&
+		mlx5e_eswitch_rep(peer_netdev) &&
+		same_hw_devs(priv, peer_priv));
 }
 
 
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
-			      struct ip_tunnel_info *tun_info,
-			      struct net_device *mirred_dev,
-			      struct net_device **encap_dev,
 			      struct mlx5e_tc_flow *flow,
+			      struct net_device *mirred_dev,
+			      int out_index,
 			      struct netlink_ext_ack *extack,
-			      int out_index)
+			      struct net_device **encap_dev,
+			      bool *encap_valid)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	unsigned short family = ip_tunnel_info_af(tun_info);
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	struct ip_tunnel_key *key = &tun_info->key;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	const struct ip_tunnel_info *tun_info;
+	struct encap_key key, e_key;
 	struct mlx5e_encap_entry *e;
+	unsigned short family;
 	uintptr_t hash_key;
 	bool found = false;
 	int err = 0;
 
-	hash_key = hash_encap_info(key);
+	parse_attr = attr->parse_attr;
+	tun_info = parse_attr->tun_info[out_index];
+	family = ip_tunnel_info_af(tun_info);
+	key.ip_tun_key = &tun_info->key;
+	key.tc_tunnel = mlx5e_get_tc_tun(mirred_dev);
+
+	hash_key = hash_encap_info(&key);
 
 	hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
 				   encap_hlist, hash_key) {
-		if (!cmp_encap_info(&e->tun_info.key, key)) {
+		e_key.ip_tun_key = &e->tun_info->key;
+		e_key.tc_tunnel = e->tunnel;
+		if (!cmp_encap_info(&e_key, &key)) {
 			found = true;
 			break;
 		}
@@ -2426,7 +2668,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	if (!e)
 		return -ENOMEM;
 
-	e->tun_info = *tun_info;
+	e->tun_info = tun_info;
 	err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack);
 	if (err)
 		goto out_err;
@@ -2438,7 +2680,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	else if (family == AF_INET6)
 		err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e);
 
-	if (err && err != -EAGAIN)
+	if (err)
 		goto out_err;
 
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
@@ -2450,8 +2692,9 @@ attach_flow:
 	if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
 		attr->dests[out_index].encap_id = e->encap_id;
 		attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+		*encap_valid = true;
 	} else {
-		err = -EAGAIN;
+		*encap_valid = false;
 	}
 
 	return err;
@@ -2462,7 +2705,7 @@ out_err:
 }
 
 static int parse_tc_vlan_action(struct mlx5e_priv *priv,
-				const struct tc_action *a,
+				const struct flow_action_entry *act,
 				struct mlx5_esw_flow_attr *attr,
 				u32 *action)
 {
@@ -2471,7 +2714,8 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 	if (vlan_idx >= MLX5_FS_VLAN_DEPTH)
 		return -EOPNOTSUPP;
 
-	if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
+	switch (act->id) {
+	case FLOW_ACTION_VLAN_POP:
 		if (vlan_idx) {
 			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
 								 MLX5_FS_VLAN_DEPTH))
@@ -2481,10 +2725,11 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 		} else {
 			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
 		}
-	} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
-		attr->vlan_vid[vlan_idx] = tcf_vlan_push_vid(a);
-		attr->vlan_prio[vlan_idx] = tcf_vlan_push_prio(a);
-		attr->vlan_proto[vlan_idx] = tcf_vlan_push_proto(a);
+		break;
+	case FLOW_ACTION_VLAN_PUSH:
+		attr->vlan_vid[vlan_idx] = act->vlan.vid;
+		attr->vlan_prio[vlan_idx] = act->vlan.prio;
+		attr->vlan_proto[vlan_idx] = act->vlan.proto;
 		if (!attr->vlan_proto[vlan_idx])
 			attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q);
 
@@ -2496,14 +2741,15 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2;
 		} else {
 			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) &&
-			    (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
-			     tcf_vlan_push_prio(a)))
+			    (act->vlan.proto != htons(ETH_P_8021Q) ||
+			     act->vlan.prio))
 				return -EOPNOTSUPP;
 
 			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
 		}
-	} else { /* action is TCA_VLAN_ACT_MODIFY */
-		return -EOPNOTSUPP;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	attr->total_vlan = vlan_idx + 1;
@@ -2511,58 +2757,108 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
-				struct mlx5e_tc_flow_parse_attr *parse_attr,
+static int add_vlan_push_action(struct mlx5e_priv *priv,
+				struct mlx5_esw_flow_attr *attr,
+				struct net_device **out_dev,
+				u32 *action)
+{
+	struct net_device *vlan_dev = *out_dev;
+	struct flow_action_entry vlan_act = {
+		.id = FLOW_ACTION_VLAN_PUSH,
+		.vlan.vid = vlan_dev_vlan_id(vlan_dev),
+		.vlan.proto = vlan_dev_vlan_proto(vlan_dev),
+		.vlan.prio = 0,
+	};
+	int err;
+
+	err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+	if (err)
+		return err;
+
+	*out_dev = dev_get_by_index_rcu(dev_net(vlan_dev),
+					dev_get_iflink(vlan_dev));
+	if (is_vlan_dev(*out_dev))
+		err = add_vlan_push_action(priv, attr, out_dev, action);
+
+	return err;
+}
+
+static int add_vlan_pop_action(struct mlx5e_priv *priv,
+			       struct mlx5_esw_flow_attr *attr,
+			       u32 *action)
+{
+	int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev);
+	struct flow_action_entry vlan_act = {
+		.id = FLOW_ACTION_VLAN_POP,
+	};
+	int err = 0;
+
+	while (nest_level--) {
+		err = parse_tc_vlan_action(priv, &vlan_act, attr, action);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
+				    struct net_device *out_dev)
+{
+	if (is_merged_eswitch_dev(priv, out_dev))
+		return true;
+
+	return mlx5e_eswitch_rep(out_dev) &&
+	       same_hw_devs(priv, netdev_priv(out_dev));
+}
+
+static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
+				struct flow_action *flow_action,
 				struct mlx5e_tc_flow *flow,
 				struct netlink_ext_ack *extack)
 {
+	struct pedit_headers_action hdrs[2] = {};
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct ip_tunnel_info *info = NULL;
-	const struct tc_action *a;
+	const struct ip_tunnel_info *info = NULL;
+	const struct flow_action_entry *act;
 	bool encap = false;
 	u32 action = 0;
 	int err, i;
 
-	if (!tcf_exts_has_actions(exts))
+	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
 
-	attr->in_rep = rpriv->rep;
-	attr->in_mdev = priv->mdev;
-
-	tcf_exts_for_each_action(i, a, exts) {
-		if (is_tcf_gact_shot(a)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
 			action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-			continue;
-		}
-
-		if (is_tcf_pedit(a)) {
-			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
-						    parse_attr, extack);
+			break;
+		case FLOW_ACTION_MANGLE:
+		case FLOW_ACTION_ADD:
+			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB,
+						    parse_attr, hdrs, extack);
 			if (err)
 				return err;
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 			attr->split_count = attr->out_count;
-			continue;
-		}
-
-		if (is_tcf_csum(a)) {
+			break;
+		case FLOW_ACTION_CSUM:
 			if (csum_offload_supported(priv, action,
-						   tcf_csum_update_flags(a),
-						   extack))
-				continue;
+						   act->csum_flags, extack))
+				break;
 
 			return -EOPNOTSUPP;
-		}
-
-		if (is_tcf_mirred_egress_redirect(a) || is_tcf_mirred_egress_mirror(a)) {
+		case FLOW_ACTION_REDIRECT:
+		case FLOW_ACTION_MIRRED: {
 			struct mlx5e_priv *out_priv;
 			struct net_device *out_dev;
 
-			out_dev = tcf_mirred_dev(a);
+			out_dev = act->dev;
 			if (!out_dev) {
 				/* out_dev is NULL when filters with
 				 * non-existing mirred device are replayed to
@@ -2581,9 +2877,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-			if (switchdev_port_same_parent_id(priv->netdev,
-							  out_dev) ||
-			    is_merged_eswitch_dev(priv, out_dev)) {
+			if (netdev_port_same_parent_id(priv->netdev, out_dev)) {
 				struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 				struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
 				struct net_device *uplink_upper = netdev_master_upper_dev_get(uplink_dev);
@@ -2593,8 +2887,28 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				    uplink_upper == out_dev)
 					out_dev = uplink_dev;
 
-				if (!mlx5e_eswitch_rep(out_dev))
+				if (is_vlan_dev(out_dev)) {
+					err = add_vlan_push_action(priv, attr,
+								   &out_dev,
+								   &action);
+					if (err)
+						return err;
+				}
+
+				if (is_vlan_dev(parse_attr->filter_dev)) {
+					err = add_vlan_pop_action(priv, attr,
+								  &action);
+					if (err)
+						return err;
+				}
+
+				if (!mlx5e_is_valid_eswitch_fwd_dev(priv, out_dev)) {
+					NL_SET_ERR_MSG_MOD(extack,
+							   "devices are not on same switch HW, can't offload forwarding");
+					pr_err("devices %s %s not on same switch HW, can't offload forwarding\n",
+					       priv->netdev->name, out_dev->name);
 					return -EOPNOTSUPP;
+				}
 
 				out_priv = netdev_priv(out_dev);
 				rpriv = out_priv->ppriv;
@@ -2604,9 +2918,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			} else if (encap) {
 				parse_attr->mirred_ifindex[attr->out_count] =
 					out_dev->ifindex;
-				parse_attr->tun_info[attr->out_count] = *info;
+				parse_attr->tun_info[attr->out_count] = info;
 				encap = false;
-				attr->parse_attr = parse_attr;
 				attr->dests[attr->out_count].flags |=
 					MLX5_ESW_DEST_ENCAP;
 				attr->out_count++;
@@ -2627,35 +2940,49 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				       priv->netdev->name, out_dev->name);
 				return -EINVAL;
 			}
-			continue;
-		}
-
-		if (is_tcf_tunnel_set(a)) {
-			info = tcf_tunnel_info(a);
+			}
+			break;
+		case FLOW_ACTION_TUNNEL_ENCAP:
+			info = act->tunnel;
 			if (info)
 				encap = true;
 			else
 				return -EOPNOTSUPP;
-			continue;
-		}
-
-		if (is_tcf_vlan(a)) {
-			err = parse_tc_vlan_action(priv, a, attr, &action);
 
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_POP:
+			if (act->id == FLOW_ACTION_VLAN_PUSH &&
+			    (action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)) {
+				/* Replace vlan pop+push with vlan modify */
+				action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+				err = add_vlan_rewrite_action(priv,
+							      MLX5_FLOW_NAMESPACE_FDB,
+							      act, parse_attr, hdrs,
+							      &action, extack);
+			} else {
+				err = parse_tc_vlan_action(priv, act, attr, &action);
+			}
 			if (err)
 				return err;
 
 			attr->split_count = attr->out_count;
-			continue;
-		}
+			break;
+		case FLOW_ACTION_VLAN_MANGLE:
+			err = add_vlan_rewrite_action(priv,
+						      MLX5_FLOW_NAMESPACE_FDB,
+						      act, parse_attr, hdrs,
+						      &action, extack);
+			if (err)
+				return err;
 
-		if (is_tcf_tunnel_release(a)) {
+			attr->split_count = attr->out_count;
+			break;
+		case FLOW_ACTION_TUNNEL_DECAP:
 			action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
-			continue;
-		}
-
-		if (is_tcf_gact_goto_chain(a)) {
-			u32 dest_chain = tcf_gact_goto_chain_index(a);
+			break;
+		case FLOW_ACTION_GOTO: {
+			u32 dest_chain = act->chain_index;
 			u32 max_chain = mlx5_eswitch_get_chain_range(esw);
 
 			if (dest_chain <= attr->chain) {
@@ -2668,15 +2995,47 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			}
 			action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			attr->dest_chain = dest_chain;
-
-			continue;
+			break;
+			}
+		default:
+			NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
+			return -EOPNOTSUPP;
 		}
+	}
 
-		return -EINVAL;
+	if (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
+	    action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) {
+		/* For prio tag mode, replace vlan pop with rewrite vlan prio
+		 * tag rewrite.
+		 */
+		action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+		err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, hdrs,
+						       &action, extack);
+		if (err)
+			return err;
+	}
+
+	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
+	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
+		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB,
+					    parse_attr, hdrs, &action, extack);
+		if (err)
+			return err;
+		/* in case all pedit actions are skipped, remove the MOD_HDR
+		 * flag. we might have set split_count either by pedit or
+		 * pop/push. if there is no pop/push either, reset it too.
+		 */
+		if (parse_attr->num_mod_hdr_actions == 0) {
+			action &= ~MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+			kfree(parse_attr->mod_hdr_actions);
+			if (!((action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) ||
+			      (action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH)))
+				attr->split_count = 0;
+		}
 	}
 
 	attr->action = action;
-	if (!actions_match_supported(priv, exts, parse_attr, flow, extack))
+	if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
 
 	if (attr->dest_chain) {
@@ -2736,20 +3095,27 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags)
 static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	bool is_rep_ingress = attr->in_rep->vport != FDB_UPLINK_VPORT &&
+	bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK &&
 			      flow->flags & MLX5E_TC_FLOW_INGRESS;
 	bool act_is_encap = !!(attr->action &
 			       MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT);
 	bool esw_paired = mlx5_devcom_is_paired(attr->in_mdev->priv.devcom,
 						MLX5_DEVCOM_ESW_OFFLOADS);
 
-	return esw_paired && mlx5_lag_is_sriov(attr->in_mdev) &&
-	       (is_rep_ingress || act_is_encap);
+	if (!esw_paired)
+		return false;
+
+	if ((mlx5_lag_is_sriov(attr->in_mdev) ||
+	     mlx5_lag_is_multipath(attr->in_mdev)) &&
+	    (is_rep_ingress || act_is_encap))
+		return true;
+
+	return false;
 }
 
 static int
 mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
-		 struct tc_cls_flower_offload *f, u16 flow_flags,
+		 struct flow_cls_offload *f, u16 flow_flags,
 		 struct mlx5e_tc_flow_parse_attr **__parse_attr,
 		 struct mlx5e_tc_flow **__flow)
 {
@@ -2779,17 +3145,40 @@ err_free:
 	return err;
 }
 
-static int
+static void
+mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr,
+			 struct mlx5e_priv *priv,
+			 struct mlx5e_tc_flow_parse_attr *parse_attr,
+			 struct flow_cls_offload *f,
+			 struct mlx5_eswitch_rep *in_rep,
+			 struct mlx5_core_dev *in_mdev)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	esw_attr->parse_attr = parse_attr;
+	esw_attr->chain = f->common.chain_index;
+	esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16;
+
+	esw_attr->in_rep = in_rep;
+	esw_attr->in_mdev = in_mdev;
+
+	if (MLX5_CAP_ESW(esw->dev, counter_eswitch_affinity) ==
+	    MLX5_COUNTER_SOURCE_ESWITCH)
+		esw_attr->counter_dev = in_mdev;
+	else
+		esw_attr->counter_dev = priv->mdev;
+}
+
+static struct mlx5e_tc_flow *
 __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
-		     struct tc_cls_flower_offload *f,
+		     struct flow_cls_offload *f,
 		     u16 flow_flags,
 		     struct net_device *filter_dev,
 		     struct mlx5_eswitch_rep *in_rep,
-		     struct mlx5_core_dev *in_mdev,
-		     struct mlx5e_tc_flow **__flow)
+		     struct mlx5_core_dev *in_mdev)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
 	int attr_size, err;
@@ -2800,45 +3189,41 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 			       &parse_attr, &flow);
 	if (err)
 		goto out;
+
 	parse_attr->filter_dev = filter_dev;
-	flow->esw_attr->parse_attr = parse_attr;
+	mlx5e_flow_esw_attr_init(flow->esw_attr,
+				 priv, parse_attr,
+				 f, in_rep, in_mdev);
+
 	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec,
 			       f, filter_dev);
 	if (err)
 		goto err_free;
 
-	flow->esw_attr->chain = f->common.chain_index;
-	flow->esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16;
-	err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow, extack);
+	err = parse_tc_fdb_actions(priv, &rule->action, flow, extack);
 	if (err)
 		goto err_free;
 
-	flow->esw_attr->in_rep = in_rep;
-	flow->esw_attr->in_mdev = in_mdev;
-
-	if (MLX5_CAP_ESW(esw->dev, counter_eswitch_affinity) ==
-	    MLX5_COUNTER_SOURCE_ESWITCH)
-		flow->esw_attr->counter_dev = in_mdev;
-	else
-		flow->esw_attr->counter_dev = priv->mdev;
-
-	err = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow, extack);
-	if (err)
-		goto err_free;
+	err = mlx5e_tc_add_fdb_flow(priv, flow, extack);
+	if (err) {
+		if (!(err == -ENETUNREACH && mlx5_lag_is_multipath(in_mdev)))
+			goto err_free;
 
-	*__flow = flow;
+		add_unready_flow(flow);
+	}
 
-	return 0;
+	return flow;
 
 err_free:
 	kfree(flow);
 	kvfree(parse_attr);
 out:
-	return err;
+	return ERR_PTR(err);
 }
 
-static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f,
-				      struct mlx5e_tc_flow *flow)
+static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
+				      struct mlx5e_tc_flow *flow,
+				      u16 flow_flags)
 {
 	struct mlx5e_priv *priv = flow->priv, *peer_priv;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw;
@@ -2861,17 +3246,19 @@ static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f,
 	 * original flow and packets redirected from uplink use the
 	 * peer mdev.
 	 */
-	if (flow->esw_attr->in_rep->vport == FDB_UPLINK_VPORT)
+	if (flow->esw_attr->in_rep->vport == MLX5_VPORT_UPLINK)
 		in_mdev = peer_priv->mdev;
 	else
 		in_mdev = priv->mdev;
 
 	parse_attr = flow->esw_attr->parse_attr;
-	err = __mlx5e_add_fdb_flow(peer_priv, f, flow->flags,
-				   parse_attr->filter_dev,
-				   flow->esw_attr->in_rep, in_mdev, &peer_flow);
-	if (err)
+	peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags,
+					 parse_attr->filter_dev,
+					 flow->esw_attr->in_rep, in_mdev);
+	if (IS_ERR(peer_flow)) {
+		err = PTR_ERR(peer_flow);
 		goto out;
+	}
 
 	flow->peer_flow = peer_flow;
 	flow->flags |= MLX5E_TC_FLOW_DUP;
@@ -2886,7 +3273,7 @@ out:
 
 static int
 mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
-		   struct tc_cls_flower_offload *f,
+		   struct flow_cls_offload *f,
 		   u16 flow_flags,
 		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
@@ -2897,13 +3284,13 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	struct mlx5e_tc_flow *flow;
 	int err;
 
-	err = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep,
-				   in_mdev, &flow);
-	if (err)
-		goto out;
+	flow = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep,
+				    in_mdev);
+	if (IS_ERR(flow))
+		return PTR_ERR(flow);
 
 	if (is_peer_flow_needed(flow)) {
-		err = mlx5e_tc_add_fdb_peer_flow(f, flow);
+		err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags);
 		if (err) {
 			mlx5e_tc_del_fdb_flow(priv, flow);
 			goto out;
@@ -2920,11 +3307,12 @@ out:
 
 static int
 mlx5e_add_nic_flow(struct mlx5e_priv *priv,
-		   struct tc_cls_flower_offload *f,
+		   struct flow_cls_offload *f,
 		   u16 flow_flags,
 		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
@@ -2947,7 +3335,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
-	err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow, extack);
+	err = parse_tc_nic_actions(priv, &rule->action, parse_attr, flow, extack);
 	if (err)
 		goto err_free;
 
@@ -2970,7 +3358,7 @@ out:
 
 static int
 mlx5e_tc_add_flow(struct mlx5e_priv *priv,
-		  struct tc_cls_flower_offload *f,
+		  struct flow_cls_offload *f,
 		  int flags,
 		  struct net_device *filter_dev,
 		  struct mlx5e_tc_flow **flow)
@@ -2984,7 +3372,7 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 	if (!tc_can_offload_extack(priv->netdev, f->common.extack))
 		return -EOPNOTSUPP;
 
-	if (esw && esw->mode == SRIOV_OFFLOADS)
+	if (esw && esw->mode == MLX5_ESWITCH_OFFLOADS)
 		err = mlx5e_add_fdb_flow(priv, f, flow_flags,
 					 filter_dev, flow);
 	else
@@ -2995,7 +3383,7 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 }
 
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			   struct tc_cls_flower_offload *f, int flags)
+			   struct flow_cls_offload *f, int flags)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
@@ -3009,6 +3397,7 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		netdev_warn_once(priv->netdev,
 				 "flow cookie %lx already exists, ignoring\n",
 				 f->cookie);
+		err = -EEXIST;
 		goto out;
 	}
 
@@ -3041,7 +3430,7 @@ static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags)
 }
 
 int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			struct tc_cls_flower_offload *f, int flags)
+			struct flow_cls_offload *f, int flags)
 {
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5e_tc_flow *flow;
@@ -3060,30 +3449,32 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 }
 
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
-		       struct tc_cls_flower_offload *f, int flags)
+		       struct flow_cls_offload *f, int flags)
 {
 	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5_eswitch *peer_esw;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5_fc *counter;
-	u64 bytes;
-	u64 packets;
-	u64 lastuse;
+	u64 lastuse = 0;
+	u64 packets = 0;
+	u64 bytes = 0;
 
 	flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
 	if (!flow || !same_flow_direction(flow, flags))
 		return -EINVAL;
 
-	if (!(flow->flags & MLX5E_TC_FLOW_OFFLOADED))
-		return 0;
-
-	counter = mlx5e_tc_get_counter(flow);
-	if (!counter)
-		return 0;
+	if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
+		counter = mlx5e_tc_get_counter(flow);
+		if (!counter)
+			return 0;
 
-	mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+		mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+	}
 
+	/* Under multipath it's possible for one rule to be currently
+	 * un-offloaded while the other rule is offloaded.
+	 */
 	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 	if (!peer_esw)
 		goto out;
@@ -3095,6 +3486,8 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		u64 lastuse2;
 
 		counter = mlx5e_tc_get_counter(flow->peer_flow);
+		if (!counter)
+			goto no_peer_counter;
 		mlx5_fc_query_cached(counter, &bytes2, &packets2, &lastuse2);
 
 		bytes += bytes2;
@@ -3102,10 +3495,10 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		lastuse = max_t(u64, lastuse, lastuse2);
 	}
 
+no_peer_counter:
 	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
-
 out:
-	tcf_exts_stats_update(f->exts, bytes, packets, lastuse);
+	flow_stats_update(&f->stats, bytes, packets, lastuse);
 
 	return 0;
 }
@@ -3225,3 +3618,18 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw)
 	list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows, peer)
 		__mlx5e_tc_del_fdb_peer_flow(flow);
 }
+
+void mlx5e_tc_reoffload_flows_work(struct work_struct *work)
+{
+	struct mlx5_rep_uplink_priv *rpriv =
+		container_of(work, struct mlx5_rep_uplink_priv,
+			     reoffload_flows_work);
+	struct mlx5e_tc_flow *flow, *tmp;
+
+	rtnl_lock();
+	list_for_each_entry_safe(flow, tmp, &rpriv->unready_flows, unready) {
+		if (!mlx5e_tc_add_fdb_flow(flow->priv, flow, NULL))
+			remove_unready_flow(flow);
+	}
+	rtnl_unlock();
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index d2d87f978c06..3ab39275ca7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -54,12 +54,12 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
 void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
 
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			   struct tc_cls_flower_offload *f, int flags);
+			   struct flow_cls_offload *f, int flags);
 int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			struct tc_cls_flower_offload *f, int flags);
+			struct flow_cls_offload *f, int flags);
 
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
-		       struct tc_cls_flower_offload *f, int flags);
+		       struct flow_cls_offload *f, int flags);
 
 struct mlx5e_encap_entry;
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
@@ -72,6 +72,10 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags);
 
+void mlx5e_tc_reoffload_flows_work(struct work_struct *work);
+
+bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
+				    struct net_device *out_dev);
 
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 0e55cd1f2e98..600e92cb629a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -32,57 +32,15 @@
 
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
+#include <net/geneve.h>
 #include <net/dsfield.h>
 #include "en.h"
+#include "en/txrx.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/en_accel.h"
+#include "en_accel/ktls.h"
 #include "lib/clock.h"
 
-#define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
-
-#ifndef CONFIG_MLX5_EN_TLS
-#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
-			    MLX5E_SQ_NOPS_ROOM)
-#else
-/* TLS offload requires MLX5E_SQ_STOP_ROOM to have
- * enough room for a resync SKB, a normal SKB and a NOP
- */
-#define MLX5E_SQ_STOP_ROOM (2 * MLX5_SEND_WQE_MAX_WQEBBS +\
-			    MLX5E_SQ_NOPS_ROOM)
-#endif
-
-static inline void mlx5e_tx_dma_unmap(struct device *pdev,
-				      struct mlx5e_sq_dma *dma)
-{
-	switch (dma->type) {
-	case MLX5E_DMA_MAP_SINGLE:
-		dma_unmap_single(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
-		break;
-	case MLX5E_DMA_MAP_PAGE:
-		dma_unmap_page(pdev, dma->addr, dma->size, DMA_TO_DEVICE);
-		break;
-	default:
-		WARN_ONCE(true, "mlx5e_tx_dma_unmap unknown DMA type!\n");
-	}
-}
-
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
-{
-	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
-}
-
-static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq,
-				  dma_addr_t addr,
-				  u32 size,
-				  enum mlx5e_dma_map_type map_type)
-{
-	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
-
-	dma->addr = addr;
-	dma->size = size;
-	dma->type = map_type;
-}
-
 static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
 {
 	int i;
@@ -110,16 +68,15 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb
 #endif
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback)
+		       struct net_device *sb_dev)
 {
+	int txq_ix = netdev_pick_tx(dev, skb, NULL);
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int channel_ix = fallback(dev, skb, NULL);
 	u16 num_channels;
 	int up = 0;
 
 	if (!netdev_get_num_tc(dev))
-		return channel_ix;
+		return txq_ix;
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP)
@@ -129,14 +86,14 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		if (skb_vlan_tag_present(skb))
 			up = skb_vlan_tag_get_prio(skb);
 
-	/* channel_ix can be larger than num_channels since
+	/* txq_ix can be larger than num_channels since
 	 * dev->num_real_tx_queues = num_channels * num_tc
 	 */
 	num_channels = priv->channels.params.num_channels;
-	if (channel_ix >= num_channels)
-		channel_ix = reciprocal_scale(channel_ix, num_channels);
+	if (txq_ix >= num_channels)
+		txq_ix = priv->txq2sq[txq_ix]->ch_ix;
 
-	return priv->channel_tc2txq[channel_ix][up];
+	return priv->channel_tc2txq[txq_ix][up];
 }
 
 static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
@@ -148,12 +105,8 @@ static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
 
 static inline int mlx5e_skb_l3_header_offset(struct sk_buff *skb)
 {
-	struct flow_keys keys;
-
 	if (skb_transport_header_was_set(skb))
 		return skb_transport_offset(skb);
-	else if (skb_flow_dissect_flow_keys(skb, &keys, 0))
-		return keys.control.thoff;
 	else
 		return mlx5e_skb_l2_header_offset(skb);
 }
@@ -167,20 +120,13 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	case MLX5_INLINE_MODE_NONE:
 		return 0;
 	case MLX5_INLINE_MODE_TCP_UDP:
-		hlen = eth_get_headlen(skb->data, skb_headlen(skb));
+		hlen = eth_get_headlen(skb->dev, skb->data, skb_headlen(skb));
 		if (hlen == ETH_HLEN && !skb_vlan_tag_present(skb))
 			hlen += VLAN_HLEN;
 		break;
 	case MLX5_INLINE_MODE_IP:
-		/* When transport header is set to zero, it means no transport
-		 * header. When transport header is set to 0xff's, it means
-		 * transport header wasn't set.
-		 */
-		if (skb_transport_offset(skb)) {
-			hlen = mlx5e_skb_l3_header_offset(skb);
-			break;
-		}
-		/* fall through */
+		hlen = mlx5e_skb_l3_header_offset(skb);
+		break;
 	case MLX5_INLINE_MODE_L2:
 	default:
 		hlen = mlx5e_skb_l2_header_offset(skb);
@@ -288,29 +234,14 @@ dma_unmap_wqe_err:
 	return -ENOMEM;
 }
 
-static inline void mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq,
-					   struct mlx5_wq_cyc *wq,
-					   u16 pi, u16 nnops)
-{
-	struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi];
-
-	edge_wi = wi + nnops;
-
-	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
-	for (; wi < edge_wi; wi++) {
-		wi->skb        = NULL;
-		wi->num_wqebbs = 1;
-		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
-	}
-	sq->stats->nop += nnops;
-}
-
 static inline void
 mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     u8 opcode, u16 ds_cnt, u8 num_wqebbs, u32 num_bytes, u8 num_dma,
-		     struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg)
+		     struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg,
+		     bool xmit_more)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
+	bool send_doorbell;
 
 	wi->num_bytes = num_bytes;
 	wi->num_dma = num_dma;
@@ -320,25 +251,23 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
 	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-	netdev_tx_sent_queue(sq->txq, num_bytes);
-
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
 	sq->pc += wi->num_wqebbs;
-	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM))) {
+	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, sq->stop_room))) {
 		netif_tx_stop_queue(sq->txq);
 		sq->stats->stopped++;
 	}
 
-	if (!skb->xmit_more || netif_xmit_stopped(sq->txq))
+	send_doorbell = __netdev_tx_sent_queue(sq->txq, num_bytes,
+					       xmit_more);
+	if (send_doorbell)
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg);
 }
 
-#define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
-
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5e_tx_wqe *wqe, u16 pi)
+			  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5_wqe_ctrl_seg *cseg;
@@ -363,15 +292,18 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs;
 		stats->packets += skb_shinfo(skb)->gso_segs;
 	} else {
+		u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ?
+			MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode;
+
 		opcode    = MLX5_OPCODE_SEND;
 		mss       = 0;
-		ihs       = mlx5e_calc_min_inline(sq->min_inline_mode, skb);
+		ihs       = mlx5e_calc_min_inline(mode, skb);
 		num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 		stats->packets++;
 	}
 
 	stats->bytes     += num_bytes;
-	stats->xmit_more += skb->xmit_more;
+	stats->xmit_more += xmit_more;
 
 	headlen = skb->len - ihs - skb->data_len;
 	ds_cnt += !!headlen;
@@ -390,11 +322,17 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 #ifdef CONFIG_MLX5_EN_IPSEC
 		struct mlx5_wqe_eth_seg cur_eth = wqe->eth;
 #endif
+#ifdef CONFIG_MLX5_EN_TLS
+		struct mlx5_wqe_ctrl_seg cur_ctrl = wqe->ctrl;
+#endif
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
-		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+		wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
 #ifdef CONFIG_MLX5_EN_IPSEC
 		wqe->eth = cur_eth;
 #endif
+#ifdef CONFIG_MLX5_EN_TLS
+		wqe->ctrl = cur_ctrl;
+#endif
 	}
 
 	/* fill wqe */
@@ -403,6 +341,10 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	eseg = &wqe->eth;
 	dseg =  wqe->data;
 
+#if IS_ENABLED(CONFIG_GENEVE)
+	if (skb->encapsulation)
+		mlx5e_tx_tunnel_accel(skb, eseg);
+#endif
 	mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
 
 	eseg->mss = mss;
@@ -430,7 +372,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
-			     num_dma, wi, cseg);
+			     num_dma, wi, cseg, xmit_more);
 
 	return NETDEV_TX_OK;
 
@@ -449,14 +391,14 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	u16 pi;
 
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
-	mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+	wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
 
 	/* might send skbs and update wqe and pi */
 	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
 	if (unlikely(!skb))
 		return NETDEV_TX_OK;
 
-	return mlx5e_sq_xmit(sq, skb, wqe, pi);
+	return mlx5e_sq_xmit(sq, skb, wqe, pi, netdev_xmit_more());
 }
 
 static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
@@ -520,7 +462,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
 				queue_work(cq->channel->priv->wq,
-					   &sq->recover.recover_work);
+					   &sq->recover_work);
 			}
 			stats->cqe_err++;
 		}
@@ -537,8 +479,16 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			wi = &sq->db.wqe_info[ci];
 			skb = wi->skb;
 
-			if (unlikely(!skb)) { /* nop */
-				sqcc++;
+			if (unlikely(!skb)) {
+#ifdef CONFIG_MLX5_EN_TLS
+				if (wi->resync_dump_frag) {
+					struct mlx5e_sq_dma *dma =
+						mlx5e_dma_get(sq, dma_fifo_cc++);
+
+					mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, dma);
+				}
+#endif
+				sqcc += wi->num_wqebbs;
 				continue;
 			}
 
@@ -580,8 +530,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
 
 	if (netif_tx_queue_stopped(sq->txq) &&
-	    mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
-				   MLX5E_SQ_STOP_ROOM) &&
+	    mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) &&
 	    !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
 		netif_tx_wake_queue(sq->txq);
 		stats->wake++;
@@ -630,7 +579,8 @@ mlx5i_txwqe_build_datagram(struct mlx5_av *av, u32 dqpn, u32 dqkey,
 }
 
 netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5_av *av, u32 dqpn, u32 dqkey)
+			  struct mlx5_av *av, u32 dqpn, u32 dqkey,
+			  bool xmit_more)
 {
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	struct mlx5i_tx_wqe *wqe;
@@ -666,7 +616,7 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	}
 
 	stats->bytes     += num_bytes;
-	stats->xmit_more += skb->xmit_more;
+	stats->xmit_more += xmit_more;
 
 	headlen = skb->len - ihs - skb->data_len;
 	ds_cnt += !!headlen;
@@ -711,7 +661,7 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		goto err_drop;
 
 	mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
-			     num_dma, wi, cseg);
+			     num_dma, wi, cseg, xmit_more);
 
 	return NETDEV_TX_OK;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index b4af5e19f6ac..c50b6f0769c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -33,6 +33,7 @@
 #include <linux/irq.h>
 #include "en.h"
 #include "en/xdp.h"
+#include "en/xsk/tx.h"
 
 static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
@@ -48,35 +49,49 @@ static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_sq_stats *stats = sq->stats;
-	struct net_dim_sample dim_sample;
+	struct dim_sample dim_sample;
 
 	if (unlikely(!test_bit(MLX5E_SQ_STATE_AM, &sq->state)))
 		return;
 
-	net_dim_sample(sq->cq.event_ctr, stats->packets, stats->bytes,
-		       &dim_sample);
+	dim_update_sample(sq->cq.event_ctr, stats->packets, stats->bytes, &dim_sample);
 	net_dim(&sq->dim, dim_sample);
 }
 
 static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq)
 {
 	struct mlx5e_rq_stats *stats = rq->stats;
-	struct net_dim_sample dim_sample;
+	struct dim_sample dim_sample;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_AM, &rq->state)))
 		return;
 
-	net_dim_sample(rq->cq.event_ctr, stats->packets, stats->bytes,
-		       &dim_sample);
+	dim_update_sample(rq->cq.event_ctr, stats->packets, stats->bytes, &dim_sample);
 	net_dim(&rq->dim, dim_sample);
 }
 
+void mlx5e_trigger_irq(struct mlx5e_icosq *sq)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	struct mlx5e_tx_wqe *nopwqe;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+
+	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
+	nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl);
+}
+
 int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
 					       napi);
 	struct mlx5e_ch_stats *ch_stats = c->stats;
+	struct mlx5e_xdpsq *xsksq = &c->xsksq;
+	struct mlx5e_rq *xskrq = &c->xskrq;
 	struct mlx5e_rq *rq = &c->rq;
+	bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state);
+	bool aff_change = false;
+	bool busy_xsk = false;
 	bool busy = false;
 	int work_done = 0;
 	int i;
@@ -86,22 +101,38 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
-	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq, NULL);
+	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
 
 	if (c->xdp)
-		busy |= mlx5e_poll_xdpsq_cq(&rq->xdpsq.cq, rq);
+		busy |= mlx5e_poll_xdpsq_cq(&c->rq_xdpsq.cq);
 
 	if (likely(budget)) { /* budget=0 means: don't poll rx rings */
-		work_done = mlx5e_poll_rx_cq(&rq->cq, budget);
+		if (xsk_open)
+			work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget);
+
+		if (likely(budget - work_done))
+			work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done);
+
 		busy |= work_done == budget;
 	}
 
-	busy |= c->rq.post_wqes(rq);
+	mlx5e_poll_ico_cq(&c->icosq.cq);
+
+	busy |= rq->post_wqes(rq);
+	if (xsk_open) {
+		mlx5e_poll_ico_cq(&c->xskicosq.cq);
+		busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq);
+		busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET);
+		busy_xsk |= xskrq->post_wqes(xskrq);
+	}
+
+	busy |= busy_xsk;
 
 	if (busy) {
 		if (likely(mlx5e_channel_no_affinity_change(c)))
 			return budget;
 		ch_stats->aff_change++;
+		aff_change = true;
 		if (budget && work_done == budget)
 			work_done--;
 	}
@@ -122,10 +153,22 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	mlx5e_cq_arm(&c->icosq.cq);
 	mlx5e_cq_arm(&c->xdpsq.cq);
 
+	if (xsk_open) {
+		mlx5e_handle_rx_dim(xskrq);
+		mlx5e_cq_arm(&c->xskicosq.cq);
+		mlx5e_cq_arm(&xsksq->cq);
+		mlx5e_cq_arm(&xskrq->cq);
+	}
+
+	if (unlikely(aff_change && busy_xsk)) {
+		mlx5e_trigger_irq(&c->icosq);
+		ch_stats->force_irq++;
+	}
+
 	return work_done;
 }
 
-void mlx5e_completion_event(struct mlx5_core_cq *mcq)
+void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index ee04aab65a9f..41f25ea2e8d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -34,6 +34,7 @@
 #include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/eq.h>
 #include <linux/mlx5/cmd.h>
 #ifdef CONFIG_RFS_ACCEL
@@ -60,17 +61,21 @@ enum {
 	MLX5_EQ_DOORBEL_OFFSET	= 0x40,
 };
 
-struct mlx5_irq_info {
-	cpumask_var_t mask;
-	char name[MLX5_MAX_IRQ_NAME];
-	void *context; /* dev_id provided to request_irq */
+/* budget must be smaller than MLX5_NUM_SPARE_EQE to guarantee that we update
+ * the ci before we polled all the entries in the EQ. MLX5_NUM_SPARE_EQE is
+ * used to set the EQ size, budget must be smaller than the EQ size.
+ */
+enum {
+	MLX5_EQ_POLLING_BUDGET	= 128,
 };
 
+static_assert(MLX5_EQ_POLLING_BUDGET <= MLX5_NUM_SPARE_EQE);
+
 struct mlx5_eq_table {
 	struct list_head        comp_eqs_list;
-	struct mlx5_eq          pages_eq;
-	struct mlx5_eq	        cmd_eq;
-	struct mlx5_eq          async_eq;
+	struct mlx5_eq_async    pages_eq;
+	struct mlx5_eq_async    cmd_eq;
+	struct mlx5_eq_async    async_eq;
 
 	struct atomic_notifier_head nh[MLX5_EVENT_TYPE_MAX];
 
@@ -78,11 +83,8 @@ struct mlx5_eq_table {
 	struct mlx5_nb          cq_err_nb;
 
 	struct mutex            lock; /* sync async eqs creations */
-	int			num_comp_vectors;
-	struct mlx5_irq_info	*irq_info;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap         *rmap;
-#endif
+	int			num_comp_eqs;
+	struct mlx5_irq_table	*irq_table;
 };
 
 #define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG)	    | \
@@ -114,25 +116,33 @@ static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
 	struct mlx5_cq_table *table = &eq->cq_table;
 	struct mlx5_core_cq *cq = NULL;
 
-	spin_lock(&table->lock);
+	rcu_read_lock();
 	cq = radix_tree_lookup(&table->tree, cqn);
 	if (likely(cq))
 		mlx5_cq_hold(cq);
-	spin_unlock(&table->lock);
+	rcu_read_unlock();
 
 	return cq;
 }
 
-static irqreturn_t mlx5_eq_comp_int(int irq, void *eq_ptr)
+static int mlx5_eq_comp_int(struct notifier_block *nb,
+			    __always_unused unsigned long action,
+			    __always_unused void *data)
 {
-	struct mlx5_eq_comp *eq_comp = eq_ptr;
-	struct mlx5_eq *eq = eq_ptr;
+	struct mlx5_eq_comp *eq_comp =
+		container_of(nb, struct mlx5_eq_comp, irq_nb);
+	struct mlx5_eq *eq = &eq_comp->core;
 	struct mlx5_eqe *eqe;
-	int set_ci = 0;
+	int num_eqes = 0;
 	u32 cqn = -1;
 
-	while ((eqe = next_eqe_sw(eq))) {
+	eqe = next_eqe_sw(eq);
+	if (!eqe)
+		goto out;
+
+	do {
 		struct mlx5_core_cq *cq;
+
 		/* Make sure we read EQ entry contents after we've
 		 * checked the ownership bit.
 		 */
@@ -143,33 +153,23 @@ static irqreturn_t mlx5_eq_comp_int(int irq, void *eq_ptr)
 		cq = mlx5_eq_cq_get(eq, cqn);
 		if (likely(cq)) {
 			++cq->arm_sn;
-			cq->comp(cq);
+			cq->comp(cq, eqe);
 			mlx5_cq_put(cq);
 		} else {
 			mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
 		}
 
 		++eq->cons_index;
-		++set_ci;
 
-		/* The HCA will think the queue has overflowed if we
-		 * don't tell it we've been processing events.  We
-		 * create our EQs with MLX5_NUM_SPARE_EQE extra
-		 * entries, so we must update our consumer index at
-		 * least that often.
-		 */
-		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
-			eq_update_ci(eq, 0);
-			set_ci = 0;
-		}
-	}
+	} while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq)));
 
+out:
 	eq_update_ci(eq, 1);
 
 	if (cqn != -1)
 		tasklet_schedule(&eq_comp->tasklet_ctx.task);
 
-	return IRQ_HANDLED;
+	return 0;
 }
 
 /* Some architectures don't latch interrupts when they are disabled, so using
@@ -183,25 +183,32 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq)
 
 	disable_irq(eq->core.irqn);
 	count_eqe = eq->core.cons_index;
-	mlx5_eq_comp_int(eq->core.irqn, eq);
+	mlx5_eq_comp_int(&eq->irq_nb, 0, NULL);
 	count_eqe = eq->core.cons_index - count_eqe;
 	enable_irq(eq->core.irqn);
 
 	return count_eqe;
 }
 
-static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
+static int mlx5_eq_async_int(struct notifier_block *nb,
+			     unsigned long action, void *data)
 {
-	struct mlx5_eq *eq = eq_ptr;
+	struct mlx5_eq_async *eq_async =
+		container_of(nb, struct mlx5_eq_async, irq_nb);
+	struct mlx5_eq *eq = &eq_async->core;
 	struct mlx5_eq_table *eqt;
 	struct mlx5_core_dev *dev;
 	struct mlx5_eqe *eqe;
-	int set_ci = 0;
+	int num_eqes = 0;
 
 	dev = eq->dev;
 	eqt = dev->priv.eq_table;
 
-	while ((eqe = next_eqe_sw(eq))) {
+	eqe = next_eqe_sw(eq);
+	if (!eqe)
+		goto out;
+
+	do {
 		/*
 		 * Make sure we read EQ entry contents after we've
 		 * checked the ownership bit.
@@ -216,23 +223,13 @@ static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 		atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe);
 
 		++eq->cons_index;
-		++set_ci;
 
-		/* The HCA will think the queue has overflowed if we
-		 * don't tell it we've been processing events.  We
-		 * create our EQs with MLX5_NUM_SPARE_EQE extra
-		 * entries, so we must update our consumer index at
-		 * least that often.
-		 */
-		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
-			eq_update_ci(eq, 0);
-			set_ci = 0;
-		}
-	}
+	} while ((++num_eqes < MLX5_EQ_POLLING_BUDGET) && (eqe = next_eqe_sw(eq)));
 
+out:
 	eq_update_ci(eq, 1);
 
-	return IRQ_HANDLED;
+	return 0;
 }
 
 static void init_eq_buf(struct mlx5_eq *eq)
@@ -247,22 +244,19 @@ static void init_eq_buf(struct mlx5_eq *eq)
 }
 
 static int
-create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, const char *name,
+create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	      struct mlx5_eq_param *param)
 {
-	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	struct mlx5_cq_table *cq_table = &eq->cq_table;
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	struct mlx5_priv *priv = &dev->priv;
-	u8 vecidx = param->index;
+	u8 vecidx = param->irq_index;
 	__be64 *pas;
 	void *eqc;
 	int inlen;
 	u32 *in;
 	int err;
-
-	if (eq_table->irq_info[vecidx].context)
-		return -EEXIST;
+	int i;
 
 	/* Init CQ table */
 	memset(cq_table, 0, sizeof(*cq_table));
@@ -290,7 +284,12 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, const char *name,
 	mlx5_fill_page_array(&eq->buf, pas);
 
 	MLX5_SET(create_eq_in, in, opcode, MLX5_CMD_OP_CREATE_EQ);
-	MLX5_SET64(create_eq_in, in, event_bitmask, param->mask);
+	if (!param->mask[0] && MLX5_CAP_GEN(dev, log_max_uctx))
+		MLX5_SET(create_eq_in, in, uid, MLX5_SHARED_RESOURCE_UID);
+
+	for (i = 0; i < 4; i++)
+		MLX5_ARRAY_SET64(create_eq_in, in, event_bitmask, i,
+				 param->mask[i]);
 
 	eqc = MLX5_ADDR_OF(create_eq_in, in, eq_context_entry);
 	MLX5_SET(eqc, eqc, log_eq_size, ilog2(eq->nent));
@@ -303,34 +302,19 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, const char *name,
 	if (err)
 		goto err_in;
 
-	snprintf(eq_table->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
-		 name, pci_name(dev->pdev));
-	eq_table->irq_info[vecidx].context = param->context;
-
 	eq->vecidx = vecidx;
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
 	eq->irqn = pci_irq_vector(dev->pdev, vecidx);
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
-	err = request_irq(eq->irqn, param->handler, 0,
-			  eq_table->irq_info[vecidx].name, param->context);
-	if (err)
-		goto err_eq;
 
 	err = mlx5_debug_eq_add(dev, eq);
 	if (err)
-		goto err_irq;
-
-	/* EQs are created in ARMED state
-	 */
-	eq_update_ci(eq, 1);
+		goto err_eq;
 
 	kvfree(in);
 	return 0;
 
-err_irq:
-	free_irq(eq->irqn, eq);
-
 err_eq:
 	mlx5_cmd_destroy_eq(dev, eq->eqn);
 
@@ -342,18 +326,48 @@ err_buf:
 	return err;
 }
 
-static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+/**
+ * mlx5_eq_enable - Enable EQ for receiving EQEs
+ * @dev - Device which owns the eq
+ * @eq - EQ to enable
+ * @nb - notifier call block
+ * mlx5_eq_enable - must be called after EQ is created in device.
+ */
+int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+		   struct notifier_block *nb)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
-	struct mlx5_irq_info *irq_info;
 	int err;
 
-	irq_info = &eq_table->irq_info[eq->vecidx];
+	err = mlx5_irq_attach_nb(eq_table->irq_table, eq->vecidx, nb);
+	if (!err)
+		eq_update_ci(eq, 1);
 
-	mlx5_debug_eq_remove(dev, eq);
+	return err;
+}
+EXPORT_SYMBOL(mlx5_eq_enable);
+
+/**
+ * mlx5_eq_disable - Enable EQ for receiving EQEs
+ * @dev - Device which owns the eq
+ * @eq - EQ to disable
+ * @nb - notifier call block
+ * mlx5_eq_disable - must be called before EQ is destroyed.
+ */
+void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+		     struct notifier_block *nb)
+{
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+
+	mlx5_irq_detach_nb(eq_table->irq_table, eq->vecidx, nb);
+}
+EXPORT_SYMBOL(mlx5_eq_disable);
 
-	free_irq(eq->irqn, irq_info->context);
-	irq_info->context = NULL;
+static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+{
+	int err;
+
+	mlx5_debug_eq_remove(dev, eq);
 
 	err = mlx5_cmd_destroy_eq(dev, eq->eqn);
 	if (err)
@@ -371,33 +385,31 @@ int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	struct mlx5_cq_table *table = &eq->cq_table;
 	int err;
 
-	spin_lock_irq(&table->lock);
+	spin_lock(&table->lock);
 	err = radix_tree_insert(&table->tree, cq->cqn, cq);
-	spin_unlock_irq(&table->lock);
+	spin_unlock(&table->lock);
 
 	return err;
 }
 
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
+void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 {
 	struct mlx5_cq_table *table = &eq->cq_table;
 	struct mlx5_core_cq *tmp;
 
-	spin_lock_irq(&table->lock);
+	spin_lock(&table->lock);
 	tmp = radix_tree_delete(&table->tree, cq->cqn);
-	spin_unlock_irq(&table->lock);
+	spin_unlock(&table->lock);
 
 	if (!tmp) {
-		mlx5_core_warn(eq->dev, "cq 0x%x not found in eq 0x%x tree\n", eq->eqn, cq->cqn);
-		return -ENOENT;
+		mlx5_core_dbg(eq->dev, "cq 0x%x not found in eq 0x%x tree\n",
+			      eq->eqn, cq->cqn);
+		return;
 	}
 
-	if (tmp != cq) {
-		mlx5_core_warn(eq->dev, "corruption on cqn 0x%x in eq 0x%x\n", eq->eqn, cq->cqn);
-		return -EINVAL;
-	}
-
-	return 0;
+	if (tmp != cq)
+		mlx5_core_dbg(eq->dev, "corruption on cqn 0x%x in eq 0x%x\n",
+			      eq->eqn, cq->cqn);
 }
 
 int mlx5_eq_table_init(struct mlx5_core_dev *dev)
@@ -419,6 +431,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 	for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++)
 		ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
 
+	eq_table->irq_table = dev->priv.irq_table;
 	return 0;
 
 kvfree_eq_table:
@@ -435,19 +448,20 @@ void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
 
 /* Async EQs */
 
-static int create_async_eq(struct mlx5_core_dev *dev, const char *name,
+static int create_async_eq(struct mlx5_core_dev *dev,
 			   struct mlx5_eq *eq, struct mlx5_eq_param *param)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
 
 	mutex_lock(&eq_table->lock);
-	if (param->index >= MLX5_EQ_MAX_ASYNC_EQS) {
-		err = -ENOSPC;
+	/* Async EQs must share irq index 0 */
+	if (param->irq_index != 0) {
+		err = -EINVAL;
 		goto unlock;
 	}
 
-	err = create_map_eq(dev, eq, name, param);
+	err = create_map_eq(dev, eq, param);
 unlock:
 	mutex_unlock(&eq_table->lock);
 	return err;
@@ -476,7 +490,7 @@ static int cq_err_event_notifier(struct notifier_block *nb,
 	/* type == MLX5_EVENT_TYPE_CQ_ERROR */
 
 	eqt = mlx5_nb_cof(nb, struct mlx5_eq_table, cq_err_nb);
-	eq  = &eqt->async_eq;
+	eq  = &eqt->async_eq.core;
 	eqe = data;
 
 	cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
@@ -489,22 +503,38 @@ static int cq_err_event_notifier(struct notifier_block *nb,
 		return NOTIFY_OK;
 	}
 
-	cq->event(cq, type);
+	if (cq->event)
+		cq->event(cq, type);
 
 	mlx5_cq_put(cq);
 
 	return NOTIFY_OK;
 }
 
-static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
+static void gather_user_async_events(struct mlx5_core_dev *dev, u64 mask[4])
+{
+	__be64 *user_unaffiliated_events;
+	__be64 *user_affiliated_events;
+	int i;
+
+	user_affiliated_events =
+		MLX5_CAP_DEV_EVENT(dev, user_affiliated_events);
+	user_unaffiliated_events =
+		MLX5_CAP_DEV_EVENT(dev, user_unaffiliated_events);
+
+	for (i = 0; i < 4; i++)
+		mask[i] |= be64_to_cpu(user_affiliated_events[i] |
+				       user_unaffiliated_events[i]);
+}
+
+static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4])
 {
 	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
 
 	if (MLX5_VPORT_MANAGER(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
 
-	if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH &&
-	    MLX5_CAP_GEN(dev, general_notification_event))
+	if (MLX5_CAP_GEN(dev, general_notification_event))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_GENERAL_EVENT);
 
 	if (MLX5_CAP_GEN(dev, port_module_event))
@@ -530,7 +560,14 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER);
 
-	return async_event_mask;
+	if (mlx5_eswitch_is_funcs_handler(dev))
+		async_event_mask |=
+			(1ull << MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED);
+
+	mask[0] = async_event_mask;
+
+	if (MLX5_CAP_GEN(dev, event_cap))
+		gather_user_async_events(dev, mask);
 }
 
 static int create_async_eqs(struct mlx5_core_dev *dev)
@@ -542,55 +579,76 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	MLX5_NB_INIT(&table->cq_err_nb, cq_err_event_notifier, CQ_ERROR);
 	mlx5_eq_notifier_register(dev, &table->cq_err_nb);
 
+	table->cmd_eq.irq_nb.notifier_call = mlx5_eq_async_int;
 	param = (struct mlx5_eq_param) {
-		.index = MLX5_EQ_CMD_IDX,
-		.mask = 1ull << MLX5_EVENT_TYPE_CMD,
+		.irq_index = 0,
 		.nent = MLX5_NUM_CMD_EQE,
-		.context = &table->cmd_eq,
-		.handler = mlx5_eq_async_int,
 	};
-	err = create_async_eq(dev, "mlx5_cmd_eq", &table->cmd_eq, &param);
+
+	param.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD;
+	err = create_async_eq(dev, &table->cmd_eq.core, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
 		goto err0;
 	}
-
+	err = mlx5_eq_enable(dev, &table->cmd_eq.core, &table->cmd_eq.irq_nb);
+	if (err) {
+		mlx5_core_warn(dev, "failed to enable cmd EQ %d\n", err);
+		goto err1;
+	}
 	mlx5_cmd_use_events(dev);
 
+	table->async_eq.irq_nb.notifier_call = mlx5_eq_async_int;
 	param = (struct mlx5_eq_param) {
-		.index = MLX5_EQ_ASYNC_IDX,
-		.mask = gather_async_events_mask(dev),
+		.irq_index = 0,
 		.nent = MLX5_NUM_ASYNC_EQE,
-		.context = &table->async_eq,
-		.handler = mlx5_eq_async_int,
 	};
-	err = create_async_eq(dev, "mlx5_async_eq", &table->async_eq, &param);
+
+	gather_async_events_mask(dev, param.mask);
+	err = create_async_eq(dev, &table->async_eq.core, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
-		goto err1;
+		goto err2;
+	}
+	err = mlx5_eq_enable(dev, &table->async_eq.core,
+			     &table->async_eq.irq_nb);
+	if (err) {
+		mlx5_core_warn(dev, "failed to enable async EQ %d\n", err);
+		goto err3;
 	}
 
+	table->pages_eq.irq_nb.notifier_call = mlx5_eq_async_int;
 	param = (struct mlx5_eq_param) {
-		.index = MLX5_EQ_PAGEREQ_IDX,
-		.mask =  1 << MLX5_EVENT_TYPE_PAGE_REQUEST,
+		.irq_index = 0,
 		.nent = /* TODO: sriov max_vf + */ 1,
-		.context = &table->pages_eq,
-		.handler = mlx5_eq_async_int,
 	};
-	err = create_async_eq(dev, "mlx5_pages_eq", &table->pages_eq, &param);
+
+	param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST;
+	err = create_async_eq(dev, &table->pages_eq.core, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
-		goto err2;
+		goto err4;
+	}
+	err = mlx5_eq_enable(dev, &table->pages_eq.core,
+			     &table->pages_eq.irq_nb);
+	if (err) {
+		mlx5_core_warn(dev, "failed to enable pages EQ %d\n", err);
+		goto err5;
 	}
 
 	return err;
 
+err5:
+	destroy_async_eq(dev, &table->pages_eq.core);
+err4:
+	mlx5_eq_disable(dev, &table->async_eq.core, &table->async_eq.irq_nb);
+err3:
+	destroy_async_eq(dev, &table->async_eq.core);
 err2:
-	destroy_async_eq(dev, &table->async_eq);
-
-err1:
 	mlx5_cmd_use_polling(dev);
-	destroy_async_eq(dev, &table->cmd_eq);
+	mlx5_eq_disable(dev, &table->cmd_eq.core, &table->cmd_eq.irq_nb);
+err1:
+	destroy_async_eq(dev, &table->cmd_eq.core);
 err0:
 	mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
 	return err;
@@ -601,19 +659,22 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	int err;
 
-	err = destroy_async_eq(dev, &table->pages_eq);
+	mlx5_eq_disable(dev, &table->pages_eq.core, &table->pages_eq.irq_nb);
+	err = destroy_async_eq(dev, &table->pages_eq.core);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
 			      err);
 
-	err = destroy_async_eq(dev, &table->async_eq);
+	mlx5_eq_disable(dev, &table->async_eq.core, &table->async_eq.irq_nb);
+	err = destroy_async_eq(dev, &table->async_eq.core);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
 			      err);
 
 	mlx5_cmd_use_polling(dev);
 
-	err = destroy_async_eq(dev, &table->cmd_eq);
+	mlx5_eq_disable(dev, &table->cmd_eq.core, &table->cmd_eq.irq_nb);
+	err = destroy_async_eq(dev, &table->cmd_eq.core);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
 			      err);
@@ -623,24 +684,24 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev)
 
 struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev)
 {
-	return &dev->priv.eq_table->async_eq;
+	return &dev->priv.eq_table->async_eq.core;
 }
 
 void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev)
 {
-	synchronize_irq(dev->priv.eq_table->async_eq.irqn);
+	synchronize_irq(dev->priv.eq_table->async_eq.core.irqn);
 }
 
 void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev)
 {
-	synchronize_irq(dev->priv.eq_table->cmd_eq.irqn);
+	synchronize_irq(dev->priv.eq_table->cmd_eq.core.irqn);
 }
 
 /* Generic EQ API for mlx5_core consumers
  * Needed For RDMA ODP EQ for now
  */
 struct mlx5_eq *
-mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+mlx5_eq_create_generic(struct mlx5_core_dev *dev,
 		       struct mlx5_eq_param *param)
 {
 	struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL);
@@ -649,7 +710,7 @@ mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
 	if (!eq)
 		return ERR_PTR(-ENOMEM);
 
-	err = create_async_eq(dev, name, eq, param);
+	err = create_async_eq(dev, eq, param);
 	if (err) {
 		kvfree(eq);
 		eq = ERR_PTR(err);
@@ -703,88 +764,18 @@ void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm)
 
 	__raw_writel((__force u32)cpu_to_be32(val), addr);
 	/* We still want ordering, just not swabbing, so add a barrier */
-	mb();
+	wmb();
 }
 EXPORT_SYMBOL(mlx5_eq_update_ci);
 
-/* Completion EQs */
-
-static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
-	int irq = pci_irq_vector(mdev->pdev, vecidx);
-	struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
-
-	if (!zalloc_cpumask_var(&irq_info->mask, GFP_KERNEL)) {
-		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
-		return -ENOMEM;
-	}
-
-	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			irq_info->mask);
-
-	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, irq_info->mask))
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
-
-	return 0;
-}
-
-static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
-	struct mlx5_priv *priv  = &mdev->priv;
-	int irq = pci_irq_vector(mdev->pdev, vecidx);
-	struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
-
-	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(irq_info->mask);
-}
-
-static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int err;
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++) {
-		err = set_comp_irq_affinity_hint(mdev, i);
-		if (err)
-			goto err_out;
-	}
-
-	return 0;
-
-err_out:
-	for (i--; i >= 0; i--)
-		clear_comp_irq_affinity_hint(mdev, i);
-
-	return err;
-}
-
-static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++)
-		clear_comp_irq_affinity_hint(mdev, i);
-}
-
 static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
 	struct mlx5_eq_comp *eq, *n;
 
-	clear_comp_irqs_affinity_hints(dev);
-
-#ifdef CONFIG_RFS_ACCEL
-	if (table->rmap) {
-		free_irq_cpu_rmap(table->rmap);
-		table->rmap = NULL;
-	}
-#endif
 	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
 		list_del(&eq->list);
+		mlx5_eq_disable(dev, &eq->core, &eq->irq_nb);
 		if (destroy_unmap_eq(dev, &eq->core))
 			mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
 				       eq->core.eqn);
@@ -796,23 +787,17 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 static int create_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	char name[MLX5_MAX_IRQ_NAME];
 	struct mlx5_eq_comp *eq;
-	int ncomp_vec;
+	int ncomp_eqs;
 	int nent;
 	int err;
 	int i;
 
 	INIT_LIST_HEAD(&table->comp_eqs_list);
-	ncomp_vec = table->num_comp_vectors;
+	ncomp_eqs = table->num_comp_eqs;
 	nent = MLX5_COMP_EQ_SIZE;
-#ifdef CONFIG_RFS_ACCEL
-	table->rmap = alloc_irq_cpu_rmap(ncomp_vec);
-	if (!table->rmap)
-		return -ENOMEM;
-#endif
-	for (i = 0; i < ncomp_vec; i++) {
-		int vecidx = i + MLX5_EQ_VEC_COMP_BASE;
+	for (i = 0; i < ncomp_eqs; i++) {
+		int vecidx = i + MLX5_IRQ_VEC_COMP_BASE;
 		struct mlx5_eq_param param = {};
 
 		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
@@ -827,33 +812,28 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
 			     (unsigned long)&eq->tasklet_ctx);
 
-#ifdef CONFIG_RFS_ACCEL
-		irq_cpu_rmap_add(table->rmap, pci_irq_vector(dev->pdev, vecidx));
-#endif
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
+		eq->irq_nb.notifier_call = mlx5_eq_comp_int;
 		param = (struct mlx5_eq_param) {
-			.index = vecidx,
-			.mask = 0,
+			.irq_index = vecidx,
 			.nent = nent,
-			.context = &eq->core,
-			.handler = mlx5_eq_comp_int
 		};
-		err = create_map_eq(dev, &eq->core, name, &param);
+		err = create_map_eq(dev, &eq->core, &param);
+		if (err) {
+			kfree(eq);
+			goto clean;
+		}
+		err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb);
 		if (err) {
+			destroy_unmap_eq(dev, &eq->core);
 			kfree(eq);
 			goto clean;
 		}
+
 		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
 		/* add tail, to keep the list ordered, for mlx5_vector2eqn to work */
 		list_add_tail(&eq->list, &table->comp_eqs_list);
 	}
 
-	err = set_comp_irq_affinity_hints(dev);
-	if (err) {
-		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
-		goto clean;
-	}
-
 	return 0;
 
 clean:
@@ -884,26 +864,26 @@ EXPORT_SYMBOL(mlx5_vector2eqn);
 
 unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
 {
-	return dev->priv.eq_table->num_comp_vectors;
+	return dev->priv.eq_table->num_comp_eqs;
 }
 EXPORT_SYMBOL(mlx5_comp_vectors_count);
 
 struct cpumask *
 mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
 {
-	/* TODO: consider irq_get_affinity_mask(irq) */
-	return dev->priv.eq_table->irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
+	int vecidx = vector + MLX5_IRQ_VEC_COMP_BASE;
+
+	return mlx5_irq_get_affinity_mask(dev->priv.eq_table->irq_table,
+					  vecidx);
 }
 EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask);
 
+#ifdef CONFIG_RFS_ACCEL
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
 {
-#ifdef CONFIG_RFS_ACCEL
-	return dev->priv.eq_table->rmap;
-#else
-	return NULL;
-#endif
+	return mlx5_irq_get_rmap(dev->priv.eq_table->irq_table);
 }
+#endif
 
 struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 {
@@ -922,82 +902,19 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	int i, max_eqs;
-
-	clear_comp_irqs_affinity_hints(dev);
-
-#ifdef CONFIG_RFS_ACCEL
-	if (table->rmap) {
-		free_irq_cpu_rmap(table->rmap);
-		table->rmap = NULL;
-	}
-#endif
 
 	mutex_lock(&table->lock); /* sync with create/destroy_async_eq */
-	max_eqs = table->num_comp_vectors + MLX5_EQ_VEC_COMP_BASE;
-	for (i = max_eqs - 1; i >= 0; i--) {
-		if (!table->irq_info[i].context)
-			continue;
-		free_irq(pci_irq_vector(dev->pdev, i), table->irq_info[i].context);
-		table->irq_info[i].context = NULL;
-	}
+	mlx5_irq_table_destroy(dev);
 	mutex_unlock(&table->lock);
-	pci_free_irq_vectors(dev->pdev);
-}
-
-static int alloc_irq_vectors(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_eq_table *table = priv->eq_table;
-	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
-		      MLX5_CAP_GEN(dev, max_num_eqs) :
-		      1 << MLX5_CAP_GEN(dev, log_max_eq);
-	int nvec;
-	int err;
-
-	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
-	       MLX5_EQ_VEC_COMP_BASE;
-	nvec = min_t(int, nvec, num_eqs);
-	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
-		return -ENOMEM;
-
-	table->irq_info = kcalloc(nvec, sizeof(*table->irq_info), GFP_KERNEL);
-	if (!table->irq_info)
-		return -ENOMEM;
-
-	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1,
-				     nvec, PCI_IRQ_MSIX);
-	if (nvec < 0) {
-		err = nvec;
-		goto err_free_irq_info;
-	}
-
-	table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
-
-	return 0;
-
-err_free_irq_info:
-	kfree(table->irq_info);
-	return err;
-}
-
-static void free_irq_vectors(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv = &dev->priv;
-
-	pci_free_irq_vectors(dev->pdev);
-	kfree(priv->eq_table->irq_info);
 }
 
 int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 {
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
 
-	err = alloc_irq_vectors(dev);
-	if (err) {
-		mlx5_core_err(dev, "alloc irq vectors failed\n");
-		return err;
-	}
+	eq_table->num_comp_eqs =
+		mlx5_irq_get_num_comp(eq_table->irq_table);
 
 	err = create_async_eqs(dev);
 	if (err) {
@@ -1015,7 +932,6 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 err_comp_eqs:
 	destroy_async_eqs(dev);
 err_async_eqs:
-	free_irq_vectors(dev);
 	return err;
 }
 
@@ -1023,7 +939,6 @@ void mlx5_eq_table_destroy(struct mlx5_core_dev *dev)
 {
 	destroy_comp_eqs(dev);
 	destroy_async_eqs(dev);
-	free_irq_vectors(dev);
 }
 
 int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
@@ -1035,6 +950,7 @@ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 
 	return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb);
 }
+EXPORT_SYMBOL(mlx5_eq_notifier_register);
 
 int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 {
@@ -1045,3 +961,4 @@ int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 
 	return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb);
 }
+EXPORT_SYMBOL(mlx5_eq_notifier_unregister);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 5b492b67f4e1..3b04d8927fb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -39,8 +39,7 @@
 #include "lib/eq.h"
 #include "eswitch.h"
 #include "fs_core.h"
-
-#define UPLINK_VPORT 0xFFFF
+#include "ecpf.h"
 
 enum {
 	MLX5_ACTION_NONE = 0,
@@ -52,7 +51,7 @@ enum {
 struct vport_addr {
 	struct l2addr_node     node;
 	u8                     action;
-	u32                    vport;
+	u16                    vport;
 	struct mlx5_flow_handle *flow_rule;
 	bool mpfs; /* UC MAC was added to MPFs */
 	/* A flag indicating that mac was added due to mc promiscuous vport */
@@ -65,11 +64,33 @@ enum {
 	PROMISC_CHANGE = BIT(3),
 };
 
+static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw);
+static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw);
+
 /* Vport context events */
 #define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \
 			    MC_ADDR_CHANGE | \
 			    PROMISC_CHANGE)
 
+struct mlx5_vport *__must_check
+mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	u16 idx;
+
+	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager))
+		return ERR_PTR(-EPERM);
+
+	idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+	if (idx > esw->total_vports - 1) {
+		esw_debug(esw->dev, "vport out of range: num(0x%x), idx(0x%x)\n",
+			  vport_num, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &esw->vports[idx];
+}
+
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 					u32 events_mask)
 {
@@ -81,8 +102,7 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 		 opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 	MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
 	nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in,
 				     in, nic_vport_context);
 
@@ -110,12 +130,35 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
 	MLX5_SET(modify_esw_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT);
 	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
 	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 }
 
-static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+					  void *in, int inlen)
+{
+	return modify_esw_vport_context_cmd(esw->dev, vport, in, inlen);
+}
+
+static int query_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
+				       void *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
+
+	MLX5_SET(query_esw_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
+	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
+	MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+					 void *out, int outlen)
+{
+	return query_esw_vport_context_cmd(esw->dev, vport, out, outlen);
+}
+
+static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 				  u16 vlan, u8 qos, u8 set_flags)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0};
@@ -152,7 +195,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
 
 /* E-Switch FDB */
 static struct mlx5_flow_handle *
-__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
+__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule,
 			 u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
 {
 	int match_header = (is_zero_ether_addr(mac_c) ? 0 :
@@ -188,7 +231,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 					misc_parameters);
 		mc_misc  = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 					misc_parameters);
-		MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT);
+		MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK);
 		MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port);
 	}
 
@@ -215,7 +258,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
+esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 
@@ -224,7 +267,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 	u8 mac_v[ETH_ALEN];
@@ -237,7 +280,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 	u8 mac_v[ETH_ALEN];
@@ -247,6 +290,37 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
 	return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
 }
 
+enum {
+	LEGACY_VEPA_PRIO = 0,
+	LEGACY_FDB_PRIO,
+};
+
+static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_table *fdb;
+	int err;
+
+	root_ns = mlx5_get_fdb_sub_ns(dev, 0);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* num FTE 2, num FG 2 */
+	fdb = mlx5_create_auto_grouped_flow_table(root_ns, LEGACY_VEPA_PRIO,
+						  2, 2, 0, 0);
+	if (IS_ERR(fdb)) {
+		err = PTR_ERR(fdb);
+		esw_warn(dev, "Failed to create VEPA FDB err %d\n", err);
+		return err;
+	}
+	esw->fdb_table.legacy.vepa_fdb = fdb;
+
+	return 0;
+}
+
 static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -275,8 +349,8 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 		return -ENOMEM;
 
 	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
-
 	ft_attr.max_fte = table_size;
+	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
@@ -335,41 +409,67 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	esw->fdb_table.legacy.promisc_grp = g;
 
 out:
-	if (err) {
-		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.allmulti_grp)) {
-			mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
-			esw->fdb_table.legacy.allmulti_grp = NULL;
-		}
-		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.addr_grp)) {
-			mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
-			esw->fdb_table.legacy.addr_grp = NULL;
-		}
-		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.fdb)) {
-			mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb);
-			esw->fdb_table.legacy.fdb = NULL;
-		}
-	}
+	if (err)
+		esw_destroy_legacy_fdb_table(esw);
 
 	kvfree(flow_group_in);
 	return err;
 }
 
+static void esw_destroy_legacy_vepa_table(struct mlx5_eswitch *esw)
+{
+	esw_debug(esw->dev, "Destroy VEPA Table\n");
+	if (!esw->fdb_table.legacy.vepa_fdb)
+		return;
+
+	mlx5_destroy_flow_table(esw->fdb_table.legacy.vepa_fdb);
+	esw->fdb_table.legacy.vepa_fdb = NULL;
+}
+
 static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
+	esw_debug(esw->dev, "Destroy FDB Table\n");
 	if (!esw->fdb_table.legacy.fdb)
 		return;
 
-	esw_debug(esw->dev, "Destroy FDB Table\n");
-	mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
+	if (esw->fdb_table.legacy.promisc_grp)
+		mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
+	if (esw->fdb_table.legacy.allmulti_grp)
+		mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
+	if (esw->fdb_table.legacy.addr_grp)
+		mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
 	mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb);
+
 	esw->fdb_table.legacy.fdb = NULL;
 	esw->fdb_table.legacy.addr_grp = NULL;
 	esw->fdb_table.legacy.allmulti_grp = NULL;
 	esw->fdb_table.legacy.promisc_grp = NULL;
 }
 
+static int esw_create_legacy_table(struct mlx5_eswitch *esw)
+{
+	int err;
+
+	memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb));
+
+	err = esw_create_legacy_vepa_table(esw);
+	if (err)
+		return err;
+
+	err = esw_create_legacy_fdb_table(esw);
+	if (err)
+		esw_destroy_legacy_vepa_table(esw);
+
+	return err;
+}
+
+static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
+{
+	esw_cleanup_vepa_rules(esw);
+	esw_destroy_legacy_fdb_table(esw);
+	esw_destroy_legacy_vepa_table(esw);
+}
+
 /* E-Switch vport UC/MC lists management */
 typedef int (*vport_addr_action)(struct mlx5_eswitch *esw,
 				 struct vport_addr *vaddr);
@@ -377,19 +477,19 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw,
 static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 	int err;
 
-	/* Skip mlx5_mpfs_add_mac for PFs,
-	 * it is already done by the PF netdev in mlx5e_execute_l2_action
+	/* Skip mlx5_mpfs_add_mac for eswitch_managers,
+	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (!vport)
+	if (esw->manager_vport == vport)
 		goto fdb_add;
 
 	err = mlx5_mpfs_add_mac(esw->dev, mac);
 	if (err) {
 		esw_warn(esw->dev,
-			 "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n",
+			 "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n",
 			 mac, vport, err);
 		return err;
 	}
@@ -397,7 +497,7 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 
 fdb_add:
 	/* SRIOV is enabled: Forward UC MAC to vport */
-	if (esw->fdb_table.legacy.fdb && esw->mode == SRIOV_LEGACY)
+	if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY)
 		vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);
 
 	esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n",
@@ -409,13 +509,13 @@ fdb_add:
 static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 	int err = 0;
 
-	/* Skip mlx5_mpfs_del_mac for PFs,
-	 * it is already done by the PF netdev in mlx5e_execute_l2_action
+	/* Skip mlx5_mpfs_del_mac for eswitch managerss,
+	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (!vport || !vaddr->mpfs)
+	if (!vaddr->mpfs || esw->manager_vport == vport)
 		goto fdb_del;
 
 	err = mlx5_mpfs_del_mac(esw->dev, mac);
@@ -438,17 +538,18 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 				   struct esw_mc_addr *esw_mc)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport_idx = 0;
+	struct mlx5_vport *vport;
+	u16 i, vport_num;
 
-	for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) {
-		struct mlx5_vport *vport = &esw->vports[vport_idx];
+	mlx5_esw_for_all_vports(esw, i, vport) {
 		struct hlist_head *vport_hash = vport->mc_list;
 		struct vport_addr *iter_vaddr =
 					l2addr_hash_find(vport_hash,
 							 mac,
 							 struct vport_addr);
+		vport_num = vport->vport;
 		if (IS_ERR_OR_NULL(vport->allmulti_rule) ||
-		    vaddr->vport == vport_idx)
+		    vaddr->vport == vport_num)
 			continue;
 		switch (vaddr->action) {
 		case MLX5_ACTION_ADD:
@@ -460,14 +561,14 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 			if (!iter_vaddr) {
 				esw_warn(esw->dev,
 					 "ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n",
-					 mac, vport_idx);
+					 mac, vport_num);
 				continue;
 			}
-			iter_vaddr->vport = vport_idx;
+			iter_vaddr->vport = vport_num;
 			iter_vaddr->flow_rule =
 					esw_fdb_set_vport_rule(esw,
 							       mac,
-							       vport_idx);
+							       vport_num);
 			iter_vaddr->mc_promisc = true;
 			break;
 		case MLX5_ACTION_DEL:
@@ -485,7 +586,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	struct hlist_head *hash = esw->mc_table;
 	struct esw_mc_addr *esw_mc;
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 
 	if (!esw->fdb_table.legacy.fdb)
 		return 0;
@@ -499,7 +600,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 		return -ENOMEM;
 
 	esw_mc->uplink_rule = /* Forward MC MAC to Uplink */
-		esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT);
+		esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK);
 
 	/* Add this multicast mac to all the mc promiscuous vports */
 	update_allmulti_vports(esw, vaddr, esw_mc);
@@ -525,7 +626,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	struct hlist_head *hash = esw->mc_table;
 	struct esw_mc_addr *esw_mc;
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 
 	if (!esw->fdb_table.legacy.fdb)
 		return 0;
@@ -564,9 +665,8 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 
 /* Apply vport UC/MC list to HW l2 table and FDB table */
 static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
-				      u32 vport_num, int list_type)
+				      struct mlx5_vport *vport, int list_type)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
 	vport_addr_action vport_addr_add;
 	vport_addr_action vport_addr_del;
@@ -599,9 +699,8 @@ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
 
 /* Sync vport UC/MC list from vport context */
 static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
-				       u32 vport_num, int list_type)
+				       struct mlx5_vport *vport, int list_type)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
 	u8 (*mac_list)[ETH_ALEN];
 	struct l2addr_node *node;
@@ -630,12 +729,12 @@ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
 	if (!vport->enabled)
 		goto out;
 
-	err = mlx5_query_nic_vport_mac_list(esw->dev, vport_num, list_type,
+	err = mlx5_query_nic_vport_mac_list(esw->dev, vport->vport, list_type,
 					    mac_list, &size);
 	if (err)
 		goto out;
 	esw_debug(esw->dev, "vport[%d] context update %s list size (%d)\n",
-		  vport_num, is_uc ? "UC" : "MC", size);
+		  vport->vport, is_uc ? "UC" : "MC", size);
 
 	for (i = 0; i < size; i++) {
 		if (is_uc && !is_valid_ether_addr(mac_list[i]))
@@ -673,10 +772,10 @@ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
 		if (!addr) {
 			esw_warn(esw->dev,
 				 "Failed to add MAC(%pM) to vport[%d] DB\n",
-				 mac_list[i], vport_num);
+				 mac_list[i], vport->vport);
 			continue;
 		}
-		addr->vport = vport_num;
+		addr->vport = vport->vport;
 		addr->action = MLX5_ACTION_ADD;
 	}
 out:
@@ -686,9 +785,9 @@ out:
 /* Sync vport UC/MC list from vport context
  * Must be called after esw_update_vport_addr_list
  */
-static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw,
+					struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	struct l2addr_node *node;
 	struct vport_addr *addr;
 	struct hlist_head *hash;
@@ -711,32 +810,32 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
 		if (!addr) {
 			esw_warn(esw->dev,
 				 "Failed to add allmulti MAC(%pM) to vport[%d] DB\n",
-				 mac, vport_num);
+				 mac, vport->vport);
 			continue;
 		}
-		addr->vport = vport_num;
+		addr->vport = vport->vport;
 		addr->action = MLX5_ACTION_ADD;
 		addr->mc_promisc = true;
 	}
 }
 
 /* Apply vport rx mode to HW FDB table */
-static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
+static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport,
 				    bool promisc, bool mc_promisc)
 {
 	struct esw_mc_addr *allmulti_addr = &esw->mc_promisc;
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 
 	if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc)
 		goto promisc;
 
 	if (mc_promisc) {
 		vport->allmulti_rule =
-				esw_fdb_set_vport_allmulti_rule(esw, vport_num);
+			esw_fdb_set_vport_allmulti_rule(esw, vport->vport);
 		if (!allmulti_addr->uplink_rule)
 			allmulti_addr->uplink_rule =
 				esw_fdb_set_vport_allmulti_rule(esw,
-								UPLINK_VPORT);
+								MLX5_VPORT_UPLINK);
 		allmulti_addr->refcnt++;
 	} else if (vport->allmulti_rule) {
 		mlx5_del_flow_rules(vport->allmulti_rule);
@@ -755,8 +854,8 @@ promisc:
 		return;
 
 	if (promisc) {
-		vport->promisc_rule = esw_fdb_set_vport_promisc_rule(esw,
-								     vport_num);
+		vport->promisc_rule =
+			esw_fdb_set_vport_promisc_rule(esw, vport->vport);
 	} else if (vport->promisc_rule) {
 		mlx5_del_flow_rules(vport->promisc_rule);
 		vport->promisc_rule = NULL;
@@ -764,23 +863,23 @@ promisc:
 }
 
 /* Sync vport rx mode from vport context */
-static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw,
+				     struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	int promisc_all = 0;
 	int promisc_uc = 0;
 	int promisc_mc = 0;
 	int err;
 
 	err = mlx5_query_nic_vport_promisc(esw->dev,
-					   vport_num,
+					   vport->vport,
 					   &promisc_uc,
 					   &promisc_mc,
 					   &promisc_all);
 	if (err)
 		return;
 	esw_debug(esw->dev, "vport[%d] context update rx mode promisc_all=%d, all_multi=%d\n",
-		  vport_num, promisc_all, promisc_mc);
+		  vport->vport, promisc_all, promisc_mc);
 
 	if (!vport->info.trusted || !vport->enabled) {
 		promisc_uc = 0;
@@ -788,7 +887,7 @@ static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num)
 		promisc_all = 0;
 	}
 
-	esw_apply_vport_rx_mode(esw, vport_num, promisc_all,
+	esw_apply_vport_rx_mode(esw, vport, promisc_all,
 				(promisc_all || promisc_mc));
 }
 
@@ -798,32 +897,26 @@ static void esw_vport_change_handle_locked(struct mlx5_vport *vport)
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	u8 mac[ETH_ALEN];
 
-	mlx5_query_nic_vport_mac_address(dev, vport->vport, mac);
+	mlx5_query_nic_vport_mac_address(dev, vport->vport, true, mac);
 	esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n",
 		  vport->vport, mac);
 
 	if (vport->enabled_events & UC_ADDR_CHANGE) {
-		esw_update_vport_addr_list(esw, vport->vport,
-					   MLX5_NVPRT_LIST_TYPE_UC);
-		esw_apply_vport_addr_list(esw, vport->vport,
-					  MLX5_NVPRT_LIST_TYPE_UC);
+		esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC);
+		esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC);
 	}
 
-	if (vport->enabled_events & MC_ADDR_CHANGE) {
-		esw_update_vport_addr_list(esw, vport->vport,
-					   MLX5_NVPRT_LIST_TYPE_MC);
-	}
+	if (vport->enabled_events & MC_ADDR_CHANGE)
+		esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC);
 
 	if (vport->enabled_events & PROMISC_CHANGE) {
-		esw_update_vport_rx_mode(esw, vport->vport);
+		esw_update_vport_rx_mode(esw, vport);
 		if (!IS_ERR_OR_NULL(vport->allmulti_rule))
-			esw_update_vport_mc_promisc(esw, vport->vport);
+			esw_update_vport_mc_promisc(esw, vport);
 	}
 
-	if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE)) {
-		esw_apply_vport_addr_list(esw, vport->vport,
-					  MLX5_NVPRT_LIST_TYPE_MC);
-	}
+	if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE))
+		esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC);
 
 	esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport);
 	if (vport->enabled)
@@ -842,8 +935,8 @@ static void esw_vport_change_handler(struct work_struct *work)
 	mutex_unlock(&esw->state_lock);
 }
 
-static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
-				       struct mlx5_vport *vport)
+int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *vlan_grp = NULL;
@@ -870,7 +963,7 @@ static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 		  vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));
 
 	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-						    vport->vport);
+			mlx5_eswitch_vport_num_to_index(esw, vport->vport));
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch egress flow namespace for vport (%d)\n", vport->vport);
 		return -EOPNOTSUPP;
@@ -926,8 +1019,8 @@ out:
 	return err;
 }
 
-static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
-					   struct mlx5_vport *vport)
+void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport)
 {
 	if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan))
 		mlx5_del_flow_rules(vport->egress.allowed_vlan);
@@ -939,8 +1032,8 @@ static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
 	vport->egress.drop_rule = NULL;
 }
 
-static void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
-					 struct mlx5_vport *vport)
+void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport)
 {
 	if (IS_ERR_OR_NULL(vport->egress.acl))
 		return;
@@ -956,8 +1049,8 @@ static void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
 	vport->egress.acl = NULL;
 }
 
-static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
-					struct mlx5_vport *vport)
+int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
+				 struct mlx5_vport *vport)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_core_dev *dev = esw->dev;
@@ -988,7 +1081,7 @@ static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 		  vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
 
 	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
-						    vport->vport);
+			mlx5_eswitch_vport_num_to_index(esw, vport->vport));
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", vport->vport);
 		return -EOPNOTSUPP;
@@ -1088,8 +1181,8 @@ out:
 	return err;
 }
 
-static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
-					    struct mlx5_vport *vport)
+void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
+				     struct mlx5_vport *vport)
 {
 	if (!IS_ERR_OR_NULL(vport->ingress.drop_rule))
 		mlx5_del_flow_rules(vport->ingress.drop_rule);
@@ -1099,10 +1192,12 @@ static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
 
 	vport->ingress.drop_rule = NULL;
 	vport->ingress.allow_rule = NULL;
+
+	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
 }
 
-static void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
-					  struct mlx5_vport *vport)
+void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
+				   struct mlx5_vport *vport)
 {
 	if (IS_ERR_OR_NULL(vport->ingress.acl))
 		return;
@@ -1340,11 +1435,11 @@ static void esw_destroy_tsar(struct mlx5_eswitch *esw)
 	esw->qos.enabled = false;
 }
 
-static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
+static int esw_vport_enable_qos(struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
 				u32 initial_max_rate, u32 initial_bw_share)
 {
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	struct mlx5_core_dev *dev = esw->dev;
 	void *vport_elem;
 	int err = 0;
@@ -1360,7 +1455,7 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
 	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
 				  element_attributes);
-	MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
 	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
 		 esw->qos.root_tsar_id);
 	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
@@ -1373,7 +1468,7 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
 						 &vport->qos.esw_tsar_ix);
 	if (err) {
 		esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport_num, err);
+			 vport->vport, err);
 		return err;
 	}
 
@@ -1381,10 +1476,10 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
 	return 0;
 }
 
-static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
+static void esw_vport_disable_qos(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
-	int err = 0;
+	int err;
 
 	if (!vport->qos.enabled)
 		return;
@@ -1394,16 +1489,16 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
 						  vport->qos.esw_tsar_ix);
 	if (err)
 		esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport_num, err);
+			 vport->vport, err);
 
 	vport->qos.enabled = false;
 }
 
-static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
+static int esw_vport_qos_config(struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
 				u32 max_rate, u32 bw_share)
 {
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	struct mlx5_core_dev *dev = esw->dev;
 	void *vport_elem;
 	u32 bitmask = 0;
@@ -1419,7 +1514,7 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
 	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
 				  element_attributes);
-	MLX5_SET(vport_element, vport_elem, vport_number, vport_num);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
 	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
 		 esw->qos.root_tsar_id);
 	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
@@ -1435,7 +1530,7 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
 						 bitmask);
 	if (err) {
 		esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
-			 vport_num, err);
+			 vport->vport, err);
 		return err;
 	}
 
@@ -1457,22 +1552,32 @@ static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN])
 static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 				 struct mlx5_vport *vport)
 {
-	int vport_num = vport->vport;
+	u16 vport_num = vport->vport;
+	int flags;
 
-	if (!vport_num)
+	if (esw->manager_vport == vport_num)
 		return;
 
 	mlx5_modify_vport_admin_state(esw->dev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-				      vport_num,
+				      vport_num, 1,
 				      vport->info.link_state);
-	mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac);
-	mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, vport->info.node_guid);
+
+	/* Host PF has its own mac/guid. */
+	if (vport_num) {
+		mlx5_modify_nic_vport_mac_address(esw->dev, vport_num,
+						  vport->info.mac);
+		mlx5_modify_nic_vport_node_guid(esw->dev, vport_num,
+						vport->info.node_guid);
+	}
+
+	flags = (vport->info.vlan || vport->info.qos) ?
+		SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
 	modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos,
-			       (vport->info.vlan || vport->info.qos));
+			       flags);
 
 	/* Only legacy mode needs ACLs */
-	if (esw->mode == SRIOV_LEGACY) {
+	if (esw->mode == MLX5_ESWITCH_LEGACY) {
 		esw_vport_ingress_config(esw, vport);
 		esw_vport_egress_config(esw, vport);
 	}
@@ -1513,10 +1618,10 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport)
 		mlx5_fc_destroy(dev, vport->egress.drop_counter);
 }
 
-static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
+static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 			     int enable_events)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	u16 vport_num = vport->vport;
 
 	mutex_lock(&esw->state_lock);
 	WARN_ON(vport->enabled);
@@ -1524,14 +1629,14 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
 
 	/* Create steering drop counters for ingress and egress ACLs */
-	if (vport_num && esw->mode == SRIOV_LEGACY)
+	if (vport_num && esw->mode == MLX5_ESWITCH_LEGACY)
 		esw_vport_create_drop_counters(vport);
 
 	/* Restore old vport configuration */
 	esw_apply_vport_conf(esw, vport);
 
 	/* Attach vport to the eswitch rate limiter */
-	if (esw_vport_enable_qos(esw, vport_num, vport->info.max_rate,
+	if (esw_vport_enable_qos(esw, vport, vport->info.max_rate,
 				 vport->qos.bw_share))
 		esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num);
 
@@ -1539,8 +1644,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	vport->enabled_events = enable_events;
 	vport->enabled = true;
 
-	/* only PF is trusted by default */
-	if (!vport_num)
+	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
+	 * in smartNIC as it's a vport group manager.
+	 */
+	if (esw->manager_vport == vport_num ||
+	    (!vport_num && mlx5_core_is_ecpf(esw->dev)))
 		vport->info.trusted = true;
 
 	esw_vport_change_handle_locked(vport);
@@ -1550,9 +1658,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	mutex_unlock(&esw->state_lock);
 }
 
-static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
+static void esw_disable_vport(struct mlx5_eswitch *esw,
+			      struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	u16 vport_num = vport->vport;
 
 	if (!vport->enabled)
 		return;
@@ -1572,11 +1681,12 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	 */
 	esw_vport_change_handle_locked(vport);
 	vport->enabled_events = 0;
-	esw_vport_disable_qos(esw, vport_num);
-	if (vport_num && esw->mode == SRIOV_LEGACY) {
+	esw_vport_disable_qos(esw, vport);
+	if (esw->manager_vport != vport_num &&
+	    esw->mode == MLX5_ESWITCH_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
 					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					      vport_num,
+					      vport_num, 1,
 					      MLX5_VPORT_ADMIN_STATE_DOWN);
 		esw_vport_disable_egress_acl(esw, vport);
 		esw_vport_disable_ingress_acl(esw, vport);
@@ -1595,45 +1705,101 @@ static int eswitch_vport_event(struct notifier_block *nb,
 	u16 vport_num;
 
 	vport_num = be16_to_cpu(eqe->data.vport_change.vport_num);
-	vport = &esw->vports[vport_num];
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return NOTIFY_OK;
+
 	if (vport->enabled)
 		queue_work(esw->work_queue, &vport->vport_change_handler);
 
 	return NOTIFY_OK;
 }
 
+/**
+ * mlx5_esw_query_functions - Returns raw output about functions state
+ * @dev:	Pointer to device to query
+ *
+ * mlx5_esw_query_functions() allocates and returns functions changed
+ * raw output memory pointer from device on success. Otherwise returns ERR_PTR.
+ * Caller must free the memory using kvfree() when valid pointer is returned.
+ */
+const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_esw_functions_out);
+	u32 in[MLX5_ST_SZ_DW(query_esw_functions_in)] = {};
+	u32 *out;
+	int err;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(query_esw_functions_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_ESW_FUNCTIONS);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	if (!err)
+		return out;
+
+	kvfree(out);
+	return ERR_PTR(err);
+}
+
+static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
+{
+	MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+	mlx5_eq_notifier_register(esw->dev, &esw->nb);
+
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) {
+		MLX5_NB_INIT(&esw->esw_funcs.nb, mlx5_esw_funcs_changed_handler,
+			     ESW_FUNCTIONS_CHANGED);
+		mlx5_eq_notifier_register(esw->dev, &esw->esw_funcs.nb);
+	}
+}
+
+static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
+{
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
+		mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
+
+	mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+
+	flush_workqueue(esw->work_queue);
+}
+
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
+int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode)
 {
+	struct mlx5_vport *vport;
 	int err;
 	int i, enabled_events;
 
 	if (!ESW_ALLOWED(esw) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
-		esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
+		esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
 		return -EOPNOTSUPP;
 	}
 
 	if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support))
-		esw_warn(esw->dev, "E-Switch ingress ACL is not supported by FW\n");
+		esw_warn(esw->dev, "ingress ACL is not supported by FW\n");
 
 	if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support))
-		esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
-
-	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
+		esw_warn(esw->dev, "engress ACL is not supported by FW\n");
 
 	esw->mode = mode;
 
 	mlx5_lag_update(esw->dev);
 
-	if (mode == SRIOV_LEGACY) {
-		err = esw_create_legacy_fdb_table(esw);
+	if (mode == MLX5_ESWITCH_LEGACY) {
+		err = esw_create_legacy_table(esw);
+		if (err)
+			goto abort;
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-		err = esw_offloads_init(esw, nvfs + 1);
+		err = esw_offloads_init(esw);
 	}
 
 	if (err)
@@ -1643,27 +1809,35 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	if (err)
 		esw_warn(esw->dev, "Failed to create eswitch TSAR");
 
-	/* Don't enable vport events when in SRIOV_OFFLOADS mode, since:
-	 * 1. L2 table (MPFS) is programmed by PF/VF representors netdevs set_rx_mode
-	 * 2. FDB/Eswitch is programmed by user space tools
-	 */
-	enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0;
-	for (i = 0; i <= nvfs; i++)
-		esw_enable_vport(esw, i, enabled_events);
+	enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS :
+		UC_ADDR_CHANGE;
+
+	/* Enable PF vport */
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
+	esw_enable_vport(esw, vport, enabled_events);
 
-	if (mode == SRIOV_LEGACY) {
-		MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
-		mlx5_eq_notifier_register(esw->dev, &esw->nb);
+	/* Enable ECPF vports */
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+		esw_enable_vport(esw, vport, enabled_events);
 	}
 
-	esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
-		 esw->enabled_vports);
+	/* Enable VF vports */
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		esw_enable_vport(esw, vport, enabled_events);
+
+	mlx5_eswitch_event_handlers_register(esw);
+
+	esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n",
+		 mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+		 esw->esw_funcs.num_vfs, esw->enabled_vports);
+
 	return 0;
 
 abort:
-	esw->mode = SRIOV_NONE;
+	esw->mode = MLX5_ESWITCH_NONE;
 
-	if (mode == SRIOV_OFFLOADS) {
+	if (mode == MLX5_ESWITCH_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 	}
@@ -1671,44 +1845,42 @@ abort:
 	return err;
 }
 
-void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 {
 	struct esw_mc_addr *mc_promisc;
+	struct mlx5_vport *vport;
 	int old_mode;
-	int nvports;
 	int i;
 
-	if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE)
+	if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE)
 		return;
 
-	esw_info(esw->dev, "disable SRIOV: active vports(%d) mode(%d)\n",
-		 esw->enabled_vports, esw->mode);
+	esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), active vports(%d)\n",
+		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+		 esw->esw_funcs.num_vfs, esw->enabled_vports);
 
 	mc_promisc = &esw->mc_promisc;
-	nvports = esw->enabled_vports;
+	mlx5_eswitch_event_handlers_unregister(esw);
 
-	if (esw->mode == SRIOV_LEGACY)
-		mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
-
-	for (i = 0; i < esw->total_vports; i++)
-		esw_disable_vport(esw, i);
+	mlx5_esw_for_all_vports(esw, i, vport)
+		esw_disable_vport(esw, vport);
 
 	if (mc_promisc && mc_promisc->uplink_rule)
 		mlx5_del_flow_rules(mc_promisc->uplink_rule);
 
 	esw_destroy_tsar(esw);
 
-	if (esw->mode == SRIOV_LEGACY)
-		esw_destroy_legacy_fdb_table(esw);
-	else if (esw->mode == SRIOV_OFFLOADS)
-		esw_offloads_cleanup(esw, nvports);
+	if (esw->mode == MLX5_ESWITCH_LEGACY)
+		esw_destroy_legacy_table(esw);
+	else if (esw->mode == MLX5_ESWITCH_OFFLOADS)
+		esw_offloads_cleanup(esw);
 
 	old_mode = esw->mode;
-	esw->mode = SRIOV_NONE;
+	esw->mode = MLX5_ESWITCH_NONE;
 
 	mlx5_lag_update(esw->dev);
 
-	if (old_mode == SRIOV_OFFLOADS) {
+	if (old_mode == MLX5_ESWITCH_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 	}
@@ -1716,14 +1888,16 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 
 int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 {
-	int total_vports = MLX5_TOTAL_VPORTS(dev);
 	struct mlx5_eswitch *esw;
-	int vport_num;
-	int err;
+	struct mlx5_vport *vport;
+	int total_vports;
+	int err, i;
 
 	if (!MLX5_VPORT_MANAGER(dev))
 		return 0;
 
+	total_vports = mlx5_eswitch_get_total_vports(dev);
+
 	esw_info(dev,
 		 "Total vports %d, per vport: max uc(%d) max mc(%d)\n",
 		 total_vports,
@@ -1735,6 +1909,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	esw->dev = dev;
+	esw->manager_vport = mlx5_eswitch_manager_vport(dev);
+	esw->first_host_vport = mlx5_eswitch_first_host_vport_num(dev);
 
 	esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
 	if (!esw->work_queue) {
@@ -1749,6 +1925,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto abort;
 	}
 
+	esw->total_vports = total_vports;
+
 	err = esw_offloads_init_reps(esw);
 	if (err)
 		goto abort;
@@ -1757,25 +1935,17 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	hash_init(esw->offloads.mod_hdr_tbl);
 	mutex_init(&esw->state_lock);
 
-	for (vport_num = 0; vport_num < total_vports; vport_num++) {
-		struct mlx5_vport *vport = &esw->vports[vport_num];
-
-		vport->vport = vport_num;
+	mlx5_esw_for_all_vports(esw, i, vport) {
+		vport->vport = mlx5_eswitch_index_to_vport_num(esw, i);
 		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 		vport->dev = dev;
 		INIT_WORK(&vport->vport_change_handler,
 			  esw_vport_change_handler);
 	}
 
-	esw->total_vports = total_vports;
 	esw->enabled_vports = 0;
-	esw->mode = SRIOV_NONE;
+	esw->mode = MLX5_ESWITCH_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
-	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) &&
-	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
-	else
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
 	dev->priv.eswitch = esw;
 	return 0;
@@ -1803,22 +1973,19 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 }
 
 /* Vport Administration */
-#define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
-
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
-			       int vport, u8 mac[ETH_ALEN])
+			       u16 vport, u8 mac[ETH_ALEN])
 {
-	struct mlx5_vport *evport;
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 	u64 node_guid;
 	int err = 0;
 
-	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
-		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
+	if (is_multicast_ether_addr(mac))
 		return -EINVAL;
 
 	mutex_lock(&esw->state_lock);
-	evport = &esw->vports[vport];
 
 	if (evport->info.spoofchk && !is_valid_ether_addr(mac))
 		mlx5_core_warn(esw->dev,
@@ -1842,7 +2009,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 
 	ether_addr_copy(evport->info.mac, mac);
 	evport->info.node_guid = node_guid;
-	if (evport->enabled && esw->mode == SRIOV_LEGACY)
+	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 
 unlock:
@@ -1851,22 +2018,21 @@ unlock:
 }
 
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
-				 int vport, int link_state)
+				 u16 vport, int link_state)
 {
-	struct mlx5_vport *evport;
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
-		return -EINVAL;
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
 
 	mutex_lock(&esw->state_lock);
-	evport = &esw->vports[vport];
 
 	err = mlx5_modify_vport_admin_state(esw->dev,
 					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					    vport, link_state);
+					    vport, 1, link_state);
 	if (err) {
 		mlx5_core_warn(esw->dev,
 			       "Failed to set vport %d link state, err = %d",
@@ -1882,16 +2048,12 @@ unlock:
 }
 
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
-				  int vport, struct ifla_vf_info *ivi)
+				  u16 vport, struct ifla_vf_info *ivi)
 {
-	struct mlx5_vport *evport;
-
-	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
-		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
-		return -EINVAL;
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 
-	evport = &esw->vports[vport];
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
 
 	memset(ivi, 0, sizeof(*ivi));
 	ivi->vf = vport - 1;
@@ -1911,18 +2073,19 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 }
 
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
-				  int vport, u16 vlan, u8 qos, u8 set_flags)
+				  u16 vport, u16 vlan, u8 qos, u8 set_flags)
 {
-	struct mlx5_vport *evport;
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport) || (vlan > 4095) || (qos > 7))
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
+	if (vlan > 4095 || qos > 7)
 		return -EINVAL;
 
 	mutex_lock(&esw->state_lock);
-	evport = &esw->vports[vport];
 
 	err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
 	if (err)
@@ -1930,7 +2093,7 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 
 	evport->info.vlan = vlan;
 	evport->info.qos = qos;
-	if (evport->enabled && esw->mode == SRIOV_LEGACY) {
+	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_vport_ingress_config(esw, evport);
 		if (err)
 			goto unlock;
@@ -1943,7 +2106,7 @@ unlock:
 }
 
 int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
-				int vport, u16 vlan, u8 qos)
+				u16 vport, u16 vlan, u8 qos)
 {
 	u8 set_flags = 0;
 
@@ -1954,26 +2117,25 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 }
 
 int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
-				    int vport, bool spoofchk)
+				    u16 vport, bool spoofchk)
 {
-	struct mlx5_vport *evport;
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 	bool pschk;
 	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
-		return -EINVAL;
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
 
 	mutex_lock(&esw->state_lock);
-	evport = &esw->vports[vport];
 	pschk = evport->info.spoofchk;
 	evport->info.spoofchk = spoofchk;
 	if (pschk && !is_valid_ether_addr(evport->info.mac))
 		mlx5_core_warn(esw->dev,
 			       "Spoofchk in set while MAC is invalid, vport(%d)\n",
 			       evport->vport);
-	if (evport->enabled && esw->mode == SRIOV_LEGACY)
+	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 	if (err)
 		evport->info.spoofchk = pschk;
@@ -1982,18 +2144,139 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 	return err;
 }
 
+static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw)
+{
+	if (esw->fdb_table.legacy.vepa_uplink_rule)
+		mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_uplink_rule);
+
+	if (esw->fdb_table.legacy.vepa_star_rule)
+		mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_star_rule);
+
+	esw->fdb_table.legacy.vepa_uplink_rule = NULL;
+	esw->fdb_table.legacy.vepa_star_rule = NULL;
+}
+
+static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw,
+					 u8 setting)
+{
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *flow_rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+	void *misc;
+
+	if (!setting) {
+		esw_cleanup_vepa_rules(esw);
+		return 0;
+	}
+
+	if (esw->fdb_table.legacy.vepa_uplink_rule)
+		return 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	/* Uplink rule forward uplink traffic to FDB */
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK);
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = esw->fdb_table.legacy.fdb;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec,
+					&flow_act, &dest, 1);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		goto out;
+	} else {
+		esw->fdb_table.legacy.vepa_uplink_rule = flow_rule;
+	}
+
+	/* Star rule to forward all traffic to uplink vport */
+	memset(spec, 0, sizeof(*spec));
+	memset(&dest, 0, sizeof(dest));
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest.vport.num = MLX5_VPORT_UPLINK;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec,
+					&flow_act, &dest, 1);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		goto out;
+	} else {
+		esw->fdb_table.legacy.vepa_star_rule = flow_rule;
+	}
+
+out:
+	kvfree(spec);
+	if (err)
+		esw_cleanup_vepa_rules(esw);
+	return err;
+}
+
+int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting)
+{
+	int err = 0;
+
+	if (!esw)
+		return -EOPNOTSUPP;
+
+	if (!ESW_ALLOWED(esw))
+		return -EPERM;
+
+	mutex_lock(&esw->state_lock);
+	if (esw->mode != MLX5_ESWITCH_LEGACY) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	err = _mlx5_eswitch_set_vepa_locked(esw, setting);
+
+out:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
+{
+	int err = 0;
+
+	if (!esw)
+		return -EOPNOTSUPP;
+
+	if (!ESW_ALLOWED(esw))
+		return -EPERM;
+
+	mutex_lock(&esw->state_lock);
+	if (esw->mode != MLX5_ESWITCH_LEGACY) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
+
+out:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
-				 int vport, bool setting)
+				 u16 vport, bool setting)
 {
-	struct mlx5_vport *evport;
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
-		return -EINVAL;
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
 
 	mutex_lock(&esw->state_lock);
-	evport = &esw->vports[vport];
 	evport->info.trusted = setting;
 	if (evport->enabled)
 		esw_vport_change_handle_locked(evport);
@@ -2009,8 +2292,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
 	u32 max_guarantee = 0;
 	int i;
 
-	for (i = 0; i < esw->total_vports; i++) {
-		evport = &esw->vports[i];
+	mlx5_esw_for_all_vports(esw, i, evport) {
 		if (!evport->enabled || evport->info.min_rate < max_guarantee)
 			continue;
 		max_guarantee = evport->info.min_rate;
@@ -2029,8 +2311,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 	int err;
 	int i;
 
-	for (i = 0; i < esw->total_vports; i++) {
-		evport = &esw->vports[i];
+	mlx5_esw_for_all_vports(esw, i, evport) {
 		if (!evport->enabled)
 			continue;
 		vport_min_rate = evport->info.min_rate;
@@ -2045,7 +2326,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 		if (bw_share == evport->qos.bw_share)
 			continue;
 
-		err = esw_vport_qos_config(esw, i, vport_max_rate,
+		err = esw_vport_qos_config(esw, evport, vport_max_rate,
 					   bw_share);
 		if (!err)
 			evport->qos.bw_share = bw_share;
@@ -2056,27 +2337,31 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 	return 0;
 }
 
-int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, int vport,
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
 				u32 max_rate, u32 min_rate)
 {
-	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	bool min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
-					fw_max_bw_share >= MLX5_MIN_BW_SHARE;
-	bool max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
-	struct mlx5_vport *evport;
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+	u32 fw_max_bw_share;
 	u32 previous_min_rate;
 	u32 divider;
+	bool min_rate_supported;
+	bool max_rate_supported;
 	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
-		return -EINVAL;
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
+
+	fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
+				fw_max_bw_share >= MLX5_MIN_BW_SHARE;
+	max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
+
 	if ((min_rate && !min_rate_supported) || (max_rate && !max_rate_supported))
 		return -EOPNOTSUPP;
 
 	mutex_lock(&esw->state_lock);
-	evport = &esw->vports[vport];
 
 	if (min_rate == evport->info.min_rate)
 		goto set_max_rate;
@@ -2094,7 +2379,7 @@ set_max_rate:
 	if (max_rate == evport->info.max_rate)
 		goto unlock;
 
-	err = esw_vport_qos_config(esw, vport, max_rate, evport->qos.bw_share);
+	err = esw_vport_qos_config(esw, evport, max_rate, evport->qos.bw_share);
 	if (!err)
 		evport->info.max_rate = max_rate;
 
@@ -2104,16 +2389,15 @@ unlock:
 }
 
 static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
-					       int vport_idx,
+					       struct mlx5_vport *vport,
 					       struct mlx5_vport_drop_stats *stats)
 {
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
-	struct mlx5_vport *vport = &esw->vports[vport_idx];
 	u64 rx_discard_vport_down, tx_discard_vport_down;
 	u64 bytes = 0;
 	int err = 0;
 
-	if (!vport->enabled || esw->mode != SRIOV_LEGACY)
+	if (!vport->enabled || esw->mode != MLX5_ESWITCH_LEGACY)
 		return 0;
 
 	if (vport->egress.drop_counter)
@@ -2128,7 +2412,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
 	    !MLX5_CAP_GEN(dev, transmit_discard_vport_down))
 		return 0;
 
-	err = mlx5_query_vport_down_stats(dev, vport_idx,
+	err = mlx5_query_vport_down_stats(dev, vport->vport, 1,
 					  &rx_discard_vport_down,
 					  &tx_discard_vport_down);
 	if (err)
@@ -2143,19 +2427,18 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
 }
 
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
-				 int vport,
+				 u16 vport_num,
 				 struct ifla_vf_stats *vf_stats)
 {
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
 	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)] = {0};
 	struct mlx5_vport_drop_stats stats = {0};
 	int err = 0;
 	u32 *out;
 
-	if (!ESW_ALLOWED(esw))
-		return -EPERM;
-	if (!LEGAL_VPORT(esw, vport))
-		return -EINVAL;
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
 
 	out = kvzalloc(outlen, GFP_KERNEL);
 	if (!out)
@@ -2164,9 +2447,8 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 	MLX5_SET(query_vport_counter_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_VPORT_COUNTER);
 	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
-	MLX5_SET(query_vport_counter_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(query_vport_counter_in, in, other_vport, 1);
+	MLX5_SET(query_vport_counter_in, in, vport_number, vport->vport);
+	MLX5_SET(query_vport_counter_in, in, other_vport, 1);
 
 	memset(out, 0, outlen);
 	err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen);
@@ -2225,17 +2507,55 @@ free_out:
 
 u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 {
-	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
+	return ESW_ALLOWED(esw) ? esw->mode : MLX5_ESWITCH_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
 
+enum devlink_eswitch_encap_mode
+mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_eswitch *esw;
+
+	esw = dev->priv.eswitch;
+	return ESW_ALLOWED(esw) ? esw->offloads.encap :
+		DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode);
+
 bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
 {
-	if ((dev0->priv.eswitch->mode == SRIOV_NONE &&
-	     dev1->priv.eswitch->mode == SRIOV_NONE) ||
-	    (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
-	     dev1->priv.eswitch->mode == SRIOV_OFFLOADS))
+	if ((dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+	     dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE) ||
+	    (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+	     dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS))
 		return true;
 
 	return false;
 }
+
+bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
+			       struct mlx5_core_dev *dev1)
+{
+	return (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+		dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS);
+}
+
+void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs)
+{
+	const u32 *out;
+
+	WARN_ON_ONCE(esw->mode != MLX5_ESWITCH_NONE);
+
+	if (!mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		esw->esw_funcs.num_vfs = num_vfs;
+		return;
+	}
+
+	out = mlx5_esw_query_functions(esw->dev);
+	if (IS_ERR(out))
+		return;
+
+	esw->esw_funcs.num_vfs = MLX5_GET(query_esw_functions_out, out,
+					  host_params_context.host_num_of_vfs);
+	kvfree(out);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 748ff178a1d6..a38e8a3c7c9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -38,6 +38,7 @@
 #include <net/devlink.h>
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/eswitch.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
 
@@ -49,8 +50,6 @@
 #define MLX5_MAX_MC_PER_VPORT(dev) \
 	(1 << MLX5_CAP_GEN(dev, log_max_current_mc_list))
 
-#define FDB_UPLINK_VPORT 0xffff
-
 #define MLX5_MIN_BW_SHARE 1
 
 #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \
@@ -69,6 +68,8 @@ struct vport_ingress {
 	struct mlx5_flow_group *allow_spoofchk_only_grp;
 	struct mlx5_flow_group *allow_untagged_only_grp;
 	struct mlx5_flow_group *drop_grp;
+	int modify_metadata_id;
+	struct mlx5_flow_handle  *modify_metadata_rule;
 	struct mlx5_flow_handle  *allow_rule;
 	struct mlx5_flow_handle  *drop_rule;
 	struct mlx5_fc           *drop_counter;
@@ -138,6 +139,9 @@ struct mlx5_eswitch_fdb {
 			struct mlx5_flow_group *addr_grp;
 			struct mlx5_flow_group *allmulti_grp;
 			struct mlx5_flow_group *promisc_grp;
+			struct mlx5_flow_table *vepa_fdb;
+			struct mlx5_flow_handle *vepa_uplink_rule;
+			struct mlx5_flow_handle *vepa_star_rule;
 		} legacy;
 
 		struct offloads_fdb {
@@ -171,9 +175,12 @@ struct mlx5_esw_offload {
 	struct mutex peer_mutex;
 	DECLARE_HASHTABLE(encap_tbl, 8);
 	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
+	DECLARE_HASHTABLE(termtbl_tbl, 8);
+	struct mutex termtbl_mutex; /* protects termtbl hash */
+	const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES];
 	u8 inline_mode;
 	u64 num_flows;
-	u8 encap;
+	enum devlink_eswitch_encap_mode encap;
 };
 
 /* E-Switch MC FDB table hash node */
@@ -183,6 +190,20 @@ struct esw_mc_addr { /* SRIOV only */
 	u32                    refcnt;
 };
 
+struct mlx5_host_work {
+	struct work_struct	work;
+	struct mlx5_eswitch	*esw;
+};
+
+struct mlx5_esw_functions {
+	struct mlx5_nb		nb;
+	u16			num_vfs;
+};
+
+enum {
+	MLX5_ESWITCH_VPORT_MATCH_METADATA = BIT(0),
+};
+
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
 	struct mlx5_nb          nb;
@@ -190,6 +211,7 @@ struct mlx5_eswitch {
 	struct hlist_head       mc_table[MLX5_L2_ADDR_HASH_SIZE];
 	struct workqueue_struct *work_queue;
 	struct mlx5_vport       *vports;
+	u32 flags;
 	int                     total_vports;
 	int                     enabled_vports;
 	/* Synchronize between vport change events
@@ -206,39 +228,82 @@ struct mlx5_eswitch {
 	struct mlx5_esw_offload offloads;
 	int                     mode;
 	int                     nvports;
+	u16                     manager_vport;
+	u16                     first_host_vport;
+	struct mlx5_esw_functions esw_funcs;
 };
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports);
-int esw_offloads_init(struct mlx5_eswitch *esw, int nvports);
+void esw_offloads_cleanup(struct mlx5_eswitch *esw);
+int esw_offloads_init(struct mlx5_eswitch *esw);
 void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
 int esw_offloads_init_reps(struct mlx5_eswitch *esw);
+void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
+				     struct mlx5_vport *vport);
+int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
+				 struct mlx5_vport *vport);
+void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport);
+int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport);
+void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport);
+void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
+				   struct mlx5_vport *vport);
+void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+					       struct mlx5_vport *vport);
 
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode);
-void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw);
+int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode);
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
-			       int vport, u8 mac[ETH_ALEN]);
+			       u16 vport, u8 mac[ETH_ALEN]);
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
-				 int vport, int link_state);
+				 u16 vport, int link_state);
 int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
-				int vport, u16 vlan, u8 qos);
+				u16 vport, u16 vlan, u8 qos);
 int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
-				    int vport, bool spoofchk);
+				    u16 vport, bool spoofchk);
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
-				 int vport_num, bool setting);
-int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, int vport,
+				 u16 vport_num, bool setting);
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
 				u32 max_rate, u32 min_rate);
+int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting);
+int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting);
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
-				  int vport, struct ifla_vf_info *ivi);
+				  u16 vport, struct ifla_vf_info *ivi);
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
-				 int vport,
+				 u16 vport,
 				 struct ifla_vf_stats *vf_stats);
 void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule);
 
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+					  void *in, int inlen);
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+					 void *out, int outlen);
+
 struct mlx5_flow_spec;
 struct mlx5_esw_flow_attr;
+struct mlx5_termtbl_handle;
+
+bool
+mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
+			      struct mlx5_flow_act *flow_act,
+			      struct mlx5_flow_spec *spec);
+
+struct mlx5_flow_handle *
+mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw,
+			      struct mlx5_flow_table *ft,
+			      struct mlx5_flow_spec *spec,
+			      struct mlx5_esw_flow_attr *attr,
+			      struct mlx5_flow_act *flow_act,
+			      struct mlx5_flow_destination *dest,
+			      int num_dest);
+
+void
+mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw,
+			 struct mlx5_termtbl_handle *tt);
 
 struct mlx5_flow_handle *
 mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
@@ -267,7 +332,7 @@ u32
 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw);
 
 struct mlx5_flow_handle *
-mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport,
+mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport,
 				  struct mlx5_flow_destination *dest);
 
 enum {
@@ -309,6 +374,7 @@ struct mlx5_esw_flow_attr {
 		struct mlx5_eswitch_rep *rep;
 		struct mlx5_core_dev *mdev;
 		u32 encap_id;
+		struct mlx5_termtbl_handle *termtbl;
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
 	u32	mod_hdr_id;
 	u8	match_level;
@@ -326,10 +392,12 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode);
 int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 					 struct netlink_ext_ack *extack);
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode);
-int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode);
-int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap,
+int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, u8 *mode);
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
+					enum devlink_eswitch_encap_mode encap,
 					struct netlink_ext_ack *extack);
-int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap);
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
+					enum devlink_eswitch_encap_mode *encap);
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type);
 
 int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
@@ -337,7 +405,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 				 struct mlx5_esw_flow_attr *attr);
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
-				  int vport, u16 vlan, u8 qos, u8 set_flags);
+				  u16 vport, u16 vlan, u8 qos, u8 set_flags);
 
 static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
 						       u8 vlan_depth)
@@ -354,24 +422,172 @@ static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev
 
 bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0,
 			 struct mlx5_core_dev *dev1);
+bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
+			       struct mlx5_core_dev *dev1);
+
+const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev);
 
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
 
-#define esw_info(dev, format, ...)				\
-	pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+#define esw_info(__dev, format, ...)			\
+	dev_info((__dev)->device, "E-Switch: " format, ##__VA_ARGS__)
 
-#define esw_warn(dev, format, ...)				\
-	pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+#define esw_warn(__dev, format, ...)			\
+	dev_warn((__dev)->device, "E-Switch: " format, ##__VA_ARGS__)
 
 #define esw_debug(dev, format, ...)				\
 	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
+
+/* The returned number is valid only when the dev is eswitch manager. */
+static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
+{
+	return mlx5_core_is_ecpf_esw_manager(dev) ?
+		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
+}
+
+static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev)
+{
+	return mlx5_core_is_ecpf_esw_manager(dev) ?
+		MLX5_VPORT_PF : MLX5_VPORT_FIRST_VF;
+}
+
+static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev)
+{
+	/* Ideally device should have the functions changed supported
+	 * capability regardless of it being ECPF or PF wherever such
+	 * event should be processed such as on eswitch manager device.
+	 * However, some ECPF based device might not have this capability
+	 * set. Hence OR for ECPF check to cover such device.
+	 */
+	return MLX5_CAP_ESW(dev, esw_functions_changed) ||
+	       mlx5_core_is_ecpf_esw_manager(dev);
+}
+
+static inline int mlx5_eswitch_uplink_idx(struct mlx5_eswitch *esw)
+{
+	/* Uplink always locate at the last element of the array.*/
+	return esw->total_vports - 1;
+}
+
+static inline int mlx5_eswitch_ecpf_idx(struct mlx5_eswitch *esw)
+{
+	return esw->total_vports - 2;
+}
+
+static inline int mlx5_eswitch_vport_num_to_index(struct mlx5_eswitch *esw,
+						  u16 vport_num)
+{
+	if (vport_num == MLX5_VPORT_ECPF) {
+		if (!mlx5_ecpf_vport_exists(esw->dev))
+			esw_warn(esw->dev, "ECPF vport doesn't exist!\n");
+		return mlx5_eswitch_ecpf_idx(esw);
+	}
+
+	if (vport_num == MLX5_VPORT_UPLINK)
+		return mlx5_eswitch_uplink_idx(esw);
+
+	return vport_num;
+}
+
+static inline u16 mlx5_eswitch_index_to_vport_num(struct mlx5_eswitch *esw,
+						  int index)
+{
+	if (index == mlx5_eswitch_ecpf_idx(esw) &&
+	    mlx5_ecpf_vport_exists(esw->dev))
+		return MLX5_VPORT_ECPF;
+
+	if (index == mlx5_eswitch_uplink_idx(esw))
+		return MLX5_VPORT_UPLINK;
+
+	return index;
+}
+
+/* TODO: This mlx5e_tc function shouldn't be called by eswitch */
+void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
+
+/* The vport getter/iterator are only valid after esw->total_vports
+ * and vport->vport are initialized in mlx5_eswitch_init.
+ */
+#define mlx5_esw_for_all_vports(esw, i, vport)		\
+	for ((i) = MLX5_VPORT_PF;			\
+	     (vport) = &(esw)->vports[i],		\
+	     (i) < (esw)->total_vports; (i)++)
+
+#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)	\
+	for ((i) = MLX5_VPORT_FIRST_VF;			\
+	     (vport) = &(esw)->vports[(i)],		\
+	     (i) <= (nvfs); (i)++)
+
+#define mlx5_esw_for_each_vf_vport_reverse(esw, i, vport, nvfs)	\
+	for ((i) = (nvfs);					\
+	     (vport) = &(esw)->vports[(i)],			\
+	     (i) >= MLX5_VPORT_FIRST_VF; (i)--)
+
+/* The rep getter/iterator are only valid after esw->total_vports
+ * and vport->vport are initialized in mlx5_eswitch_init.
+ */
+#define mlx5_esw_for_all_reps(esw, i, rep)			\
+	for ((i) = MLX5_VPORT_PF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) < (esw)->total_vports; (i)++)
+
+#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs)		\
+	for ((i) = MLX5_VPORT_FIRST_VF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) <= (nvfs); (i)++)
+
+#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs)	\
+	for ((i) = (nvfs);					\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) >= MLX5_VPORT_FIRST_VF; (i)--)
+
+#define mlx5_esw_for_each_vf_vport_num(esw, vport, nvfs)	\
+	for ((vport) = MLX5_VPORT_FIRST_VF; (vport) <= (nvfs); (vport)++)
+
+#define mlx5_esw_for_each_vf_vport_num_reverse(esw, vport, nvfs)	\
+	for ((vport) = (nvfs); (vport) >= MLX5_VPORT_FIRST_VF; (vport)--)
+
+/* Includes host PF (vport 0) if it's not esw manager. */
+#define mlx5_esw_for_each_host_func_rep(esw, i, rep, nvfs)	\
+	for ((i) = (esw)->first_host_vport;			\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) <= (nvfs); (i)++)
+
+#define mlx5_esw_for_each_host_func_rep_reverse(esw, i, rep, nvfs)	\
+	for ((i) = (nvfs);						\
+	     (rep) = &(esw)->offloads.vport_reps[i],			\
+	     (i) >= (esw)->first_host_vport; (i)--)
+
+#define mlx5_esw_for_each_host_func_vport(esw, vport, nvfs)	\
+	for ((vport) = (esw)->first_host_vport;			\
+	     (vport) <= (nvfs); (vport)++)
+
+#define mlx5_esw_for_each_host_func_vport_reverse(esw, vport, nvfs)	\
+	for ((vport) = (nvfs);						\
+	     (vport) >= (esw)->first_host_vport; (vport)--)
+
+struct mlx5_vport *__must_check
+mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num);
+
+bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num);
+
+void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs);
+int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
-static inline int  mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
-static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
+static inline int  mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) { return 0; }
+static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {}
 static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
+static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
+static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs) {}
 
 #define FDB_MAX_CHAIN 1
 #define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d4e6fe5b9300..957d9b09dc3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -37,18 +37,31 @@
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
 #include "eswitch.h"
+#include "rdma.h"
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
+#include "lib/eq.h"
 
-enum {
-	FDB_FAST_PATH = 0,
-	FDB_SLOW_PATH
-};
+/* There are two match-all miss flows, one for unicast dst mac and
+ * one for multicast.
+ */
+#define MLX5_ESW_MISS_FLOWS (2)
 
 #define fdb_prio_table(esw, chain, prio, level) \
 	(esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)]
 
+#define UPLINK_REP_INDEX 0
+
+static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
+						     u16 vport_num)
+{
+	int idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+	WARN_ON(idx > esw->total_vports - 1);
+	return &esw->offloads.vport_reps[idx];
+}
+
 static struct mlx5_flow_table *
 esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
 static void
@@ -75,6 +88,53 @@ u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw)
 	return 1;
 }
 
+static void
+mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
+				  struct mlx5_flow_spec *spec,
+				  struct mlx5_esw_flow_attr *attr)
+{
+	void *misc2;
+	void *misc;
+
+	/* Use metadata matching because vport is not represented by single
+	 * VHCA in dual-port RoCE mode, and matching on source vport may fail.
+	 */
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+		MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(attr->in_mdev->priv.eswitch,
+								   attr->in_rep->vport));
+
+		misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc2, metadata_reg_c_0);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+		if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc)))
+			spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+		MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
+
+		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+			MLX5_SET(fte_match_set_misc, misc,
+				 source_eswitch_owner_vhca_id,
+				 MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+			MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+					 source_eswitch_owner_vhca_id);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+	}
+
+	if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) &&
+	    attr->in_rep->vport == MLX5_VPORT_UPLINK)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+}
+
 struct mlx5_flow_handle *
 mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_spec *spec,
@@ -86,9 +146,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_table *fdb;
 	int j, i = 0;
-	void *misc;
 
-	if (esw->mode != SRIOV_OFFLOADS)
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	flow_act.action = attr->action;
@@ -146,21 +205,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		i++;
 	}
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-	MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET(fte_match_set_misc, misc,
-			 source_eswitch_owner_vhca_id,
-			 MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+	mlx5_eswitch_set_rule_source_port(esw, spec, attr);
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
-				 source_eswitch_owner_vhca_id);
-
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
 		if (attr->tunnel_match_level != MLX5_MATCH_NONE)
 			spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
@@ -179,7 +225,11 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		goto err_esw_get;
 	}
 
-	rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
+	if (mlx5_eswitch_termtbl_required(esw, &flow_act, spec))
+		rule = mlx5_eswitch_add_termtbl_rule(esw, fdb, spec, attr,
+						     &flow_act, dest, i);
+	else
+		rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
 	if (IS_ERR(rule))
 		goto err_add_rule;
 	else
@@ -206,7 +256,6 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	struct mlx5_flow_table *fast_fdb;
 	struct mlx5_flow_table *fwd_fdb;
 	struct mlx5_flow_handle *rule;
-	void *misc;
 	int i;
 
 	fast_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 0);
@@ -238,25 +287,11 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	dest[i].ft = fwd_fdb,
 	i++;
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-	MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET(fte_match_set_misc, misc,
-			 source_eswitch_owner_vhca_id,
-			 MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+	mlx5_eswitch_set_rule_source_port(esw, spec, attr);
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
-				 source_eswitch_owner_vhca_id);
-
-	if (attr->match_level == MLX5_MATCH_NONE)
-		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
-	else
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
-					      MLX5_MATCH_MISC_PARAMETERS;
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+	if (attr->match_level != MLX5_MATCH_NONE)
+		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
 
 	rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);
 
@@ -281,8 +316,16 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 			bool fwd_rule)
 {
 	bool split = (attr->split_count > 0);
+	int i;
 
 	mlx5_del_flow_rules(rule);
+
+	/* unref the term table */
+	for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
+		if (attr->dests[i].termtbl)
+			mlx5_eswitch_termtbl_put(esw, attr->dests[i].termtbl);
+	}
+
 	esw->offloads.num_flows--;
 
 	if (fwd_rule)  {
@@ -314,12 +357,11 @@ mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
 static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vf_vport, err = 0;
+	int i, err = 0;
 
 	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
-	for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
-		rep = &esw->offloads.vport_reps[vf_vport];
-		if (!rep->rep_if[REP_ETH].valid)
+	mlx5_esw_for_each_host_func_rep(esw, i, rep, esw->esw_funcs.num_vfs) {
+		if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
 			continue;
 
 		err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
@@ -360,15 +402,15 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 	in_rep  = attr->in_rep;
 	out_rep = attr->dests[0].rep;
 
-	if (push && in_rep->vport == FDB_UPLINK_VPORT)
+	if (push && in_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
-	if (pop && out_rep->vport == FDB_UPLINK_VPORT)
+	if (pop && out_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
 	/* vport has vlan push configured, can't offload VF --> wire rules w.o it */
 	if (!push && !pop && fwd)
-		if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT)
+		if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK)
 			goto out_notsupp;
 
 	/* protects against (1) setting rules with different vlans to push and
@@ -410,7 +452,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) {
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
 			vport->vlan_refcount++;
 			attr->vlan_handled = true;
 		}
@@ -470,7 +512,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT)
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
 			vport->vlan_refcount--;
 
 		return 0;
@@ -501,7 +543,8 @@ out:
 }
 
 struct mlx5_flow_handle *
-mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn)
+mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, u16 vport,
+				    u32 sqn)
 {
 	struct mlx5_flow_act flow_act = {0};
 	struct mlx5_flow_destination dest = {};
@@ -517,7 +560,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
 	MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
-	MLX5_SET(fte_match_set_misc, misc, source_port, 0x0); /* source vport is 0 */
+	/* source vport is the esw manager */
+	MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport);
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
 	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
@@ -543,30 +587,114 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
 	mlx5_del_flow_rules(rule);
 }
 
-static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
+static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+	u8 fdb_to_vport_reg_c_id;
+	int err;
+
+	err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+						   out, sizeof(out));
+	if (err)
+		return err;
+
+	fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+					 esw_vport_context.fdb_to_vport_reg_c_id);
+
+	fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0;
+	MLX5_SET(modify_esw_vport_context_in, in,
+		 esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+	MLX5_SET(modify_esw_vport_context_in, in,
+		 field_select.fdb_to_vport_reg_c_id, 1);
+
+	return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
+						     in, sizeof(in));
+}
+
+static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+	u8 fdb_to_vport_reg_c_id;
+	int err;
+
+	err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+						   out, sizeof(out));
+	if (err)
+		return err;
+
+	fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+					 esw_vport_context.fdb_to_vport_reg_c_id);
+
+	fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0;
+
+	MLX5_SET(modify_esw_vport_context_in, in,
+		 esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+	MLX5_SET(modify_esw_vport_context_in, in,
+		 field_select.fdb_to_vport_reg_c_id, 1);
+
+	return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
+						     in, sizeof(in));
+}
+
+static void peer_miss_rules_setup(struct mlx5_eswitch *esw,
+				  struct mlx5_core_dev *peer_dev,
 				  struct mlx5_flow_spec *spec,
 				  struct mlx5_flow_destination *dest)
 {
-	void *misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-				  misc_parameters);
+	void *misc;
 
-	MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
-		 MLX5_CAP_GEN(peer_dev, vhca_id));
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters_2);
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
 
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-			    misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc,
-			 source_eswitch_owner_vhca_id);
+		MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(peer_dev, vhca_id));
+
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+				 source_eswitch_owner_vhca_id);
+	}
 
 	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest->vport.num = 0;
+	dest->vport.num = peer_dev->priv.eswitch->manager_vport;
 	dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
 	dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 }
 
+static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw,
+					       struct mlx5_eswitch *peer_esw,
+					       struct mlx5_flow_spec *spec,
+					       u16 vport)
+{
+	void *misc;
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters_2);
+		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(peer_esw,
+								   vport));
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
+		MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+	}
+}
+
 static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 				       struct mlx5_core_dev *peer_dev)
 {
@@ -584,7 +712,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	if (!spec)
 		return -ENOMEM;
 
-	peer_miss_rules_setup(peer_dev, spec, &dest);
+	peer_miss_rules_setup(esw, peer_dev, spec, &dest);
 
 	flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
 	if (!flows) {
@@ -596,14 +724,40 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 			    misc_parameters);
 
-	for (i = 1; i < nvports; i++) {
-		MLX5_SET(fte_match_set_misc, misc, source_port, i);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
+						   spec, MLX5_VPORT_PF);
+
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_pf_flow_err;
+		}
+		flows[MLX5_VPORT_PF] = flow;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_ecpf_flow_err;
+		}
+		flows[mlx5_eswitch_ecpf_idx(esw)] = flow;
+	}
+
+	mlx5_esw_for_each_vf_vport_num(esw, i, mlx5_core_max_vfs(esw->dev)) {
+		esw_set_peer_miss_rule_source_port(esw,
+						   peer_dev->priv.eswitch,
+						   spec, i);
+
 		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
 			err = PTR_ERR(flow);
-			esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
-			goto add_flow_err;
+			goto add_vf_flow_err;
 		}
 		flows[i] = flow;
 	}
@@ -613,9 +767,18 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	kvfree(spec);
 	return 0;
 
-add_flow_err:
-	for (i--; i > 0; i--)
+add_vf_flow_err:
+	nvports = --i;
+	mlx5_esw_for_each_vf_vport_num_reverse(esw, i, nvports)
 		mlx5_del_flow_rules(flows[i]);
+
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+add_ecpf_flow_err:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+add_pf_flow_err:
+	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
 	kvfree(flows);
 alloc_flows_err:
 	kvfree(spec);
@@ -629,9 +792,16 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
 
 	flows = esw->fdb_table.offloads.peer_miss_rules;
 
-	for (i = 1; i < esw->total_vports; i++)
+	mlx5_esw_for_each_vf_vport_num_reverse(esw, i,
+					       mlx5_core_max_vfs(esw->dev))
 		mlx5_del_flow_rules(flows[i]);
 
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+
 	kvfree(flows);
 }
 
@@ -661,7 +831,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 	dmac_c[0] = 0x01;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest.vport.num = 0;
+	dest.vport.num = esw->manager_vport;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
 	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
@@ -866,6 +1036,30 @@ static void esw_destroy_offloads_fast_fdb_tables(struct mlx5_eswitch *esw)
 #define MAX_PF_SQ 256
 #define MAX_SQ_NVPORTS 32
 
+static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
+					   u32 *flow_group_in)
+{
+	void *match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+					    flow_group_in,
+					    match_criteria);
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		MLX5_SET(create_flow_group_in, flow_group_in,
+			 match_criteria_enable,
+			 MLX5_MATCH_MISC_PARAMETERS_2);
+
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+				 misc_parameters_2.metadata_reg_c_0);
+	} else {
+		MLX5_SET(create_flow_group_in, flow_group_in,
+			 match_criteria_enable,
+			 MLX5_MATCH_MISC_PARAMETERS);
+
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+				 misc_parameters.source_port);
+	}
+}
+
 static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -905,8 +1099,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		esw->fdb_table.offloads.fdb_left[i] =
 			ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
 
-	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2 +
-		esw->total_vports;
+	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
+		MLX5_ESW_MISS_FLOWS + esw->total_vports;
 
 	/* create the slow path fdb with encap set, so further table instances
 	 * can be created at run time while VFs are probed if the FW allows that.
@@ -963,19 +1157,21 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 
 	/* create peer esw miss group */
 	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
-		 MLX5_MATCH_MISC_PARAMETERS);
 
-	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
-				      match_criteria);
+	esw_set_flow_group_source_port(esw, flow_group_in);
+
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+					      flow_group_in,
+					      match_criteria);
 
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-			 misc_parameters.source_port);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-			 misc_parameters.source_eswitch_owner_vhca_id);
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+				 misc_parameters.source_eswitch_owner_vhca_id);
+
+		MLX5_SET(create_flow_group_in, flow_group_in,
+			 source_eswitch_owner_vhca_id_valid, 1);
+	}
 
-	MLX5_SET(create_flow_group_in, flow_group_in,
-		 source_eswitch_owner_vhca_id_valid, 1);
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
 		 ix + esw->total_vports - 1);
@@ -1000,7 +1196,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	dmac[0] = 0x01;
 
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ix + MLX5_ESW_MISS_FLOWS);
 
 	g = mlx5_create_flow_group(fdb, flow_group_in);
 	if (IS_ERR(g)) {
@@ -1049,7 +1246,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	esw_destroy_offloads_fast_fdb_tables(esw);
 }
 
-static int esw_create_offloads_table(struct mlx5_eswitch *esw)
+static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
@@ -1063,7 +1260,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 		return -EOPNOTSUPP;
 	}
 
-	ft_attr.max_fte = dev->priv.sriov.num_vfs + 2;
+	ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS;
 
 	ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft_offloads)) {
@@ -1083,28 +1280,22 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
 	mlx5_destroy_flow_table(offloads->ft_offloads);
 }
 
-static int esw_create_vport_rx_group(struct mlx5_eswitch *esw)
+static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *g;
-	struct mlx5_priv *priv = &esw->dev->priv;
 	u32 *flow_group_in;
-	void *match_criteria, *misc;
 	int err = 0;
-	int nvports = priv->sriov.num_vfs + 2;
 
+	nvports = nvports + MLX5_ESW_MISS_FLOWS;
 	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	if (!flow_group_in)
 		return -ENOMEM;
 
 	/* create vport rx group */
 	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
-		 MLX5_MATCH_MISC_PARAMETERS);
 
-	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
-	misc = MLX5_ADDR_OF(fte_match_param, match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+	esw_set_flow_group_source_port(esw, flow_group_in);
 
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, nvports - 1);
@@ -1129,7 +1320,7 @@ static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw)
 }
 
 struct mlx5_flow_handle *
-mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport,
+mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport,
 				  struct mlx5_flow_destination *dest)
 {
 	struct mlx5_flow_act flow_act = {0};
@@ -1143,13 +1334,24 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport,
 		goto out;
 	}
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-	MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(esw, vport));
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
 
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+		MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
@@ -1167,20 +1369,22 @@ out:
 static int esw_offloads_start(struct mlx5_eswitch *esw,
 			      struct netlink_ext_ack *extack)
 {
-	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
+	int err, err1;
 
-	if (esw->mode != SRIOV_LEGACY) {
+	if (esw->mode != MLX5_ESWITCH_LEGACY &&
+	    !mlx5_core_is_ecpf_esw_manager(esw->dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't set offloads mode, SRIOV legacy not enabled");
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable_sriov(esw);
-	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+	mlx5_eswitch_disable(esw);
+	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
+	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Failed setting eswitch to offloads");
-		err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+		err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 		if (err1) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Failed setting eswitch back to legacy");
@@ -1188,7 +1392,6 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 	}
 	if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
 		if (mlx5_eswitch_inline_mode_get(esw,
-						 num_vfs,
 						 &esw->offloads.inline_mode)) {
 			esw->offloads.inline_mode = MLX5_INLINE_MODE_L2;
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1205,88 +1408,212 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
 
 int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 {
-	int total_vfs = MLX5_TOTAL_VPORTS(esw->dev);
+	int total_vports = esw->total_vports;
 	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_esw_offload *offloads;
 	struct mlx5_eswitch_rep *rep;
-	u8 hw_id[ETH_ALEN];
-	int vport;
+	u8 hw_id[ETH_ALEN], rep_type;
+	int vport_index;
 
-	esw->offloads.vport_reps = kcalloc(total_vfs,
+	esw->offloads.vport_reps = kcalloc(total_vports,
 					   sizeof(struct mlx5_eswitch_rep),
 					   GFP_KERNEL);
 	if (!esw->offloads.vport_reps)
 		return -ENOMEM;
 
-	offloads = &esw->offloads;
-	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
-
-	for (vport = 0; vport < total_vfs; vport++) {
-		rep = &offloads->vport_reps[vport];
+	mlx5_query_mac_address(dev, hw_id);
 
-		rep->vport = vport;
+	mlx5_esw_for_all_reps(esw, vport_index, rep) {
+		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index);
+		rep->vport_index = vport_index;
 		ether_addr_copy(rep->hw_id, hw_id);
-	}
 
-	offloads->vport_reps[0].vport = FDB_UPLINK_VPORT;
+		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
+			atomic_set(&rep->rep_data[rep_type].state,
+				   REP_UNREGISTERED);
+	}
 
 	return 0;
 }
 
-static void esw_offloads_unload_reps_type(struct mlx5_eswitch *esw, int nvports,
-					  u8 rep_type)
+static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
+			   REP_LOADED, REP_REGISTERED) == REP_LOADED)
+		esw->offloads.rep_ops[rep_type]->unload(rep);
+}
+
+static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 
-	for (vport = nvports - 1; vport >= 0; vport--) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
 
-		rep->rep_if[rep_type].unload(rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
 	}
+
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+}
+
+static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				   u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int i;
+
+	mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports)
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+}
+
+static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = NUM_REP_TYPES;
+
+	while (rep_type-- > 0)
+		__unload_reps_vf_vport(esw, nvports, rep_type);
+}
+
+static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
+{
+	__unload_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);
+
+	/* Special vports must be the last to unload. */
+	__unload_reps_special_vport(esw, rep_type);
 }
 
-static void esw_offloads_unload_reps(struct mlx5_eswitch *esw, int nvports)
+static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw)
 {
 	u8 rep_type = NUM_REP_TYPES;
 
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_all_vport(esw, rep_type);
 }
 
-static int esw_offloads_load_reps_type(struct mlx5_eswitch *esw, int nvports,
-				       u8 rep_type)
+static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
+				   struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	int err = 0;
+
+	if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
+			   REP_REGISTERED, REP_LOADED) == REP_REGISTERED) {
+		err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
+		if (err)
+			atomic_set(&rep->rep_data[rep_type].state,
+				   REP_REGISTERED);
+	}
+
+	return err;
+}
+
+static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 	int err;
 
-	for (vport = 0; vport < nvports; vport++) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	err = __esw_offloads_load_rep(esw, rep, rep_type);
+	if (err)
+		return err;
 
-		err = rep->rep_if[rep_type].load(esw->dev, rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
 		if (err)
-			goto err_reps;
+			goto err_pf;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_ecpf;
+	}
+
+	return 0;
+
+err_ecpf:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
+
+err_pf:
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+	return err;
+}
+
+static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int err, i;
+
+	mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) {
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_vf;
 	}
 
 	return 0;
 
+err_vf:
+	__unload_reps_vf_vport(esw, --i, rep_type);
+	return err;
+}
+
+static int __load_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
+{
+	int err;
+
+	/* Special vports must be loaded first, uplink rep creates mdev resource. */
+	err = __load_reps_special_vport(esw, rep_type);
+	if (err)
+		return err;
+
+	err = __load_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);
+	if (err)
+		goto err_vfs;
+
+	return 0;
+
+err_vfs:
+	__unload_reps_special_vport(esw, rep_type);
+	return err;
+}
+
+static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = 0;
+	int err;
+
+	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
+		err = __load_reps_vf_vport(esw, nvports, rep_type);
+		if (err)
+			goto err_reps;
+	}
+
+	return err;
+
 err_reps:
-	esw_offloads_unload_reps_type(esw, vport, rep_type);
+	while (rep_type-- > 0)
+		__unload_reps_vf_vport(esw, nvports, rep_type);
 	return err;
 }
 
-static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
+static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw)
 {
 	u8 rep_type = 0;
 	int err;
 
 	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
-		err = esw_offloads_load_reps_type(esw, nvports, rep_type);
+		err = __load_reps_all_vport(esw, rep_type);
 		if (err)
 			goto err_reps;
 	}
@@ -1295,7 +1622,7 @@ static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
 
 err_reps:
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_all_vport(esw, rep_type);
 	return err;
 }
 
@@ -1314,8 +1641,6 @@ static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
 	return 0;
 }
 
-void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
-
 static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
 {
 	mlx5e_tc_clean_fdb_peer_flows(esw);
@@ -1333,6 +1658,10 @@ static int mlx5_esw_offloads_devcom_event(int event,
 
 	switch (event) {
 	case ESW_OFFLOADS_DEVCOM_PAIR:
+		if (mlx5_eswitch_vport_match_metadata_enabled(esw) !=
+		    mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
+			break;
+
 		err = mlx5_esw_offloads_pair(esw, peer_esw);
 		if (err)
 			goto err_out;
@@ -1398,53 +1727,455 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 }
 
-int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
+static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
+					     struct mlx5_vport *vport)
 {
+	struct mlx5_flow_act flow_act = {0};
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	/* For prio tag mode, there is only 1 FTEs:
+	 * 1) Untagged packets - push prio tag VLAN and modify metadata if
+	 * required, allow
+	 * Unmatched traffic is allowed by default
+	 */
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		err = -ENOMEM;
+		goto out_no_mem;
+	}
+
+	/* Untagged packets - push prio tag VLAN, allow */
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.cvlan_tag, 0);
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
+			  MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_act.vlan[0].ethtype = ETH_P_8021Q;
+	flow_act.vlan[0].vid = 0;
+	flow_act.vlan[0].prio = 0;
+
+	if (vport->ingress.modify_metadata_rule) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+		flow_act.modify_id = vport->ingress.modify_metadata_id;
+	}
+
+	vport->ingress.allow_rule =
+		mlx5_add_flow_rules(vport->ingress.acl, spec,
+				    &flow_act, NULL, 0);
+	if (IS_ERR(vport->ingress.allow_rule)) {
+		err = PTR_ERR(vport->ingress.allow_rule);
+		esw_warn(esw->dev,
+			 "vport[%d] configure ingress untagged allow rule, err(%d)\n",
+			 vport->vport, err);
+		vport->ingress.allow_rule = NULL;
+		goto out;
+	}
+
+out:
+	kvfree(spec);
+out_no_mem:
+	if (err)
+		esw_vport_cleanup_ingress_rules(esw, vport);
+	return err;
+}
+
+static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+						     struct mlx5_vport *vport)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)] = {};
+	static const struct mlx5_flow_spec spec = {};
+	struct mlx5_flow_act flow_act = {};
+	int err = 0;
+
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+	MLX5_SET(set_action_in, action, data,
+		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));
+
+	err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+				       1, action, &vport->ingress.modify_metadata_id);
+	if (err) {
+		esw_warn(esw->dev,
+			 "failed to alloc modify header for vport %d ingress acl (%d)\n",
+			 vport->vport, err);
+		return err;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_act.modify_id = vport->ingress.modify_metadata_id;
+	vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl,
+								  &spec, &flow_act, NULL, 0);
+	if (IS_ERR(vport->ingress.modify_metadata_rule)) {
+		err = PTR_ERR(vport->ingress.modify_metadata_rule);
+		esw_warn(esw->dev,
+			 "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n",
+			 vport->vport, err);
+		vport->ingress.modify_metadata_rule = NULL;
+		goto out;
+	}
+
+out:
+	if (err)
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+	return err;
+}
+
+void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+					       struct mlx5_vport *vport)
+{
+	if (vport->ingress.modify_metadata_rule) {
+		mlx5_del_flow_rules(vport->ingress.modify_metadata_rule);
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+
+		vport->ingress.modify_metadata_rule = NULL;
+	}
+}
+
+static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
+					    struct mlx5_vport *vport)
+{
+	struct mlx5_flow_act flow_act = {0};
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		return 0;
+
+	/* For prio tag mode, there is only 1 FTEs:
+	 * 1) prio tag packets - pop the prio tag VLAN, allow
+	 * Unmatched traffic is allowed by default
+	 */
+
+	esw_vport_cleanup_egress_rules(esw, vport);
+
+	err = esw_vport_enable_egress_acl(esw, vport);
+	if (err) {
+		mlx5_core_warn(esw->dev,
+			       "failed to enable egress acl (%d) on vport[%d]\n",
+			       err, vport->vport);
+		return err;
+	}
+
+	esw_debug(esw->dev,
+		  "vport[%d] configure prio tag egress rules\n", vport->vport);
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		err = -ENOMEM;
+		goto out_no_mem;
+	}
+
+	/* prio tag vlan rule - pop it so VF receives untagged packets */
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, 0);
+
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
+			  MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	vport->egress.allowed_vlan =
+		mlx5_add_flow_rules(vport->egress.acl, spec,
+				    &flow_act, NULL, 0);
+	if (IS_ERR(vport->egress.allowed_vlan)) {
+		err = PTR_ERR(vport->egress.allowed_vlan);
+		esw_warn(esw->dev,
+			 "vport[%d] configure egress pop prio tag vlan rule failed, err(%d)\n",
+			 vport->vport, err);
+		vport->egress.allowed_vlan = NULL;
+		goto out;
+	}
+
+out:
+	kvfree(spec);
+out_no_mem:
+	if (err)
+		esw_vport_cleanup_egress_rules(esw, vport);
+	return err;
+}
+
+static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
+					   struct mlx5_vport *vport)
+{
+	int err;
+
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+	    !MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		return 0;
+
+	esw_vport_cleanup_ingress_rules(esw, vport);
+
+	err = esw_vport_enable_ingress_acl(esw, vport);
+	if (err) {
+		esw_warn(esw->dev,
+			 "failed to enable ingress acl (%d) on vport[%d]\n",
+			 err, vport->vport);
+		return err;
+	}
+
+	esw_debug(esw->dev,
+		  "vport[%d] configure ingress rules\n", vport->vport);
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		err = esw_vport_add_ingress_acl_modify_metadata(esw, vport);
+		if (err)
+			goto out;
+	}
+
+	if (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
+	    mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
+		err = esw_vport_ingress_prio_tag_config(esw, vport);
+		if (err)
+			goto out;
+	}
+
+out:
+	if (err)
+		esw_vport_disable_ingress_acl(esw, vport);
+	return err;
+}
+
+static bool
+esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
+{
+	if (!MLX5_CAP_ESW(esw->dev, esw_uplink_ingress_acl))
+		return false;
+
+	if (!(MLX5_CAP_ESW_FLOWTABLE(esw->dev, fdb_to_vport_reg_c_id) &
+	      MLX5_FDB_TO_VPORT_REG_C_0))
+		return false;
+
+	if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source))
+		return false;
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+	    mlx5_ecpf_vport_exists(esw->dev))
+		return false;
+
+	return true;
+}
+
+static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	int i, j;
 	int err;
 
+	if (esw_check_vport_match_metadata_supported(esw))
+		esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+
+	mlx5_esw_for_all_vports(esw, i, vport) {
+		err = esw_vport_ingress_common_config(esw, vport);
+		if (err)
+			goto err_ingress;
+
+		if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
+			err = esw_vport_egress_prio_tag_config(esw, vport);
+			if (err)
+				goto err_egress;
+		}
+	}
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+		esw_info(esw->dev, "Use metadata reg_c as source vport to match\n");
+
+	return 0;
+
+err_egress:
+	esw_vport_disable_ingress_acl(esw, vport);
+err_ingress:
+	for (j = MLX5_VPORT_PF; j < i; j++) {
+		vport = &esw->vports[j];
+		esw_vport_disable_egress_acl(esw, vport);
+		esw_vport_disable_ingress_acl(esw, vport);
+	}
+
+	return err;
+}
+
+static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	int i;
+
+	mlx5_esw_for_all_vports(esw, i, vport) {
+		esw_vport_disable_egress_acl(esw, vport);
+		esw_vport_disable_ingress_acl(esw, vport);
+	}
+
+	esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
+}
+
+static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
+{
+	int num_vfs = esw->esw_funcs.num_vfs;
+	int total_vports;
+	int err;
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		total_vports = esw->total_vports;
+	else
+		total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev);
+
+	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
 	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
 
-	err = esw_create_offloads_fdb_tables(esw, nvports);
+	err = esw_create_offloads_acl_tables(esw);
 	if (err)
 		return err;
 
-	err = esw_create_offloads_table(esw);
+	err = esw_create_offloads_fdb_tables(esw, total_vports);
 	if (err)
-		goto create_ft_err;
+		goto create_fdb_err;
 
-	err = esw_create_vport_rx_group(esw);
+	err = esw_create_offloads_table(esw, total_vports);
 	if (err)
-		goto create_fg_err;
+		goto create_ft_err;
 
-	err = esw_offloads_load_reps(esw, nvports);
+	err = esw_create_vport_rx_group(esw, total_vports);
 	if (err)
-		goto err_reps;
+		goto create_fg_err;
 
-	esw_offloads_devcom_init(esw);
 	return 0;
 
-err_reps:
-	esw_destroy_vport_rx_group(esw);
-
 create_fg_err:
 	esw_destroy_offloads_table(esw);
 
 create_ft_err:
 	esw_destroy_offloads_fdb_tables(esw);
 
+create_fdb_err:
+	esw_destroy_offloads_acl_tables(esw);
+
+	return err;
+}
+
+static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
+{
+	esw_destroy_vport_rx_group(esw);
+	esw_destroy_offloads_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
+	esw_destroy_offloads_acl_tables(esw);
+}
+
+static void
+esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
+{
+	bool host_pf_disabled;
+	u16 new_num_vfs;
+
+	new_num_vfs = MLX5_GET(query_esw_functions_out, out,
+			       host_params_context.host_num_of_vfs);
+	host_pf_disabled = MLX5_GET(query_esw_functions_out, out,
+				    host_params_context.host_pf_disabled);
+
+	if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
+		return;
+
+	/* Number of VFs can only change from "0 to x" or "x to 0". */
+	if (esw->esw_funcs.num_vfs > 0) {
+		esw_offloads_unload_vf_reps(esw, esw->esw_funcs.num_vfs);
+	} else {
+		int err;
+
+		err = esw_offloads_load_vf_reps(esw, new_num_vfs);
+		if (err)
+			return;
+	}
+	esw->esw_funcs.num_vfs = new_num_vfs;
+}
+
+static void esw_functions_changed_event_handler(struct work_struct *work)
+{
+	struct mlx5_host_work *host_work;
+	struct mlx5_eswitch *esw;
+	const u32 *out;
+
+	host_work = container_of(work, struct mlx5_host_work, work);
+	esw = host_work->esw;
+
+	out = mlx5_esw_query_functions(esw->dev);
+	if (IS_ERR(out))
+		goto out;
+
+	esw_vfs_changed_event_handler(esw, out);
+	kvfree(out);
+out:
+	kfree(host_work);
+}
+
+int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_esw_functions *esw_funcs;
+	struct mlx5_host_work *host_work;
+	struct mlx5_eswitch *esw;
+
+	host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC);
+	if (!host_work)
+		return NOTIFY_DONE;
+
+	esw_funcs = mlx5_nb_cof(nb, struct mlx5_esw_functions, nb);
+	esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs);
+
+	host_work->esw = esw;
+
+	INIT_WORK(&host_work->work, esw_functions_changed_event_handler);
+	queue_work(esw->work_queue, &host_work->work);
+
+	return NOTIFY_OK;
+}
+
+int esw_offloads_init(struct mlx5_eswitch *esw)
+{
+	int err;
+
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
+	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+	else
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+
+	err = esw_offloads_steering_init(esw);
+	if (err)
+		return err;
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		err = mlx5_eswitch_enable_passing_vport_metadata(esw);
+		if (err)
+			goto err_vport_metadata;
+	}
+
+	err = esw_offloads_load_all_reps(esw);
+	if (err)
+		goto err_reps;
+
+	esw_offloads_devcom_init(esw);
+	mutex_init(&esw->offloads.termtbl_mutex);
+
+	mlx5_rdma_enable_roce(esw->dev);
+
+	return 0;
+
+err_reps:
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+		mlx5_eswitch_disable_passing_vport_metadata(esw);
+err_vport_metadata:
+	esw_offloads_steering_cleanup(esw);
 	return err;
 }
 
 static int esw_offloads_stop(struct mlx5_eswitch *esw,
 			     struct netlink_ext_ack *extack)
 {
-	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
+	int err, err1;
 
-	mlx5_eswitch_disable_sriov(esw);
-	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+	mlx5_eswitch_disable(esw);
+	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
-		err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+		err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 		if (err1) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Failed setting eswitch back to offloads");
@@ -1454,23 +2185,25 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 	return err;
 }
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
+void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 {
+	mlx5_rdma_disable_roce(esw->dev);
 	esw_offloads_devcom_cleanup(esw);
-	esw_offloads_unload_reps(esw, nvports);
-	esw_destroy_vport_rx_group(esw);
-	esw_destroy_offloads_table(esw);
-	esw_destroy_offloads_fdb_tables(esw);
+	esw_offloads_unload_all_reps(esw);
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+		mlx5_eswitch_disable_passing_vport_metadata(esw);
+	esw_offloads_steering_cleanup(esw);
+	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
 {
 	switch (mode) {
 	case DEVLINK_ESWITCH_MODE_LEGACY:
-		*mlx5_mode = SRIOV_LEGACY;
+		*mlx5_mode = MLX5_ESWITCH_LEGACY;
 		break;
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
-		*mlx5_mode = SRIOV_OFFLOADS;
+		*mlx5_mode = MLX5_ESWITCH_OFFLOADS;
 		break;
 	default:
 		return -EINVAL;
@@ -1482,10 +2215,10 @@ static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
 static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
 {
 	switch (mlx5_mode) {
-	case SRIOV_LEGACY:
+	case MLX5_ESWITCH_LEGACY:
 		*mode = DEVLINK_ESWITCH_MODE_LEGACY;
 		break;
-	case SRIOV_OFFLOADS:
+	case MLX5_ESWITCH_OFFLOADS:
 		*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
 		break;
 	default:
@@ -1549,7 +2282,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if(!MLX5_ESWITCH_MANAGER(dev))
 		return -EPERM;
 
-	if (dev->priv.eswitch->mode == SRIOV_NONE)
+	if (dev->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+	    !mlx5_core_is_ecpf_esw_manager(dev))
 		return -EOPNOTSUPP;
 
 	return 0;
@@ -1599,7 +2333,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
-	int err, vport;
+	int err, vport, num_vport;
 	u8 mlx5_mode;
 
 	err = mlx5_devlink_eswitch_check(devlink);
@@ -1628,7 +2362,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	if (err)
 		goto out;
 
-	for (vport = 1; vport < esw->enabled_vports; vport++) {
+	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
 		err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode);
 		if (err) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1641,7 +2375,8 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	return 0;
 
 revert_inline_mode:
-	while (--vport > 0)
+	num_vport = --vport;
+	mlx5_esw_for_each_host_func_vport_reverse(esw, vport, num_vport)
 		mlx5_modify_nic_vport_min_inline(dev,
 						 vport,
 						 esw->offloads.inline_mode);
@@ -1662,7 +2397,7 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
-int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
+int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, u8 *mode)
 {
 	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
 	struct mlx5_core_dev *dev = esw->dev;
@@ -1671,7 +2406,7 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 	if (!MLX5_CAP_GEN(dev, vport_group_manager))
 		return -EOPNOTSUPP;
 
-	if (esw->mode == SRIOV_NONE)
+	if (esw->mode == MLX5_ESWITCH_NONE)
 		return -EOPNOTSUPP;
 
 	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
@@ -1686,9 +2421,10 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 	}
 
 query_vports:
-	for (vport = 1; vport <= nvfs; vport++) {
+	mlx5_query_nic_vport_min_inline(dev, esw->first_host_vport, &prev_mlx5_mode);
+	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
 		mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
-		if (vport > 1 && prev_mlx5_mode != mlx5_mode)
+		if (prev_mlx5_mode != mlx5_mode)
 			return -EINVAL;
 		prev_mlx5_mode = mlx5_mode;
 	}
@@ -1698,7 +2434,8 @@ out:
 	return 0;
 }
 
-int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap,
+int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
+					enum devlink_eswitch_encap_mode encap,
 					struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
@@ -1717,7 +2454,7 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap,
 	if (encap && encap != DEVLINK_ESWITCH_ENCAP_MODE_BASIC)
 		return -EOPNOTSUPP;
 
-	if (esw->mode == SRIOV_LEGACY) {
+	if (esw->mode == MLX5_ESWITCH_LEGACY) {
 		esw->offloads.encap = encap;
 		return 0;
 	}
@@ -1747,7 +2484,8 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap,
 	return err;
 }
 
-int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
+int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
+					enum devlink_eswitch_encap_mode *encap)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
@@ -1761,78 +2499,86 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
 	return 0;
 }
 
-void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
-				     int vport_index,
-				     struct mlx5_eswitch_rep_if *__rep_if,
-				     u8 rep_type)
+void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
+				      const struct mlx5_eswitch_rep_ops *ops,
+				      u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
-	struct mlx5_eswitch_rep_if *rep_if;
-
-	rep_if = &offloads->vport_reps[vport_index].rep_if[rep_type];
-
-	rep_if->load   = __rep_if->load;
-	rep_if->unload = __rep_if->unload;
-	rep_if->get_proto_dev = __rep_if->get_proto_dev;
-	rep_if->priv = __rep_if->priv;
+	struct mlx5_eswitch_rep_data *rep_data;
+	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep_if->valid = true;
+	esw->offloads.rep_ops[rep_type] = ops;
+	mlx5_esw_for_all_reps(esw, i, rep) {
+		rep_data = &rep->rep_data[rep_type];
+		atomic_set(&rep_data->state, REP_REGISTERED);
+	}
 }
-EXPORT_SYMBOL(mlx5_eswitch_register_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
 
-void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
-				       int vport_index, u8 rep_type)
+void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep = &offloads->vport_reps[vport_index];
-
-	if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled)
-		rep->rep_if[rep_type].unload(rep);
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
+		__unload_reps_all_vport(esw, rep_type);
 
-	rep->rep_if[rep_type].valid = false;
+	mlx5_esw_for_all_reps(esw, i, rep)
+		atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
 }
-EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
 
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
 {
-#define UPLINK_REP_INDEX 0
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	rep = &offloads->vport_reps[UPLINK_REP_INDEX];
-	return rep->rep_if[rep_type].priv;
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	return rep->rep_data[rep_type].priv;
 }
 
 void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
-				 int vport,
+				 u16 vport,
 				 u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	if (vport == FDB_UPLINK_VPORT)
-		vport = UPLINK_REP_INDEX;
+	rep = mlx5_eswitch_get_rep(esw, vport);
 
-	rep = &offloads->vport_reps[vport];
-
-	if (rep->rep_if[rep_type].valid &&
-	    rep->rep_if[rep_type].get_proto_dev)
-		return rep->rep_if[rep_type].get_proto_dev(rep);
+	if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED &&
+	    esw->offloads.rep_ops[rep_type]->get_proto_dev)
+		return esw->offloads.rep_ops[rep_type]->get_proto_dev(rep);
 	return NULL;
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev);
 
 void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	return mlx5_eswitch_get_proto_dev(esw, UPLINK_REP_INDEX, rep_type);
+	return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type);
 }
 EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev);
 
 struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
-						int vport)
+						u16 vport)
 {
-	return &esw->offloads.vport_reps[vport];
+	return mlx5_eswitch_get_rep(esw, vport);
 }
 EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
+
+bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return vport_num >= MLX5_VPORT_FIRST_VF &&
+	       vport_num <= esw->dev->priv.sriov.max_vfs;
+}
+
+bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw)
+{
+	return !!(esw->flags & MLX5_ESWITCH_VPORT_MATCH_METADATA);
+}
+EXPORT_SYMBOL(mlx5_eswitch_vport_match_metadata_enabled);
+
+u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+					      u16 vport_num)
+{
+	return ((MLX5_CAP_GEN(esw->dev, vhca_id) & 0xffff) << 16) | vport_num;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
new file mode 100644
index 000000000000..1d55a324a17e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include <linux/mlx5/fs.h>
+#include "eswitch.h"
+
+struct mlx5_termtbl_handle {
+	struct hlist_node termtbl_hlist;
+
+	struct mlx5_flow_table *termtbl;
+	struct mlx5_flow_act flow_act;
+	struct mlx5_flow_destination dest;
+
+	struct mlx5_flow_handle *rule;
+	int ref_count;
+};
+
+static u32
+mlx5_eswitch_termtbl_hash(struct mlx5_flow_act *flow_act,
+			  struct mlx5_flow_destination *dest)
+{
+	u32 hash;
+
+	hash = jhash_1word(flow_act->action, 0);
+	hash = jhash((const void *)&flow_act->vlan,
+		     sizeof(flow_act->vlan), hash);
+	hash = jhash((const void *)&dest->vport.num,
+		     sizeof(dest->vport.num), hash);
+	hash = jhash((const void *)&dest->vport.vhca_id,
+		     sizeof(dest->vport.num), hash);
+	return hash;
+}
+
+static int
+mlx5_eswitch_termtbl_cmp(struct mlx5_flow_act *flow_act1,
+			 struct mlx5_flow_destination *dest1,
+			 struct mlx5_flow_act *flow_act2,
+			 struct mlx5_flow_destination *dest2)
+{
+	return flow_act1->action != flow_act2->action ||
+	       dest1->vport.num != dest2->vport.num ||
+	       dest1->vport.vhca_id != dest2->vport.vhca_id ||
+	       memcmp(&flow_act1->vlan, &flow_act2->vlan,
+		      sizeof(flow_act1->vlan));
+}
+
+static int
+mlx5_eswitch_termtbl_create(struct mlx5_core_dev *dev,
+			    struct mlx5_termtbl_handle *tt,
+			    struct mlx5_flow_act *flow_act)
+{
+	static const struct mlx5_flow_spec spec = {};
+	struct mlx5_flow_namespace *root_ns;
+	int prio, flags;
+	int err;
+
+	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* As this is the terminating action then the termination table is the
+	 * same prio as the slow path
+	 */
+	prio = FDB_SLOW_PATH;
+	flags = MLX5_FLOW_TABLE_TERMINATION;
+	tt->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, prio, 1, 1,
+							  0, flags);
+	if (IS_ERR(tt->termtbl)) {
+		esw_warn(dev, "Failed to create termination table\n");
+		return -EOPNOTSUPP;
+	}
+
+	tt->rule = mlx5_add_flow_rules(tt->termtbl, &spec, flow_act,
+				       &tt->dest, 1);
+
+	if (IS_ERR(tt->rule)) {
+		esw_warn(dev, "Failed to create termination table rule\n");
+		goto add_flow_err;
+	}
+	return 0;
+
+add_flow_err:
+	err = mlx5_destroy_flow_table(tt->termtbl);
+	if (err)
+		esw_warn(dev, "Failed to destroy termination table\n");
+
+	return -EOPNOTSUPP;
+}
+
+static struct mlx5_termtbl_handle *
+mlx5_eswitch_termtbl_get_create(struct mlx5_eswitch *esw,
+				struct mlx5_flow_act *flow_act,
+				struct mlx5_flow_destination *dest)
+{
+	struct mlx5_termtbl_handle *tt;
+	bool found = false;
+	u32 hash_key;
+	int err;
+
+	mutex_lock(&esw->offloads.termtbl_mutex);
+
+	hash_key = mlx5_eswitch_termtbl_hash(flow_act, dest);
+	hash_for_each_possible(esw->offloads.termtbl_tbl, tt,
+			       termtbl_hlist, hash_key) {
+		if (!mlx5_eswitch_termtbl_cmp(&tt->flow_act, &tt->dest,
+					      flow_act, dest)) {
+			found = true;
+			break;
+		}
+	}
+	if (found)
+		goto tt_add_ref;
+
+	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
+	if (!tt) {
+		err = -ENOMEM;
+		goto tt_create_err;
+	}
+
+	tt->dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	tt->dest.vport.num = dest->vport.num;
+	tt->dest.vport.vhca_id = dest->vport.vhca_id;
+	memcpy(&tt->flow_act, flow_act, sizeof(*flow_act));
+
+	err = mlx5_eswitch_termtbl_create(esw->dev, tt, flow_act);
+	if (err) {
+		esw_warn(esw->dev, "Failed to create termination table\n");
+		goto tt_create_err;
+	}
+	hash_add(esw->offloads.termtbl_tbl, &tt->termtbl_hlist, hash_key);
+tt_add_ref:
+	tt->ref_count++;
+	mutex_unlock(&esw->offloads.termtbl_mutex);
+	return tt;
+tt_create_err:
+	kfree(tt);
+	mutex_unlock(&esw->offloads.termtbl_mutex);
+	return ERR_PTR(err);
+}
+
+void
+mlx5_eswitch_termtbl_put(struct mlx5_eswitch *esw,
+			 struct mlx5_termtbl_handle *tt)
+{
+	mutex_lock(&esw->offloads.termtbl_mutex);
+	if (--tt->ref_count == 0)
+		hash_del(&tt->termtbl_hlist);
+	mutex_unlock(&esw->offloads.termtbl_mutex);
+
+	if (!tt->ref_count) {
+		mlx5_del_flow_rules(tt->rule);
+		mlx5_destroy_flow_table(tt->termtbl);
+		kfree(tt);
+	}
+}
+
+static void
+mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src,
+				  struct mlx5_flow_act *dst)
+{
+	if (!(src->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH))
+		return;
+
+	src->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+	dst->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+	memcpy(&dst->vlan[0], &src->vlan[0], sizeof(src->vlan[0]));
+	memset(&src->vlan[0], 0, sizeof(src->vlan[0]));
+
+	if (!(src->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2))
+		return;
+
+	src->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2;
+	dst->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2;
+	memcpy(&dst->vlan[1], &src->vlan[1], sizeof(src->vlan[1]));
+	memset(&src->vlan[1], 0, sizeof(src->vlan[1]));
+}
+
+bool
+mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
+			      struct mlx5_flow_act *flow_act,
+			      struct mlx5_flow_spec *spec)
+{
+	u32 port_mask = MLX5_GET(fte_match_param, spec->match_criteria,
+				 misc_parameters.source_port);
+	u32 port_value = MLX5_GET(fte_match_param, spec->match_value,
+				  misc_parameters.source_port);
+
+	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table))
+		return false;
+
+	/* push vlan on RX */
+	return (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) &&
+		((port_mask & port_value) == MLX5_VPORT_UPLINK);
+}
+
+struct mlx5_flow_handle *
+mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw,
+			      struct mlx5_flow_table *fdb,
+			      struct mlx5_flow_spec *spec,
+			      struct mlx5_esw_flow_attr *attr,
+			      struct mlx5_flow_act *flow_act,
+			      struct mlx5_flow_destination *dest,
+			      int num_dest)
+{
+	struct mlx5_flow_act term_tbl_act = {};
+	struct mlx5_flow_handle *rule = NULL;
+	bool term_table_created = false;
+	int num_vport_dests = 0;
+	int i, curr_dest;
+
+	mlx5_eswitch_termtbl_actions_move(flow_act, &term_tbl_act);
+	term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+
+	for (i = 0; i < num_dest; i++) {
+		struct mlx5_termtbl_handle *tt;
+
+		/* only vport destinations can be terminated */
+		if (dest[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT)
+			continue;
+
+		/* get the terminating table for the action list */
+		tt = mlx5_eswitch_termtbl_get_create(esw, &term_tbl_act,
+						     &dest[i]);
+		if (IS_ERR(tt)) {
+			esw_warn(esw->dev, "Failed to create termination table\n");
+			goto revert_changes;
+		}
+		attr->dests[num_vport_dests].termtbl = tt;
+		num_vport_dests++;
+
+		/* link the destination with the termination table */
+		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		dest[i].ft = tt->termtbl;
+		term_table_created = true;
+	}
+
+	/* at least one destination should reference a termination table */
+	if (!term_table_created)
+		goto revert_changes;
+
+	/* create the FTE */
+	rule = mlx5_add_flow_rules(fdb, spec, flow_act, dest, num_dest);
+	if (IS_ERR(rule))
+		goto revert_changes;
+
+	goto out;
+
+revert_changes:
+	/* revert the changes that were made to the original flow_act
+	 * and fall-back to the original rule actions
+	 */
+	mlx5_eswitch_termtbl_actions_move(&term_tbl_act, flow_act);
+
+	for (curr_dest = 0; curr_dest < num_vport_dests; curr_dest++) {
+		struct mlx5_termtbl_handle *tt = attr->dests[curr_dest].termtbl;
+
+		/* search for the destination associated with the
+		 * current term table
+		 */
+		for (i = 0; i < num_dest; i++) {
+			if (dest[i].ft != tt->termtbl)
+				continue;
+
+			memset(&dest[i], 0, sizeof(dest[i]));
+			dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+			dest[i].vport.num = tt->dest.vport.num;
+			dest[i].vport.vhca_id = tt->dest.vport.vhca_id;
+			mlx5_eswitch_termtbl_put(esw, tt);
+			break;
+		}
+	}
+	rule = mlx5_add_flow_rules(fdb, spec, flow_act, dest, num_dest);
+out:
+	return rule;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index fbc42b7252a9..8bcf3426b9c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -21,6 +21,7 @@ struct mlx5_event_nb {
 static int any_notifier(struct notifier_block *, unsigned long, void *);
 static int temp_warn(struct notifier_block *, unsigned long, void *);
 static int port_module(struct notifier_block *, unsigned long, void *);
+static int pcie_core(struct notifier_block *, unsigned long, void *);
 
 /* handler which forwards the event to events->nh, driver notifiers */
 static int forward_event(struct notifier_block *, unsigned long, void *);
@@ -30,6 +31,7 @@ static struct mlx5_nb events_nbs_ref[] = {
 	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
 	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
 	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+	{.nb.notifier_call = pcie_core,     .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
 
 	/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
@@ -51,11 +53,14 @@ static struct mlx5_nb events_nbs_ref[] = {
 
 struct mlx5_events {
 	struct mlx5_core_dev *dev;
+	struct workqueue_struct *wq;
 	struct mlx5_event_nb  notifiers[ARRAY_SIZE(events_nbs_ref)];
 	/* driver notifier chain */
 	struct atomic_notifier_head nh;
 	/* port module events stats */
 	struct mlx5_pme_stats pme_stats;
+	/*pcie_core*/
+	struct work_struct pcie_core_work;
 };
 
 static const char *eqe_type_str(u8 type)
@@ -103,6 +108,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_STALL_EVENT";
 	case MLX5_EVENT_TYPE_CMD:
 		return "MLX5_EVENT_TYPE_CMD";
+	case MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED:
+		return "MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED";
 	case MLX5_EVENT_TYPE_PAGE_REQUEST:
 		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
 	case MLX5_EVENT_TYPE_PAGE_FAULT:
@@ -211,11 +218,10 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 	enum port_module_event_status_type module_status;
 	enum port_module_event_error_type error_type;
 	struct mlx5_eqe_port_module *module_event_eqe;
-	const char *status_str, *error_str;
+	const char *status_str;
 	u8 module_num;
 
 	module_event_eqe = &eqe->data.port_module;
-	module_num = module_event_eqe->module;
 	module_status = module_event_eqe->module_status &
 			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
 	error_type = module_event_eqe->error_type &
@@ -223,25 +229,90 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 
 	if (module_status < MLX5_MODULE_STATUS_NUM)
 		events->pme_stats.status_counters[module_status]++;
-	status_str = mlx5_pme_status_to_string(module_status);
 
-	if (module_status == MLX5_MODULE_STATUS_ERROR) {
+	if (module_status == MLX5_MODULE_STATUS_ERROR)
 		if (error_type < MLX5_MODULE_EVENT_ERROR_NUM)
 			events->pme_stats.error_counters[error_type]++;
-		error_str = mlx5_pme_error_to_string(error_type);
-	}
 
 	if (!printk_ratelimit())
 		return NOTIFY_OK;
 
-	if (module_status == MLX5_MODULE_STATUS_ERROR)
+	module_num = module_event_eqe->module;
+	status_str = mlx5_pme_status_to_string(module_status);
+	if (module_status == MLX5_MODULE_STATUS_ERROR) {
+		const char *error_str = mlx5_pme_error_to_string(error_type);
+
 		mlx5_core_err(events->dev,
 			      "Port module event[error]: module %u, %s, %s\n",
 			      module_num, status_str, error_str);
-	else
+	} else {
 		mlx5_core_info(events->dev,
 			       "Port module event: module %u, %s\n",
 			       module_num, status_str);
+	}
+
+	return NOTIFY_OK;
+}
+
+enum {
+	MLX5_PCI_POWER_COULD_NOT_BE_READ = 0x0,
+	MLX5_PCI_POWER_SUFFICIENT_REPORTED = 0x1,
+	MLX5_PCI_POWER_INSUFFICIENT_REPORTED = 0x2,
+};
+
+static void mlx5_pcie_event(struct work_struct *work)
+{
+	u32 out[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+	struct mlx5_events *events;
+	struct mlx5_core_dev *dev;
+	u8 power_status;
+	u16 pci_power;
+
+	events = container_of(work, struct mlx5_events, pcie_core_work);
+	dev  = events->dev;
+
+	if (!MLX5_CAP_MCAM_FEATURE(dev, pci_status_and_power))
+		return;
+
+	mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+			     MLX5_REG_MPEIN, 0, 0);
+	power_status = MLX5_GET(mpein_reg, out, pwr_status);
+	pci_power = MLX5_GET(mpein_reg, out, pci_power);
+
+	switch (power_status) {
+	case MLX5_PCI_POWER_COULD_NOT_BE_READ:
+		mlx5_core_info_rl(dev,
+				  "PCIe slot power capability was not advertised.\n");
+		break;
+	case MLX5_PCI_POWER_INSUFFICIENT_REPORTED:
+		mlx5_core_warn_rl(dev,
+				  "Detected insufficient power on the PCIe slot (%uW).\n",
+				  pci_power);
+		break;
+	case MLX5_PCI_POWER_SUFFICIENT_REPORTED:
+		mlx5_core_info_rl(dev,
+				  "PCIe slot advertised sufficient power (%uW).\n",
+				  pci_power);
+		break;
+	}
+}
+
+static int pcie_core(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_event_nb    *event_nb = mlx5_nb_cof(nb,
+							struct mlx5_event_nb,
+							nb);
+	struct mlx5_events      *events   = event_nb->ctx;
+	struct mlx5_eqe         *eqe      = data;
+
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT:
+			queue_work(events->wq, &events->pcie_core_work);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
 
 	return NOTIFY_OK;
 }
@@ -274,11 +345,17 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	ATOMIC_INIT_NOTIFIER_HEAD(&events->nh);
 	events->dev = dev;
 	dev->priv.events = events;
+	events->wq = create_singlethread_workqueue("mlx5_events");
+	if (!events->wq)
+		return -ENOMEM;
+	INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
+
 	return 0;
 }
 
 void mlx5_events_cleanup(struct mlx5_core_dev *dev)
 {
+	destroy_workqueue(dev->priv.events->wq);
 	kvfree(dev->priv.events);
 }
 
@@ -301,6 +378,7 @@ void mlx5_events_stop(struct mlx5_core_dev *dev)
 
 	for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
 		mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
+	flush_workqueue(events->wq);
 }
 
 int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/fpga/Makefile
index d8e17110f25d..c78512eed8d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 873541ef4c1b..4c50efe4e7f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -135,7 +135,7 @@ static void mlx5_fpga_conn_notify_hw(struct mlx5_fpga_conn *conn, void *wqe)
 	*conn->qp.wq.sq.db = cpu_to_be32(conn->qp.sq.pc);
 	/* Make sure that doorbell record is visible before ringing */
 	wmb();
-	mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET, NULL);
+	mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET);
 }
 
 static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn,
@@ -414,7 +414,8 @@ static void mlx5_fpga_conn_cq_tasklet(unsigned long data)
 	mlx5_fpga_conn_cqes(conn, MLX5_FPGA_CQ_BUDGET);
 }
 
-static void mlx5_fpga_conn_cq_complete(struct mlx5_core_cq *mcq)
+static void mlx5_fpga_conn_cq_complete(struct mlx5_core_cq *mcq,
+				       struct mlx5_eqe *eqe)
 {
 	struct mlx5_fpga_conn *conn;
 
@@ -429,6 +430,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	struct mlx5_fpga_device *fdev = conn->fdev;
 	struct mlx5_core_dev *mdev = fdev->mdev;
 	u32 temp_cqc[MLX5_ST_SZ_DW(cqc)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	struct mlx5_wq_param wqp;
 	struct mlx5_cqe64 *cqe;
 	int inlen, err, eqn;
@@ -476,7 +478,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
 	mlx5_fill_page_frag_array(&conn->cq.wq_ctrl.buf, pas);
 
-	err = mlx5_core_create_cq(mdev, &conn->cq.mcq, in, inlen);
+	err = mlx5_core_create_cq(mdev, &conn->cq.mcq, in, inlen, out, sizeof(out));
 	kvfree(in);
 
 	if (err)
@@ -867,7 +869,7 @@ struct mlx5_fpga_conn *mlx5_fpga_conn_create(struct mlx5_fpga_device *fdev,
 	conn->cb_arg = attr->cb_arg;
 
 	remote_mac = MLX5_ADDR_OF(fpga_qpc, conn->fpga_qpc, remote_mac_47_32);
-	err = mlx5_query_nic_vport_mac_address(fdev->mdev, 0, remote_mac);
+	err = mlx5_query_mac_address(fdev->mdev, remote_mac);
 	if (err) {
 		mlx5_fpga_err(fdev, "Failed to query local MAC: %d\n", err);
 		ret = ERR_PTR(err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index 27c5f6c7d36a..d046d1ec2a86 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -317,7 +317,6 @@ static int mlx5_fpga_event(struct mlx5_fpga_device *fdev,
 	const char *event_name;
 	bool teardown = false;
 	unsigned long flags;
-	u32 fpga_qpn;
 	u8 syndrome;
 
 	switch (event) {
@@ -328,7 +327,6 @@ static int mlx5_fpga_event(struct mlx5_fpga_device *fdev,
 	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
 		syndrome = MLX5_GET(fpga_qp_error_event, data, syndrome);
 		event_name = mlx5_fpga_qp_syndrome_to_string(syndrome);
-		fpga_qpn = MLX5_GET(fpga_qp_error_event, data, fpga_qpn);
 		break;
 	default:
 		return NOTIFY_DONE;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
index 7e2e871dbf83..52c9dee91ea4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
@@ -37,6 +37,7 @@
 
 #include <linux/mlx5/eq.h>
 
+#include "mlx5_core.h"
 #include "lib/eq.h"
 #include "fpga/cmd.h"
 
@@ -62,26 +63,26 @@ struct mlx5_fpga_device {
 };
 
 #define mlx5_fpga_dbg(__adev, format, ...) \
-	dev_dbg(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
-		 __func__, __LINE__, current->pid, ##__VA_ARGS__)
+	mlx5_core_dbg((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+		       __func__, __LINE__, current->pid, ##__VA_ARGS__)
 
 #define mlx5_fpga_err(__adev, format, ...) \
-	dev_err(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
-		__func__, __LINE__, current->pid, ##__VA_ARGS__)
+	mlx5_core_err((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+		      __func__, __LINE__, current->pid, ##__VA_ARGS__)
 
 #define mlx5_fpga_warn(__adev, format, ...) \
-	dev_warn(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d:(pid %d): " format, \
-		__func__, __LINE__, current->pid, ##__VA_ARGS__)
+	mlx5_core_warn((__adev)->mdev, "FPGA: %s:%d:(pid %d): " format, \
+		       __func__, __LINE__, current->pid, ##__VA_ARGS__)
 
 #define mlx5_fpga_warn_ratelimited(__adev, format, ...) \
-	dev_warn_ratelimited(&(__adev)->mdev->pdev->dev, "FPGA: %s:%d: " \
-		format, __func__, __LINE__, ##__VA_ARGS__)
+	mlx5_core_err_rl((__adev)->mdev, "FPGA: %s:%d: " \
+			 format, __func__, __LINE__, ##__VA_ARGS__)
 
 #define mlx5_fpga_notice(__adev, format, ...) \
-	dev_notice(&(__adev)->mdev->pdev->dev, "FPGA: " format, ##__VA_ARGS__)
+	mlx5_core_info((__adev)->mdev, "FPGA: " format, ##__VA_ARGS__)
 
 #define mlx5_fpga_info(__adev, format, ...) \
-	dev_info(&(__adev)->mdev->pdev->dev, "FPGA: " format, ##__VA_ARGS__)
+	mlx5_core_info((__adev)->mdev, "FPGA: " format, ##__VA_ARGS__)
 
 int mlx5_fpga_init(struct mlx5_core_dev *mdev);
 void mlx5_fpga_cleanup(struct mlx5_core_dev *mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 5a22c5874f3b..c76da309506b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -636,7 +636,8 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
 					   u8 match_criteria_enable,
 					   const u32 *match_c,
 					   const u32 *match_v,
-					   struct mlx5_flow_act *flow_act)
+					   struct mlx5_flow_act *flow_act,
+					   struct mlx5_flow_context *flow_context)
 {
 	const void *outer_c = MLX5_ADDR_OF(fte_match_param, match_c,
 					   outer_headers);
@@ -655,7 +656,7 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
 	    (match_criteria_enable &
 	     ~(MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS)) ||
 	    (flow_act->action & ~(MLX5_FLOW_CONTEXT_ACTION_ENCRYPT | MLX5_FLOW_CONTEXT_ACTION_ALLOW)) ||
-	     (flow_act->flags & FLOW_ACT_HAS_TAG))
+	     (flow_context->flags & FLOW_CONTEXT_HAS_TAG))
 		return false;
 
 	return true;
@@ -767,7 +768,8 @@ mlx5_fpga_ipsec_fs_create_sa_ctx(struct mlx5_core_dev *mdev,
 					    fg->mask.match_criteria_enable,
 					    fg->mask.match_criteria,
 					    fte->val,
-					    &fte->action))
+					    &fte->action,
+					    &fte->flow_context))
 		return ERR_PTR(-EINVAL);
 	else if (!mlx5_is_fpga_ipsec_rule(mdev,
 					  fg->mask.match_criteria_enable,
@@ -989,32 +991,33 @@ static enum fs_flow_table_type egress_to_fs_ft(bool egress)
 	return egress ? FS_FT_NIC_TX : FS_FT_NIC_RX;
 }
 
-static int fpga_ipsec_fs_create_flow_group(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_create_flow_group(struct mlx5_flow_root_namespace *ns,
 					   struct mlx5_flow_table *ft,
 					   u32 *in,
-					   unsigned int *group_id,
+					   struct mlx5_flow_group *fg,
 					   bool is_egress)
 {
-	int (*create_flow_group)(struct mlx5_core_dev *dev,
+	int (*create_flow_group)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft, u32 *in,
-				 unsigned int *group_id) =
+				 struct mlx5_flow_group *fg) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->create_flow_group;
 	char *misc_params_c = MLX5_ADDR_OF(create_flow_group_in, in,
 					   match_criteria.misc_parameters);
+	struct mlx5_core_dev *dev = ns->dev;
 	u32 saved_outer_esp_spi_mask;
 	u8 match_criteria_enable;
 	int ret;
 
 	if (MLX5_CAP_FLOWTABLE(dev,
 			       flow_table_properties_nic_receive.ft_field_support.outer_esp_spi))
-		return create_flow_group(dev, ft, in, group_id);
+		return create_flow_group(ns, ft, in, fg);
 
 	match_criteria_enable =
 		MLX5_GET(create_flow_group_in, in, match_criteria_enable);
 	saved_outer_esp_spi_mask =
 		MLX5_GET(fte_match_set_misc, misc_params_c, outer_esp_spi);
 	if (!match_criteria_enable || !saved_outer_esp_spi_mask)
-		return create_flow_group(dev, ft, in, group_id);
+		return create_flow_group(ns, ft, in, fg);
 
 	MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi, 0);
 
@@ -1023,7 +1026,7 @@ static int fpga_ipsec_fs_create_flow_group(struct mlx5_core_dev *dev,
 		MLX5_SET(create_flow_group_in, in, match_criteria_enable,
 			 match_criteria_enable & ~MLX5_MATCH_MISC_PARAMETERS);
 
-	ret = create_flow_group(dev, ft, in, group_id);
+	ret = create_flow_group(ns, ft, in, fg);
 
 	MLX5_SET(fte_match_set_misc, misc_params_c, outer_esp_spi, saved_outer_esp_spi_mask);
 	MLX5_SET(create_flow_group_in, in, match_criteria_enable, match_criteria_enable);
@@ -1031,17 +1034,18 @@ static int fpga_ipsec_fs_create_flow_group(struct mlx5_core_dev *dev,
 	return ret;
 }
 
-static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_create_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
 				    struct mlx5_flow_group *fg,
 				    struct fs_fte *fte,
 				    bool is_egress)
 {
-	int (*create_fte)(struct mlx5_core_dev *dev,
+	int (*create_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct mlx5_flow_group *fg,
 			  struct fs_fte *fte) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->create_fte;
+	struct mlx5_core_dev *dev = ns->dev;
 	struct mlx5_fpga_device *fdev = dev->fpga;
 	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
 	struct mlx5_fpga_ipsec_rule *rule;
@@ -1053,7 +1057,7 @@ static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
 	    !(fte->action.action &
 	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
 	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return create_fte(dev, ft, fg, fte);
+		return create_fte(ns, ft, fg, fte);
 
 	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
 	if (!rule)
@@ -1070,7 +1074,7 @@ static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
 	WARN_ON(rule_insert(fipsec, rule));
 
 	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = create_fte(dev, ft, fg, fte);
+	ret = create_fte(ns, ft, fg, fte);
 	restore_spec_mailbox(fte, &mbox_mod);
 	if (ret) {
 		_rule_delete(fipsec, rule);
@@ -1081,19 +1085,20 @@ static int fpga_ipsec_fs_create_fte(struct mlx5_core_dev *dev,
 	return ret;
 }
 
-static int fpga_ipsec_fs_update_fte(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_update_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
-				    unsigned int group_id,
+				    struct mlx5_flow_group *fg,
 				    int modify_mask,
 				    struct fs_fte *fte,
 				    bool is_egress)
 {
-	int (*update_fte)(struct mlx5_core_dev *dev,
+	int (*update_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
-			  unsigned int group_id,
+			  struct mlx5_flow_group *fg,
 			  int modify_mask,
 			  struct fs_fte *fte) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->update_fte;
+	struct mlx5_core_dev *dev = ns->dev;
 	bool is_esp = fte->action.esp_id;
 	struct mailbox_mod mbox_mod;
 	int ret;
@@ -1102,24 +1107,25 @@ static int fpga_ipsec_fs_update_fte(struct mlx5_core_dev *dev,
 	    !(fte->action.action &
 	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
 	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return update_fte(dev, ft, group_id, modify_mask, fte);
+		return update_fte(ns, ft, fg, modify_mask, fte);
 
 	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = update_fte(dev, ft, group_id, modify_mask, fte);
+	ret = update_fte(ns, ft, fg, modify_mask, fte);
 	restore_spec_mailbox(fte, &mbox_mod);
 
 	return ret;
 }
 
-static int fpga_ipsec_fs_delete_fte(struct mlx5_core_dev *dev,
+static int fpga_ipsec_fs_delete_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
 				    struct fs_fte *fte,
 				    bool is_egress)
 {
-	int (*delete_fte)(struct mlx5_core_dev *dev,
+	int (*delete_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct fs_fte *fte) =
 		mlx5_fs_cmd_get_default(egress_to_fs_ft(is_egress))->delete_fte;
+	struct mlx5_core_dev *dev = ns->dev;
 	struct mlx5_fpga_device *fdev = dev->fpga;
 	struct mlx5_fpga_ipsec *fipsec = fdev->ipsec;
 	struct mlx5_fpga_ipsec_rule *rule;
@@ -1131,7 +1137,7 @@ static int fpga_ipsec_fs_delete_fte(struct mlx5_core_dev *dev,
 	    !(fte->action.action &
 	      (MLX5_FLOW_CONTEXT_ACTION_ENCRYPT |
 	       MLX5_FLOW_CONTEXT_ACTION_DECRYPT)))
-		return delete_fte(dev, ft, fte);
+		return delete_fte(ns, ft, fte);
 
 	rule = rule_search(fipsec, fte);
 	if (!rule)
@@ -1141,84 +1147,84 @@ static int fpga_ipsec_fs_delete_fte(struct mlx5_core_dev *dev,
 	rule_delete(fipsec, rule);
 
 	modify_spec_mailbox(dev, fte, &mbox_mod);
-	ret = delete_fte(dev, ft, fte);
+	ret = delete_fte(ns, ft, fte);
 	restore_spec_mailbox(fte, &mbox_mod);
 
 	return ret;
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_flow_group_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_flow_group_egress(struct mlx5_flow_root_namespace *ns,
 					    struct mlx5_flow_table *ft,
 					    u32 *in,
-					    unsigned int *group_id)
+					    struct mlx5_flow_group *fg)
 {
-	return fpga_ipsec_fs_create_flow_group(dev, ft, in, group_id, true);
+	return fpga_ipsec_fs_create_flow_group(ns, ft, in, fg, true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_fte_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_fte_egress(struct mlx5_flow_root_namespace *ns,
 				     struct mlx5_flow_table *ft,
 				     struct mlx5_flow_group *fg,
 				     struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_create_fte(dev, ft, fg, fte, true);
+	return fpga_ipsec_fs_create_fte(ns, ft, fg, fte, true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_update_fte_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_update_fte_egress(struct mlx5_flow_root_namespace *ns,
 				     struct mlx5_flow_table *ft,
-				     unsigned int group_id,
+				     struct mlx5_flow_group *fg,
 				     int modify_mask,
 				     struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_update_fte(dev, ft, group_id, modify_mask, fte,
+	return fpga_ipsec_fs_update_fte(ns, ft, fg, modify_mask, fte,
 					true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_delete_fte_egress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_delete_fte_egress(struct mlx5_flow_root_namespace *ns,
 				     struct mlx5_flow_table *ft,
 				     struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_delete_fte(dev, ft, fte, true);
+	return fpga_ipsec_fs_delete_fte(ns, ft, fte, true);
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_flow_group_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_flow_group_ingress(struct mlx5_flow_root_namespace *ns,
 					     struct mlx5_flow_table *ft,
 					     u32 *in,
-					     unsigned int *group_id)
+					     struct mlx5_flow_group *fg)
 {
-	return fpga_ipsec_fs_create_flow_group(dev, ft, in, group_id, false);
+	return fpga_ipsec_fs_create_flow_group(ns, ft, in, fg, false);
 }
 
 static int
-mlx5_fpga_ipsec_fs_create_fte_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_create_fte_ingress(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      struct mlx5_flow_group *fg,
 				      struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_create_fte(dev, ft, fg, fte, false);
+	return fpga_ipsec_fs_create_fte(ns, ft, fg, fte, false);
 }
 
 static int
-mlx5_fpga_ipsec_fs_update_fte_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_update_fte_ingress(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
-				      unsigned int group_id,
+				      struct mlx5_flow_group *fg,
 				      int modify_mask,
 				      struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_update_fte(dev, ft, group_id, modify_mask, fte,
+	return fpga_ipsec_fs_update_fte(ns, ft, fg, modify_mask, fte,
 					false);
 }
 
 static int
-mlx5_fpga_ipsec_fs_delete_fte_ingress(struct mlx5_core_dev *dev,
+mlx5_fpga_ipsec_fs_delete_fte_ingress(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      struct fs_fte *fte)
 {
-	return fpga_ipsec_fs_delete_fte(dev, ft, fte, false);
+	return fpga_ipsec_fs_delete_fte(ns, ft, fte, false);
 }
 
 static struct mlx5_flow_cmds fpga_ipsec_ingress;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
index 2b5e63b0d4d6..382985e65b48 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.h
@@ -37,8 +37,6 @@
 #include "accel/ipsec.h"
 #include "fs_cmd.h"
 
-#ifdef CONFIG_MLX5_FPGA
-
 u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev);
 unsigned int mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev);
 int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev, u64 *counters,
@@ -66,77 +64,4 @@ int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 const struct mlx5_flow_cmds *
 mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type);
 
-#else
-
-static inline u32 mlx5_fpga_ipsec_device_caps(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
-
-static inline unsigned int
-mlx5_fpga_ipsec_counters_count(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
-
-static inline int mlx5_fpga_ipsec_counters_read(struct mlx5_core_dev *mdev,
-						u64 *counters)
-{
-	return 0;
-}
-
-static inline void *
-mlx5_fpga_ipsec_create_sa_ctx(struct mlx5_core_dev *mdev,
-			      struct mlx5_accel_esp_xfrm *accel_xfrm,
-			      const __be32 saddr[4],
-			      const __be32 daddr[4],
-			      const __be32 spi, bool is_ipv6)
-{
-	return NULL;
-}
-
-static inline void mlx5_fpga_ipsec_delete_sa_ctx(void *context)
-{
-}
-
-static inline int mlx5_fpga_ipsec_init(struct mlx5_core_dev *mdev)
-{
-	return 0;
-}
-
-static inline void mlx5_fpga_ipsec_cleanup(struct mlx5_core_dev *mdev)
-{
-}
-
-static inline void mlx5_fpga_ipsec_build_fs_cmds(void)
-{
-}
-
-static inline struct mlx5_accel_esp_xfrm *
-mlx5_fpga_esp_create_xfrm(struct mlx5_core_dev *mdev,
-			  const struct mlx5_accel_esp_xfrm_attrs *attrs,
-			  u32 flags)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline void mlx5_fpga_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm)
-{
-}
-
-static inline int
-mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
-			  const struct mlx5_accel_esp_xfrm_attrs *attrs)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline const struct mlx5_flow_cmds *
-mlx5_fs_cmd_get_default_ipsec_fpga_cmds(enum fs_flow_table_type type)
-{
-	return mlx5_fs_cmd_get_default(type);
-}
-
-#endif /* CONFIG_MLX5_FPGA */
-
 #endif	/* __MLX5_FPGA_SADB_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 5cf5f2a9d51f..22a2ef111514 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -148,14 +148,16 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	return ret;
 }
 
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
-				       spinlock_t *idr_spinlock, u32 swid)
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
+					spinlock_t *idr_spinlock, u32 swid)
 {
 	unsigned long flags;
+	void *ptr;
 
 	spin_lock_irqsave(idr_spinlock, flags);
-	idr_remove(idr, swid);
+	ptr = idr_remove(idr, swid);
 	spin_unlock_irqrestore(idr_spinlock, flags);
+	return ptr;
 }
 
 static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
@@ -165,20 +167,12 @@ static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
 	kfree(buf);
 }
 
-struct mlx5_teardown_stream_context {
-	struct mlx5_fpga_tls_command_context cmd;
-	u32 swid;
-};
-
 static void
 mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 				  struct mlx5_fpga_device *fdev,
 				  struct mlx5_fpga_tls_command_context *cmd,
 				  struct mlx5_fpga_dma_buf *resp)
 {
-	struct mlx5_teardown_stream_context *ctx =
-		    container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
 	if (resp) {
 		u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
 
@@ -186,14 +180,6 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
-			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->tx_idr_spinlock,
-						   ctx->swid);
-		else
-			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
-						   &fdev->tls->rx_idr_spinlock,
-						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
 }
@@ -225,8 +211,14 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 
 	rcu_read_lock();
 	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
+	if (unlikely(!flow)) {
+		rcu_read_unlock();
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		kfree(buf);
+		return -EINVAL;
+	}
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+	rcu_read_unlock();
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
 	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
@@ -238,6 +230,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	buf->complete = mlx_tls_kfree_complete;
 
 	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+	if (ret < 0)
+		kfree(buf);
 
 	return ret;
 }
@@ -245,7 +239,7 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
-	struct mlx5_teardown_stream_context *ctx;
+	struct mlx5_fpga_tls_command_context *ctx;
 	struct mlx5_fpga_dma_buf *buf;
 	void *cmd;
 
@@ -253,7 +247,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	if (!ctx)
 		return;
 
-	buf = &ctx->cmd.buf;
+	buf = &ctx->buf;
 	cmd = (ctx + 1);
 	MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
 	MLX5_SET(tls_cmd, cmd, swid, swid);
@@ -264,8 +258,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	buf->sg[0].data = cmd;
 	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
 
-	ctx->swid = swid;
-	mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+	mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
@@ -275,13 +268,14 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
-	rcu_read_lock();
 	if (direction_sx)
-		flow = idr_find(&tls->tx_idr, swid);
+		flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+						  &tls->tx_idr_spinlock,
+						  swid);
 	else
-		flow = idr_find(&tls->rx_idr, swid);
-
-	rcu_read_unlock();
+		flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+						  &tls->rx_idr_spinlock,
+						  swid);
 
 	if (!flow) {
 		mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
@@ -289,6 +283,7 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 		return;
 	}
 
+	synchronize_rcu(); /* before kfree(flow) */
 	mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index c44ccb67c4a3..7ac1249eadc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -39,7 +39,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 
-static int mlx5_cmd_stub_update_root_ft(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_update_root_ft(struct mlx5_flow_root_namespace *ns,
 					struct mlx5_flow_table *ft,
 					u32 underlay_qpn,
 					bool disconnect)
@@ -47,47 +47,43 @@ static int mlx5_cmd_stub_update_root_ft(struct mlx5_core_dev *dev,
 	return 0;
 }
 
-static int mlx5_cmd_stub_create_flow_table(struct mlx5_core_dev *dev,
-					   u16 vport,
-					   enum fs_flow_table_op_mod op_mod,
-					   enum fs_flow_table_type type,
-					   unsigned int level,
+static int mlx5_cmd_stub_create_flow_table(struct mlx5_flow_root_namespace *ns,
+					   struct mlx5_flow_table *ft,
 					   unsigned int log_size,
-					   struct mlx5_flow_table *next_ft,
-					   unsigned int *table_id, u32 flags)
+					   struct mlx5_flow_table *next_ft)
 {
 	return 0;
 }
 
-static int mlx5_cmd_stub_destroy_flow_table(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 					    struct mlx5_flow_table *ft)
 {
 	return 0;
 }
 
-static int mlx5_cmd_stub_modify_flow_table(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 					   struct mlx5_flow_table *ft,
 					   struct mlx5_flow_table *next_ft)
 {
 	return 0;
 }
 
-static int mlx5_cmd_stub_create_flow_group(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_create_flow_group(struct mlx5_flow_root_namespace *ns,
 					   struct mlx5_flow_table *ft,
 					   u32 *in,
-					   unsigned int *group_id)
+					   struct mlx5_flow_group *fg)
 {
 	return 0;
 }
 
-static int mlx5_cmd_stub_destroy_flow_group(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
 					    struct mlx5_flow_table *ft,
-					    unsigned int group_id)
+					    struct mlx5_flow_group *fg)
 {
 	return 0;
 }
 
-static int mlx5_cmd_stub_create_fte(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_create_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
 				    struct mlx5_flow_group *group,
 				    struct fs_fte *fte)
@@ -95,28 +91,29 @@ static int mlx5_cmd_stub_create_fte(struct mlx5_core_dev *dev,
 	return 0;
 }
 
-static int mlx5_cmd_stub_update_fte(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_update_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
-				    unsigned int group_id,
+				    struct mlx5_flow_group *group,
 				    int modify_mask,
 				    struct fs_fte *fte)
 {
 	return -EOPNOTSUPP;
 }
 
-static int mlx5_cmd_stub_delete_fte(struct mlx5_core_dev *dev,
+static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns,
 				    struct mlx5_flow_table *ft,
 				    struct fs_fte *fte)
 {
 	return 0;
 }
 
-static int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
+static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 				   struct mlx5_flow_table *ft, u32 underlay_qpn,
 				   bool disconnect)
 {
 	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0};
+	struct mlx5_core_dev *dev = ns->dev;
 
 	if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
 	    underlay_qpn == 0)
@@ -143,29 +140,27 @@ static int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-static int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
-				      u16 vport,
-				      enum fs_flow_table_op_mod op_mod,
-				      enum fs_flow_table_type type,
-				      unsigned int level,
+static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
+				      struct mlx5_flow_table *ft,
 				      unsigned int log_size,
-				      struct mlx5_flow_table *next_ft,
-				      unsigned int *table_id, u32 flags)
+				      struct mlx5_flow_table *next_ft)
 {
-	int en_encap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
-	int en_decap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
+	int en_encap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
+	int en_decap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
+	int term = !!(ft->flags & MLX5_FLOW_TABLE_TERMINATION);
 	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)]   = {0};
+	struct mlx5_core_dev *dev = ns->dev;
 	int err;
 
 	MLX5_SET(create_flow_table_in, in, opcode,
 		 MLX5_CMD_OP_CREATE_FLOW_TABLE);
 
-	MLX5_SET(create_flow_table_in, in, table_type, type);
-	MLX5_SET(create_flow_table_in, in, flow_table_context.level, level);
+	MLX5_SET(create_flow_table_in, in, table_type, ft->type);
+	MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, log_size);
-	if (vport) {
-		MLX5_SET(create_flow_table_in, in, vport_number, vport);
+	if (ft->vport) {
+		MLX5_SET(create_flow_table_in, in, vport_number, ft->vport);
 		MLX5_SET(create_flow_table_in, in, other_vport, 1);
 	}
 
@@ -173,14 +168,21 @@ static int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
 		 en_decap);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.reformat_en,
 		 en_encap);
+	MLX5_SET(create_flow_table_in, in, flow_table_context.termination_table,
+		 term);
 
-	switch (op_mod) {
+	switch (ft->op_mod) {
 	case FS_FT_OP_MOD_NORMAL:
 		if (next_ft) {
 			MLX5_SET(create_flow_table_in, in,
-				 flow_table_context.table_miss_action, 1);
+				 flow_table_context.table_miss_action,
+				 MLX5_FLOW_TABLE_MISS_ACTION_FWD);
 			MLX5_SET(create_flow_table_in, in,
 				 flow_table_context.table_miss_id, next_ft->id);
+		} else {
+			MLX5_SET(create_flow_table_in, in,
+				 flow_table_context.table_miss_action,
+				 ns->def_miss_action);
 		}
 		break;
 
@@ -195,16 +197,17 @@ static int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev,
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (!err)
-		*table_id = MLX5_GET(create_flow_table_out, out,
-				     table_id);
+		ft->id = MLX5_GET(create_flow_table_out, out,
+				  table_id);
 	return err;
 }
 
-static int mlx5_cmd_destroy_flow_table(struct mlx5_core_dev *dev,
+static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 				       struct mlx5_flow_table *ft)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)] = {0};
+	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(destroy_flow_table_in, in, opcode,
 		 MLX5_CMD_OP_DESTROY_FLOW_TABLE);
@@ -218,12 +221,13 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-static int mlx5_cmd_modify_flow_table(struct mlx5_core_dev *dev,
+static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      struct mlx5_flow_table *next_ft)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_flow_table_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(modify_flow_table_out)] = {0};
+	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(modify_flow_table_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_FLOW_TABLE);
@@ -250,26 +254,29 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_core_dev *dev,
 			 MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID);
 		if (next_ft) {
 			MLX5_SET(modify_flow_table_in, in,
-				 flow_table_context.table_miss_action, 1);
+				 flow_table_context.table_miss_action,
+				 MLX5_FLOW_TABLE_MISS_ACTION_FWD);
 			MLX5_SET(modify_flow_table_in, in,
 				 flow_table_context.table_miss_id,
 				 next_ft->id);
 		} else {
 			MLX5_SET(modify_flow_table_in, in,
-				 flow_table_context.table_miss_action, 0);
+				 flow_table_context.table_miss_action,
+				 ns->def_miss_action);
 		}
 	}
 
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-static int mlx5_cmd_create_flow_group(struct mlx5_core_dev *dev,
+static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      u32 *in,
-				      unsigned int *group_id)
+				      struct mlx5_flow_group *fg)
 {
 	u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {0};
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_dev *dev = ns->dev;
 	int err;
 
 	MLX5_SET(create_flow_group_in, in, opcode,
@@ -283,23 +290,24 @@ static int mlx5_cmd_create_flow_group(struct mlx5_core_dev *dev,
 
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 	if (!err)
-		*group_id = MLX5_GET(create_flow_group_out, out,
-				     group_id);
+		fg->id = MLX5_GET(create_flow_group_out, out,
+				  group_id);
 	return err;
 }
 
-static int mlx5_cmd_destroy_flow_group(struct mlx5_core_dev *dev,
+static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
 				       struct mlx5_flow_table *ft,
-				       unsigned int group_id)
+				       struct mlx5_flow_group *fg)
 {
 	u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)]   = {0};
+	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(destroy_flow_group_in, in, opcode,
 		 MLX5_CMD_OP_DESTROY_FLOW_GROUP);
 	MLX5_SET(destroy_flow_group_in, in, table_type, ft->type);
 	MLX5_SET(destroy_flow_group_in, in, table_id, ft->id);
-	MLX5_SET(destroy_flow_group_in, in, group_id, group_id);
+	MLX5_SET(destroy_flow_group_in, in, group_id, fg->id);
 	if (ft->vport) {
 		MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport);
 		MLX5_SET(destroy_flow_group_in, in, other_vport, 1);
@@ -388,7 +396,11 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
 
-	MLX5_SET(flow_context, in_flow_context, flow_tag, fte->action.flow_tag);
+	MLX5_SET(flow_context, in_flow_context, flow_tag,
+		 fte->flow_context.flow_tag);
+	MLX5_SET(flow_context, in_flow_context, flow_source,
+		 fte->flow_context.flow_source);
+
 	MLX5_SET(flow_context, in_flow_context, extended_destination,
 		 extended_dest);
 	if (extended_dest) {
@@ -505,23 +517,25 @@ err_out:
 	return err;
 }
 
-static int mlx5_cmd_create_fte(struct mlx5_core_dev *dev,
+static int mlx5_cmd_create_fte(struct mlx5_flow_root_namespace *ns,
 			       struct mlx5_flow_table *ft,
 			       struct mlx5_flow_group *group,
 			       struct fs_fte *fte)
 {
+	struct mlx5_core_dev *dev = ns->dev;
 	unsigned int group_id = group->id;
 
 	return mlx5_cmd_set_fte(dev, 0, 0, ft, group_id, fte);
 }
 
-static int mlx5_cmd_update_fte(struct mlx5_core_dev *dev,
+static int mlx5_cmd_update_fte(struct mlx5_flow_root_namespace *ns,
 			       struct mlx5_flow_table *ft,
-			       unsigned int group_id,
+			       struct mlx5_flow_group *fg,
 			       int modify_mask,
 			       struct fs_fte *fte)
 {
 	int opmod;
+	struct mlx5_core_dev *dev = ns->dev;
 	int atomic_mod_cap = MLX5_CAP_FLOWTABLE(dev,
 						flow_table_properties_nic_receive.
 						flow_modify_en);
@@ -529,15 +543,16 @@ static int mlx5_cmd_update_fte(struct mlx5_core_dev *dev,
 		return -EOPNOTSUPP;
 	opmod = 1;
 
-	return	mlx5_cmd_set_fte(dev, opmod, modify_mask, ft, group_id, fte);
+	return	mlx5_cmd_set_fte(dev, opmod, modify_mask, ft, fg->id, fte);
 }
 
-static int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev,
+static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns,
 			       struct mlx5_flow_table *ft,
 			       struct fs_fte *fte)
 {
 	u32 out[MLX5_ST_SZ_DW(delete_fte_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(delete_fte_in)]   = {0};
+	struct mlx5_core_dev *dev = ns->dev;
 
 	MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY);
 	MLX5_SET(delete_fte_in, in, table_type, ft->type);
@@ -760,6 +775,10 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
 		max_actions = MLX5_CAP_FLOWTABLE_NIC_TX(dev, max_modify_header_actions);
 		table_type = FS_FT_NIC_TX;
 		break;
+	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:
+		max_actions = MLX5_CAP_ESW_INGRESS_ACL(dev, max_modify_header_actions);
+		table_type = FS_FT_ESW_INGRESS_ACL;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -853,6 +872,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ
 	case FS_FT_SNIFFER_RX:
 	case FS_FT_SNIFFER_TX:
 	case FS_FT_NIC_TX:
+	case FS_FT_RDMA_RX:
 		return mlx5_fs_cmd_get_fw_cmds();
 	default:
 		return mlx5_fs_cmd_get_stub_cmds();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index 6228ba7bfa1a..e340f9af2f5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -36,45 +36,42 @@
 #include "fs_core.h"
 
 struct mlx5_flow_cmds {
-	int (*create_flow_table)(struct mlx5_core_dev *dev,
-				 u16 vport,
-				 enum fs_flow_table_op_mod op_mod,
-				 enum fs_flow_table_type type,
-				 unsigned int level, unsigned int log_size,
-				 struct mlx5_flow_table *next_ft,
-				 unsigned int *table_id, u32 flags);
-	int (*destroy_flow_table)(struct mlx5_core_dev *dev,
+	int (*create_flow_table)(struct mlx5_flow_root_namespace *ns,
+				 struct mlx5_flow_table *ft,
+				 unsigned int log_size,
+				 struct mlx5_flow_table *next_ft);
+	int (*destroy_flow_table)(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft);
 
-	int (*modify_flow_table)(struct mlx5_core_dev *dev,
+	int (*modify_flow_table)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft,
 				 struct mlx5_flow_table *next_ft);
 
-	int (*create_flow_group)(struct mlx5_core_dev *dev,
+	int (*create_flow_group)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft,
 				 u32 *in,
-				 unsigned int *group_id);
+				 struct mlx5_flow_group *fg);
 
-	int (*destroy_flow_group)(struct mlx5_core_dev *dev,
+	int (*destroy_flow_group)(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft,
-				  unsigned int group_id);
+				  struct mlx5_flow_group *fg);
 
-	int (*create_fte)(struct mlx5_core_dev *dev,
+	int (*create_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct mlx5_flow_group *fg,
 			  struct fs_fte *fte);
 
-	int (*update_fte)(struct mlx5_core_dev *dev,
+	int (*update_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
-			  unsigned int group_id,
+			  struct mlx5_flow_group *fg,
 			  int modify_mask,
 			  struct fs_fte *fte);
 
-	int (*delete_fte)(struct mlx5_core_dev *dev,
+	int (*delete_fte)(struct mlx5_flow_root_namespace *ns,
 			  struct mlx5_flow_table *ft,
 			  struct fs_fte *fte);
 
-	int (*update_root_ft)(struct mlx5_core_dev *dev,
+	int (*update_root_ft)(struct mlx5_flow_root_namespace *ns,
 			      struct mlx5_flow_table *ft,
 			      u32 underlay_qpn,
 			      bool disconnect);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 79f122b45def..3e99799bdb40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -32,6 +32,7 @@
 
 #include <linux/mutex.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/eswitch.h>
 
 #include "mlx5_core.h"
@@ -262,10 +263,11 @@ static void nested_down_write_ref_node(struct fs_node *node,
 	}
 }
 
-static void down_write_ref_node(struct fs_node *node)
+static void down_write_ref_node(struct fs_node *node, bool locked)
 {
 	if (node) {
-		down_write(&node->lock);
+		if (!locked)
+			down_write(&node->lock);
 		refcount_inc(&node->refcount);
 	}
 }
@@ -276,13 +278,14 @@ static void up_read_ref_node(struct fs_node *node)
 	up_read(&node->lock);
 }
 
-static void up_write_ref_node(struct fs_node *node)
+static void up_write_ref_node(struct fs_node *node, bool locked)
 {
 	refcount_dec(&node->refcount);
-	up_write(&node->lock);
+	if (!locked)
+		up_write(&node->lock);
 }
 
-static void tree_put_node(struct fs_node *node)
+static void tree_put_node(struct fs_node *node, bool locked)
 {
 	struct fs_node *parent_node = node->parent;
 
@@ -293,27 +296,27 @@ static void tree_put_node(struct fs_node *node)
 			/* Only root namespace doesn't have parent and we just
 			 * need to free its node.
 			 */
-			down_write_ref_node(parent_node);
+			down_write_ref_node(parent_node, locked);
 			list_del_init(&node->list);
 			if (node->del_sw_func)
 				node->del_sw_func(node);
-			up_write_ref_node(parent_node);
+			up_write_ref_node(parent_node, locked);
 		} else {
 			kfree(node);
 		}
 		node = NULL;
 	}
 	if (!node && parent_node)
-		tree_put_node(parent_node);
+		tree_put_node(parent_node, locked);
 }
 
-static int tree_remove_node(struct fs_node *node)
+static int tree_remove_node(struct fs_node *node, bool locked)
 {
 	if (refcount_read(&node->refcount) > 1) {
 		refcount_dec(&node->refcount);
 		return -EEXIST;
 	}
-	tree_put_node(node);
+	tree_put_node(node, locked);
 	return 0;
 }
 
@@ -397,9 +400,10 @@ static void del_hw_flow_table(struct fs_node *node)
 	fs_get_obj(ft, node);
 	dev = get_dev(&ft->node);
 	root = find_root(&ft->node);
+	trace_mlx5_fs_del_ft(ft);
 
 	if (node->active) {
-		err = root->cmds->destroy_flow_table(dev, ft);
+		err = root->cmds->destroy_flow_table(root, ft);
 		if (err)
 			mlx5_core_warn(dev, "flow steering can't destroy ft\n");
 	}
@@ -418,22 +422,34 @@ static void del_sw_flow_table(struct fs_node *node)
 	kfree(ft);
 }
 
-static void del_sw_hw_rule(struct fs_node *node)
+static void modify_fte(struct fs_fte *fte)
 {
 	struct mlx5_flow_root_namespace *root;
-	struct mlx5_flow_rule *rule;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *fg;
-	struct fs_fte *fte;
-	int modify_mask;
-	struct mlx5_core_dev *dev = get_dev(node);
+	struct mlx5_core_dev *dev;
 	int err;
-	bool update_fte = false;
 
-	fs_get_obj(rule, node);
-	fs_get_obj(fte, rule->node.parent);
 	fs_get_obj(fg, fte->node.parent);
 	fs_get_obj(ft, fg->node.parent);
+	dev = get_dev(&fte->node);
+
+	root = find_root(&ft->node);
+	err = root->cmds->update_fte(root, ft, fg, fte->modify_mask, fte);
+	if (err)
+		mlx5_core_warn(dev,
+			       "%s can't del rule fg id=%d fte_index=%d\n",
+			       __func__, fg->id, fte->index);
+	fte->modify_mask = 0;
+}
+
+static void del_sw_hw_rule(struct fs_node *node)
+{
+	struct mlx5_flow_rule *rule;
+	struct fs_fte *fte;
+
+	fs_get_obj(rule, node);
+	fs_get_obj(fte, rule->node.parent);
 	trace_mlx5_fs_del_rule(rule);
 	if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		mutex_lock(&rule->dest_attr.ft->lock);
@@ -443,27 +459,19 @@ static void del_sw_hw_rule(struct fs_node *node)
 
 	if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER  &&
 	    --fte->dests_size) {
-		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
-			      BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
+		fte->modify_mask |=
+			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
+			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
 		fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
-		update_fte = true;
 		goto out;
 	}
 
 	if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
 	    --fte->dests_size) {
-		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
-		update_fte = true;
+		fte->modify_mask |=
+			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
 	}
 out:
-	root = find_root(&ft->node);
-	if (update_fte && fte->dests_size) {
-		err = root->cmds->update_fte(dev, ft, fg->id, modify_mask, fte);
-		if (err)
-			mlx5_core_warn(dev,
-				       "%s can't del rule fg id=%d fte_index=%d\n",
-				       __func__, fg->id, fte->index);
-	}
 	kfree(rule);
 }
 
@@ -484,11 +492,12 @@ static void del_hw_fte(struct fs_node *node)
 	dev = get_dev(&ft->node);
 	root = find_root(&ft->node);
 	if (node->active) {
-		err = root->cmds->delete_fte(dev, ft, fte);
+		err = root->cmds->delete_fte(root, ft, fte);
 		if (err)
 			mlx5_core_warn(dev,
 				       "flow steering can't delete fte in index %d of flow group id %d\n",
 				       fte->index, fg->id);
+		node->active = 0;
 	}
 }
 
@@ -523,7 +532,7 @@ static void del_hw_flow_group(struct fs_node *node)
 	trace_mlx5_fs_del_fg(fg);
 
 	root = find_root(&ft->node);
-	if (fg->node.active && root->cmds->destroy_flow_group(dev, ft, fg->id))
+	if (fg->node.active && root->cmds->destroy_flow_group(root, ft, fg))
 		mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n",
 			       fg->id, ft->id);
 }
@@ -575,7 +584,7 @@ err_ida_remove:
 }
 
 static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
-				u32 *match_value,
+				const struct mlx5_flow_spec *spec,
 				struct mlx5_flow_act *flow_act)
 {
 	struct mlx5_flow_steering *steering = get_steering(&ft->node);
@@ -585,11 +594,12 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 	if (!fte)
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(fte->val, match_value, sizeof(fte->val));
+	memcpy(fte->val, &spec->match_value, sizeof(fte->val));
 	fte->node.type =  FS_TYPE_FLOW_ENTRY;
 	fte->action = *flow_act;
+	fte->flow_context = spec->flow_context;
 
-	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
+	tree_init_node(&fte->node, NULL, del_sw_fte);
 
 	return fte;
 }
@@ -603,7 +613,7 @@ static void dealloc_flow_group(struct mlx5_flow_steering *steering,
 
 static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steering,
 						u8 match_criteria_enable,
-						void *match_criteria,
+						const void *match_criteria,
 						int start_index,
 						int end_index)
 {
@@ -618,7 +628,8 @@ static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steer
 	if (ret) {
 		kmem_cache_free(steering->fgs_cache, fg);
 		return ERR_PTR(ret);
-}
+	}
+
 	ida_init(&fg->fte_allocator);
 	fg->mask.match_criteria_enable = match_criteria_enable;
 	memcpy(&fg->mask.match_criteria, match_criteria,
@@ -632,7 +643,7 @@ static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steer
 
 static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *ft,
 						       u8 match_criteria_enable,
-						       void *match_criteria,
+						       const void *match_criteria,
 						       int start_index,
 						       int end_index,
 						       struct list_head *prev)
@@ -773,7 +784,7 @@ static int connect_fts_in_prio(struct mlx5_core_dev *dev,
 
 	fs_for_each_ft(iter, prio) {
 		i++;
-		err = root->cmds->modify_flow_table(dev, iter, ft);
+		err = root->cmds->modify_flow_table(root, iter, ft);
 		if (err) {
 			mlx5_core_warn(dev, "Failed to modify flow table %d\n",
 				       iter->id);
@@ -809,7 +820,7 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 	struct mlx5_flow_root_namespace *root = find_root(&prio->node);
 	struct mlx5_ft_underlay_qp *uqp;
 	int min_level = INT_MAX;
-	int err;
+	int err = 0;
 	u32 qpn;
 
 	if (root->root_ft)
@@ -821,11 +832,11 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 	if (list_empty(&root->underlay_qpns)) {
 		/* Don't set any QPN (zero) in case QPN list is empty */
 		qpn = 0;
-		err = root->cmds->update_root_ft(root->dev, ft, qpn, false);
+		err = root->cmds->update_root_ft(root, ft, qpn, false);
 	} else {
 		list_for_each_entry(uqp, &root->underlay_qpns, list) {
 			qpn = uqp->qpn;
-			err = root->cmds->update_root_ft(root->dev, ft,
+			err = root->cmds->update_root_ft(root, ft,
 							 qpn, false);
 			if (err)
 				break;
@@ -855,15 +866,15 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 	fs_get_obj(fte, rule->node.parent);
 	if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
 		return -EINVAL;
-	down_write_ref_node(&fte->node);
+	down_write_ref_node(&fte->node, false);
 	fs_get_obj(fg, fte->node.parent);
 	fs_get_obj(ft, fg->node.parent);
 
 	memcpy(&rule->dest_attr, dest, sizeof(*dest));
 	root = find_root(&ft->node);
-	err = root->cmds->update_fte(get_dev(&ft->node), ft, fg->id,
+	err = root->cmds->update_fte(root, ft, fg,
 				     modify_mask, fte);
-	up_write_ref_node(&fte->node);
+	up_write_ref_node(&fte->node, false);
 
 	return err;
 }
@@ -1003,9 +1014,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table);
 	log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
 	next_ft = find_next_chained_ft(fs_prio);
-	err = root->cmds->create_flow_table(root->dev, ft->vport, ft->op_mod,
-					    ft->type, ft->level, log_table_sz,
-					    next_ft, &ft->id, ft->flags);
+	err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft);
 	if (err)
 		goto free_ft;
 
@@ -1013,15 +1022,16 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	if (err)
 		goto destroy_ft;
 	ft->node.active = true;
-	down_write_ref_node(&fs_prio->node);
+	down_write_ref_node(&fs_prio->node, false);
 	tree_add_node(&ft->node, &fs_prio->node);
 	list_add_flow_table(ft, fs_prio);
 	fs_prio->num_ft++;
-	up_write_ref_node(&fs_prio->node);
+	up_write_ref_node(&fs_prio->node, false);
 	mutex_unlock(&root->chain_lock);
+	trace_mlx5_fs_add_ft(ft);
 	return ft;
 destroy_ft:
-	root->cmds->destroy_flow_table(root->dev, ft);
+	root->cmds->destroy_flow_table(root, ft);
 free_ft:
 	kfree(ft);
 unlock_root:
@@ -1103,24 +1113,23 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 				   start_flow_index);
 	int end_index = MLX5_GET(create_flow_group_in, fg_in,
 				 end_flow_index);
-	struct mlx5_core_dev *dev = get_dev(&ft->node);
 	struct mlx5_flow_group *fg;
 	int err;
 
 	if (ft->autogroup.active)
 		return ERR_PTR(-EPERM);
 
-	down_write_ref_node(&ft->node);
+	down_write_ref_node(&ft->node, false);
 	fg = alloc_insert_flow_group(ft, match_criteria_enable, match_criteria,
 				     start_index, end_index,
 				     ft->node.children.prev);
-	up_write_ref_node(&ft->node);
+	up_write_ref_node(&ft->node, false);
 	if (IS_ERR(fg))
 		return fg;
 
-	err = root->cmds->create_flow_group(dev, ft, fg_in, &fg->id);
+	err = root->cmds->create_flow_group(root, ft, fg_in, fg);
 	if (err) {
-		tree_put_node(&fg->node);
+		tree_put_node(&fg->node, false);
 		return ERR_PTR(err);
 	}
 	trace_mlx5_fs_add_fg(fg);
@@ -1258,11 +1267,9 @@ add_rule_fte(struct fs_fte *fte,
 	fs_get_obj(ft, fg->node.parent);
 	root = find_root(&fg->node);
 	if (!(fte->status & FS_FTE_STATUS_EXISTING))
-		err = root->cmds->create_fte(get_dev(&ft->node),
-					     ft, fg, fte);
+		err = root->cmds->create_fte(root, ft, fg, fte);
 	else
-		err = root->cmds->update_fte(get_dev(&ft->node), ft, fg->id,
-						     modify_mask, fte);
+		err = root->cmds->update_fte(root, ft, fg, modify_mask, fte);
 	if (err)
 		goto free_handle;
 
@@ -1279,7 +1286,7 @@ free_handle:
 }
 
 static struct mlx5_flow_group *alloc_auto_flow_group(struct mlx5_flow_table  *ft,
-						     struct mlx5_flow_spec *spec)
+						     const struct mlx5_flow_spec *spec)
 {
 	struct list_head *prev = &ft->node.children;
 	struct mlx5_flow_group *fg;
@@ -1328,7 +1335,6 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
 				  struct mlx5_flow_group *fg)
 {
 	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
-	struct mlx5_core_dev *dev = get_dev(&ft->node);
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	void *match_criteria_addr;
 	u8 src_esw_owner_mask_on;
@@ -1358,7 +1364,7 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
 	memcpy(match_criteria_addr, fg->mask.match_criteria,
 	       sizeof(fg->mask.match_criteria));
 
-	err = root->cmds->create_flow_group(dev, ft, in, &fg->id);
+	err = root->cmds->create_flow_group(root, ft, in, fg);
 	if (!err) {
 		fg->node.active = true;
 		trace_mlx5_fs_add_fg(fg);
@@ -1375,6 +1381,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 		if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
 		     d1->vport.num == d2->vport.num &&
 		     d1->vport.flags == d2->vport.flags &&
+		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ?
+		      (d1->vport.vhca_id == d2->vport.vhca_id) : true) &&
 		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
 		      (d1->vport.reformat_id == d2->vport.reformat_id) : true)) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
@@ -1423,7 +1431,9 @@ static bool check_conflicting_actions(u32 action1, u32 action2)
 	return false;
 }
 
-static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act *flow_act)
+static int check_conflicting_ftes(struct fs_fte *fte,
+				  const struct mlx5_flow_context *flow_context,
+				  const struct mlx5_flow_act *flow_act)
 {
 	if (check_conflicting_actions(flow_act->action, fte->action.action)) {
 		mlx5_core_warn(get_dev(&fte->node),
@@ -1431,12 +1441,12 @@ static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act
 		return -EEXIST;
 	}
 
-	if ((flow_act->flags & FLOW_ACT_HAS_TAG) &&
-	    fte->action.flow_tag != flow_act->flow_tag) {
+	if ((flow_context->flags & FLOW_CONTEXT_HAS_TAG) &&
+	    fte->flow_context.flow_tag != flow_context->flow_tag) {
 		mlx5_core_warn(get_dev(&fte->node),
 			       "FTE flow tag %u already exists with different flow tag %u\n",
-			       fte->action.flow_tag,
-			       flow_act->flow_tag);
+			       fte->flow_context.flow_tag,
+			       flow_context->flow_tag);
 		return -EEXIST;
 	}
 
@@ -1444,7 +1454,7 @@ static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act
 }
 
 static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
-					    u32 *match_value,
+					    const struct mlx5_flow_spec *spec,
 					    struct mlx5_flow_act *flow_act,
 					    struct mlx5_flow_destination *dest,
 					    int dest_num,
@@ -1455,7 +1465,7 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
 	int i;
 	int ret;
 
-	ret = check_conflicting_ftes(fte, flow_act);
+	ret = check_conflicting_ftes(fte, &spec->flow_context, flow_act);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -1517,10 +1527,10 @@ static void free_match_list(struct match_list_head *head)
 		struct match_list *iter, *match_tmp;
 
 		list_del(&head->first.list);
-		tree_put_node(&head->first.g->node);
+		tree_put_node(&head->first.g->node, false);
 		list_for_each_entry_safe(iter, match_tmp, &head->list,
 					 list) {
-			tree_put_node(&iter->g->node);
+			tree_put_node(&iter->g->node, false);
 			list_del(&iter->list);
 			kfree(iter);
 		}
@@ -1529,7 +1539,7 @@ static void free_match_list(struct match_list_head *head)
 
 static int build_match_list(struct match_list_head *match_head,
 			    struct mlx5_flow_table *ft,
-			    struct mlx5_flow_spec *spec)
+			    const struct mlx5_flow_spec *spec)
 {
 	struct rhlist_head *tmp, *list;
 	struct mlx5_flow_group *g;
@@ -1582,7 +1592,7 @@ static u64 matched_fgs_get_version(struct list_head *match_head)
 
 static struct fs_fte *
 lookup_fte_locked(struct mlx5_flow_group *g,
-		  u32 *match_value,
+		  const u32 *match_value,
 		  bool take_write)
 {
 	struct fs_fte *fte_tmp;
@@ -1597,11 +1607,16 @@ lookup_fte_locked(struct mlx5_flow_group *g,
 		fte_tmp = NULL;
 		goto out;
 	}
+	if (!fte_tmp->node.active) {
+		tree_put_node(&fte_tmp->node, false);
+		fte_tmp = NULL;
+		goto out;
+	}
 
 	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
 out:
 	if (take_write)
-		up_write_ref_node(&g->node);
+		up_write_ref_node(&g->node, false);
 	else
 		up_read_ref_node(&g->node);
 	return fte_tmp;
@@ -1610,7 +1625,7 @@ out:
 static struct mlx5_flow_handle *
 try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		       struct list_head *match_head,
-		       struct mlx5_flow_spec *spec,
+		       const struct mlx5_flow_spec *spec,
 		       struct mlx5_flow_act *flow_act,
 		       struct mlx5_flow_destination *dest,
 		       int dest_num,
@@ -1625,7 +1640,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	u64  version;
 	int err;
 
-	fte = alloc_fte(ft, spec->match_value, flow_act);
+	fte = alloc_fte(ft, spec, flow_act);
 	if (IS_ERR(fte))
 		return  ERR_PTR(-ENOMEM);
 
@@ -1641,10 +1656,9 @@ search_again_locked:
 		fte_tmp = lookup_fte_locked(g, spec->match_value, take_write);
 		if (!fte_tmp)
 			continue;
-		rule = add_rule_fg(g, spec->match_value,
-				   flow_act, dest, dest_num, fte_tmp);
-		up_write_ref_node(&fte_tmp->node);
-		tree_put_node(&fte_tmp->node);
+		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp);
+		up_write_ref_node(&fte_tmp->node, false);
+		tree_put_node(&fte_tmp->node, false);
 		kmem_cache_free(steering->ftes_cache, fte);
 		return rule;
 	}
@@ -1680,7 +1694,7 @@ skip_search:
 
 		err = insert_fte(g, fte);
 		if (err) {
-			up_write_ref_node(&g->node);
+			up_write_ref_node(&g->node, false);
 			if (err == -ENOSPC)
 				continue;
 			kmem_cache_free(steering->ftes_cache, fte);
@@ -1688,11 +1702,10 @@ skip_search:
 		}
 
 		nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
-		up_write_ref_node(&g->node);
-		rule = add_rule_fg(g, spec->match_value,
-				   flow_act, dest, dest_num, fte);
-		up_write_ref_node(&fte->node);
-		tree_put_node(&fte->node);
+		up_write_ref_node(&g->node, false);
+		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
+		up_write_ref_node(&fte->node, false);
+		tree_put_node(&fte->node, false);
 		return rule;
 	}
 	rule = ERR_PTR(-ENOENT);
@@ -1703,7 +1716,7 @@ out:
 
 static struct mlx5_flow_handle *
 _mlx5_add_flow_rules(struct mlx5_flow_table *ft,
-		     struct mlx5_flow_spec *spec,
+		     const struct mlx5_flow_spec *spec,
 		     struct mlx5_flow_act *flow_act,
 		     struct mlx5_flow_destination *dest,
 		     int dest_num)
@@ -1734,7 +1747,7 @@ search_again_locked:
 	err = build_match_list(&match_head, ft, spec);
 	if (err) {
 		if (take_write)
-			up_write_ref_node(&ft->node);
+			up_write_ref_node(&ft->node, false);
 		else
 			up_read_ref_node(&ft->node);
 		return ERR_PTR(err);
@@ -1749,7 +1762,7 @@ search_again_locked:
 	if (!IS_ERR(rule) ||
 	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) {
 		if (take_write)
-			up_write_ref_node(&ft->node);
+			up_write_ref_node(&ft->node, false);
 		return rule;
 	}
 
@@ -1765,18 +1778,18 @@ search_again_locked:
 	g = alloc_auto_flow_group(ft, spec);
 	if (IS_ERR(g)) {
 		rule = ERR_CAST(g);
-		up_write_ref_node(&ft->node);
+		up_write_ref_node(&ft->node, false);
 		return rule;
 	}
 
 	nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
-	up_write_ref_node(&ft->node);
+	up_write_ref_node(&ft->node, false);
 
 	err = create_auto_flow_group(ft, g);
 	if (err)
 		goto err_release_fg;
 
-	fte = alloc_fte(ft, spec->match_value, flow_act);
+	fte = alloc_fte(ft, spec, flow_act);
 	if (IS_ERR(fte)) {
 		err = PTR_ERR(fte);
 		goto err_release_fg;
@@ -1789,17 +1802,16 @@ search_again_locked:
 	}
 
 	nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
-	up_write_ref_node(&g->node);
-	rule = add_rule_fg(g, spec->match_value, flow_act, dest,
-			   dest_num, fte);
-	up_write_ref_node(&fte->node);
-	tree_put_node(&fte->node);
-	tree_put_node(&g->node);
+	up_write_ref_node(&g->node, false);
+	rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
+	up_write_ref_node(&fte->node, false);
+	tree_put_node(&fte->node, false);
+	tree_put_node(&g->node, false);
 	return rule;
 
 err_release_fg:
-	up_write_ref_node(&g->node);
-	tree_put_node(&g->node);
+	up_write_ref_node(&g->node, false);
+	tree_put_node(&g->node, false);
 	return ERR_PTR(err);
 }
 
@@ -1811,7 +1823,7 @@ static bool fwd_next_prio_supported(struct mlx5_flow_table *ft)
 
 struct mlx5_flow_handle *
 mlx5_add_flow_rules(struct mlx5_flow_table *ft,
-		    struct mlx5_flow_spec *spec,
+		    const struct mlx5_flow_spec *spec,
 		    struct mlx5_flow_act *flow_act,
 		    struct mlx5_flow_destination *dest,
 		    int num_dest)
@@ -1862,10 +1874,33 @@ EXPORT_SYMBOL(mlx5_add_flow_rules);
 
 void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 {
+	struct fs_fte *fte;
 	int i;
 
+	/* In order to consolidate the HW changes we lock the FTE for other
+	 * changes, and increase its refcount, in order not to perform the
+	 * "del" functions of the FTE. Will handle them here.
+	 * The removal of the rules is done under locked FTE.
+	 * After removing all the handle's rules, if there are remaining
+	 * rules, it means we just need to modify the FTE in FW, and
+	 * unlock/decrease the refcount we increased before.
+	 * Otherwise, it means the FTE should be deleted. First delete the
+	 * FTE in FW. Then, unlock the FTE, and proceed the tree_put_node of
+	 * the FTE, which will handle the last decrease of the refcount, as
+	 * well as required handling of its parent.
+	 */
+	fs_get_obj(fte, handle->rule[0]->node.parent);
+	down_write_ref_node(&fte->node, false);
 	for (i = handle->num_rules - 1; i >= 0; i--)
-		tree_remove_node(&handle->rule[i]->node);
+		tree_remove_node(&handle->rule[i]->node, true);
+	if (fte->modify_mask && fte->dests_size) {
+		modify_fte(fte);
+		up_write_ref_node(&fte->node, false);
+	} else {
+		del_hw_fte(&fte->node);
+		up_write(&fte->node.lock);
+		tree_put_node(&fte->node, false);
+	}
 	kfree(handle);
 }
 EXPORT_SYMBOL(mlx5_del_flow_rules);
@@ -1902,12 +1937,12 @@ static int update_root_ft_destroy(struct mlx5_flow_table *ft)
 	if (list_empty(&root->underlay_qpns)) {
 		/* Don't set any QPN (zero) in case QPN list is empty */
 		qpn = 0;
-		err = root->cmds->update_root_ft(root->dev, new_root_ft,
+		err = root->cmds->update_root_ft(root, new_root_ft,
 						 qpn, false);
 	} else {
 		list_for_each_entry(uqp, &root->underlay_qpns, list) {
 			qpn = uqp->qpn;
-			err = root->cmds->update_root_ft(root->dev,
+			err = root->cmds->update_root_ft(root,
 							 new_root_ft, qpn,
 							 false);
 			if (err)
@@ -1968,7 +2003,7 @@ int mlx5_destroy_flow_table(struct mlx5_flow_table *ft)
 		mutex_unlock(&root->chain_lock);
 		return err;
 	}
-	if (tree_remove_node(&ft->node))
+	if (tree_remove_node(&ft->node, false))
 		mlx5_core_warn(get_dev(&ft->node), "Flow table %d wasn't destroyed, refcount > 1\n",
 			       ft->id);
 	mutex_unlock(&root->chain_lock);
@@ -1979,7 +2014,7 @@ EXPORT_SYMBOL(mlx5_destroy_flow_table);
 
 void mlx5_destroy_flow_group(struct mlx5_flow_group *fg)
 {
-	if (tree_remove_node(&fg->node))
+	if (tree_remove_node(&fg->node, false))
 		mlx5_core_warn(get_dev(&fg->node), "Flow group %d wasn't destroyed, refcount > 1\n",
 			       fg->id);
 }
@@ -2021,6 +2056,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		if (steering->sniffer_tx_root_ns)
 			return &steering->sniffer_tx_root_ns->ns;
 		return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_RX:
+		if (steering->rdma_rx_root_ns)
+			return &steering->rdma_rx_root_ns->ns;
+		return NULL;
 	default:
 		break;
 	}
@@ -2053,7 +2092,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_d
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
 
-	if (!steering || vport >= MLX5_TOTAL_VPORTS(dev))
+	if (!steering || vport >= mlx5_eswitch_get_total_vports(dev))
 		return NULL;
 
 	switch (type) {
@@ -2245,7 +2284,7 @@ static struct mlx5_flow_root_namespace
 		cmds = mlx5_fs_cmd_get_default_ipsec_fpga_cmds(table_type);
 
 	/* Create the root namespace */
-	root_ns = kvzalloc(sizeof(*root_ns), GFP_KERNEL);
+	root_ns = kzalloc(sizeof(*root_ns), GFP_KERNEL);
 	if (!root_ns)
 		return NULL;
 
@@ -2363,8 +2402,8 @@ static void clean_tree(struct fs_node *node)
 		tree_get_node(node);
 		list_for_each_entry_safe(iter, temp, &node->children, list)
 			clean_tree(iter);
-		tree_put_node(node);
-		tree_remove_node(node);
+		tree_put_node(node, false);
+		tree_remove_node(node, false);
 	}
 }
 
@@ -2384,10 +2423,11 @@ static void cleanup_egress_acls_root_ns(struct mlx5_core_dev *dev)
 	if (!steering->esw_egress_root_ns)
 		return;
 
-	for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++)
+	for (i = 0; i < mlx5_eswitch_get_total_vports(dev); i++)
 		cleanup_root_ns(steering->esw_egress_root_ns[i]);
 
 	kfree(steering->esw_egress_root_ns);
+	steering->esw_egress_root_ns = NULL;
 }
 
 static void cleanup_ingress_acls_root_ns(struct mlx5_core_dev *dev)
@@ -2398,10 +2438,11 @@ static void cleanup_ingress_acls_root_ns(struct mlx5_core_dev *dev)
 	if (!steering->esw_ingress_root_ns)
 		return;
 
-	for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++)
+	for (i = 0; i < mlx5_eswitch_get_total_vports(dev); i++)
 		cleanup_root_ns(steering->esw_ingress_root_ns[i]);
 
 	kfree(steering->esw_ingress_root_ns);
+	steering->esw_ingress_root_ns = NULL;
 }
 
 void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
@@ -2417,6 +2458,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 	steering->fdb_sub_ns = NULL;
 	cleanup_root_ns(steering->sniffer_rx_root_ns);
 	cleanup_root_ns(steering->sniffer_tx_root_ns);
+	cleanup_root_ns(steering->rdma_rx_root_ns);
 	cleanup_root_ns(steering->egress_root_ns);
 	mlx5_cleanup_fc_stats(dev);
 	kmem_cache_destroy(steering->ftes_cache);
@@ -2434,11 +2476,7 @@ static int init_sniffer_tx_root_ns(struct mlx5_flow_steering *steering)
 
 	/* Create single prio */
 	prio = fs_create_prio(&steering->sniffer_tx_root_ns->ns, 0, 1);
-	if (IS_ERR(prio)) {
-		cleanup_root_ns(steering->sniffer_tx_root_ns);
-		return PTR_ERR(prio);
-	}
-	return 0;
+	return PTR_ERR_OR_ZERO(prio);
 }
 
 static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering)
@@ -2451,13 +2489,24 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering)
 
 	/* Create single prio */
 	prio = fs_create_prio(&steering->sniffer_rx_root_ns->ns, 0, 1);
-	if (IS_ERR(prio)) {
-		cleanup_root_ns(steering->sniffer_rx_root_ns);
-		return PTR_ERR(prio);
-	}
-	return 0;
+	return PTR_ERR_OR_ZERO(prio);
 }
 
+static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct fs_prio *prio;
+
+	steering->rdma_rx_root_ns = create_root_ns(steering, FS_FT_RDMA_RX);
+	if (!steering->rdma_rx_root_ns)
+		return -ENOMEM;
+
+	steering->rdma_rx_root_ns->def_miss_action =
+		MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN;
+
+	/* Create single prio */
+	prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1);
+	return PTR_ERR_OR_ZERO(prio);
+}
 static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 {
 	struct mlx5_flow_namespace *ns;
@@ -2477,8 +2526,16 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 	if (!steering->fdb_sub_ns)
 		return -ENOMEM;
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH,
+				  1);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1);
-	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, 0,
+	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns,
+					  FDB_FAST_PATH,
 					  levels);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
@@ -2503,7 +2560,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 		steering->fdb_sub_ns[chain] = ns;
 	}
 
-	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, 1, 1);
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
 		goto out_err;
@@ -2549,16 +2606,18 @@ static int init_ingress_acl_root_ns(struct mlx5_flow_steering *steering, int vpo
 static int init_egress_acls_root_ns(struct mlx5_core_dev *dev)
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
+	int total_vports = mlx5_eswitch_get_total_vports(dev);
 	int err;
 	int i;
 
-	steering->esw_egress_root_ns = kcalloc(MLX5_TOTAL_VPORTS(dev),
-					       sizeof(*steering->esw_egress_root_ns),
-					       GFP_KERNEL);
+	steering->esw_egress_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->esw_egress_root_ns),
+				GFP_KERNEL);
 	if (!steering->esw_egress_root_ns)
 		return -ENOMEM;
 
-	for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++) {
+	for (i = 0; i < total_vports; i++) {
 		err = init_egress_acl_root_ns(steering, i);
 		if (err)
 			goto cleanup_root_ns;
@@ -2570,22 +2629,25 @@ cleanup_root_ns:
 	for (i--; i >= 0; i--)
 		cleanup_root_ns(steering->esw_egress_root_ns[i]);
 	kfree(steering->esw_egress_root_ns);
+	steering->esw_egress_root_ns = NULL;
 	return err;
 }
 
 static int init_ingress_acls_root_ns(struct mlx5_core_dev *dev)
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
+	int total_vports = mlx5_eswitch_get_total_vports(dev);
 	int err;
 	int i;
 
-	steering->esw_ingress_root_ns = kcalloc(MLX5_TOTAL_VPORTS(dev),
-						sizeof(*steering->esw_ingress_root_ns),
-						GFP_KERNEL);
+	steering->esw_ingress_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->esw_ingress_root_ns),
+				GFP_KERNEL);
 	if (!steering->esw_ingress_root_ns)
 		return -ENOMEM;
 
-	for (i = 0; i < MLX5_TOTAL_VPORTS(dev); i++) {
+	for (i = 0; i < total_vports; i++) {
 		err = init_ingress_acl_root_ns(steering, i);
 		if (err)
 			goto cleanup_root_ns;
@@ -2597,6 +2659,7 @@ cleanup_root_ns:
 	for (i--; i >= 0; i--)
 		cleanup_root_ns(steering->esw_ingress_root_ns[i]);
 	kfree(steering->esw_ingress_root_ns);
+	steering->esw_ingress_root_ns = NULL;
 	return err;
 }
 
@@ -2686,6 +2749,13 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
+	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
+	    MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) {
+		err = init_rdma_rx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
 	if (MLX5_IPSEC_DEV(dev) || MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) {
 		err = init_egress_root_ns(steering);
 		if (err)
@@ -2715,7 +2785,7 @@ int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
 		goto update_ft_fail;
 	}
 
-	err = root->cmds->update_root_ft(dev, root->root_ft, underlay_qpn,
+	err = root->cmds->update_root_ft(root, root->root_ft, underlay_qpn,
 					 false);
 	if (err) {
 		mlx5_core_warn(dev, "Failed adding underlay QPN (%u) to root FT err(%d)\n",
@@ -2759,7 +2829,7 @@ int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
 		goto out;
 	}
 
-	err = root->cmds->update_root_ft(dev, root->root_ft, underlay_qpn,
+	err = root->cmds->update_root_ft(root, root->root_ft, underlay_qpn,
 					 true);
 	if (err)
 		mlx5_core_warn(dev, "Failed removing underlay QPN (%u) from root FT err(%d)\n",
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 2dc86347af58..c48c382f926f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -67,6 +67,7 @@ enum fs_flow_table_type {
 	FS_FT_FDB             = 0X4,
 	FS_FT_SNIFFER_RX	= 0X5,
 	FS_FT_SNIFFER_TX	= 0X6,
+	FS_FT_RDMA_RX		= 0X7,
 	FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX,
 };
 
@@ -90,6 +91,7 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace **esw_ingress_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_tx_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_rx_root_ns;
+	struct mlx5_flow_root_namespace	*rdma_rx_root_ns;
 	struct mlx5_flow_root_namespace	*egress_root_ns;
 };
 
@@ -150,7 +152,7 @@ struct mlx5_ft_underlay_qp {
 	u32 qpn;
 };
 
-#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_800
+#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_a00
 /* Calculate the fte_match_param length and without the reserved length.
  * Make sure the reserved field is the last.
  */
@@ -168,10 +170,12 @@ struct fs_fte {
 	u32				val[MLX5_ST_SZ_DW_MATCH_PARAM];
 	u32				dests_size;
 	u32				index;
+	struct mlx5_flow_context	flow_context;
 	struct mlx5_flow_act		action;
 	enum fs_fte_status		status;
 	struct mlx5_fc			*counter;
 	struct rhash_head		hash;
+	int				modify_mask;
 };
 
 /* Type of children is mlx5_flow_table/namespace */
@@ -215,6 +219,7 @@ struct mlx5_flow_root_namespace {
 	struct mutex			chain_lock;
 	struct list_head		underlay_qpns;
 	const struct mlx5_flow_cmds	*cmds;
+	enum mlx5_flow_table_miss_action def_miss_action;
 };
 
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index c6c28f56aa29..b3762123a69c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -102,13 +102,15 @@ static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev,
 	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
 	unsigned long next_id = (unsigned long)id + 1;
 	struct mlx5_fc *counter;
+	unsigned long tmp;
 
 	rcu_read_lock();
 	/* skip counters that are in idr, but not yet in counters list */
-	while ((counter = idr_get_next_ul(&fc_stats->counters_idr,
-					  &next_id)) != NULL &&
-	       list_empty(&counter->list))
-		next_id++;
+	idr_for_each_entry_continue_ul(&fc_stats->counters_idr,
+				       counter, tmp, next_id) {
+		if (!list_empty(&counter->list))
+			break;
+	}
 	rcu_read_unlock();
 
 	return counter ? &counter->list : &fc_stats->counters;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 1ab6f7e3bec6..a19790dee7b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -37,6 +37,37 @@
 #include "mlx5_core.h"
 #include "../../mlxfw/mlxfw.h"
 
+enum {
+	MCQS_IDENTIFIER_BOOT_IMG	= 0x1,
+	MCQS_IDENTIFIER_OEM_NVCONFIG	= 0x4,
+	MCQS_IDENTIFIER_MLNX_NVCONFIG	= 0x5,
+	MCQS_IDENTIFIER_CS_TOKEN	= 0x6,
+	MCQS_IDENTIFIER_DBG_TOKEN	= 0x7,
+	MCQS_IDENTIFIER_GEARBOX		= 0xA,
+};
+
+enum {
+	MCQS_UPDATE_STATE_IDLE,
+	MCQS_UPDATE_STATE_IN_PROGRESS,
+	MCQS_UPDATE_STATE_APPLIED,
+	MCQS_UPDATE_STATE_ACTIVE,
+	MCQS_UPDATE_STATE_ACTIVE_PENDING_RESET,
+	MCQS_UPDATE_STATE_FAILED,
+	MCQS_UPDATE_STATE_CANCELED,
+	MCQS_UPDATE_STATE_BUSY,
+};
+
+enum {
+	MCQI_INFO_TYPE_CAPABILITIES	  = 0x0,
+	MCQI_INFO_TYPE_VERSION		  = 0x1,
+	MCQI_INFO_TYPE_ACTIVATION_METHOD  = 0x5,
+};
+
+enum {
+	MCQI_FW_RUNNING_VERSION = 0,
+	MCQI_FW_STORED_VERSION  = 1,
+};
+
 static int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev, u32 *out,
 				  int outlen)
 {
@@ -202,6 +233,18 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, event_cap)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_EVENT);
+		if (err)
+			return err;
+	}
+
+	if (MLX5_CAP_GEN(dev, tls)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_TLS);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -392,33 +435,49 @@ static int mlx5_reg_mcda_set(struct mlx5_core_dev *dev,
 }
 
 static int mlx5_reg_mcqi_query(struct mlx5_core_dev *dev,
-			       u16 component_index,
-			       u32 *max_component_size,
-			       u8 *log_mcda_word_size,
-			       u16 *mcda_max_write_size)
+			       u16 component_index, bool read_pending,
+			       u8 info_type, u16 data_size, void *mcqi_data)
 {
-	u32 out[MLX5_ST_SZ_DW(mcqi_reg) + MLX5_ST_SZ_DW(mcqi_cap)];
-	int offset = MLX5_ST_SZ_DW(mcqi_reg);
-	u32 in[MLX5_ST_SZ_DW(mcqi_reg)];
+	u32 out[MLX5_ST_SZ_DW(mcqi_reg) + MLX5_UN_SZ_DW(mcqi_reg_data)] = {};
+	u32 in[MLX5_ST_SZ_DW(mcqi_reg)] = {};
+	void *data;
 	int err;
 
-	memset(in, 0, sizeof(in));
-	memset(out, 0, sizeof(out));
-
 	MLX5_SET(mcqi_reg, in, component_index, component_index);
-	MLX5_SET(mcqi_reg, in, data_size, MLX5_ST_SZ_BYTES(mcqi_cap));
+	MLX5_SET(mcqi_reg, in, read_pending_component, read_pending);
+	MLX5_SET(mcqi_reg, in, info_type, info_type);
+	MLX5_SET(mcqi_reg, in, data_size, data_size);
 
 	err = mlx5_core_access_reg(dev, in, sizeof(in), out,
-				   sizeof(out), MLX5_REG_MCQI, 0, 0);
+				   MLX5_ST_SZ_BYTES(mcqi_reg) + data_size,
+				   MLX5_REG_MCQI, 0, 0);
 	if (err)
-		goto out;
+		return err;
 
-	*max_component_size = MLX5_GET(mcqi_cap, out + offset, max_component_size);
-	*log_mcda_word_size = MLX5_GET(mcqi_cap, out + offset, log_mcda_word_size);
-	*mcda_max_write_size = MLX5_GET(mcqi_cap, out + offset, mcda_max_write_size);
+	data = MLX5_ADDR_OF(mcqi_reg, out, data);
+	memcpy(mcqi_data, data, data_size);
 
-out:
-	return err;
+	return 0;
+}
+
+static int mlx5_reg_mcqi_caps_query(struct mlx5_core_dev *dev, u16 component_index,
+				    u32 *max_component_size, u8 *log_mcda_word_size,
+				    u16 *mcda_max_write_size)
+{
+	u32 mcqi_reg[MLX5_ST_SZ_DW(mcqi_cap)] = {};
+	int err;
+
+	err = mlx5_reg_mcqi_query(dev, component_index, 0,
+				  MCQI_INFO_TYPE_CAPABILITIES,
+				  MLX5_ST_SZ_BYTES(mcqi_cap), mcqi_reg);
+	if (err)
+		return err;
+
+	*max_component_size = MLX5_GET(mcqi_cap, mcqi_reg, max_component_size);
+	*log_mcda_word_size = MLX5_GET(mcqi_cap, mcqi_reg, log_mcda_word_size);
+	*mcda_max_write_size = MLX5_GET(mcqi_cap, mcqi_reg, mcda_max_write_size);
+
+	return 0;
 }
 
 struct mlx5_mlxfw_dev {
@@ -434,8 +493,13 @@ static int mlx5_component_query(struct mlxfw_dev *mlxfw_dev,
 		container_of(mlxfw_dev, struct mlx5_mlxfw_dev, mlxfw_dev);
 	struct mlx5_core_dev *dev = mlx5_mlxfw_dev->mlx5_core_dev;
 
-	return mlx5_reg_mcqi_query(dev, component_index, p_max_size,
-				   p_align_bits, p_max_write_size);
+	if (!MLX5_CAP_GEN(dev, mcam_reg) || !MLX5_CAP_MCAM_REG(dev, mcqi)) {
+		mlx5_core_warn(dev, "caps query isn't supported by running FW\n");
+		return -EOPNOTSUPP;
+	}
+
+	return mlx5_reg_mcqi_caps_query(dev, component_index, p_max_size,
+					p_align_bits, p_max_write_size);
 }
 
 static int mlx5_fsm_lock(struct mlxfw_dev *mlxfw_dev, u32 *fwhandle)
@@ -552,7 +616,8 @@ static const struct mlxfw_dev_ops mlx5_mlxfw_dev_ops = {
 };
 
 int mlx5_firmware_flash(struct mlx5_core_dev *dev,
-			const struct firmware *firmware)
+			const struct firmware *firmware,
+			struct netlink_ext_ack *extack)
 {
 	struct mlx5_mlxfw_dev mlx5_mlxfw_dev = {
 		.mlxfw_dev = {
@@ -571,5 +636,133 @@ int mlx5_firmware_flash(struct mlx5_core_dev *dev,
 		return -EOPNOTSUPP;
 	}
 
-	return mlxfw_firmware_flash(&mlx5_mlxfw_dev.mlxfw_dev, firmware);
+	return mlxfw_firmware_flash(&mlx5_mlxfw_dev.mlxfw_dev,
+				    firmware, extack);
+}
+
+static int mlx5_reg_mcqi_version_query(struct mlx5_core_dev *dev,
+				       u16 component_index, bool read_pending,
+				       u32 *mcqi_version_out)
+{
+	return mlx5_reg_mcqi_query(dev, component_index, read_pending,
+				   MCQI_INFO_TYPE_VERSION,
+				   MLX5_ST_SZ_BYTES(mcqi_version),
+				   mcqi_version_out);
+}
+
+static int mlx5_reg_mcqs_query(struct mlx5_core_dev *dev, u32 *out,
+			       u16 component_index)
+{
+	u8 out_sz = MLX5_ST_SZ_BYTES(mcqs_reg);
+	u32 in[MLX5_ST_SZ_DW(mcqs_reg)] = {};
+	int err;
+
+	memset(out, 0, out_sz);
+
+	MLX5_SET(mcqs_reg, in, component_index, component_index);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+				   out_sz, MLX5_REG_MCQS, 0, 0);
+	return err;
+}
+
+/* scans component index sequentially, to find the boot img index */
+static int mlx5_get_boot_img_component_index(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(mcqs_reg)] = {};
+	u16 identifier, component_idx = 0;
+	bool quit;
+	int err;
+
+	do {
+		err = mlx5_reg_mcqs_query(dev, out, component_idx);
+		if (err)
+			return err;
+
+		identifier = MLX5_GET(mcqs_reg, out, identifier);
+		quit = !!MLX5_GET(mcqs_reg, out, last_index_flag);
+		quit |= identifier == MCQS_IDENTIFIER_BOOT_IMG;
+	} while (!quit && ++component_idx);
+
+	if (identifier != MCQS_IDENTIFIER_BOOT_IMG) {
+		mlx5_core_warn(dev, "mcqs: can't find boot_img component ix, last scanned idx %d\n",
+			       component_idx);
+		return -EOPNOTSUPP;
+	}
+
+	return component_idx;
+}
+
+static int
+mlx5_fw_image_pending(struct mlx5_core_dev *dev,
+		      int component_index,
+		      bool *pending_version_exists)
+{
+	u32 out[MLX5_ST_SZ_DW(mcqs_reg)];
+	u8 component_update_state;
+	int err;
+
+	err = mlx5_reg_mcqs_query(dev, out, component_index);
+	if (err)
+		return err;
+
+	component_update_state = MLX5_GET(mcqs_reg, out, component_update_state);
+
+	if (component_update_state == MCQS_UPDATE_STATE_IDLE) {
+		*pending_version_exists = false;
+	} else if (component_update_state == MCQS_UPDATE_STATE_ACTIVE_PENDING_RESET) {
+		*pending_version_exists = true;
+	} else {
+		mlx5_core_warn(dev,
+			       "mcqs: can't read pending fw version while fw state is %d\n",
+			       component_update_state);
+		return -ENODATA;
+	}
+	return 0;
+}
+
+int mlx5_fw_version_query(struct mlx5_core_dev *dev,
+			  u32 *running_ver, u32 *pending_ver)
+{
+	u32 reg_mcqi_version[MLX5_ST_SZ_DW(mcqi_version)] = {};
+	bool pending_version_exists;
+	int component_index;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, mcam_reg) || !MLX5_CAP_MCAM_REG(dev, mcqi) ||
+	    !MLX5_CAP_MCAM_REG(dev, mcqs)) {
+		mlx5_core_warn(dev, "fw query isn't supported by the FW\n");
+		return -EOPNOTSUPP;
+	}
+
+	component_index = mlx5_get_boot_img_component_index(dev);
+	if (component_index < 0)
+		return component_index;
+
+	err = mlx5_reg_mcqi_version_query(dev, component_index,
+					  MCQI_FW_RUNNING_VERSION,
+					  reg_mcqi_version);
+	if (err)
+		return err;
+
+	*running_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version);
+
+	err = mlx5_fw_image_pending(dev, component_index, &pending_version_exists);
+	if (err)
+		return err;
+
+	if (!pending_version_exists) {
+		*pending_ver = 0;
+		return 0;
+	}
+
+	err = mlx5_reg_mcqi_version_query(dev, component_index,
+					  MCQI_FW_STORED_VERSION,
+					  reg_mcqi_version);
+	if (err)
+		return err;
+
+	*pending_ver = MLX5_GET(mcqi_version, reg_mcqi_version, version);
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 196c07383082..2fe6923f7ce0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -40,6 +40,8 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/mlx5.h"
+#include "lib/pci_vsc.h"
+#include "diag/fw_tracer.h"
 
 enum {
 	MLX5_HEALTH_POLL_INTERVAL	= 2 * HZ,
@@ -62,12 +64,20 @@ enum {
 
 enum {
 	MLX5_DROP_NEW_HEALTH_WORK,
-	MLX5_DROP_NEW_RECOVERY_WORK,
+};
+
+enum  {
+	MLX5_SENSOR_NO_ERR		= 0,
+	MLX5_SENSOR_PCI_COMM_ERR	= 1,
+	MLX5_SENSOR_PCI_ERR		= 2,
+	MLX5_SENSOR_NIC_DISABLED	= 3,
+	MLX5_SENSOR_NIC_SW_RESET	= 4,
+	MLX5_SENSOR_FW_SYND_RFR		= 5,
 };
 
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev)
 {
-	return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3;
+	return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 7;
 }
 
 void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state)
@@ -80,18 +90,105 @@ void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state)
 		    &dev->iseg->cmdq_addr_l_sz);
 }
 
-static int in_fatal(struct mlx5_core_dev *dev)
+static bool sensor_pci_not_working(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
 
+	/* Offline PCI reads return 0xffffffff */
+	return (ioread32be(&h->fw_ver) == 0xffffffff);
+}
+
+static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+	struct health_buffer __iomem *h = health->health;
+	u32 rfr = ioread32be(&h->rfr) >> MLX5_RFR_OFFSET;
+	u8 synd = ioread8(&h->synd);
+
+	if (rfr && synd)
+		mlx5_core_dbg(dev, "FW requests reset, synd: %d\n", synd);
+	return rfr && synd;
+}
+
+static u32 check_fatal_sensors(struct mlx5_core_dev *dev)
+{
+	if (sensor_pci_not_working(dev))
+		return MLX5_SENSOR_PCI_COMM_ERR;
+	if (pci_channel_offline(dev->pdev))
+		return MLX5_SENSOR_PCI_ERR;
 	if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
-		return 1;
+		return MLX5_SENSOR_NIC_DISABLED;
+	if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_SW_RESET)
+		return MLX5_SENSOR_NIC_SW_RESET;
+	if (sensor_fw_synd_rfr(dev))
+		return MLX5_SENSOR_FW_SYND_RFR;
 
-	if (ioread32be(&h->fw_ver) == 0xffffffff)
-		return 1;
+	return MLX5_SENSOR_NO_ERR;
+}
 
-	return 0;
+static int lock_sem_sw_reset(struct mlx5_core_dev *dev, bool lock)
+{
+	enum mlx5_vsc_state state;
+	int ret;
+
+	if (!mlx5_core_is_pf(dev))
+		return -EBUSY;
+
+	/* Try to lock GW access, this stage doesn't return
+	 * EBUSY because locked GW does not mean that other PF
+	 * already started the reset.
+	 */
+	ret = mlx5_vsc_gw_lock(dev);
+	if (ret == -EBUSY)
+		return -EINVAL;
+	if (ret)
+		return ret;
+
+	state = lock ? MLX5_VSC_LOCK : MLX5_VSC_UNLOCK;
+	/* At this stage, if the return status == EBUSY, then we know
+	 * for sure that another PF started the reset, so don't allow
+	 * another reset.
+	 */
+	ret = mlx5_vsc_sem_set_space(dev, MLX5_SEMAPHORE_SW_RESET, state);
+	if (ret)
+		mlx5_core_warn(dev, "Failed to lock SW reset semaphore\n");
+
+	/* Unlock GW access */
+	mlx5_vsc_gw_unlock(dev);
+
+	return ret;
+}
+
+static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
+{
+	bool supported = (ioread32be(&dev->iseg->initializing) >>
+			  MLX5_FW_RESET_SUPPORTED_OFFSET) & 1;
+	u32 fatal_error;
+
+	if (!supported)
+		return false;
+
+	/* The reset only needs to be issued by one PF. The health buffer is
+	 * shared between all functions, and will be cleared during a reset.
+	 * Check again to avoid a redundant 2nd reset. If the fatal erros was
+	 * PCI related a reset won't help.
+	 */
+	fatal_error = check_fatal_sensors(dev);
+	if (fatal_error == MLX5_SENSOR_PCI_COMM_ERR ||
+	    fatal_error == MLX5_SENSOR_NIC_DISABLED ||
+	    fatal_error == MLX5_SENSOR_NIC_SW_RESET) {
+		mlx5_core_warn(dev, "Not issuing FW reset. Either it's already done or won't help.");
+		return false;
+	}
+
+	mlx5_core_warn(dev, "Issuing FW Reset\n");
+	/* Write the NIC interface field to initiate the reset, the command
+	 * interface address also resides here, don't overwrite it.
+	 */
+	mlx5_set_nic_state(dev, MLX5_NIC_IFC_SW_RESET);
+
+	return true;
 }
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
@@ -99,14 +196,65 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	mutex_lock(&dev->intf_state_mutex);
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto unlock;
+	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
+		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		goto unlock;
+	}
 
-	mlx5_core_err(dev, "start\n");
-	if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) {
+	if (check_fatal_sensors(dev) || force) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-		mlx5_cmd_trigger_completions(dev);
+		mlx5_cmd_flush(dev);
 	}
 
 	mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1);
+unlock:
+	mutex_unlock(&dev->intf_state_mutex);
+}
+
+#define MLX5_CRDUMP_WAIT_MS	60000
+#define MLX5_FW_RESET_WAIT_MS	1000
+void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
+{
+	unsigned long end, delay_ms = MLX5_FW_RESET_WAIT_MS;
+	int lock = -EBUSY;
+
+	mutex_lock(&dev->intf_state_mutex);
+	if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		goto unlock;
+
+	mlx5_core_err(dev, "start\n");
+
+	if (check_fatal_sensors(dev) == MLX5_SENSOR_FW_SYND_RFR) {
+		/* Get cr-dump and reset FW semaphore */
+		lock = lock_sem_sw_reset(dev, true);
+
+		if (lock == -EBUSY) {
+			delay_ms = MLX5_CRDUMP_WAIT_MS;
+			goto recover_from_sw_reset;
+		}
+		/* Execute SW reset */
+		reset_fw_if_needed(dev);
+	}
+
+recover_from_sw_reset:
+	/* Recover from SW reset */
+	end = jiffies + msecs_to_jiffies(delay_ms);
+	do {
+		if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
+			break;
+
+		cond_resched();
+	} while (!time_after(jiffies, end));
+
+	if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) {
+		dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n",
+			mlx5_get_nic_state(dev), delay_ms);
+	}
+
+	/* Release FW semaphore if you are the lock owner */
+	if (!lock)
+		lock_sem_sw_reset(dev, false);
+
 	mlx5_core_err(dev, "end\n");
 
 unlock:
@@ -129,6 +277,20 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 	case MLX5_NIC_IFC_NO_DRAM_NIC:
 		mlx5_core_warn(dev, "Expected to see disabled NIC but it is no dram nic\n");
 		break;
+
+	case MLX5_NIC_IFC_SW_RESET:
+		/* The IFC mode field is 3 bits, so it will read 0x7 in 2 cases:
+		 * 1. PCI has been disabled (ie. PCI-AER, PF driver unloaded
+		 *    and this is a VF), this is not recoverable by SW reset.
+		 *    Logging of this is handled elsewhere.
+		 * 2. FW reset has been issued by another function, driver can
+		 *    be reloaded to recover after the mode switches to
+		 *    MLX5_NIC_IFC_DISABLED.
+		 */
+		if (dev->priv.health.fatal_error != MLX5_SENSOR_PCI_COMM_ERR)
+			mlx5_core_warn(dev, "NIC SW reset in progress\n");
+		break;
+
 	default:
 		mlx5_core_warn(dev, "Expected to see disabled NIC but it is has invalid value %d\n",
 			       nic_interface);
@@ -137,52 +299,32 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 	mlx5_disable_device(dev);
 }
 
-static void health_recover(struct work_struct *work)
-{
-	struct mlx5_core_health *health;
-	struct delayed_work *dwork;
-	struct mlx5_core_dev *dev;
-	struct mlx5_priv *priv;
-	u8 nic_state;
-
-	dwork = container_of(work, struct delayed_work, work);
-	health = container_of(dwork, struct mlx5_core_health, recover_work);
-	priv = container_of(health, struct mlx5_priv, health);
-	dev = container_of(priv, struct mlx5_core_dev, priv);
-
-	nic_state = mlx5_get_nic_state(dev);
-	if (nic_state == MLX5_NIC_IFC_INVALID) {
-		dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n");
-		return;
-	}
-
-	dev_err(&dev->pdev->dev, "starting health recovery flow\n");
-	mlx5_recover_device(dev);
-}
-
 /* How much time to wait until health resetting the driver (in msecs) */
-#define MLX5_RECOVERY_DELAY_MSECS 60000
-static void health_care(struct work_struct *work)
+#define MLX5_RECOVERY_WAIT_MSECS 60000
+static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
 {
-	unsigned long recover_delay = msecs_to_jiffies(MLX5_RECOVERY_DELAY_MSECS);
-	struct mlx5_core_health *health;
-	struct mlx5_core_dev *dev;
-	struct mlx5_priv *priv;
-	unsigned long flags;
+	unsigned long end;
 
-	health = container_of(work, struct mlx5_core_health, work);
-	priv = container_of(health, struct mlx5_priv, health);
-	dev = container_of(priv, struct mlx5_core_dev, priv);
 	mlx5_core_warn(dev, "handling bad device here\n");
 	mlx5_handle_bad_state(dev);
+	end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS);
+	while (sensor_pci_not_working(dev)) {
+		if (time_after(jiffies, end)) {
+			mlx5_core_err(dev,
+				      "health recovery flow aborted, PCI reads still not working\n");
+			return -EIO;
+		}
+		msleep(100);
+	}
 
-	spin_lock_irqsave(&health->wq_lock, flags);
-	if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags))
-		schedule_delayed_work(&health->recover_work, recover_delay);
-	else
-		dev_err(&dev->pdev->dev,
-			"new health works are not permitted at this stage\n");
-	spin_unlock_irqrestore(&health->wq_lock, flags);
+	mlx5_core_err(dev, "starting health recovery flow\n");
+	mlx5_recover_device(dev);
+	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state) ||
+	    check_fatal_sensors(dev)) {
+		mlx5_core_err(dev, "health recovery failed\n");
+		return -EIO;
+	}
+	return 0;
 }
 
 static const char *hsynd_str(u8 synd)
@@ -228,18 +370,298 @@ static void print_health_info(struct mlx5_core_dev *dev)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(h->assert_var); i++)
-		dev_err(&dev->pdev->dev, "assert_var[%d] 0x%08x\n", i, ioread32be(h->assert_var + i));
+		mlx5_core_err(dev, "assert_var[%d] 0x%08x\n", i,
+			      ioread32be(h->assert_var + i));
 
-	dev_err(&dev->pdev->dev, "assert_exit_ptr 0x%08x\n", ioread32be(&h->assert_exit_ptr));
-	dev_err(&dev->pdev->dev, "assert_callra 0x%08x\n", ioread32be(&h->assert_callra));
+	mlx5_core_err(dev, "assert_exit_ptr 0x%08x\n",
+		      ioread32be(&h->assert_exit_ptr));
+	mlx5_core_err(dev, "assert_callra 0x%08x\n",
+		      ioread32be(&h->assert_callra));
 	sprintf(fw_str, "%d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev));
-	dev_err(&dev->pdev->dev, "fw_ver %s\n", fw_str);
-	dev_err(&dev->pdev->dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
-	dev_err(&dev->pdev->dev, "irisc_index %d\n", ioread8(&h->irisc_index));
-	dev_err(&dev->pdev->dev, "synd 0x%x: %s\n", ioread8(&h->synd), hsynd_str(ioread8(&h->synd)));
-	dev_err(&dev->pdev->dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
+	mlx5_core_err(dev, "fw_ver %s\n", fw_str);
+	mlx5_core_err(dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
+	mlx5_core_err(dev, "irisc_index %d\n", ioread8(&h->irisc_index));
+	mlx5_core_err(dev, "synd 0x%x: %s\n", ioread8(&h->synd),
+		      hsynd_str(ioread8(&h->synd)));
+	mlx5_core_err(dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
 	fw = ioread32be(&h->fw_ver);
-	dev_err(&dev->pdev->dev, "raw fw_ver 0x%08x\n", fw);
+	mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw);
+}
+
+static int
+mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+			  struct devlink_fmsg *fmsg)
+{
+	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+	struct mlx5_core_health *health = &dev->priv.health;
+	struct health_buffer __iomem *h = health->health;
+	u8 synd;
+	int err;
+
+	synd = ioread8(&h->synd);
+	err = devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd);
+	if (err || !synd)
+		return err;
+	return devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd));
+}
+
+struct mlx5_fw_reporter_ctx {
+	u8 err_synd;
+	int miss_counter;
+};
+
+static int
+mlx5_fw_reporter_ctx_pairs_put(struct devlink_fmsg *fmsg,
+			       struct mlx5_fw_reporter_ctx *fw_reporter_ctx)
+{
+	int err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "syndrome",
+				       fw_reporter_ctx->err_synd);
+	if (err)
+		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "fw_miss_counter",
+					fw_reporter_ctx->miss_counter);
+	if (err)
+		return err;
+	return 0;
+}
+
+static int
+mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev,
+				       struct devlink_fmsg *fmsg)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+	struct health_buffer __iomem *h = health->health;
+	int err;
+	int i;
+
+	if (!ioread8(&h->synd))
+		return 0;
+
+	err = devlink_fmsg_pair_nest_start(fmsg, "health buffer");
+	if (err)
+		return err;
+	err = devlink_fmsg_obj_nest_start(fmsg);
+	if (err)
+		return err;
+	err = devlink_fmsg_arr_pair_nest_start(fmsg, "assert_var");
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(h->assert_var); i++) {
+		err = devlink_fmsg_u32_put(fmsg, ioread32be(h->assert_var + i));
+		if (err)
+			return err;
+	}
+	err = devlink_fmsg_arr_pair_nest_end(fmsg);
+	if (err)
+		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "assert_exit_ptr",
+					ioread32be(&h->assert_exit_ptr));
+	if (err)
+		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "assert_callra",
+					ioread32be(&h->assert_callra));
+	if (err)
+		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "hw_id", ioread32be(&h->hw_id));
+	if (err)
+		return err;
+	err = devlink_fmsg_u8_pair_put(fmsg, "irisc_index",
+				       ioread8(&h->irisc_index));
+	if (err)
+		return err;
+	err = devlink_fmsg_u8_pair_put(fmsg, "synd", ioread8(&h->synd));
+	if (err)
+		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "ext_synd",
+					ioread16be(&h->ext_synd));
+	if (err)
+		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "raw_fw_ver",
+					ioread32be(&h->fw_ver));
+	if (err)
+		return err;
+	err = devlink_fmsg_obj_nest_end(fmsg);
+	if (err)
+		return err;
+	return devlink_fmsg_pair_nest_end(fmsg);
+}
+
+static int
+mlx5_fw_reporter_dump(struct devlink_health_reporter *reporter,
+		      struct devlink_fmsg *fmsg, void *priv_ctx)
+{
+	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+	int err;
+
+	err = mlx5_fw_tracer_trigger_core_dump_general(dev);
+	if (err)
+		return err;
+
+	if (priv_ctx) {
+		struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
+
+		err = mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx);
+		if (err)
+			return err;
+	}
+
+	err = mlx5_fw_reporter_heath_buffer_data_put(dev, fmsg);
+	if (err)
+		return err;
+	return mlx5_fw_tracer_get_saved_traces_objects(dev->tracer, fmsg);
+}
+
+static void mlx5_fw_reporter_err_work(struct work_struct *work)
+{
+	struct mlx5_fw_reporter_ctx fw_reporter_ctx;
+	struct mlx5_core_health *health;
+
+	health = container_of(work, struct mlx5_core_health, report_work);
+
+	if (IS_ERR_OR_NULL(health->fw_reporter))
+		return;
+
+	fw_reporter_ctx.err_synd = health->synd;
+	fw_reporter_ctx.miss_counter = health->miss_counter;
+	if (fw_reporter_ctx.err_synd) {
+		devlink_health_report(health->fw_reporter,
+				      "FW syndrom reported", &fw_reporter_ctx);
+		return;
+	}
+	if (fw_reporter_ctx.miss_counter)
+		devlink_health_report(health->fw_reporter,
+				      "FW miss counter reported",
+				      &fw_reporter_ctx);
+}
+
+static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
+		.name = "fw",
+		.diagnose = mlx5_fw_reporter_diagnose,
+		.dump = mlx5_fw_reporter_dump,
+};
+
+static int
+mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
+			       void *priv_ctx)
+{
+	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+
+	return mlx5_health_try_recover(dev);
+}
+
+#define MLX5_CR_DUMP_CHUNK_SIZE 256
+static int
+mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
+			    struct devlink_fmsg *fmsg, void *priv_ctx)
+{
+	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+	u32 crdump_size = dev->priv.health.crdump_size;
+	u32 *cr_data;
+	u32 data_size;
+	u32 offset;
+	int err;
+
+	if (!mlx5_core_is_pf(dev))
+		return -EPERM;
+
+	cr_data = kvmalloc(crdump_size, GFP_KERNEL);
+	if (!cr_data)
+		return -ENOMEM;
+	err = mlx5_crdump_collect(dev, cr_data);
+	if (err)
+		return err;
+
+	if (priv_ctx) {
+		struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
+
+		err = mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx);
+		if (err)
+			goto free_data;
+	}
+
+	err = devlink_fmsg_arr_pair_nest_start(fmsg, "crdump_data");
+	if (err)
+		goto free_data;
+	for (offset = 0; offset < crdump_size; offset += data_size) {
+		if (crdump_size - offset < MLX5_CR_DUMP_CHUNK_SIZE)
+			data_size = crdump_size - offset;
+		else
+			data_size = MLX5_CR_DUMP_CHUNK_SIZE;
+		err = devlink_fmsg_binary_put(fmsg, cr_data, data_size);
+		if (err)
+			goto free_data;
+	}
+	err = devlink_fmsg_arr_pair_nest_end(fmsg);
+
+free_data:
+	kfree(cr_data);
+	return err;
+}
+
+static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
+{
+	struct mlx5_fw_reporter_ctx fw_reporter_ctx;
+	struct mlx5_core_health *health;
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+
+	health = container_of(work, struct mlx5_core_health, fatal_report_work);
+	priv = container_of(health, struct mlx5_priv, health);
+	dev = container_of(priv, struct mlx5_core_dev, priv);
+
+	mlx5_enter_error_state(dev, false);
+	if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
+		if (mlx5_health_try_recover(dev))
+			mlx5_core_err(dev, "health recovery failed\n");
+		return;
+	}
+	fw_reporter_ctx.err_synd = health->synd;
+	fw_reporter_ctx.miss_counter = health->miss_counter;
+	devlink_health_report(health->fw_fatal_reporter,
+			      "FW fatal error reported", &fw_reporter_ctx);
+}
+
+static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
+		.name = "fw_fatal",
+		.recover = mlx5_fw_fatal_reporter_recover,
+		.dump = mlx5_fw_fatal_reporter_dump,
+};
+
+#define MLX5_REPORTER_FW_GRACEFUL_PERIOD 1200000
+static void mlx5_fw_reporters_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+	struct devlink *devlink = priv_to_devlink(dev);
+
+	health->fw_reporter =
+		devlink_health_reporter_create(devlink, &mlx5_fw_reporter_ops,
+					       0, false, dev);
+	if (IS_ERR(health->fw_reporter))
+		mlx5_core_warn(dev, "Failed to create fw reporter, err = %ld\n",
+			       PTR_ERR(health->fw_reporter));
+
+	health->fw_fatal_reporter =
+		devlink_health_reporter_create(devlink,
+					       &mlx5_fw_fatal_reporter_ops,
+					       MLX5_REPORTER_FW_GRACEFUL_PERIOD,
+					       true, dev);
+	if (IS_ERR(health->fw_fatal_reporter))
+		mlx5_core_warn(dev, "Failed to create fw fatal reporter, err = %ld\n",
+			       PTR_ERR(health->fw_fatal_reporter));
+}
+
+static void mlx5_fw_reporters_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	if (!IS_ERR_OR_NULL(health->fw_reporter))
+		devlink_health_reporter_destroy(health->fw_reporter);
+
+	if (!IS_ERR_OR_NULL(health->fw_fatal_reporter))
+		devlink_health_reporter_destroy(health->fw_fatal_reporter);
 }
 
 static unsigned long get_next_poll_jiffies(void)
@@ -260,10 +682,9 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev)
 
 	spin_lock_irqsave(&health->wq_lock, flags);
 	if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags))
-		queue_work(health->wq, &health->work);
+		queue_work(health->wq, &health->fatal_report_work);
 	else
-		dev_err(&dev->pdev->dev,
-			"new health works are not permitted at this stage\n");
+		mlx5_core_err(dev, "new health works are not permitted at this stage\n");
 	spin_unlock_irqrestore(&health->wq_lock, flags);
 }
 
@@ -271,6 +692,9 @@ static void poll_health(struct timer_list *t)
 {
 	struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
 	struct mlx5_core_health *health = &dev->priv.health;
+	struct health_buffer __iomem *h = health->health;
+	u32 fatal_error;
+	u8 prev_synd;
 	u32 count;
 
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
@@ -284,12 +708,21 @@ static void poll_health(struct timer_list *t)
 
 	health->prev = count;
 	if (health->miss_counter == MAX_MISSES) {
-		dev_err(&dev->pdev->dev, "device's health compromised - reached miss count\n");
+		mlx5_core_err(dev, "device's health compromised - reached miss count\n");
 		print_health_info(dev);
+		queue_work(health->wq, &health->report_work);
 	}
 
-	if (in_fatal(dev) && !health->sick) {
-		health->sick = true;
+	prev_synd = health->synd;
+	health->synd = ioread8(&h->synd);
+	if (health->synd && health->synd != prev_synd)
+		queue_work(health->wq, &health->report_work);
+
+	fatal_error = check_fatal_sensors(dev);
+
+	if (fatal_error && !health->fatal_error) {
+		mlx5_core_err(dev, "Fatal error %u detected\n", fatal_error);
+		dev->priv.health.fatal_error = fatal_error;
 		print_health_info(dev);
 		mlx5_trigger_health_work(dev);
 	}
@@ -303,9 +736,8 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	struct mlx5_core_health *health = &dev->priv.health;
 
 	timer_setup(&health->timer, poll_health, 0);
-	health->sick = 0;
+	health->fatal_error = MLX5_SENSOR_NO_ERR;
 	clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
-	clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	health->health = &dev->iseg->health;
 	health->health_counter = &dev->iseg->health_counter;
 
@@ -321,7 +753,6 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 	if (disable_health) {
 		spin_lock_irqsave(&health->wq_lock, flags);
 		set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
-		set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 		spin_unlock_irqrestore(&health->wq_lock, flags);
 	}
 
@@ -335,21 +766,16 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 
 	spin_lock_irqsave(&health->wq_lock, flags);
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
-	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
 	spin_unlock_irqrestore(&health->wq_lock, flags);
-	cancel_delayed_work_sync(&health->recover_work);
-	cancel_work_sync(&health->work);
+	cancel_work_sync(&health->report_work);
+	cancel_work_sync(&health->fatal_report_work);
 }
 
-void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
+void mlx5_health_flush(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
-	unsigned long flags;
 
-	spin_lock_irqsave(&health->wq_lock, flags);
-	set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
-	spin_unlock_irqrestore(&health->wq_lock, flags);
-	cancel_delayed_work_sync(&dev->priv.health.recover_work);
+	flush_workqueue(health->wq);
 }
 
 void mlx5_health_cleanup(struct mlx5_core_dev *dev)
@@ -357,6 +783,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 	struct mlx5_core_health *health = &dev->priv.health;
 
 	destroy_workqueue(health->wq);
+	mlx5_fw_reporters_destroy(dev);
 }
 
 int mlx5_health_init(struct mlx5_core_dev *dev)
@@ -364,20 +791,26 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 	struct mlx5_core_health *health;
 	char *name;
 
+	mlx5_fw_reporters_create(dev);
+
 	health = &dev->priv.health;
 	name = kmalloc(64, GFP_KERNEL);
 	if (!name)
-		return -ENOMEM;
+		goto out_err;
 
 	strcpy(name, "mlx5_health");
-	strcat(name, dev_name(&dev->pdev->dev));
+	strcat(name, dev_name(dev->device));
 	health->wq = create_singlethread_workqueue(name);
 	kfree(name);
 	if (!health->wq)
-		return -ENOMEM;
+		goto out_err;
 	spin_lock_init(&health->wq_lock);
-	INIT_WORK(&health->work, health_care);
-	INIT_DELAYED_WORK(&health->recover_work, health_recover);
+	INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work);
+	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
 
 	return 0;
+
+out_err:
+	mlx5_fw_reporters_destroy(dev);
+	return -ENOMEM;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/Makefile
index d8e17110f25d..c78512eed8d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 90cb50fe17fd..ebd81f6b556e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -122,14 +122,6 @@ static int mlx5i_get_ts_info(struct net_device *netdev,
 	return mlx5e_ethtool_get_ts_info(priv, info);
 }
 
-static int mlx5i_flash_device(struct net_device *netdev,
-			      struct ethtool_flash *flash)
-{
-	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
-
-	return mlx5e_ethtool_flash_device(priv, flash);
-}
-
 enum mlx5_ptys_width {
 	MLX5_PTYS_WIDTH_1X	= 1 << 0,
 	MLX5_PTYS_WIDTH_2X	= 1 << 1,
@@ -241,7 +233,6 @@ const struct ethtool_ops mlx5i_ethtool_ops = {
 	.get_ethtool_stats  = mlx5i_get_ethtool_stats,
 	.get_ringparam      = mlx5i_get_ringparam,
 	.set_ringparam      = mlx5i_set_ringparam,
-	.flash_device       = mlx5i_flash_device,
 	.get_channels       = mlx5i_get_channels,
 	.set_channels       = mlx5i_set_channels,
 	.get_coalesce       = mlx5i_get_coalesce,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index bfc0f6581729..6bfaaab362dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -68,6 +68,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 
 	params->lro_en = false;
 	params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
+	params->tunneled_offload_en = false;
 }
 
 /* Called directly after IPoIB netdevice was created to initialize SW structs */
@@ -77,17 +78,16 @@ int mlx5i_init(struct mlx5_core_dev *mdev,
 	       void *ppriv)
 {
 	struct mlx5e_priv *priv  = mlx5i_epriv(netdev);
-	u16 max_mtu;
 	int err;
 
 	err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv);
 	if (err)
 		return err;
 
-	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
-	netdev->mtu = max_mtu;
+	mlx5e_set_netdev_mtu_boundaries(priv);
+	netdev->mtu = netdev->max_mtu;
 
-	mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params,
+	mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params,
 			       mlx5e_get_netdev_max_channels(netdev),
 			       netdev->mtu);
 	mlx5i_build_nic_params(mdev, &priv->channels.params);
@@ -258,6 +258,18 @@ void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *
 	mlx5_core_destroy_qp(mdev, qp);
 }
 
+int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn)
+{
+	u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {};
+	void *tisc;
+
+	tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+	MLX5_SET(tisc, tisc, underlay_qpn, underlay_qpn);
+
+	return mlx5e_create_tis(mdev, in, tisn);
+}
+
 static int mlx5i_init_tx(struct mlx5e_priv *priv)
 {
 	struct mlx5i_priv *ipriv = priv->ppriv;
@@ -269,7 +281,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
+	err = mlx5i_create_tis(priv->mdev, ipriv->qp.qpn, &priv->tisn[0]);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
 		goto err_destroy_underlay_qp;
@@ -365,7 +377,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_close_drop_rq;
 
-	err = mlx5e_create_direct_rqts(priv);
+	err = mlx5e_create_direct_rqts(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_rqts;
 
@@ -373,7 +385,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 	if (err)
 		goto err_destroy_direct_rqts;
 
-	err = mlx5e_create_direct_tirs(priv);
+	err = mlx5e_create_direct_tirs(priv, priv->direct_tir);
 	if (err)
 		goto err_destroy_indirect_tirs;
 
@@ -384,11 +396,11 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 	return 0;
 
 err_destroy_direct_tirs:
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 err_destroy_indirect_tirs:
 	mlx5e_destroy_indirect_tirs(priv, true);
 err_destroy_direct_rqts:
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 err_destroy_indirect_rqts:
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 err_close_drop_rq:
@@ -401,9 +413,9 @@ err_destroy_q_counters:
 static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
 {
 	mlx5i_destroy_flow_steering(priv);
-	mlx5e_destroy_direct_tirs(priv);
+	mlx5e_destroy_direct_tirs(priv, priv->direct_tir);
 	mlx5e_destroy_indirect_tirs(priv, true);
-	mlx5e_destroy_direct_rqts(priv);
+	mlx5e_destroy_direct_rqts(priv, priv->direct_tir);
 	mlx5e_destroy_rqt(priv, &priv->indir_rqt);
 	mlx5e_close_drop_rq(&priv->drop_rq);
 	mlx5e_destroy_q_counters(priv);
@@ -418,6 +430,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
 	.cleanup_rx	   = mlx5i_cleanup_rx,
 	.enable		   = NULL, /* mlx5i_enable */
 	.disable	   = NULL, /* mlx5i_disable */
+	.update_rx	   = mlx5e_update_nic_rx,
 	.update_stats	   = NULL, /* mlx5i_update_stats */
 	.update_carrier    = NULL, /* no HW update in IB link */
 	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
@@ -446,11 +459,11 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu)
 
 	new_channels.params = *params;
 	new_channels.params.sw_mtu = new_mtu;
-	err = mlx5e_open_channels(priv, &new_channels);
+
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 	if (err)
 		goto out;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
@@ -526,7 +539,7 @@ static int mlx5i_open(struct net_device *netdev)
 	if (err)
 		goto err_remove_fs_underlay_qp;
 
-	mlx5e_refresh_tirs(epriv, false);
+	epriv->profile->update_rx(epriv);
 	mlx5e_activate_priv_channels(epriv);
 
 	mutex_unlock(&epriv->state_lock);
@@ -619,7 +632,7 @@ static int mlx5i_xmit(struct net_device *dev, struct sk_buff *skb,
 	struct mlx5_ib_ah *mah   = to_mah(address);
 	struct mlx5i_priv *ipriv = epriv->ppriv;
 
-	return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey);
+	return mlx5i_sq_xmit(sq, skb, &mah->av, dqpn, ipriv->qkey, netdev_xmit_more());
 }
 
 static void mlx5i_set_pkey_index(struct net_device *netdev, int id)
@@ -698,7 +711,9 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	prof->init(mdev, netdev, prof, ipriv);
 
-	mlx5e_attach_netdev(epriv);
+	err = mlx5e_attach_netdev(epriv);
+	if (err)
+		goto detach;
 	netif_carrier_off(netdev);
 
 	/* set rdma_netdev func pointers */
@@ -714,6 +729,11 @@ static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num,
 
 	return 0;
 
+detach:
+	prof->cleanup(epriv);
+	if (ipriv->sub_interface)
+		return err;
+	mlx5e_destroy_mdev_resources(mdev);
 destroy_ht:
 	mlx5i_pkey_qpn_ht_cleanup(netdev);
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index 9165ca567047..c87962cab921 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -59,6 +59,8 @@ struct mlx5i_priv {
 	char  *mlx5e_priv[0];
 };
 
+int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn);
+
 /* Underlay QP create/destroy functions */
 int mlx5i_create_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp);
 void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp);
@@ -119,7 +121,8 @@ static inline void mlx5i_sq_fetch_wqe(struct mlx5e_txqsq *sq,
 }
 
 netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-			  struct mlx5_av *av, u32 dqpn, u32 dqkey);
+			  struct mlx5_av *av, u32 dqpn, u32 dqkey,
+			  bool xmit_more);
 void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index b491b8f5fd6b..6e56fa769d2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -210,7 +210,7 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 		goto err_unint_underlay_qp;
 	}
 
-	err = mlx5e_create_tis(mdev, 0 /* tc */, ipriv->qp.qpn, &epriv->tisn[0]);
+	err = mlx5i_create_tis(mdev, ipriv->qp.qpn, &epriv->tisn[0]);
 	if (err) {
 		mlx5_core_warn(mdev, "create child tis failed, %d\n", err);
 		goto err_remove_rx_uderlay_qp;
@@ -221,7 +221,7 @@ static int mlx5i_pkey_open(struct net_device *netdev)
 		mlx5_core_warn(mdev, "opening child channels failed, %d\n", err);
 		goto err_clear_state_opened_flag;
 	}
-	mlx5e_refresh_tirs(epriv, false);
+	epriv->profile->update_rx(epriv);
 	mlx5e_activate_priv_channels(epriv);
 	mutex_unlock(&epriv->state_lock);
 
@@ -350,6 +350,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
 	.cleanup_rx	   = mlx5i_pkey_cleanup_rx,
 	.enable		   = NULL,
 	.disable	   = NULL,
+	.update_rx	   = mlx5e_update_nic_rx,
 	.update_stats	   = NULL,
 	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
 	.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 2d223385dc81..c5ef2ff26465 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -35,37 +35,8 @@
 #include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
 #include "eswitch.h"
-
-enum {
-	MLX5_LAG_FLAG_ROCE   = 1 << 0,
-	MLX5_LAG_FLAG_SRIOV  = 1 << 1,
-};
-
-#define MLX5_LAG_MODE_FLAGS (MLX5_LAG_FLAG_ROCE | MLX5_LAG_FLAG_SRIOV)
-
-struct lag_func {
-	struct mlx5_core_dev *dev;
-	struct net_device    *netdev;
-};
-
-/* Used for collection of netdev event info. */
-struct lag_tracker {
-	enum   netdev_lag_tx_type           tx_type;
-	struct netdev_lag_lower_state_info  netdev_state[MLX5_MAX_PORTS];
-	bool is_bonded;
-};
-
-/* LAG data of a ConnectX card.
- * It serves both its phys functions.
- */
-struct mlx5_lag {
-	u8                        flags;
-	u8                        v2p_map[MLX5_MAX_PORTS];
-	struct lag_func           pf[MLX5_MAX_PORTS];
-	struct lag_tracker        tracker;
-	struct delayed_work       bond_work;
-	struct notifier_block     nb;
-};
+#include "lag.h"
+#include "lag_mp.h"
 
 /* General purpose, use for short periods of time.
  * Beware of lock dependencies (preferably, no locks should be acquired
@@ -147,13 +118,8 @@ static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
 }
 
-static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev)
-{
-	return dev->priv.lag;
-}
-
-static int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
-				       struct net_device *ndev)
+int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
+				struct net_device *ndev)
 {
 	int i;
 
@@ -174,11 +140,6 @@ static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev)
 	return !!(ldev->flags & MLX5_LAG_FLAG_SRIOV);
 }
 
-static bool __mlx5_lag_is_active(struct mlx5_lag *ldev)
-{
-	return !!(ldev->flags & MLX5_LAG_MODE_FLAGS);
-}
-
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 					   u8 *port1, u8 *port2)
 {
@@ -195,8 +156,8 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 		*port2 = 1;
 }
 
-static void mlx5_modify_lag(struct mlx5_lag *ldev,
-			    struct lag_tracker *tracker)
+void mlx5_modify_lag(struct mlx5_lag *ldev,
+		     struct lag_tracker *tracker)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	u8 v2p_port1, v2p_port2;
@@ -241,9 +202,9 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 	return err;
 }
 
-static int mlx5_activate_lag(struct mlx5_lag *ldev,
-			     struct lag_tracker *tracker,
-			     u8 flags)
+int mlx5_activate_lag(struct mlx5_lag *ldev,
+		      struct lag_tracker *tracker,
+		      u8 flags)
 {
 	bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE);
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
@@ -343,6 +304,11 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 		roce_lag = !mlx5_sriov_is_enabled(dev0) &&
 			   !mlx5_sriov_is_enabled(dev1);
 
+#ifdef CONFIG_MLX5_ESWITCH
+		roce_lag &= dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+			    dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE;
+#endif
+
 		if (roce_lag)
 			mlx5_lag_remove_ib_devices(ldev);
 
@@ -381,7 +347,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 
 static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay)
 {
-	schedule_delayed_work(&ldev->bond_work, delay);
+	queue_delayed_work(ldev->wq, &ldev->bond_work, delay);
 }
 
 static void mlx5_do_bond_work(struct work_struct *work)
@@ -533,6 +499,12 @@ static struct mlx5_lag *mlx5_lag_dev_alloc(void)
 	if (!ldev)
 		return NULL;
 
+	ldev->wq = create_singlethread_workqueue("mlx5_lag");
+	if (!ldev->wq) {
+		kfree(ldev);
+		return NULL;
+	}
+
 	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);
 
 	return ldev;
@@ -540,6 +512,7 @@ static struct mlx5_lag *mlx5_lag_dev_alloc(void)
 
 static void mlx5_lag_dev_free(struct mlx5_lag *ldev)
 {
+	destroy_workqueue(ldev->wq);
 	kfree(ldev);
 }
 
@@ -587,6 +560,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 {
 	struct mlx5_lag *ldev = NULL;
 	struct mlx5_core_dev *tmp_dev;
+	int err;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(dev, lag_master) ||
@@ -614,27 +588,11 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 			mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
 		}
 	}
-}
-
-int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num)
-{
-	struct mlx5_lag *ldev;
-	int n;
-
-	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev) {
-		mlx5_core_warn(dev, "no lag device, can't get pf num\n");
-		return -EINVAL;
-	}
 
-	for (n = 0; n < MLX5_MAX_PORTS; n++)
-		if (ldev->pf[n].dev == dev) {
-			*pf_num = n;
-			return 0;
-		}
-
-	mlx5_core_warn(dev, "wasn't able to locate pf in the lag device\n");
-	return -EINVAL;
+	err = mlx5_lag_mp_init(ldev);
+	if (err)
+		mlx5_core_err(dev, "Failed to init multipath lag err=%d\n",
+			      err);
 }
 
 /* Must be called with intf_mutex held */
@@ -659,6 +617,7 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev)
 	if (i == MLX5_MAX_PORTS) {
 		if (ldev->nb.notifier_call)
 			unregister_netdevice_notifier(&ldev->nb);
+		mlx5_lag_mp_cleanup(ldev);
 		cancel_delayed_work_sync(&ldev->bond_work);
 		mlx5_lag_dev_free(ldev);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
new file mode 100644
index 000000000000..1dea0b1c9826
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_LAG_H__
+#define __MLX5_LAG_H__
+
+#include "mlx5_core.h"
+#include "lag_mp.h"
+
+enum {
+	MLX5_LAG_FLAG_ROCE   = 1 << 0,
+	MLX5_LAG_FLAG_SRIOV  = 1 << 1,
+	MLX5_LAG_FLAG_MULTIPATH = 1 << 2,
+};
+
+#define MLX5_LAG_MODE_FLAGS (MLX5_LAG_FLAG_ROCE | MLX5_LAG_FLAG_SRIOV |\
+			     MLX5_LAG_FLAG_MULTIPATH)
+
+struct lag_func {
+	struct mlx5_core_dev *dev;
+	struct net_device    *netdev;
+};
+
+/* Used for collection of netdev event info. */
+struct lag_tracker {
+	enum   netdev_lag_tx_type           tx_type;
+	struct netdev_lag_lower_state_info  netdev_state[MLX5_MAX_PORTS];
+	unsigned int is_bonded:1;
+};
+
+/* LAG data of a ConnectX card.
+ * It serves both its phys functions.
+ */
+struct mlx5_lag {
+	u8                        flags;
+	u8                        v2p_map[MLX5_MAX_PORTS];
+	struct lag_func           pf[MLX5_MAX_PORTS];
+	struct lag_tracker        tracker;
+	struct workqueue_struct   *wq;
+	struct delayed_work       bond_work;
+	struct notifier_block     nb;
+	struct lag_mp             lag_mp;
+};
+
+static inline struct mlx5_lag *
+mlx5_lag_dev_get(struct mlx5_core_dev *dev)
+{
+	return dev->priv.lag;
+}
+
+static inline bool
+__mlx5_lag_is_active(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_MODE_FLAGS);
+}
+
+void mlx5_modify_lag(struct mlx5_lag *ldev,
+		     struct lag_tracker *tracker);
+int mlx5_activate_lag(struct mlx5_lag *ldev,
+		      struct lag_tracker *tracker,
+		      u8 flags);
+int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
+				struct net_device *ndev);
+
+#endif /* __MLX5_LAG_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
new file mode 100644
index 000000000000..e69766393990
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/netdevice.h>
+#include <net/nexthop.h>
+#include "lag.h"
+#include "lag_mp.h"
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "lib/mlx5.h"
+
+static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
+{
+	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
+		return false;
+
+	return mlx5_esw_multipath_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+}
+
+static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH);
+}
+
+bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	bool res;
+
+	ldev = mlx5_lag_dev_get(dev);
+	res  = ldev && __mlx5_lag_is_multipath(ldev);
+
+	return res;
+}
+
+/**
+ * Set lag port affinity
+ *
+ * @ldev: lag device
+ * @port:
+ *     0 - set normal affinity.
+ *     1 - set affinity to port 1.
+ *     2 - set affinity to port 2.
+ *
+ **/
+static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port)
+{
+	struct lag_tracker tracker;
+
+	if (!__mlx5_lag_is_multipath(ldev))
+		return;
+
+	switch (port) {
+	case 0:
+		tracker.netdev_state[0].tx_enabled = true;
+		tracker.netdev_state[1].tx_enabled = true;
+		tracker.netdev_state[0].link_up = true;
+		tracker.netdev_state[1].link_up = true;
+		break;
+	case 1:
+		tracker.netdev_state[0].tx_enabled = true;
+		tracker.netdev_state[0].link_up = true;
+		tracker.netdev_state[1].tx_enabled = false;
+		tracker.netdev_state[1].link_up = false;
+		break;
+	case 2:
+		tracker.netdev_state[0].tx_enabled = false;
+		tracker.netdev_state[0].link_up = false;
+		tracker.netdev_state[1].tx_enabled = true;
+		tracker.netdev_state[1].link_up = true;
+		break;
+	default:
+		mlx5_core_warn(ldev->pf[0].dev, "Invalid affinity port %d",
+			       port);
+		return;
+	}
+
+	if (tracker.netdev_state[0].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[0].dev->priv.events,
+					 MLX5_DEV_EVENT_PORT_AFFINITY,
+					 (void *)0);
+
+	if (tracker.netdev_state[1].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[1].dev->priv.events,
+					 MLX5_DEV_EVENT_PORT_AFFINITY,
+					 (void *)0);
+
+	mlx5_modify_lag(ldev, &tracker);
+}
+
+static void mlx5_lag_fib_event_flush(struct notifier_block *nb)
+{
+	struct lag_mp *mp = container_of(nb, struct lag_mp, fib_nb);
+	struct mlx5_lag *ldev = container_of(mp, struct mlx5_lag, lag_mp);
+
+	flush_workqueue(ldev->wq);
+}
+
+struct mlx5_fib_event_work {
+	struct work_struct work;
+	struct mlx5_lag *ldev;
+	unsigned long event;
+	union {
+		struct fib_entry_notifier_info fen_info;
+		struct fib_nh_notifier_info fnh_info;
+	};
+};
+
+static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
+				     unsigned long event,
+				     struct fib_info *fi)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+	struct fib_nh *fib_nh0, *fib_nh1;
+	unsigned int nhs;
+
+	/* Handle delete event */
+	if (event == FIB_EVENT_ENTRY_DEL) {
+		/* stop track */
+		if (mp->mfi == fi)
+			mp->mfi = NULL;
+		return;
+	}
+
+	/* Handle add/replace event */
+	nhs = fib_info_num_path(fi);
+	if (nhs == 1) {
+		if (__mlx5_lag_is_active(ldev)) {
+			struct fib_nh *nh = fib_info_nh(fi, 0);
+			struct net_device *nh_dev = nh->fib_nh_dev;
+			int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev);
+
+			mlx5_lag_set_port_affinity(ldev, ++i);
+		}
+		return;
+	}
+
+	if (nhs != 2)
+		return;
+
+	/* Verify next hops are ports of the same hca */
+	fib_nh0 = fib_info_nh(fi, 0);
+	fib_nh1 = fib_info_nh(fi, 1);
+	if (!(fib_nh0->fib_nh_dev == ldev->pf[0].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[1].netdev) &&
+	    !(fib_nh0->fib_nh_dev == ldev->pf[1].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[0].netdev)) {
+		mlx5_core_warn(ldev->pf[0].dev, "Multipath offload require two ports of the same HCA\n");
+		return;
+	}
+
+	/* First time we see multipath route */
+	if (!mp->mfi && !__mlx5_lag_is_active(ldev)) {
+		struct lag_tracker tracker;
+
+		tracker = ldev->tracker;
+		mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH);
+	}
+
+	mlx5_lag_set_port_affinity(ldev, 0);
+	mp->mfi = fi;
+}
+
+static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev,
+				       unsigned long event,
+				       struct fib_nh *fib_nh,
+				       struct fib_info *fi)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+
+	/* Check the nh event is related to the route */
+	if (!mp->mfi || mp->mfi != fi)
+		return;
+
+	/* nh added/removed */
+	if (event == FIB_EVENT_NH_DEL) {
+		int i = mlx5_lag_dev_get_netdev_idx(ldev, fib_nh->fib_nh_dev);
+
+		if (i >= 0) {
+			i = (i + 1) % 2 + 1; /* peer port */
+			mlx5_lag_set_port_affinity(ldev, i);
+		}
+	} else if (event == FIB_EVENT_NH_ADD &&
+		   fib_info_num_path(fi) == 2) {
+		mlx5_lag_set_port_affinity(ldev, 0);
+	}
+}
+
+static void mlx5_lag_fib_update(struct work_struct *work)
+{
+	struct mlx5_fib_event_work *fib_work =
+		container_of(work, struct mlx5_fib_event_work, work);
+	struct mlx5_lag *ldev = fib_work->ldev;
+	struct fib_nh *fib_nh;
+
+	/* Protect internal structures from changes */
+	rtnl_lock();
+	switch (fib_work->event) {
+	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_APPEND: /* fall through */
+	case FIB_EVENT_ENTRY_ADD: /* fall through */
+	case FIB_EVENT_ENTRY_DEL:
+		mlx5_lag_fib_route_event(ldev, fib_work->event,
+					 fib_work->fen_info.fi);
+		fib_info_put(fib_work->fen_info.fi);
+		break;
+	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_DEL:
+		fib_nh = fib_work->fnh_info.fib_nh;
+		mlx5_lag_fib_nexthop_event(ldev,
+					   fib_work->event,
+					   fib_work->fnh_info.fib_nh,
+					   fib_nh->nh_parent);
+		fib_info_put(fib_work->fnh_info.fib_nh->nh_parent);
+		break;
+	}
+
+	rtnl_unlock();
+	kfree(fib_work);
+}
+
+static struct mlx5_fib_event_work *
+mlx5_lag_init_fib_work(struct mlx5_lag *ldev, unsigned long event)
+{
+	struct mlx5_fib_event_work *fib_work;
+
+	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
+	if (WARN_ON(!fib_work))
+		return NULL;
+
+	INIT_WORK(&fib_work->work, mlx5_lag_fib_update);
+	fib_work->ldev = ldev;
+	fib_work->event = event;
+
+	return fib_work;
+}
+
+static int mlx5_lag_fib_event(struct notifier_block *nb,
+			      unsigned long event,
+			      void *ptr)
+{
+	struct lag_mp *mp = container_of(nb, struct lag_mp, fib_nb);
+	struct mlx5_lag *ldev = container_of(mp, struct mlx5_lag, lag_mp);
+	struct fib_notifier_info *info = ptr;
+	struct mlx5_fib_event_work *fib_work;
+	struct fib_entry_notifier_info *fen_info;
+	struct fib_nh_notifier_info *fnh_info;
+	struct net_device *fib_dev;
+	struct fib_info *fi;
+
+	if (info->family != AF_INET)
+		return NOTIFY_DONE;
+
+	if (!mlx5_lag_multipath_check_prereq(ldev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_APPEND: /* fall through */
+	case FIB_EVENT_ENTRY_ADD: /* fall through */
+	case FIB_EVENT_ENTRY_DEL:
+		fen_info = container_of(info, struct fib_entry_notifier_info,
+					info);
+		fi = fen_info->fi;
+		if (fi->nh) {
+			NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
+			return notifier_from_errno(-EINVAL);
+		}
+		fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
+		if (fib_dev != ldev->pf[0].netdev &&
+		    fib_dev != ldev->pf[1].netdev) {
+			return NOTIFY_DONE;
+		}
+		fib_work = mlx5_lag_init_fib_work(ldev, event);
+		if (!fib_work)
+			return NOTIFY_DONE;
+		fib_work->fen_info = *fen_info;
+		/* Take reference on fib_info to prevent it from being
+		 * freed while work is queued. Release it afterwards.
+		 */
+		fib_info_hold(fib_work->fen_info.fi);
+		break;
+	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_DEL:
+		fnh_info = container_of(info, struct fib_nh_notifier_info,
+					info);
+		fib_work = mlx5_lag_init_fib_work(ldev, event);
+		if (!fib_work)
+			return NOTIFY_DONE;
+		fib_work->fnh_info = *fnh_info;
+		fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	queue_work(ldev->wq, &fib_work->work);
+
+	return NOTIFY_DONE;
+}
+
+int mlx5_lag_mp_init(struct mlx5_lag *ldev)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+	int err;
+
+	if (mp->fib_nb.notifier_call)
+		return 0;
+
+	mp->fib_nb.notifier_call = mlx5_lag_fib_event;
+	err = register_fib_notifier(&mp->fib_nb,
+				    mlx5_lag_fib_event_flush);
+	if (err)
+		mp->fib_nb.notifier_call = NULL;
+
+	return err;
+}
+
+void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+
+	if (!mp->fib_nb.notifier_call)
+		return;
+
+	unregister_fib_notifier(&mp->fib_nb);
+	mp->fib_nb.notifier_call = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
new file mode 100644
index 000000000000..6d14b1100be9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_LAG_MP_H__
+#define __MLX5_LAG_MP_H__
+
+#include "lag.h"
+#include "mlx5_core.h"
+
+struct lag_mp {
+	struct notifier_block     fib_nb;
+	struct fib_info           *mfi; /* used in tracking fib events */
+};
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+int mlx5_lag_mp_init(struct mlx5_lag *ldev);
+void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev);
+
+#else /* CONFIG_MLX5_ESWITCH */
+
+static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; }
+static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_LAG_MP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/lib/Makefile
index d8e17110f25d..c78512eed8d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index ca0ee9916e9e..0059b290e095 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -535,23 +535,16 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 	do_div(ns, NSEC_PER_SEC / HZ);
 	clock->overflow_period = ns;
 
-	mdev->clock_info_page = alloc_page(GFP_KERNEL);
-	if (mdev->clock_info_page) {
-		mdev->clock_info = kmap(mdev->clock_info_page);
-		if (!mdev->clock_info) {
-			__free_page(mdev->clock_info_page);
-			mlx5_core_warn(mdev, "failed to map clock page\n");
-		} else {
-			mdev->clock_info->sign   = 0;
-			mdev->clock_info->nsec   = clock->tc.nsec;
-			mdev->clock_info->cycles = clock->tc.cycle_last;
-			mdev->clock_info->mask   = clock->cycles.mask;
-			mdev->clock_info->mult   = clock->nominal_c_mult;
-			mdev->clock_info->shift  = clock->cycles.shift;
-			mdev->clock_info->frac   = clock->tc.frac;
-			mdev->clock_info->overflow_period =
-						clock->overflow_period;
-		}
+	mdev->clock_info =
+		(struct mlx5_ib_clock_info *)get_zeroed_page(GFP_KERNEL);
+	if (mdev->clock_info) {
+		mdev->clock_info->nsec = clock->tc.nsec;
+		mdev->clock_info->cycles = clock->tc.cycle_last;
+		mdev->clock_info->mask = clock->cycles.mask;
+		mdev->clock_info->mult = clock->nominal_c_mult;
+		mdev->clock_info->shift = clock->cycles.shift;
+		mdev->clock_info->frac = clock->tc.frac;
+		mdev->clock_info->overflow_period = clock->overflow_period;
 	}
 
 	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
@@ -599,8 +592,7 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	cancel_delayed_work_sync(&clock->overflow_work);
 
 	if (mdev->clock_info) {
-		kunmap(mdev->clock_info_page);
-		__free_page(mdev->clock_info_page);
+		free_page((unsigned long)mdev->clock_info);
 		mdev->clock_info = NULL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c
new file mode 100644
index 000000000000..ea9ee88491e5
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2019 Mellanox Technologies.
+
+#include "mlx5_core.h"
+
+int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
+			       void *key, u32 sz_bytes,
+			       u32 *p_key_id)
+{
+	u32 in[MLX5_ST_SZ_DW(create_encryption_key_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
+	u32 sz_bits = sz_bytes * BITS_PER_BYTE;
+	u8  general_obj_key_size;
+	u64 general_obj_types;
+	void *obj, *key_p;
+	int err;
+
+	obj = MLX5_ADDR_OF(create_encryption_key_in, in, encryption_key_object);
+	key_p = MLX5_ADDR_OF(encryption_key_obj, obj, key);
+
+	general_obj_types = MLX5_CAP_GEN_64(mdev, general_obj_types);
+	if (!(general_obj_types &
+	      MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY))
+		return -EINVAL;
+
+	switch (sz_bits) {
+	case 128:
+		general_obj_key_size =
+			MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128;
+		break;
+	case 256:
+		general_obj_key_size =
+			MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	memcpy(key_p, key, sz_bytes);
+
+	MLX5_SET(encryption_key_obj, obj, key_size, general_obj_key_size);
+	MLX5_SET(encryption_key_obj, obj, key_type,
+		 MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_TYPE_DEK);
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode,
+		 MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type,
+		 MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY);
+	MLX5_SET(encryption_key_obj, obj, pd, mdev->mlx5e_res.pdn);
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (!err)
+		*p_key_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+
+	/* avoid leaking key on the stack */
+	memzero_explicit(in, sizeof(in));
+
+	return err;
+}
+
+void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id)
+{
+	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
+
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode,
+		 MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type,
+		 MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, key_id);
+
+	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index c0fb6d72b695..3dfab91ae5f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -7,7 +7,6 @@
 #include <linux/mlx5/eq.h>
 #include <linux/mlx5/cq.h>
 
-#define MLX5_MAX_IRQ_NAME   (32)
 #define MLX5_EQE_SIZE       (sizeof(struct mlx5_eqe))
 
 struct mlx5_eq_tasklet {
@@ -36,8 +35,14 @@ struct mlx5_eq {
 	struct mlx5_rsc_debug   *dbg;
 };
 
+struct mlx5_eq_async {
+	struct mlx5_eq          core;
+	struct notifier_block   irq_nb;
+};
+
 struct mlx5_eq_comp {
-	struct mlx5_eq          core; /* Must be first */
+	struct mlx5_eq          core;
+	struct notifier_block   irq_nb;
 	struct mlx5_eq_tasklet  tasklet_ctx;
 	struct list_head        list;
 };
@@ -70,7 +75,7 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev);
 void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
 
 int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
 struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn);
 struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev);
 void mlx5_cq_tasklet_cb(unsigned long data);
@@ -92,7 +97,4 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
 #endif
 
-int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
-int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
-
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c
new file mode 100644
index 000000000000..23361a9ae4fa
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/kernel.h>
+#include "mlx5_core.h"
+#include "geneve.h"
+
+struct mlx5_geneve {
+	struct mlx5_core_dev *mdev;
+	__be16 opt_class;
+	u8 opt_type;
+	u32 obj_id;
+	struct mutex sync_lock; /* protect GENEVE obj operations */
+	u32 refcount;
+};
+
+static int mlx5_geneve_tlv_option_create(struct mlx5_core_dev *mdev,
+					 __be16 class,
+					 u8 type,
+					 u8 len)
+{
+	u32 in[MLX5_ST_SZ_DW(create_geneve_tlv_option_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
+	u64 general_obj_types;
+	void *hdr, *opt;
+	u16 obj_id;
+	int err;
+
+	general_obj_types = MLX5_CAP_GEN_64(mdev, general_obj_types);
+	if (!(general_obj_types & MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT))
+		return -EINVAL;
+
+	hdr = MLX5_ADDR_OF(create_geneve_tlv_option_in, in, hdr);
+	opt = MLX5_ADDR_OF(create_geneve_tlv_option_in, in, geneve_tlv_opt);
+
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type, MLX5_OBJ_TYPE_GENEVE_TLV_OPT);
+
+	MLX5_SET(geneve_tlv_option, opt, option_class, be16_to_cpu(class));
+	MLX5_SET(geneve_tlv_option, opt, option_type, type);
+	MLX5_SET(geneve_tlv_option, opt, option_data_length, len);
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+	return obj_id;
+}
+
+static void mlx5_geneve_tlv_option_destroy(struct mlx5_core_dev *mdev, u16 obj_id)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
+	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
+
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_GENEVE_TLV_OPT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id);
+
+	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_geneve_tlv_option_add(struct mlx5_geneve *geneve, struct geneve_opt *opt)
+{
+	int res = 0;
+
+	if (IS_ERR_OR_NULL(geneve))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&geneve->sync_lock);
+
+	if (geneve->refcount) {
+		if (geneve->opt_class == opt->opt_class &&
+		    geneve->opt_type == opt->type) {
+			/* We already have TLV options obj allocated */
+			geneve->refcount++;
+		} else {
+			/* TLV options obj allocated, but its params
+			 * do not match the new request.
+			 * We support only one such object.
+			 */
+			mlx5_core_warn(geneve->mdev,
+				       "Won't create Geneve TLV opt object with class:type:len = 0x%x:0x%x:%d (another class:type already exists)\n",
+				       be16_to_cpu(opt->opt_class),
+				       opt->type,
+				       opt->length);
+			res = -EOPNOTSUPP;
+			goto unlock;
+		}
+	} else {
+		/* We don't have any TLV options obj allocated */
+
+		res = mlx5_geneve_tlv_option_create(geneve->mdev,
+						    opt->opt_class,
+						    opt->type,
+						    opt->length);
+		if (res < 0) {
+			mlx5_core_warn(geneve->mdev,
+				       "Failed creating Geneve TLV opt object class:type:len = 0x%x:0x%x:%d (err=%d)\n",
+				       be16_to_cpu(opt->opt_class),
+				       opt->type, opt->length, res);
+			goto unlock;
+		}
+		geneve->opt_class = opt->opt_class;
+		geneve->opt_type = opt->type;
+		geneve->obj_id = res;
+		geneve->refcount++;
+	}
+
+unlock:
+	mutex_unlock(&geneve->sync_lock);
+	return res;
+}
+
+void mlx5_geneve_tlv_option_del(struct mlx5_geneve *geneve)
+{
+	if (IS_ERR_OR_NULL(geneve))
+		return;
+
+	mutex_lock(&geneve->sync_lock);
+	if (--geneve->refcount == 0) {
+		/* We've just removed the last user of Geneve option.
+		 * Now delete the object in FW.
+		 */
+		mlx5_geneve_tlv_option_destroy(geneve->mdev, geneve->obj_id);
+
+		geneve->opt_class = 0;
+		geneve->opt_type = 0;
+		geneve->obj_id = 0;
+	}
+	mutex_unlock(&geneve->sync_lock);
+}
+
+struct mlx5_geneve *mlx5_geneve_create(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_geneve *geneve =
+		kzalloc(sizeof(*geneve), GFP_KERNEL);
+
+	if (!geneve)
+		return ERR_PTR(-ENOMEM);
+	geneve->mdev = mdev;
+	mutex_init(&geneve->sync_lock);
+
+	return geneve;
+}
+
+void mlx5_geneve_destroy(struct mlx5_geneve *geneve)
+{
+	if (IS_ERR_OR_NULL(geneve))
+		return;
+
+	/* Lockless since we are unloading */
+	if (geneve->refcount)
+		mlx5_geneve_tlv_option_destroy(geneve->mdev, geneve->obj_id);
+
+	kfree(geneve);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.h
new file mode 100644
index 000000000000..adee0cbba19c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_GENEVE_H__
+#define __MLX5_GENEVE_H__
+
+#include <net/geneve.h>
+#include <linux/mlx5/driver.h>
+
+struct mlx5_geneve;
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+struct mlx5_geneve *mlx5_geneve_create(struct mlx5_core_dev *mdev);
+void mlx5_geneve_destroy(struct mlx5_geneve *geneve);
+
+int mlx5_geneve_tlv_option_add(struct mlx5_geneve *geneve, struct geneve_opt *opt);
+void mlx5_geneve_tlv_option_del(struct mlx5_geneve *geneve);
+
+#else /* CONFIG_MLX5_ESWITCH */
+
+static inline struct mlx5_geneve
+*mlx5_geneve_create(struct mlx5_core_dev *mdev) { return NULL; }
+static inline void
+mlx5_geneve_destroy(struct mlx5_geneve *geneve) {}
+static inline int
+mlx5_geneve_tlv_option_add(struct mlx5_geneve *geneve, struct geneve_opt *opt) { return 0; }
+static inline void
+mlx5_geneve_tlv_option_del(struct mlx5_geneve *geneve) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+
+#endif /* __MLX5_GENEVE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 397a2847867a..b99d469e4e64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -41,6 +41,9 @@ int  mlx5_core_reserve_gids(struct mlx5_core_dev *dev, unsigned int count);
 void mlx5_core_unreserve_gids(struct mlx5_core_dev *dev, unsigned int count);
 int  mlx5_core_reserved_gid_alloc(struct mlx5_core_dev *dev, int *gid_index);
 void mlx5_core_reserved_gid_free(struct mlx5_core_dev *dev, int gid_index);
+int mlx5_crdump_enable(struct mlx5_core_dev *dev);
+void mlx5_crdump_disable(struct mlx5_core_dev *dev);
+int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data);
 
 /* TODO move to lib/events.h */
 
@@ -76,4 +79,9 @@ struct mlx5_pme_stats {
 void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats);
 int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data);
 
+/* Crypto */
+int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
+			       void *key, u32 sz_bytes, u32 *p_key_id);
+void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 98359559c77e..3118e8d66407 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -67,6 +67,7 @@ static int del_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index)
 struct l2table_node {
 	struct l2addr_node node;
 	u32                index; /* index in HW l2 table */
+	int                ref_count;
 };
 
 struct mlx5_mpfs {
@@ -108,8 +109,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev)
 
 	mutex_init(&mpfs->lock);
 	mpfs->size   = l2table_size;
-	mpfs->bitmap = kcalloc(BITS_TO_LONGS(l2table_size),
-			       sizeof(uintptr_t), GFP_KERNEL);
+	mpfs->bitmap = bitmap_zalloc(l2table_size, GFP_KERNEL);
 	if (!mpfs->bitmap) {
 		kfree(mpfs);
 		return -ENOMEM;
@@ -127,7 +127,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev)
 		return;
 
 	WARN_ON(!hlist_empty(mpfs->hash));
-	kfree(mpfs->bitmap);
+	bitmap_free(mpfs->bitmap);
 	kfree(mpfs);
 }
 
@@ -135,8 +135,8 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 {
 	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
 	struct l2table_node *l2addr;
+	int err = 0;
 	u32 index;
-	int err;
 
 	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
@@ -145,30 +145,35 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 
 	l2addr = l2addr_hash_find(mpfs->hash, mac, struct l2table_node);
 	if (l2addr) {
-		err = -EEXIST;
-		goto abort;
+		l2addr->ref_count++;
+		goto out;
 	}
 
 	err = alloc_l2table_index(mpfs, &index);
 	if (err)
-		goto abort;
+		goto out;
 
 	l2addr = l2addr_hash_add(mpfs->hash, mac, struct l2table_node, GFP_KERNEL);
 	if (!l2addr) {
-		free_l2table_index(mpfs, index);
 		err = -ENOMEM;
-		goto abort;
+		goto hash_add_err;
 	}
 
-	l2addr->index = index;
 	err = set_l2table_entry_cmd(dev, index, mac);
-	if (err) {
-		l2addr_hash_del(l2addr);
-		free_l2table_index(mpfs, index);
-	}
+	if (err)
+		goto set_table_entry_err;
+
+	l2addr->index = index;
+	l2addr->ref_count = 1;
 
 	mlx5_core_dbg(dev, "MPFS mac added %pM, index (%d)\n", mac, index);
-abort:
+	goto out;
+
+set_table_entry_err:
+	l2addr_hash_del(l2addr);
+hash_add_err:
+	free_l2table_index(mpfs, index);
+out:
 	mutex_unlock(&mpfs->lock);
 	return err;
 }
@@ -191,6 +196,9 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 		goto unlock;
 	}
 
+	if (--l2addr->ref_count > 0)
+		goto unlock;
+
 	index = l2addr->index;
 	del_l2table_entry_cmd(dev, index);
 	l2addr_hash_del(l2addr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
new file mode 100644
index 000000000000..6b774e0c2766
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <linux/pci.h>
+#include "mlx5_core.h"
+#include "pci_vsc.h"
+
+#define MLX5_EXTRACT_C(source, offset, size)	\
+	((((u32)(source)) >> (offset)) & MLX5_ONES32(size))
+#define MLX5_EXTRACT(src, start, len)		\
+	(((len) == 32) ? (src) : MLX5_EXTRACT_C(src, start, len))
+#define MLX5_ONES32(size)			\
+	((size) ? (0xffffffff >> (32 - (size))) : 0)
+#define MLX5_MASK32(offset, size)		\
+	(MLX5_ONES32(size) << (offset))
+#define MLX5_MERGE_C(rsrc1, rsrc2, start, len)  \
+	((((rsrc2) << (start)) & (MLX5_MASK32((start), (len)))) | \
+	((rsrc1) & (~MLX5_MASK32((start), (len)))))
+#define MLX5_MERGE(rsrc1, rsrc2, start, len)	\
+	(((len) == 32) ? (rsrc2) : MLX5_MERGE_C(rsrc1, rsrc2, start, len))
+#define vsc_read(dev, offset, val) \
+	pci_read_config_dword((dev)->pdev, (dev)->vsc_addr + (offset), (val))
+#define vsc_write(dev, offset, val) \
+	pci_write_config_dword((dev)->pdev, (dev)->vsc_addr + (offset), (val))
+#define VSC_MAX_RETRIES 2048
+
+enum {
+	VSC_CTRL_OFFSET = 0x4,
+	VSC_COUNTER_OFFSET = 0x8,
+	VSC_SEMAPHORE_OFFSET = 0xc,
+	VSC_ADDR_OFFSET = 0x10,
+	VSC_DATA_OFFSET = 0x14,
+
+	VSC_FLAG_BIT_OFFS = 31,
+	VSC_FLAG_BIT_LEN = 1,
+
+	VSC_SYND_BIT_OFFS = 30,
+	VSC_SYND_BIT_LEN = 1,
+
+	VSC_ADDR_BIT_OFFS = 0,
+	VSC_ADDR_BIT_LEN = 30,
+
+	VSC_SPACE_BIT_OFFS = 0,
+	VSC_SPACE_BIT_LEN = 16,
+
+	VSC_SIZE_VLD_BIT_OFFS = 28,
+	VSC_SIZE_VLD_BIT_LEN = 1,
+
+	VSC_STATUS_BIT_OFFS = 29,
+	VSC_STATUS_BIT_LEN = 3,
+};
+
+void mlx5_pci_vsc_init(struct mlx5_core_dev *dev)
+{
+	if (!mlx5_core_is_pf(dev))
+		return;
+
+	dev->vsc_addr = pci_find_capability(dev->pdev,
+					    PCI_CAP_ID_VNDR);
+	if (!dev->vsc_addr)
+		mlx5_core_warn(dev, "Failed to get valid vendor specific ID\n");
+}
+
+int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev)
+{
+	u32 counter = 0;
+	int retries = 0;
+	u32 lock_val;
+	int ret;
+
+	pci_cfg_access_lock(dev->pdev);
+	do {
+		if (retries > VSC_MAX_RETRIES) {
+			ret = -EBUSY;
+			goto pci_unlock;
+		}
+
+		/* Check if semaphore is already locked */
+		ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val);
+		if (ret)
+			goto pci_unlock;
+
+		if (lock_val) {
+			retries++;
+			usleep_range(1000, 2000);
+			continue;
+		}
+
+		/* Read and write counter value, if written value is
+		 * the same, semaphore was acquired successfully.
+		 */
+		ret = vsc_read(dev, VSC_COUNTER_OFFSET, &counter);
+		if (ret)
+			goto pci_unlock;
+
+		ret = vsc_write(dev, VSC_SEMAPHORE_OFFSET, counter);
+		if (ret)
+			goto pci_unlock;
+
+		ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val);
+		if (ret)
+			goto pci_unlock;
+
+		retries++;
+	} while (counter != lock_val);
+
+	return 0;
+
+pci_unlock:
+	pci_cfg_access_unlock(dev->pdev);
+	return ret;
+}
+
+int mlx5_vsc_gw_unlock(struct mlx5_core_dev *dev)
+{
+	int ret;
+
+	ret = vsc_write(dev, VSC_SEMAPHORE_OFFSET, MLX5_VSC_UNLOCK);
+	pci_cfg_access_unlock(dev->pdev);
+	return ret;
+}
+
+int mlx5_vsc_gw_set_space(struct mlx5_core_dev *dev, u16 space,
+			  u32 *ret_space_size)
+{
+	int ret;
+	u32 val = 0;
+
+	if (!mlx5_vsc_accessible(dev))
+		return -EINVAL;
+
+	if (ret_space_size)
+		*ret_space_size = 0;
+
+	/* Get a unique val */
+	ret = vsc_read(dev, VSC_CTRL_OFFSET, &val);
+	if (ret)
+		goto out;
+
+	/* Try to modify the lock */
+	val = MLX5_MERGE(val, space, VSC_SPACE_BIT_OFFS, VSC_SPACE_BIT_LEN);
+	ret = vsc_write(dev, VSC_CTRL_OFFSET, val);
+	if (ret)
+		goto out;
+
+	/* Verify lock was modified */
+	ret = vsc_read(dev, VSC_CTRL_OFFSET, &val);
+	if (ret)
+		goto out;
+
+	if (MLX5_EXTRACT(val, VSC_STATUS_BIT_OFFS, VSC_STATUS_BIT_LEN) == 0)
+		return -EINVAL;
+
+	/* Get space max address if indicated by size valid bit */
+	if (ret_space_size &&
+	    MLX5_EXTRACT(val, VSC_SIZE_VLD_BIT_OFFS, VSC_SIZE_VLD_BIT_LEN)) {
+		ret = vsc_read(dev, VSC_ADDR_OFFSET, &val);
+		if (ret) {
+			mlx5_core_warn(dev, "Failed to get max space size\n");
+			goto out;
+		}
+		*ret_space_size = MLX5_EXTRACT(val, VSC_ADDR_BIT_OFFS,
+					       VSC_ADDR_BIT_LEN);
+	}
+	return 0;
+
+out:
+	return ret;
+}
+
+static int mlx5_vsc_wait_on_flag(struct mlx5_core_dev *dev, u8 expected_val)
+{
+	int retries = 0;
+	u32 flag;
+	int ret;
+
+	do {
+		if (retries > VSC_MAX_RETRIES)
+			return -EBUSY;
+
+		ret = vsc_read(dev, VSC_ADDR_OFFSET, &flag);
+		if (ret)
+			return ret;
+		flag = MLX5_EXTRACT(flag, VSC_FLAG_BIT_OFFS, VSC_FLAG_BIT_LEN);
+		retries++;
+
+		if ((retries & 0xf) == 0)
+			usleep_range(1000, 2000);
+
+	} while (flag != expected_val);
+
+	return 0;
+}
+
+static int mlx5_vsc_gw_write(struct mlx5_core_dev *dev, unsigned int address,
+			     u32 data)
+{
+	int ret;
+
+	if (MLX5_EXTRACT(address, VSC_SYND_BIT_OFFS,
+			 VSC_FLAG_BIT_LEN + VSC_SYND_BIT_LEN))
+		return -EINVAL;
+
+	/* Set flag to 0x1 */
+	address = MLX5_MERGE(address, 1, VSC_FLAG_BIT_OFFS, 1);
+	ret = vsc_write(dev, VSC_DATA_OFFSET, data);
+	if (ret)
+		goto out;
+
+	ret = vsc_write(dev, VSC_ADDR_OFFSET, address);
+	if (ret)
+		goto out;
+
+	/* Wait for the flag to be cleared */
+	ret = mlx5_vsc_wait_on_flag(dev, 0);
+
+out:
+	return ret;
+}
+
+static int mlx5_vsc_gw_read(struct mlx5_core_dev *dev, unsigned int address,
+			    u32 *data)
+{
+	int ret;
+
+	if (MLX5_EXTRACT(address, VSC_SYND_BIT_OFFS,
+			 VSC_FLAG_BIT_LEN + VSC_SYND_BIT_LEN))
+		return -EINVAL;
+
+	ret = vsc_write(dev, VSC_ADDR_OFFSET, address);
+	if (ret)
+		goto out;
+
+	ret = mlx5_vsc_wait_on_flag(dev, 1);
+	if (ret)
+		goto out;
+
+	ret = vsc_read(dev, VSC_DATA_OFFSET, data);
+out:
+	return ret;
+}
+
+static int mlx5_vsc_gw_read_fast(struct mlx5_core_dev *dev,
+				 unsigned int read_addr,
+				 unsigned int *next_read_addr,
+				 u32 *data)
+{
+	int ret;
+
+	ret = mlx5_vsc_gw_read(dev, read_addr, data);
+	if (ret)
+		goto out;
+
+	ret = vsc_read(dev, VSC_ADDR_OFFSET, next_read_addr);
+	if (ret)
+		goto out;
+
+	*next_read_addr = MLX5_EXTRACT(*next_read_addr, VSC_ADDR_BIT_OFFS,
+				       VSC_ADDR_BIT_LEN);
+
+	if (*next_read_addr <= read_addr)
+		ret = -EINVAL;
+out:
+	return ret;
+}
+
+int mlx5_vsc_gw_read_block_fast(struct mlx5_core_dev *dev, u32 *data,
+				int length)
+{
+	unsigned int next_read_addr = 0;
+	unsigned int read_addr = 0;
+
+	while (read_addr < length) {
+		if (mlx5_vsc_gw_read_fast(dev, read_addr, &next_read_addr,
+					  &data[(read_addr >> 2)]))
+			return read_addr;
+
+		read_addr = next_read_addr;
+	}
+	return length;
+}
+
+int mlx5_vsc_sem_set_space(struct mlx5_core_dev *dev, u16 space,
+			   enum mlx5_vsc_state state)
+{
+	u32 data, id = 0;
+	int ret;
+
+	ret = mlx5_vsc_gw_set_space(dev, MLX5_SEMAPHORE_SPACE_DOMAIN, NULL);
+	if (ret) {
+		mlx5_core_warn(dev, "Failed to set gw space %d\n", ret);
+		return ret;
+	}
+
+	if (state == MLX5_VSC_LOCK) {
+		/* Get a unique ID based on the counter */
+		ret = vsc_read(dev, VSC_COUNTER_OFFSET, &id);
+		if (ret)
+			return ret;
+	}
+
+	/* Try to modify lock */
+	ret = mlx5_vsc_gw_write(dev, space, id);
+	if (ret)
+		return ret;
+
+	/* Verify lock was modified */
+	ret = mlx5_vsc_gw_read(dev, space, &data);
+	if (ret)
+		return -EINVAL;
+
+	if (data != id)
+		return -EBUSY;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
new file mode 100644
index 000000000000..64272a6d7754
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#ifndef __MLX5_PCI_VSC_H__
+#define __MLX5_PCI_VSC_H__
+
+enum mlx5_vsc_state {
+	MLX5_VSC_UNLOCK,
+	MLX5_VSC_LOCK,
+};
+
+enum {
+	MLX5_VSC_SPACE_SCAN_CRSPACE = 0x7,
+};
+
+void mlx5_pci_vsc_init(struct mlx5_core_dev *dev);
+int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev);
+int mlx5_vsc_gw_unlock(struct mlx5_core_dev *dev);
+int mlx5_vsc_gw_set_space(struct mlx5_core_dev *dev, u16 space,
+			  u32 *ret_space_size);
+int mlx5_vsc_gw_read_block_fast(struct mlx5_core_dev *dev, u32 *data,
+				int length);
+
+static inline bool mlx5_vsc_accessible(struct mlx5_core_dev *dev)
+{
+	return !!dev->vsc_addr;
+}
+
+int mlx5_vsc_sem_set_space(struct mlx5_core_dev *dev, u16 space,
+			   enum mlx5_vsc_state state);
+
+#endif /* __MLX5_PCI_VSC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
new file mode 100644
index 000000000000..48b5c847b642
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
@@ -0,0 +1,188 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/port.h>
+#include <linux/mlx5/cmd.h>
+#include "mlx5_core.h"
+#include "lib/port_tun.h"
+
+struct mlx5_port_tun_entropy_flags {
+	bool force_supported, force_enabled;
+	bool calc_supported, calc_enabled;
+	bool gre_calc_supported, gre_calc_enabled;
+};
+
+static void mlx5_query_port_tun_entropy(struct mlx5_core_dev *mdev,
+					struct mlx5_port_tun_entropy_flags *entropy_flags)
+{
+	u32 out[MLX5_ST_SZ_DW(pcmr_reg)];
+	/* Default values for FW which do not support MLX5_REG_PCMR */
+	entropy_flags->force_supported = false;
+	entropy_flags->calc_supported = false;
+	entropy_flags->gre_calc_supported = false;
+	entropy_flags->force_enabled = false;
+	entropy_flags->calc_enabled = true;
+	entropy_flags->gre_calc_enabled = true;
+
+	if (!MLX5_CAP_GEN(mdev, ports_check))
+		return;
+
+	if (mlx5_query_ports_check(mdev, out, sizeof(out)))
+		return;
+
+	entropy_flags->force_supported = !!(MLX5_GET(pcmr_reg, out, entropy_force_cap));
+	entropy_flags->calc_supported = !!(MLX5_GET(pcmr_reg, out, entropy_calc_cap));
+	entropy_flags->gre_calc_supported = !!(MLX5_GET(pcmr_reg, out, entropy_gre_calc_cap));
+	entropy_flags->force_enabled = !!(MLX5_GET(pcmr_reg, out, entropy_force));
+	entropy_flags->calc_enabled = !!(MLX5_GET(pcmr_reg, out, entropy_calc));
+	entropy_flags->gre_calc_enabled = !!(MLX5_GET(pcmr_reg, out, entropy_gre_calc));
+}
+
+static int mlx5_set_port_tun_entropy_calc(struct mlx5_core_dev *mdev, u8 enable,
+					  u8 force)
+{
+	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
+	int err;
+
+	err = mlx5_query_ports_check(mdev, in, sizeof(in));
+	if (err)
+		return err;
+	MLX5_SET(pcmr_reg, in, local_port, 1);
+	MLX5_SET(pcmr_reg, in, entropy_force, force);
+	MLX5_SET(pcmr_reg, in, entropy_calc, enable);
+	return mlx5_set_ports_check(mdev, in, sizeof(in));
+}
+
+static int mlx5_set_port_gre_tun_entropy_calc(struct mlx5_core_dev *mdev,
+					      u8 enable, u8 force)
+{
+	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
+	int err;
+
+	err = mlx5_query_ports_check(mdev, in, sizeof(in));
+	if (err)
+		return err;
+	MLX5_SET(pcmr_reg, in, local_port, 1);
+	MLX5_SET(pcmr_reg, in, entropy_force, force);
+	MLX5_SET(pcmr_reg, in, entropy_gre_calc, enable);
+	return mlx5_set_ports_check(mdev, in, sizeof(in));
+}
+
+void mlx5_init_port_tun_entropy(struct mlx5_tun_entropy *tun_entropy,
+				struct mlx5_core_dev *mdev)
+{
+	struct mlx5_port_tun_entropy_flags entropy_flags;
+
+	tun_entropy->mdev = mdev;
+	mutex_init(&tun_entropy->lock);
+	mlx5_query_port_tun_entropy(mdev, &entropy_flags);
+	tun_entropy->num_enabling_entries = 0;
+	tun_entropy->num_disabling_entries = 0;
+	tun_entropy->enabled = entropy_flags.calc_supported ?
+			       entropy_flags.calc_enabled : true;
+}
+
+static int mlx5_set_entropy(struct mlx5_tun_entropy *tun_entropy,
+			    int reformat_type, bool enable)
+{
+	struct mlx5_port_tun_entropy_flags entropy_flags;
+	int err;
+
+	mlx5_query_port_tun_entropy(tun_entropy->mdev, &entropy_flags);
+	/* Tunnel entropy calculation may be controlled either on port basis
+	 * for all tunneling protocols or specifically for GRE protocol.
+	 * Prioritize GRE protocol control (if capable) over global port
+	 * configuration.
+	 */
+	if (entropy_flags.gre_calc_supported &&
+	    reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE) {
+		if (!entropy_flags.force_supported)
+			return 0;
+		err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev,
+							 enable, !enable);
+		if (err)
+			return err;
+	} else if (entropy_flags.calc_supported) {
+		/* Other applications may change the global FW entropy
+		 * calculations settings. Check that the current entropy value
+		 * is the negative of the updated value.
+		 */
+		if (entropy_flags.force_enabled &&
+		    enable == entropy_flags.calc_enabled) {
+			mlx5_core_warn(tun_entropy->mdev,
+				       "Unexpected entropy calc setting - expected %d",
+				       !entropy_flags.calc_enabled);
+			return -EOPNOTSUPP;
+		}
+		/* GRE requires disabling entropy calculation. if there are
+		 * enabling entries (i.e VXLAN) we cannot turn it off for them,
+		 * thus fail.
+		 */
+		if (tun_entropy->num_enabling_entries)
+			return -EOPNOTSUPP;
+		err = mlx5_set_port_tun_entropy_calc(tun_entropy->mdev, enable,
+						     entropy_flags.force_supported);
+		if (err)
+			return err;
+		tun_entropy->enabled = enable;
+		/* if we turn on the entropy we don't need to force it anymore */
+		if (entropy_flags.force_supported && enable) {
+			err = mlx5_set_port_tun_entropy_calc(tun_entropy->mdev, 1, 0);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+/* the function manages the refcount for enabling/disabling tunnel types.
+ * the return value indicates if the inc is successful or not, depending on
+ * entropy capabilities and configuration.
+ */
+int mlx5_tun_entropy_refcount_inc(struct mlx5_tun_entropy *tun_entropy,
+				  int reformat_type)
+{
+	/* the default is error for unknown (non VXLAN/GRE tunnel types) */
+	int err = -EOPNOTSUPP;
+
+	mutex_lock(&tun_entropy->lock);
+	if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN &&
+	    tun_entropy->enabled) {
+		/* in case entropy calculation is enabled for all tunneling
+		 * types, it is ok for VXLAN, so approve.
+		 * otherwise keep the error default.
+		 */
+		tun_entropy->num_enabling_entries++;
+		err = 0;
+	} else if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE) {
+		/* turn off the entropy only for the first GRE rule.
+		 * for the next rules the entropy was already disabled
+		 * successfully.
+		 */
+		if (tun_entropy->num_disabling_entries == 0)
+			err = mlx5_set_entropy(tun_entropy, reformat_type, 0);
+		else
+			err = 0;
+		if (!err)
+			tun_entropy->num_disabling_entries++;
+	}
+	mutex_unlock(&tun_entropy->lock);
+
+	return err;
+}
+
+void mlx5_tun_entropy_refcount_dec(struct mlx5_tun_entropy *tun_entropy,
+				   int reformat_type)
+{
+	mutex_lock(&tun_entropy->lock);
+	if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN)
+		tun_entropy->num_enabling_entries--;
+	else if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE &&
+		 --tun_entropy->num_disabling_entries == 0)
+		mlx5_set_entropy(tun_entropy, reformat_type, 1);
+	mutex_unlock(&tun_entropy->lock);
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.h
new file mode 100644
index 000000000000..54c42a88705e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_PORT_TUN_H__
+#define __MLX5_PORT_TUN_H__
+
+#include <linux/mlx5/driver.h>
+
+struct mlx5_tun_entropy {
+	struct mlx5_core_dev *mdev;
+	u32 num_enabling_entries;
+	u32 num_disabling_entries;
+	u8  enabled;
+	struct mutex lock;	/* lock the entropy fields */
+};
+
+void mlx5_init_port_tun_entropy(struct mlx5_tun_entropy *tun_entropy,
+				struct mlx5_core_dev *mdev);
+int mlx5_tun_entropy_refcount_inc(struct mlx5_tun_entropy *tun_entropy,
+				  int reformat_type);
+void mlx5_tun_entropy_refcount_dec(struct mlx5_tun_entropy *tun_entropy,
+				   int reformat_type);
+
+#endif /* __MLX5_PORT_TUN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
index 9a8fd762167b..b9d4f4e19ff9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -33,6 +33,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
+#include <net/vxlan.h>
 #include "mlx5_core.h"
 #include "vxlan.h"
 
@@ -204,8 +205,8 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
 	spin_lock_init(&vxlan->lock);
 	hash_init(vxlan->htable);
 
-	/* Hardware adds 4789 by default */
-	mlx5_vxlan_add_port(vxlan, 4789);
+	/* Hardware adds 4789 (IANA_VXLAN_UDP_PORT) by default */
+	mlx5_vxlan_add_port(vxlan, IANA_VXLAN_UDP_PORT);
 
 	return vxlan;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mad.c b/drivers/net/ethernet/mellanox/mlx5/core/mad.c
deleted file mode 100644
index 3a3b0005fd2b..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/mad.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
-#include "mlx5_core.h"
-
-int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
-		      u16 opmod, u8 port)
-{
-	int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out);
-	int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in);
-	int err = -ENOMEM;
-	void *data;
-	void *resp;
-	u32 *out;
-	u32 *in;
-
-	in = kzalloc(inlen, GFP_KERNEL);
-	out = kzalloc(outlen, GFP_KERNEL);
-	if (!in || !out)
-		goto out;
-
-	MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC);
-	MLX5_SET(mad_ifc_in, in, op_mod, opmod);
-	MLX5_SET(mad_ifc_in, in, port, port);
-
-	data = MLX5_ADDR_OF(mad_ifc_in, in, mad);
-	memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad));
-
-	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
-	if (err)
-		goto out;
-
-	resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet);
-	memcpy(outb, resp,
-	       MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet));
-
-out:
-	kfree(out);
-	kfree(in);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_mad_ifc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index be81b319b0dc..b15b27a497fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -56,6 +56,7 @@
 #include "fs_core.h"
 #include "lib/mpfs.h"
 #include "eswitch.h"
+#include "devlink.h"
 #include "lib/mlx5.h"
 #include "fpga/core.h"
 #include "fpga/ipsec.h"
@@ -63,8 +64,11 @@
 #include "accel/tls.h"
 #include "lib/clock.h"
 #include "lib/vxlan.h"
+#include "lib/geneve.h"
 #include "lib/devcom.h"
+#include "lib/pci_vsc.h"
 #include "diag/fw_tracer.h"
+#include "ecpf.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -163,43 +167,33 @@ static struct mlx5_profile profile[] = {
 			.size	= 8,
 			.limit	= 4
 		},
-		.mr_cache[16]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[17]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[18]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[19]	= {
-			.size	= 4,
-			.limit	= 2
-		},
-		.mr_cache[20]	= {
-			.size	= 4,
-			.limit	= 2
-		},
 	},
 };
 
 #define FW_INIT_TIMEOUT_MILI		2000
 #define FW_INIT_WAIT_MS			2
-#define FW_PRE_INIT_TIMEOUT_MILI	10000
+#define FW_PRE_INIT_TIMEOUT_MILI	120000
+#define FW_INIT_WARN_MESSAGE_INTERVAL	20000
 
-static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
+static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
+			u32 warn_time_mili)
 {
+	unsigned long warn = jiffies + msecs_to_jiffies(warn_time_mili);
 	unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili);
 	int err = 0;
 
+	BUILD_BUG_ON(FW_PRE_INIT_TIMEOUT_MILI < FW_INIT_WARN_MESSAGE_INTERVAL);
+
 	while (fw_initializing(dev)) {
 		if (time_after(jiffies, end)) {
 			err = -EBUSY;
 			break;
 		}
+		if (warn_time_mili && time_after(jiffies, warn)) {
+			mlx5_core_warn(dev, "Waiting for FW initialization, timeout abort in %ds\n",
+				       jiffies_to_msecs(end - warn) / 1000);
+			warn = jiffies + msecs_to_jiffies(warn_time_mili);
+		}
 		msleep(FW_INIT_WAIT_MS);
 	}
 
@@ -459,6 +453,58 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev)
 	return err;
 }
 
+static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
+{
+	void *set_hca_cap;
+	void *set_ctx;
+	int set_sz;
+	bool do_set = false;
+	int err;
+
+	if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) ||
+	    !MLX5_CAP_GEN(dev, pg))
+		return 0;
+
+	err = mlx5_core_get_caps(dev, MLX5_CAP_ODP);
+	if (err)
+		return err;
+
+	set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	set_ctx = kzalloc(set_sz, GFP_KERNEL);
+	if (!set_ctx)
+		return -ENOMEM;
+
+	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
+	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP],
+	       MLX5_ST_SZ_BYTES(odp_cap));
+
+#define ODP_CAP_SET_MAX(dev, field)                                            \
+	do {                                                                   \
+		u32 _res = MLX5_CAP_ODP_MAX(dev, field);                       \
+		if (_res) {                                                    \
+			do_set = true;                                         \
+			MLX5_SET(odp_cap, set_hca_cap, field, _res);           \
+		}                                                              \
+	} while (0)
+
+	ODP_CAP_SET_MAX(dev, ud_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, rc_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.send);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.receive);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.write);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.read);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic);
+
+	if (do_set)
+		err = set_caps(dev, set_ctx, set_sz,
+			       MLX5_SET_HCA_CAP_OP_MOD_ODP);
+
+	kfree(set_ctx);
+
+	return err;
+}
+
 static int handle_hca_cap(struct mlx5_core_dev *dev)
 {
 	void *set_ctx = NULL;
@@ -532,6 +578,32 @@ query_ex:
 	return err;
 }
 
+static int set_hca_cap(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = handle_hca_cap(dev);
+	if (err) {
+		mlx5_core_err(dev, "handle_hca_cap failed\n");
+		goto out;
+	}
+
+	err = handle_hca_cap_atomic(dev);
+	if (err) {
+		mlx5_core_err(dev, "handle_hca_cap_atomic failed\n");
+		goto out;
+	}
+
+	err = handle_hca_cap_odp(dev);
+	if (err) {
+		mlx5_core_err(dev, "handle_hca_cap_odp failed\n");
+		goto out;
+	}
+
+out:
+	return err;
+}
+
 static int set_hca_ctrl(struct mlx5_core_dev *dev)
 {
 	struct mlx5_reg_host_endianness he_in;
@@ -567,6 +639,8 @@ int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id)
 
 	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
 	MLX5_SET(enable_hca_in, in, function_id, func_id);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
+		 dev->caps.embedded_cpu);
 	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
 }
 
@@ -577,6 +651,8 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
 
 	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
 	MLX5_SET(disable_hca_in, in, function_id, func_id);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
+		 dev->caps.embedded_cpu);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
@@ -652,36 +728,27 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 	return -EOPNOTSUPP;
 }
 
-static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
+			 const struct pci_device_id *id)
 {
-	struct pci_dev *pdev = dev->pdev;
+	struct mlx5_priv *priv = &dev->priv;
 	int err = 0;
 
+	mutex_init(&dev->pci_status_mutex);
 	pci_set_drvdata(dev->pdev, dev);
-	strncpy(priv->name, dev_name(&pdev->dev), MLX5_MAX_NAME_LEN);
-	priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
-
-	mutex_init(&priv->pgdir_mutex);
-	INIT_LIST_HEAD(&priv->pgdir_list);
-	spin_lock_init(&priv->mkey_lock);
-
-	mutex_init(&priv->alloc_mutex);
 
+	dev->bar_addr = pci_resource_start(pdev, 0);
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
-	if (mlx5_debugfs_root)
-		priv->dbg_root =
-			debugfs_create_dir(pci_name(pdev), mlx5_debugfs_root);
-
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
-		goto err_dbg;
+		mlx5_core_err(dev, "Cannot enable PCI device, aborting\n");
+		return err;
 	}
 
 	err = request_bar(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "error requesting BARs, aborting\n");
+		mlx5_core_err(dev, "error requesting BARs, aborting\n");
 		goto err_disable;
 	}
 
@@ -689,18 +756,25 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	err = set_dma_caps(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed setting DMA capabilities mask, aborting\n");
+		mlx5_core_err(dev, "Failed setting DMA capabilities mask, aborting\n");
 		goto err_clr_master;
 	}
 
-	dev->iseg_base = pci_resource_start(dev->pdev, 0);
+	if (pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP32) &&
+	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP64) &&
+	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128))
+		mlx5_core_dbg(dev, "Enabling pci atomics failed\n");
+
+	dev->iseg_base = dev->bar_addr;
 	dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg));
 	if (!dev->iseg) {
 		err = -ENOMEM;
-		dev_err(&pdev->dev, "Failed mapping initialization segment, aborting\n");
+		mlx5_core_err(dev, "Failed mapping initialization segment, aborting\n");
 		goto err_clr_master;
 	}
 
+	mlx5_pci_vsc_init(dev);
+
 	return 0;
 
 err_clr_master:
@@ -708,52 +782,53 @@ err_clr_master:
 	release_bar(dev->pdev);
 err_disable:
 	mlx5_pci_disable_device(dev);
-
-err_dbg:
-	debugfs_remove(priv->dbg_root);
 	return err;
 }
 
-static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
 	mlx5_pci_disable_device(dev);
-	debugfs_remove_recursive(priv->dbg_root);
 }
 
-static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
+static int mlx5_init_once(struct mlx5_core_dev *dev)
 {
-	struct pci_dev *pdev = dev->pdev;
 	int err;
 
-	priv->devcom = mlx5_devcom_register_device(dev);
-	if (IS_ERR(priv->devcom))
-		dev_err(&pdev->dev, "failed to register with devcom (0x%p)\n",
-			priv->devcom);
+	dev->priv.devcom = mlx5_devcom_register_device(dev);
+	if (IS_ERR(dev->priv.devcom))
+		mlx5_core_err(dev, "failed to register with devcom (0x%p)\n",
+			      dev->priv.devcom);
 
 	err = mlx5_query_board_id(dev);
 	if (err) {
-		dev_err(&pdev->dev, "query board id failed\n");
+		mlx5_core_err(dev, "query board id failed\n");
 		goto err_devcom;
 	}
 
-	err = mlx5_eq_table_init(dev);
+	err = mlx5_irq_table_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to initialize eq\n");
+		mlx5_core_err(dev, "failed to initialize irq table\n");
 		goto err_devcom;
 	}
 
+	err = mlx5_eq_table_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize eq\n");
+		goto err_irq_cleanup;
+	}
+
 	err = mlx5_events_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to initialize events\n");
+		mlx5_core_err(dev, "failed to initialize events\n");
 		goto err_eq_cleanup;
 	}
 
 	err = mlx5_cq_debugfs_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to initialize cq debugfs\n");
+		mlx5_core_err(dev, "failed to initialize cq debugfs\n");
 		goto err_events_cleanup;
 	}
 
@@ -766,50 +841,52 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	mlx5_init_clock(dev);
 
 	dev->vxlan = mlx5_vxlan_create(dev);
+	dev->geneve = mlx5_geneve_create(dev);
 
 	err = mlx5_init_rl_table(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init rate limiting\n");
+		mlx5_core_err(dev, "Failed to init rate limiting\n");
 		goto err_tables_cleanup;
 	}
 
 	err = mlx5_mpfs_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init l2 table %d\n", err);
+		mlx5_core_err(dev, "Failed to init l2 table %d\n", err);
 		goto err_rl_cleanup;
 	}
 
-	err = mlx5_eswitch_init(dev);
+	err = mlx5_sriov_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init eswitch %d\n", err);
+		mlx5_core_err(dev, "Failed to init sriov %d\n", err);
 		goto err_mpfs_cleanup;
 	}
 
-	err = mlx5_sriov_init(dev);
+	err = mlx5_eswitch_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init sriov %d\n", err);
-		goto err_eswitch_cleanup;
+		mlx5_core_err(dev, "Failed to init eswitch %d\n", err);
+		goto err_sriov_cleanup;
 	}
 
 	err = mlx5_fpga_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init fpga device %d\n", err);
-		goto err_sriov_cleanup;
+		mlx5_core_err(dev, "Failed to init fpga device %d\n", err);
+		goto err_eswitch_cleanup;
 	}
 
 	dev->tracer = mlx5_fw_tracer_create(dev);
 
 	return 0;
 
-err_sriov_cleanup:
-	mlx5_sriov_cleanup(dev);
 err_eswitch_cleanup:
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
+err_sriov_cleanup:
+	mlx5_sriov_cleanup(dev);
 err_mpfs_cleanup:
 	mlx5_mpfs_cleanup(dev);
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
 err_tables_cleanup:
+	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_qp_table(dev);
@@ -818,6 +895,8 @@ err_events_cleanup:
 	mlx5_events_cleanup(dev);
 err_eq_cleanup:
 	mlx5_eq_table_cleanup(dev);
+err_irq_cleanup:
+	mlx5_irq_table_cleanup(dev);
 err_devcom:
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 
@@ -828,10 +907,11 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
 	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_fpga_cleanup(dev);
-	mlx5_sriov_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
+	mlx5_sriov_cleanup(dev);
 	mlx5_mpfs_cleanup(dev);
 	mlx5_cleanup_rl_table(dev);
+	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
@@ -840,101 +920,82 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_events_cleanup(dev);
 	mlx5_eq_table_cleanup(dev);
+	mlx5_irq_table_cleanup(dev);
 	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
-static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
-			 bool boot)
+static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 {
-	struct pci_dev *pdev = dev->pdev;
 	int err;
 
-	mutex_lock(&dev->intf_state_mutex);
-	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
-		dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n",
-			 __func__);
-		goto out;
-	}
-
-	dev_info(&pdev->dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev),
-		 fw_rev_min(dev), fw_rev_sub(dev));
+	mlx5_core_info(dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev),
+		       fw_rev_min(dev), fw_rev_sub(dev));
 
 	/* Only PFs hold the relevant PCIe information for this query */
 	if (mlx5_core_is_pf(dev))
 		pcie_print_link_status(dev->pdev);
 
-	/* on load removing any previous indication of internal error, device is
-	 * up
-	 */
-	dev->state = MLX5_DEVICE_STATE_UP;
-
 	/* wait for firmware to accept initialization segments configurations
 	 */
-	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI);
+	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI, FW_INIT_WARN_MESSAGE_INTERVAL);
 	if (err) {
-		dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n",
-			FW_PRE_INIT_TIMEOUT_MILI);
-		goto out_err;
+		mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n",
+			      FW_PRE_INIT_TIMEOUT_MILI);
+		return err;
 	}
 
 	err = mlx5_cmd_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed initializing command interface, aborting\n");
-		goto out_err;
+		mlx5_core_err(dev, "Failed initializing command interface, aborting\n");
+		return err;
 	}
 
-	err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI);
+	err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI, 0);
 	if (err) {
-		dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
-			FW_INIT_TIMEOUT_MILI);
+		mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n",
+			      FW_INIT_TIMEOUT_MILI);
 		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
-		dev_err(&pdev->dev, "enable hca failed\n");
+		mlx5_core_err(dev, "enable hca failed\n");
 		goto err_cmd_cleanup;
 	}
 
 	err = mlx5_core_set_issi(dev);
 	if (err) {
-		dev_err(&pdev->dev, "failed to set issi\n");
+		mlx5_core_err(dev, "failed to set issi\n");
 		goto err_disable_hca;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 1);
 	if (err) {
-		dev_err(&pdev->dev, "failed to allocate boot pages\n");
+		mlx5_core_err(dev, "failed to allocate boot pages\n");
 		goto err_disable_hca;
 	}
 
 	err = set_hca_ctrl(dev);
 	if (err) {
-		dev_err(&pdev->dev, "set_hca_ctrl failed\n");
+		mlx5_core_err(dev, "set_hca_ctrl failed\n");
 		goto reclaim_boot_pages;
 	}
 
-	err = handle_hca_cap(dev);
-	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap failed\n");
-		goto reclaim_boot_pages;
-	}
-
-	err = handle_hca_cap_atomic(dev);
+	err = set_hca_cap(dev);
 	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap_atomic failed\n");
+		mlx5_core_err(dev, "set_hca_cap failed\n");
 		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 0);
 	if (err) {
-		dev_err(&pdev->dev, "failed to allocate init pages\n");
+		mlx5_core_err(dev, "failed to allocate init pages\n");
 		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_cmd_init_hca(dev, sw_owner_id);
 	if (err) {
-		dev_err(&pdev->dev, "init hca failed\n");
+		mlx5_core_err(dev, "init hca failed\n");
 		goto reclaim_boot_pages;
 	}
 
@@ -944,157 +1005,225 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 
 	err = mlx5_query_hca_caps(dev);
 	if (err) {
-		dev_err(&pdev->dev, "query hca failed\n");
-		goto err_stop_poll;
+		mlx5_core_err(dev, "query hca failed\n");
+		goto stop_health;
 	}
 
-	if (boot) {
-		err = mlx5_init_once(dev, priv);
-		if (err) {
-			dev_err(&pdev->dev, "sw objs init failed\n");
-			goto err_stop_poll;
-		}
+	return 0;
+
+stop_health:
+	mlx5_stop_health_poll(dev, boot);
+reclaim_boot_pages:
+	mlx5_reclaim_startup_pages(dev);
+err_disable_hca:
+	mlx5_core_disable_hca(dev, 0);
+err_cmd_cleanup:
+	mlx5_cmd_cleanup(dev);
+
+	return err;
+}
+
+static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
+{
+	int err;
+
+	mlx5_stop_health_poll(dev, boot);
+	err = mlx5_cmd_teardown_hca(dev);
+	if (err) {
+		mlx5_core_err(dev, "tear_down_hca failed, skip cleanup\n");
+		return err;
 	}
+	mlx5_reclaim_startup_pages(dev);
+	mlx5_core_disable_hca(dev, 0);
+	mlx5_cmd_cleanup(dev);
+
+	return 0;
+}
+
+static int mlx5_load(struct mlx5_core_dev *dev)
+{
+	int err;
 
 	dev->priv.uar = mlx5_get_uars_page(dev);
 	if (IS_ERR(dev->priv.uar)) {
-		dev_err(&pdev->dev, "Failed allocating uar, aborting\n");
+		mlx5_core_err(dev, "Failed allocating uar, aborting\n");
 		err = PTR_ERR(dev->priv.uar);
-		goto err_get_uars;
+		return err;
 	}
 
 	mlx5_events_start(dev);
 	mlx5_pagealloc_start(dev);
 
+	err = mlx5_irq_table_create(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc IRQs\n");
+		goto err_irq_table;
+	}
+
 	err = mlx5_eq_table_create(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to create EQs\n");
+		mlx5_core_err(dev, "Failed to create EQs\n");
 		goto err_eq_table;
 	}
 
 	err = mlx5_fw_tracer_init(dev->tracer);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init FW tracer\n");
+		mlx5_core_err(dev, "Failed to init FW tracer\n");
 		goto err_fw_tracer;
 	}
 
 	err = mlx5_fpga_device_start(dev);
 	if (err) {
-		dev_err(&pdev->dev, "fpga device start failed %d\n", err);
+		mlx5_core_err(dev, "fpga device start failed %d\n", err);
 		goto err_fpga_start;
 	}
 
 	err = mlx5_accel_ipsec_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "IPSec device start failed %d\n", err);
+		mlx5_core_err(dev, "IPSec device start failed %d\n", err);
 		goto err_ipsec_start;
 	}
 
 	err = mlx5_accel_tls_init(dev);
 	if (err) {
-		dev_err(&pdev->dev, "TLS device start failed %d\n", err);
+		mlx5_core_err(dev, "TLS device start failed %d\n", err);
 		goto err_tls_start;
 	}
 
 	err = mlx5_init_fs(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to init flow steering\n");
+		mlx5_core_err(dev, "Failed to init flow steering\n");
 		goto err_fs;
 	}
 
 	err = mlx5_core_set_hca_defaults(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to set hca defaults\n");
-		goto err_fs;
+		mlx5_core_err(dev, "Failed to set hca defaults\n");
+		goto err_sriov;
 	}
 
 	err = mlx5_sriov_attach(dev);
 	if (err) {
-		dev_err(&pdev->dev, "sriov init failed %d\n", err);
+		mlx5_core_err(dev, "sriov init failed %d\n", err);
 		goto err_sriov;
 	}
 
-	if (mlx5_device_registered(dev)) {
-		mlx5_attach_device(dev);
-	} else {
-		err = mlx5_register_device(dev);
-		if (err) {
-			dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err);
-			goto err_reg_dev;
-		}
+	err = mlx5_ec_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to init embedded CPU\n");
+		goto err_ec;
 	}
 
-	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
-out:
-	mutex_unlock(&dev->intf_state_mutex);
-
 	return 0;
 
-err_reg_dev:
+err_ec:
 	mlx5_sriov_detach(dev);
-
 err_sriov:
 	mlx5_cleanup_fs(dev);
-
 err_fs:
 	mlx5_accel_tls_cleanup(dev);
-
 err_tls_start:
 	mlx5_accel_ipsec_cleanup(dev);
-
 err_ipsec_start:
 	mlx5_fpga_device_stop(dev);
-
 err_fpga_start:
 	mlx5_fw_tracer_cleanup(dev->tracer);
-
 err_fw_tracer:
 	mlx5_eq_table_destroy(dev);
-
 err_eq_table:
+	mlx5_irq_table_destroy(dev);
+err_irq_table:
 	mlx5_pagealloc_stop(dev);
 	mlx5_events_stop(dev);
-	mlx5_put_uars_page(dev, priv->uar);
+	mlx5_put_uars_page(dev, dev->priv.uar);
+	return err;
+}
 
-err_get_uars:
-	if (boot)
-		mlx5_cleanup_once(dev);
+static void mlx5_unload(struct mlx5_core_dev *dev)
+{
+	mlx5_ec_cleanup(dev);
+	mlx5_sriov_detach(dev);
+	mlx5_cleanup_fs(dev);
+	mlx5_accel_ipsec_cleanup(dev);
+	mlx5_accel_tls_cleanup(dev);
+	mlx5_fpga_device_stop(dev);
+	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_eq_table_destroy(dev);
+	mlx5_irq_table_destroy(dev);
+	mlx5_pagealloc_stop(dev);
+	mlx5_events_stop(dev);
+	mlx5_put_uars_page(dev, dev->priv.uar);
+}
 
-err_stop_poll:
-	mlx5_stop_health_poll(dev, boot);
-	if (mlx5_cmd_teardown_hca(dev)) {
-		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
-		goto out_err;
+static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
+{
+	int err = 0;
+
+	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
+	mutex_lock(&dev->intf_state_mutex);
+	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
+		mlx5_core_warn(dev, "interface is up, NOP\n");
+		goto out;
 	}
+	/* remove any previous indication of internal error */
+	dev->state = MLX5_DEVICE_STATE_UP;
 
-reclaim_boot_pages:
-	mlx5_reclaim_startup_pages(dev);
+	err = mlx5_function_setup(dev, boot);
+	if (err)
+		goto out;
 
-err_disable_hca:
-	mlx5_core_disable_hca(dev, 0);
+	if (boot) {
+		err = mlx5_init_once(dev);
+		if (err) {
+			mlx5_core_err(dev, "sw objs init failed\n");
+			goto function_teardown;
+		}
+	}
 
-err_cmd_cleanup:
-	mlx5_cmd_cleanup(dev);
+	err = mlx5_load(dev);
+	if (err)
+		goto err_load;
 
-out_err:
+	if (mlx5_device_registered(dev)) {
+		mlx5_attach_device(dev);
+	} else {
+		err = mlx5_register_device(dev);
+		if (err) {
+			mlx5_core_err(dev, "register device failed %d\n", err);
+			goto err_reg_dev;
+		}
+	}
+
+	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
+out:
+	mutex_unlock(&dev->intf_state_mutex);
+
+	return err;
+
+err_reg_dev:
+	mlx5_unload(dev);
+err_load:
+	if (boot)
+		mlx5_cleanup_once(dev);
+function_teardown:
+	mlx5_function_teardown(dev, boot);
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 	mutex_unlock(&dev->intf_state_mutex);
 
 	return err;
 }
 
-static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
-			   bool cleanup)
+static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 {
 	int err = 0;
 
 	if (cleanup)
-		mlx5_drain_health_recovery(dev);
+		mlx5_drain_health_wq(dev);
 
 	mutex_lock(&dev->intf_state_mutex);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
-		dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n",
-			 __func__);
+		mlx5_core_warn(dev, "%s: interface is down, NOP\n",
+			       __func__);
 		if (cleanup)
 			mlx5_cleanup_once(dev);
 		goto out;
@@ -1105,72 +1234,26 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (mlx5_device_registered(dev))
 		mlx5_detach_device(dev);
 
-	mlx5_sriov_detach(dev);
-	mlx5_cleanup_fs(dev);
-	mlx5_accel_ipsec_cleanup(dev);
-	mlx5_accel_tls_cleanup(dev);
-	mlx5_fpga_device_stop(dev);
-	mlx5_fw_tracer_cleanup(dev->tracer);
-	mlx5_eq_table_destroy(dev);
-	mlx5_pagealloc_stop(dev);
-	mlx5_events_stop(dev);
-	mlx5_put_uars_page(dev, priv->uar);
+	mlx5_unload(dev);
+
 	if (cleanup)
 		mlx5_cleanup_once(dev);
-	mlx5_stop_health_poll(dev, cleanup);
-
-	err = mlx5_cmd_teardown_hca(dev);
-	if (err) {
-		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
-		goto out;
-	}
-	mlx5_reclaim_startup_pages(dev);
-	mlx5_core_disable_hca(dev, 0);
-	mlx5_cmd_cleanup(dev);
 
+	mlx5_function_teardown(dev, cleanup);
 out:
 	mutex_unlock(&dev->intf_state_mutex);
 	return err;
 }
 
-static const struct devlink_ops mlx5_devlink_ops = {
-#ifdef CONFIG_MLX5_ESWITCH
-	.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
-	.eswitch_mode_get = mlx5_devlink_eswitch_mode_get,
-	.eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set,
-	.eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get,
-	.eswitch_encap_mode_set = mlx5_devlink_eswitch_encap_mode_set,
-	.eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get,
-#endif
-};
-
-#define MLX5_IB_MOD "mlx5_ib"
-static int init_one(struct pci_dev *pdev,
-		    const struct pci_device_id *id)
+static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
-	struct mlx5_core_dev *dev;
-	struct devlink *devlink;
-	struct mlx5_priv *priv;
+	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	devlink = devlink_alloc(&mlx5_devlink_ops, sizeof(*dev));
-	if (!devlink) {
-		dev_err(&pdev->dev, "kzalloc failed\n");
-		return -ENOMEM;
-	}
-
-	dev = devlink_priv(devlink);
-	priv = &dev->priv;
-	priv->pci_dev_data = id->driver_data;
-
-	pci_set_drvdata(pdev, dev);
-
-	dev->pdev = pdev;
-	dev->profile = &profile[prof_sel];
+	dev->profile = &profile[profile_idx];
 
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
-	mutex_init(&dev->pci_status_mutex);
 	mutex_init(&dev->intf_state_mutex);
 
 	mutex_init(&priv->bfregs.reg_head.lock);
@@ -1178,47 +1261,103 @@ static int init_one(struct pci_dev *pdev,
 	INIT_LIST_HEAD(&priv->bfregs.reg_head.list);
 	INIT_LIST_HEAD(&priv->bfregs.wc_head.list);
 
-	err = mlx5_pci_init(dev, priv);
-	if (err) {
-		dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err);
-		goto clean_dev;
+	mutex_init(&priv->alloc_mutex);
+	mutex_init(&priv->pgdir_mutex);
+	INIT_LIST_HEAD(&priv->pgdir_list);
+	spin_lock_init(&priv->mkey_lock);
+
+	priv->dbg_root = debugfs_create_dir(dev_name(dev->device),
+					    mlx5_debugfs_root);
+	if (!priv->dbg_root) {
+		dev_err(dev->device, "mlx5_core: error, Cannot create debugfs dir, aborting\n");
+		return -ENOMEM;
 	}
 
 	err = mlx5_health_init(dev);
-	if (err) {
-		dev_err(&pdev->dev, "mlx5_health_init failed with error code %d\n", err);
-		goto close_pci;
-	}
+	if (err)
+		goto err_health_init;
 
 	err = mlx5_pagealloc_init(dev);
 	if (err)
 		goto err_pagealloc_init;
 
-	err = mlx5_load_one(dev, priv, true);
+	return 0;
+
+err_pagealloc_init:
+	mlx5_health_cleanup(dev);
+err_health_init:
+	debugfs_remove(dev->priv.dbg_root);
+
+	return err;
+}
+
+static void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
+{
+	mlx5_pagealloc_cleanup(dev);
+	mlx5_health_cleanup(dev);
+	debugfs_remove_recursive(dev->priv.dbg_root);
+}
+
+#define MLX5_IB_MOD "mlx5_ib"
+static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct mlx5_core_dev *dev;
+	struct devlink *devlink;
+	int err;
+
+	devlink = mlx5_devlink_alloc();
+	if (!devlink) {
+		dev_err(&pdev->dev, "devlink alloc failed\n");
+		return -ENOMEM;
+	}
+
+	dev = devlink_priv(devlink);
+	dev->device = &pdev->dev;
+	dev->pdev = pdev;
+
+	dev->coredev_type = id->driver_data & MLX5_PCI_DEV_IS_VF ?
+			 MLX5_COREDEV_VF : MLX5_COREDEV_PF;
+
+	err = mlx5_mdev_init(dev, prof_sel);
+	if (err)
+		goto mdev_init_err;
+
+	err = mlx5_pci_init(dev, pdev, id);
 	if (err) {
-		dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err);
+		mlx5_core_err(dev, "mlx5_pci_init failed with error code %d\n",
+			      err);
+		goto pci_init_err;
+	}
+
+	err = mlx5_load_one(dev, true);
+	if (err) {
+		mlx5_core_err(dev, "mlx5_load_one failed with error code %d\n",
+			      err);
 		goto err_load_one;
 	}
 
 	request_module_nowait(MLX5_IB_MOD);
 
-	err = devlink_register(devlink, &pdev->dev);
+	err = mlx5_devlink_register(devlink, &pdev->dev);
 	if (err)
 		goto clean_load;
 
+	err = mlx5_crdump_enable(dev);
+	if (err)
+		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
+
 	pci_save_state(pdev);
 	return 0;
 
 clean_load:
-	mlx5_unload_one(dev, priv, true);
+	mlx5_unload_one(dev, true);
+
 err_load_one:
-	mlx5_pagealloc_cleanup(dev);
-err_pagealloc_init:
-	mlx5_health_cleanup(dev);
-close_pci:
-	mlx5_pci_close(dev, priv);
-clean_dev:
-	devlink_free(devlink);
+	mlx5_pci_close(dev);
+pci_init_err:
+	mlx5_mdev_uninit(dev);
+mdev_init_err:
+	mlx5_devlink_free(devlink);
 
 	return err;
 }
@@ -1227,38 +1366,34 @@ static void remove_one(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
-	struct mlx5_priv *priv = &dev->priv;
 
-	devlink_unregister(devlink);
+	mlx5_crdump_disable(dev);
+	mlx5_devlink_unregister(devlink);
 	mlx5_unregister_device(dev);
 
-	if (mlx5_unload_one(dev, priv, true)) {
-		dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n");
-		mlx5_health_cleanup(dev);
+	if (mlx5_unload_one(dev, true)) {
+		mlx5_core_err(dev, "mlx5_unload_one failed\n");
+		mlx5_health_flush(dev);
 		return;
 	}
 
-	mlx5_pagealloc_cleanup(dev);
-	mlx5_health_cleanup(dev);
-	mlx5_pci_close(dev, priv);
-	devlink_free(devlink);
+	mlx5_pci_close(dev);
+	mlx5_mdev_uninit(dev);
+	mlx5_devlink_free(devlink);
 }
 
 static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev,
 					      pci_channel_state_t state)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
-	struct mlx5_priv *priv = &dev->priv;
 
-	dev_info(&pdev->dev, "%s was called\n", __func__);
+	mlx5_core_info(dev, "%s was called\n", __func__);
 
 	mlx5_enter_error_state(dev, false);
-	mlx5_unload_one(dev, priv, false);
-	/* In case of kernel call drain the health wq */
-	if (state) {
-		mlx5_drain_health_wq(dev);
-		mlx5_pci_disable_device(dev);
-	}
+	mlx5_error_sw_reset(dev);
+	mlx5_unload_one(dev, false);
+	mlx5_drain_health_wq(dev);
+	mlx5_pci_disable_device(dev);
 
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -1280,7 +1415,9 @@ static int wait_vital(struct pci_dev *pdev)
 		count = ioread32be(health->health_counter);
 		if (count && count != 0xffffffff) {
 			if (last_count && last_count != count) {
-				dev_info(&pdev->dev, "Counter value 0x%x after %d iterations\n", count, i);
+				mlx5_core_info(dev,
+					       "wait vital counter value 0x%x after %d iterations\n",
+					       count, i);
 				return 0;
 			}
 			last_count = count;
@@ -1296,12 +1433,12 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
 	int err;
 
-	dev_info(&pdev->dev, "%s was called\n", __func__);
+	mlx5_core_info(dev, "%s was called\n", __func__);
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
-		dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
-			, __func__, err);
+		mlx5_core_err(dev, "%s: mlx5_pci_enable_device failed with error code: %d\n",
+			      __func__, err);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -1310,7 +1447,7 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 	pci_save_state(pdev);
 
 	if (wait_vital(pdev)) {
-		dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
+		mlx5_core_err(dev, "%s: wait_vital timed out\n", __func__);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -1320,17 +1457,16 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
 static void mlx5_pci_resume(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
-	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	dev_info(&pdev->dev, "%s was called\n", __func__);
+	mlx5_core_info(dev, "%s was called\n", __func__);
 
-	err = mlx5_load_one(dev, priv, false);
+	err = mlx5_load_one(dev, false);
 	if (err)
-		dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n"
-			, __func__, err);
+		mlx5_core_err(dev, "%s: mlx5_load_one failed with error code: %d\n",
+			      __func__, err);
 	else
-		dev_info(&pdev->dev, "%s: device recovered\n", __func__);
+		mlx5_core_info(dev, "%s: device recovered\n", __func__);
 }
 
 static const struct pci_error_handlers mlx5_err_handler = {
@@ -1392,13 +1528,12 @@ succeed:
 static void shutdown(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
-	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	dev_info(&pdev->dev, "Shutdown was called\n");
+	mlx5_core_info(dev, "Shutdown was called\n");
 	err = mlx5_try_fast_unload(dev);
 	if (err)
-		mlx5_unload_one(dev, priv, false);
+		mlx5_unload_one(dev, false);
 	mlx5_pci_disable_device(dev);
 }
 
@@ -1415,6 +1550,8 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5 Ex VF */
 	{ PCI_VDEVICE(MELLANOX, 0x101b) },			/* ConnectX-6 */
 	{ PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF},	/* ConnectX-6 VF */
+	{ PCI_VDEVICE(MELLANOX, 0x101d) },			/* ConnectX-6 Dx */
+	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ 0, }
@@ -1424,7 +1561,8 @@ MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table);
 
 void mlx5_disable_device(struct mlx5_core_dev *dev)
 {
-	mlx5_pci_err_detected(dev->pdev, 0);
+	mlx5_error_sw_reset(dev);
+	mlx5_unload_one(dev, false);
 }
 
 void mlx5_recover_device(struct mlx5_core_dev *dev)
@@ -1462,7 +1600,7 @@ static int __init init(void)
 	get_random_bytes(&sw_owner_id, sizeof(sw_owner_id));
 
 	mlx5_core_verify_params();
-	mlx5_fpga_ipsec_build_fs_cmds();
+	mlx5_accel_ipsec_build_fs_cmds();
 	mlx5_register_debugfs();
 
 	err = pci_register_driver(&mlx5_core_driver);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 5300b0b6d836..471bbc48bc1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -41,6 +41,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/driver.h>
 
 #define DRIVER_NAME "mlx5_core"
 #define DRIVER_VERSION "5.0-0"
@@ -48,44 +49,57 @@
 extern uint mlx5_core_debug_mask;
 
 #define mlx5_core_dbg(__dev, format, ...)				\
-	dev_dbg(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,		\
+	dev_dbg((__dev)->device, "%s:%d:(pid %d): " format,		\
 		 __func__, __LINE__, current->pid,			\
 		 ##__VA_ARGS__)
 
-#define mlx5_core_dbg_once(__dev, format, ...)				\
-	dev_dbg_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
-		     __func__, __LINE__, current->pid,			\
+#define mlx5_core_dbg_once(__dev, format, ...)		\
+	dev_dbg_once((__dev)->device,		\
+		     "%s:%d:(pid %d): " format,		\
+		     __func__, __LINE__, current->pid,	\
 		     ##__VA_ARGS__)
 
-#define mlx5_core_dbg_mask(__dev, mask, format, ...)			\
-do {									\
-	if ((mask) & mlx5_core_debug_mask)				\
-		mlx5_core_dbg(__dev, format, ##__VA_ARGS__);		\
+#define mlx5_core_dbg_mask(__dev, mask, format, ...)		\
+do {								\
+	if ((mask) & mlx5_core_debug_mask)			\
+		mlx5_core_dbg(__dev, format, ##__VA_ARGS__);	\
 } while (0)
 
-#define mlx5_core_err(__dev, format, ...)				\
-	dev_err(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
-		__func__, __LINE__, current->pid,	\
+#define mlx5_core_err(__dev, format, ...)			\
+	dev_err((__dev)->device, "%s:%d:(pid %d): " format,	\
+		__func__, __LINE__, current->pid,		\
 	       ##__VA_ARGS__)
 
-#define mlx5_core_err_rl(__dev, format, ...)				\
-	dev_err_ratelimited(&(__dev)->pdev->dev,			\
-			   "%s:%d:(pid %d): " format,			\
-			   __func__, __LINE__, current->pid,		\
-			   ##__VA_ARGS__)
+#define mlx5_core_err_rl(__dev, format, ...)			\
+	dev_err_ratelimited((__dev)->device,			\
+			    "%s:%d:(pid %d): " format,		\
+			    __func__, __LINE__, current->pid,	\
+			    ##__VA_ARGS__)
 
-#define mlx5_core_warn(__dev, format, ...)				\
-	dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
-		 __func__, __LINE__, current->pid,			\
-		##__VA_ARGS__)
+#define mlx5_core_warn(__dev, format, ...)			\
+	dev_warn((__dev)->device, "%s:%d:(pid %d): " format,	\
+		 __func__, __LINE__, current->pid,		\
+		 ##__VA_ARGS__)
 
 #define mlx5_core_warn_once(__dev, format, ...)				\
-	dev_warn_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
+	dev_warn_once((__dev)->device, "%s:%d:(pid %d): " format,	\
 		      __func__, __LINE__, current->pid,			\
 		      ##__VA_ARGS__)
 
-#define mlx5_core_info(__dev, format, ...)				\
-	dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__)
+#define mlx5_core_warn_rl(__dev, format, ...)			\
+	dev_warn_ratelimited((__dev)->device,			\
+			     "%s:%d:(pid %d): " format,		\
+			     __func__, __LINE__, current->pid,	\
+			     ##__VA_ARGS__)
+
+#define mlx5_core_info(__dev, format, ...)		\
+	dev_info((__dev)->device, format, ##__VA_ARGS__)
+
+#define mlx5_core_info_rl(__dev, format, ...)			\
+	dev_info_ratelimited((__dev)->device,			\
+			     "%s:%d:(pid %d): " format,		\
+			     __func__, __LINE__, current->pid,	\
+			     ##__VA_ARGS__)
 
 enum {
 	MLX5_CMD_DATA, /* print command payload only */
@@ -97,6 +111,11 @@ enum {
 	MLX5_DRIVER_SYND = 0xbadd00de,
 };
 
+enum mlx5_semaphore_space_address {
+	MLX5_SEMAPHORE_SPACE_DOMAIN     = 0xA,
+	MLX5_SEMAPHORE_SW_RESET         = 0x20,
+};
+
 int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
 int mlx5_query_board_id(struct mlx5_core_dev *dev);
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
@@ -104,6 +123,7 @@ int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
+void mlx5_error_sw_reset(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);
 int mlx5_sriov_init(struct mlx5_core_dev *dev);
@@ -111,7 +131,6 @@ void mlx5_sriov_cleanup(struct mlx5_core_dev *dev);
 int mlx5_sriov_attach(struct mlx5_core_dev *dev);
 void mlx5_sriov_detach(struct mlx5_core_dev *dev);
 int mlx5_core_sriov_configure(struct pci_dev *dev, int num_vfs);
-bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev);
 int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id);
 int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id);
 int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
@@ -121,11 +140,12 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 				       u32 modify_bitmask);
 int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
-int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
+int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
 			     struct ptp_system_timestamp *sts);
 
 void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev);
+void mlx5_cmd_flush(struct mlx5_core_dev *dev);
 int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
 
@@ -139,6 +159,19 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
 void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_remove(struct mlx5_core_dev *dev);
 
+int mlx5_irq_table_init(struct mlx5_core_dev *dev);
+void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
+int mlx5_irq_table_create(struct mlx5_core_dev *dev);
+void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
+int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb);
+int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb);
+struct cpumask *
+mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx);
+struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *table);
+int mlx5_irq_get_num_comp(struct mlx5_irq_table *table);
+
 int mlx5_events_init(struct mlx5_core_dev *dev);
 void mlx5_events_cleanup(struct mlx5_core_dev *dev);
 void mlx5_events_start(struct mlx5_core_dev *dev);
@@ -170,11 +203,19 @@ int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) &&	\
 			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_enh_out_per_adj))
 
-int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw);
+int mlx5_firmware_flash(struct mlx5_core_dev *dev, const struct firmware *fw,
+			struct netlink_ext_ack *extack);
+int mlx5_fw_version_query(struct mlx5_core_dev *dev,
+			  u32 *running_ver, u32 *stored_ver);
 
 void mlx5e_init(void);
 void mlx5e_cleanup(void);
 
+static inline bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev)
+{
+	return pci_num_vf(dev->pdev) ? true : false;
+}
+
 static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev)
 {
 	/* LACP owner conditions:
@@ -187,8 +228,6 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev)
 		    MLX5_CAP_GEN(dev, lag_master);
 }
 
-int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num);
-
 void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol);
 void mlx5_lag_update(struct mlx5_core_dev *dev);
 
@@ -196,7 +235,7 @@ enum {
 	MLX5_NIC_IFC_FULL		= 0,
 	MLX5_NIC_IFC_DISABLED		= 1,
 	MLX5_NIC_IFC_NO_DRAM_NIC	= 2,
-	MLX5_NIC_IFC_INVALID		= 3
+	MLX5_NIC_IFC_SW_RESET		= 7
 };
 
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 0670165afd5f..9231b39d18b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -38,25 +38,23 @@
 
 void mlx5_init_mkey_table(struct mlx5_core_dev *dev)
 {
-	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
-
-	memset(table, 0, sizeof(*table));
-	rwlock_init(&table->lock);
-	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+	xa_init_flags(&dev->priv.mkey_table, XA_FLAGS_LOCK_IRQ);
 }
 
 void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev)
 {
+	WARN_ON(!xa_empty(&dev->priv.mkey_table));
 }
 
 int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 			     struct mlx5_core_mkey *mkey,
-			     u32 *in, int inlen,
-			     u32 *out, int outlen,
-			     mlx5_cmd_cbk_t callback, void *context)
+			     struct mlx5_async_ctx *async_ctx, u32 *in,
+			     int inlen, u32 *out, int outlen,
+			     mlx5_async_cbk_t callback,
+			     struct mlx5_async_work *context)
 {
-	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0};
+	struct xarray *mkeys = &dev->priv.mkey_table;
 	u32 mkey_index;
 	void *mkc;
 	int err;
@@ -71,7 +69,7 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 	MLX5_SET(mkc, mkc, mkey_7_0, key);
 
 	if (callback)
-		return mlx5_cmd_exec_cb(dev, in, inlen, out, outlen,
+		return mlx5_cmd_exec_cb(async_ctx, in, inlen, out, outlen,
 					callback, context);
 
 	err = mlx5_cmd_exec(dev, in, inlen, lout, sizeof(lout));
@@ -87,12 +85,10 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n",
 		      mkey_index, key, mkey->key);
 
-	/* connect to mkey tree */
-	write_lock_irq(&table->lock);
-	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mkey->key), mkey);
-	write_unlock_irq(&table->lock);
+	err = xa_err(xa_store_irq(mkeys, mlx5_base_mkey(mkey->key), mkey,
+				  GFP_KERNEL));
 	if (err) {
-		mlx5_core_warn(dev, "failed radix tree insert of mkey 0x%x, %d\n",
+		mlx5_core_warn(dev, "failed xarray insert of mkey 0x%x, %d\n",
 			       mlx5_base_mkey(mkey->key), err);
 		mlx5_core_destroy_mkey(dev, mkey);
 	}
@@ -105,7 +101,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 			  struct mlx5_core_mkey *mkey,
 			  u32 *in, int inlen)
 {
-	return mlx5_core_create_mkey_cb(dev, mkey, in, inlen,
+	return mlx5_core_create_mkey_cb(dev, mkey, NULL, in, inlen,
 					NULL, 0, NULL, NULL);
 }
 EXPORT_SYMBOL(mlx5_core_create_mkey);
@@ -113,17 +109,17 @@ EXPORT_SYMBOL(mlx5_core_create_mkey);
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
 			   struct mlx5_core_mkey *mkey)
 {
-	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	u32 out[MLX5_ST_SZ_DW(destroy_mkey_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)]   = {0};
+	struct xarray *mkeys = &dev->priv.mkey_table;
 	struct mlx5_core_mkey *deleted_mkey;
 	unsigned long flags;
 
-	write_lock_irqsave(&table->lock, flags);
-	deleted_mkey = radix_tree_delete(&table->tree, mlx5_base_mkey(mkey->key));
-	write_unlock_irqrestore(&table->lock, flags);
+	xa_lock_irqsave(mkeys, flags);
+	deleted_mkey = __xa_erase(mkeys, mlx5_base_mkey(mkey->key));
+	xa_unlock_irqrestore(mkeys, flags);
 	if (!deleted_mkey) {
-		mlx5_core_dbg(dev, "failed radix tree delete of mkey 0x%x\n",
+		mlx5_core_dbg(dev, "failed xarray delete of mkey 0x%x\n",
 			      mlx5_base_mkey(mkey->key));
 		return -ENOENT;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index a83b517b0714..91bd258ecf1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -48,6 +48,7 @@ enum {
 struct mlx5_pages_req {
 	struct mlx5_core_dev *dev;
 	u16	func_id;
+	u8	ec_function;
 	s32	npages;
 	struct work_struct work;
 };
@@ -143,6 +144,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 	MLX5_SET(query_pages_in, in, op_mod, boot ?
 		 MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES :
 		 MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES);
+	MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev));
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -198,7 +200,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 		rb_erase(&fwp->rb_node, &dev->priv.page_root);
 		if (fwp->free_count != 1)
 			list_del(&fwp->list);
-		dma_unmap_page(&dev->pdev->dev, addr & MLX5_U64_4K_PAGE_MASK,
+		dma_unmap_page(dev->device, addr & MLX5_U64_4K_PAGE_MASK,
 			       PAGE_SIZE, DMA_BIDIRECTIONAL);
 		__free_page(fwp->page);
 		kfree(fwp);
@@ -209,11 +211,12 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 
 static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 {
+	struct device *device = dev->device;
+	int nid = dev_to_node(device);
 	struct page *page;
 	u64 zero_addr = 1;
 	u64 addr;
 	int err;
-	int nid = dev_to_node(&dev->pdev->dev);
 
 	page = alloc_pages_node(nid, GFP_HIGHUSER, 0);
 	if (!page) {
@@ -221,9 +224,8 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id)
 		return -ENOMEM;
 	}
 map:
-	addr = dma_map_page(&dev->pdev->dev, page, 0,
-			    PAGE_SIZE, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(&dev->pdev->dev, addr)) {
+	addr = dma_map_page(device, page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(device, addr)) {
 		mlx5_core_warn(dev, "failed dma mapping page\n");
 		err = -ENOMEM;
 		goto err_mapping;
@@ -238,8 +240,7 @@ map:
 	err = insert_page(dev, addr, page, func_id);
 	if (err) {
 		mlx5_core_err(dev, "failed to track allocated page\n");
-		dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE,
-			       DMA_BIDIRECTIONAL);
+		dma_unmap_page(device, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
 	}
 
 err_mapping:
@@ -247,13 +248,14 @@ err_mapping:
 		__free_page(page);
 
 	if (zero_addr == 0)
-		dma_unmap_page(&dev->pdev->dev, zero_addr, PAGE_SIZE,
+		dma_unmap_page(device, zero_addr, PAGE_SIZE,
 			       DMA_BIDIRECTIONAL);
 
 	return err;
 }
 
-static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
+static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
+			     bool ec_function)
 {
 	u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(manage_pages_in)]   = {0};
@@ -262,6 +264,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
 	MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -270,7 +273,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
 }
 
 static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
-		      int notify_fail)
+		      int notify_fail, bool ec_function)
 {
 	u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
 	int inlen = MLX5_ST_SZ_BYTES(manage_pages_in);
@@ -305,6 +308,7 @@ retry:
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
 	MLX5_SET(manage_pages_in, in, input_num_entries, npages);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 	if (err) {
@@ -316,8 +320,11 @@ retry:
 	dev->priv.fw_pages += npages;
 	if (func_id)
 		dev->priv.vfs_pages += npages;
+	else if (mlx5_core_is_ecpf(dev) && !ec_function)
+		dev->priv.peer_pf_pages += npages;
 
-	mlx5_core_dbg(dev, "err %d\n", err);
+	mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
+		      npages, ec_function, func_id, err);
 
 	kvfree(in);
 	return 0;
@@ -328,7 +335,7 @@ out_4k:
 out_free:
 	kvfree(in);
 	if (notify_fail)
-		page_notify_fail(dev, func_id);
+		page_notify_fail(dev, func_id, ec_function);
 	return err;
 }
 
@@ -364,7 +371,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 }
 
 static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
-			 int *nclaimed)
+			 int *nclaimed, bool ec_function)
 {
 	int outlen = MLX5_ST_SZ_BYTES(manage_pages_out);
 	u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0};
@@ -385,6 +392,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
 	MLX5_SET(manage_pages_in, in, input_num_entries, npages);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
 	err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen);
@@ -410,6 +418,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	dev->priv.fw_pages -= num_claimed;
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
+	else if (mlx5_core_is_ecpf(dev) && !ec_function)
+		dev->priv.peer_pf_pages -= num_claimed;
 
 out_free:
 	kvfree(out);
@@ -423,9 +433,10 @@ static void pages_work_handler(struct work_struct *work)
 	int err = 0;
 
 	if (req->npages < 0)
-		err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL);
+		err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL,
+				    req->ec_function);
 	else if (req->npages > 0)
-		err = give_pages(dev, req->func_id, req->npages, 1);
+		err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function);
 
 	if (err)
 		mlx5_core_warn(dev, "%s fail %d\n",
@@ -434,6 +445,10 @@ static void pages_work_handler(struct work_struct *work)
 	kfree(req);
 }
 
+enum {
+	EC_FUNCTION_MASK = 0x8000,
+};
+
 static int req_pages_handler(struct notifier_block *nb,
 			     unsigned long type, void *data)
 {
@@ -441,6 +456,7 @@ static int req_pages_handler(struct notifier_block *nb,
 	struct mlx5_core_dev *dev;
 	struct mlx5_priv *priv;
 	struct mlx5_eqe *eqe;
+	bool ec_function;
 	u16 func_id;
 	s32 npages;
 
@@ -450,6 +466,7 @@ static int req_pages_handler(struct notifier_block *nb,
 
 	func_id = be16_to_cpu(eqe->data.req_pages.func_id);
 	npages  = be32_to_cpu(eqe->data.req_pages.num_pages);
+	ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK;
 	mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
 		      func_id, npages);
 	req = kzalloc(sizeof(*req), GFP_ATOMIC);
@@ -461,6 +478,7 @@ static int req_pages_handler(struct notifier_block *nb,
 	req->dev = dev;
 	req->func_id = func_id;
 	req->npages = npages;
+	req->ec_function = ec_function;
 	INIT_WORK(&req->work, pages_work_handler);
 	queue_work(dev->priv.pg_wq, &req->work);
 	return NOTIFY_OK;
@@ -479,7 +497,7 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
 	mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
 		      npages, boot ? "boot" : "init", func_id);
 
-	return give_pages(dev, func_id, npages, 0);
+	return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev));
 }
 
 enum {
@@ -513,7 +531,7 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 			fwp = rb_entry(p, struct fw_page, rb_node);
 			err = reclaim_pages(dev, fwp->func_id,
 					    optimal_reclaimed_pages(),
-					    &nclaimed);
+					    &nclaimed, mlx5_core_is_ecpf(dev));
 
 			if (err) {
 				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
@@ -535,6 +553,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 	WARN(dev->priv.vfs_pages,
 	     "VFs FW pages counter is %d after reclaiming all pages\n",
 	     dev->priv.vfs_pages);
+	WARN(dev->priv.peer_pf_pages,
+	     "Peer PF FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.peer_pf_pages);
 
 	return 0;
 }
@@ -567,10 +588,10 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev)
 	flush_workqueue(dev->priv.pg_wq);
 }
 
-int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
+int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
 {
 	unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS);
-	int prev_vfs_pages = dev->priv.vfs_pages;
+	int prev_pages = *pages;
 
 	/* In case of internal error we will free the pages manually later */
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -578,20 +599,19 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
 		return 0;
 	}
 
-	mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_vfs_pages,
-		      dev->priv.name);
-	while (dev->priv.vfs_pages) {
+	mlx5_core_dbg(dev, "Waiting for %d pages\n", prev_pages);
+	while (*pages) {
 		if (time_after(jiffies, end)) {
-			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", dev->priv.vfs_pages);
+			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages);
 			return -ETIMEDOUT;
 		}
-		if (dev->priv.vfs_pages < prev_vfs_pages) {
+		if (*pages < prev_pages) {
 			end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS);
-			prev_vfs_pages = dev->priv.vfs_pages;
+			prev_pages = *pages;
 		}
 		msleep(50);
 	}
 
-	mlx5_core_dbg(dev, "All pages received from %s\n", dev->priv.name);
+	mlx5_core_dbg(dev, "All pages received\n");
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
new file mode 100644
index 000000000000..373981a659c7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -0,0 +1,334 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
+
+#define MLX5_MAX_IRQ_NAME (32)
+
+struct mlx5_irq {
+	struct atomic_notifier_head nh;
+	cpumask_var_t mask;
+	char name[MLX5_MAX_IRQ_NAME];
+};
+
+struct mlx5_irq_table {
+	struct mlx5_irq *irq;
+	int nvec;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap *rmap;
+#endif
+};
+
+int mlx5_irq_table_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *irq_table;
+
+	irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL);
+	if (!irq_table)
+		return -ENOMEM;
+
+	dev->priv.irq_table = irq_table;
+	return 0;
+}
+
+void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
+{
+	kvfree(dev->priv.irq_table);
+}
+
+int mlx5_irq_get_num_comp(struct mlx5_irq_table *table)
+{
+	return table->nvec - MLX5_IRQ_VEC_COMP_BASE;
+}
+
+static struct mlx5_irq *mlx5_irq_get(struct mlx5_core_dev *dev, int vecidx)
+{
+	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
+
+	return &irq_table->irq[vecidx];
+}
+
+int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb)
+{
+	struct mlx5_irq *irq;
+
+	irq = &irq_table->irq[vecidx];
+	return atomic_notifier_chain_register(&irq->nh, nb);
+}
+
+int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb)
+{
+	struct mlx5_irq *irq;
+
+	irq = &irq_table->irq[vecidx];
+	return atomic_notifier_chain_unregister(&irq->nh, nb);
+}
+
+static irqreturn_t mlx5_irq_int_handler(int irq, void *nh)
+{
+	atomic_notifier_call_chain(nh, 0, NULL);
+	return IRQ_HANDLED;
+}
+
+static void irq_set_name(char *name, int vecidx)
+{
+	if (vecidx == 0) {
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async");
+		return;
+	}
+
+	snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d",
+		 vecidx - MLX5_IRQ_VEC_COMP_BASE);
+	return;
+}
+
+static int request_irqs(struct mlx5_core_dev *dev, int nvec)
+{
+	char name[MLX5_MAX_IRQ_NAME];
+	int err;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		struct mlx5_irq *irq = mlx5_irq_get(dev, i);
+		int irqn = pci_irq_vector(dev->pdev, i);
+
+		irq_set_name(name, i);
+		ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
+		snprintf(irq->name, MLX5_MAX_IRQ_NAME,
+			 "%s@pci:%s", name, pci_name(dev->pdev));
+		err = request_irq(irqn, mlx5_irq_int_handler, 0, irq->name,
+				  &irq->nh);
+		if (err) {
+			mlx5_core_err(dev, "Failed to request irq\n");
+			goto err_request_irq;
+		}
+	}
+	return 0;
+
+err_request_irq:
+	for (; i >= 0; i--) {
+		struct mlx5_irq *irq = mlx5_irq_get(dev, i);
+		int irqn = pci_irq_vector(dev->pdev, i);
+
+		free_irq(irqn, &irq->nh);
+	}
+	return  err;
+}
+
+static void irq_clear_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
+
+	free_irq_cpu_rmap(irq_table->rmap);
+#endif
+}
+
+static int irq_set_rmap(struct mlx5_core_dev *mdev)
+{
+	int err = 0;
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_irq_table *irq_table = mdev->priv.irq_table;
+	int num_affinity_vec;
+	int vecidx;
+
+	num_affinity_vec = mlx5_irq_get_num_comp(irq_table);
+	irq_table->rmap = alloc_irq_cpu_rmap(num_affinity_vec);
+	if (!irq_table->rmap) {
+		err = -ENOMEM;
+		mlx5_core_err(mdev, "Failed to allocate cpu_rmap. err %d", err);
+		goto err_out;
+	}
+
+	vecidx = MLX5_IRQ_VEC_COMP_BASE;
+	for (; vecidx < irq_table->nvec; vecidx++) {
+		err = irq_cpu_rmap_add(irq_table->rmap,
+				       pci_irq_vector(mdev->pdev, vecidx));
+		if (err) {
+			mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d",
+				      err);
+			goto err_irq_cpu_rmap_add;
+		}
+	}
+	return 0;
+
+err_irq_cpu_rmap_add:
+	irq_clear_rmap(mdev);
+err_out:
+#endif
+	return err;
+}
+
+/* Completion IRQ vectors */
+
+static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_IRQ_VEC_COMP_BASE + i;
+	struct mlx5_irq *irq;
+	int irqn;
+
+	irq = mlx5_irq_get(mdev, vecidx);
+	irqn = pci_irq_vector(mdev->pdev, vecidx);
+	if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, mdev->priv.numa_node),
+			irq->mask);
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    irq_set_affinity_hint(irqn, irq->mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x",
+			       irqn);
+
+	return 0;
+}
+
+static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_IRQ_VEC_COMP_BASE + i;
+	struct mlx5_irq *irq;
+	int irqn;
+
+	irq = mlx5_irq_get(mdev, vecidx);
+	irqn = pci_irq_vector(mdev->pdev, vecidx);
+	irq_set_affinity_hint(irqn, NULL);
+	free_cpumask_var(irq->mask);
+}
+
+static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
+	int err;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		err = set_comp_irq_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		clear_comp_irq_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
+	int i;
+
+	for (i = 0; i < nvec; i++)
+		clear_comp_irq_affinity_hint(mdev, i);
+}
+
+struct cpumask *
+mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx)
+{
+	return irq_table->irq[vecidx].mask;
+}
+
+#ifdef CONFIG_RFS_ACCEL
+struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *irq_table)
+{
+	return irq_table->rmap;
+}
+#endif
+
+static void unrequest_irqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int i;
+
+	for (i = 0; i < table->nvec; i++)
+		free_irq(pci_irq_vector(dev->pdev, i),
+			 &mlx5_irq_get(dev, i)->nh);
+}
+
+int mlx5_irq_table_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	struct mlx5_irq_table *table = priv->irq_table;
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int nvec;
+	int err;
+
+	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+	       MLX5_IRQ_VEC_COMP_BASE;
+	nvec = min_t(int, nvec, num_eqs);
+	if (nvec <= MLX5_IRQ_VEC_COMP_BASE)
+		return -ENOMEM;
+
+	table->irq = kcalloc(nvec, sizeof(*table->irq), GFP_KERNEL);
+	if (!table->irq)
+		return -ENOMEM;
+
+	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1,
+				     nvec, PCI_IRQ_MSIX);
+	if (nvec < 0) {
+		err = nvec;
+		goto err_free_irq;
+	}
+
+	table->nvec = nvec;
+
+	err = irq_set_rmap(dev);
+	if (err)
+		goto err_set_rmap;
+
+	err = request_irqs(dev, nvec);
+	if (err)
+		goto err_request_irqs;
+
+	err = set_comp_irq_affinity_hints(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
+		goto err_set_affinity;
+	}
+
+	return 0;
+
+err_set_affinity:
+	unrequest_irqs(dev);
+err_request_irqs:
+	irq_clear_rmap(dev);
+err_set_rmap:
+	pci_free_irq_vectors(dev->pdev);
+err_free_irq:
+	kfree(table->irq);
+	return err;
+}
+
+void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int i;
+
+	/* free_irq requires that affinity and rmap will be cleared
+	 * before calling it. This is why there is asymmetry with set_rmap
+	 * which should be called after alloc_irq but before request_irq.
+	 */
+	irq_clear_rmap(dev);
+	clear_comp_irqs_affinity_hints(dev);
+	for (i = 0; i < table->nvec; i++)
+		free_irq(pci_irq_vector(dev->pdev, i),
+			 &mlx5_irq_get(dev, i)->nh);
+	pci_free_irq_vectors(dev->pdev);
+	kfree(table->irq);
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 2b82f35f4c35..cc262b30aed5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -30,10 +30,7 @@
  * SOFTWARE.
  */
 
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
 #include <linux/mlx5/port.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
 int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
@@ -157,44 +154,6 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration)
 				    sizeof(out), MLX5_REG_MLCR, 0, 1);
 }
 
-int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
-			      u32 *proto_cap, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
-	if (err)
-		return err;
-
-	if (proto_mask == MLX5_PTYS_EN)
-		*proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability);
-	else
-		*proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap);
-
-int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
-				u32 *proto_admin, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
-	if (err)
-		return err;
-
-	if (proto_mask == MLX5_PTYS_EN)
-		*proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
-	else
-		*proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin);
-
 int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 				    u8 *link_width_oper, u8 local_port)
 {
@@ -211,23 +170,6 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper);
 
-int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev,
-				   u32 *proto_oper, u8 local_port)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN,
-				   local_port);
-	if (err)
-		return err;
-
-	*proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-
-	return 0;
-}
-EXPORT_SYMBOL(mlx5_query_port_eth_proto_oper);
-
 int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 				  u8 *proto_oper, u8 local_port)
 {
@@ -245,35 +187,6 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper);
 
-int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
-		       u32 proto_admin, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
-	u8 an_disable_admin;
-	u8 an_disable_cap;
-	u8 an_status;
-
-	mlx5_query_port_autoneg(dev, proto_mask, &an_status,
-				&an_disable_cap, &an_disable_admin);
-	if (!an_disable_cap && an_disable)
-		return -EPERM;
-
-	memset(in, 0, sizeof(in));
-
-	MLX5_SET(ptys_reg, in, local_port, 1);
-	MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
-	MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
-	if (proto_mask == MLX5_PTYS_EN)
-		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
-	else
-		MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin);
-
-	return mlx5_core_access_reg(dev, in, sizeof(in), out,
-				    sizeof(out), MLX5_REG_PTYS, 0, 1);
-}
-EXPORT_SYMBOL_GPL(mlx5_set_port_ptys);
-
 /* This function should be used after setting a port register only */
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
 {
@@ -380,15 +293,36 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
 	return 0;
 }
 
+static int mlx5_eeprom_page(int offset)
+{
+	if (offset < MLX5_EEPROM_PAGE_LENGTH)
+		/* Addresses between 0-255 - page 00 */
+		return 0;
+
+	/* Addresses between 256 - 639 belongs to pages 01, 02 and 03
+	 * For example, offset = 400 belongs to page 02:
+	 * 1 + ((400 - 256)/128) = 2
+	 */
+	return 1 + ((offset - MLX5_EEPROM_PAGE_LENGTH) /
+		    MLX5_EEPROM_HIGH_PAGE_LENGTH);
+}
+
+static int mlx5_eeprom_high_page_offset(int page_num)
+{
+	if (!page_num) /* Page 0 always start from low page */
+		return 0;
+
+	/* High page */
+	return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH;
+}
+
 int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 			     u16 offset, u16 size, u8 *data)
 {
+	int module_num, page_num, status, err;
 	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
 	u32 in[MLX5_ST_SZ_DW(mcia_reg)];
-	int module_num;
 	u16 i2c_addr;
-	int status;
-	int err;
 	void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
 
 	err = mlx5_query_module_num(dev, &module_num);
@@ -398,21 +332,24 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 	memset(in, 0, sizeof(in));
 	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
 
-	if (offset < MLX5_EEPROM_PAGE_LENGTH &&
-	    offset + size > MLX5_EEPROM_PAGE_LENGTH)
+	/* Get the page number related to the given offset */
+	page_num = mlx5_eeprom_page(offset);
+
+	/* Set the right offset according to the page number,
+	 * For page_num > 0, relative offset is always >= 128 (high page).
+	 */
+	offset -= mlx5_eeprom_high_page_offset(page_num);
+
+	if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
 		/* Cross pages read, read until offset 256 in low page */
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
 	i2c_addr = MLX5_I2C_ADDR_LOW;
-	if (offset >= MLX5_EEPROM_PAGE_LENGTH) {
-		i2c_addr = MLX5_I2C_ADDR_HIGH;
-		offset -= MLX5_EEPROM_PAGE_LENGTH;
-	}
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
 	MLX5_SET(mcia_reg, in, i2c_device_address, i2c_addr);
-	MLX5_SET(mcia_reg, in, page_number, 0);
+	MLX5_SET(mcia_reg, in, page_number, page_num);
 	MLX5_SET(mcia_reg, in, device_address, offset);
 	MLX5_SET(mcia_reg, in, size, size);
 
@@ -606,25 +543,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
 
-void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
-			     u8 *an_status,
-			     u8 *an_disable_cap, u8 *an_disable_admin)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-
-	*an_status = 0;
-	*an_disable_cap = 0;
-	*an_disable_admin = 0;
-
-	if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1))
-		return;
-
-	*an_status = MLX5_GET(ptys_reg, out, an_status);
-	*an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
-	*an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg);
-
 int mlx5_max_tc(struct mlx5_core_dev *mdev)
 {
 	u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8;
@@ -870,8 +788,7 @@ int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_wol);
 
-static int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out,
-				  int outlen)
+int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen)
 {
 	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
 
@@ -880,7 +797,7 @@ static int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out,
 				    outlen, MLX5_REG_PCMR, 0, 0);
 }
 
-static int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen)
+int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen)
 {
 	u32 out[MLX5_ST_SZ_DW(pcmr_reg)];
 
@@ -891,7 +808,11 @@ static int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen)
 int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable)
 {
 	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
+	int err;
 
+	err = mlx5_query_ports_check(mdev, in, sizeof(in));
+	if (err)
+		return err;
 	MLX5_SET(pcmr_reg, in, local_port, 1);
 	MLX5_SET(pcmr_reg, in, fcs_chk, enable);
 	return mlx5_set_ports_check(mdev, in, sizeof(in));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 370ca94b6775..b8ba74de9555 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -40,6 +40,9 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
 
+static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
+			       struct mlx5_core_dct *dct);
+
 static struct mlx5_core_rsc_common *
 mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
 {
@@ -227,20 +230,49 @@ static void destroy_resource_common(struct mlx5_core_dev *dev,
 	wait_for_completion(&qp->common.free);
 }
 
+static int _mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
+				  struct mlx5_core_dct *dct, bool need_cleanup)
+{
+	u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
+	struct mlx5_core_qp *qp = &dct->mqp;
+	int err;
+
+	err = mlx5_core_drain_dct(dev, dct);
+	if (err) {
+		if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+			goto destroy;
+		} else {
+			mlx5_core_warn(
+				dev, "failed drain DCT 0x%x with error 0x%x\n",
+				qp->qpn, err);
+			return err;
+		}
+	}
+	wait_for_completion(&dct->drained);
+destroy:
+	if (need_cleanup)
+		destroy_resource_common(dev, &dct->mqp);
+	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
+	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
+	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
+	err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
+			    (void *)&out, sizeof(out));
+	return err;
+}
+
 int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 			 struct mlx5_core_dct *dct,
-			 u32 *in, int inlen)
+			 u32 *in, int inlen,
+			 u32 *out, int outlen)
 {
-	u32 out[MLX5_ST_SZ_DW(create_dct_out)]   = {0};
-	u32 din[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-	u32 dout[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
 	struct mlx5_core_qp *qp = &dct->mqp;
 	int err;
 
 	init_completion(&dct->drained);
 	MLX5_SET(create_dct_in, in, opcode, MLX5_CMD_OP_CREATE_DCT);
 
-	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
+	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
 	if (err) {
 		mlx5_core_warn(dev, "create DCT failed, ret %d\n", err);
 		return err;
@@ -254,11 +286,7 @@ int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 
 	return 0;
 err_cmd:
-	MLX5_SET(destroy_dct_in, din, opcode, MLX5_CMD_OP_DESTROY_DCT);
-	MLX5_SET(destroy_dct_in, din, dctn, qp->qpn);
-	MLX5_SET(destroy_dct_in, din, uid, qp->uid);
-	mlx5_cmd_exec(dev, (void *)&in, sizeof(din),
-		      (void *)&out, sizeof(dout));
+	_mlx5_core_destroy_dct(dev, dct, false);
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_create_dct);
@@ -323,29 +351,7 @@ static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
 int mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
 			  struct mlx5_core_dct *dct)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-	struct mlx5_core_qp *qp = &dct->mqp;
-	int err;
-
-	err = mlx5_core_drain_dct(dev, dct);
-	if (err) {
-		if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-			goto destroy;
-		} else {
-			mlx5_core_warn(dev, "failed drain DCT 0x%x with error 0x%x\n", qp->qpn, err);
-			return err;
-		}
-	}
-	wait_for_completion(&dct->drained);
-destroy:
-	destroy_resource_common(dev, &dct->mqp);
-	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
-	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
-	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
-	err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
-			    (void *)&out, sizeof(out));
-	return err;
+	return _mlx5_core_destroy_dct(dev, dct, true);
 }
 EXPORT_SYMBOL_GPL(mlx5_core_destroy_dct);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
new file mode 100644
index 000000000000..17ce9dd56b13
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <linux/mlx5/vport.h>
+#include <rdma/ib_verbs.h>
+#include <net/addrconf.h>
+
+#include "lib/mlx5.h"
+#include "eswitch.h"
+#include "fs_core.h"
+#include "rdma.h"
+
+static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+
+	if (!roce->ft)
+		return;
+
+	mlx5_del_flow_rules(roce->allow_rule);
+	mlx5_destroy_flow_group(roce->fg);
+	mlx5_destroy_flow_table(roce->ft);
+}
+
+static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+	struct mlx5_flow_handle *flow_rule = NULL;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns = NULL;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	void *match_criteria;
+	u32 *flow_group_in;
+	void *misc;
+	int err;
+
+	if (!(MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
+	      MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)))
+		return -EOPNOTSUPP;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		kvfree(flow_group_in);
+		return -ENOMEM;
+	}
+
+	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX);
+	if (!ns) {
+		mlx5_core_err(dev, "Failed to get RDMA RX namespace");
+		err = -EOPNOTSUPP;
+		goto free;
+	}
+
+	ft_attr.max_fte = 1;
+	ft = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		mlx5_core_err(dev, "Failed to create RDMA RX flow table");
+		err = PTR_ERR(ft);
+		goto free;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_port);
+
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_err(dev, "Failed to create RDMA RX flow group err(%d)\n", err);
+		goto destroy_flow_table;
+	}
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			    misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port,
+		 dev->priv.eswitch->manager_vport);
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			    misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		mlx5_core_err(dev, "Failed to add RoCE allow rule, err=%d\n",
+			      err);
+		goto destroy_flow_group;
+	}
+
+	kvfree(spec);
+	kvfree(flow_group_in);
+	roce->ft = ft;
+	roce->fg = fg;
+	roce->allow_rule = flow_rule;
+
+	return 0;
+
+destroy_flow_group:
+	mlx5_destroy_flow_group(fg);
+destroy_flow_table:
+	mlx5_destroy_flow_table(ft);
+free:
+	kvfree(spec);
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
+{
+	mlx5_core_roce_gid_set(dev, 0, 0, 0,
+			       NULL, NULL, false, 0, 0);
+}
+
+static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)
+{
+	u8 hw_id[ETH_ALEN];
+
+	mlx5_query_mac_address(dev, hw_id);
+	gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+	addrconf_addr_eui48(&gid->raw[8], hw_id);
+}
+
+static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
+{
+	union ib_gid gid;
+	u8 mac[ETH_ALEN];
+
+	mlx5_rdma_make_default_gid(dev, &gid);
+	return mlx5_core_roce_gid_set(dev, 0,
+				      MLX5_ROCE_VERSION_1,
+				      0, gid.raw, mac,
+				      false, 0, 1);
+}
+
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
+{
+	mlx5_rdma_disable_roce_steering(dev);
+	mlx5_rdma_del_roce_addr(dev);
+	mlx5_nic_vport_disable_roce(dev);
+}
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_nic_vport_enable_roce(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
+		return;
+	}
+
+	err = mlx5_rdma_add_roce_addr(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to add RoCE address: %d\n", err);
+		goto disable_roce;
+	}
+
+	err = mlx5_rdma_enable_roce_steering(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to enable RoCE steering: %d\n", err);
+		goto del_roce_addr;
+	}
+
+	return;
+
+del_roce_addr:
+	mlx5_rdma_del_roce_addr(dev);
+disable_roce:
+	mlx5_nic_vport_disable_roce(dev);
+	return;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
new file mode 100644
index 000000000000..750cff2a71a4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_RDMA_H__
+#define __MLX5_RDMA_H__
+
+#include "mlx5_core.h"
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
+
+#else /* CONFIG_MLX5_ESWITCH */
+
+static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_RDMA_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 6e178030d8fb..61fcfd8b39b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -36,13 +36,6 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 
-bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev)
-{
-	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
-
-	return !!sriov->num_vfs;
-}
-
 static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
@@ -81,17 +74,11 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 	int err;
 	int vf;
 
-	if (sriov->enabled_vfs) {
-		mlx5_core_warn(dev,
-			       "failed to enable SRIOV on device, already enabled with %d vfs\n",
-			       sriov->enabled_vfs);
-		return -EBUSY;
-	}
-
 	if (!MLX5_ESWITCH_MANAGER(dev))
 		goto enable_vfs_hca;
 
-	err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
+	mlx5_eswitch_update_num_of_vfs(dev->priv.eswitch, num_vfs);
+	err = mlx5_eswitch_enable(dev->priv.eswitch, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		mlx5_core_warn(dev,
 			       "failed to enable eswitch SRIOV (%d)\n", err);
@@ -106,7 +93,6 @@ enable_vfs_hca:
 			continue;
 		}
 		sriov->vfs_ctx[vf].enabled = 1;
-		sriov->enabled_vfs++;
 		if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) {
 			err = sriov_restore_guids(dev, vf);
 			if (err) {
@@ -125,13 +111,11 @@ enable_vfs_hca:
 static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
+	int num_vfs = pci_num_vf(dev->pdev);
 	int err;
 	int vf;
 
-	if (!sriov->enabled_vfs)
-		goto out;
-
-	for (vf = 0; vf < sriov->num_vfs; vf++) {
+	for (vf = num_vfs - 1; vf >= 0; vf--) {
 		if (!sriov->vfs_ctx[vf].enabled)
 			continue;
 		err = mlx5_core_disable_hca(dev, vf + 1);
@@ -140,44 +124,19 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 			continue;
 		}
 		sriov->vfs_ctx[vf].enabled = 0;
-		sriov->enabled_vfs--;
 	}
 
-out:
 	if (MLX5_ESWITCH_MANAGER(dev))
-		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+		mlx5_eswitch_disable(dev->priv.eswitch);
 
-	if (mlx5_wait_for_vf_pages(dev))
+	if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
 }
 
-static int mlx5_pci_enable_sriov(struct pci_dev *pdev, int num_vfs)
-{
-	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
-	int err = 0;
-
-	if (pci_num_vf(pdev)) {
-		mlx5_core_warn(dev, "Unable to enable pci sriov, already enabled\n");
-		return -EBUSY;
-	}
-
-	err = pci_enable_sriov(pdev, num_vfs);
-	if (err)
-		mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err);
-
-	return err;
-}
-
-static void mlx5_pci_disable_sriov(struct pci_dev *pdev)
-{
-	pci_disable_sriov(pdev);
-}
-
 static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
-	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
-	int err = 0;
+	int err;
 
 	err = mlx5_device_enable_sriov(dev, num_vfs);
 	if (err) {
@@ -185,54 +144,47 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 		return err;
 	}
 
-	err = mlx5_pci_enable_sriov(pdev, num_vfs);
+	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
-		mlx5_core_warn(dev, "mlx5_pci_enable_sriov failed : %d\n", err);
+		mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err);
 		mlx5_device_disable_sriov(dev);
-		return err;
 	}
-
-	sriov->num_vfs = num_vfs;
-
-	return 0;
+	return err;
 }
 
 static void mlx5_sriov_disable(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
-	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
 
-	mlx5_pci_disable_sriov(pdev);
+	pci_disable_sriov(pdev);
 	mlx5_device_disable_sriov(dev);
-	sriov->num_vfs = 0;
 }
 
 int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
+	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
 	int err = 0;
 
 	mlx5_core_dbg(dev, "requested num_vfs %d\n", num_vfs);
-	if (!mlx5_core_is_pf(dev))
-		return -EPERM;
 
 	if (num_vfs)
 		err = mlx5_sriov_enable(pdev, num_vfs);
 	else
 		mlx5_sriov_disable(pdev);
 
+	if (!err)
+		sriov->num_vfs = num_vfs;
 	return err ? err : num_vfs;
 }
 
 int mlx5_sriov_attach(struct mlx5_core_dev *dev)
 {
-	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
-
-	if (!mlx5_core_is_pf(dev) || !sriov->num_vfs)
+	if (!mlx5_core_is_pf(dev) || !pci_num_vf(dev->pdev))
 		return 0;
 
 	/* If sriov VFs exist in PCI level, enable them in device level */
-	return mlx5_device_enable_sriov(dev, sriov->num_vfs);
+	return mlx5_device_enable_sriov(dev, pci_num_vf(dev->pdev));
 }
 
 void mlx5_sriov_detach(struct mlx5_core_dev *dev)
@@ -243,6 +195,30 @@ void mlx5_sriov_detach(struct mlx5_core_dev *dev)
 	mlx5_device_disable_sriov(dev);
 }
 
+static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
+{
+	u16 host_total_vfs;
+	const u32 *out;
+
+	if (mlx5_core_is_ecpf_esw_manager(dev)) {
+		out = mlx5_esw_query_functions(dev);
+
+		/* Old FW doesn't support getting total_vfs from esw func
+		 * but supports getting it from pci_sriov.
+		 */
+		if (IS_ERR(out))
+			goto done;
+		host_total_vfs = MLX5_GET(query_esw_functions_out, out,
+					  host_params_context.host_total_vfs);
+		kvfree(out);
+		if (host_total_vfs)
+			return host_total_vfs;
+	}
+
+done:
+	return pci_sriov_get_totalvfs(dev->pdev);
+}
+
 int mlx5_sriov_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
@@ -253,6 +229,7 @@ int mlx5_sriov_init(struct mlx5_core_dev *dev)
 		return 0;
 
 	total_vfs = pci_sriov_get_totalvfs(pdev);
+	sriov->max_vfs = mlx5_get_max_vfs(dev);
 	sriov->num_vfs = pci_num_vf(pdev);
 	sriov->vfs_ctx = kcalloc(total_vfs, sizeof(*sriov->vfs_ctx), GFP_KERNEL);
 	if (!sriov->vfs_ctx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index c4d4b76096dc..b1068500f1df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -182,16 +182,24 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_core_query_sq_state);
 
+int mlx5_core_create_tir_out(struct mlx5_core_dev *dev,
+			     u32 *in, int inlen,
+			     u32 *out, int outlen)
+{
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+
+	return mlx5_cmd_exec(dev, in, inlen, out, outlen);
+}
+EXPORT_SYMBOL(mlx5_core_create_tir_out);
+
 int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *tirn)
 {
-	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
 	int err;
 
-	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
-
-	memset(out, 0, sizeof(out));
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_core_create_tir_out(dev, in, inlen,
+				       out, sizeof(out));
 	if (!err)
 		*tirn = MLX5_GET(create_tir_out, out, tirn);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 8b97066dd1f1..0d006224d7b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -79,7 +79,7 @@ static u64 uar2pfn(struct mlx5_core_dev *mdev, u32 index)
 	else
 		system_page_index = index;
 
-	return (pci_resource_start(mdev->pdev, 0) >> PAGE_SHIFT) + system_page_index;
+	return (mdev->bar_addr >> PAGE_SHIFT) + system_page_index;
 }
 
 static void up_rel_func(struct kref *kref)
@@ -90,8 +90,8 @@ static void up_rel_func(struct kref *kref)
 	iounmap(up->map);
 	if (mlx5_cmd_free_uar(up->mdev, up->index))
 		mlx5_core_warn(up->mdev, "failed to free uar index %d\n", up->index);
-	kfree(up->reg_bitmap);
-	kfree(up->fp_bitmap);
+	bitmap_free(up->reg_bitmap);
+	bitmap_free(up->fp_bitmap);
 	kfree(up);
 }
 
@@ -110,11 +110,11 @@ static struct mlx5_uars_page *alloc_uars_page(struct mlx5_core_dev *mdev,
 		return ERR_PTR(err);
 
 	up->mdev = mdev;
-	up->reg_bitmap = kcalloc(BITS_TO_LONGS(bfregs), sizeof(unsigned long), GFP_KERNEL);
+	up->reg_bitmap = bitmap_zalloc(bfregs, GFP_KERNEL);
 	if (!up->reg_bitmap)
 		goto error1;
 
-	up->fp_bitmap = kcalloc(BITS_TO_LONGS(bfregs), sizeof(unsigned long), GFP_KERNEL);
+	up->fp_bitmap = bitmap_zalloc(bfregs, GFP_KERNEL);
 	if (!up->fp_bitmap)
 		goto error1;
 
@@ -157,8 +157,8 @@ error2:
 	if (mlx5_cmd_free_uar(mdev, up->index))
 		mlx5_core_warn(mdev, "failed to free uar index %d\n", up->index);
 error1:
-	kfree(up->fp_bitmap);
-	kfree(up->reg_bitmap);
+	bitmap_free(up->fp_bitmap);
+	bitmap_free(up->reg_bitmap);
 	kfree(up);
 	return ERR_PTR(err);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 9b150ce9d315..c912d82ca64b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -34,6 +34,7 @@
 #include <linux/etherdevice.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/vport.h>
+#include <linux/mlx5/eswitch.h>
 #include "mlx5_core.h"
 
 /* Mutex to hold while enabling or disabling RoCE */
@@ -64,7 +65,7 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 }
 
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
-				  u16 vport, u8 state)
+				  u16 vport, u8 other_vport, u8 state)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(modify_vport_state_out)] = {0};
@@ -73,8 +74,7 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 		 MLX5_CMD_OP_MODIFY_VPORT_STATE);
 	MLX5_SET(modify_vport_state_in, in, op_mod, opmod);
 	MLX5_SET(modify_vport_state_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_vport_state_in, in, other_vport, 1);
+	MLX5_SET(modify_vport_state_in, in, other_vport, other_vport);
 	MLX5_SET(modify_vport_state_in, in, admin_state, state);
 
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
@@ -156,11 +156,12 @@ int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 }
 
 int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
-				     u16 vport, u8 *addr)
+				     u16 vport, bool other, u8 *addr)
 {
-	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {};
 	u8 *out_addr;
+	u32 *out;
 	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
@@ -170,7 +171,12 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 	out_addr = MLX5_ADDR_OF(query_nic_vport_context_out, out,
 				nic_vport_context.permanent_address);
 
-	err = mlx5_query_nic_vport_context(mdev, vport, out, outlen);
+	MLX5_SET(query_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
+	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
+	MLX5_SET(query_nic_vport_context_in, in, other_vport, other);
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
 	if (!err)
 		ether_addr_copy(addr, &out_addr[2]);
 
@@ -179,6 +185,12 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_mac_address);
 
+int mlx5_query_mac_address(struct mlx5_core_dev *mdev, u8 *addr)
+{
+	return mlx5_query_nic_vport_mac_address(mdev, 0, false, addr);
+}
+EXPORT_SYMBOL_GPL(mlx5_query_mac_address);
+
 int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				      u16 vport, u8 *addr)
 {
@@ -195,9 +207,7 @@ int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 field_select.permanent_address, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
-
-	if (vport)
-		MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
 
 	nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in,
 				     in, nic_vport_context);
@@ -255,7 +265,7 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu)
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu);
 
 int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
-				  u32 vport,
+				  u16 vport,
 				  enum mlx5_list_type list_type,
 				  u8 addr_list[][ETH_ALEN],
 				  int *list_size)
@@ -292,9 +302,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
 	MLX5_SET(query_nic_vport_context_in, in, allowed_list_type, list_type);
 	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
-
-	if (vport)
-		MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
 	if (err)
@@ -372,67 +380,6 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list);
 
-int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev,
-			       u32 vport,
-			       u16 vlans[],
-			       int *size)
-{
-	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)];
-	void *nic_vport_ctx;
-	int req_list_size;
-	int max_list_size;
-	int out_sz;
-	void *out;
-	int err;
-	int i;
-
-	req_list_size = *size;
-	max_list_size = 1 << MLX5_CAP_GEN(dev, log_max_vlan_list);
-	if (req_list_size > max_list_size) {
-		mlx5_core_warn(dev, "Requested list size (%d) > (%d) max list size\n",
-			       req_list_size, max_list_size);
-		req_list_size = max_list_size;
-	}
-
-	out_sz = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in) +
-			req_list_size * MLX5_ST_SZ_BYTES(vlan_layout);
-
-	memset(in, 0, sizeof(in));
-	out = kzalloc(out_sz, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	MLX5_SET(query_nic_vport_context_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
-	MLX5_SET(query_nic_vport_context_in, in, allowed_list_type,
-		 MLX5_NVPRT_LIST_TYPE_VLAN);
-	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
-
-	if (vport)
-		MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
-
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
-	if (err)
-		goto out;
-
-	nic_vport_ctx = MLX5_ADDR_OF(query_nic_vport_context_out, out,
-				     nic_vport_context);
-	req_list_size = MLX5_GET(nic_vport_context, nic_vport_ctx,
-				 allowed_list_size);
-
-	*size = req_list_size;
-	for (i = 0; i < req_list_size; i++) {
-		void *vlan_addr = MLX5_ADDR_OF(nic_vport_context,
-					       nic_vport_ctx,
-					       current_uc_mac_address[i]);
-		vlans[i] = MLX5_GET(vlan_layout, vlan_addr, vlan);
-	}
-out:
-	kfree(out);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_vlans);
-
 int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev,
 				u16 vlans[],
 				int list_size)
@@ -526,7 +473,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
-				    u32 vport, u64 node_guid)
+				    u16 vport, u64 node_guid)
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
 	void *nic_vport_context;
@@ -545,7 +492,7 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 field_select.node_guid, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
-	MLX5_SET(modify_nic_vport_context_in, in, other_vport, !!vport);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
 
 	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
 					 in, nic_vport_context);
@@ -827,7 +774,7 @@ int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev,
 EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_node_guid);
 
 int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev,
-				 u32 vport,
+				 u16 vport,
 				 int *promisc_uc,
 				 int *promisc_mc,
 				 int *promisc_all)
@@ -1057,7 +1004,7 @@ free:
 EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter);
 
 int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
-				u64 *rx_discard_vport_down,
+				u8 other_vport, u64 *rx_discard_vport_down,
 				u64 *tx_discard_vport_down)
 {
 	u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {0};
@@ -1068,8 +1015,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
 		 MLX5_CMD_OP_QUERY_VNIC_ENV);
 	MLX5_SET(query_vnic_env_in, in, op_mod, 0);
 	MLX5_SET(query_vnic_env_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(query_vnic_env_in, in, other_vport, 1);
+	MLX5_SET(query_vnic_env_in, in, other_vport, other_vport);
 
 	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -1220,3 +1166,17 @@ u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev)
 	return tmp;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid);
+
+/**
+ * mlx5_eswitch_get_total_vports - Get total vports of the eswitch
+ *
+ * @dev:	Pointer to core device
+ *
+ * mlx5_eswitch_get_total_vports returns total number of vports for
+ * the eswitch.
+ */
+u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev)
+{
+	return MLX5_SPECIAL_VPORTS(dev) + mlx5_core_max_vfs(dev);
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_total_vports);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index ea934a48c90a..f1ec58c9e9e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -243,6 +243,13 @@ static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
 }
 
+static inline u16 mlx5_wq_ll_get_wqe_next_ix(struct mlx5_wq_ll *wq, u16 ix)
+{
+	struct mlx5_wqe_srq_next_seg *wqe = mlx5_wq_ll_get_wqe(wq, ix);
+
+	return be16_to_cpu(wqe->next_wqe_index);
+}
+
 static inline void mlx5_wq_ll_push(struct mlx5_wq_ll *wq, u16 head_next)
 {
 	wq->head = head_next;
diff --git a/drivers/net/ethernet/mellanox/mlxfw/Kconfig b/drivers/net/ethernet/mellanox/mlxfw/Kconfig
index 186ebe783f97..0367f835a846 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxfw/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Mellanox firmware flash library configuration
 #
diff --git a/drivers/net/ethernet/mellanox/mlxfw/Makefile b/drivers/net/ethernet/mellanox/mlxfw/Makefile
index 7448b301104c..36007cd24c01 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxfw/Makefile
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MLXFW)	+= mlxfw.o
 mlxfw-objs		:= mlxfw_fsm.o mlxfw_mfa2_tlv_multi.o mlxfw_mfa2.o
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
index 7a712b6b09ec..c50e74ab02c4 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
@@ -1,41 +1,11 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_H
 #define _MLXFW_H
 
 #include <linux/firmware.h>
+#include <linux/netlink.h>
 
 enum mlxfw_fsm_state {
 	MLXFW_FSM_STATE_IDLE,
@@ -88,6 +58,10 @@ struct mlxfw_dev_ops {
 	void (*fsm_cancel)(struct mlxfw_dev *mlxfw_dev, u32 fwhandle);
 
 	void (*fsm_release)(struct mlxfw_dev *mlxfw_dev, u32 fwhandle);
+
+	void (*status_notify)(struct mlxfw_dev *mlxfw_dev,
+			      const char *msg, const char *comp_name,
+			      u32 done_bytes, u32 total_bytes);
 };
 
 struct mlxfw_dev {
@@ -98,11 +72,13 @@ struct mlxfw_dev {
 
 #if IS_REACHABLE(CONFIG_MLXFW)
 int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev,
-			 const struct firmware *firmware);
+			 const struct firmware *firmware,
+			 struct netlink_ext_ack *extack);
 #else
 static inline
 int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev,
-			 const struct firmware *firmware)
+			 const struct firmware *firmware,
+			 struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 2cf89126fb23..67990406cba2 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #define pr_fmt(fmt) "mlxfw: " fmt
 
@@ -70,8 +39,19 @@ static const char * const mlxfw_fsm_state_err_str[] = {
 		"unknown error"
 };
 
+static void mlxfw_status_notify(struct mlxfw_dev *mlxfw_dev,
+				const char *msg, const char *comp_name,
+				u32 done_bytes, u32 total_bytes)
+{
+	if (!mlxfw_dev->ops->status_notify)
+		return;
+	mlxfw_dev->ops->status_notify(mlxfw_dev, msg, comp_name,
+				      done_bytes, total_bytes);
+}
+
 static int mlxfw_fsm_state_wait(struct mlxfw_dev *mlxfw_dev, u32 fwhandle,
-				enum mlxfw_fsm_state fsm_state)
+				enum mlxfw_fsm_state fsm_state,
+				struct netlink_ext_ack *extack)
 {
 	enum mlxfw_fsm_state_err fsm_state_err;
 	enum mlxfw_fsm_state curr_fsm_state;
@@ -88,11 +68,13 @@ retry:
 	if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) {
 		pr_err("Firmware flash failed: %s\n",
 		       mlxfw_fsm_state_err_str[fsm_state_err]);
+		NL_SET_ERR_MSG_MOD(extack, "Firmware flash failed");
 		return -EINVAL;
 	}
 	if (curr_fsm_state != fsm_state) {
 		if (--times == 0) {
 			pr_err("Timeout reached on FSM state change");
+			NL_SET_ERR_MSG_MOD(extack, "Timeout reached on FSM state change");
 			return -ETIMEDOUT;
 		}
 		msleep(MLXFW_FSM_STATE_WAIT_CYCLE_MS);
@@ -107,16 +89,20 @@ retry:
 
 static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 				 u32 fwhandle,
-				 struct mlxfw_mfa2_component *comp)
+				 struct mlxfw_mfa2_component *comp,
+				 struct netlink_ext_ack *extack)
 {
 	u16 comp_max_write_size;
 	u8 comp_align_bits;
 	u32 comp_max_size;
+	char comp_name[8];
 	u16 block_size;
 	u8 *block_ptr;
 	u32 offset;
 	int err;
 
+	sprintf(comp_name, "%u", comp->index);
+
 	err = mlxfw_dev->ops->component_query(mlxfw_dev, comp->index,
 					      &comp_max_size, &comp_align_bits,
 					      &comp_max_write_size);
@@ -127,6 +113,7 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 	if (comp->data_size > comp_max_size) {
 		pr_err("Component %d is of size %d which is bigger than limit %d\n",
 		       comp->index, comp->data_size, comp_max_size);
+		NL_SET_ERR_MSG_MOD(extack, "Component is bigger than limit");
 		return -EINVAL;
 	}
 
@@ -134,6 +121,7 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 					       comp_align_bits);
 
 	pr_debug("Component update\n");
+	mlxfw_status_notify(mlxfw_dev, "Updating component", comp_name, 0, 0);
 	err = mlxfw_dev->ops->fsm_component_update(mlxfw_dev, fwhandle,
 						   comp->index,
 						   comp->data_size);
@@ -141,11 +129,13 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 		return err;
 
 	err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle,
-				   MLXFW_FSM_STATE_DOWNLOAD);
+				   MLXFW_FSM_STATE_DOWNLOAD, extack);
 	if (err)
 		goto err_out;
 
 	pr_debug("Component download\n");
+	mlxfw_status_notify(mlxfw_dev, "Downloading component",
+			    comp_name, 0, comp->data_size);
 	for (offset = 0;
 	     offset < MLXFW_ALIGN_UP(comp->data_size, comp_align_bits);
 	     offset += comp_max_write_size) {
@@ -157,15 +147,20 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev,
 							 offset);
 		if (err)
 			goto err_out;
+		mlxfw_status_notify(mlxfw_dev, "Downloading component",
+				    comp_name, offset + block_size,
+				    comp->data_size);
 	}
 
 	pr_debug("Component verify\n");
+	mlxfw_status_notify(mlxfw_dev, "Verifying component", comp_name, 0, 0);
 	err = mlxfw_dev->ops->fsm_component_verify(mlxfw_dev, fwhandle,
 						   comp->index);
 	if (err)
 		goto err_out;
 
-	err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle, MLXFW_FSM_STATE_LOCKED);
+	err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle,
+				   MLXFW_FSM_STATE_LOCKED, extack);
 	if (err)
 		goto err_out;
 	return 0;
@@ -176,7 +171,8 @@ err_out:
 }
 
 static int mlxfw_flash_components(struct mlxfw_dev *mlxfw_dev, u32 fwhandle,
-				  struct mlxfw_mfa2_file *mfa2_file)
+				  struct mlxfw_mfa2_file *mfa2_file,
+				  struct netlink_ext_ack *extack)
 {
 	u32 component_count;
 	int err;
@@ -187,6 +183,7 @@ static int mlxfw_flash_components(struct mlxfw_dev *mlxfw_dev, u32 fwhandle,
 					      &component_count);
 	if (err) {
 		pr_err("Could not find device PSID in MFA2 file\n");
+		NL_SET_ERR_MSG_MOD(extack, "Could not find device PSID in MFA2 file");
 		return err;
 	}
 
@@ -199,7 +196,7 @@ static int mlxfw_flash_components(struct mlxfw_dev *mlxfw_dev, u32 fwhandle,
 			return PTR_ERR(comp);
 
 		pr_info("Flashing component type %d\n", comp->index);
-		err = mlxfw_flash_component(mlxfw_dev, fwhandle, comp);
+		err = mlxfw_flash_component(mlxfw_dev, fwhandle, comp, extack);
 		mlxfw_mfa2_file_component_put(comp);
 		if (err)
 			return err;
@@ -208,7 +205,8 @@ static int mlxfw_flash_components(struct mlxfw_dev *mlxfw_dev, u32 fwhandle,
 }
 
 int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev,
-			 const struct firmware *firmware)
+			 const struct firmware *firmware,
+			 struct netlink_ext_ack *extack)
 {
 	struct mlxfw_mfa2_file *mfa2_file;
 	u32 fwhandle;
@@ -216,6 +214,7 @@ int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev,
 
 	if (!mlxfw_mfa2_check(firmware)) {
 		pr_err("Firmware file is not MFA2\n");
+		NL_SET_ERR_MSG_MOD(extack, "Firmware file is not MFA2");
 		return -EINVAL;
 	}
 
@@ -224,29 +223,35 @@ int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev,
 		return PTR_ERR(mfa2_file);
 
 	pr_info("Initialize firmware flash process\n");
+	mlxfw_status_notify(mlxfw_dev, "Initializing firmware flash process",
+			    NULL, 0, 0);
 	err = mlxfw_dev->ops->fsm_lock(mlxfw_dev, &fwhandle);
 	if (err) {
 		pr_err("Could not lock the firmware FSM\n");
+		NL_SET_ERR_MSG_MOD(extack, "Could not lock the firmware FSM");
 		goto err_fsm_lock;
 	}
 
 	err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle,
-				   MLXFW_FSM_STATE_LOCKED);
+				   MLXFW_FSM_STATE_LOCKED, extack);
 	if (err)
 		goto err_state_wait_idle_to_locked;
 
-	err = mlxfw_flash_components(mlxfw_dev, fwhandle, mfa2_file);
+	err = mlxfw_flash_components(mlxfw_dev, fwhandle, mfa2_file, extack);
 	if (err)
 		goto err_flash_components;
 
 	pr_debug("Activate image\n");
+	mlxfw_status_notify(mlxfw_dev, "Activating image", NULL, 0, 0);
 	err = mlxfw_dev->ops->fsm_activate(mlxfw_dev, fwhandle);
 	if (err) {
 		pr_err("Could not activate the downloaded image\n");
+		NL_SET_ERR_MSG_MOD(extack, "Could not activate the downloaded image");
 		goto err_fsm_activate;
 	}
 
-	err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle, MLXFW_FSM_STATE_LOCKED);
+	err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle,
+				   MLXFW_FSM_STATE_LOCKED, extack);
 	if (err)
 		goto err_state_wait_activate_to_locked;
 
@@ -254,6 +259,7 @@ int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev,
 	mlxfw_dev->ops->fsm_release(mlxfw_dev, fwhandle);
 
 	pr_info("Firmware flash done.\n");
+	mlxfw_status_notify(mlxfw_dev, "Firmware flash done", NULL, 0, 0);
 	mlxfw_mfa2_file_fini(mfa2_file);
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
index 993cb5ba934e..544344ac4894 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #define pr_fmt(fmt) "mlxfw_mfa2: " fmt
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
index 20472aa139cd..5bba6ad79d34 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_MFA2_H
 #define _MLXFW_MFA2_H
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
index f667942b1ea3..874c0a2474ae 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_MFA2_FILE_H
 #define _MLXFW_MFA2_FILE_H
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
index dd66737c033d..b001e5258091 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
@@ -1,36 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXFW_MFA2_FORMAT_H
 #define _MLXFW_MFA2_FORMAT_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
index cc013e77b326..33c971190bba 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_MFA2_TLV_H
 #define _MLXFW_MFA2_TLV_H
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
index 0094b92a233b..017d68f1e123 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #define pr_fmt(fmt) "MFA2: " fmt
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
index 2c667894f3a2..633284eeded7 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
@@ -1,36 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXFW_MFA2_TLV_MULTI_H
 #define _MLXFW_MFA2_TLV_MULTI_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index b9a25aed5d11..06c80343d9ed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -1,10 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Mellanox switch drivers configuration
 #
 
 config MLXSW_CORE
 	tristate "Mellanox Technologies Switch ASICs support"
-	depends on MAY_USE_DEVLINK
+	select NET_DEVLINK
 	---help---
 	  This driver supports Mellanox Technologies Switch ASICs family.
 
@@ -22,7 +23,6 @@ config MLXSW_CORE_HWMON
 config MLXSW_CORE_THERMAL
 	bool "Thermal zone support for Mellanox Technologies Switch ASICs"
 	depends on MLXSW_CORE && THERMAL
-	depends on !(MLXSW_CORE=y && THERMAL=m)
 	default y
 	---help---
 	 Say Y here if you want to automatically control fans speed according
@@ -83,6 +83,8 @@ config MLXSW_SPECTRUM
 	select PARMAN
 	select OBJAGG
 	select MLXFW
+	imply PTP_1588_CLOCK
+	select NET_PTP_CLASSIFY if PTP_1588_CLOCK
 	default m
 	---help---
 	  This driver supports Mellanox Technologies Spectrum Ethernet
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index bbf45f10c208..171b36bd8a4e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_MLXSW_CORE)	+= mlxsw_core.o
 mlxsw_core-objs			:= core.o core_acl_flex_keys.o \
-				   core_acl_flex_actions.o
+				   core_acl_flex_actions.o core_env.o
 mlxsw_core-$(CONFIG_MLXSW_CORE_HWMON) += core_hwmon.o
 mlxsw_core-$(CONFIG_MLXSW_CORE_THERMAL) += core_thermal.o
 obj-$(CONFIG_MLXSW_PCI)		+= mlxsw_pci.o
@@ -28,8 +28,9 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum1_mr_tcam.o spectrum2_mr_tcam.o \
 				   spectrum_mr_tcam.o spectrum_mr.o \
 				   spectrum_qdisc.o spectrum_span.o \
-				   spectrum_nve.o spectrum_nve_vxlan.o
+				   spectrum_nve.o spectrum_nve_vxlan.o \
+				   spectrum_dpipe.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
-mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o
+mlxsw_spectrum-$(CONFIG_PTP_1588_CLOCK)		+= spectrum_ptp.o
 obj-$(CONFIG_MLXSW_MINIMAL)	+= mlxsw_minimal.o
 mlxsw_minimal-objs		:= minimal.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index 0772e4339b33..5ffdfb532cb7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -317,6 +317,18 @@ MLXSW_ITEM64(cmd_mbox, query_fw, doorbell_page_offset, 0x40, 0, 64);
  */
 MLXSW_ITEM32(cmd_mbox, query_fw, doorbell_page_bar, 0x48, 30, 2);
 
+/* cmd_mbox_query_fw_free_running_clock_offset
+ * The offset of the free running clock page
+ */
+MLXSW_ITEM64(cmd_mbox, query_fw, free_running_clock_offset, 0x50, 0, 64);
+
+/* cmd_mbox_query_fw_fr_rn_clk_bar
+ * PCI base address register (BAR) of the free running clock page
+ * 0: BAR 0
+ * 1: 64 bit BAR
+ */
+MLXSW_ITEM32(cmd_mbox, query_fw, fr_rn_clk_bar, 0x58, 30, 2);
+
 /* QUERY_BOARDINFO - Query Board Information
  * -----------------------------------------
  * OpMod == 0 (N/A), INMmod == 0 (N/A)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index ddedf8ab5b64..17ceac7505e5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -122,6 +122,12 @@ void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_driver_priv);
 
+bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->driver->res_query_enabled;
+}
+EXPORT_SYMBOL(mlxsw_core_res_query_enabled);
+
 struct mlxsw_rx_listener_item {
 	struct list_head list;
 	struct mlxsw_rx_listener rxl;
@@ -568,7 +574,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
 		return 0;
 
-	emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0);
+	emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
 	if (!emad_wq)
 		return -ENOMEM;
 	mlxsw_core->emad_wq = emad_wq;
@@ -781,7 +787,8 @@ mlxsw_devlink_sb_pool_get(struct devlink *devlink,
 static int
 mlxsw_devlink_sb_pool_set(struct devlink *devlink,
 			  unsigned int sb_index, u16 pool_index, u32 size,
-			  enum devlink_sb_threshold_type threshold_type)
+			  enum devlink_sb_threshold_type threshold_type,
+			  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
@@ -789,7 +796,8 @@ mlxsw_devlink_sb_pool_set(struct devlink *devlink,
 	if (!mlxsw_driver->sb_pool_set)
 		return -EOPNOTSUPP;
 	return mlxsw_driver->sb_pool_set(mlxsw_core, sb_index,
-					 pool_index, size, threshold_type);
+					 pool_index, size, threshold_type,
+					 extack);
 }
 
 static void *__dl_port(struct devlink_port *devlink_port)
@@ -829,7 +837,8 @@ static int mlxsw_devlink_sb_port_pool_get(struct devlink_port *devlink_port,
 
 static int mlxsw_devlink_sb_port_pool_set(struct devlink_port *devlink_port,
 					  unsigned int sb_index, u16 pool_index,
-					  u32 threshold)
+					  u32 threshold,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
 	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
@@ -839,7 +848,7 @@ static int mlxsw_devlink_sb_port_pool_set(struct devlink_port *devlink_port,
 	    !mlxsw_core_port_check(mlxsw_core_port))
 		return -EOPNOTSUPP;
 	return mlxsw_driver->sb_port_pool_set(mlxsw_core_port, sb_index,
-					      pool_index, threshold);
+					      pool_index, threshold, extack);
 }
 
 static int
@@ -864,7 +873,8 @@ static int
 mlxsw_devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
 				  unsigned int sb_index, u16 tc_index,
 				  enum devlink_sb_pool_type pool_type,
-				  u16 pool_index, u32 threshold)
+				  u16 pool_index, u32 threshold,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
 	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
@@ -875,7 +885,7 @@ mlxsw_devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
 		return -EOPNOTSUPP;
 	return mlxsw_driver->sb_tc_pool_bind_set(mlxsw_core_port, sb_index,
 						 tc_index, pool_type,
-						 pool_index, threshold);
+						 pool_index, threshold, extack);
 }
 
 static int mlxsw_devlink_sb_occ_snapshot(struct devlink *devlink,
@@ -934,6 +944,46 @@ mlxsw_devlink_sb_occ_tc_port_bind_get(struct devlink_port *devlink_port,
 						     pool_type, p_cur, p_max);
 }
 
+static int
+mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
+		       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	char fw_info_psid[MLXSW_REG_MGIR_FW_INFO_PSID_SIZE];
+	u32 hw_rev, fw_major, fw_minor, fw_sub_minor;
+	char mgir_pl[MLXSW_REG_MGIR_LEN];
+	char buf[32];
+	int err;
+
+	err = devlink_info_driver_name_put(req,
+					   mlxsw_core->bus_info->device_kind);
+	if (err)
+		return err;
+
+	mlxsw_reg_mgir_pack(mgir_pl);
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgir), mgir_pl);
+	if (err)
+		return err;
+	mlxsw_reg_mgir_unpack(mgir_pl, &hw_rev, fw_info_psid, &fw_major,
+			      &fw_minor, &fw_sub_minor);
+
+	sprintf(buf, "%X", hw_rev);
+	err = devlink_info_version_fixed_put(req, "hw.revision", buf);
+	if (err)
+		return err;
+
+	err = devlink_info_version_fixed_put(req, "fw.psid", fw_info_psid);
+	if (err)
+		return err;
+
+	sprintf(buf, "%d.%d.%d", fw_major, fw_minor, fw_sub_minor);
+	err = devlink_info_version_running_put(req, "fw.version", buf);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink,
 						struct netlink_ext_ack *extack)
 {
@@ -953,6 +1003,20 @@ static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink,
 	return err;
 }
 
+static int mlxsw_devlink_flash_update(struct devlink *devlink,
+				      const char *file_name,
+				      const char *component,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
+
+	if (!mlxsw_driver->flash_update)
+		return -EOPNOTSUPP;
+	return mlxsw_driver->flash_update(mlxsw_core, file_name,
+					  component, extack);
+}
+
 static const struct devlink_ops mlxsw_devlink_ops = {
 	.reload				= mlxsw_devlink_core_bus_device_reload,
 	.port_type_set			= mlxsw_devlink_port_type_set,
@@ -968,6 +1032,8 @@ static const struct devlink_ops mlxsw_devlink_ops = {
 	.sb_occ_max_clear		= mlxsw_devlink_sb_occ_max_clear,
 	.sb_occ_port_pool_get		= mlxsw_devlink_sb_occ_port_pool_get,
 	.sb_occ_tc_port_bind_get	= mlxsw_devlink_sb_occ_tc_port_bind_get,
+	.info_get			= mlxsw_devlink_info_get,
+	.flash_update			= mlxsw_devlink_flash_update,
 };
 
 static int
@@ -1047,6 +1113,12 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 			goto err_register_params;
 	}
 
+	if (mlxsw_driver->init) {
+		err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info);
+		if (err)
+			goto err_driver_init;
+	}
+
 	err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon);
 	if (err)
 		goto err_hwmon_init;
@@ -1056,19 +1128,17 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_thermal_init;
 
-	if (mlxsw_driver->init) {
-		err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info);
-		if (err)
-			goto err_driver_init;
-	}
+	if (mlxsw_driver->params_register && !reload)
+		devlink_params_publish(devlink);
 
 	return 0;
 
-err_driver_init:
-	mlxsw_thermal_fini(mlxsw_core->thermal);
 err_thermal_init:
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 err_hwmon_init:
+	if (mlxsw_core->driver->fini)
+		mlxsw_core->driver->fini(mlxsw_core);
+err_driver_init:
 	if (mlxsw_driver->params_unregister && !reload)
 		mlxsw_driver->params_unregister(mlxsw_core);
 err_register_params:
@@ -1131,10 +1201,12 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 			return;
 	}
 
-	if (mlxsw_core->driver->fini)
-		mlxsw_core->driver->fini(mlxsw_core);
+	if (mlxsw_core->driver->params_unregister && !reload)
+		devlink_params_unpublish(devlink);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
+	if (mlxsw_core->driver->fini)
+		mlxsw_core->driver->fini(mlxsw_core);
 	if (mlxsw_core->driver->params_unregister && !reload)
 		mlxsw_core->driver->params_unregister(mlxsw_core);
 	if (!reload)
@@ -1173,6 +1245,15 @@ int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(mlxsw_core_skb_transmit);
 
+void mlxsw_core_ptp_transmitted(struct mlxsw_core *mlxsw_core,
+				struct sk_buff *skb, u8 local_port)
+{
+	if (mlxsw_core->driver->ptp_transmitted)
+		mlxsw_core->driver->ptp_transmitted(mlxsw_core, skb,
+						    local_port);
+}
+EXPORT_SYMBOL(mlxsw_core_ptp_transmitted);
+
 static bool __is_rx_listener_equal(const struct mlxsw_rx_listener *rxl_a,
 				   const struct mlxsw_rx_listener *rxl_b)
 {
@@ -1460,13 +1541,17 @@ static int mlxsw_reg_trans_wait(struct mlxsw_reg_trans *trans)
 	if (trans->retries)
 		dev_warn(mlxsw_core->bus_info->dev, "EMAD retries (%d/%d) (tid=%llx)\n",
 			 trans->retries, MLXSW_EMAD_MAX_RETRY, trans->tid);
-	if (err)
+	if (err) {
 		dev_err(mlxsw_core->bus_info->dev, "EMAD reg access failed (tid=%llx,reg_id=%x(%s),type=%s,status=%x(%s))\n",
 			trans->tid, trans->reg->id,
 			mlxsw_reg_id_str(trans->reg->id),
 			mlxsw_core_reg_access_type_str(trans->type),
 			trans->emad_status,
 			mlxsw_emad_op_tlv_status_str(trans->emad_status));
+		trace_devlink_hwerr(priv_to_devlink(mlxsw_core),
+				    trans->emad_status,
+				    mlxsw_emad_op_tlv_status_str(trans->emad_status));
+	}
 
 	list_del(&trans->bulk_list);
 	kfree_rcu(trans, rcu);
@@ -1709,7 +1794,11 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_res_get);
 
-int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port)
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port,
+			 u32 port_number, bool split,
+			 u32 split_port_subnumber,
+			 const unsigned char *switch_id,
+			 unsigned char switch_id_len)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 	struct mlxsw_core_port *mlxsw_core_port =
@@ -1718,6 +1807,9 @@ int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port)
 	int err;
 
 	mlxsw_core_port->local_port = local_port;
+	devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
+			       port_number, split, split_port_subnumber,
+			       switch_id, switch_id_len);
 	err = devlink_port_register(devlink, devlink_port, local_port);
 	if (err)
 		memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port));
@@ -1737,17 +1829,13 @@ void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port)
 EXPORT_SYMBOL(mlxsw_core_port_fini);
 
 void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port,
-			     void *port_driver_priv, struct net_device *dev,
-			     u32 port_number, bool split,
-			     u32 split_port_subnumber)
+			     void *port_driver_priv, struct net_device *dev)
 {
 	struct mlxsw_core_port *mlxsw_core_port =
 					&mlxsw_core->ports[local_port];
 	struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
 
 	mlxsw_core_port->port_driver_priv = port_driver_priv;
-	devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
-			       port_number, split, split_port_subnumber);
 	devlink_port_type_eth_set(devlink_port, dev);
 }
 EXPORT_SYMBOL(mlxsw_core_port_eth_set);
@@ -1787,16 +1875,18 @@ enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core,
 }
 EXPORT_SYMBOL(mlxsw_core_port_type_get);
 
-int mlxsw_core_port_get_phys_port_name(struct mlxsw_core *mlxsw_core,
-				       u8 local_port, char *name, size_t len)
+
+struct devlink_port *
+mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core,
+				 u8 local_port)
 {
 	struct mlxsw_core_port *mlxsw_core_port =
 					&mlxsw_core->ports[local_port];
 	struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port;
 
-	return devlink_port_get_phys_port_name(devlink_port, name, len);
+	return devlink_port;
 }
-EXPORT_SYMBOL(mlxsw_core_port_get_phys_port_name);
+EXPORT_SYMBOL(mlxsw_core_port_devlink_port_get);
 
 static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core,
 				    const char *buf, size_t size)
@@ -1908,14 +1998,63 @@ void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_fw_flash_end);
 
+int mlxsw_core_resources_query(struct mlxsw_core *mlxsw_core, char *mbox,
+			       struct mlxsw_res *res)
+{
+	int index, i;
+	u64 data;
+	u16 id;
+	int err;
+
+	if (!res)
+		return 0;
+
+	mlxsw_cmd_mbox_zero(mbox);
+
+	for (index = 0; index < MLXSW_CMD_QUERY_RESOURCES_MAX_QUERIES;
+	     index++) {
+		err = mlxsw_cmd_query_resources(mlxsw_core, mbox, index);
+		if (err)
+			return err;
+
+		for (i = 0; i < MLXSW_CMD_QUERY_RESOURCES_PER_QUERY; i++) {
+			id = mlxsw_cmd_mbox_query_resource_id_get(mbox, i);
+			data = mlxsw_cmd_mbox_query_resource_data_get(mbox, i);
+
+			if (id == MLXSW_CMD_QUERY_RESOURCES_TABLE_END_ID)
+				return 0;
+
+			mlxsw_res_parse(res, id, data);
+		}
+	}
+
+	/* If after MLXSW_RESOURCES_QUERY_MAX_QUERIES we still didn't get
+	 * MLXSW_RESOURCES_TABLE_END_ID, something went bad in the FW.
+	 */
+	return -EIO;
+}
+EXPORT_SYMBOL(mlxsw_core_resources_query);
+
+u32 mlxsw_core_read_frc_h(struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->bus->read_frc_h(mlxsw_core->bus_priv);
+}
+EXPORT_SYMBOL(mlxsw_core_read_frc_h);
+
+u32 mlxsw_core_read_frc_l(struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_core->bus->read_frc_l(mlxsw_core->bus_priv);
+}
+EXPORT_SYMBOL(mlxsw_core_read_frc_l);
+
 static int __init mlxsw_core_module_init(void)
 {
 	int err;
 
-	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
 	if (!mlxsw_wq)
 		return -ENOMEM;
-	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM,
+	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0,
 					    mlxsw_core_driver_name);
 	if (!mlxsw_owq) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 4e114f35ee0d..8efcff4b59cb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -28,6 +28,8 @@ unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core);
 
 void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core);
 
+bool mlxsw_core_res_query_enabled(const struct mlxsw_core *mlxsw_core);
+
 int mlxsw_core_driver_register(struct mlxsw_driver *mlxsw_driver);
 void mlxsw_core_driver_unregister(struct mlxsw_driver *mlxsw_driver);
 
@@ -46,6 +48,8 @@ bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_tx_info *tx_info);
 int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    const struct mlxsw_tx_info *tx_info);
+void mlxsw_core_ptp_transmitted(struct mlxsw_core *mlxsw_core,
+				struct sk_buff *skb, u8 local_port);
 
 struct mlxsw_rx_listener {
 	void (*func)(struct sk_buff *skb, u8 local_port, void *priv);
@@ -164,24 +168,29 @@ void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
 				  u16 lag_id, u8 local_port);
 
 void *mlxsw_core_port_driver_priv(struct mlxsw_core_port *mlxsw_core_port);
-int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port);
+int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port,
+			 u32 port_number, bool split,
+			 u32 split_port_subnumber,
+			 const unsigned char *switch_id,
+			 unsigned char switch_id_len);
 void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port);
 void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port,
-			     void *port_driver_priv, struct net_device *dev,
-			     u32 port_number, bool split,
-			     u32 split_port_subnumber);
+			     void *port_driver_priv, struct net_device *dev);
 void mlxsw_core_port_ib_set(struct mlxsw_core *mlxsw_core, u8 local_port,
 			    void *port_driver_priv);
 void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u8 local_port,
 			   void *port_driver_priv);
 enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core,
 						u8 local_port);
-int mlxsw_core_port_get_phys_port_name(struct mlxsw_core *mlxsw_core,
-				       u8 local_port, char *name, size_t len);
+struct devlink_port *
+mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core,
+				 u8 local_port);
 
 int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay);
 bool mlxsw_core_schedule_work(struct work_struct *work);
 void mlxsw_core_flush_owq(void);
+int mlxsw_core_resources_query(struct mlxsw_core *mlxsw_core, char *mbox,
+			       struct mlxsw_res *res);
 
 #define MLXSW_CONFIG_PROFILE_SWID_COUNT 8
 
@@ -249,13 +258,14 @@ struct mlxsw_driver {
 			   struct devlink_sb_pool_info *pool_info);
 	int (*sb_pool_set)(struct mlxsw_core *mlxsw_core,
 			   unsigned int sb_index, u16 pool_index, u32 size,
-			   enum devlink_sb_threshold_type threshold_type);
+			   enum devlink_sb_threshold_type threshold_type,
+			   struct netlink_ext_ack *extack);
 	int (*sb_port_pool_get)(struct mlxsw_core_port *mlxsw_core_port,
 				unsigned int sb_index, u16 pool_index,
 				u32 *p_threshold);
 	int (*sb_port_pool_set)(struct mlxsw_core_port *mlxsw_core_port,
 				unsigned int sb_index, u16 pool_index,
-				u32 threshold);
+				u32 threshold, struct netlink_ext_ack *extack);
 	int (*sb_tc_pool_bind_get)(struct mlxsw_core_port *mlxsw_core_port,
 				   unsigned int sb_index, u16 tc_index,
 				   enum devlink_sb_pool_type pool_type,
@@ -263,7 +273,8 @@ struct mlxsw_driver {
 	int (*sb_tc_pool_bind_set)(struct mlxsw_core_port *mlxsw_core_port,
 				   unsigned int sb_index, u16 tc_index,
 				   enum devlink_sb_pool_type pool_type,
-				   u16 pool_index, u32 threshold);
+				   u16 pool_index, u32 threshold,
+				   struct netlink_ext_ack *extack);
 	int (*sb_occ_snapshot)(struct mlxsw_core *mlxsw_core,
 			       unsigned int sb_index);
 	int (*sb_occ_max_clear)(struct mlxsw_core *mlxsw_core,
@@ -275,6 +286,9 @@ struct mlxsw_driver {
 				       unsigned int sb_index, u16 tc_index,
 				       enum devlink_sb_pool_type pool_type,
 				       u32 *p_cur, u32 *p_max);
+	int (*flash_update)(struct mlxsw_core *mlxsw_core,
+			    const char *file_name, const char *component,
+			    struct netlink_ext_ack *extack);
 	void (*txhdr_construct)(struct sk_buff *skb,
 				const struct mlxsw_tx_info *tx_info);
 	int (*resources_register)(struct mlxsw_core *mlxsw_core);
@@ -284,6 +298,13 @@ struct mlxsw_driver {
 			     u64 *p_linear_size);
 	int (*params_register)(struct mlxsw_core *mlxsw_core);
 	void (*params_unregister)(struct mlxsw_core *mlxsw_core);
+
+	/* Notify a driver that a timestamped packet was transmitted. Driver
+	 * is responsible for freeing the passed-in SKB.
+	 */
+	void (*ptp_transmitted)(struct mlxsw_core *mlxsw_core,
+				struct sk_buff *skb, u8 local_port);
+
 	u8 txhdr_len;
 	const struct mlxsw_config_profile *profile;
 	bool res_query_enabled;
@@ -297,6 +318,9 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core);
 void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core);
 
+u32 mlxsw_core_read_frc_h(struct mlxsw_core *mlxsw_core);
+u32 mlxsw_core_read_frc_l(struct mlxsw_core *mlxsw_core);
+
 bool mlxsw_core_res_valid(struct mlxsw_core *mlxsw_core,
 			  enum mlxsw_res_id res_id);
 
@@ -327,6 +351,8 @@ struct mlxsw_bus {
 			char *in_mbox, size_t in_mbox_size,
 			char *out_mbox, size_t out_mbox_size,
 			u8 *p_status);
+	u32 (*read_frc_h)(void *bus_priv);
+	u32 (*read_frc_l)(void *bus_priv);
 	u8 features;
 };
 
@@ -344,6 +370,8 @@ struct mlxsw_bus_info {
 	struct mlxsw_fw_rev fw_rev;
 	u8 vsd[MLXSW_CMD_BOARDINFO_VSD_LEN];
 	u8 psid[MLXSW_CMD_BOARDINFO_PSID_LEN];
+	u8 low_frequency:1,
+	   read_frc_capable:1;
 };
 
 struct mlxsw_hwmon;
@@ -394,4 +422,19 @@ static inline void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 
 #endif
 
+enum mlxsw_devlink_param_id {
+	MLXSW_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL,
+};
+
+struct mlxsw_skb_cb {
+	struct mlxsw_tx_info tx_info;
+};
+
+static inline struct mlxsw_skb_cb *mlxsw_skb_cb(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(mlxsw_skb_cb) > sizeof(skb->cb));
+	return (struct mlxsw_skb_cb *) skb->cb;
+}
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index df78d23b3ec3..feb4672a5ac0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -30,8 +30,9 @@ static bool mlxsw_afk_blocks_check(struct mlxsw_afk *mlxsw_afk)
 
 			elinst = &block->instances[j];
 			if (elinst->type != elinst->info->type ||
-			    elinst->item.size.bits !=
-			    elinst->info->item.size.bits)
+			    (!elinst->avoid_size_check &&
+			     elinst->item.size.bits !=
+			     elinst->info->item.size.bits))
 				return false;
 		}
 	}
@@ -236,12 +237,10 @@ mlxsw_afk_key_info_create(struct mlxsw_afk *mlxsw_afk,
 			  struct mlxsw_afk_element_usage *elusage)
 {
 	struct mlxsw_afk_key_info *key_info;
-	size_t alloc_size;
 	int err;
 
-	alloc_size = sizeof(*key_info) +
-		     sizeof(key_info->blocks[0]) * mlxsw_afk->max_blocks;
-	key_info = kzalloc(alloc_size, GFP_KERNEL);
+	key_info = kzalloc(struct_size(key_info, blocks, mlxsw_afk->max_blocks),
+			   GFP_KERNEL);
 	if (!key_info)
 		return ERR_PTR(-ENOMEM);
 	err = mlxsw_afk_picker(mlxsw_afk, key_info, elusage);
@@ -387,12 +386,12 @@ EXPORT_SYMBOL(mlxsw_afk_values_add_buf);
 
 static void mlxsw_sp_afk_encode_u32(const struct mlxsw_item *storage_item,
 				    const struct mlxsw_item *output_item,
-				    char *storage, char *output)
+				    char *storage, char *output, int diff)
 {
 	u32 value;
 
 	value = __mlxsw_item_get32(storage, storage_item, 0);
-	__mlxsw_item_set32(output, output_item, 0, value);
+	__mlxsw_item_set32(output, output_item, 0, value + diff);
 }
 
 static void mlxsw_sp_afk_encode_buf(const struct mlxsw_item *storage_item,
@@ -408,14 +407,14 @@ static void mlxsw_sp_afk_encode_buf(const struct mlxsw_item *storage_item,
 
 static void
 mlxsw_sp_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
-			char *output, char *storage)
+			char *output, char *storage, int u32_diff)
 {
 	const struct mlxsw_item *storage_item = &elinst->info->item;
 	const struct mlxsw_item *output_item = &elinst->item;
 
 	if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
 		mlxsw_sp_afk_encode_u32(storage_item, output_item,
-					storage, output);
+					storage, output, u32_diff);
 	else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
 		mlxsw_sp_afk_encode_buf(storage_item, output_item,
 					storage, output);
@@ -448,9 +447,10 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 				continue;
 
 			mlxsw_sp_afk_encode_one(elinst, block_key,
-						values->storage.key);
+						values->storage.key,
+						elinst->u32_key_diff);
 			mlxsw_sp_afk_encode_one(elinst, block_mask,
-						values->storage.mask);
+						values->storage.mask, 0);
 		}
 
 		mlxsw_afk->ops->encode_block(key, i, block_key);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 4a625cdf3e7c..cb229b55ecc4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -74,7 +74,7 @@ struct mlxsw_afk_element_info {
  * define an internal storage geometry.
  */
 static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
-	MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 8),
+	MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 16),
 	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_32_47, 0x04, 2),
 	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_0_31, 0x06, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_32_47, 0x0A, 2),
@@ -107,9 +107,14 @@ struct mlxsw_afk_element_inst { /* element instance in actual block */
 	const struct mlxsw_afk_element_info *info;
 	enum mlxsw_afk_element_type type;
 	struct mlxsw_item item; /* element geometry in block */
+	int u32_key_diff; /* in case value needs to be adjusted before write
+			   * this diff is here to handle that
+			   */
+	bool avoid_size_check;
 };
 
-#define MLXSW_AFK_ELEMENT_INST(_type, _element, _offset, _shift, _size)		\
+#define MLXSW_AFK_ELEMENT_INST(_type, _element, _offset,			\
+			       _shift, _size, _u32_key_diff, _avoid_size_check)	\
 	{									\
 		.info = &mlxsw_afk_element_infos[MLXSW_AFK_ELEMENT_##_element],	\
 		.type = _type,							\
@@ -119,15 +124,24 @@ struct mlxsw_afk_element_inst { /* element instance in actual block */
 			.size = {.bits = _size},				\
 			.name = #_element,					\
 		},								\
+		.u32_key_diff = _u32_key_diff,					\
+		.avoid_size_check = _avoid_size_check,				\
 	}
 
 #define MLXSW_AFK_ELEMENT_INST_U32(_element, _offset, _shift, _size)		\
 	MLXSW_AFK_ELEMENT_INST(MLXSW_AFK_ELEMENT_TYPE_U32,			\
-			       _element, _offset, _shift, _size)
+			       _element, _offset, _shift, _size, 0, false)
+
+#define MLXSW_AFK_ELEMENT_INST_EXT_U32(_element, _offset,			\
+				       _shift, _size, _key_diff,		\
+				       _avoid_size_check)			\
+	MLXSW_AFK_ELEMENT_INST(MLXSW_AFK_ELEMENT_TYPE_U32,			\
+			       _element, _offset, _shift, _size,		\
+			       _key_diff, _avoid_size_check)
 
 #define MLXSW_AFK_ELEMENT_INST_BUF(_element, _offset, _size)			\
 	MLXSW_AFK_ELEMENT_INST(MLXSW_AFK_ELEMENT_TYPE_BUF,			\
-			       _element, _offset, 0, _size)
+			       _element, _offset, 0, _size, 0, false)
 
 struct mlxsw_afk_block {
 	u16 encoding; /* block ID */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
new file mode 100644
index 000000000000..d2c7ce67c300
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -0,0 +1,239 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/sfp.h>
+
+#include "core.h"
+#include "core_env.h"
+#include "item.h"
+#include "reg.h"
+
+static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
+					  bool *qsfp)
+{
+	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
+	char mcia_pl[MLXSW_REG_MCIA_LEN];
+	u8 ident;
+	int err;
+
+	mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1,
+			    MLXSW_REG_MCIA_I2C_ADDR_LOW);
+	err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
+	if (err)
+		return err;
+	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
+	ident = eeprom_tmp[0];
+	switch (ident) {
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
+		*qsfp = false;
+		break;
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD:
+		*qsfp = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module,
+			      u16 offset, u16 size, void *data,
+			      unsigned int *p_read_size)
+{
+	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
+	char mcia_pl[MLXSW_REG_MCIA_LEN];
+	u16 i2c_addr;
+	int status;
+	int err;
+
+	size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE);
+
+	if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH &&
+	    offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH)
+		/* Cross pages read, read until offset 256 in low page */
+		size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset;
+
+	i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW;
+	if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) {
+		i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH;
+		offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH;
+	}
+
+	mlxsw_reg_mcia_pack(mcia_pl, module, 0, 0, offset, size, i2c_addr);
+
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcia), mcia_pl);
+	if (err)
+		return err;
+
+	status = mlxsw_reg_mcia_status_get(mcia_pl);
+	if (status)
+		return -EIO;
+
+	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
+	memcpy(data, eeprom_tmp, size);
+	*p_read_size = size;
+
+	return 0;
+}
+
+int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
+					 int off, int *temp)
+{
+	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
+	union {
+		u8 buf[MLXSW_REG_MCIA_TH_ITEM_SIZE];
+		u16 temp;
+	} temp_thresh;
+	char mcia_pl[MLXSW_REG_MCIA_LEN] = {0};
+	char mtmp_pl[MLXSW_REG_MTMP_LEN];
+	unsigned int module_temp;
+	bool qsfp;
+	int err;
+
+	mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN + module,
+			    false, false);
+	err = mlxsw_reg_query(core, MLXSW_REG(mtmp), mtmp_pl);
+	if (err)
+		return err;
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &module_temp, NULL, NULL);
+	if (!module_temp) {
+		*temp = 0;
+		return 0;
+	}
+
+	/* Read Free Side Device Temperature Thresholds from page 03h
+	 * (MSB at lower byte address).
+	 * Bytes:
+	 * 128-129 - Temp High Alarm (SFP_TEMP_HIGH_ALARM);
+	 * 130-131 - Temp Low Alarm (SFP_TEMP_LOW_ALARM);
+	 * 132-133 - Temp High Warning (SFP_TEMP_HIGH_WARN);
+	 * 134-135 - Temp Low Warning (SFP_TEMP_LOW_WARN);
+	 */
+
+	/* Validate module identifier value. */
+	err = mlxsw_env_validate_cable_ident(core, module, &qsfp);
+	if (err)
+		return err;
+
+	if (qsfp)
+		mlxsw_reg_mcia_pack(mcia_pl, module, 0,
+				    MLXSW_REG_MCIA_TH_PAGE_NUM,
+				    MLXSW_REG_MCIA_TH_PAGE_OFF + off,
+				    MLXSW_REG_MCIA_TH_ITEM_SIZE,
+				    MLXSW_REG_MCIA_I2C_ADDR_LOW);
+	else
+		mlxsw_reg_mcia_pack(mcia_pl, module, 0,
+				    MLXSW_REG_MCIA_PAGE0_LO,
+				    off, MLXSW_REG_MCIA_TH_ITEM_SIZE,
+				    MLXSW_REG_MCIA_I2C_ADDR_HIGH);
+
+	err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
+	memcpy(temp_thresh.buf, eeprom_tmp, MLXSW_REG_MCIA_TH_ITEM_SIZE);
+	*temp = temp_thresh.temp * 1000;
+
+	return 0;
+}
+
+int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
+			      struct ethtool_modinfo *modinfo)
+{
+	u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE];
+	u16 offset = MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE;
+	u8 module_rev_id, module_id, diag_mon;
+	unsigned int read_size;
+	int err;
+
+	err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset,
+					    module_info, &read_size);
+	if (err)
+		return err;
+
+	if (read_size < offset)
+		return -EIO;
+
+	module_rev_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID];
+	module_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID];
+
+	switch (module_id) {
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP:
+		modinfo->type       = ETH_MODULE_SFF_8436;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		break;
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28:
+		if (module_id == MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 ||
+		    module_rev_id >=
+		    MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636) {
+			modinfo->type       = ETH_MODULE_SFF_8636;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		} else {
+			modinfo->type       = ETH_MODULE_SFF_8436;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		}
+		break;
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
+		/* Verify if transceiver provides diagnostic monitoring page */
+		err = mlxsw_env_query_module_eeprom(mlxsw_core, module,
+						    SFP_DIAGMON, 1, &diag_mon,
+						    &read_size);
+		if (err)
+			return err;
+
+		if (read_size < 1)
+			return -EIO;
+
+		modinfo->type       = ETH_MODULE_SFF_8472;
+		if (diag_mon)
+			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		else
+			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN / 2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_env_get_module_info);
+
+int mlxsw_env_get_module_eeprom(struct net_device *netdev,
+				struct mlxsw_core *mlxsw_core, int module,
+				struct ethtool_eeprom *ee, u8 *data)
+{
+	int offset = ee->offset;
+	unsigned int read_size;
+	int i = 0;
+	int err;
+
+	if (!ee->len)
+		return -EINVAL;
+
+	memset(data, 0, ee->len);
+
+	while (i < ee->len) {
+		err = mlxsw_env_query_module_eeprom(mlxsw_core, module, offset,
+						    ee->len - i, data + i,
+						    &read_size);
+		if (err) {
+			netdev_err(netdev, "Eeprom query failed\n");
+			return err;
+		}
+
+		i += read_size;
+		offset += read_size;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_env_get_module_eeprom);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
new file mode 100644
index 000000000000..064d0e770c01
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#ifndef _MLXSW_CORE_ENV_H
+#define _MLXSW_CORE_ENV_H
+
+int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
+					 int off, int *temp);
+
+int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
+			      struct ethtool_modinfo *modinfo);
+
+int mlxsw_env_get_module_eeprom(struct net_device *netdev,
+				struct mlxsw_core *mlxsw_core, int module,
+				struct ethtool_eeprom *ee, u8 *data);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index e04e8162aa14..5b00726c4346 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -7,8 +7,10 @@
 #include <linux/sysfs.h>
 #include <linux/hwmon.h>
 #include <linux/err.h>
+#include <linux/sfp.h>
 
 #include "core.h"
+#include "core_env.h"
 
 #define MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT 127
 #define MLXSW_HWMON_ATTR_COUNT (MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT * 4 + \
@@ -21,6 +23,14 @@ struct mlxsw_hwmon_attr {
 	char name[32];
 };
 
+static int mlxsw_hwmon_get_attr_index(int index, int count)
+{
+	if (index >= count)
+		return index % count + MLXSW_REG_MTMP_GBOX_INDEX_MIN;
+
+	return index;
+}
+
 struct mlxsw_hwmon {
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
@@ -30,6 +40,8 @@ struct mlxsw_hwmon {
 	struct attribute *attrs[MLXSW_HWMON_ATTR_COUNT + 1];
 	struct mlxsw_hwmon_attr hwmon_attrs[MLXSW_HWMON_ATTR_COUNT];
 	unsigned int attrs_count;
+	u8 sensor_count;
+	u8 module_sensor_count;
 };
 
 static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
@@ -40,18 +52,19 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
 			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
 	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp;
+	int temp, index;
 	int err;
 
-	mlxsw_reg_mtmp_pack(mtmp_pl, mlwsw_hwmon_attr->type_index,
-			    false, false);
+	index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
+					   mlxsw_hwmon->module_sensor_count);
+	mlxsw_reg_mtmp_pack(mtmp_pl, index, false, false);
 	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl);
 	if (err) {
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query temp sensor\n");
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
-	return sprintf(buf, "%u\n", temp);
+	return sprintf(buf, "%d\n", temp);
 }
 
 static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
@@ -62,18 +75,19 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
 			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
 	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp_max;
+	int temp_max, index;
 	int err;
 
-	mlxsw_reg_mtmp_pack(mtmp_pl, mlwsw_hwmon_attr->type_index,
-			    false, false);
+	index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
+					   mlxsw_hwmon->module_sensor_count);
+	mlxsw_reg_mtmp_pack(mtmp_pl, index, false, false);
 	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl);
 	if (err) {
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query temp sensor\n");
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, NULL, &temp_max, NULL);
-	return sprintf(buf, "%u\n", temp_max);
+	return sprintf(buf, "%d\n", temp_max);
 }
 
 static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev,
@@ -85,6 +99,7 @@ static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev,
 	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
 	unsigned long val;
+	int index;
 	int err;
 
 	err = kstrtoul(buf, 10, &val);
@@ -93,7 +108,9 @@ static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev,
 	if (val != 1)
 		return -EINVAL;
 
-	mlxsw_reg_mtmp_pack(mtmp_pl, mlwsw_hwmon_attr->type_index, true, true);
+	index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
+					   mlxsw_hwmon->module_sensor_count);
+	mlxsw_reg_mtmp_pack(mtmp_pl, index, true, true);
 	err = mlxsw_reg_write(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl);
 	if (err) {
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to reset temp sensor history\n");
@@ -121,6 +138,27 @@ static ssize_t mlxsw_hwmon_fan_rpm_show(struct device *dev,
 	return sprintf(buf, "%u\n", mlxsw_reg_mfsm_rpm_get(mfsm_pl));
 }
 
+static ssize_t mlxsw_hwmon_fan_fault_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	char fore_pl[MLXSW_REG_FORE_LEN];
+	bool fault;
+	int err;
+
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(fore), fore_pl);
+	if (err) {
+		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query fan\n");
+		return err;
+	}
+	mlxsw_reg_fore_unpack(fore_pl, mlwsw_hwmon_attr->type_index, &fault);
+
+	return sprintf(buf, "%u\n", fault);
+}
+
 static ssize_t mlxsw_hwmon_pwm_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -167,12 +205,155 @@ static ssize_t mlxsw_hwmon_pwm_store(struct device *dev,
 	return len;
 }
 
+static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	char mtmp_pl[MLXSW_REG_MTMP_LEN];
+	u8 module;
+	int temp;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN + module,
+			    false, false);
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl);
+	if (err)
+		return err;
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+
+	return sprintf(buf, "%d\n", temp);
+}
+
+static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev,
+						  struct device_attribute *attr,
+						  char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0};
+	u8 module, fault;
+	u16 temp;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module,
+			    1);
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtbr), mtbr_pl);
+	if (err) {
+		dev_err(dev, "Failed to query module temperature sensor\n");
+		return err;
+	}
+
+	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL);
+
+	/* Update status and temperature cache. */
+	switch (temp) {
+	case MLXSW_REG_MTBR_BAD_SENS_INFO:
+		/* Untrusted cable is connected. Reading temperature from its
+		 * sensor is faulty.
+		 */
+		fault = 1;
+		break;
+	case MLXSW_REG_MTBR_NO_CONN: /* fall-through */
+	case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */
+	case MLXSW_REG_MTBR_INDEX_NA:
+	default:
+		fault = 0;
+		break;
+	}
+
+	return sprintf(buf, "%u\n", fault);
+}
+
+static ssize_t
+mlxsw_hwmon_module_temp_critical_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	int temp;
+	u8 module;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module,
+						   SFP_TEMP_HIGH_WARN, &temp);
+	if (err) {
+		dev_err(dev, "Failed to query module temperature thresholds\n");
+		return err;
+	}
+
+	return sprintf(buf, "%u\n", temp);
+}
+
+static ssize_t
+mlxsw_hwmon_module_temp_emergency_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	u8 module;
+	int temp;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module,
+						   SFP_TEMP_HIGH_ALARM, &temp);
+	if (err) {
+		dev_err(dev, "Failed to query module temperature thresholds\n");
+		return err;
+	}
+
+	return sprintf(buf, "%u\n", temp);
+}
+
+static ssize_t
+mlxsw_hwmon_module_temp_label_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+
+	return sprintf(buf, "front panel %03u\n",
+		       mlwsw_hwmon_attr->type_index);
+}
+
+static ssize_t
+mlxsw_hwmon_gbox_temp_label_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	int index = mlwsw_hwmon_attr->type_index -
+		    mlxsw_hwmon->module_sensor_count + 1;
+
+	return sprintf(buf, "gearbox %03u\n", index);
+}
+
 enum mlxsw_hwmon_attr_type {
 	MLXSW_HWMON_ATTR_TYPE_TEMP,
 	MLXSW_HWMON_ATTR_TYPE_TEMP_MAX,
 	MLXSW_HWMON_ATTR_TYPE_TEMP_RST,
 	MLXSW_HWMON_ATTR_TYPE_FAN_RPM,
+	MLXSW_HWMON_ATTR_TYPE_FAN_FAULT,
 	MLXSW_HWMON_ATTR_TYPE_PWM,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_GBOX_LABEL,
 };
 
 static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
@@ -209,6 +390,12 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
 		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
 			 "fan%u_input", num + 1);
 		break;
+	case MLXSW_HWMON_ATTR_TYPE_FAN_FAULT:
+		mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_fan_fault_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "fan%u_fault", num + 1);
+		break;
 	case MLXSW_HWMON_ATTR_TYPE_PWM:
 		mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_pwm_show;
 		mlxsw_hwmon_attr->dev_attr.store = mlxsw_hwmon_pwm_store;
@@ -216,6 +403,47 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
 		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
 			 "pwm%u", num + 1);
 		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE:
+		mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_module_temp_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_input", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT:
+		mlxsw_hwmon_attr->dev_attr.show =
+					mlxsw_hwmon_module_temp_fault_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_fault", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT:
+		mlxsw_hwmon_attr->dev_attr.show =
+			mlxsw_hwmon_module_temp_critical_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_crit", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG:
+		mlxsw_hwmon_attr->dev_attr.show =
+			mlxsw_hwmon_module_temp_emergency_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_emergency", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL:
+		mlxsw_hwmon_attr->dev_attr.show =
+			mlxsw_hwmon_module_temp_label_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_label", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_GBOX_LABEL:
+		mlxsw_hwmon_attr->dev_attr.show =
+			mlxsw_hwmon_gbox_temp_label_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_label", num + 1);
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -233,7 +461,6 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
 {
 	char mtcap_pl[MLXSW_REG_MTCAP_LEN] = {0};
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	u8 sensor_count;
 	int i;
 	int err;
 
@@ -242,8 +469,8 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to get number of temp sensors\n");
 		return err;
 	}
-	sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl);
-	for (i = 0; i < sensor_count; i++) {
+	mlxsw_hwmon->sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl);
+	for (i = 0; i < mlxsw_hwmon->sensor_count; i++) {
 		mlxsw_reg_mtmp_pack(mtmp_pl, i, true, true);
 		err = mlxsw_reg_write(mlxsw_hwmon->core,
 				      MLXSW_REG(mtmp), mtmp_pl);
@@ -280,10 +507,14 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon)
 	mlxsw_reg_mfcr_unpack(mfcr_pl, &freq, &tacho_active, &pwm_active);
 	num = 0;
 	for (type_index = 0; type_index < MLXSW_MFCR_TACHOS_MAX; type_index++) {
-		if (tacho_active & BIT(type_index))
+		if (tacho_active & BIT(type_index)) {
 			mlxsw_hwmon_attr_add(mlxsw_hwmon,
 					     MLXSW_HWMON_ATTR_TYPE_FAN_RPM,
+					     type_index, num);
+			mlxsw_hwmon_attr_add(mlxsw_hwmon,
+					     MLXSW_HWMON_ATTR_TYPE_FAN_FAULT,
 					     type_index, num++);
+		}
 	}
 	num = 0;
 	for (type_index = 0; type_index < MLXSW_MFCR_PWMS_MAX; type_index++) {
@@ -295,6 +526,104 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon)
 	return 0;
 }
 
+static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon)
+{
+	unsigned int module_count = mlxsw_core_max_ports(mlxsw_hwmon->core);
+	char pmlp_pl[MLXSW_REG_PMLP_LEN] = {0};
+	int i, index;
+	u8 width;
+	int err;
+
+	if (!mlxsw_core_res_query_enabled(mlxsw_hwmon->core))
+		return 0;
+
+	/* Add extra attributes for module temperature. Sensor index is
+	 * assigned to sensor_count value, while all indexed before
+	 * sensor_count are already utilized by the sensors connected through
+	 * mtmp register by mlxsw_hwmon_temp_init().
+	 */
+	index = mlxsw_hwmon->sensor_count;
+	for (i = 1; i < module_count; i++) {
+		mlxsw_reg_pmlp_pack(pmlp_pl, i);
+		err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(pmlp),
+				      pmlp_pl);
+		if (err) {
+			dev_err(mlxsw_hwmon->bus_info->dev, "Failed to read module index %d\n",
+				i);
+			return err;
+		}
+		width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+		if (!width)
+			continue;
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, index,
+				     index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT,
+				     index, index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT,
+				     index, index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG,
+				     index, index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL,
+				     index, index);
+		index++;
+	}
+	mlxsw_hwmon->module_sensor_count = index;
+
+	return 0;
+}
+
+static int mlxsw_hwmon_gearbox_init(struct mlxsw_hwmon *mlxsw_hwmon)
+{
+	int index, max_index, sensor_index;
+	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
+	char mtmp_pl[MLXSW_REG_MTMP_LEN];
+	u8 gbox_num;
+	int err;
+
+	mlxsw_reg_mgpir_pack(mgpir_pl);
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mgpir), mgpir_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mgpir_unpack(mgpir_pl, &gbox_num, NULL, NULL);
+	if (!gbox_num)
+		return 0;
+
+	index = mlxsw_hwmon->module_sensor_count;
+	max_index = mlxsw_hwmon->module_sensor_count + gbox_num;
+	while (index < max_index) {
+		sensor_index = index % mlxsw_hwmon->module_sensor_count +
+			       MLXSW_REG_MTMP_GBOX_INDEX_MIN;
+		mlxsw_reg_mtmp_pack(mtmp_pl, sensor_index, true, true);
+		err = mlxsw_reg_write(mlxsw_hwmon->core,
+				      MLXSW_REG(mtmp), mtmp_pl);
+		if (err) {
+			dev_err(mlxsw_hwmon->bus_info->dev, "Failed to setup temp sensor number %d\n",
+				sensor_index);
+			return err;
+		}
+		mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_TEMP,
+				     index, index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MAX, index,
+				     index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_RST, index,
+				     index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_GBOX_LABEL,
+				     index, index);
+		index++;
+	}
+
+	return 0;
+}
+
 int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 		     const struct mlxsw_bus_info *mlxsw_bus_info,
 		     struct mlxsw_hwmon **p_hwmon)
@@ -317,6 +646,14 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_fans_init;
 
+	err = mlxsw_hwmon_module_init(mlxsw_hwmon);
+	if (err)
+		goto err_temp_module_init;
+
+	err = mlxsw_hwmon_gearbox_init(mlxsw_hwmon);
+	if (err)
+		goto err_temp_gearbox_init;
+
 	mlxsw_hwmon->groups[0] = &mlxsw_hwmon->group;
 	mlxsw_hwmon->group.attrs = mlxsw_hwmon->attrs;
 
@@ -333,6 +670,8 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 	return 0;
 
 err_hwmon_register:
+err_temp_gearbox_init:
+err_temp_module_init:
 err_fans_init:
 err_temp_init:
 	kfree(mlxsw_hwmon);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 61f897b40f82..35a1dc89c28a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -9,11 +9,21 @@
 #include <linux/sysfs.h>
 #include <linux/thermal.h>
 #include <linux/err.h>
+#include <linux/sfp.h>
 
 #include "core.h"
+#include "core_env.h"
 
 #define MLXSW_THERMAL_POLL_INT	1000	/* ms */
-#define MLXSW_THERMAL_MAX_TEMP	110000	/* 110C */
+#define MLXSW_THERMAL_SLOW_POLL_INT	20000	/* ms */
+#define MLXSW_THERMAL_ASIC_TEMP_NORM	75000	/* 75C */
+#define MLXSW_THERMAL_ASIC_TEMP_HIGH	85000	/* 85C */
+#define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
+#define MLXSW_THERMAL_ASIC_TEMP_CRIT	110000	/* 110C */
+#define MLXSW_THERMAL_HYSTERESIS_TEMP	5000	/* 5C */
+#define MLXSW_THERMAL_MODULE_TEMP_SHIFT	(MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
+#define MLXSW_THERMAL_ZONE_MAX_NAME	16
+#define MLXSW_THERMAL_TEMP_SCORE_MAX	GENMASK(31, 0)
 #define MLXSW_THERMAL_MAX_STATE	10
 #define MLXSW_THERMAL_MAX_DUTY	255
 /* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values
@@ -26,9 +36,22 @@
 #define MLXSW_THERMAL_SPEED_MAX		(MLXSW_THERMAL_MAX_STATE * 2)
 #define MLXSW_THERMAL_SPEED_MIN_LEVEL	2		/* 20% */
 
+/* External cooling devices, allowed for binding to mlxsw thermal zones. */
+static char * const mlxsw_thermal_external_allowed_cdev[] = {
+	"mlxreg_fan",
+};
+
+enum mlxsw_thermal_trips {
+	MLXSW_THERMAL_TEMP_TRIP_NORM,
+	MLXSW_THERMAL_TEMP_TRIP_HIGH,
+	MLXSW_THERMAL_TEMP_TRIP_HOT,
+	MLXSW_THERMAL_TEMP_TRIP_CRIT,
+};
+
 struct mlxsw_thermal_trip {
 	int	type;
 	int	temp;
+	int	hyst;
 	int	min_state;
 	int	max_state;
 };
@@ -36,32 +59,29 @@ struct mlxsw_thermal_trip {
 static const struct mlxsw_thermal_trip default_thermal_trips[] = {
 	{	/* In range - 0-40% PWM */
 		.type		= THERMAL_TRIP_ACTIVE,
-		.temp		= 75000,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_NORM,
+		.hyst		= MLXSW_THERMAL_HYSTERESIS_TEMP,
 		.min_state	= 0,
 		.max_state	= (4 * MLXSW_THERMAL_MAX_STATE) / 10,
 	},
-	{	/* High - 40-100% PWM */
-		.type		= THERMAL_TRIP_ACTIVE,
-		.temp		= 80000,
-		.min_state	= (4 * MLXSW_THERMAL_MAX_STATE) / 10,
-		.max_state	= MLXSW_THERMAL_MAX_STATE,
-	},
 	{
-		/* Very high - 100% PWM */
+		/* In range - 40-100% PWM */
 		.type		= THERMAL_TRIP_ACTIVE,
-		.temp		= 85000,
-		.min_state	= MLXSW_THERMAL_MAX_STATE,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_HIGH,
+		.hyst		= MLXSW_THERMAL_HYSTERESIS_TEMP,
+		.min_state	= (4 * MLXSW_THERMAL_MAX_STATE) / 10,
 		.max_state	= MLXSW_THERMAL_MAX_STATE,
 	},
 	{	/* Warning */
 		.type		= THERMAL_TRIP_HOT,
-		.temp		= 105000,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_HOT,
+		.hyst		= MLXSW_THERMAL_HYSTERESIS_TEMP,
 		.min_state	= MLXSW_THERMAL_MAX_STATE,
 		.max_state	= MLXSW_THERMAL_MAX_STATE,
 	},
 	{	/* Critical - soft poweroff */
 		.type		= THERMAL_TRIP_CRITICAL,
-		.temp		= MLXSW_THERMAL_MAX_TEMP,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_CRIT,
 		.min_state	= MLXSW_THERMAL_MAX_STATE,
 		.max_state	= MLXSW_THERMAL_MAX_STATE,
 	}
@@ -72,14 +92,30 @@ static const struct mlxsw_thermal_trip default_thermal_trips[] = {
 /* Make sure all trips are writable */
 #define MLXSW_THERMAL_TRIP_MASK	(BIT(MLXSW_THERMAL_NUM_TRIPS) - 1)
 
+struct mlxsw_thermal;
+
+struct mlxsw_thermal_module {
+	struct mlxsw_thermal *parent;
+	struct thermal_zone_device *tzdev;
+	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
+	enum thermal_device_mode mode;
+	int module; /* Module or gearbox number */
+};
+
 struct mlxsw_thermal {
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
 	struct thermal_zone_device *tzdev;
+	int polling_delay;
 	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
 	u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	enum thermal_device_mode mode;
+	struct mlxsw_thermal_module *tz_module_arr;
+	struct mlxsw_thermal_module *tz_gearbox_arr;
+	u8 tz_gearbox_num;
+	unsigned int tz_highest_score;
+	struct thermal_zone_device *tz_highest_dev;
 };
 
 static inline u8 mlxsw_state_to_duty(int state)
@@ -103,9 +139,95 @@ static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal,
 		if (thermal->cdevs[i] == cdev)
 			return i;
 
+	/* Allow mlxsw thermal zone binding to an external cooling device */
+	for (i = 0; i < ARRAY_SIZE(mlxsw_thermal_external_allowed_cdev); i++) {
+		if (strnstr(cdev->type, mlxsw_thermal_external_allowed_cdev[i],
+			    sizeof(cdev->type)))
+			return 0;
+	}
+
 	return -ENODEV;
 }
 
+static void
+mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz)
+{
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = 0;
+}
+
+static int
+mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
+				  struct mlxsw_thermal_module *tz)
+{
+	int crit_temp, emerg_temp;
+	int err;
+
+	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+						   SFP_TEMP_HIGH_WARN,
+						   &crit_temp);
+	if (err)
+		return err;
+
+	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+						   SFP_TEMP_HIGH_ALARM,
+						   &emerg_temp);
+	if (err)
+		return err;
+
+	/* According to the system thermal requirements, the thermal zones are
+	 * defined with four trip points. The critical and emergency
+	 * temperature thresholds, provided by QSFP module are set as "active"
+	 * and "hot" trip points, "normal" and "critical" trip points are
+	 * derived from "active" and "hot" by subtracting or adding double
+	 * hysteresis value.
+	 */
+	if (crit_temp >= MLXSW_THERMAL_MODULE_TEMP_SHIFT)
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp -
+					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
+	else
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp;
+	if (emerg_temp > crit_temp)
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp +
+					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
+	else
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp;
+
+	return 0;
+}
+
+static void mlxsw_thermal_tz_score_update(struct mlxsw_thermal *thermal,
+					  struct thermal_zone_device *tzdev,
+					  struct mlxsw_thermal_trip *trips,
+					  int temp)
+{
+	struct mlxsw_thermal_trip *trip = trips;
+	unsigned int score, delta, i, shift = 1;
+
+	/* Calculate thermal zone score, if temperature is above the critical
+	 * threshold score is set to MLXSW_THERMAL_TEMP_SCORE_MAX.
+	 */
+	score = MLXSW_THERMAL_TEMP_SCORE_MAX;
+	for (i = MLXSW_THERMAL_TEMP_TRIP_NORM; i < MLXSW_THERMAL_NUM_TRIPS;
+	     i++, trip++) {
+		if (temp < trip->temp) {
+			delta = DIV_ROUND_CLOSEST(temp, trip->temp - temp);
+			score = delta * shift;
+			break;
+		}
+		shift *= 256;
+	}
+
+	if (score > thermal->tz_highest_score) {
+		thermal->tz_highest_score = score;
+		thermal->tz_highest_dev = tzdev;
+	}
+}
+
 static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev,
 			      struct thermal_cooling_device *cdev)
 {
@@ -172,7 +294,7 @@ static int mlxsw_thermal_set_mode(struct thermal_zone_device *tzdev,
 	mutex_lock(&tzdev->lock);
 
 	if (mode == THERMAL_DEVICE_ENABLED)
-		tzdev->polling_delay = MLXSW_THERMAL_POLL_INT;
+		tzdev->polling_delay = thermal->polling_delay;
 	else
 		tzdev->polling_delay = 0;
 
@@ -190,7 +312,7 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 	struct mlxsw_thermal *thermal = tzdev->devdata;
 	struct device *dev = thermal->bus_info->dev;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp;
+	int temp;
 	int err;
 
 	mlxsw_reg_mtmp_pack(mtmp_pl, 0, false, false);
@@ -201,8 +323,11 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	if (temp > 0)
+		mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
+					      temp);
 
-	*p_temp = (int) temp;
+	*p_temp = temp;
 	return 0;
 }
 
@@ -237,13 +362,47 @@ static int mlxsw_thermal_set_trip_temp(struct thermal_zone_device *tzdev,
 	struct mlxsw_thermal *thermal = tzdev->devdata;
 
 	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS ||
-	    temp > MLXSW_THERMAL_MAX_TEMP)
+	    temp > MLXSW_THERMAL_ASIC_TEMP_CRIT)
 		return -EINVAL;
 
 	thermal->trips[trip].temp = temp;
 	return 0;
 }
 
+static int mlxsw_thermal_get_trip_hyst(struct thermal_zone_device *tzdev,
+				       int trip, int *p_hyst)
+{
+	struct mlxsw_thermal *thermal = tzdev->devdata;
+
+	*p_hyst = thermal->trips[trip].hyst;
+	return 0;
+}
+
+static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
+				       int trip, int hyst)
+{
+	struct mlxsw_thermal *thermal = tzdev->devdata;
+
+	thermal->trips[trip].hyst = hyst;
+	return 0;
+}
+
+static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
+				   int trip, enum thermal_trend *trend)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	if (tzdev == thermal->tz_highest_dev)
+		return 1;
+
+	*trend = THERMAL_TREND_STABLE;
+	return 0;
+}
+
 static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.bind = mlxsw_thermal_bind,
 	.unbind = mlxsw_thermal_unbind,
@@ -253,6 +412,237 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.get_trip_type	= mlxsw_thermal_get_trip_type,
 	.get_trip_temp	= mlxsw_thermal_get_trip_temp,
 	.set_trip_temp	= mlxsw_thermal_set_trip_temp,
+	.get_trip_hyst	= mlxsw_thermal_get_trip_hyst,
+	.set_trip_hyst	= mlxsw_thermal_set_trip_hyst,
+	.get_trend	= mlxsw_thermal_trend_get,
+};
+
+static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev,
+				     struct thermal_cooling_device *cdev)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	int i, j, err;
+
+	/* If the cooling device is one of ours bind it */
+	if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0)
+		return 0;
+
+	for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) {
+		const struct mlxsw_thermal_trip *trip = &tz->trips[i];
+
+		err = thermal_zone_bind_cooling_device(tzdev, i, cdev,
+						       trip->max_state,
+						       trip->min_state,
+						       THERMAL_WEIGHT_DEFAULT);
+		if (err < 0)
+			goto err_bind_cooling_device;
+	}
+	return 0;
+
+err_bind_cooling_device:
+	for (j = i - 1; j >= 0; j--)
+		thermal_zone_unbind_cooling_device(tzdev, j, cdev);
+	return err;
+}
+
+static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev,
+				       struct thermal_cooling_device *cdev)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	int i;
+	int err;
+
+	/* If the cooling device is one of ours unbind it */
+	if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0)
+		return 0;
+
+	for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) {
+		err = thermal_zone_unbind_cooling_device(tzdev, i, cdev);
+		WARN_ON(err);
+	}
+	return err;
+}
+
+static int mlxsw_thermal_module_mode_get(struct thermal_zone_device *tzdev,
+					 enum thermal_device_mode *mode)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	*mode = tz->mode;
+
+	return 0;
+}
+
+static int mlxsw_thermal_module_mode_set(struct thermal_zone_device *tzdev,
+					 enum thermal_device_mode mode)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+
+	mutex_lock(&tzdev->lock);
+
+	if (mode == THERMAL_DEVICE_ENABLED)
+		tzdev->polling_delay = thermal->polling_delay;
+	else
+		tzdev->polling_delay = 0;
+
+	mutex_unlock(&tzdev->lock);
+
+	tz->mode = mode;
+	thermal_zone_device_update(tzdev, THERMAL_EVENT_UNSPECIFIED);
+
+	return 0;
+}
+
+static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
+					 int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	struct device *dev = thermal->bus_info->dev;
+	char mtmp_pl[MLXSW_REG_MTMP_LEN];
+	int temp;
+	int err;
+
+	/* Read module temperature. */
+	mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN +
+			    tz->module, false, false);
+	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtmp), mtmp_pl);
+	if (err) {
+		/* Do not return error - in case of broken module's sensor
+		 * it will cause error message flooding.
+		 */
+		temp = 0;
+		*p_temp = (int) temp;
+		return 0;
+	}
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	*p_temp = temp;
+
+	if (!temp)
+		return 0;
+
+	/* Update trip points. */
+	err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
+	if (!err && temp > 0)
+		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
+
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_type_get(struct thermal_zone_device *tzdev, int trip,
+				   enum thermal_trip_type *p_type)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	*p_type = tz->trips[trip].type;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_temp_get(struct thermal_zone_device *tzdev,
+				   int trip, int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	*p_temp = tz->trips[trip].temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_temp_set(struct thermal_zone_device *tzdev,
+				   int trip, int temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS ||
+	    temp > tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp)
+		return -EINVAL;
+
+	tz->trips[trip].temp = temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_hyst_get(struct thermal_zone_device *tzdev, int trip,
+				   int *p_hyst)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	*p_hyst = tz->trips[trip].hyst;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
+				   int hyst)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	tz->trips[trip].hyst = hyst;
+	return 0;
+}
+
+static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
+	.bind		= mlxsw_thermal_module_bind,
+	.unbind		= mlxsw_thermal_module_unbind,
+	.get_mode	= mlxsw_thermal_module_mode_get,
+	.set_mode	= mlxsw_thermal_module_mode_set,
+	.get_temp	= mlxsw_thermal_module_temp_get,
+	.get_trip_type	= mlxsw_thermal_module_trip_type_get,
+	.get_trip_temp	= mlxsw_thermal_module_trip_temp_get,
+	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
+	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
+	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
+	.get_trend	= mlxsw_thermal_trend_get,
+};
+
+static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
+					  int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	char mtmp_pl[MLXSW_REG_MTMP_LEN];
+	u16 index;
+	int temp;
+	int err;
+
+	index = MLXSW_REG_MTMP_GBOX_INDEX_MIN + tz->module;
+	mlxsw_reg_mtmp_pack(mtmp_pl, index, false, false);
+
+	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtmp), mtmp_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	if (temp > 0)
+		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
+
+	*p_temp = temp;
+	return 0;
+}
+
+static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
+	.bind		= mlxsw_thermal_module_bind,
+	.unbind		= mlxsw_thermal_module_unbind,
+	.get_mode	= mlxsw_thermal_module_mode_get,
+	.set_mode	= mlxsw_thermal_module_mode_set,
+	.get_temp	= mlxsw_thermal_gearbox_temp_get,
+	.get_trip_type	= mlxsw_thermal_module_trip_type_get,
+	.get_trip_temp	= mlxsw_thermal_module_trip_temp_get,
+	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
+	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
+	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
+	.get_trend	= mlxsw_thermal_trend_get,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
@@ -355,6 +745,217 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = {
 	.set_cur_state	= mlxsw_thermal_set_cur_state,
 };
 
+static int
+mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
+{
+	char tz_name[MLXSW_THERMAL_ZONE_MAX_NAME];
+	int err;
+
+	snprintf(tz_name, sizeof(tz_name), "mlxsw-module%d",
+		 module_tz->module + 1);
+	module_tz->tzdev = thermal_zone_device_register(tz_name,
+							MLXSW_THERMAL_NUM_TRIPS,
+							MLXSW_THERMAL_TRIP_MASK,
+							module_tz,
+							&mlxsw_thermal_module_ops,
+							NULL, 0, 0);
+	if (IS_ERR(module_tz->tzdev)) {
+		err = PTR_ERR(module_tz->tzdev);
+		return err;
+	}
+
+	module_tz->mode = THERMAL_DEVICE_ENABLED;
+	return 0;
+}
+
+static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev)
+{
+	thermal_zone_device_unregister(tzdev);
+}
+
+static int
+mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
+			  struct mlxsw_thermal *thermal, u8 local_port)
+{
+	struct mlxsw_thermal_module *module_tz;
+	char pmlp_pl[MLXSW_REG_PMLP_LEN];
+	u8 width, module;
+	int err;
+
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+	err = mlxsw_reg_query(core, MLXSW_REG(pmlp), pmlp_pl);
+	if (err)
+		return err;
+
+	width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+	if (!width)
+		return 0;
+
+	module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+	module_tz = &thermal->tz_module_arr[module];
+	/* Skip if parent is already set (case of port split). */
+	if (module_tz->parent)
+		return 0;
+	module_tz->module = module;
+	module_tz->parent = thermal;
+	memcpy(module_tz->trips, default_thermal_trips,
+	       sizeof(thermal->trips));
+	/* Initialize all trip point. */
+	mlxsw_thermal_module_trips_reset(module_tz);
+	/* Update trip point according to the module data. */
+	return mlxsw_thermal_module_trips_update(dev, core, module_tz);
+}
+
+static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)
+{
+	if (module_tz && module_tz->tzdev) {
+		mlxsw_thermal_module_tz_fini(module_tz->tzdev);
+		module_tz->tzdev = NULL;
+		module_tz->parent = NULL;
+	}
+}
+
+static int
+mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
+			   struct mlxsw_thermal *thermal)
+{
+	unsigned int module_count = mlxsw_core_max_ports(core);
+	struct mlxsw_thermal_module *module_tz;
+	int i, err;
+
+	if (!mlxsw_core_res_query_enabled(core))
+		return 0;
+
+	thermal->tz_module_arr = kcalloc(module_count,
+					 sizeof(*thermal->tz_module_arr),
+					 GFP_KERNEL);
+	if (!thermal->tz_module_arr)
+		return -ENOMEM;
+
+	for (i = 1; i < module_count; i++) {
+		err = mlxsw_thermal_module_init(dev, core, thermal, i);
+		if (err)
+			goto err_unreg_tz_module_arr;
+	}
+
+	for (i = 0; i < module_count - 1; i++) {
+		module_tz = &thermal->tz_module_arr[i];
+		if (!module_tz->parent)
+			continue;
+		err = mlxsw_thermal_module_tz_init(module_tz);
+		if (err)
+			goto err_unreg_tz_module_arr;
+	}
+
+	return 0;
+
+err_unreg_tz_module_arr:
+	for (i = module_count - 1; i >= 0; i--)
+		mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]);
+	kfree(thermal->tz_module_arr);
+	return err;
+}
+
+static void
+mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal)
+{
+	unsigned int module_count = mlxsw_core_max_ports(thermal->core);
+	int i;
+
+	if (!mlxsw_core_res_query_enabled(thermal->core))
+		return;
+
+	for (i = module_count - 1; i >= 0; i--)
+		mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]);
+	kfree(thermal->tz_module_arr);
+}
+
+static int
+mlxsw_thermal_gearbox_tz_init(struct mlxsw_thermal_module *gearbox_tz)
+{
+	char tz_name[MLXSW_THERMAL_ZONE_MAX_NAME];
+
+	snprintf(tz_name, sizeof(tz_name), "mlxsw-gearbox%d",
+		 gearbox_tz->module + 1);
+	gearbox_tz->tzdev = thermal_zone_device_register(tz_name,
+						MLXSW_THERMAL_NUM_TRIPS,
+						MLXSW_THERMAL_TRIP_MASK,
+						gearbox_tz,
+						&mlxsw_thermal_gearbox_ops,
+						NULL, 0, 0);
+	if (IS_ERR(gearbox_tz->tzdev))
+		return PTR_ERR(gearbox_tz->tzdev);
+
+	gearbox_tz->mode = THERMAL_DEVICE_ENABLED;
+	return 0;
+}
+
+static void
+mlxsw_thermal_gearbox_tz_fini(struct mlxsw_thermal_module *gearbox_tz)
+{
+	thermal_zone_device_unregister(gearbox_tz->tzdev);
+}
+
+static int
+mlxsw_thermal_gearboxes_init(struct device *dev, struct mlxsw_core *core,
+			     struct mlxsw_thermal *thermal)
+{
+	struct mlxsw_thermal_module *gearbox_tz;
+	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
+	int i;
+	int err;
+
+	if (!mlxsw_core_res_query_enabled(core))
+		return 0;
+
+	mlxsw_reg_mgpir_pack(mgpir_pl);
+	err = mlxsw_reg_query(core, MLXSW_REG(mgpir), mgpir_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mgpir_unpack(mgpir_pl, &thermal->tz_gearbox_num, NULL, NULL);
+	if (!thermal->tz_gearbox_num)
+		return 0;
+
+	thermal->tz_gearbox_arr = kcalloc(thermal->tz_gearbox_num,
+					  sizeof(*thermal->tz_gearbox_arr),
+					  GFP_KERNEL);
+	if (!thermal->tz_gearbox_arr)
+		return -ENOMEM;
+
+	for (i = 0; i < thermal->tz_gearbox_num; i++) {
+		gearbox_tz = &thermal->tz_gearbox_arr[i];
+		memcpy(gearbox_tz->trips, default_thermal_trips,
+		       sizeof(thermal->trips));
+		gearbox_tz->module = i;
+		gearbox_tz->parent = thermal;
+		err = mlxsw_thermal_gearbox_tz_init(gearbox_tz);
+		if (err)
+			goto err_unreg_tz_gearbox;
+	}
+
+	return 0;
+
+err_unreg_tz_gearbox:
+	for (i--; i >= 0; i--)
+		mlxsw_thermal_gearbox_tz_fini(&thermal->tz_gearbox_arr[i]);
+	kfree(thermal->tz_gearbox_arr);
+	return err;
+}
+
+static void
+mlxsw_thermal_gearboxes_fini(struct mlxsw_thermal *thermal)
+{
+	int i;
+
+	if (!mlxsw_core_res_query_enabled(thermal->core))
+		return;
+
+	for (i = thermal->tz_gearbox_num - 1; i >= 0; i--)
+		mlxsw_thermal_gearbox_tz_fini(&thermal->tz_gearbox_arr[i]);
+	kfree(thermal->tz_gearbox_arr);
+}
+
 int mlxsw_thermal_init(struct mlxsw_core *core,
 		       const struct mlxsw_bus_info *bus_info,
 		       struct mlxsw_thermal **p_thermal)
@@ -407,8 +1008,9 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 		if (pwm_active & BIT(i)) {
 			struct thermal_cooling_device *cdev;
 
-			cdev = thermal_cooling_device_register("Fan", thermal,
-							&mlxsw_cooling_ops);
+			cdev = thermal_cooling_device_register("mlxsw_fan",
+							       thermal,
+							       &mlxsw_cooling_ops);
 			if (IS_ERR(cdev)) {
 				err = PTR_ERR(cdev);
 				dev_err(dev, "Failed to register cooling device\n");
@@ -423,22 +1025,42 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 		thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL,
 						 i);
 
+	thermal->polling_delay = bus_info->low_frequency ?
+				 MLXSW_THERMAL_SLOW_POLL_INT :
+				 MLXSW_THERMAL_POLL_INT;
+
 	thermal->tzdev = thermal_zone_device_register("mlxsw",
 						      MLXSW_THERMAL_NUM_TRIPS,
 						      MLXSW_THERMAL_TRIP_MASK,
 						      thermal,
 						      &mlxsw_thermal_ops,
 						      NULL, 0,
-						      MLXSW_THERMAL_POLL_INT);
+						      thermal->polling_delay);
 	if (IS_ERR(thermal->tzdev)) {
 		err = PTR_ERR(thermal->tzdev);
 		dev_err(dev, "Failed to register thermal zone\n");
 		goto err_unreg_cdevs;
 	}
 
+	err = mlxsw_thermal_modules_init(dev, core, thermal);
+	if (err)
+		goto err_unreg_tzdev;
+
+	err = mlxsw_thermal_gearboxes_init(dev, core, thermal);
+	if (err)
+		goto err_unreg_modules_tzdev;
+
 	thermal->mode = THERMAL_DEVICE_ENABLED;
 	*p_thermal = thermal;
 	return 0;
+
+err_unreg_modules_tzdev:
+	mlxsw_thermal_modules_fini(thermal);
+err_unreg_tzdev:
+	if (thermal->tzdev) {
+		thermal_zone_device_unregister(thermal->tzdev);
+		thermal->tzdev = NULL;
+	}
 err_unreg_cdevs:
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
 		if (thermal->cdevs[i])
@@ -452,6 +1074,8 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 {
 	int i;
 
+	mlxsw_thermal_gearboxes_fini(thermal);
+	mlxsw_thermal_modules_fini(thermal);
 	if (thermal->tzdev) {
 		thermal_zone_device_unregister(thermal->tzdev);
 		thermal->tzdev = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 798bd5aca384..95f408d0e103 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -14,14 +14,17 @@
 #include "cmd.h"
 #include "core.h"
 #include "i2c.h"
+#include "resources.h"
 
 #define MLXSW_I2C_CIR2_BASE		0x72000
 #define MLXSW_I2C_CIR_STATUS_OFF	0x18
 #define MLXSW_I2C_CIR2_OFF_STATUS	(MLXSW_I2C_CIR2_BASE + \
 					 MLXSW_I2C_CIR_STATUS_OFF)
 #define MLXSW_I2C_OPMOD_SHIFT		12
+#define MLXSW_I2C_EVENT_BIT_SHIFT	22
 #define MLXSW_I2C_GO_BIT_SHIFT		23
 #define MLXSW_I2C_CIR_CTRL_STATUS_SHIFT	24
+#define MLXSW_I2C_EVENT_BIT		BIT(MLXSW_I2C_EVENT_BIT_SHIFT)
 #define MLXSW_I2C_GO_BIT		BIT(MLXSW_I2C_GO_BIT_SHIFT)
 #define MLXSW_I2C_GO_OPMODE		BIT(MLXSW_I2C_OPMOD_SHIFT)
 #define MLXSW_I2C_SET_IMM_CMD		(MLXSW_I2C_GO_OPMODE | \
@@ -33,17 +36,20 @@
 #define MLXSW_I2C_TLV_HDR_SIZE		0x10
 #define MLXSW_I2C_ADDR_WIDTH		4
 #define MLXSW_I2C_PUSH_CMD_SIZE		(MLXSW_I2C_ADDR_WIDTH + 4)
+#define MLXSW_I2C_SET_EVENT_CMD		(MLXSW_I2C_EVENT_BIT)
+#define MLXSW_I2C_PUSH_EVENT_CMD	(MLXSW_I2C_GO_BIT | \
+					 MLXSW_I2C_SET_EVENT_CMD)
 #define MLXSW_I2C_READ_SEMA_SIZE	4
 #define MLXSW_I2C_PREP_SIZE		(MLXSW_I2C_ADDR_WIDTH + 28)
 #define MLXSW_I2C_MBOX_SIZE		20
 #define MLXSW_I2C_MBOX_OUT_PARAM_OFF	12
-#define MLXSW_I2C_MAX_BUFF_SIZE		32
 #define MLXSW_I2C_MBOX_OFFSET_BITS	20
 #define MLXSW_I2C_MBOX_SIZE_BITS	12
 #define MLXSW_I2C_ADDR_BUF_SIZE		4
-#define MLXSW_I2C_BLK_MAX		32
+#define MLXSW_I2C_BLK_DEF		32
 #define MLXSW_I2C_RETRY			5
 #define MLXSW_I2C_TIMEOUT_MSECS		5000
+#define MLXSW_I2C_MAX_DATA_SIZE		256
 
 /**
  * struct mlxsw_i2c - device private data:
@@ -55,6 +61,7 @@
  * @dev: I2C device;
  * @core: switch core pointer;
  * @bus_info: bus info block;
+ * @block_size: maximum block size allowed to pass to under layer;
  */
 struct mlxsw_i2c {
 	struct {
@@ -67,6 +74,7 @@ struct mlxsw_i2c {
 	struct device *dev;
 	struct mlxsw_core *core;
 	struct mlxsw_bus_info bus_info;
+	u16 block_size;
 };
 
 #define MLXSW_I2C_READ_MSG(_client, _addr_buf, _buf, _len) {	\
@@ -167,7 +175,7 @@ static int mlxsw_i2c_wait_go_bit(struct i2c_client *client,
 	return err > 0 ? 0 : err;
 }
 
-/* Routine posts a command to ASIC though mail box. */
+/* Routine posts a command to ASIC through mail box. */
 static int mlxsw_i2c_write_cmd(struct i2c_client *client,
 			       struct mlxsw_i2c *mlxsw_i2c,
 			       int immediate)
@@ -213,6 +221,66 @@ static int mlxsw_i2c_write_cmd(struct i2c_client *client,
 	return 0;
 }
 
+/* Routine posts initialization command to ASIC through mail box. */
+static int
+mlxsw_i2c_write_init_cmd(struct i2c_client *client,
+			 struct mlxsw_i2c *mlxsw_i2c, u16 opcode, u32 in_mod)
+{
+	__be32 push_cmd_buf[MLXSW_I2C_PUSH_CMD_SIZE / 4] = {
+		0, cpu_to_be32(MLXSW_I2C_PUSH_EVENT_CMD)
+	};
+	__be32 prep_cmd_buf[MLXSW_I2C_PREP_SIZE / 4] = {
+		0, 0, 0, 0, 0, 0,
+		cpu_to_be32(client->adapter->nr & 0xffff),
+		cpu_to_be32(MLXSW_I2C_SET_EVENT_CMD)
+	};
+	struct i2c_msg push_cmd =
+		MLXSW_I2C_WRITE_MSG(client, push_cmd_buf,
+				    MLXSW_I2C_PUSH_CMD_SIZE);
+	struct i2c_msg prep_cmd =
+		MLXSW_I2C_WRITE_MSG(client, prep_cmd_buf, MLXSW_I2C_PREP_SIZE);
+	u8 status;
+	int err;
+
+	push_cmd_buf[1] = cpu_to_be32(MLXSW_I2C_PUSH_EVENT_CMD | opcode);
+	prep_cmd_buf[3] = cpu_to_be32(in_mod);
+	prep_cmd_buf[7] = cpu_to_be32(MLXSW_I2C_GO_BIT | opcode);
+	mlxsw_i2c_set_slave_addr((u8 *)prep_cmd_buf,
+				 MLXSW_I2C_CIR2_BASE);
+	mlxsw_i2c_set_slave_addr((u8 *)push_cmd_buf,
+				 MLXSW_I2C_CIR2_OFF_STATUS);
+
+	/* Prepare Command Interface Register for transaction */
+	err = i2c_transfer(client->adapter, &prep_cmd, 1);
+	if (err < 0)
+		return err;
+	else if (err != 1)
+		return -EIO;
+
+	/* Write out Command Interface Register GO bit to push transaction */
+	err = i2c_transfer(client->adapter, &push_cmd, 1);
+	if (err < 0)
+		return err;
+	else if (err != 1)
+		return -EIO;
+
+	/* Wait until go bit is cleared. */
+	err = mlxsw_i2c_wait_go_bit(client, mlxsw_i2c, &status);
+	if (err) {
+		dev_err(&client->dev, "HW semaphore is not released");
+		return err;
+	}
+
+	/* Validate transaction completion status. */
+	if (status) {
+		dev_err(&client->dev, "Bad transaction completion status %x\n",
+			status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 /* Routine obtains mail box offsets from ASIC register space. */
 static int mlxsw_i2c_get_mbox(struct i2c_client *client,
 			      struct mlxsw_i2c *mlxsw_i2c)
@@ -248,20 +316,26 @@ mlxsw_i2c_write(struct device *dev, size_t in_mbox_size, u8 *in_mbox, int num,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct mlxsw_i2c *mlxsw_i2c = i2c_get_clientdata(client);
 	unsigned long timeout = msecs_to_jiffies(MLXSW_I2C_TIMEOUT_MSECS);
-	u8 tran_buf[MLXSW_I2C_MAX_BUFF_SIZE + MLXSW_I2C_ADDR_BUF_SIZE];
 	int off = mlxsw_i2c->cmd.mb_off_in, chunk_size, i, j;
 	unsigned long end;
+	u8 *tran_buf;
 	struct i2c_msg write_tran =
-		MLXSW_I2C_WRITE_MSG(client, tran_buf, MLXSW_I2C_PUSH_CMD_SIZE);
+		MLXSW_I2C_WRITE_MSG(client, NULL, MLXSW_I2C_PUSH_CMD_SIZE);
 	int err;
 
+	tran_buf = kmalloc(mlxsw_i2c->block_size + MLXSW_I2C_ADDR_BUF_SIZE,
+			   GFP_KERNEL);
+	if (!tran_buf)
+		return -ENOMEM;
+
+	write_tran.buf = tran_buf;
 	for (i = 0; i < num; i++) {
-		chunk_size = (in_mbox_size > MLXSW_I2C_BLK_MAX) ?
-			     MLXSW_I2C_BLK_MAX : in_mbox_size;
+		chunk_size = (in_mbox_size > mlxsw_i2c->block_size) ?
+			     mlxsw_i2c->block_size : in_mbox_size;
 		write_tran.len = MLXSW_I2C_ADDR_WIDTH + chunk_size;
 		mlxsw_i2c_set_slave_addr(tran_buf, off);
 		memcpy(&tran_buf[MLXSW_I2C_ADDR_BUF_SIZE], in_mbox +
-		       MLXSW_I2C_BLK_MAX * i, chunk_size);
+		       mlxsw_i2c->block_size * i, chunk_size);
 
 		j = 0;
 		end = jiffies + timeout;
@@ -275,9 +349,10 @@ mlxsw_i2c_write(struct device *dev, size_t in_mbox_size, u8 *in_mbox, int num,
 			 (j++ < MLXSW_I2C_RETRY));
 
 		if (err != 1) {
-			if (!err)
+			if (!err) {
 				err = -EIO;
-			return err;
+				goto mlxsw_i2c_write_exit;
+			}
 		}
 
 		off += chunk_size;
@@ -288,30 +363,33 @@ mlxsw_i2c_write(struct device *dev, size_t in_mbox_size, u8 *in_mbox, int num,
 	err = mlxsw_i2c_write_cmd(client, mlxsw_i2c, 0);
 	if (err) {
 		dev_err(&client->dev, "Could not start transaction");
-		return -EIO;
+		err = -EIO;
+		goto mlxsw_i2c_write_exit;
 	}
 
 	/* Wait until go bit is cleared. */
 	err = mlxsw_i2c_wait_go_bit(client, mlxsw_i2c, p_status);
 	if (err) {
 		dev_err(&client->dev, "HW semaphore is not released");
-		return err;
+		goto mlxsw_i2c_write_exit;
 	}
 
 	/* Validate transaction completion status. */
 	if (*p_status) {
 		dev_err(&client->dev, "Bad transaction completion status %x\n",
 			*p_status);
-		return -EIO;
+		err = -EIO;
 	}
 
-	return 0;
+mlxsw_i2c_write_exit:
+	kfree(tran_buf);
+	return err;
 }
 
 /* Routine executes I2C command. */
 static int
-mlxsw_i2c_cmd(struct device *dev, size_t in_mbox_size, u8 *in_mbox,
-	      size_t out_mbox_size, u8 *out_mbox, u8 *status)
+mlxsw_i2c_cmd(struct device *dev, u16 opcode, u32 in_mod, size_t in_mbox_size,
+	      u8 *in_mbox, size_t out_mbox_size, u8 *out_mbox, u8 *status)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct mlxsw_i2c *mlxsw_i2c = i2c_get_clientdata(client);
@@ -326,31 +404,47 @@ mlxsw_i2c_cmd(struct device *dev, size_t in_mbox_size, u8 *in_mbox,
 
 	WARN_ON(in_mbox_size % sizeof(u32) || out_mbox_size % sizeof(u32));
 
-	reg_size = mlxsw_i2c_get_reg_size(in_mbox);
-	num = reg_size / MLXSW_I2C_BLK_MAX;
-	if (reg_size % MLXSW_I2C_BLK_MAX)
-		num++;
+	if (in_mbox) {
+		reg_size = mlxsw_i2c_get_reg_size(in_mbox);
+		num = reg_size / mlxsw_i2c->block_size;
+		if (reg_size % mlxsw_i2c->block_size)
+			num++;
 
-	if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
-		dev_err(&client->dev, "Could not acquire lock");
-		return -EINVAL;
-	}
+		if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
+			dev_err(&client->dev, "Could not acquire lock");
+			return -EINVAL;
+		}
 
-	err = mlxsw_i2c_write(dev, reg_size, in_mbox, num, status);
-	if (err)
-		goto cmd_fail;
+		err = mlxsw_i2c_write(dev, reg_size, in_mbox, num, status);
+		if (err)
+			goto cmd_fail;
+
+		/* No out mailbox is case of write transaction. */
+		if (!out_mbox) {
+			mutex_unlock(&mlxsw_i2c->cmd.lock);
+			return 0;
+		}
+	} else {
+		/* No input mailbox is case of initialization query command. */
+		reg_size = MLXSW_I2C_MAX_DATA_SIZE;
+		num = reg_size / mlxsw_i2c->block_size;
 
-	/* No out mailbox is case of write transaction. */
-	if (!out_mbox) {
-		mutex_unlock(&mlxsw_i2c->cmd.lock);
-		return 0;
+		if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
+			dev_err(&client->dev, "Could not acquire lock");
+			return -EINVAL;
+		}
+
+		err = mlxsw_i2c_write_init_cmd(client, mlxsw_i2c, opcode,
+					       in_mod);
+		if (err)
+			goto cmd_fail;
 	}
 
 	/* Send read transaction to get output mailbox content. */
 	read_tran[1].buf = out_mbox;
 	for (i = 0; i < num; i++) {
-		chunk_size = (reg_size > MLXSW_I2C_BLK_MAX) ?
-			     MLXSW_I2C_BLK_MAX : reg_size;
+		chunk_size = (reg_size > mlxsw_i2c->block_size) ?
+			     mlxsw_i2c->block_size : reg_size;
 		read_tran[1].len = chunk_size;
 		mlxsw_i2c_set_slave_addr(tran_buf, off);
 
@@ -395,8 +489,8 @@ static int mlxsw_i2c_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
 {
 	struct mlxsw_i2c *mlxsw_i2c = bus_priv;
 
-	return mlxsw_i2c_cmd(mlxsw_i2c->dev, in_mbox_size, in_mbox,
-			     out_mbox_size, out_mbox, status);
+	return mlxsw_i2c_cmd(mlxsw_i2c->dev, opcode, in_mod, in_mbox_size,
+			     in_mbox, out_mbox_size, out_mbox, status);
 }
 
 static bool mlxsw_i2c_skb_transmit_busy(void *bus_priv,
@@ -414,13 +508,34 @@ static int mlxsw_i2c_skb_transmit(void *bus_priv, struct sk_buff *skb,
 static int
 mlxsw_i2c_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	       const struct mlxsw_config_profile *profile,
-	       struct mlxsw_res *resources)
+	       struct mlxsw_res *res)
 {
 	struct mlxsw_i2c *mlxsw_i2c = bus_priv;
+	char *mbox;
+	int err;
 
 	mlxsw_i2c->core = mlxsw_core;
 
-	return 0;
+	mbox = mlxsw_cmd_mbox_alloc();
+	if (!mbox)
+		return -ENOMEM;
+
+	err = mlxsw_cmd_query_fw(mlxsw_core, mbox);
+	if (err)
+		goto mbox_put;
+
+	mlxsw_i2c->bus_info.fw_rev.major =
+		mlxsw_cmd_mbox_query_fw_fw_rev_major_get(mbox);
+	mlxsw_i2c->bus_info.fw_rev.minor =
+		mlxsw_cmd_mbox_query_fw_fw_rev_minor_get(mbox);
+	mlxsw_i2c->bus_info.fw_rev.subminor =
+		mlxsw_cmd_mbox_query_fw_fw_rev_subminor_get(mbox);
+
+	err = mlxsw_core_resources_query(mlxsw_core, mbox, res);
+
+mbox_put:
+	mlxsw_cmd_mbox_free(mbox);
+	return err;
 }
 
 static void mlxsw_i2c_fini(void *bus_priv)
@@ -442,6 +557,7 @@ static const struct mlxsw_bus mlxsw_i2c_bus = {
 static int mlxsw_i2c_probe(struct i2c_client *client,
 			   const struct i2c_device_id *id)
 {
+	const struct i2c_adapter_quirks *quirks = client->adapter->quirks;
 	struct mlxsw_i2c *mlxsw_i2c;
 	u8 status;
 	int err;
@@ -450,6 +566,22 @@ static int mlxsw_i2c_probe(struct i2c_client *client,
 	if (!mlxsw_i2c)
 		return -ENOMEM;
 
+	if (quirks) {
+		if ((quirks->max_read_len &&
+		     quirks->max_read_len < MLXSW_I2C_BLK_DEF) ||
+		    (quirks->max_write_len &&
+		     quirks->max_write_len < MLXSW_I2C_BLK_DEF)) {
+			dev_err(&client->dev, "Insufficient transaction buffer length\n");
+			return -EOPNOTSUPP;
+		}
+
+		mlxsw_i2c->block_size = max_t(u16, MLXSW_I2C_BLK_DEF,
+					      min_t(u16, quirks->max_read_len,
+						    quirks->max_write_len));
+	} else {
+		mlxsw_i2c->block_size = MLXSW_I2C_BLK_DEF;
+	}
+
 	i2c_set_clientdata(client, mlxsw_i2c);
 	mutex_init(&mlxsw_i2c->cmd.lock);
 
@@ -503,6 +635,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client,
 	mlxsw_i2c->bus_info.device_kind = id->name;
 	mlxsw_i2c->bus_info.device_name = client->name;
 	mlxsw_i2c->bus_info.dev = &client->dev;
+	mlxsw_i2c->bus_info.low_frequency = true;
 	mlxsw_i2c->dev = &client->dev;
 
 	err = mlxsw_core_bus_device_register(&mlxsw_i2c->bus_info,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index 5a6c4457fb55..471b0ca6d69a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
-/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
+/* Copyright (c) 2016-2019 Mellanox Technologies. All rights reserved */
 
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -8,59 +11,403 @@
 #include <linux/types.h>
 
 #include "core.h"
+#include "core_env.h"
 #include "i2c.h"
 
-static const char mlxsw_minimal_driver_name[] = "mlxsw_minimal";
+static const char mlxsw_m_driver_name[] = "mlxsw_minimal";
 
-static const struct mlxsw_config_profile mlxsw_minimal_config_profile;
+struct mlxsw_m_port;
 
-static struct mlxsw_driver mlxsw_minimal_driver = {
-	.kind		= mlxsw_minimal_driver_name,
-	.priv_size	= 1,
-	.profile	= &mlxsw_minimal_config_profile,
+struct mlxsw_m {
+	struct mlxsw_m_port **ports;
+	int *module_to_port;
+	struct mlxsw_core *core;
+	const struct mlxsw_bus_info *bus_info;
+	u8 base_mac[ETH_ALEN];
+	u8 max_ports;
 };
 
-static const struct i2c_device_id mlxsw_minimal_i2c_id[] = {
+struct mlxsw_m_port {
+	struct net_device *dev;
+	struct mlxsw_m *mlxsw_m;
+	u8 local_port;
+	u8 module;
+};
+
+static int mlxsw_m_base_mac_get(struct mlxsw_m *mlxsw_m)
+{
+	char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
+	int err;
+
+	err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(spad), spad_pl);
+	if (err)
+		return err;
+	mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_m->base_mac);
+	return 0;
+}
+
+static int mlxsw_m_port_dummy_open_stop(struct net_device *dev)
+{
+	return 0;
+}
+
+static struct devlink_port *
+mlxsw_m_port_get_devlink_port(struct net_device *dev)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev);
+	struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m;
+
+	return mlxsw_core_port_devlink_port_get(mlxsw_m->core,
+						mlxsw_m_port->local_port);
+}
+
+static const struct net_device_ops mlxsw_m_port_netdev_ops = {
+	.ndo_open		= mlxsw_m_port_dummy_open_stop,
+	.ndo_stop		= mlxsw_m_port_dummy_open_stop,
+	.ndo_get_devlink_port	= mlxsw_m_port_get_devlink_port,
+};
+
+static void mlxsw_m_module_get_drvinfo(struct net_device *dev,
+				       struct ethtool_drvinfo *drvinfo)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev);
+	struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m;
+
+	strlcpy(drvinfo->driver, mlxsw_m->bus_info->device_kind,
+		sizeof(drvinfo->driver));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "%d.%d.%d",
+		 mlxsw_m->bus_info->fw_rev.major,
+		 mlxsw_m->bus_info->fw_rev.minor,
+		 mlxsw_m->bus_info->fw_rev.subminor);
+	strlcpy(drvinfo->bus_info, mlxsw_m->bus_info->device_name,
+		sizeof(drvinfo->bus_info));
+}
+
+static int mlxsw_m_get_module_info(struct net_device *netdev,
+				   struct ethtool_modinfo *modinfo)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+
+	return mlxsw_env_get_module_info(core, mlxsw_m_port->module, modinfo);
+}
+
+static int
+mlxsw_m_get_module_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee,
+			  u8 *data)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+
+	return mlxsw_env_get_module_eeprom(netdev, core, mlxsw_m_port->module,
+					   ee, data);
+}
+
+static const struct ethtool_ops mlxsw_m_port_ethtool_ops = {
+	.get_drvinfo		= mlxsw_m_module_get_drvinfo,
+	.get_module_info	= mlxsw_m_get_module_info,
+	.get_module_eeprom	= mlxsw_m_get_module_eeprom,
+};
+
+static int
+mlxsw_m_port_module_info_get(struct mlxsw_m *mlxsw_m, u8 local_port,
+			     u8 *p_module, u8 *p_width)
+{
+	char pmlp_pl[MLXSW_REG_PMLP_LEN];
+	int err;
+
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+	err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(pmlp), pmlp_pl);
+	if (err)
+		return err;
+	*p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+	*p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+
+	return 0;
+}
+
+static int
+mlxsw_m_port_dev_addr_get(struct mlxsw_m_port *mlxsw_m_port)
+{
+	struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m;
+	struct net_device *dev = mlxsw_m_port->dev;
+	char ppad_pl[MLXSW_REG_PPAD_LEN];
+	int err;
+
+	mlxsw_reg_ppad_pack(ppad_pl, false, 0);
+	err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(ppad), ppad_pl);
+	if (err)
+		return err;
+	mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, dev->dev_addr);
+	/* The last byte value in base mac address is guaranteed
+	 * to be such it does not overflow when adding local_port
+	 * value.
+	 */
+	dev->dev_addr[ETH_ALEN - 1] += mlxsw_m_port->module + 1;
+	return 0;
+}
+
+static int
+mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module)
+{
+	struct mlxsw_m_port *mlxsw_m_port;
+	struct net_device *dev;
+	int err;
+
+	err = mlxsw_core_port_init(mlxsw_m->core, local_port,
+				   module + 1, false, 0,
+				   mlxsw_m->base_mac,
+				   sizeof(mlxsw_m->base_mac));
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Port %d: Failed to init core port\n",
+			local_port);
+		return err;
+	}
+
+	dev = alloc_etherdev(sizeof(struct mlxsw_m_port));
+	if (!dev) {
+		err = -ENOMEM;
+		goto err_alloc_etherdev;
+	}
+
+	SET_NETDEV_DEV(dev, mlxsw_m->bus_info->dev);
+	mlxsw_m_port = netdev_priv(dev);
+	mlxsw_m_port->dev = dev;
+	mlxsw_m_port->mlxsw_m = mlxsw_m;
+	mlxsw_m_port->local_port = local_port;
+	mlxsw_m_port->module = module;
+
+	dev->netdev_ops = &mlxsw_m_port_netdev_ops;
+	dev->ethtool_ops = &mlxsw_m_port_ethtool_ops;
+
+	err = mlxsw_m_port_dev_addr_get(mlxsw_m_port);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Port %d: Unable to get port mac address\n",
+			mlxsw_m_port->local_port);
+		goto err_dev_addr_get;
+	}
+
+	netif_carrier_off(dev);
+	mlxsw_m->ports[local_port] = mlxsw_m_port;
+	err = register_netdev(dev);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Port %d: Failed to register netdev\n",
+			mlxsw_m_port->local_port);
+		goto err_register_netdev;
+	}
+
+	mlxsw_core_port_eth_set(mlxsw_m->core, mlxsw_m_port->local_port,
+				mlxsw_m_port, dev);
+
+	return 0;
+
+err_register_netdev:
+	mlxsw_m->ports[local_port] = NULL;
+	free_netdev(dev);
+err_dev_addr_get:
+err_alloc_etherdev:
+	mlxsw_core_port_fini(mlxsw_m->core, local_port);
+	return err;
+}
+
+static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u8 local_port)
+{
+	struct mlxsw_m_port *mlxsw_m_port = mlxsw_m->ports[local_port];
+
+	mlxsw_core_port_clear(mlxsw_m->core, local_port, mlxsw_m);
+	unregister_netdev(mlxsw_m_port->dev); /* This calls ndo_stop */
+	mlxsw_m->ports[local_port] = NULL;
+	free_netdev(mlxsw_m_port->dev);
+	mlxsw_core_port_fini(mlxsw_m->core, local_port);
+}
+
+static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port,
+				   u8 *last_module)
+{
+	u8 module, width;
+	int err;
+
+	/* Fill out to local port mapping array */
+	err = mlxsw_m_port_module_info_get(mlxsw_m, local_port, &module,
+					   &width);
+	if (err)
+		return err;
+
+	if (!width)
+		return 0;
+	/* Skip, if port belongs to the cluster */
+	if (module == *last_module)
+		return 0;
+	*last_module = module;
+	mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports;
+
+	return 0;
+}
+
+static void mlxsw_m_port_module_unmap(struct mlxsw_m *mlxsw_m, u8 module)
+{
+	mlxsw_m->module_to_port[module] = -1;
+}
+
+static int mlxsw_m_ports_create(struct mlxsw_m *mlxsw_m)
+{
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_m->core);
+	u8 last_module = max_ports;
+	int i;
+	int err;
+
+	mlxsw_m->ports = kcalloc(max_ports, sizeof(*mlxsw_m->ports),
+				 GFP_KERNEL);
+	if (!mlxsw_m->ports)
+		return -ENOMEM;
+
+	mlxsw_m->module_to_port = kmalloc_array(max_ports, sizeof(int),
+						GFP_KERNEL);
+	if (!mlxsw_m->module_to_port) {
+		err = -ENOMEM;
+		goto err_module_to_port_alloc;
+	}
+
+	/* Invalidate the entries of module to local port mapping array */
+	for (i = 0; i < max_ports; i++)
+		mlxsw_m->module_to_port[i] = -1;
+
+	/* Fill out module to local port mapping array */
+	for (i = 1; i < max_ports; i++) {
+		err = mlxsw_m_port_module_map(mlxsw_m, i, &last_module);
+		if (err)
+			goto err_module_to_port_map;
+	}
+
+	/* Create port objects for each valid entry */
+	for (i = 0; i < mlxsw_m->max_ports; i++) {
+		if (mlxsw_m->module_to_port[i] > 0) {
+			err = mlxsw_m_port_create(mlxsw_m,
+						  mlxsw_m->module_to_port[i],
+						  i);
+			if (err)
+				goto err_module_to_port_create;
+		}
+	}
+
+	return 0;
+
+err_module_to_port_create:
+	for (i--; i >= 0; i--) {
+		if (mlxsw_m->module_to_port[i] > 0)
+			mlxsw_m_port_remove(mlxsw_m,
+					    mlxsw_m->module_to_port[i]);
+	}
+	i = max_ports;
+err_module_to_port_map:
+	for (i--; i > 0; i--)
+		mlxsw_m_port_module_unmap(mlxsw_m, i);
+	kfree(mlxsw_m->module_to_port);
+err_module_to_port_alloc:
+	kfree(mlxsw_m->ports);
+	return err;
+}
+
+static void mlxsw_m_ports_remove(struct mlxsw_m *mlxsw_m)
+{
+	int i;
+
+	for (i = 0; i < mlxsw_m->max_ports; i++) {
+		if (mlxsw_m->module_to_port[i] > 0) {
+			mlxsw_m_port_remove(mlxsw_m,
+					    mlxsw_m->module_to_port[i]);
+			mlxsw_m_port_module_unmap(mlxsw_m, i);
+		}
+	}
+
+	kfree(mlxsw_m->module_to_port);
+	kfree(mlxsw_m->ports);
+}
+
+static int mlxsw_m_init(struct mlxsw_core *mlxsw_core,
+			const struct mlxsw_bus_info *mlxsw_bus_info)
+{
+	struct mlxsw_m *mlxsw_m = mlxsw_core_driver_priv(mlxsw_core);
+	int err;
+
+	mlxsw_m->core = mlxsw_core;
+	mlxsw_m->bus_info = mlxsw_bus_info;
+
+	err = mlxsw_m_base_mac_get(mlxsw_m);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Failed to get base mac\n");
+		return err;
+	}
+
+	err = mlxsw_m_ports_create(mlxsw_m);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Failed to create ports\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void mlxsw_m_fini(struct mlxsw_core *mlxsw_core)
+{
+	struct mlxsw_m *mlxsw_m = mlxsw_core_driver_priv(mlxsw_core);
+
+	mlxsw_m_ports_remove(mlxsw_m);
+}
+
+static const struct mlxsw_config_profile mlxsw_m_config_profile;
+
+static struct mlxsw_driver mlxsw_m_driver = {
+	.kind			= mlxsw_m_driver_name,
+	.priv_size		= sizeof(struct mlxsw_m),
+	.init			= mlxsw_m_init,
+	.fini			= mlxsw_m_fini,
+	.profile		= &mlxsw_m_config_profile,
+	.res_query_enabled	= true,
+};
+
+static const struct i2c_device_id mlxsw_m_i2c_id[] = {
 	{ "mlxsw_minimal", 0},
 	{ },
 };
 
-static struct i2c_driver mlxsw_minimal_i2c_driver = {
+static struct i2c_driver mlxsw_m_i2c_driver = {
 	.driver.name = "mlxsw_minimal",
 	.class = I2C_CLASS_HWMON,
-	.id_table = mlxsw_minimal_i2c_id,
+	.id_table = mlxsw_m_i2c_id,
 };
 
-static int __init mlxsw_minimal_module_init(void)
+static int __init mlxsw_m_module_init(void)
 {
 	int err;
 
-	err = mlxsw_core_driver_register(&mlxsw_minimal_driver);
+	err = mlxsw_core_driver_register(&mlxsw_m_driver);
 	if (err)
 		return err;
 
-	err = mlxsw_i2c_driver_register(&mlxsw_minimal_i2c_driver);
+	err = mlxsw_i2c_driver_register(&mlxsw_m_i2c_driver);
 	if (err)
 		goto err_i2c_driver_register;
 
 	return 0;
 
 err_i2c_driver_register:
-	mlxsw_core_driver_unregister(&mlxsw_minimal_driver);
+	mlxsw_core_driver_unregister(&mlxsw_m_driver);
 
 	return err;
 }
 
-static void __exit mlxsw_minimal_module_exit(void)
+static void __exit mlxsw_m_module_exit(void)
 {
-	mlxsw_i2c_driver_unregister(&mlxsw_minimal_i2c_driver);
-	mlxsw_core_driver_unregister(&mlxsw_minimal_driver);
+	mlxsw_i2c_driver_unregister(&mlxsw_m_i2c_driver);
+	mlxsw_core_driver_unregister(&mlxsw_m_driver);
 }
 
-module_init(mlxsw_minimal_module_init);
-module_exit(mlxsw_minimal_module_exit);
+module_init(mlxsw_m_module_init);
+module_exit(mlxsw_m_module_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox minimal driver");
-MODULE_DEVICE_TABLE(i2c, mlxsw_minimal_i2c_id);
+MODULE_DEVICE_TABLE(i2c, mlxsw_m_i2c_id);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index a2321fe8d6a0..051b19388a81 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -102,6 +102,7 @@ struct mlxsw_pci_queue_type_group {
 struct mlxsw_pci {
 	struct pci_dev *pdev;
 	u8 __iomem *hw_addr;
+	u64 free_running_clock_offset;
 	struct mlxsw_pci_queue_type_group queues[MLXSW_PCI_QUEUE_TYPE_COUNT];
 	u32 doorbell_offset;
 	struct mlxsw_core *core;
@@ -507,17 +508,28 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci,
 {
 	struct pci_dev *pdev = mlxsw_pci->pdev;
 	struct mlxsw_pci_queue_elem_info *elem_info;
+	struct mlxsw_tx_info tx_info;
 	char *wqe;
 	struct sk_buff *skb;
 	int i;
 
 	spin_lock(&q->lock);
 	elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
+	tx_info = mlxsw_skb_cb(elem_info->u.sdq.skb)->tx_info;
 	skb = elem_info->u.sdq.skb;
 	wqe = elem_info->elem;
 	for (i = 0; i < MLXSW_PCI_WQE_SG_ENTRIES; i++)
 		mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, i, DMA_TO_DEVICE);
-	dev_kfree_skb_any(skb);
+
+	if (unlikely(!tx_info.is_emad &&
+		     skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+		mlxsw_core_ptp_transmitted(mlxsw_pci->core, skb,
+					   tx_info.local_port);
+		skb = NULL;
+	}
+
+	if (skb)
+		dev_kfree_skb_any(skb);
 	elem_info->u.sdq.skb = NULL;
 
 	if (q->consumer_counter++ != consumer_counter_limit)
@@ -1039,42 +1051,6 @@ mlxsw_pci_config_profile_swid_config(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_mbox_config_profile_swid_config_mask_set(mbox, index, mask);
 }
 
-static int mlxsw_pci_resources_query(struct mlxsw_pci *mlxsw_pci, char *mbox,
-				     struct mlxsw_res *res)
-{
-	int index, i;
-	u64 data;
-	u16 id;
-	int err;
-
-	if (!res)
-		return 0;
-
-	mlxsw_cmd_mbox_zero(mbox);
-
-	for (index = 0; index < MLXSW_CMD_QUERY_RESOURCES_MAX_QUERIES;
-	     index++) {
-		err = mlxsw_cmd_query_resources(mlxsw_pci->core, mbox, index);
-		if (err)
-			return err;
-
-		for (i = 0; i < MLXSW_CMD_QUERY_RESOURCES_PER_QUERY; i++) {
-			id = mlxsw_cmd_mbox_query_resource_id_get(mbox, i);
-			data = mlxsw_cmd_mbox_query_resource_data_get(mbox, i);
-
-			if (id == MLXSW_CMD_QUERY_RESOURCES_TABLE_END_ID)
-				return 0;
-
-			mlxsw_res_parse(res, id, data);
-		}
-	}
-
-	/* If after MLXSW_RESOURCES_QUERY_MAX_QUERIES we still didn't get
-	 * MLXSW_RESOURCES_TABLE_END_ID, something went bad in the FW.
-	 */
-	return -EIO;
-}
-
 static int
 mlxsw_pci_profile_get_kvd_sizes(const struct mlxsw_pci *mlxsw_pci,
 				const struct mlxsw_config_profile *profile,
@@ -1450,6 +1426,15 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	mlxsw_pci->doorbell_offset =
 		mlxsw_cmd_mbox_query_fw_doorbell_page_offset_get(mbox);
 
+	if (mlxsw_cmd_mbox_query_fw_fr_rn_clk_bar_get(mbox) != 0) {
+		dev_err(&pdev->dev, "Unsupported free running clock BAR queried from hw\n");
+		err = -EINVAL;
+		goto err_fr_rn_clk_bar;
+	}
+
+	mlxsw_pci->free_running_clock_offset =
+		mlxsw_cmd_mbox_query_fw_free_running_clock_offset_get(mbox);
+
 	num_pages = mlxsw_cmd_mbox_query_fw_fw_pages_get(mbox);
 	err = mlxsw_pci_fw_area_init(mlxsw_pci, mbox, num_pages);
 	if (err)
@@ -1459,7 +1444,7 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_boardinfo;
 
-	err = mlxsw_pci_resources_query(mlxsw_pci, mbox, res);
+	err = mlxsw_core_resources_query(mlxsw_core, mbox, res);
 	if (err)
 		goto err_query_resources;
 
@@ -1505,6 +1490,7 @@ err_query_resources:
 err_boardinfo:
 	mlxsw_pci_fw_area_fini(mlxsw_pci);
 err_fw_area_init:
+err_fr_rn_clk_bar:
 err_doorbell_page_bar:
 err_iface_rev:
 err_query_fw:
@@ -1573,6 +1559,7 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 		err = -EAGAIN;
 		goto unlock;
 	}
+	mlxsw_skb_cb(skb)->tx_info = *tx_info;
 	elem_info->u.sdq.skb = skb;
 
 	wqe = elem_info->elem;
@@ -1596,6 +1583,9 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 			goto unmap_frags;
 	}
 
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
 	/* Set unused sq entries byte count to zero. */
 	for (i++; i < MLXSW_PCI_WQE_SG_ENTRIES; i++)
 		mlxsw_pci_wqe_byte_count_set(wqe, i, 0);
@@ -1708,6 +1698,24 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
 	return err;
 }
 
+static u32 mlxsw_pci_read_frc_h(void *bus_priv)
+{
+	struct mlxsw_pci *mlxsw_pci = bus_priv;
+	u64 frc_offset;
+
+	frc_offset = mlxsw_pci->free_running_clock_offset;
+	return mlxsw_pci_read32(mlxsw_pci, FREE_RUNNING_CLOCK_H(frc_offset));
+}
+
+static u32 mlxsw_pci_read_frc_l(void *bus_priv)
+{
+	struct mlxsw_pci *mlxsw_pci = bus_priv;
+	u64 frc_offset;
+
+	frc_offset = mlxsw_pci->free_running_clock_offset;
+	return mlxsw_pci_read32(mlxsw_pci, FREE_RUNNING_CLOCK_L(frc_offset));
+}
+
 static const struct mlxsw_bus mlxsw_pci_bus = {
 	.kind			= "pci",
 	.init			= mlxsw_pci_init,
@@ -1715,6 +1723,8 @@ static const struct mlxsw_bus mlxsw_pci_bus = {
 	.skb_transmit_busy	= mlxsw_pci_skb_transmit_busy,
 	.skb_transmit		= mlxsw_pci_skb_transmit,
 	.cmd_exec		= mlxsw_pci_cmd_exec,
+	.read_frc_h		= mlxsw_pci_read_frc_h,
+	.read_frc_l		= mlxsw_pci_read_frc_l,
 	.features		= MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET,
 };
 
@@ -1776,6 +1786,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->bus_info.device_kind = driver_name;
 	mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev);
 	mlxsw_pci->bus_info.dev = &pdev->dev;
+	mlxsw_pci->bus_info.read_frc_capable = true;
 	mlxsw_pci->id = id;
 
 	err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index ffee38e36ce8..e57e42e2d2b2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
 
 #define MLXSW_PCI_SW_RESET			0xF0010
 #define MLXSW_PCI_SW_RESET_RST_BIT		BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	13000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	20000
 #define MLXSW_PCI_SW_RESET_WAIT_MSECS		100
 #define MLXSW_PCI_FW_READY			0xA1844
 #define MLXSW_PCI_FW_READY_MASK			0xFFFF
@@ -43,6 +43,9 @@
 #define MLXSW_PCI_DOORBELL(offset, type_offset, num)	\
 	((offset) + (type_offset) + (num) * 4)
 
+#define MLXSW_PCI_FREE_RUNNING_CLOCK_H(offset)	(offset)
+#define MLXSW_PCI_FREE_RUNNING_CLOCK_L(offset)	((offset) + 4)
+
 #define MLXSW_PCI_CQS_MAX	96
 #define MLXSW_PCI_EQS_COUNT	2
 #define MLXSW_PCI_EQ_ASYNC_NUM	0
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 9b48dffc9f63..ead36702549a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -997,7 +997,7 @@ static inline void mlxsw_reg_spaft_pack(char *payload, u8 local_port,
 	MLXSW_REG_ZERO(spaft, payload);
 	mlxsw_reg_spaft_local_port_set(payload, local_port);
 	mlxsw_reg_spaft_allow_untagged_set(payload, allow_untagged);
-	mlxsw_reg_spaft_allow_prio_tagged_set(payload, true);
+	mlxsw_reg_spaft_allow_prio_tagged_set(payload, allow_untagged);
 	mlxsw_reg_spaft_allow_tagged_set(payload, true);
 }
 
@@ -2199,6 +2199,14 @@ MLXSW_ITEM32(reg, pagt, size, 0x00, 0, 8);
  */
 MLXSW_ITEM32(reg, pagt, acl_group_id, 0x08, 0, 16);
 
+/* reg_pagt_multi
+ * Multi-ACL
+ * 0 - This ACL is the last ACL in the multi-ACL
+ * 1 - This ACL is part of a multi-ACL
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, pagt, multi, 0x30, 31, 1, 0x04, 0x00, false);
+
 /* reg_pagt_acl_id
  * ACL identifier
  * Access: RW
@@ -2212,12 +2220,13 @@ static inline void mlxsw_reg_pagt_pack(char *payload, u16 acl_group_id)
 }
 
 static inline void mlxsw_reg_pagt_acl_id_pack(char *payload, int index,
-					      u16 acl_id)
+					      u16 acl_id, bool multi)
 {
 	u8 size = mlxsw_reg_pagt_size_get(payload);
 
 	if (index >= size)
 		mlxsw_reg_pagt_size_set(payload, index + 1);
+	mlxsw_reg_pagt_multi_set(payload, index, multi);
 	mlxsw_reg_pagt_acl_id_set(payload, index, acl_id);
 }
 
@@ -3506,6 +3515,18 @@ MLXSW_ITEM32(reg, qeec, next_element_index, 0x08, 0, 8);
  */
 MLXSW_ITEM32(reg, qeec, mise, 0x0C, 31, 1);
 
+/* reg_qeec_ptps
+ * PTP shaper
+ * 0: regular shaper mode
+ * 1: PTP oriented shaper
+ * Allowed only for hierarchy 0
+ * Not supported for CPU port
+ * Note that ptps mode may affect the shaper rates of all hierarchies
+ * Supported only on Spectrum-1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, ptps, 0x0C, 29, 1);
+
 enum {
 	MLXSW_REG_QEEC_BYTES_MODE,
 	MLXSW_REG_QEEC_PACKETS_MODE,
@@ -3592,6 +3613,16 @@ static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
 	mlxsw_reg_qeec_next_element_index_set(payload, next_index);
 }
 
+static inline void mlxsw_reg_qeec_ptps_pack(char *payload, u8 local_port,
+					    bool ptps)
+{
+	MLXSW_REG_ZERO(qeec, payload);
+	mlxsw_reg_qeec_local_port_set(payload, local_port);
+	mlxsw_reg_qeec_element_hierarchy_set(payload,
+					     MLXSW_REG_QEEC_HIERARCY_PORT);
+	mlxsw_reg_qeec_ptps_set(payload, ptps);
+}
+
 /* QRWE - QoS ReWrite Enable
  * -------------------------
  * This register configures the rewrite enable per receive port.
@@ -3805,6 +3836,112 @@ mlxsw_reg_qtctm_pack(char *payload, u8 local_port, bool mc)
 	mlxsw_reg_qtctm_mc_set(payload, mc);
 }
 
+/* QPSC - QoS PTP Shaper Configuration Register
+ * --------------------------------------------
+ * The QPSC allows advanced configuration of the shapers when QEEC.ptps=1.
+ * Supported only on Spectrum-1.
+ */
+#define MLXSW_REG_QPSC_ID 0x401B
+#define MLXSW_REG_QPSC_LEN 0x28
+
+MLXSW_REG_DEFINE(qpsc, MLXSW_REG_QPSC_ID, MLXSW_REG_QPSC_LEN);
+
+enum mlxsw_reg_qpsc_port_speed {
+	MLXSW_REG_QPSC_PORT_SPEED_100M,
+	MLXSW_REG_QPSC_PORT_SPEED_1G,
+	MLXSW_REG_QPSC_PORT_SPEED_10G,
+	MLXSW_REG_QPSC_PORT_SPEED_25G,
+};
+
+/* reg_qpsc_port_speed
+ * Port speed.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qpsc, port_speed, 0x00, 0, 4);
+
+/* reg_qpsc_shaper_time_exp
+ * The base-time-interval for updating the shapers tokens (for all hierarchies).
+ * shaper_update_rate = 2 ^ shaper_time_exp * (1 + shaper_time_mantissa) * 32nSec
+ * shaper_rate = 64bit * shaper_inc / shaper_update_rate
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpsc, shaper_time_exp, 0x04, 16, 4);
+
+/* reg_qpsc_shaper_time_mantissa
+ * The base-time-interval for updating the shapers tokens (for all hierarchies).
+ * shaper_update_rate = 2 ^ shaper_time_exp * (1 + shaper_time_mantissa) * 32nSec
+ * shaper_rate = 64bit * shaper_inc / shaper_update_rate
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpsc, shaper_time_mantissa, 0x04, 0, 5);
+
+/* reg_qpsc_shaper_inc
+ * Number of tokens added to shaper on each update.
+ * Units of 8B.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpsc, shaper_inc, 0x08, 0, 5);
+
+/* reg_qpsc_shaper_bs
+ * Max shaper Burst size.
+ * Burst size is 2 ^ max_shaper_bs * 512 [bits]
+ * Range is: 5..25 (from 2KB..2GB)
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpsc, shaper_bs, 0x0C, 0, 6);
+
+/* reg_qpsc_ptsc_we
+ * Write enable to port_to_shaper_credits.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, qpsc, ptsc_we, 0x10, 31, 1);
+
+/* reg_qpsc_port_to_shaper_credits
+ * For split ports: range 1..57
+ * For non-split ports: range 1..112
+ * Written only when ptsc_we is set.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpsc, port_to_shaper_credits, 0x10, 0, 8);
+
+/* reg_qpsc_ing_timestamp_inc
+ * Ingress timestamp increment.
+ * 2's complement.
+ * The timestamp of MTPPTR at ingress will be incremented by this value. Global
+ * value for all ports.
+ * Same units as used by MTPPTR.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpsc, ing_timestamp_inc, 0x20, 0, 32);
+
+/* reg_qpsc_egr_timestamp_inc
+ * Egress timestamp increment.
+ * 2's complement.
+ * The timestamp of MTPPTR at egress will be incremented by this value. Global
+ * value for all ports.
+ * Same units as used by MTPPTR.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpsc, egr_timestamp_inc, 0x24, 0, 32);
+
+static inline void
+mlxsw_reg_qpsc_pack(char *payload, enum mlxsw_reg_qpsc_port_speed port_speed,
+		    u8 shaper_time_exp, u8 shaper_time_mantissa, u8 shaper_inc,
+		    u8 shaper_bs, u8 port_to_shaper_credits,
+		    int ing_timestamp_inc, int egr_timestamp_inc)
+{
+	MLXSW_REG_ZERO(qpsc, payload);
+	mlxsw_reg_qpsc_port_speed_set(payload, port_speed);
+	mlxsw_reg_qpsc_shaper_time_exp_set(payload, shaper_time_exp);
+	mlxsw_reg_qpsc_shaper_time_mantissa_set(payload, shaper_time_mantissa);
+	mlxsw_reg_qpsc_shaper_inc_set(payload, shaper_inc);
+	mlxsw_reg_qpsc_shaper_bs_set(payload, shaper_bs);
+	mlxsw_reg_qpsc_ptsc_we_set(payload, true);
+	mlxsw_reg_qpsc_port_to_shaper_credits_set(payload, port_to_shaper_credits);
+	mlxsw_reg_qpsc_ing_timestamp_inc_set(payload, ing_timestamp_inc);
+	mlxsw_reg_qpsc_egr_timestamp_inc_set(payload, egr_timestamp_inc);
+}
+
 /* PMLP - Ports Module to Local Port Register
  * ------------------------------------------
  * Configures the assignment of modules to local ports.
@@ -3962,6 +4099,25 @@ enum {
  */
 MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4);
 
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_SGMII_100M				BIT(0)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_1000BASE_X_SGMII			BIT(1)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII			BIT(2)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R				BIT(3)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_XFI_XAUI_1_10G			BIT(4)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G		BIT(5)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR		BIT(6)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_2_LAUI_2_50GBASE_CR2_KR2	BIT(7)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR	BIT(8)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4		BIT(9)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2		BIT(10)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4		BIT(12)
+
+/* reg_ptys_ext_eth_proto_cap
+ * Extended Ethernet port supported speeds and protocols.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32);
+
 #define MLXSW_REG_PTYS_ETH_SPEED_SGMII			BIT(0)
 #define MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX		BIT(1)
 #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4		BIT(2)
@@ -4016,6 +4172,12 @@ MLXSW_ITEM32(reg, ptys, ib_link_width_cap, 0x10, 16, 16);
  */
 MLXSW_ITEM32(reg, ptys, ib_proto_cap, 0x10, 0, 16);
 
+/* reg_ptys_ext_eth_proto_admin
+ * Extended speed and protocol to set port to.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptys, ext_eth_proto_admin, 0x14, 0, 32);
+
 /* reg_ptys_eth_proto_admin
  * Speed and protocol to set port to.
  * Access: RW
@@ -4034,6 +4196,12 @@ MLXSW_ITEM32(reg, ptys, ib_link_width_admin, 0x1C, 16, 16);
  */
 MLXSW_ITEM32(reg, ptys, ib_proto_admin, 0x1C, 0, 16);
 
+/* reg_ptys_ext_eth_proto_oper
+ * The extended current speed and protocol configured for the port.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ext_eth_proto_oper, 0x20, 0, 32);
+
 /* reg_ptys_eth_proto_oper
  * The current speed and protocol configured for the port.
  * Access: RO
@@ -4052,12 +4220,23 @@ MLXSW_ITEM32(reg, ptys, ib_link_width_oper, 0x28, 16, 16);
  */
 MLXSW_ITEM32(reg, ptys, ib_proto_oper, 0x28, 0, 16);
 
-/* reg_ptys_eth_proto_lp_advertise
- * The protocols that were advertised by the link partner during
- * autonegotiation.
+enum mlxsw_reg_ptys_connector_type {
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_UNKNOWN_OR_NO_CONNECTOR,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_NONE,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_TP,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_AUI,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_BNC,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_MII,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_FIBRE,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_DA,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_OTHER,
+};
+
+/* reg_ptys_connector_type
+ * Connector type indication.
  * Access: RO
  */
-MLXSW_ITEM32(reg, ptys, eth_proto_lp_advertise, 0x30, 0, 32);
+MLXSW_ITEM32(reg, ptys, connector_type, 0x2C, 0, 4);
 
 static inline void mlxsw_reg_ptys_eth_pack(char *payload, u8 local_port,
 					   u32 proto_admin, bool autoneg)
@@ -4069,17 +4248,46 @@ static inline void mlxsw_reg_ptys_eth_pack(char *payload, u8 local_port,
 	mlxsw_reg_ptys_an_disable_admin_set(payload, !autoneg);
 }
 
+static inline void mlxsw_reg_ptys_ext_eth_pack(char *payload, u8 local_port,
+					       u32 proto_admin, bool autoneg)
+{
+	MLXSW_REG_ZERO(ptys, payload);
+	mlxsw_reg_ptys_local_port_set(payload, local_port);
+	mlxsw_reg_ptys_proto_mask_set(payload, MLXSW_REG_PTYS_PROTO_MASK_ETH);
+	mlxsw_reg_ptys_ext_eth_proto_admin_set(payload, proto_admin);
+	mlxsw_reg_ptys_an_disable_admin_set(payload, !autoneg);
+}
+
 static inline void mlxsw_reg_ptys_eth_unpack(char *payload,
 					     u32 *p_eth_proto_cap,
-					     u32 *p_eth_proto_adm,
+					     u32 *p_eth_proto_admin,
 					     u32 *p_eth_proto_oper)
 {
 	if (p_eth_proto_cap)
-		*p_eth_proto_cap = mlxsw_reg_ptys_eth_proto_cap_get(payload);
-	if (p_eth_proto_adm)
-		*p_eth_proto_adm = mlxsw_reg_ptys_eth_proto_admin_get(payload);
+		*p_eth_proto_cap =
+			mlxsw_reg_ptys_eth_proto_cap_get(payload);
+	if (p_eth_proto_admin)
+		*p_eth_proto_admin =
+			mlxsw_reg_ptys_eth_proto_admin_get(payload);
 	if (p_eth_proto_oper)
-		*p_eth_proto_oper = mlxsw_reg_ptys_eth_proto_oper_get(payload);
+		*p_eth_proto_oper =
+			mlxsw_reg_ptys_eth_proto_oper_get(payload);
+}
+
+static inline void mlxsw_reg_ptys_ext_eth_unpack(char *payload,
+						 u32 *p_eth_proto_cap,
+						 u32 *p_eth_proto_admin,
+						 u32 *p_eth_proto_oper)
+{
+	if (p_eth_proto_cap)
+		*p_eth_proto_cap =
+			mlxsw_reg_ptys_ext_eth_proto_cap_get(payload);
+	if (p_eth_proto_admin)
+		*p_eth_proto_admin =
+			mlxsw_reg_ptys_ext_eth_proto_admin_get(payload);
+	if (p_eth_proto_oper)
+		*p_eth_proto_oper =
+			mlxsw_reg_ptys_ext_eth_proto_oper_get(payload);
 }
 
 static inline void mlxsw_reg_ptys_ib_pack(char *payload, u8 local_port,
@@ -5130,6 +5338,42 @@ static inline void mlxsw_reg_pspa_pack(char *payload, u8 swid, u8 local_port)
 	mlxsw_reg_pspa_sub_port_set(payload, 0);
 }
 
+/* PPLR - Port Physical Loopback Register
+ * --------------------------------------
+ * This register allows configuration of the port's loopback mode.
+ */
+#define MLXSW_REG_PPLR_ID 0x5018
+#define MLXSW_REG_PPLR_LEN 0x8
+
+MLXSW_REG_DEFINE(pplr, MLXSW_REG_PPLR_ID, MLXSW_REG_PPLR_LEN);
+
+/* reg_pplr_local_port
+ * Local port number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pplr, local_port, 0x00, 16, 8);
+
+/* Phy local loopback. When set the port's egress traffic is looped back
+ * to the receiver and the port transmitter is disabled.
+ */
+#define MLXSW_REG_PPLR_LB_TYPE_BIT_PHY_LOCAL BIT(1)
+
+/* reg_pplr_lb_en
+ * Loopback enable.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pplr, lb_en, 0x04, 0, 8);
+
+static inline void mlxsw_reg_pplr_pack(char *payload, u8 local_port,
+				       bool phy_local)
+{
+	MLXSW_REG_ZERO(pplr, payload);
+	mlxsw_reg_pplr_local_port_set(payload, local_port);
+	mlxsw_reg_pplr_lb_en_set(payload,
+				 phy_local ?
+				 MLXSW_REG_PPLR_LB_TYPE_BIT_PHY_LOCAL : 0);
+}
+
 /* HTGT - Host Trap Group Table
  * ----------------------------
  * Configures the properties for forwarding to CPU.
@@ -5176,6 +5420,8 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
 };
 
 /* reg_htgt_trap_group
@@ -5666,6 +5912,8 @@ enum mlxsw_reg_ritr_loopback_protocol {
 	MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4,
 	/* IPinIP IPv6 underlay Unicast */
 	MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV6,
+	/* IPinIP generic - used for Spectrum-2 underlay RIF */
+	MLXSW_REG_RITR_LOOPBACK_GENERIC,
 };
 
 /* reg_ritr_loopback_protocol
@@ -5706,6 +5954,13 @@ MLXSW_ITEM32(reg, ritr, loopback_ipip_options, 0x10, 20, 4);
  */
 MLXSW_ITEM32(reg, ritr, loopback_ipip_uvr, 0x10, 0, 16);
 
+/* reg_ritr_loopback_ipip_underlay_rif
+ * Underlay ingress router interface.
+ * Reserved for Spectrum.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, loopback_ipip_underlay_rif, 0x14, 0, 16);
+
 /* reg_ritr_loopback_ipip_usip*
  * Encapsulation Underlay source IP.
  * Access: RW
@@ -5821,11 +6076,12 @@ static inline void
 mlxsw_reg_ritr_loopback_ipip_common_pack(char *payload,
 			    enum mlxsw_reg_ritr_loopback_ipip_type ipip_type,
 			    enum mlxsw_reg_ritr_loopback_ipip_options options,
-			    u16 uvr_id, u32 gre_key)
+			    u16 uvr_id, u16 underlay_rif, u32 gre_key)
 {
 	mlxsw_reg_ritr_loopback_ipip_type_set(payload, ipip_type);
 	mlxsw_reg_ritr_loopback_ipip_options_set(payload, options);
 	mlxsw_reg_ritr_loopback_ipip_uvr_set(payload, uvr_id);
+	mlxsw_reg_ritr_loopback_ipip_underlay_rif_set(payload, underlay_rif);
 	mlxsw_reg_ritr_loopback_ipip_gre_key_set(payload, gre_key);
 }
 
@@ -5833,12 +6089,12 @@ static inline void
 mlxsw_reg_ritr_loopback_ipip4_pack(char *payload,
 			    enum mlxsw_reg_ritr_loopback_ipip_type ipip_type,
 			    enum mlxsw_reg_ritr_loopback_ipip_options options,
-			    u16 uvr_id, u32 usip, u32 gre_key)
+			    u16 uvr_id, u16 underlay_rif, u32 usip, u32 gre_key)
 {
 	mlxsw_reg_ritr_loopback_protocol_set(payload,
 				    MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4);
 	mlxsw_reg_ritr_loopback_ipip_common_pack(payload, ipip_type, options,
-						 uvr_id, gre_key);
+						 uvr_id, underlay_rif, gre_key);
 	mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip);
 }
 
@@ -7200,6 +7456,13 @@ MLXSW_ITEM32(reg, rtdp, type, 0x00, 28, 4);
  */
 MLXSW_ITEM32(reg, rtdp, tunnel_index, 0x00, 0, 24);
 
+/* reg_rtdp_egress_router_interface
+ * Underlay egress router interface.
+ * Valid range is from 0 to cap_max_router_interfaces - 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, egress_router_interface, 0x40, 0, 16);
+
 /* IPinIP */
 
 /* reg_rtdp_ipip_irif
@@ -7849,6 +8112,35 @@ static inline void mlxsw_reg_mfsl_unpack(char *payload, u8 tacho,
 		*p_tach_max = mlxsw_reg_mfsl_tach_max_get(payload);
 }
 
+/* FORE - Fan Out of Range Event Register
+ * --------------------------------------
+ * This register reports the status of the controlled fans compared to the
+ * range defined by the MFSL register.
+ */
+#define MLXSW_REG_FORE_ID 0x9007
+#define MLXSW_REG_FORE_LEN 0x0C
+
+MLXSW_REG_DEFINE(fore, MLXSW_REG_FORE_ID, MLXSW_REG_FORE_LEN);
+
+/* fan_under_limit
+ * Fan speed is below the low limit defined in MFSL register. Each bit relates
+ * to a single tachometer and indicates the specific tachometer reading is
+ * below the threshold.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, fore, fan_under_limit, 0x00, 16, 10);
+
+static inline void mlxsw_reg_fore_unpack(char *payload, u8 tacho,
+					 bool *fault)
+{
+	u16 limit;
+
+	if (fault) {
+		limit = mlxsw_reg_fore_fan_under_limit_get(payload);
+		*fault = limit & BIT(tacho);
+	}
+}
+
 /* MTCAP - Management Temperature Capabilities
  * -------------------------------------------
  * This register exposes the capabilities of the device and
@@ -7877,16 +8169,21 @@ MLXSW_ITEM32(reg, mtcap, sensor_count, 0x00, 0, 7);
 
 MLXSW_REG_DEFINE(mtmp, MLXSW_REG_MTMP_ID, MLXSW_REG_MTMP_LEN);
 
+#define MLXSW_REG_MTMP_MODULE_INDEX_MIN 64
+#define MLXSW_REG_MTMP_GBOX_INDEX_MIN 256
 /* reg_mtmp_sensor_index
  * Sensors index to access.
  * 64-127 of sensor_index are mapped to the SFP+/QSFP modules sequentially
  * (module 0 is mapped to sensor_index 64).
  * Access: Index
  */
-MLXSW_ITEM32(reg, mtmp, sensor_index, 0x00, 0, 7);
+MLXSW_ITEM32(reg, mtmp, sensor_index, 0x00, 0, 12);
 
 /* Convert to milli degrees Celsius */
-#define MLXSW_REG_MTMP_TEMP_TO_MC(val) (val * 125)
+#define MLXSW_REG_MTMP_TEMP_TO_MC(val) ({ typeof(val) v_ = (val); \
+					  ((v_) >= 0) ? ((v_) * 125) : \
+					  ((s16)((GENMASK(15, 0) + (v_) + 1) \
+					   * 125)); })
 
 /* reg_mtmp_temperature
  * Temperature reading from the sensor. Reading is in 0.125 Celsius
@@ -7945,7 +8242,7 @@ MLXSW_ITEM32(reg, mtmp, temperature_threshold_lo, 0x10, 0, 16);
  */
 MLXSW_ITEM_BUF(reg, mtmp, sensor_name, 0x18, MLXSW_REG_MTMP_SENSOR_NAME_SIZE);
 
-static inline void mlxsw_reg_mtmp_pack(char *payload, u8 sensor_index,
+static inline void mlxsw_reg_mtmp_pack(char *payload, u16 sensor_index,
 				       bool max_temp_enable,
 				       bool max_temp_reset)
 {
@@ -7957,11 +8254,10 @@ static inline void mlxsw_reg_mtmp_pack(char *payload, u8 sensor_index,
 						    MLXSW_REG_MTMP_THRESH_HI);
 }
 
-static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp,
-					 unsigned int *p_max_temp,
-					 char *sensor_name)
+static inline void mlxsw_reg_mtmp_unpack(char *payload, int *p_temp,
+					 int *p_max_temp, char *sensor_name)
 {
-	u16 temp;
+	s16 temp;
 
 	if (p_temp) {
 		temp = mlxsw_reg_mtmp_temperature_get(payload);
@@ -7975,6 +8271,80 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp,
 		mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name);
 }
 
+/* MTBR - Management Temperature Bulk Register
+ * -------------------------------------------
+ * This register is used for bulk temperature reading.
+ */
+#define MLXSW_REG_MTBR_ID 0x900F
+#define MLXSW_REG_MTBR_BASE_LEN 0x10 /* base length, without records */
+#define MLXSW_REG_MTBR_REC_LEN 0x04 /* record length */
+#define MLXSW_REG_MTBR_REC_MAX_COUNT 47 /* firmware limitation */
+#define MLXSW_REG_MTBR_LEN (MLXSW_REG_MTBR_BASE_LEN +	\
+			    MLXSW_REG_MTBR_REC_LEN *	\
+			    MLXSW_REG_MTBR_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(mtbr, MLXSW_REG_MTBR_ID, MLXSW_REG_MTBR_LEN);
+
+/* reg_mtbr_base_sensor_index
+ * Base sensors index to access (0 - ASIC sensor, 1-63 - ambient sensors,
+ * 64-127 are mapped to the SFP+/QSFP modules sequentially).
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mtbr, base_sensor_index, 0x00, 0, 12);
+
+/* reg_mtbr_num_rec
+ * Request: Number of records to read
+ * Response: Number of records read
+ * See above description for more details.
+ * Range 1..255
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mtbr, num_rec, 0x04, 0, 8);
+
+/* reg_mtbr_rec_max_temp
+ * The highest measured temperature from the sensor.
+ * When the bit mte is cleared, the field max_temperature is reserved.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtbr, rec_max_temp, MLXSW_REG_MTBR_BASE_LEN, 16,
+		     16, MLXSW_REG_MTBR_REC_LEN, 0x00, false);
+
+/* reg_mtbr_rec_temp
+ * Temperature reading from the sensor. Reading is in 0..125 Celsius
+ * degrees units.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtbr, rec_temp, MLXSW_REG_MTBR_BASE_LEN, 0, 16,
+		     MLXSW_REG_MTBR_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_mtbr_pack(char *payload, u16 base_sensor_index,
+				       u8 num_rec)
+{
+	MLXSW_REG_ZERO(mtbr, payload);
+	mlxsw_reg_mtbr_base_sensor_index_set(payload, base_sensor_index);
+	mlxsw_reg_mtbr_num_rec_set(payload, num_rec);
+}
+
+/* Error codes from temperatute reading */
+enum mlxsw_reg_mtbr_temp_status {
+	MLXSW_REG_MTBR_NO_CONN		= 0x8000,
+	MLXSW_REG_MTBR_NO_TEMP_SENS	= 0x8001,
+	MLXSW_REG_MTBR_INDEX_NA		= 0x8002,
+	MLXSW_REG_MTBR_BAD_SENS_INFO	= 0x8003,
+};
+
+/* Base index for reading modules temperature */
+#define MLXSW_REG_MTBR_BASE_MODULE_INDEX 64
+
+static inline void mlxsw_reg_mtbr_temp_unpack(char *payload, int rec_ind,
+					      u16 *p_temp, u16 *p_max_temp)
+{
+	if (p_temp)
+		*p_temp = mlxsw_reg_mtbr_rec_temp_get(payload, rec_ind);
+	if (p_max_temp)
+		*p_max_temp = mlxsw_reg_mtbr_rec_max_temp_get(payload, rec_ind);
+}
+
 /* MCIA - Management Cable Info Access
  * -----------------------------------
  * MCIA register is used to access the SFP+ and QSFP connector's EPROM.
@@ -8029,13 +8399,41 @@ MLXSW_ITEM32(reg, mcia, device_address, 0x04, 0, 16);
  */
 MLXSW_ITEM32(reg, mcia, size, 0x08, 0, 16);
 
-#define MLXSW_SP_REG_MCIA_EEPROM_SIZE 48
+#define MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH	256
+#define MLXSW_REG_MCIA_EEPROM_SIZE		48
+#define MLXSW_REG_MCIA_I2C_ADDR_LOW		0x50
+#define MLXSW_REG_MCIA_I2C_ADDR_HIGH		0x51
+#define MLXSW_REG_MCIA_PAGE0_LO_OFF		0xa0
+#define MLXSW_REG_MCIA_TH_ITEM_SIZE		2
+#define MLXSW_REG_MCIA_TH_PAGE_NUM		3
+#define MLXSW_REG_MCIA_PAGE0_LO			0
+#define MLXSW_REG_MCIA_TH_PAGE_OFF		0x80
+
+enum mlxsw_reg_mcia_eeprom_module_info_rev_id {
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_UNSPC	= 0x00,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8436	= 0x01,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636	= 0x03,
+};
+
+enum mlxsw_reg_mcia_eeprom_module_info_id {
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP	= 0x03,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP	= 0x0C,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS	= 0x0D,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28	= 0x11,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD	= 0x18,
+};
+
+enum mlxsw_reg_mcia_eeprom_module_info {
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE,
+};
 
 /* reg_mcia_eeprom
  * Bytes to read/write.
  * Access: RW
  */
-MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_SP_REG_MCIA_EEPROM_SIZE);
+MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_REG_MCIA_EEPROM_SIZE);
 
 static inline void mlxsw_reg_mcia_pack(char *payload, u8 module, u8 lock,
 				       u8 page_number, u16 device_addr,
@@ -8306,6 +8704,60 @@ static inline void mlxsw_reg_mpar_pack(char *payload, u8 local_port,
 	mlxsw_reg_mpar_pa_id_set(payload, pa_id);
 }
 
+/* MGIR - Management General Information Register
+ * ----------------------------------------------
+ * MGIR register allows software to query the hardware and firmware general
+ * information.
+ */
+#define MLXSW_REG_MGIR_ID 0x9020
+#define MLXSW_REG_MGIR_LEN 0x9C
+
+MLXSW_REG_DEFINE(mgir, MLXSW_REG_MGIR_ID, MLXSW_REG_MGIR_LEN);
+
+/* reg_mgir_hw_info_device_hw_revision
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, hw_info_device_hw_revision, 0x0, 16, 16);
+
+#define MLXSW_REG_MGIR_FW_INFO_PSID_SIZE 16
+
+/* reg_mgir_fw_info_psid
+ * PSID (ASCII string).
+ * Access: RO
+ */
+MLXSW_ITEM_BUF(reg, mgir, fw_info_psid, 0x30, MLXSW_REG_MGIR_FW_INFO_PSID_SIZE);
+
+/* reg_mgir_fw_info_extended_major
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, fw_info_extended_major, 0x44, 0, 32);
+
+/* reg_mgir_fw_info_extended_minor
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, fw_info_extended_minor, 0x48, 0, 32);
+
+/* reg_mgir_fw_info_extended_sub_minor
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgir, fw_info_extended_sub_minor, 0x4C, 0, 32);
+
+static inline void mlxsw_reg_mgir_pack(char *payload)
+{
+	MLXSW_REG_ZERO(mgir, payload);
+}
+
+static inline void
+mlxsw_reg_mgir_unpack(char *payload, u32 *hw_rev, char *fw_info_psid,
+		      u32 *fw_major, u32 *fw_minor, u32 *fw_sub_minor)
+{
+	*hw_rev = mlxsw_reg_mgir_hw_info_device_hw_revision_get(payload);
+	mlxsw_reg_mgir_fw_info_psid_memcpy_from(payload, fw_info_psid);
+	*fw_major = mlxsw_reg_mgir_fw_info_extended_major_get(payload);
+	*fw_minor = mlxsw_reg_mgir_fw_info_extended_minor_get(payload);
+	*fw_sub_minor = mlxsw_reg_mgir_fw_info_extended_sub_minor_get(payload);
+}
+
 /* MRSR - Management Reset and Shutdown Register
  * ---------------------------------------------
  * MRSR register is used to reset or shutdown the switch or
@@ -8371,6 +8823,107 @@ static inline void mlxsw_reg_mlcr_pack(char *payload, u8 local_port,
 					   MLXSW_REG_MLCR_DURATION_MAX : 0);
 }
 
+/* MTPPS - Management Pulse Per Second Register
+ * --------------------------------------------
+ * This register provides the device PPS capabilities, configure the PPS in and
+ * out modules and holds the PPS in time stamp.
+ */
+#define MLXSW_REG_MTPPS_ID 0x9053
+#define MLXSW_REG_MTPPS_LEN 0x3C
+
+MLXSW_REG_DEFINE(mtpps, MLXSW_REG_MTPPS_ID, MLXSW_REG_MTPPS_LEN);
+
+/* reg_mtpps_enable
+ * Enables the PPS functionality the specific pin.
+ * A boolean variable.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mtpps, enable, 0x20, 31, 1);
+
+enum mlxsw_reg_mtpps_pin_mode {
+	MLXSW_REG_MTPPS_PIN_MODE_VIRTUAL_PIN = 0x2,
+};
+
+/* reg_mtpps_pin_mode
+ * Pin mode to be used. The mode must comply with the supported modes of the
+ * requested pin.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mtpps, pin_mode, 0x20, 8, 4);
+
+#define MLXSW_REG_MTPPS_PIN_SP_VIRTUAL_PIN	7
+
+/* reg_mtpps_pin
+ * Pin to be configured or queried out of the supported pins.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mtpps, pin, 0x20, 0, 8);
+
+/* reg_mtpps_time_stamp
+ * When pin_mode = pps_in, the latched device time when it was triggered from
+ * the external GPIO pin.
+ * When pin_mode = pps_out or virtual_pin or pps_out_and_virtual_pin, the target
+ * time to generate next output signal.
+ * Time is in units of device clock.
+ * Access: RW
+ */
+MLXSW_ITEM64(reg, mtpps, time_stamp, 0x28, 0, 64);
+
+static inline void
+mlxsw_reg_mtpps_vpin_pack(char *payload, u64 time_stamp)
+{
+	MLXSW_REG_ZERO(mtpps, payload);
+	mlxsw_reg_mtpps_pin_set(payload, MLXSW_REG_MTPPS_PIN_SP_VIRTUAL_PIN);
+	mlxsw_reg_mtpps_pin_mode_set(payload,
+				     MLXSW_REG_MTPPS_PIN_MODE_VIRTUAL_PIN);
+	mlxsw_reg_mtpps_enable_set(payload, true);
+	mlxsw_reg_mtpps_time_stamp_set(payload, time_stamp);
+}
+
+/* MTUTC - Management UTC Register
+ * -------------------------------
+ * Configures the HW UTC counter.
+ */
+#define MLXSW_REG_MTUTC_ID 0x9055
+#define MLXSW_REG_MTUTC_LEN 0x1C
+
+MLXSW_REG_DEFINE(mtutc, MLXSW_REG_MTUTC_ID, MLXSW_REG_MTUTC_LEN);
+
+enum mlxsw_reg_mtutc_operation {
+	MLXSW_REG_MTUTC_OPERATION_SET_TIME_AT_NEXT_SEC = 0,
+	MLXSW_REG_MTUTC_OPERATION_ADJUST_FREQ = 3,
+};
+
+/* reg_mtutc_operation
+ * Operation.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mtutc, operation, 0x00, 0, 4);
+
+/* reg_mtutc_freq_adjustment
+ * Frequency adjustment: Every PPS the HW frequency will be
+ * adjusted by this value. Units of HW clock, where HW counts
+ * 10^9 HW clocks for 1 HW second.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mtutc, freq_adjustment, 0x04, 0, 32);
+
+/* reg_mtutc_utc_sec
+ * UTC seconds.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, mtutc, utc_sec, 0x10, 0, 32);
+
+static inline void
+mlxsw_reg_mtutc_pack(char *payload, enum mlxsw_reg_mtutc_operation oper,
+		     u32 freq_adj, u32 utc_sec)
+{
+	MLXSW_REG_ZERO(mtutc, payload);
+	mlxsw_reg_mtutc_operation_set(payload, oper);
+	mlxsw_reg_mtutc_freq_adjustment_set(payload, freq_adj);
+	mlxsw_reg_mtutc_utc_sec_set(payload, utc_sec);
+}
+
 /* MCQI - Management Component Query Information
  * ---------------------------------------------
  * This register allows querying information about firmware components.
@@ -8725,6 +9278,267 @@ static inline void mlxsw_reg_mprs_pack(char *payload, u16 parsing_depth,
 	mlxsw_reg_mprs_vxlan_udp_dport_set(payload, vxlan_udp_dport);
 }
 
+/* MOGCR - Monitoring Global Configuration Register
+ * ------------------------------------------------
+ */
+#define MLXSW_REG_MOGCR_ID 0x9086
+#define MLXSW_REG_MOGCR_LEN 0x20
+
+MLXSW_REG_DEFINE(mogcr, MLXSW_REG_MOGCR_ID, MLXSW_REG_MOGCR_LEN);
+
+/* reg_mogcr_ptp_iftc
+ * PTP Ingress FIFO Trap Clear
+ * The PTP_ING_FIFO trap provides MTPPTR with clr according
+ * to this value. Default 0.
+ * Reserved when IB switches and when SwitchX/-2, Spectrum-2
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mogcr, ptp_iftc, 0x00, 1, 1);
+
+/* reg_mogcr_ptp_eftc
+ * PTP Egress FIFO Trap Clear
+ * The PTP_EGR_FIFO trap provides MTPPTR with clr according
+ * to this value. Default 0.
+ * Reserved when IB switches and when SwitchX/-2, Spectrum-2
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mogcr, ptp_eftc, 0x00, 0, 1);
+
+/* MTPPPC - Time Precision Packet Port Configuration
+ * -------------------------------------------------
+ * This register serves for configuration of which PTP messages should be
+ * timestamped. This is a global configuration, despite the register name.
+ *
+ * Reserved when Spectrum-2.
+ */
+#define MLXSW_REG_MTPPPC_ID 0x9090
+#define MLXSW_REG_MTPPPC_LEN 0x28
+
+MLXSW_REG_DEFINE(mtpppc, MLXSW_REG_MTPPPC_ID, MLXSW_REG_MTPPPC_LEN);
+
+/* reg_mtpppc_ing_timestamp_message_type
+ * Bitwise vector of PTP message types to timestamp at ingress.
+ * MessageType field as defined by IEEE 1588
+ * Each bit corresponds to a value (e.g. Bit0: Sync, Bit1: Delay_Req)
+ * Default all 0
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mtpppc, ing_timestamp_message_type, 0x08, 0, 16);
+
+/* reg_mtpppc_egr_timestamp_message_type
+ * Bitwise vector of PTP message types to timestamp at egress.
+ * MessageType field as defined by IEEE 1588
+ * Each bit corresponds to a value (e.g. Bit0: Sync, Bit1: Delay_Req)
+ * Default all 0
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mtpppc, egr_timestamp_message_type, 0x0C, 0, 16);
+
+static inline void mlxsw_reg_mtpppc_pack(char *payload, u16 ing, u16 egr)
+{
+	MLXSW_REG_ZERO(mtpppc, payload);
+	mlxsw_reg_mtpppc_ing_timestamp_message_type_set(payload, ing);
+	mlxsw_reg_mtpppc_egr_timestamp_message_type_set(payload, egr);
+}
+
+/* MTPPTR - Time Precision Packet Timestamping Reading
+ * ---------------------------------------------------
+ * The MTPPTR is used for reading the per port PTP timestamp FIFO.
+ * There is a trap for packets which are latched to the timestamp FIFO, thus the
+ * SW knows which FIFO to read. Note that packets enter the FIFO before been
+ * trapped. The sequence number is used to synchronize the timestamp FIFO
+ * entries and the trapped packets.
+ * Reserved when Spectrum-2.
+ */
+
+#define MLXSW_REG_MTPPTR_ID 0x9091
+#define MLXSW_REG_MTPPTR_BASE_LEN 0x10 /* base length, without records */
+#define MLXSW_REG_MTPPTR_REC_LEN 0x10 /* record length */
+#define MLXSW_REG_MTPPTR_REC_MAX_COUNT 4
+#define MLXSW_REG_MTPPTR_LEN (MLXSW_REG_MTPPTR_BASE_LEN +		\
+		    MLXSW_REG_MTPPTR_REC_LEN * MLXSW_REG_MTPPTR_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(mtpptr, MLXSW_REG_MTPPTR_ID, MLXSW_REG_MTPPTR_LEN);
+
+/* reg_mtpptr_local_port
+ * Not supported for CPU port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mtpptr, local_port, 0x00, 16, 8);
+
+enum mlxsw_reg_mtpptr_dir {
+	MLXSW_REG_MTPPTR_DIR_INGRESS,
+	MLXSW_REG_MTPPTR_DIR_EGRESS,
+};
+
+/* reg_mtpptr_dir
+ * Direction.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mtpptr, dir, 0x00, 0, 1);
+
+/* reg_mtpptr_clr
+ * Clear the records.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, mtpptr, clr, 0x04, 31, 1);
+
+/* reg_mtpptr_num_rec
+ * Number of valid records in the response
+ * Range 0.. cap_ptp_timestamp_fifo
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mtpptr, num_rec, 0x08, 0, 4);
+
+/* reg_mtpptr_rec_message_type
+ * MessageType field as defined by IEEE 1588 Each bit corresponds to a value
+ * (e.g. Bit0: Sync, Bit1: Delay_Req)
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtpptr, rec_message_type,
+		     MLXSW_REG_MTPPTR_BASE_LEN, 8, 4,
+		     MLXSW_REG_MTPPTR_REC_LEN, 0, false);
+
+/* reg_mtpptr_rec_domain_number
+ * DomainNumber field as defined by IEEE 1588
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtpptr, rec_domain_number,
+		     MLXSW_REG_MTPPTR_BASE_LEN, 0, 8,
+		     MLXSW_REG_MTPPTR_REC_LEN, 0, false);
+
+/* reg_mtpptr_rec_sequence_id
+ * SequenceId field as defined by IEEE 1588
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtpptr, rec_sequence_id,
+		     MLXSW_REG_MTPPTR_BASE_LEN, 0, 16,
+		     MLXSW_REG_MTPPTR_REC_LEN, 0x4, false);
+
+/* reg_mtpptr_rec_timestamp_high
+ * Timestamp of when the PTP packet has passed through the port Units of PLL
+ * clock time.
+ * For Spectrum-1 the PLL clock is 156.25Mhz and PLL clock time is 6.4nSec.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtpptr, rec_timestamp_high,
+		     MLXSW_REG_MTPPTR_BASE_LEN, 0, 32,
+		     MLXSW_REG_MTPPTR_REC_LEN, 0x8, false);
+
+/* reg_mtpptr_rec_timestamp_low
+ * See rec_timestamp_high.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtpptr, rec_timestamp_low,
+		     MLXSW_REG_MTPPTR_BASE_LEN, 0, 32,
+		     MLXSW_REG_MTPPTR_REC_LEN, 0xC, false);
+
+static inline void mlxsw_reg_mtpptr_unpack(const char *payload,
+					   unsigned int rec,
+					   u8 *p_message_type,
+					   u8 *p_domain_number,
+					   u16 *p_sequence_id,
+					   u64 *p_timestamp)
+{
+	u32 timestamp_high, timestamp_low;
+
+	*p_message_type = mlxsw_reg_mtpptr_rec_message_type_get(payload, rec);
+	*p_domain_number = mlxsw_reg_mtpptr_rec_domain_number_get(payload, rec);
+	*p_sequence_id = mlxsw_reg_mtpptr_rec_sequence_id_get(payload, rec);
+	timestamp_high = mlxsw_reg_mtpptr_rec_timestamp_high_get(payload, rec);
+	timestamp_low = mlxsw_reg_mtpptr_rec_timestamp_low_get(payload, rec);
+	*p_timestamp = (u64)timestamp_high << 32 | timestamp_low;
+}
+
+/* MTPTPT - Monitoring Precision Time Protocol Trap Register
+ * ---------------------------------------------------------
+ * This register is used for configuring under which trap to deliver PTP
+ * packets depending on type of the packet.
+ */
+#define MLXSW_REG_MTPTPT_ID 0x9092
+#define MLXSW_REG_MTPTPT_LEN 0x08
+
+MLXSW_REG_DEFINE(mtptpt, MLXSW_REG_MTPTPT_ID, MLXSW_REG_MTPTPT_LEN);
+
+enum mlxsw_reg_mtptpt_trap_id {
+	MLXSW_REG_MTPTPT_TRAP_ID_PTP0,
+	MLXSW_REG_MTPTPT_TRAP_ID_PTP1,
+};
+
+/* reg_mtptpt_trap_id
+ * Trap id.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mtptpt, trap_id, 0x00, 0, 4);
+
+/* reg_mtptpt_message_type
+ * Bitwise vector of PTP message types to trap. This is a necessary but
+ * non-sufficient condition since need to enable also per port. See MTPPPC.
+ * Message types are defined by IEEE 1588 Each bit corresponds to a value (e.g.
+ * Bit0: Sync, Bit1: Delay_Req)
+ */
+MLXSW_ITEM32(reg, mtptpt, message_type, 0x04, 0, 16);
+
+static inline void mlxsw_reg_mtptptp_pack(char *payload,
+					  enum mlxsw_reg_mtptpt_trap_id trap_id,
+					  u16 message_type)
+{
+	MLXSW_REG_ZERO(mtptpt, payload);
+	mlxsw_reg_mtptpt_trap_id_set(payload, trap_id);
+	mlxsw_reg_mtptpt_message_type_set(payload, message_type);
+}
+
+/* MGPIR - Management General Peripheral Information Register
+ * ----------------------------------------------------------
+ * MGPIR register allows software to query the hardware and
+ * firmware general information of peripheral entities.
+ */
+#define MLXSW_REG_MGPIR_ID 0x9100
+#define MLXSW_REG_MGPIR_LEN 0xA0
+
+MLXSW_REG_DEFINE(mgpir, MLXSW_REG_MGPIR_ID, MLXSW_REG_MGPIR_LEN);
+
+enum mlxsw_reg_mgpir_device_type {
+	MLXSW_REG_MGPIR_DEVICE_TYPE_NONE,
+	MLXSW_REG_MGPIR_DEVICE_TYPE_GEARBOX_DIE,
+};
+
+/* device_type
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgpir, device_type, 0x00, 24, 4);
+
+/* devices_per_flash
+ * Number of devices of device_type per flash (can be shared by few devices).
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgpir, devices_per_flash, 0x00, 16, 8);
+
+/* num_of_devices
+ * Number of devices of device_type.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, mgpir, num_of_devices, 0x00, 0, 8);
+
+static inline void mlxsw_reg_mgpir_pack(char *payload)
+{
+	MLXSW_REG_ZERO(mgpir, payload);
+}
+
+static inline void
+mlxsw_reg_mgpir_unpack(char *payload, u8 *num_of_devices,
+		       enum mlxsw_reg_mgpir_device_type *device_type,
+		       u8 *devices_per_flash)
+{
+	if (num_of_devices)
+		*num_of_devices = mlxsw_reg_mgpir_num_of_devices_get(payload);
+	if (device_type)
+		*device_type = mlxsw_reg_mgpir_device_type_get(payload);
+	if (devices_per_flash)
+		*devices_per_flash =
+				mlxsw_reg_mgpir_devices_per_flash_get(payload);
+}
+
 /* TNGCR - Tunneling NVE General Configuration Register
  * ----------------------------------------------------
  * The TNGCR register is used for setting up the NVE Tunneling configuration.
@@ -9688,6 +10502,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(qpdsm),
 	MLXSW_REG(qpdpm),
 	MLXSW_REG(qtctm),
+	MLXSW_REG(qpsc),
 	MLXSW_REG(pmlp),
 	MLXSW_REG(pmtu),
 	MLXSW_REG(ptys),
@@ -9699,6 +10514,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(pptb),
 	MLXSW_REG(pbmc),
 	MLXSW_REG(pspa),
+	MLXSW_REG(pplr),
 	MLXSW_REG(htgt),
 	MLXSW_REG(hpkt),
 	MLXSW_REG(rgcr),
@@ -9723,19 +10539,29 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mfsc),
 	MLXSW_REG(mfsm),
 	MLXSW_REG(mfsl),
+	MLXSW_REG(fore),
 	MLXSW_REG(mtcap),
 	MLXSW_REG(mtmp),
+	MLXSW_REG(mtbr),
 	MLXSW_REG(mcia),
 	MLXSW_REG(mpat),
 	MLXSW_REG(mpar),
+	MLXSW_REG(mgir),
 	MLXSW_REG(mrsr),
 	MLXSW_REG(mlcr),
+	MLXSW_REG(mtpps),
+	MLXSW_REG(mtutc),
 	MLXSW_REG(mpsc),
 	MLXSW_REG(mcqi),
 	MLXSW_REG(mcc),
 	MLXSW_REG(mcda),
 	MLXSW_REG(mgpc),
 	MLXSW_REG(mprs),
+	MLXSW_REG(mogcr),
+	MLXSW_REG(mtpppc),
+	MLXSW_REG(mtpptr),
+	MLXSW_REG(mtptpt),
+	MLXSW_REG(mgpir),
 	MLXSW_REG(tngcr),
 	MLXSW_REG(tnumt),
 	MLXSW_REG(tnqcr),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index b8b3a01c2a9e..33a9fc9ef6a4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -24,8 +24,11 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_MAX_SYSTEM_PORT,
 	MLXSW_RES_ID_MAX_LAG,
 	MLXSW_RES_ID_MAX_LAG_MEMBERS,
+	MLXSW_RES_ID_LOCAL_PORTS_IN_1X,
+	MLXSW_RES_ID_LOCAL_PORTS_IN_2X,
 	MLXSW_RES_ID_MAX_BUFFER_SIZE,
 	MLXSW_RES_ID_CELL_SIZE,
+	MLXSW_RES_ID_MAX_HEADROOM_SIZE,
 	MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS,
 	MLXSW_RES_ID_ACL_MAX_TCAM_RULES,
 	MLXSW_RES_ID_ACL_MAX_REGIONS,
@@ -77,8 +80,11 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502,
 	[MLXSW_RES_ID_MAX_LAG] = 0x2520,
 	[MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521,
+	[MLXSW_RES_ID_LOCAL_PORTS_IN_1X] = 0x2610,
+	[MLXSW_RES_ID_LOCAL_PORTS_IN_2X] = 0x2611,
 	[MLXSW_RES_ID_MAX_BUFFER_SIZE] = 0x2802,	/* Bytes */
 	[MLXSW_RES_ID_CELL_SIZE] = 0x2803,	/* Bytes */
+	[MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811,	/* Bytes */
 	[MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS] = 0x2901,
 	[MLXSW_RES_ID_ACL_MAX_TCAM_RULES] = 0x2902,
 	[MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 32519c93df17..4d34d42b3b0e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -21,7 +21,7 @@
 #include <linux/dcbnl.h>
 #include <linux/inetdevice.h>
 #include <linux/netlink.h>
-#include <linux/random.h>
+#include <linux/jhash.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_mirred.h>
@@ -32,6 +32,7 @@
 #include "spectrum.h"
 #include "pci.h"
 #include "core.h"
+#include "core_env.h"
 #include "reg.h"
 #include "port.h"
 #include "trap.h"
@@ -40,13 +41,14 @@
 #include "spectrum_dpipe.h"
 #include "spectrum_acl_flex_actions.h"
 #include "spectrum_span.h"
+#include "spectrum_ptp.h"
 #include "../mlxfw/mlxfw.h"
 
 #define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
 
 #define MLXSW_SP1_FWREV_MAJOR 13
-#define MLXSW_SP1_FWREV_MINOR 1910
-#define MLXSW_SP1_FWREV_SUBMINOR 622
+#define MLXSW_SP1_FWREV_MINOR 2000
+#define MLXSW_SP1_FWREV_SUBMINOR 1122
 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702
 
 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
@@ -145,6 +147,35 @@ struct mlxsw_sp_mlxfw_dev {
 	struct mlxsw_sp *mlxsw_sp;
 };
 
+struct mlxsw_sp_ptp_ops {
+	struct mlxsw_sp_ptp_clock *
+		(*clock_init)(struct mlxsw_sp *mlxsw_sp, struct device *dev);
+	void (*clock_fini)(struct mlxsw_sp_ptp_clock *clock);
+
+	struct mlxsw_sp_ptp_state *(*init)(struct mlxsw_sp *mlxsw_sp);
+	void (*fini)(struct mlxsw_sp_ptp_state *ptp_state);
+
+	/* Notify a driver that a packet that might be PTP was received. Driver
+	 * is responsible for freeing the passed-in SKB.
+	 */
+	void (*receive)(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			u8 local_port);
+
+	/* Notify a driver that a timestamped packet was transmitted. Driver
+	 * is responsible for freeing the passed-in SKB.
+	 */
+	void (*transmitted)(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			    u8 local_port);
+
+	int (*hwtstamp_get)(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct hwtstamp_config *config);
+	int (*hwtstamp_set)(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct hwtstamp_config *config);
+	void (*shaper_work)(struct work_struct *work);
+	int (*get_ts_info)(struct mlxsw_sp *mlxsw_sp,
+			   struct ethtool_ts_info *info);
+};
+
 static int mlxsw_sp_component_query(struct mlxfw_dev *mlxfw_dev,
 				    u16 component_index, u32 *p_max_size,
 				    u8 *p_align_bits, u16 *p_max_write_size)
@@ -293,6 +324,19 @@ static void mlxsw_sp_fsm_release(struct mlxfw_dev *mlxfw_dev, u32 fwhandle)
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mcc), mcc_pl);
 }
 
+static void mlxsw_sp_status_notify(struct mlxfw_dev *mlxfw_dev,
+				   const char *msg, const char *comp_name,
+				   u32 done_bytes, u32 total_bytes)
+{
+	struct mlxsw_sp_mlxfw_dev *mlxsw_sp_mlxfw_dev =
+		container_of(mlxfw_dev, struct mlxsw_sp_mlxfw_dev, mlxfw_dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_mlxfw_dev->mlxsw_sp;
+
+	devlink_flash_update_status_notify(priv_to_devlink(mlxsw_sp->core),
+					   msg, comp_name,
+					   done_bytes, total_bytes);
+}
+
 static const struct mlxfw_dev_ops mlxsw_sp_mlxfw_dev_ops = {
 	.component_query	= mlxsw_sp_component_query,
 	.fsm_lock		= mlxsw_sp_fsm_lock,
@@ -302,11 +346,13 @@ static const struct mlxfw_dev_ops mlxsw_sp_mlxfw_dev_ops = {
 	.fsm_activate		= mlxsw_sp_fsm_activate,
 	.fsm_query_state	= mlxsw_sp_fsm_query_state,
 	.fsm_cancel		= mlxsw_sp_fsm_cancel,
-	.fsm_release		= mlxsw_sp_fsm_release
+	.fsm_release		= mlxsw_sp_fsm_release,
+	.status_notify		= mlxsw_sp_status_notify,
 };
 
 static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp,
-				   const struct firmware *firmware)
+				   const struct firmware *firmware,
+				   struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_mlxfw_dev mlxsw_sp_mlxfw_dev = {
 		.mlxfw_dev = {
@@ -319,7 +365,10 @@ static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_core_fw_flash_start(mlxsw_sp->core);
-	err = mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware);
+	devlink_flash_update_begin_notify(priv_to_devlink(mlxsw_sp->core));
+	err = mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev,
+				   firmware, extack);
+	devlink_flash_update_end_notify(priv_to_devlink(mlxsw_sp->core));
 	mlxsw_core_fw_flash_end(mlxsw_sp->core);
 
 	return err;
@@ -373,7 +422,7 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 		return err;
 	}
 
-	err = mlxsw_sp_firmware_flash(mlxsw_sp, firmware);
+	err = mlxsw_sp_firmware_flash(mlxsw_sp, firmware, NULL);
 	release_firmware(firmware);
 	if (err)
 		dev_err(mlxsw_sp->bus_info->dev, "Could not upgrade firmware\n");
@@ -387,6 +436,27 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 		return 0;
 }
 
+static int mlxsw_sp_flash_update(struct mlxsw_core *mlxsw_core,
+				 const char *file_name, const char *component,
+				 struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	const struct firmware *firmware;
+	int err;
+
+	if (component)
+		return -EOPNOTSUPP;
+
+	err = request_firmware_direct(&firmware, file_name,
+				      mlxsw_sp->bus_info->dev);
+	if (err)
+		return err;
+	err = mlxsw_sp_firmware_flash(mlxsw_sp, firmware, extack);
+	release_firmware(firmware);
+
+	return err;
+}
+
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
 			      unsigned int counter_index, u64 *packets,
 			      u64 *bytes)
@@ -737,6 +807,8 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
+	memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
+
 	if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info))
 		return NETDEV_TX_BUSY;
 
@@ -852,8 +924,12 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	u8 pfc_en = !!my_pfc ? my_pfc->pfc_en : 0;
 	u16 delay = !!my_pfc ? my_pfc->delay : 0;
 	char pbmc_pl[MLXSW_REG_PBMC_LEN];
+	u32 taken_headroom_cells = 0;
+	u32 max_headroom_cells;
 	int i, j, err;
 
+	max_headroom_cells = mlxsw_sp_sb_max_headroom_cells(mlxsw_sp);
+
 	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port, 0, 0);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
 	if (err)
@@ -862,8 +938,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		bool configure = false;
 		bool pfc = false;
+		u16 thres_cells;
+		u16 delay_cells;
+		u16 total_cells;
 		bool lossy;
-		u16 thres;
 
 		for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
 			if (prio_tc[j] == i) {
@@ -877,10 +955,17 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 			continue;
 
 		lossy = !(pfc || pause_en);
-		thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
-		delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc,
-						  pause_en);
-		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy);
+		thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+		delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
+							pfc, pause_en);
+		total_cells = thres_cells + delay_cells;
+
+		taken_headroom_cells += total_cells;
+		if (taken_headroom_cells > max_headroom_cells)
+			return -ENOBUFS;
+
+		mlxsw_sp_pg_buf_pack(pbmc_pl, i, total_cells,
+				     thres_cells, lossy);
 	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
@@ -1240,16 +1325,6 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	return 0;
 }
 
-static int mlxsw_sp_port_get_phys_port_name(struct net_device *dev, char *name,
-					    size_t len)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-
-	return mlxsw_core_port_get_phys_port_name(mlxsw_sp_port->mlxsw_sp->core,
-						  mlxsw_sp_port->local_port,
-						  name, len);
-}
-
 static struct mlxsw_sp_port_mall_tc_entry *
 mlxsw_sp_port_mall_tc_entry_find(struct mlxsw_sp_port *port,
 				 unsigned long cookie) {
@@ -1265,21 +1340,19 @@ mlxsw_sp_port_mall_tc_entry_find(struct mlxsw_sp_port *port,
 static int
 mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
 				      struct mlxsw_sp_port_mall_mirror_tc_entry *mirror,
-				      const struct tc_action *a,
+				      const struct flow_action_entry *act,
 				      bool ingress)
 {
 	enum mlxsw_sp_span_type span_type;
-	struct net_device *to_dev;
 
-	to_dev = tcf_mirred_dev(a);
-	if (!to_dev) {
+	if (!act->dev) {
 		netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n");
 		return -EINVAL;
 	}
 
 	mirror->ingress = ingress;
 	span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	return mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_dev, span_type,
+	return mlxsw_sp_span_mirror_add(mlxsw_sp_port, act->dev, span_type,
 					true, &mirror->span_id);
 }
 
@@ -1298,7 +1371,7 @@ mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
 static int
 mlxsw_sp_port_add_cls_matchall_sample(struct mlxsw_sp_port *mlxsw_sp_port,
 				      struct tc_cls_matchall_offload *cls,
-				      const struct tc_action *a,
+				      const struct flow_action_entry *act,
 				      bool ingress)
 {
 	int err;
@@ -1309,18 +1382,18 @@ mlxsw_sp_port_add_cls_matchall_sample(struct mlxsw_sp_port *mlxsw_sp_port,
 		netdev_err(mlxsw_sp_port->dev, "sample already active\n");
 		return -EEXIST;
 	}
-	if (tcf_sample_rate(a) > MLXSW_REG_MPSC_RATE_MAX) {
+	if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
 		netdev_err(mlxsw_sp_port->dev, "sample rate not supported\n");
 		return -EOPNOTSUPP;
 	}
 
 	rcu_assign_pointer(mlxsw_sp_port->sample->psample_group,
-			   tcf_sample_psample_group(a));
-	mlxsw_sp_port->sample->truncate = tcf_sample_truncate(a);
-	mlxsw_sp_port->sample->trunc_size = tcf_sample_trunc_size(a);
-	mlxsw_sp_port->sample->rate = tcf_sample_rate(a);
+			   act->sample.psample_group);
+	mlxsw_sp_port->sample->truncate = act->sample.truncate;
+	mlxsw_sp_port->sample->trunc_size = act->sample.trunc_size;
+	mlxsw_sp_port->sample->rate = act->sample.rate;
 
-	err = mlxsw_sp_port_sample_set(mlxsw_sp_port, true, tcf_sample_rate(a));
+	err = mlxsw_sp_port_sample_set(mlxsw_sp_port, true, act->sample.rate);
 	if (err)
 		goto err_port_sample_set;
 	return 0;
@@ -1346,10 +1419,10 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
 	__be16 protocol = f->common.protocol;
-	const struct tc_action *a;
+	struct flow_action_entry *act;
 	int err;
 
-	if (!tcf_exts_has_one_action(f->exts)) {
+	if (!flow_offload_has_one_action(&f->rule->action)) {
 		netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n");
 		return -EOPNOTSUPP;
 	}
@@ -1359,19 +1432,21 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 		return -ENOMEM;
 	mall_tc_entry->cookie = f->cookie;
 
-	a = tcf_exts_first_action(f->exts);
+	act = &f->rule->action.entries[0];
 
-	if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) {
+	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
 		struct mlxsw_sp_port_mall_mirror_tc_entry *mirror;
 
 		mall_tc_entry->type = MLXSW_SP_PORT_MALL_MIRROR;
 		mirror = &mall_tc_entry->mirror;
 		err = mlxsw_sp_port_add_cls_matchall_mirror(mlxsw_sp_port,
-							    mirror, a, ingress);
-	} else if (is_tcf_sample(a) && protocol == htons(ETH_P_ALL)) {
+							    mirror, act,
+							    ingress);
+	} else if (act->id == FLOW_ACTION_SAMPLE &&
+		   protocol == htons(ETH_P_ALL)) {
 		mall_tc_entry->type = MLXSW_SP_PORT_MALL_SAMPLE;
 		err = mlxsw_sp_port_add_cls_matchall_sample(mlxsw_sp_port, f,
-							    a, ingress);
+							    act, ingress);
 	} else {
 		err = -EOPNOTSUPP;
 	}
@@ -1433,21 +1508,21 @@ static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 
 static int
 mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_acl_block *acl_block,
-			     struct tc_cls_flower_offload *f)
+			     struct flow_cls_offload *f)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_acl_block_mlxsw_sp(acl_block);
 
 	switch (f->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return mlxsw_sp_flower_replace(mlxsw_sp, acl_block, f);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		mlxsw_sp_flower_destroy(mlxsw_sp, acl_block, f);
 		return 0;
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return mlxsw_sp_flower_stats(mlxsw_sp, acl_block, f);
-	case TC_CLSFLOWER_TMPLT_CREATE:
+	case FLOW_CLS_TMPLT_CREATE:
 		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, acl_block, f);
-	case TC_CLSFLOWER_TMPLT_DESTROY:
+	case FLOW_CLS_TMPLT_DESTROY:
 		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, acl_block, f);
 		return 0;
 	default:
@@ -1510,33 +1585,45 @@ static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type,
 	}
 }
 
+static void mlxsw_sp_tc_block_flower_release(void *cb_priv)
+{
+	struct mlxsw_sp_acl_block *acl_block = cb_priv;
+
+	mlxsw_sp_acl_block_destroy(acl_block);
+}
+
+static LIST_HEAD(mlxsw_sp_block_cb_list);
+
 static int
 mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
-				    struct tcf_block *block, bool ingress,
-				    struct netlink_ext_ack *extack)
+			            struct flow_block_offload *f, bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_acl_block *acl_block;
-	struct tcf_block_cb *block_cb;
+	struct flow_block_cb *block_cb;
+	bool register_block = false;
 	int err;
 
-	block_cb = tcf_block_cb_lookup(block, mlxsw_sp_setup_tc_block_cb_flower,
-				       mlxsw_sp);
+	block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+					mlxsw_sp);
 	if (!block_cb) {
-		acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, block->net);
+		acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, f->net);
 		if (!acl_block)
 			return -ENOMEM;
-		block_cb = __tcf_block_cb_register(block,
-						   mlxsw_sp_setup_tc_block_cb_flower,
-						   mlxsw_sp, acl_block, extack);
+		block_cb = flow_block_cb_alloc(f->net,
+					       mlxsw_sp_setup_tc_block_cb_flower,
+					       mlxsw_sp, acl_block,
+					       mlxsw_sp_tc_block_flower_release);
 		if (IS_ERR(block_cb)) {
+			mlxsw_sp_acl_block_destroy(acl_block);
 			err = PTR_ERR(block_cb);
 			goto err_cb_register;
 		}
+		register_block = true;
 	} else {
-		acl_block = tcf_block_cb_priv(block_cb);
+		acl_block = flow_block_cb_priv(block_cb);
 	}
-	tcf_block_cb_incref(block_cb);
+	flow_block_cb_incref(block_cb);
 	err = mlxsw_sp_acl_block_bind(mlxsw_sp, acl_block,
 				      mlxsw_sp_port, ingress);
 	if (err)
@@ -1547,28 +1634,31 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 	else
 		mlxsw_sp_port->eg_acl_block = acl_block;
 
+	if (register_block) {
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlxsw_sp_block_cb_list);
+	}
+
 	return 0;
 
 err_block_bind:
-	if (!tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block, block_cb);
+	if (!flow_block_cb_decref(block_cb))
+		flow_block_cb_free(block_cb);
 err_cb_register:
-		mlxsw_sp_acl_block_destroy(acl_block);
-	}
 	return err;
 }
 
 static void
 mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct tcf_block *block, bool ingress)
+				      struct flow_block_offload *f, bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_acl_block *acl_block;
-	struct tcf_block_cb *block_cb;
+	struct flow_block_cb *block_cb;
 	int err;
 
-	block_cb = tcf_block_cb_lookup(block, mlxsw_sp_setup_tc_block_cb_flower,
-				       mlxsw_sp);
+	block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+					mlxsw_sp);
 	if (!block_cb)
 		return;
 
@@ -1577,50 +1667,63 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 	else
 		mlxsw_sp_port->eg_acl_block = NULL;
 
-	acl_block = tcf_block_cb_priv(block_cb);
+	acl_block = flow_block_cb_priv(block_cb);
 	err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block,
 					mlxsw_sp_port, ingress);
-	if (!err && !tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block, block_cb);
-		mlxsw_sp_acl_block_destroy(acl_block);
+	if (!err && !flow_block_cb_decref(block_cb)) {
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 	}
 }
 
 static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
-				   struct tc_block_offload *f)
+				   struct flow_block_offload *f)
 {
+	struct flow_block_cb *block_cb;
 	tc_setup_cb_t *cb;
 	bool ingress;
 	int err;
 
-	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
 		cb = mlxsw_sp_setup_tc_block_cb_matchall_ig;
 		ingress = true;
-	} else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
+	} else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
 		cb = mlxsw_sp_setup_tc_block_cb_matchall_eg;
 		ingress = false;
 	} else {
 		return -EOPNOTSUPP;
 	}
 
+	f->driver_block_list = &mlxsw_sp_block_cb_list;
+
 	switch (f->command) {
-	case TC_BLOCK_BIND:
-		err = tcf_block_cb_register(f->block, cb, mlxsw_sp_port,
-					    mlxsw_sp_port, f->extack);
-		if (err)
-			return err;
-		err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port,
-							  f->block, ingress,
-							  f->extack);
+	case FLOW_BLOCK_BIND:
+		if (flow_block_cb_is_busy(cb, mlxsw_sp_port,
+					  &mlxsw_sp_block_cb_list))
+			return -EBUSY;
+
+		block_cb = flow_block_cb_alloc(f->net, cb, mlxsw_sp_port,
+					       mlxsw_sp_port, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+		err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port, f,
+							  ingress);
 		if (err) {
-			tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
+			flow_block_cb_free(block_cb);
 			return err;
 		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlxsw_sp_block_cb_list);
 		return 0;
-	case TC_BLOCK_UNBIND:
+	case FLOW_BLOCK_UNBIND:
 		mlxsw_sp_setup_tc_block_flower_unbind(mlxsw_sp_port,
-						      f->block, ingress);
-		tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
+						      f, ingress);
+		block_cb = flow_block_cb_lookup(f, cb, mlxsw_sp_port);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -1665,6 +1768,25 @@ static int mlxsw_sp_feature_hw_tc(struct net_device *dev, bool enable)
 	return 0;
 }
 
+static int mlxsw_sp_feature_loopback(struct net_device *dev, bool enable)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	char pplr_pl[MLXSW_REG_PPLR_LEN];
+	int err;
+
+	if (netif_running(dev))
+		mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
+
+	mlxsw_reg_pplr_pack(pplr_pl, mlxsw_sp_port->local_port, enable);
+	err = mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pplr),
+			      pplr_pl);
+
+	if (netif_running(dev))
+		mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
+
+	return err;
+}
+
 typedef int (*mlxsw_sp_feature_handler)(struct net_device *dev, bool enable);
 
 static int mlxsw_sp_handle_feature(struct net_device *dev,
@@ -1696,8 +1818,89 @@ static int mlxsw_sp_handle_feature(struct net_device *dev,
 static int mlxsw_sp_set_features(struct net_device *dev,
 				 netdev_features_t features)
 {
-	return mlxsw_sp_handle_feature(dev, features, NETIF_F_HW_TC,
+	netdev_features_t oper_features = dev->features;
+	int err = 0;
+
+	err |= mlxsw_sp_handle_feature(dev, features, NETIF_F_HW_TC,
 				       mlxsw_sp_feature_hw_tc);
+	err |= mlxsw_sp_handle_feature(dev, features, NETIF_F_LOOPBACK,
+				       mlxsw_sp_feature_loopback);
+
+	if (err) {
+		dev->features = oper_features;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct devlink_port *
+mlxsw_sp_port_get_devlink_port(struct net_device *dev)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+
+	return mlxsw_core_port_devlink_port_get(mlxsw_sp->core,
+						mlxsw_sp_port->local_port);
+}
+
+static int mlxsw_sp_port_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				      struct ifreq *ifr)
+{
+	struct hwtstamp_config config;
+	int err;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port,
+							     &config);
+	if (err)
+		return err;
+
+	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int mlxsw_sp_port_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
+				      struct ifreq *ifr)
+{
+	struct hwtstamp_config config;
+	int err;
+
+	err = mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_get(mlxsw_sp_port,
+							     &config);
+	if (err)
+		return err;
+
+	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static inline void mlxsw_sp_port_ptp_clear(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct hwtstamp_config config = {0};
+
+	mlxsw_sp_port->mlxsw_sp->ptp_ops->hwtstamp_set(mlxsw_sp_port, &config);
+}
+
+static int
+mlxsw_sp_port_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+
+	switch (cmd) {
+	case SIOCSHWTSTAMP:
+		return mlxsw_sp_port_hwtstamp_set(mlxsw_sp_port, ifr);
+	case SIOCGHWTSTAMP:
+		return mlxsw_sp_port_hwtstamp_get(mlxsw_sp_port, ifr);
+	default:
+		return -EOPNOTSUPP;
+	}
 }
 
 static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
@@ -1713,8 +1916,9 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_get_offload_stats	= mlxsw_sp_port_get_offload_stats,
 	.ndo_vlan_rx_add_vid	= mlxsw_sp_port_add_vid,
 	.ndo_vlan_rx_kill_vid	= mlxsw_sp_port_kill_vid,
-	.ndo_get_phys_port_name	= mlxsw_sp_port_get_phys_port_name,
 	.ndo_set_features	= mlxsw_sp_set_features,
+	.ndo_get_devlink_port	= mlxsw_sp_port_get_devlink_port,
+	.ndo_do_ioctl		= mlxsw_sp_port_ioctl,
 };
 
 static void mlxsw_sp_port_get_drvinfo(struct net_device *dev,
@@ -2103,7 +2307,7 @@ static void mlxsw_sp_port_get_prio_strings(u8 **p, int prio)
 	int i;
 
 	for (i = 0; i < MLXSW_SP_PORT_HW_PRIO_STATS_LEN; i++) {
-		snprintf(*p, ETH_GSTRING_LEN, "%s_%d",
+		snprintf(*p, ETH_GSTRING_LEN, "%.29s_%.1d",
 			 mlxsw_sp_port_hw_prio_stats[i].str, prio);
 		*p += ETH_GSTRING_LEN;
 	}
@@ -2114,7 +2318,7 @@ static void mlxsw_sp_port_get_tc_strings(u8 **p, int tc)
 	int i;
 
 	for (i = 0; i < MLXSW_SP_PORT_HW_TC_STATS_LEN; i++) {
-		snprintf(*p, ETH_GSTRING_LEN, "%s_%d",
+		snprintf(*p, ETH_GSTRING_LEN, "%.29s_%.1d",
 			 mlxsw_sp_port_hw_tc_stats[i].str, tc);
 		*p += ETH_GSTRING_LEN;
 	}
@@ -2310,13 +2514,13 @@ static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
-struct mlxsw_sp_port_link_mode {
+struct mlxsw_sp1_port_link_mode {
 	enum ethtool_link_mode_bit_indices mask_ethtool;
 	u32 mask;
 	u32 speed;
 };
 
-static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
+static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = {
 	{
 		.mask		= MLXSW_REG_PTYS_ETH_SPEED_100BASE_T,
 		.mask_ethtool	= ETHTOOL_LINK_MODE_100baseT_Full_BIT,
@@ -2388,11 +2592,6 @@ static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
 		.speed		= SPEED_25000,
 	},
 	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR,
-		.mask_ethtool	= ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
-		.speed		= SPEED_25000,
-	},
-	{
 		.mask		= MLXSW_REG_PTYS_ETH_SPEED_50GBASE_CR2,
 		.mask_ethtool	= ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
 		.speed		= SPEED_50000,
@@ -2449,11 +2648,12 @@ static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
 	},
 };
 
-#define MLXSW_SP_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp_port_link_mode)
+#define MLXSW_SP1_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp1_port_link_mode)
 
 static void
-mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto,
-				  struct ethtool_link_ksettings *cmd)
+mlxsw_sp1_from_ptys_supported_port(struct mlxsw_sp *mlxsw_sp,
+				   u32 ptys_eth_proto,
+				   struct ethtool_link_ksettings *cmd)
 {
 	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
 			      MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
@@ -2471,162 +2671,608 @@ mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto,
 		ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
 }
 
-static void mlxsw_sp_from_ptys_link(u32 ptys_eth_proto, unsigned long *mode)
+static void
+mlxsw_sp1_from_ptys_link(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto,
+			 unsigned long *mode)
 {
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask)
-			__set_bit(mlxsw_sp_port_link_mode[i].mask_ethtool,
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask)
+			__set_bit(mlxsw_sp1_port_link_mode[i].mask_ethtool,
 				  mode);
 	}
 }
 
-static void mlxsw_sp_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto,
-					    struct ethtool_link_ksettings *cmd)
+static u32
+mlxsw_sp1_from_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto)
 {
-	u32 speed = SPEED_UNKNOWN;
-	u8 duplex = DUPLEX_UNKNOWN;
 	int i;
 
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask)
+			return mlxsw_sp1_port_link_mode[i].speed;
+	}
+
+	return SPEED_UNKNOWN;
+}
+
+static void
+mlxsw_sp1_from_ptys_speed_duplex(struct mlxsw_sp *mlxsw_sp, bool carrier_ok,
+				 u32 ptys_eth_proto,
+				 struct ethtool_link_ksettings *cmd)
+{
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
+
 	if (!carrier_ok)
-		goto out;
+		return;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask) {
-			speed = mlxsw_sp_port_link_mode[i].speed;
-			duplex = DUPLEX_FULL;
-			break;
-		}
+	cmd->base.speed = mlxsw_sp1_from_ptys_speed(mlxsw_sp, ptys_eth_proto);
+	if (cmd->base.speed != SPEED_UNKNOWN)
+		cmd->base.duplex = DUPLEX_FULL;
+}
+
+static u32
+mlxsw_sp1_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp,
+			      const struct ethtool_link_ksettings *cmd)
+{
+	u32 ptys_proto = 0;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (test_bit(mlxsw_sp1_port_link_mode[i].mask_ethtool,
+			     cmd->link_modes.advertising))
+			ptys_proto |= mlxsw_sp1_port_link_mode[i].mask;
 	}
-out:
-	cmd->base.speed = speed;
-	cmd->base.duplex = duplex;
+	return ptys_proto;
 }
 
-static u8 mlxsw_sp_port_connector_port(u32 ptys_eth_proto)
+static u32 mlxsw_sp1_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 speed)
 {
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_SGMII))
-		return PORT_FIBRE;
+	u32 ptys_proto = 0;
+	int i;
 
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4))
-		return PORT_DA;
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (speed == mlxsw_sp1_port_link_mode[i].speed)
+			ptys_proto |= mlxsw_sp1_port_link_mode[i].mask;
+	}
+	return ptys_proto;
+}
 
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
-			      MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4))
-		return PORT_NONE;
+static u32
+mlxsw_sp1_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed)
+{
+	u32 ptys_proto = 0;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (mlxsw_sp1_port_link_mode[i].speed <= upper_speed)
+			ptys_proto |= mlxsw_sp1_port_link_mode[i].mask;
+	}
+	return ptys_proto;
+}
+
+static int
+mlxsw_sp1_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+			  u32 *base_speed)
+{
+	*base_speed = MLXSW_SP_PORT_BASE_SPEED_25G;
+	return 0;
+}
+
+static void
+mlxsw_sp1_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			    u8 local_port, u32 proto_admin, bool autoneg)
+{
+	mlxsw_reg_ptys_eth_pack(payload, local_port, proto_admin, autoneg);
+}
+
+static void
+mlxsw_sp1_reg_ptys_eth_unpack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			      u32 *p_eth_proto_cap, u32 *p_eth_proto_admin,
+			      u32 *p_eth_proto_oper)
+{
+	mlxsw_reg_ptys_eth_unpack(payload, p_eth_proto_cap, p_eth_proto_admin,
+				  p_eth_proto_oper);
+}
+
+static const struct mlxsw_sp_port_type_speed_ops
+mlxsw_sp1_port_type_speed_ops = {
+	.from_ptys_supported_port	= mlxsw_sp1_from_ptys_supported_port,
+	.from_ptys_link			= mlxsw_sp1_from_ptys_link,
+	.from_ptys_speed		= mlxsw_sp1_from_ptys_speed,
+	.from_ptys_speed_duplex		= mlxsw_sp1_from_ptys_speed_duplex,
+	.to_ptys_advert_link		= mlxsw_sp1_to_ptys_advert_link,
+	.to_ptys_speed			= mlxsw_sp1_to_ptys_speed,
+	.to_ptys_upper_speed		= mlxsw_sp1_to_ptys_upper_speed,
+	.port_speed_base		= mlxsw_sp1_port_speed_base,
+	.reg_ptys_eth_pack		= mlxsw_sp1_reg_ptys_eth_pack,
+	.reg_ptys_eth_unpack		= mlxsw_sp1_reg_ptys_eth_unpack,
+};
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_sgmii_100m[] = {
+	ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_SGMII_100M_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_sgmii_100m)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_1000base_x_sgmii[] = {
+	ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_1000BASE_X_SGMII_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_1000base_x_sgmii)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii[] = {
+	ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_5gbase_r[] = {
+	ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_5gbase_r)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_xfi_xaui_1_10g[] = {
+	ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+	ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_XFI_XAUI_1_10G_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_xfi_xaui_1_10g)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g[] = {
+	ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_XLAUI_4_XLPPI_4_40G_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_25gaui_1_25gbase_cr_kr[] = {
+	ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_25GAUI_1_25GBASE_CR_KR_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_25gaui_1_25gbase_cr_kr)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2[] = {
+	ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_50GAUI_2_LAUI_2_50GBASE_CR2_KR2_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_50gaui_1_laui_1_50gbase_cr_kr[] = {
+	ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseDR_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_50GAUI_1_LAUI_1_50GBASE_CR_KR_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_50gaui_1_laui_1_50gbase_cr_kr)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4[] = {
+	ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_CAUI_4_100GBASE_CR4_KR4_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2[] = {
+	ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_100GAUI_2_100GBASE_CR2_KR2_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4[] = {
+	ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4)
+
+struct mlxsw_sp2_port_link_mode {
+	const enum ethtool_link_mode_bit_indices *mask_ethtool;
+	int m_ethtool_len;
+	u32 mask;
+	u32 speed;
+};
+
+static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = {
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_SGMII_100M,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_sgmii_100m,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_SGMII_100M_LEN,
+		.speed		= SPEED_100,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_1000BASE_X_SGMII,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_1000base_x_sgmii,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_1000BASE_X_SGMII_LEN,
+		.speed		= SPEED_1000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN,
+		.speed		= SPEED_2500,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_5gbase_r,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN,
+		.speed		= SPEED_5000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_XFI_XAUI_1_10G,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_xfi_xaui_1_10g,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_XFI_XAUI_1_10G_LEN,
+		.speed		= SPEED_10000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_XLAUI_4_XLPPI_4_40G_LEN,
+		.speed		= SPEED_40000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_25gaui_1_25gbase_cr_kr,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_25GAUI_1_25GBASE_CR_KR_LEN,
+		.speed		= SPEED_25000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_2_LAUI_2_50GBASE_CR2_KR2,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_50GAUI_2_LAUI_2_50GBASE_CR2_KR2_LEN,
+		.speed		= SPEED_50000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_50gaui_1_laui_1_50gbase_cr_kr,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_50GAUI_1_LAUI_1_50GBASE_CR_KR_LEN,
+		.speed		= SPEED_50000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_CAUI_4_100GBASE_CR4_KR4_LEN,
+		.speed		= SPEED_100000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_100GAUI_2_100GBASE_CR2_KR2_LEN,
+		.speed		= SPEED_100000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN,
+		.speed		= SPEED_200000,
+	},
+};
+
+#define MLXSW_SP2_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp2_port_link_mode)
+
+static void
+mlxsw_sp2_from_ptys_supported_port(struct mlxsw_sp *mlxsw_sp,
+				   u32 ptys_eth_proto,
+				   struct ethtool_link_ksettings *cmd)
+{
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
+}
+
+static void
+mlxsw_sp2_set_bit_ethtool(const struct mlxsw_sp2_port_link_mode *link_mode,
+			  unsigned long *mode)
+{
+	int i;
+
+	for (i = 0; i < link_mode->m_ethtool_len; i++)
+		__set_bit(link_mode->mask_ethtool[i], mode);
+}
+
+static void
+mlxsw_sp2_from_ptys_link(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto,
+			 unsigned long *mode)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask)
+			mlxsw_sp2_set_bit_ethtool(&mlxsw_sp2_port_link_mode[i],
+						  mode);
+	}
+}
+
+static u32
+mlxsw_sp2_from_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask)
+			return mlxsw_sp2_port_link_mode[i].speed;
+	}
+
+	return SPEED_UNKNOWN;
+}
+
+static void
+mlxsw_sp2_from_ptys_speed_duplex(struct mlxsw_sp *mlxsw_sp, bool carrier_ok,
+				 u32 ptys_eth_proto,
+				 struct ethtool_link_ksettings *cmd)
+{
+	cmd->base.speed = SPEED_UNKNOWN;
+	cmd->base.duplex = DUPLEX_UNKNOWN;
+
+	if (!carrier_ok)
+		return;
+
+	cmd->base.speed = mlxsw_sp2_from_ptys_speed(mlxsw_sp, ptys_eth_proto);
+	if (cmd->base.speed != SPEED_UNKNOWN)
+		cmd->base.duplex = DUPLEX_FULL;
+}
+
+static bool
+mlxsw_sp2_test_bit_ethtool(const struct mlxsw_sp2_port_link_mode *link_mode,
+			   const unsigned long *mode)
+{
+	int cnt = 0;
+	int i;
+
+	for (i = 0; i < link_mode->m_ethtool_len; i++) {
+		if (test_bit(link_mode->mask_ethtool[i], mode))
+			cnt++;
+	}
 
-	return PORT_OTHER;
+	return cnt == link_mode->m_ethtool_len;
 }
 
 static u32
-mlxsw_sp_to_ptys_advert_link(const struct ethtool_link_ksettings *cmd)
+mlxsw_sp2_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp,
+			      const struct ethtool_link_ksettings *cmd)
 {
 	u32 ptys_proto = 0;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (test_bit(mlxsw_sp_port_link_mode[i].mask_ethtool,
-			     cmd->link_modes.advertising))
-			ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (mlxsw_sp2_test_bit_ethtool(&mlxsw_sp2_port_link_mode[i],
+					       cmd->link_modes.advertising))
+			ptys_proto |= mlxsw_sp2_port_link_mode[i].mask;
 	}
 	return ptys_proto;
 }
 
-static u32 mlxsw_sp_to_ptys_speed(u32 speed)
+static u32 mlxsw_sp2_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 speed)
 {
 	u32 ptys_proto = 0;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (speed == mlxsw_sp_port_link_mode[i].speed)
-			ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (speed == mlxsw_sp2_port_link_mode[i].speed)
+			ptys_proto |= mlxsw_sp2_port_link_mode[i].mask;
 	}
 	return ptys_proto;
 }
 
-static u32 mlxsw_sp_to_ptys_upper_speed(u32 upper_speed)
+static u32
+mlxsw_sp2_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed)
 {
 	u32 ptys_proto = 0;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (mlxsw_sp_port_link_mode[i].speed <= upper_speed)
-			ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (mlxsw_sp2_port_link_mode[i].speed <= upper_speed)
+			ptys_proto |= mlxsw_sp2_port_link_mode[i].mask;
 	}
 	return ptys_proto;
 }
 
-static void mlxsw_sp_port_get_link_supported(u32 eth_proto_cap,
-					     struct ethtool_link_ksettings *cmd)
+static int
+mlxsw_sp2_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+			  u32 *base_speed)
+{
+	char ptys_pl[MLXSW_REG_PTYS_LEN];
+	u32 eth_proto_cap;
+	int err;
+
+	/* In Spectrum-2, the speed of 1x can change from port to port, so query
+	 * it from firmware.
+	 */
+	mlxsw_reg_ptys_ext_eth_pack(ptys_pl, local_port, 0, false);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
+	if (err)
+		return err;
+	mlxsw_reg_ptys_ext_eth_unpack(ptys_pl, &eth_proto_cap, NULL, NULL);
+
+	if (eth_proto_cap &
+	    MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR) {
+		*base_speed = MLXSW_SP_PORT_BASE_SPEED_50G;
+		return 0;
+	}
+
+	if (eth_proto_cap &
+	    MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR) {
+		*base_speed = MLXSW_SP_PORT_BASE_SPEED_25G;
+		return 0;
+	}
+
+	return -EIO;
+}
+
+static void
+mlxsw_sp2_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			    u8 local_port, u32 proto_admin,
+			    bool autoneg)
+{
+	mlxsw_reg_ptys_ext_eth_pack(payload, local_port, proto_admin, autoneg);
+}
+
+static void
+mlxsw_sp2_reg_ptys_eth_unpack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			      u32 *p_eth_proto_cap, u32 *p_eth_proto_admin,
+			      u32 *p_eth_proto_oper)
+{
+	mlxsw_reg_ptys_ext_eth_unpack(payload, p_eth_proto_cap,
+				      p_eth_proto_admin, p_eth_proto_oper);
+}
+
+static const struct mlxsw_sp_port_type_speed_ops
+mlxsw_sp2_port_type_speed_ops = {
+	.from_ptys_supported_port	= mlxsw_sp2_from_ptys_supported_port,
+	.from_ptys_link			= mlxsw_sp2_from_ptys_link,
+	.from_ptys_speed		= mlxsw_sp2_from_ptys_speed,
+	.from_ptys_speed_duplex		= mlxsw_sp2_from_ptys_speed_duplex,
+	.to_ptys_advert_link		= mlxsw_sp2_to_ptys_advert_link,
+	.to_ptys_speed			= mlxsw_sp2_to_ptys_speed,
+	.to_ptys_upper_speed		= mlxsw_sp2_to_ptys_upper_speed,
+	.port_speed_base		= mlxsw_sp2_port_speed_base,
+	.reg_ptys_eth_pack		= mlxsw_sp2_reg_ptys_eth_pack,
+	.reg_ptys_eth_unpack		= mlxsw_sp2_reg_ptys_eth_unpack,
+};
+
+static void
+mlxsw_sp_port_get_link_supported(struct mlxsw_sp *mlxsw_sp, u32 eth_proto_cap,
+				 struct ethtool_link_ksettings *cmd)
 {
+	const struct mlxsw_sp_port_type_speed_ops *ops;
+
+	ops = mlxsw_sp->port_type_speed_ops;
+
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Asym_Pause);
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
 
-	mlxsw_sp_from_ptys_supported_port(eth_proto_cap, cmd);
-	mlxsw_sp_from_ptys_link(eth_proto_cap, cmd->link_modes.supported);
+	ops->from_ptys_supported_port(mlxsw_sp, eth_proto_cap, cmd);
+	ops->from_ptys_link(mlxsw_sp, eth_proto_cap, cmd->link_modes.supported);
 }
 
-static void mlxsw_sp_port_get_link_advertise(u32 eth_proto_admin, bool autoneg,
-					     struct ethtool_link_ksettings *cmd)
+static void
+mlxsw_sp_port_get_link_advertise(struct mlxsw_sp *mlxsw_sp,
+				 u32 eth_proto_admin, bool autoneg,
+				 struct ethtool_link_ksettings *cmd)
 {
+	const struct mlxsw_sp_port_type_speed_ops *ops;
+
+	ops = mlxsw_sp->port_type_speed_ops;
+
 	if (!autoneg)
 		return;
 
 	ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
-	mlxsw_sp_from_ptys_link(eth_proto_admin, cmd->link_modes.advertising);
+	ops->from_ptys_link(mlxsw_sp, eth_proto_admin,
+			    cmd->link_modes.advertising);
 }
 
-static void
-mlxsw_sp_port_get_link_lp_advertise(u32 eth_proto_lp, u8 autoneg_status,
-				    struct ethtool_link_ksettings *cmd)
+static u8
+mlxsw_sp_port_connector_port(enum mlxsw_reg_ptys_connector_type connector_type)
 {
-	if (autoneg_status != MLXSW_REG_PTYS_AN_STATUS_OK || !eth_proto_lp)
-		return;
-
-	ethtool_link_ksettings_add_link_mode(cmd, lp_advertising, Autoneg);
-	mlxsw_sp_from_ptys_link(eth_proto_lp, cmd->link_modes.lp_advertising);
+	switch (connector_type) {
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_UNKNOWN_OR_NO_CONNECTOR:
+		return PORT_OTHER;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_NONE:
+		return PORT_NONE;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_TP:
+		return PORT_TP;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_AUI:
+		return PORT_AUI;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_BNC:
+		return PORT_BNC;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_MII:
+		return PORT_MII;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_FIBRE:
+		return PORT_FIBRE;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_DA:
+		return PORT_DA;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_OTHER:
+		return PORT_OTHER;
+	default:
+		WARN_ON_ONCE(1);
+		return PORT_OTHER;
+	}
 }
 
 static int mlxsw_sp_port_get_link_ksettings(struct net_device *dev,
 					    struct ethtool_link_ksettings *cmd)
 {
-	u32 eth_proto_cap, eth_proto_admin, eth_proto_oper, eth_proto_lp;
+	u32 eth_proto_cap, eth_proto_admin, eth_proto_oper;
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	const struct mlxsw_sp_port_type_speed_ops *ops;
 	char ptys_pl[MLXSW_REG_PTYS_LEN];
-	u8 autoneg_status;
+	u8 connector_type;
 	bool autoneg;
 	int err;
 
+	ops = mlxsw_sp->port_type_speed_ops;
+
 	autoneg = mlxsw_sp_port->link.autoneg;
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port, 0, false);
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       0, false);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 	if (err)
 		return err;
-	mlxsw_reg_ptys_eth_unpack(ptys_pl, &eth_proto_cap, &eth_proto_admin,
-				  &eth_proto_oper);
-
-	mlxsw_sp_port_get_link_supported(eth_proto_cap, cmd);
+	ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, &eth_proto_cap,
+				 &eth_proto_admin, &eth_proto_oper);
 
-	mlxsw_sp_port_get_link_advertise(eth_proto_admin, autoneg, cmd);
+	mlxsw_sp_port_get_link_supported(mlxsw_sp, eth_proto_cap, cmd);
 
-	eth_proto_lp = mlxsw_reg_ptys_eth_proto_lp_advertise_get(ptys_pl);
-	autoneg_status = mlxsw_reg_ptys_an_status_get(ptys_pl);
-	mlxsw_sp_port_get_link_lp_advertise(eth_proto_lp, autoneg_status, cmd);
+	mlxsw_sp_port_get_link_advertise(mlxsw_sp, eth_proto_admin, autoneg,
+					 cmd);
 
 	cmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
-	cmd->base.port = mlxsw_sp_port_connector_port(eth_proto_oper);
-	mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev), eth_proto_oper,
-					cmd);
+	connector_type = mlxsw_reg_ptys_connector_type_get(ptys_pl);
+	cmd->base.port = mlxsw_sp_port_connector_port(connector_type);
+	ops->from_ptys_speed_duplex(mlxsw_sp, netif_carrier_ok(dev),
+				    eth_proto_oper, cmd);
 
 	return 0;
 }
@@ -2637,21 +3283,29 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	const struct mlxsw_sp_port_type_speed_ops *ops;
 	char ptys_pl[MLXSW_REG_PTYS_LEN];
 	u32 eth_proto_cap, eth_proto_new;
 	bool autoneg;
 	int err;
 
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port, 0, false);
+	ops = mlxsw_sp->port_type_speed_ops;
+
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       0, false);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 	if (err)
 		return err;
-	mlxsw_reg_ptys_eth_unpack(ptys_pl, &eth_proto_cap, NULL, NULL);
+	ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, &eth_proto_cap, NULL, NULL);
 
 	autoneg = cmd->base.autoneg == AUTONEG_ENABLE;
+	if (!autoneg && cmd->base.speed == SPEED_56000) {
+		netdev_err(dev, "56G not supported with autoneg off\n");
+		return -EINVAL;
+	}
 	eth_proto_new = autoneg ?
-		mlxsw_sp_to_ptys_advert_link(cmd) :
-		mlxsw_sp_to_ptys_speed(cmd->base.speed);
+		ops->to_ptys_advert_link(mlxsw_sp, cmd) :
+		ops->to_ptys_speed(mlxsw_sp, cmd->base.speed);
 
 	eth_proto_new = eth_proto_new & eth_proto_cap;
 	if (!eth_proto_new) {
@@ -2659,159 +3313,35 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port,
-				eth_proto_new, autoneg);
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       eth_proto_new, autoneg);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 	if (err)
 		return err;
 
+	mlxsw_sp_port->link.autoneg = autoneg;
+
 	if (!netif_running(dev))
 		return 0;
 
-	mlxsw_sp_port->link.autoneg = autoneg;
-
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
 
 	return 0;
 }
 
-static int mlxsw_sp_flash_device(struct net_device *dev,
-				 struct ethtool_flash *flash)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	const struct firmware *firmware;
-	int err;
-
-	if (flash->region != ETHTOOL_FLASH_ALL_REGIONS)
-		return -EOPNOTSUPP;
-
-	dev_hold(dev);
-	rtnl_unlock();
-
-	err = request_firmware_direct(&firmware, flash->data, &dev->dev);
-	if (err)
-		goto out;
-	err = mlxsw_sp_firmware_flash(mlxsw_sp, firmware);
-	release_firmware(firmware);
-out:
-	rtnl_lock();
-	dev_put(dev);
-	return err;
-}
-
-#define MLXSW_SP_I2C_ADDR_LOW 0x50
-#define MLXSW_SP_I2C_ADDR_HIGH 0x51
-#define MLXSW_SP_EEPROM_PAGE_LENGTH 256
-
-static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
-					u16 offset, u16 size, void *data,
-					unsigned int *p_read_size)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char eeprom_tmp[MLXSW_SP_REG_MCIA_EEPROM_SIZE];
-	char mcia_pl[MLXSW_REG_MCIA_LEN];
-	u16 i2c_addr;
-	int status;
-	int err;
-
-	size = min_t(u16, size, MLXSW_SP_REG_MCIA_EEPROM_SIZE);
-
-	if (offset < MLXSW_SP_EEPROM_PAGE_LENGTH &&
-	    offset + size > MLXSW_SP_EEPROM_PAGE_LENGTH)
-		/* Cross pages read, read until offset 256 in low page */
-		size = MLXSW_SP_EEPROM_PAGE_LENGTH - offset;
-
-	i2c_addr = MLXSW_SP_I2C_ADDR_LOW;
-	if (offset >= MLXSW_SP_EEPROM_PAGE_LENGTH) {
-		i2c_addr = MLXSW_SP_I2C_ADDR_HIGH;
-		offset -= MLXSW_SP_EEPROM_PAGE_LENGTH;
-	}
-
-	mlxsw_reg_mcia_pack(mcia_pl, mlxsw_sp_port->mapping.module,
-			    0, 0, offset, size, i2c_addr);
-
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mcia), mcia_pl);
-	if (err)
-		return err;
-
-	status = mlxsw_reg_mcia_status_get(mcia_pl);
-	if (status)
-		return -EIO;
-
-	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
-	memcpy(data, eeprom_tmp, size);
-	*p_read_size = size;
-
-	return 0;
-}
-
-enum mlxsw_sp_eeprom_module_info_rev_id {
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_UNSPC      = 0x00,
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8436       = 0x01,
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636       = 0x03,
-};
-
-enum mlxsw_sp_eeprom_module_info_id {
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP              = 0x03,
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP             = 0x0C,
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS        = 0x0D,
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28           = 0x11,
-};
-
-enum mlxsw_sp_eeprom_module_info {
-	MLXSW_SP_EEPROM_MODULE_INFO_ID,
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID,
-	MLXSW_SP_EEPROM_MODULE_INFO_SIZE,
-};
-
 static int mlxsw_sp_get_module_info(struct net_device *netdev,
 				    struct ethtool_modinfo *modinfo)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
-	u8 module_info[MLXSW_SP_EEPROM_MODULE_INFO_SIZE];
-	u8 module_rev_id, module_id;
-	unsigned int read_size;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	int err;
 
-	err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, 0,
-					   MLXSW_SP_EEPROM_MODULE_INFO_SIZE,
-					   module_info, &read_size);
-	if (err)
-		return err;
-
-	if (read_size < MLXSW_SP_EEPROM_MODULE_INFO_SIZE)
-		return -EIO;
-
-	module_rev_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_REV_ID];
-	module_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_ID];
-
-	switch (module_id) {
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP:
-		modinfo->type       = ETH_MODULE_SFF_8436;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
-		break;
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS:
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28:
-		if (module_id  == MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28 ||
-		    module_rev_id >= MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636) {
-			modinfo->type       = ETH_MODULE_SFF_8636;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
-		} else {
-			modinfo->type       = ETH_MODULE_SFF_8436;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
-		}
-		break;
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP:
-		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
-		break;
-	default:
-		return -EINVAL;
-	}
+	err = mlxsw_env_get_module_info(mlxsw_sp->core,
+					mlxsw_sp_port->mapping.module,
+					modinfo);
 
-	return 0;
+	return err;
 }
 
 static int mlxsw_sp_get_module_eeprom(struct net_device *netdev,
@@ -2819,30 +3349,23 @@ static int mlxsw_sp_get_module_eeprom(struct net_device *netdev,
 				      u8 *data)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
-	int offset = ee->offset;
-	unsigned int read_size;
-	int i = 0;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	int err;
 
-	if (!ee->len)
-		return -EINVAL;
-
-	memset(data, 0, ee->len);
+	err = mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core,
+					  mlxsw_sp_port->mapping.module, ee,
+					  data);
 
-	while (i < ee->len) {
-		err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, offset,
-						   ee->len - i, data + i,
-						   &read_size);
-		if (err) {
-			netdev_err(mlxsw_sp_port->dev, "Eeprom query failed\n");
-			return err;
-		}
+	return err;
+}
 
-		i += read_size;
-		offset += read_size;
-	}
+static int
+mlxsw_sp_get_ts_info(struct net_device *netdev, struct ethtool_ts_info *info)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 
-	return 0;
+	return mlxsw_sp->ptp_ops->get_ts_info(mlxsw_sp, info);
 }
 
 static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
@@ -2856,22 +3379,33 @@ static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
 	.get_sset_count		= mlxsw_sp_port_get_sset_count,
 	.get_link_ksettings	= mlxsw_sp_port_get_link_ksettings,
 	.set_link_ksettings	= mlxsw_sp_port_set_link_ksettings,
-	.flash_device		= mlxsw_sp_flash_device,
 	.get_module_info	= mlxsw_sp_get_module_info,
 	.get_module_eeprom	= mlxsw_sp_get_module_eeprom,
+	.get_ts_info		= mlxsw_sp_get_ts_info,
 };
 
 static int
 mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	u32 upper_speed = MLXSW_SP_PORT_BASE_SPEED * width;
+	const struct mlxsw_sp_port_type_speed_ops *ops;
 	char ptys_pl[MLXSW_REG_PTYS_LEN];
 	u32 eth_proto_admin;
+	u32 upper_speed;
+	u32 base_speed;
+	int err;
+
+	ops = mlxsw_sp->port_type_speed_ops;
+
+	err = ops->port_speed_base(mlxsw_sp, mlxsw_sp_port->local_port,
+				   &base_speed);
+	if (err)
+		return err;
+	upper_speed = base_speed * width;
 
-	eth_proto_admin = mlxsw_sp_to_ptys_upper_speed(upper_speed);
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port,
-				eth_proto_admin, mlxsw_sp_port->link.autoneg);
+	eth_proto_admin = ops->to_ptys_upper_speed(mlxsw_sp, upper_speed);
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       eth_proto_admin, mlxsw_sp_port->link.autoneg);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 }
 
@@ -2959,13 +3493,14 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
 					    MLXSW_REG_QEEC_HIERARCY_TC,
 					    i + 8, i,
-					    false, 0);
+					    true, 100);
 		if (err)
 			return err;
 	}
 
-	/* Make sure the max shaper is disabled in all hierarchies that
-	 * support it.
+	/* Make sure the max shaper is disabled in all hierarchies that support
+	 * it. Note that this disables ptps (PTP shaper), but that is intended
+	 * for the initial configuration.
 	 */
 	err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
 					    MLXSW_REG_QEEC_HIERARCY_PORT, 0, 0,
@@ -3034,7 +3569,10 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	struct net_device *dev;
 	int err;
 
-	err = mlxsw_core_port_init(mlxsw_sp->core, local_port);
+	err = mlxsw_core_port_init(mlxsw_sp->core, local_port,
+				   module + 1, split, lane / width,
+				   mlxsw_sp->base_mac,
+				   sizeof(mlxsw_sp->base_mac));
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n",
 			local_port);
@@ -3105,7 +3643,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG |
 			 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC;
-	dev->hw_features |= NETIF_F_HW_TC;
+	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
 
 	dev->min_mtu = 0;
 	dev->max_mtu = ETH_MAX_MTU;
@@ -3207,7 +3745,9 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	}
 	mlxsw_sp_port->default_vlan = mlxsw_sp_port_vlan;
 
-	mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
+	INIT_DELAYED_WORK(&mlxsw_sp_port->ptp.shaper_dw,
+			  mlxsw_sp->ptp_ops->shaper_work);
+
 	mlxsw_sp->ports[local_port] = mlxsw_sp_port;
 	err = register_netdev(dev);
 	if (err) {
@@ -3217,14 +3757,12 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	}
 
 	mlxsw_core_port_eth_set(mlxsw_sp->core, mlxsw_sp_port->local_port,
-				mlxsw_sp_port, dev, module + 1,
-				mlxsw_sp_port->split, lane / width);
+				mlxsw_sp_port, dev);
 	mlxsw_core_schedule_dw(&mlxsw_sp_port->periodic_hw_stats.update_dw, 0);
 	return 0;
 
 err_register_netdev:
 	mlxsw_sp->ports[local_port] = NULL;
-	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
 	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 err_port_vlan_create:
 err_port_pvid_set:
@@ -3264,10 +3802,11 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
 
 	cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw);
+	cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw);
+	mlxsw_sp_port_ptp_clear(mlxsw_sp_port);
 	mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
 	mlxsw_sp->ports[local_port] = NULL;
-	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
 	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
 	mlxsw_sp_port_nve_fini(mlxsw_sp_port);
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
@@ -3356,14 +3895,14 @@ static u8 mlxsw_sp_cluster_base_port_get(u8 local_port)
 }
 
 static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port,
-				      u8 module, unsigned int count)
+				      u8 module, unsigned int count, u8 offset)
 {
 	u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count;
 	int err, i;
 
 	for (i = 0; i < count; i++) {
-		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true,
-					   module, width, i * width);
+		err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * offset,
+					   true, module, width, i * width);
 		if (err)
 			goto err_port_create;
 	}
@@ -3372,8 +3911,8 @@ static int mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port,
 
 err_port_create:
 	for (i--; i >= 0; i--)
-		if (mlxsw_sp_port_created(mlxsw_sp, base_port + i))
-			mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+		if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset))
+			mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset);
 	return err;
 }
 
@@ -3404,11 +3943,19 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	u8 local_ports_in_1x, local_ports_in_2x, offset;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 module, cur_width, base_port;
 	int i;
 	int err;
 
+	if (!MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_1X) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_2X))
+		return -EIO;
+
+	local_ports_in_1x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_1X);
+	local_ports_in_2x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_2X);
+
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
@@ -3434,13 +3981,15 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 
 	/* Make sure we have enough slave (even) ports for the split. */
 	if (count == 2) {
+		offset = local_ports_in_2x;
 		base_port = local_port;
-		if (mlxsw_sp->ports[base_port + 1]) {
+		if (mlxsw_sp->ports[base_port + local_ports_in_2x]) {
 			netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n");
 			NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration");
 			return -EINVAL;
 		}
 	} else {
+		offset = local_ports_in_1x;
 		base_port = mlxsw_sp_cluster_base_port_get(local_port);
 		if (mlxsw_sp->ports[base_port + 1] ||
 		    mlxsw_sp->ports[base_port + 3]) {
@@ -3451,10 +4000,11 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port,
 	}
 
 	for (i = 0; i < count; i++)
-		if (mlxsw_sp_port_created(mlxsw_sp, base_port + i))
-			mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+		if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset))
+			mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset);
 
-	err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count);
+	err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, module, count,
+					 offset);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n");
 		goto err_port_split_create;
@@ -3471,11 +4021,19 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
 				 struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	u8 local_ports_in_1x, local_ports_in_2x, offset;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 cur_width, base_port;
 	unsigned int count;
 	int i;
 
+	if (!MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_1X) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_core, LOCAL_PORTS_IN_2X))
+		return -EIO;
+
+	local_ports_in_1x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_1X);
+	local_ports_in_2x = MLXSW_CORE_RES_GET(mlxsw_core, LOCAL_PORTS_IN_2X);
+
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n",
@@ -3493,6 +4051,11 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
 	cur_width = mlxsw_sp_port->mapping.width;
 	count = cur_width == 1 ? 4 : 2;
 
+	if (count == 2)
+		offset = local_ports_in_2x;
+	else
+		offset = local_ports_in_1x;
+
 	base_port = mlxsw_sp_cluster_base_port_get(local_port);
 
 	/* Determine which ports to remove. */
@@ -3500,8 +4063,8 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port,
 		base_port = base_port + 2;
 
 	for (i = 0; i < count; i++)
-		if (mlxsw_sp_port_created(mlxsw_sp, base_port + i))
-			mlxsw_sp_port_remove(mlxsw_sp, base_port + i);
+		if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset))
+			mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset);
 
 	mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count);
 
@@ -3525,14 +4088,55 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 	if (status == MLXSW_PORT_OPER_STATUS_UP) {
 		netdev_info(mlxsw_sp_port->dev, "link up\n");
 		netif_carrier_on(mlxsw_sp_port->dev);
+		mlxsw_core_schedule_dw(&mlxsw_sp_port->ptp.shaper_dw, 0);
 	} else {
 		netdev_info(mlxsw_sp_port->dev, "link down\n");
 		netif_carrier_off(mlxsw_sp_port->dev);
 	}
 }
 
-static void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb,
-					      u8 local_port, void *priv)
+static void mlxsw_sp1_ptp_fifo_event_func(struct mlxsw_sp *mlxsw_sp,
+					  char *mtpptr_pl, bool ingress)
+{
+	u8 local_port;
+	u8 num_rec;
+	int i;
+
+	local_port = mlxsw_reg_mtpptr_local_port_get(mtpptr_pl);
+	num_rec = mlxsw_reg_mtpptr_num_rec_get(mtpptr_pl);
+	for (i = 0; i < num_rec; i++) {
+		u8 domain_number;
+		u8 message_type;
+		u16 sequence_id;
+		u64 timestamp;
+
+		mlxsw_reg_mtpptr_unpack(mtpptr_pl, i, &message_type,
+					&domain_number, &sequence_id,
+					&timestamp);
+		mlxsw_sp1_ptp_got_timestamp(mlxsw_sp, ingress, local_port,
+					    message_type, domain_number,
+					    sequence_id, timestamp);
+	}
+}
+
+static void mlxsw_sp1_ptp_ing_fifo_event_func(const struct mlxsw_reg_info *reg,
+					      char *mtpptr_pl, void *priv)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+
+	mlxsw_sp1_ptp_fifo_event_func(mlxsw_sp, mtpptr_pl, true);
+}
+
+static void mlxsw_sp1_ptp_egr_fifo_event_func(const struct mlxsw_reg_info *reg,
+					      char *mtpptr_pl, void *priv)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+
+	mlxsw_sp1_ptp_fifo_event_func(mlxsw_sp, mtpptr_pl, false);
+}
+
+void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb,
+				       u8 local_port, void *priv)
 {
 	struct mlxsw_sp *mlxsw_sp = priv;
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port];
@@ -3606,6 +4210,14 @@ out:
 	consume_skb(skb);
 }
 
+static void mlxsw_sp_rx_listener_ptp(struct sk_buff *skb, u8 local_port,
+				     void *priv)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+
+	mlxsw_sp->ptp_ops->receive(mlxsw_sp, skb, local_port);
+}
+
 #define MLXSW_SP_RXL_NO_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
 	MLXSW_RXL(mlxsw_sp_rx_listener_no_mark_func, _trap_id, _action,	\
 		  _is_ctrl, SP_##_trap_group, DISCARD)
@@ -3627,7 +4239,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* L2 traps */
 	MLXSW_SP_RXL_NO_MARK(STP, TRAP_TO_CPU, STP, true),
 	MLXSW_SP_RXL_NO_MARK(LACP, TRAP_TO_CPU, LACP, true),
-	MLXSW_SP_RXL_NO_MARK(LLDP, TRAP_TO_CPU, LLDP, true),
+	MLXSW_RXL(mlxsw_sp_rx_listener_ptp, LLDP, TRAP_TO_CPU,
+		  false, SP_LLDP, DISCARD),
 	MLXSW_SP_RXL_MARK(DHCP, MIRROR_TO_CPU, DHCP, false),
 	MLXSW_SP_RXL_MARK(IGMP_QUERY, MIRROR_TO_CPU, IGMP, false),
 	MLXSW_SP_RXL_NO_MARK(IGMP_V1_REPORT, TRAP_TO_CPU, IGMP, false),
@@ -3696,6 +4309,16 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* NVE traps */
 	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, ARP, false),
 	MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, TRAP_TO_CPU, ARP, false),
+	/* PTP traps */
+	MLXSW_RXL(mlxsw_sp_rx_listener_ptp, PTP0, TRAP_TO_CPU,
+		  false, SP_PTP0, DISCARD),
+	MLXSW_SP_RXL_NO_MARK(PTP1, TRAP_TO_CPU, PTP1, false),
+};
+
+static const struct mlxsw_listener mlxsw_sp1_listener[] = {
+	/* Events */
+	MLXSW_EVENTL(mlxsw_sp1_ptp_egr_fifo_event_func, PTP_EGR_FIFO, SP_PTP0),
+	MLXSW_EVENTL(mlxsw_sp1_ptp_ing_fifo_event_func, PTP_ING_FIFO, SP_PTP0),
 };
 
 static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
@@ -3744,8 +4367,16 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			burst_size = 7;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
-			rate = 4 * 1024;
-			burst_size = 4;
+			rate = 1024;
+			burst_size = 7;
+			break;
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
+			rate = 24 * 1024;
+			burst_size = 12;
+			break;
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
+			rate = 19 * 1024;
+			burst_size = 12;
 			break;
 		default:
 			continue;
@@ -3785,6 +4416,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
 			priority = 5;
 			tc = 5;
 			break;
@@ -3802,6 +4434,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1:
 			priority = 2;
 			tc = 2;
 			break;
@@ -3835,22 +4468,16 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 	return 0;
 }
 
-static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
+static int mlxsw_sp_traps_register(struct mlxsw_sp *mlxsw_sp,
+				   const struct mlxsw_listener listeners[],
+				   size_t listeners_count)
 {
 	int i;
 	int err;
 
-	err = mlxsw_sp_cpu_policers_set(mlxsw_sp->core);
-	if (err)
-		return err;
-
-	err = mlxsw_sp_trap_groups_set(mlxsw_sp->core);
-	if (err)
-		return err;
-
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener); i++) {
+	for (i = 0; i < listeners_count; i++) {
 		err = mlxsw_core_trap_register(mlxsw_sp->core,
-					       &mlxsw_sp_listener[i],
+					       &listeners[i],
 					       mlxsw_sp);
 		if (err)
 			goto err_listener_register;
@@ -3861,30 +4488,73 @@ static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
 err_listener_register:
 	for (i--; i >= 0; i--) {
 		mlxsw_core_trap_unregister(mlxsw_sp->core,
-					   &mlxsw_sp_listener[i],
+					   &listeners[i],
 					   mlxsw_sp);
 	}
 	return err;
 }
 
-static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp)
+static void mlxsw_sp_traps_unregister(struct mlxsw_sp *mlxsw_sp,
+				      const struct mlxsw_listener listeners[],
+				      size_t listeners_count)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener); i++) {
+	for (i = 0; i < listeners_count; i++) {
 		mlxsw_core_trap_unregister(mlxsw_sp->core,
-					   &mlxsw_sp_listener[i],
+					   &listeners[i],
 					   mlxsw_sp);
 	}
 }
 
+static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
+{
+	int err;
+
+	err = mlxsw_sp_cpu_policers_set(mlxsw_sp->core);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_trap_groups_set(mlxsw_sp->core);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp_listener,
+				      ARRAY_SIZE(mlxsw_sp_listener));
+	if (err)
+		return err;
+
+	err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp->listeners,
+				      mlxsw_sp->listeners_count);
+	if (err)
+		goto err_extra_traps_init;
+
+	return 0;
+
+err_extra_traps_init:
+	mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener,
+				  ARRAY_SIZE(mlxsw_sp_listener));
+	return err;
+}
+
+static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp->listeners,
+				  mlxsw_sp->listeners_count);
+	mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener,
+				  ARRAY_SIZE(mlxsw_sp_listener));
+}
+
+#define MLXSW_SP_LAG_SEED_INIT 0xcafecafe
+
 static int mlxsw_sp_lag_init(struct mlxsw_sp *mlxsw_sp)
 {
 	char slcr_pl[MLXSW_REG_SLCR_LEN];
 	u32 seed;
 	int err;
 
-	get_random_bytes(&seed, sizeof(seed));
+	seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac),
+		     MLXSW_SP_LAG_SEED_INIT);
 	mlxsw_reg_slcr_pack(slcr_pl, MLXSW_REG_SLCR_LAG_HASH_SMAC |
 				     MLXSW_REG_SLCR_LAG_HASH_DMAC |
 				     MLXSW_REG_SLCR_LAG_HASH_ETHERTYPE |
@@ -3927,6 +4597,32 @@ static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core)
 	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
 }
 
+static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = {
+	.clock_init	= mlxsw_sp1_ptp_clock_init,
+	.clock_fini	= mlxsw_sp1_ptp_clock_fini,
+	.init		= mlxsw_sp1_ptp_init,
+	.fini		= mlxsw_sp1_ptp_fini,
+	.receive	= mlxsw_sp1_ptp_receive,
+	.transmitted	= mlxsw_sp1_ptp_transmitted,
+	.hwtstamp_get	= mlxsw_sp1_ptp_hwtstamp_get,
+	.hwtstamp_set	= mlxsw_sp1_ptp_hwtstamp_set,
+	.shaper_work	= mlxsw_sp1_ptp_shaper_work,
+	.get_ts_info	= mlxsw_sp1_ptp_get_ts_info,
+};
+
+static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
+	.clock_init	= mlxsw_sp2_ptp_clock_init,
+	.clock_fini	= mlxsw_sp2_ptp_clock_fini,
+	.init		= mlxsw_sp2_ptp_init,
+	.fini		= mlxsw_sp2_ptp_fini,
+	.receive	= mlxsw_sp2_ptp_receive,
+	.transmitted	= mlxsw_sp2_ptp_transmitted,
+	.hwtstamp_get	= mlxsw_sp2_ptp_hwtstamp_get,
+	.hwtstamp_set	= mlxsw_sp2_ptp_hwtstamp_set,
+	.shaper_work	= mlxsw_sp2_ptp_shaper_work,
+	.get_ts_info	= mlxsw_sp2_ptp_get_ts_info,
+};
+
 static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 				    unsigned long event, void *ptr);
 
@@ -4024,6 +4720,28 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_router_init;
 	}
 
+	if (mlxsw_sp->bus_info->read_frc_capable) {
+		/* NULL is a valid return value from clock_init */
+		mlxsw_sp->clock =
+			mlxsw_sp->ptp_ops->clock_init(mlxsw_sp,
+						      mlxsw_sp->bus_info->dev);
+		if (IS_ERR(mlxsw_sp->clock)) {
+			err = PTR_ERR(mlxsw_sp->clock);
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to init ptp clock\n");
+			goto err_ptp_clock_init;
+		}
+	}
+
+	if (mlxsw_sp->clock) {
+		/* NULL is a valid return value from ptp_ops->init */
+		mlxsw_sp->ptp_state = mlxsw_sp->ptp_ops->init(mlxsw_sp);
+		if (IS_ERR(mlxsw_sp->ptp_state)) {
+			err = PTR_ERR(mlxsw_sp->ptp_state);
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize PTP\n");
+			goto err_ptp_init;
+		}
+	}
+
 	/* Initialize netdevice notifier after router and SPAN is initialized,
 	 * so that the event handler can use router structures and call SPAN
 	 * respin.
@@ -4054,6 +4772,12 @@ err_ports_create:
 err_dpipe_init:
 	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
 err_netdev_notifier:
+	if (mlxsw_sp->clock)
+		mlxsw_sp->ptp_ops->fini(mlxsw_sp->ptp_state);
+err_ptp_init:
+	if (mlxsw_sp->clock)
+		mlxsw_sp->ptp_ops->clock_fini(mlxsw_sp->clock);
+err_ptp_clock_init:
 	mlxsw_sp_router_fini(mlxsw_sp);
 err_router_init:
 	mlxsw_sp_acl_fini(mlxsw_sp);
@@ -4094,6 +4818,12 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
 	mlxsw_sp->nve_ops_arr = mlxsw_sp1_nve_ops_arr;
 	mlxsw_sp->mac_mask = mlxsw_sp1_mac_mask;
+	mlxsw_sp->rif_ops_arr = mlxsw_sp1_rif_ops_arr;
+	mlxsw_sp->sb_vals = &mlxsw_sp1_sb_vals;
+	mlxsw_sp->port_type_speed_ops = &mlxsw_sp1_port_type_speed_ops;
+	mlxsw_sp->ptp_ops = &mlxsw_sp1_ptp_ops;
+	mlxsw_sp->listeners = mlxsw_sp1_listener;
+	mlxsw_sp->listeners_count = ARRAY_SIZE(mlxsw_sp1_listener);
 
 	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
 }
@@ -4110,6 +4840,10 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->acl_tcam_ops = &mlxsw_sp2_acl_tcam_ops;
 	mlxsw_sp->nve_ops_arr = mlxsw_sp2_nve_ops_arr;
 	mlxsw_sp->mac_mask = mlxsw_sp2_mac_mask;
+	mlxsw_sp->rif_ops_arr = mlxsw_sp2_rif_ops_arr;
+	mlxsw_sp->sb_vals = &mlxsw_sp2_sb_vals;
+	mlxsw_sp->port_type_speed_ops = &mlxsw_sp2_port_type_speed_ops;
+	mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops;
 
 	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
 }
@@ -4121,6 +4855,10 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_ports_remove(mlxsw_sp);
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
 	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
+	if (mlxsw_sp->clock) {
+		mlxsw_sp->ptp_ops->fini(mlxsw_sp->ptp_state);
+		mlxsw_sp->ptp_ops->clock_fini(mlxsw_sp->clock);
+	}
 	mlxsw_sp_router_fini(mlxsw_sp);
 	mlxsw_sp_acl_fini(mlxsw_sp);
 	mlxsw_sp_nve_fini(mlxsw_sp);
@@ -4398,6 +5136,80 @@ static void mlxsw_sp_params_unregister(struct mlxsw_core *mlxsw_core)
 				  ARRAY_SIZE(mlxsw_sp_devlink_params));
 }
 
+static int
+mlxsw_sp_params_acl_region_rehash_intrvl_get(struct devlink *devlink, u32 id,
+					     struct devlink_param_gset_ctx *ctx)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	ctx->val.vu32 = mlxsw_sp_acl_region_rehash_intrvl_get(mlxsw_sp);
+	return 0;
+}
+
+static int
+mlxsw_sp_params_acl_region_rehash_intrvl_set(struct devlink *devlink, u32 id,
+					     struct devlink_param_gset_ctx *ctx)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	return mlxsw_sp_acl_region_rehash_intrvl_set(mlxsw_sp, ctx->val.vu32);
+}
+
+static const struct devlink_param mlxsw_sp2_devlink_params[] = {
+	DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL,
+			     "acl_region_rehash_interval",
+			     DEVLINK_PARAM_TYPE_U32,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     mlxsw_sp_params_acl_region_rehash_intrvl_get,
+			     mlxsw_sp_params_acl_region_rehash_intrvl_set,
+			     NULL),
+};
+
+static int mlxsw_sp2_params_register(struct mlxsw_core *mlxsw_core)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	union devlink_param_value value;
+	int err;
+
+	err = mlxsw_sp_params_register(mlxsw_core);
+	if (err)
+		return err;
+
+	err = devlink_params_register(devlink, mlxsw_sp2_devlink_params,
+				      ARRAY_SIZE(mlxsw_sp2_devlink_params));
+	if (err)
+		goto err_devlink_params_register;
+
+	value.vu32 = 0;
+	devlink_param_driverinit_value_set(devlink,
+					   MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL,
+					   value);
+	return 0;
+
+err_devlink_params_register:
+	mlxsw_sp_params_unregister(mlxsw_core);
+	return err;
+}
+
+static void mlxsw_sp2_params_unregister(struct mlxsw_core *mlxsw_core)
+{
+	devlink_params_unregister(priv_to_devlink(mlxsw_core),
+				  mlxsw_sp2_devlink_params,
+				  ARRAY_SIZE(mlxsw_sp2_devlink_params));
+	mlxsw_sp_params_unregister(mlxsw_core);
+}
+
+static void mlxsw_sp_ptp_transmitted(struct mlxsw_core *mlxsw_core,
+				     struct sk_buff *skb, u8 local_port)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	skb_pull(skb, MLXSW_TXHDR_LEN);
+	mlxsw_sp->ptp_ops->transmitted(mlxsw_sp, skb, local_port);
+}
+
 static struct mlxsw_driver mlxsw_sp1_driver = {
 	.kind				= mlxsw_sp1_driver_name,
 	.priv_size			= sizeof(struct mlxsw_sp),
@@ -4416,11 +5228,13 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
 	.sb_occ_max_clear		= mlxsw_sp_sb_occ_max_clear,
 	.sb_occ_port_pool_get		= mlxsw_sp_sb_occ_port_pool_get,
 	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
+	.flash_update			= mlxsw_sp_flash_update,
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp1_resources_register,
 	.kvd_sizes_get			= mlxsw_sp_kvd_sizes_get,
 	.params_register		= mlxsw_sp_params_register,
 	.params_unregister		= mlxsw_sp_params_unregister,
+	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp1_config_profile,
 	.res_query_enabled		= true,
@@ -4444,10 +5258,12 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
 	.sb_occ_max_clear		= mlxsw_sp_sb_occ_max_clear,
 	.sb_occ_port_pool_get		= mlxsw_sp_sb_occ_port_pool_get,
 	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
+	.flash_update			= mlxsw_sp_flash_update,
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
-	.params_register		= mlxsw_sp_params_register,
-	.params_unregister		= mlxsw_sp_params_unregister,
+	.params_register		= mlxsw_sp2_params_register,
+	.params_unregister		= mlxsw_sp2_params_unregister,
+	.ptp_transmitted		= mlxsw_sp_ptp_transmitted,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp2_config_profile,
 	.res_query_enabled		= true,
@@ -4691,9 +5507,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	err = mlxsw_sp_lag_col_port_add(mlxsw_sp_port, lag_id, port_index);
 	if (err)
 		goto err_col_port_add;
-	err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port, lag_id);
-	if (err)
-		goto err_col_port_enable;
 
 	mlxsw_core_lag_mapping_set(mlxsw_sp->core, lag_id, port_index,
 				   mlxsw_sp_port->local_port);
@@ -4707,8 +5520,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	return 0;
 
-err_col_port_enable:
-	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 err_col_port_add:
 	if (!lag->ref_count)
 		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
@@ -4727,7 +5538,6 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id);
 	WARN_ON(lag->ref_count == 0);
 
-	mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id);
 	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 
 	/* Any VLANs configured on the port are no longer valid */
@@ -4772,21 +5582,56 @@ static int mlxsw_sp_lag_dist_port_remove(struct mlxsw_sp_port *mlxsw_sp_port,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl);
 }
 
-static int mlxsw_sp_port_lag_tx_en_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				       bool lag_tx_enabled)
+static int
+mlxsw_sp_port_lag_col_dist_enable(struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	if (lag_tx_enabled)
-		return mlxsw_sp_lag_dist_port_add(mlxsw_sp_port,
-						  mlxsw_sp_port->lag_id);
-	else
-		return mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port,
-						     mlxsw_sp_port->lag_id);
+	int err;
+
+	err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port,
+					   mlxsw_sp_port->lag_id);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id);
+	if (err)
+		goto err_dist_port_add;
+
+	return 0;
+
+err_dist_port_add:
+	mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, mlxsw_sp_port->lag_id);
+	return err;
+}
+
+static int
+mlxsw_sp_port_lag_col_dist_disable(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int err;
+
+	err = mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port,
+					    mlxsw_sp_port->lag_id);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port,
+					    mlxsw_sp_port->lag_id);
+	if (err)
+		goto err_col_port_disable;
+
+	return 0;
+
+err_col_port_disable:
+	mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id);
+	return err;
 }
 
 static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port,
 				     struct netdev_lag_lower_state_info *info)
 {
-	return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled);
+	if (info->tx_enabled)
+		return mlxsw_sp_port_lag_col_dist_enable(mlxsw_sp_port);
+	else
+		return mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port);
 }
 
 static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -5009,8 +5854,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
 							     upper_dev);
 			} else {
-				mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port,
-							    false);
+				mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port);
 				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
 							upper_dev);
 			}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a1c32a81b011..a252b080dda9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -33,7 +33,8 @@
 
 #define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4
 
-#define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
+#define MLXSW_SP_PORT_BASE_SPEED_25G 25000 /* Mb/s */
+#define MLXSW_SP_PORT_BASE_SPEED_50G 50000 /* Mb/s */
 
 #define MLXSW_SP_KVD_LINEAR_SIZE 98304 /* entries */
 #define MLXSW_SP_KVD_GRANULARITY 128
@@ -75,6 +76,11 @@ enum mlxsw_sp_rif_type {
 	MLXSW_SP_RIF_TYPE_MAX,
 };
 
+struct mlxsw_sp_rif_ops;
+
+extern const struct mlxsw_sp_rif_ops *mlxsw_sp1_rif_ops_arr[];
+extern const struct mlxsw_sp_rif_ops *mlxsw_sp2_rif_ops_arr[];
+
 enum mlxsw_sp_fid_type {
 	MLXSW_SP_FID_TYPE_8021Q,
 	MLXSW_SP_FID_TYPE_8021D,
@@ -128,6 +134,10 @@ struct mlxsw_sp_kvdl_ops;
 struct mlxsw_sp_mr_tcam_ops;
 struct mlxsw_sp_acl_tcam_ops;
 struct mlxsw_sp_nve_ops;
+struct mlxsw_sp_sb_vals;
+struct mlxsw_sp_port_type_speed_ops;
+struct mlxsw_sp_ptp_state;
+struct mlxsw_sp_ptp_ops;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
@@ -147,6 +157,8 @@ struct mlxsw_sp {
 	struct mlxsw_sp_kvdl *kvdl;
 	struct mlxsw_sp_nve *nve;
 	struct notifier_block netdevice_nb;
+	struct mlxsw_sp_ptp_clock *clock;
+	struct mlxsw_sp_ptp_state *ptp_state;
 
 	struct mlxsw_sp_counter_pool *counter_pool;
 	struct {
@@ -161,6 +173,12 @@ struct mlxsw_sp {
 	const struct mlxsw_sp_mr_tcam_ops *mr_tcam_ops;
 	const struct mlxsw_sp_acl_tcam_ops *acl_tcam_ops;
 	const struct mlxsw_sp_nve_ops **nve_ops_arr;
+	const struct mlxsw_sp_rif_ops **rif_ops_arr;
+	const struct mlxsw_sp_sb_vals *sb_vals;
+	const struct mlxsw_sp_port_type_speed_ops *port_type_speed_ops;
+	const struct mlxsw_sp_ptp_ops *ptp_ops;
+	const struct mlxsw_listener *listeners;
+	size_t listeners_count;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -248,6 +266,36 @@ struct mlxsw_sp_port {
 	unsigned acl_rule_count;
 	struct mlxsw_sp_acl_block *ing_acl_block;
 	struct mlxsw_sp_acl_block *eg_acl_block;
+	struct {
+		struct delayed_work shaper_dw;
+		struct hwtstamp_config hwtstamp_config;
+		u16 ing_types;
+		u16 egr_types;
+	} ptp;
+};
+
+struct mlxsw_sp_port_type_speed_ops {
+	void (*from_ptys_supported_port)(struct mlxsw_sp *mlxsw_sp,
+					 u32 ptys_eth_proto,
+					 struct ethtool_link_ksettings *cmd);
+	void (*from_ptys_link)(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto,
+			       unsigned long *mode);
+	u32 (*from_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto);
+	void (*from_ptys_speed_duplex)(struct mlxsw_sp *mlxsw_sp,
+				       bool carrier_ok, u32 ptys_eth_proto,
+				       struct ethtool_link_ksettings *cmd);
+	u32 (*to_ptys_advert_link)(struct mlxsw_sp *mlxsw_sp,
+				   const struct ethtool_link_ksettings *cmd);
+	u32 (*to_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u32 speed);
+	u32 (*to_ptys_upper_speed)(struct mlxsw_sp *mlxsw_sp, u32 upper_speed);
+	int (*port_speed_base)(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+			       u32 *base_speed);
+	void (*reg_ptys_eth_pack)(struct mlxsw_sp *mlxsw_sp, char *payload,
+				  u8 local_port, u32 proto_admin, bool autoneg);
+	void (*reg_ptys_eth_unpack)(struct mlxsw_sp *mlxsw_sp, char *payload,
+				    u32 *p_eth_proto_cap,
+				    u32 *p_eth_proto_admin,
+				    u32 *p_eth_proto_oper);
 };
 
 static inline struct net_device *
@@ -337,13 +385,14 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
 			 struct devlink_sb_pool_info *pool_info);
 int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core,
 			 unsigned int sb_index, u16 pool_index, u32 size,
-			 enum devlink_sb_threshold_type threshold_type);
+			 enum devlink_sb_threshold_type threshold_type,
+			 struct netlink_ext_ack *extack);
 int mlxsw_sp_sb_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
 			      unsigned int sb_index, u16 pool_index,
 			      u32 *p_threshold);
 int mlxsw_sp_sb_port_pool_set(struct mlxsw_core_port *mlxsw_core_port,
 			      unsigned int sb_index, u16 pool_index,
-			      u32 threshold);
+			      u32 threshold, struct netlink_ext_ack *extack);
 int mlxsw_sp_sb_tc_pool_bind_get(struct mlxsw_core_port *mlxsw_core_port,
 				 unsigned int sb_index, u16 tc_index,
 				 enum devlink_sb_pool_type pool_type,
@@ -351,7 +400,8 @@ int mlxsw_sp_sb_tc_pool_bind_get(struct mlxsw_core_port *mlxsw_core_port,
 int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port,
 				 unsigned int sb_index, u16 tc_index,
 				 enum devlink_sb_pool_type pool_type,
-				 u16 pool_index, u32 threshold);
+				 u16 pool_index, u32 threshold,
+				 struct netlink_ext_ack *extack);
 int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core,
 			     unsigned int sb_index);
 int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core,
@@ -365,12 +415,14 @@ int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port,
 				     u32 *p_cur, u32 *p_max);
 u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp, u32 cells);
 u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp, u32 bytes);
+u32 mlxsw_sp_sb_max_headroom_cells(const struct mlxsw_sp *mlxsw_sp);
+
+extern const struct mlxsw_sp_sb_vals mlxsw_sp1_sb_vals;
+extern const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals;
 
 /* spectrum_switchdev.c */
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp);
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port);
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
 			bool adding);
 void
@@ -397,6 +449,8 @@ struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
 extern struct notifier_block mlxsw_sp_switchdev_notifier;
 
 /* spectrum.c */
+void mlxsw_sp_rx_listener_no_mark_func(struct sk_buff *skb,
+				       u8 local_port, void *priv);
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
 			  enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index,
 			  bool dwrr, u8 dwrr_weight);
@@ -501,6 +555,9 @@ void mlxsw_sp_router_nve_demote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
 				      const union mlxsw_sp_l3addr *ul_sip);
 int mlxsw_sp_router_tb_id_vr_id(struct mlxsw_sp *mlxsw_sp, u32 tb_id,
 				u16 *vr_id);
+int mlxsw_sp_router_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
+			       u16 *ul_rif_index);
+void mlxsw_sp_router_ul_rif_put(struct mlxsw_sp *mlxsw_sp, u16 ul_rif_index);
 
 /* spectrum_kvdl.c */
 enum mlxsw_sp_kvdl_entry_type {
@@ -579,6 +636,15 @@ enum mlxsw_sp_acl_profile {
 	MLXSW_SP_ACL_PROFILE_MR,
 };
 
+struct mlxsw_sp_acl_block {
+	struct list_head binding_list;
+	struct mlxsw_sp_acl_ruleset *ruleset_zero;
+	struct mlxsw_sp *mlxsw_sp;
+	unsigned int rule_count;
+	unsigned int disable_count;
+	struct net *net;
+};
+
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
 struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block);
 unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block);
@@ -681,6 +747,8 @@ struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp);
 
 int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
+u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val);
 
 /* spectrum_acl_tcam.c */
 struct mlxsw_sp_acl_tcam;
@@ -695,10 +763,13 @@ struct mlxsw_sp_acl_tcam_ops {
 	size_t region_priv_size;
 	int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			   void *tcam_priv,
-			   struct mlxsw_sp_acl_tcam_region *region);
+			   struct mlxsw_sp_acl_tcam_region *region,
+			   void *hints_priv);
 	void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv);
 	int (*region_associate)(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam_region *region);
+	void * (*region_rehash_hints_get)(void *region_priv);
+	void (*region_rehash_hints_put)(void *hints_priv);
 	size_t chunk_priv_size;
 	void (*chunk_init)(void *region_priv, void *chunk_priv,
 			   unsigned int priority);
@@ -712,8 +783,7 @@ struct mlxsw_sp_acl_tcam_ops {
 			  void *region_priv, void *chunk_priv,
 			  void *entry_priv);
 	int (*entry_action_replace)(struct mlxsw_sp *mlxsw_sp,
-				    void *region_priv, void *chunk_priv,
-				    void *entry_priv,
+				    void *region_priv, void *entry_priv,
 				    struct mlxsw_sp_acl_rule_info *rulei);
 	int (*entry_activity_get)(struct mlxsw_sp *mlxsw_sp,
 				  void *region_priv, void *entry_priv,
@@ -737,19 +807,19 @@ extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block,
-			    struct tc_cls_flower_offload *f);
+			    struct flow_cls_offload *f);
 void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_block *block,
-			     struct tc_cls_flower_offload *f);
+			     struct flow_cls_offload *f);
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_block *block,
-			  struct tc_cls_flower_offload *f);
+			  struct flow_cls_offload *f);
 int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_block *block,
-				 struct tc_cls_flower_offload *f);
+				 struct flow_cls_offload *f);
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_block *block,
-				   struct tc_cls_flower_offload *f);
+				   struct flow_cls_offload *f);
 
 /* spectrum_qdisc.c */
 int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index fe270c1a26a6..3a636f753607 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -112,7 +112,8 @@ mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
 static int
 mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			       void *tcam_priv,
-			       struct mlxsw_sp_acl_tcam_region *_region)
+			       struct mlxsw_sp_acl_tcam_region *_region,
+			       void *hints_priv)
 {
 	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
 	int err;
@@ -194,8 +195,7 @@ static void mlxsw_sp1_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 
 static int
 mlxsw_sp1_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
-					void *region_priv, void *chunk_priv,
-					void *entry_priv,
+					void *region_priv, void *entry_priv,
 					struct mlxsw_sp_acl_rule_info *rulei)
 {
 	return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 234ab51916db..6c66a0f1b79e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -139,7 +139,8 @@ static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
 static int
 mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			       void *tcam_priv,
-			       struct mlxsw_sp_acl_tcam_region *_region)
+			       struct mlxsw_sp_acl_tcam_region *_region,
+			       void *hints_priv)
 {
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
 	struct mlxsw_sp2_acl_tcam *tcam = tcam_priv;
@@ -147,7 +148,8 @@ mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 	region->region = _region;
 
 	return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam,
-					      &region->aregion, _region,
+					      &region->aregion,
+					      _region, hints_priv,
 					      &mlxsw_sp2_acl_ctcam_region_ops);
 }
 
@@ -166,6 +168,18 @@ mlxsw_sp2_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id);
 }
 
+static void *mlxsw_sp2_acl_tcam_region_rehash_hints_get(void *region_priv)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+
+	return mlxsw_sp_acl_atcam_rehash_hints_get(&region->aregion);
+}
+
+static void mlxsw_sp2_acl_tcam_region_rehash_hints_put(void *hints_priv)
+{
+	mlxsw_sp_acl_atcam_rehash_hints_put(hints_priv);
+}
+
 static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
 					  unsigned int priority)
 {
@@ -212,18 +226,15 @@ static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 
 static int
 mlxsw_sp2_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
-					void *region_priv, void *chunk_priv,
-					void *entry_priv,
+					void *region_priv, void *entry_priv,
 					struct mlxsw_sp_acl_rule_info *rulei)
 {
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
-	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
 	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
 
 	entry->act_block = rulei->act_block;
 	return mlxsw_sp_acl_atcam_entry_action_replace(mlxsw_sp,
 						       &region->aregion,
-						       &chunk->achunk,
 						       &entry->aentry, rulei);
 }
 
@@ -246,6 +257,8 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops = {
 	.region_init		= mlxsw_sp2_acl_tcam_region_init,
 	.region_fini		= mlxsw_sp2_acl_tcam_region_fini,
 	.region_associate	= mlxsw_sp2_acl_tcam_region_associate,
+	.region_rehash_hints_get = mlxsw_sp2_acl_tcam_region_rehash_hints_get,
+	.region_rehash_hints_put = mlxsw_sp2_acl_tcam_region_rehash_hints_put,
 	.chunk_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_chunk),
 	.chunk_init		= mlxsw_sp2_acl_tcam_chunk_init,
 	.chunk_fini		= mlxsw_sp2_acl_tcam_chunk_fini,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 695d33358988..e8ac90564dbe 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -45,14 +45,6 @@ struct mlxsw_sp_acl_block_binding {
 	bool ingress;
 };
 
-struct mlxsw_sp_acl_block {
-	struct list_head binding_list;
-	struct mlxsw_sp_acl_ruleset *ruleset_zero;
-	struct mlxsw_sp *mlxsw_sp;
-	unsigned int rule_count;
-	unsigned int disable_count;
-};
-
 struct mlxsw_sp_acl_ruleset_ht_key {
 	struct mlxsw_sp_acl_block *block;
 	u32 chain_index;
@@ -221,6 +213,7 @@ struct mlxsw_sp_acl_block *mlxsw_sp_acl_block_create(struct mlxsw_sp *mlxsw_sp,
 		return NULL;
 	INIT_LIST_HEAD(&block->binding_list);
 	block->mlxsw_sp = mlxsw_sp;
+	block->net = net;
 	return block;
 }
 
@@ -588,7 +581,7 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 {
 	u8 ethertype;
 
-	if (action == TCA_VLAN_ACT_MODIFY) {
+	if (action == FLOW_ACTION_VLAN_MANGLE) {
 		switch (proto) {
 		case ETH_P_8021Q:
 			ethertype = 0;
@@ -640,7 +633,7 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_sp_acl_ruleset_ref_inc(ruleset);
-	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size(mlxsw_sp),
+	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size,
 		       GFP_KERNEL);
 	if (!rule) {
 		err = -ENOMEM;
@@ -742,8 +735,7 @@ int mlxsw_sp_acl_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
 	rulei = mlxsw_sp_acl_rule_rulei(rule);
 	rulei->act_block = afa_block;
 
-	return ops->rule_action_replace(mlxsw_sp, ruleset->priv, rule->priv,
-					rule->rulei);
+	return ops->rule_action_replace(mlxsw_sp, rule->priv, rule->rulei);
 }
 
 struct mlxsw_sp_acl_rule *
@@ -806,7 +798,7 @@ static void mlxsw_sp_acl_rule_activity_work_schedule(struct mlxsw_sp_acl *acl)
 			       msecs_to_jiffies(interval));
 }
 
-static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work)
+static void mlxsw_sp_acl_rule_activity_update_work(struct work_struct *work)
 {
 	struct mlxsw_sp_acl *acl = container_of(work, struct mlxsw_sp_acl,
 						rule_activity_update.dw.work);
@@ -885,7 +877,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 
 	/* Create the delayed work for the rule activity_update */
 	INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
-			  mlxsw_sp_acl_rul_activity_update_work);
+			  mlxsw_sp_acl_rule_activity_update_work);
 	acl->rule_activity_update.interval = MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS;
 	mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, 0);
 	return 0;
@@ -913,3 +905,19 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_afk_destroy(acl->afk);
 	kfree(acl);
 }
+
+u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
+
+	return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(mlxsw_sp,
+							   &acl->tcam);
+}
+
+int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val)
+{
+	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
+
+	return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(mlxsw_sp,
+							   &acl->tcam, val);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 80fb268d51a5..ded4cf658680 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -7,6 +7,8 @@
 #include <linux/gfp.h>
 #include <linux/refcount.h>
 #include <linux/rhashtable.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/mlxsw.h>
 
 #include "reg.h"
 #include "core.h"
@@ -316,6 +318,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam *atcam,
 			       struct mlxsw_sp_acl_atcam_region *aregion,
 			       struct mlxsw_sp_acl_tcam_region *region,
+			       void *hints_priv,
 			       const struct mlxsw_sp_acl_ctcam_region_ops *ops)
 {
 	int err;
@@ -332,7 +335,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 	err = aregion->ops->init(aregion);
 	if (err)
 		goto err_ops_init;
-	err = mlxsw_sp_acl_erp_region_init(aregion);
+	err = mlxsw_sp_acl_erp_region_init(aregion, hints_priv);
 	if (err)
 		goto err_erp_region_init;
 	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
@@ -390,8 +393,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->ht_key.enc_key,
-					    erp_id);
+	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->enc_key, erp_id);
 	if (IS_ERR(lkey_id))
 		return PTR_ERR(lkey_id);
 	aentry->lkey_id = lkey_id;
@@ -399,7 +401,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
 			     priority, region->tcam_region_info,
-			     aentry->ht_key.enc_key, erp_id,
+			     aentry->enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -424,12 +426,11 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
 	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
-	char *enc_key = aentry->ht_key.enc_key;
 	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
 
 	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
 			     region->tcam_region_info,
-			     enc_key, erp_id,
+			     aentry->enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -458,7 +459,7 @@ mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE,
 			     priority, region->tcam_region_info,
-			     aentry->ht_key.enc_key, erp_id,
+			     aentry->enc_key, erp_id,
 			     aentry->delta_info.start,
 			     aentry->delta_info.mask,
 			     aentry->delta_info.value,
@@ -481,15 +482,15 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
-			 aentry->full_enc_key, mask);
+			 aentry->ht_key.full_enc_key, mask);
 
 	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
 	if (IS_ERR(erp_mask))
 		return PTR_ERR(erp_mask);
 	aentry->erp_mask = erp_mask;
 	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask);
-	memcpy(aentry->ht_key.enc_key, aentry->full_enc_key,
-	       sizeof(aentry->ht_key.enc_key));
+	memcpy(aentry->enc_key, aentry->ht_key.full_enc_key,
+	       sizeof(aentry->enc_key));
 
 	/* Compute all needed delta information and clear the delta bits
 	 * from the encrypted key.
@@ -498,8 +499,9 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta);
 	aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta);
 	aentry->delta_info.value =
-		mlxsw_sp_acl_erp_delta_value(delta, aentry->full_enc_key);
-	mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key);
+		mlxsw_sp_acl_erp_delta_value(delta,
+					     aentry->ht_key.full_enc_key);
+	mlxsw_sp_acl_erp_delta_clear(delta, aentry->enc_key);
 
 	/* Add rule to the list of A-TCAM rules, assuming this
 	 * rule is intended to A-TCAM. In case this rule does
@@ -579,6 +581,7 @@ int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	/* It is possible we failed to add the rule to the A-TCAM due to
 	 * exceeded number of masks. Try to spill into C-TCAM.
 	 */
+	trace_mlxsw_sp_acl_atcam_entry_add_ctcam_spill(mlxsw_sp, aregion);
 	err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &aregion->cregion,
 					   &achunk->cchunk, &aentry->centry,
 					   rulei, true);
@@ -603,7 +606,6 @@ void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 int
 mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 					struct mlxsw_sp_acl_atcam_region *aregion,
-					struct mlxsw_sp_acl_atcam_chunk *achunk,
 					struct mlxsw_sp_acl_atcam_entry *aentry,
 					struct mlxsw_sp_acl_rule_info *rulei)
 {
@@ -612,7 +614,6 @@ mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 	if (mlxsw_sp_acl_atcam_is_centry(aentry))
 		err = mlxsw_sp_acl_ctcam_entry_action_replace(mlxsw_sp,
 							      &aregion->cregion,
-							      &achunk->cchunk,
 							      &aentry->centry,
 							      rulei);
 	else
@@ -634,3 +635,14 @@ void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
 {
 	mlxsw_sp_acl_erps_fini(mlxsw_sp, atcam);
 }
+
+void *
+mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	return mlxsw_sp_acl_erp_rehash_hints_get(aregion);
+}
+
+void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv)
+{
+	mlxsw_sp_acl_erp_rehash_hints_put(hints_priv);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
index 505b87846acc..3a2de13fcb68 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -5,11 +5,13 @@
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/refcount.h>
+#include <linux/mutex.h>
 
 #include "spectrum.h"
 #include "spectrum_acl_tcam.h"
 
 struct mlxsw_sp_acl_bf {
+	struct mutex lock; /* Protects Bloom Filter updates. */
 	unsigned int bank_size;
 	refcount_t refcnt[0];
 };
@@ -133,7 +135,7 @@ mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 		memcpy(chunk + MLXSW_BLOOM_CHUNK_PAD_BYTES, &erp_region_id,
 		       sizeof(erp_region_id));
 		memcpy(chunk + MLXSW_BLOOM_CHUNK_KEY_OFFSET,
-		       &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
+		       &aentry->enc_key[chunk_key_offsets[chunk_index]],
 		       MLXSW_BLOOM_CHUNK_KEY_BYTES);
 		chunk += MLXSW_BLOOM_KEY_CHUNK_BYTES;
 	}
@@ -172,26 +174,36 @@ mlxsw_sp_acl_bf_entry_add(struct mlxsw_sp *mlxsw_sp,
 	u16 bf_index;
 	int err;
 
+	mutex_lock(&bf->lock);
+
 	bf_index = mlxsw_sp_acl_bf_index_get(bf, aregion, aentry);
 	rule_index = mlxsw_sp_acl_bf_rule_count_index_get(bf, erp_bank,
 							  bf_index);
 
-	if (refcount_inc_not_zero(&bf->refcnt[rule_index]))
-		return 0;
+	if (refcount_inc_not_zero(&bf->refcnt[rule_index])) {
+		err = 0;
+		goto unlock;
+	}
 
 	peabfe_pl = kmalloc(MLXSW_REG_PEABFE_LEN, GFP_KERNEL);
-	if (!peabfe_pl)
-		return -ENOMEM;
+	if (!peabfe_pl) {
+		err = -ENOMEM;
+		goto unlock;
+	}
 
 	mlxsw_reg_peabfe_pack(peabfe_pl);
 	mlxsw_reg_peabfe_rec_pack(peabfe_pl, 0, 1, erp_bank, bf_index);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(peabfe), peabfe_pl);
 	kfree(peabfe_pl);
 	if (err)
-		return err;
+		goto unlock;
 
 	refcount_set(&bf->refcnt[rule_index], 1);
-	return 0;
+	err = 0;
+
+unlock:
+	mutex_unlock(&bf->lock);
+	return err;
 }
 
 void
@@ -205,6 +217,8 @@ mlxsw_sp_acl_bf_entry_del(struct mlxsw_sp *mlxsw_sp,
 	char *peabfe_pl;
 	u16 bf_index;
 
+	mutex_lock(&bf->lock);
+
 	bf_index = mlxsw_sp_acl_bf_index_get(bf, aregion, aentry);
 	rule_index = mlxsw_sp_acl_bf_rule_count_index_get(bf, erp_bank,
 							  bf_index);
@@ -212,13 +226,16 @@ mlxsw_sp_acl_bf_entry_del(struct mlxsw_sp *mlxsw_sp,
 	if (refcount_dec_and_test(&bf->refcnt[rule_index])) {
 		peabfe_pl = kmalloc(MLXSW_REG_PEABFE_LEN, GFP_KERNEL);
 		if (!peabfe_pl)
-			return;
+			goto unlock;
 
 		mlxsw_reg_peabfe_pack(peabfe_pl);
 		mlxsw_reg_peabfe_rec_pack(peabfe_pl, 0, 0, erp_bank, bf_index);
 		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(peabfe), peabfe_pl);
 		kfree(peabfe_pl);
 	}
+
+unlock:
+	mutex_unlock(&bf->lock);
 }
 
 struct mlxsw_sp_acl_bf *
@@ -234,16 +251,19 @@ mlxsw_sp_acl_bf_init(struct mlxsw_sp *mlxsw_sp, unsigned int num_erp_banks)
 	 * is 2^ACL_MAX_BF_LOG
 	 */
 	bf_bank_size = 1 << MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_BF_LOG);
-	bf = kzalloc(sizeof(*bf) + bf_bank_size * num_erp_banks *
-		     sizeof(*bf->refcnt), GFP_KERNEL);
+	bf = kzalloc(struct_size(bf, refcnt, bf_bank_size * num_erp_banks),
+		     GFP_KERNEL);
 	if (!bf)
 		return ERR_PTR(-ENOMEM);
 
 	bf->bank_size = bf_bank_size;
+	mutex_init(&bf->lock);
+
 	return bf;
 }
 
 void mlxsw_sp_acl_bf_fini(struct mlxsw_sp_acl_bf *bf)
 {
+	mutex_destroy(&bf->lock);
 	kfree(bf);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index ac222833a5cf..05680a7e6c56 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -223,7 +223,6 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_acl_ctcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 					    struct mlxsw_sp_acl_ctcam_region *cregion,
-					    struct mlxsw_sp_acl_ctcam_chunk *cchunk,
 					    struct mlxsw_sp_acl_ctcam_entry *centry,
 					    struct mlxsw_sp_acl_rule_info *rulei)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 2941967e1cc5..4c98950380d5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -7,6 +7,7 @@
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/objagg.h>
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
@@ -63,6 +64,7 @@ struct mlxsw_sp_acl_erp_table {
 	unsigned int num_ctcam_erps;
 	unsigned int num_deltas;
 	struct objagg *objagg;
+	struct mutex objagg_lock; /* guards objagg manipulation */
 };
 
 struct mlxsw_sp_acl_erp_table_ops {
@@ -1001,17 +1003,15 @@ struct mlxsw_sp_acl_erp_mask *
 mlxsw_sp_acl_erp_mask_get(struct mlxsw_sp_acl_atcam_region *aregion,
 			  const char *mask, bool ctcam)
 {
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 	struct mlxsw_sp_acl_erp_key key;
 	struct objagg_obj *objagg_obj;
 
-	/* eRPs are allocated from a shared resource, but currently all
-	 * allocations are done under RTNL.
-	 */
-	ASSERT_RTNL();
-
 	memcpy(key.mask, mask, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 	key.ctcam = ctcam;
-	objagg_obj = objagg_obj_get(aregion->erp_table->objagg, &key);
+	mutex_lock(&erp_table->objagg_lock);
+	objagg_obj = objagg_obj_get(erp_table->objagg, &key);
+	mutex_unlock(&erp_table->objagg_lock);
 	if (IS_ERR(objagg_obj))
 		return ERR_CAST(objagg_obj);
 	return (struct mlxsw_sp_acl_erp_mask *) objagg_obj;
@@ -1021,8 +1021,11 @@ void mlxsw_sp_acl_erp_mask_put(struct mlxsw_sp_acl_atcam_region *aregion,
 			       struct mlxsw_sp_acl_erp_mask *erp_mask)
 {
 	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 
-	objagg_obj_put(aregion->erp_table->objagg, objagg_obj);
+	mutex_lock(&erp_table->objagg_lock);
+	objagg_obj_put(erp_table->objagg, objagg_obj);
+	mutex_unlock(&erp_table->objagg_lock);
 }
 
 int mlxsw_sp_acl_erp_bf_insert(struct mlxsw_sp *mlxsw_sp,
@@ -1034,7 +1037,6 @@ int mlxsw_sp_acl_erp_bf_insert(struct mlxsw_sp *mlxsw_sp,
 	const struct mlxsw_sp_acl_erp *erp = objagg_obj_root_priv(objagg_obj);
 	unsigned int erp_bank;
 
-	ASSERT_RTNL();
 	if (!mlxsw_sp_acl_erp_table_is_used(erp->erp_table))
 		return 0;
 
@@ -1169,13 +1171,12 @@ mlxsw_sp_acl_erp_delta_fill(const struct mlxsw_sp_acl_erp_key *parent_key,
 			return -EINVAL;
 	}
 	if (si == -1) {
-		/* The masks are the same, this cannot happen.
-		 * That means the caller is broken.
+		/* The masks are the same, this can happen in case eRPs with
+		 * the same mask were created in both A-TCAM and C-TCAM.
+		 * The only possible condition under which this can happen
+		 * is identical rule insertion. Delta is not possible here.
 		 */
-		WARN_ON(1);
-		*delta_start = 0;
-		*delta_mask = 0;
-		return 0;
+		return -EINVAL;
 	}
 	pmask = (unsigned char) parent_key->mask[__MASK_IDX(si)];
 	mask = (unsigned char) key->mask[__MASK_IDX(si)];
@@ -1200,6 +1201,32 @@ mlxsw_sp_acl_erp_delta_fill(const struct mlxsw_sp_acl_erp_key *parent_key,
 	return 0;
 }
 
+static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj,
+					 const void *obj)
+{
+	const struct mlxsw_sp_acl_erp_key *parent_key = parent_obj;
+	const struct mlxsw_sp_acl_erp_key *key = obj;
+	u16 delta_start;
+	u8 delta_mask;
+	int err;
+
+	err = mlxsw_sp_acl_erp_delta_fill(parent_key, key,
+					  &delta_start, &delta_mask);
+	return err ? false : true;
+}
+
+static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2)
+{
+	const struct mlxsw_sp_acl_erp_key *key1 = obj1;
+	const struct mlxsw_sp_acl_erp_key *key2 = obj2;
+
+	/* For hints purposes, two objects are considered equal
+	 * in case the masks are the same. Does not matter what
+	 * the "ctcam" value is.
+	 */
+	return memcmp(key1->mask, key2->mask, sizeof(key1->mask));
+}
+
 static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj,
 					   void *obj)
 {
@@ -1254,12 +1281,17 @@ static void mlxsw_sp_acl_erp_delta_destroy(void *priv, void *delta_priv)
 	kfree(delta);
 }
 
-static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj)
+static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj,
+					  unsigned int root_id)
 {
 	struct mlxsw_sp_acl_atcam_region *aregion = priv;
 	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 	struct mlxsw_sp_acl_erp_key *key = obj;
 
+	if (!key->ctcam &&
+	    root_id != OBJAGG_OBJ_ROOT_ID_INVALID &&
+	    root_id >= MLXSW_SP_ACL_ERP_MAX_PER_REGION)
+		return ERR_PTR(-ENOBUFS);
 	return erp_table->ops->erp_create(erp_table, key);
 }
 
@@ -1273,6 +1305,8 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv)
 
 static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = {
 	.obj_size = sizeof(struct mlxsw_sp_acl_erp_key),
+	.delta_check = mlxsw_sp_acl_erp_delta_check,
+	.hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp,
 	.delta_create = mlxsw_sp_acl_erp_delta_create,
 	.delta_destroy = mlxsw_sp_acl_erp_delta_destroy,
 	.root_create = mlxsw_sp_acl_erp_root_create,
@@ -1280,7 +1314,8 @@ static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = {
 };
 
 static struct mlxsw_sp_acl_erp_table *
-mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
+mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion,
+			      struct objagg_hints *hints)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table;
 	int err;
@@ -1290,7 +1325,7 @@ mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
 		return ERR_PTR(-ENOMEM);
 
 	erp_table->objagg = objagg_create(&mlxsw_sp_acl_erp_objagg_ops,
-					  aregion);
+					  hints, aregion);
 	if (IS_ERR(erp_table->objagg)) {
 		err = PTR_ERR(erp_table->objagg);
 		goto err_objagg_create;
@@ -1300,6 +1335,7 @@ mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
 	erp_table->ops = &erp_no_mask_ops;
 	INIT_LIST_HEAD(&erp_table->atcam_erps_list);
 	erp_table->aregion = aregion;
+	mutex_init(&erp_table->objagg_lock);
 
 	return erp_table;
 
@@ -1312,6 +1348,7 @@ static void
 mlxsw_sp_acl_erp_table_destroy(struct mlxsw_sp_acl_erp_table *erp_table)
 {
 	WARN_ON(!list_empty(&erp_table->atcam_erps_list));
+	mutex_destroy(&erp_table->objagg_lock);
 	objagg_destroy(erp_table->objagg);
 	kfree(erp_table);
 }
@@ -1337,12 +1374,93 @@ mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
 }
 
-int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion)
+static int
+mlxsw_sp_acl_erp_hints_check(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_atcam_region *aregion,
+			     struct objagg_hints *hints, bool *p_rehash_needed)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	const struct objagg_stats *ostats;
+	const struct objagg_stats *hstats;
+	int err;
+
+	*p_rehash_needed = false;
+
+	mutex_lock(&erp_table->objagg_lock);
+	ostats = objagg_stats_get(erp_table->objagg);
+	mutex_unlock(&erp_table->objagg_lock);
+	if (IS_ERR(ostats)) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP stats\n");
+		return PTR_ERR(ostats);
+	}
+
+	hstats = objagg_hints_stats_get(hints);
+	if (IS_ERR(hstats)) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP hints stats\n");
+		err = PTR_ERR(hstats);
+		goto err_hints_stats_get;
+	}
+
+	/* Very basic criterion for now. */
+	if (hstats->root_count < ostats->root_count)
+		*p_rehash_needed = true;
+
+	err = 0;
+
+	objagg_stats_put(hstats);
+err_hints_stats_get:
+	objagg_stats_put(ostats);
+	return err;
+}
+
+void *
+mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	struct objagg_hints *hints;
+	bool rehash_needed;
+	int err;
+
+	mutex_lock(&erp_table->objagg_lock);
+	hints = objagg_hints_get(erp_table->objagg,
+				 OBJAGG_OPT_ALGO_SIMPLE_GREEDY);
+	mutex_unlock(&erp_table->objagg_lock);
+	if (IS_ERR(hints)) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to create ERP hints\n");
+		return ERR_CAST(hints);
+	}
+	err = mlxsw_sp_acl_erp_hints_check(mlxsw_sp, aregion, hints,
+					   &rehash_needed);
+	if (err)
+		goto errout;
+
+	if (!rehash_needed) {
+		err = -EAGAIN;
+		goto errout;
+	}
+	return hints;
+
+errout:
+	objagg_hints_put(hints);
+	return ERR_PTR(err);
+}
+
+void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv)
+{
+	struct objagg_hints *hints = hints_priv;
+
+	objagg_hints_put(hints);
+}
+
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				 void *hints_priv)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table;
+	struct objagg_hints *hints = hints_priv;
 	int err;
 
-	erp_table = mlxsw_sp_acl_erp_table_create(aregion);
+	erp_table = mlxsw_sp_acl_erp_table_create(aregion, hints);
 	if (IS_ERR(erp_table))
 		return PTR_ERR(erp_table);
 	aregion->erp_table = erp_table;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 2a998dea4f39..279c241f76f0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -12,7 +12,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x02, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
@@ -20,7 +20,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x02, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
@@ -32,13 +32,13 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
@@ -149,7 +149,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_4[] = {
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x04, 16, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x04, 0, 8), /* RX_ACL_SYSTEM_PORT */
+	MLXSW_AFK_ELEMENT_INST_EXT_U32(SRC_SYS_PORT, 0x04, 0, 8, -1, true), /* RX_ACL_SYSTEM_PORT */
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_0[] = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index fe230acf92a9..e993159e8e4c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -8,6 +8,8 @@
 #include <linux/list.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <linux/mutex.h>
+#include <trace/events/mlxsw.h>
 
 #include "reg.h"
 #include "core.h"
@@ -23,6 +25,10 @@ size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp)
 	return ops->priv_size;
 }
 
+#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT 5000 /* ms */
+#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN 3000 /* ms */
+#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS 100 /* number of entries */
+
 int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_tcam *tcam)
 {
@@ -33,6 +39,11 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 	size_t alloc_size;
 	int err;
 
+	mutex_init(&tcam->lock);
+	tcam->vregion_rehash_intrvl =
+			MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT;
+	INIT_LIST_HEAD(&tcam->vregion_list);
+
 	max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 					      ACL_MAX_TCAM_REGIONS);
 	max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS);
@@ -76,6 +87,7 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
+	mutex_destroy(&tcam->lock);
 	ops->fini(mlxsw_sp, tcam->priv);
 	kfree(tcam->used_groups);
 	kfree(tcam->used_regions);
@@ -153,37 +165,99 @@ struct mlxsw_sp_acl_tcam_pattern {
 struct mlxsw_sp_acl_tcam_group {
 	struct mlxsw_sp_acl_tcam *tcam;
 	u16 id;
+	struct mutex lock; /* guards region list updates */
 	struct list_head region_list;
 	unsigned int region_count;
-	struct rhashtable chunk_ht;
-	struct mlxsw_sp_acl_tcam_group_ops *ops;
+};
+
+struct mlxsw_sp_acl_tcam_vgroup {
+	struct mlxsw_sp_acl_tcam_group group;
+	struct list_head vregion_list;
+	struct rhashtable vchunk_ht;
 	const struct mlxsw_sp_acl_tcam_pattern *patterns;
 	unsigned int patterns_count;
 	bool tmplt_elusage_set;
 	struct mlxsw_afk_element_usage tmplt_elusage;
+	bool vregion_rehash_enabled;
 };
 
-struct mlxsw_sp_acl_tcam_chunk {
-	struct list_head list; /* Member of a TCAM region */
-	struct rhash_head ht_node; /* Member of a chunk HT */
-	unsigned int priority; /* Priority within the region and group */
-	struct mlxsw_sp_acl_tcam_group *group;
+struct mlxsw_sp_acl_tcam_rehash_ctx {
+	void *hints_priv;
+	bool this_is_rollback;
+	struct mlxsw_sp_acl_tcam_vchunk *current_vchunk; /* vchunk being
+							  * currently migrated.
+							  */
+	struct mlxsw_sp_acl_tcam_ventry *start_ventry; /* ventry to start
+							* migration from in
+							* a vchunk being
+							* currently migrated.
+							*/
+	struct mlxsw_sp_acl_tcam_ventry *stop_ventry; /* ventry to stop
+						       * migration at
+						       * a vchunk being
+						       * currently migrated.
+						       */
+};
+
+struct mlxsw_sp_acl_tcam_vregion {
+	struct mutex lock; /* Protects consistency of region, region2 pointers
+			    * and vchunk_list.
+			    */
 	struct mlxsw_sp_acl_tcam_region *region;
+	struct mlxsw_sp_acl_tcam_region *region2; /* Used during migration */
+	struct list_head list; /* Member of a TCAM group */
+	struct list_head tlist; /* Member of a TCAM */
+	struct list_head vchunk_list; /* List of vchunks under this vregion */
+	struct mlxsw_afk_key_info *key_info;
+	struct mlxsw_sp_acl_tcam *tcam;
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup;
+	struct {
+		struct delayed_work dw;
+		struct mlxsw_sp_acl_tcam_rehash_ctx ctx;
+	} rehash;
+	struct mlxsw_sp *mlxsw_sp;
 	unsigned int ref_count;
+};
+
+struct mlxsw_sp_acl_tcam_vchunk;
+
+struct mlxsw_sp_acl_tcam_chunk {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct mlxsw_sp_acl_tcam_region *region;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
 
+struct mlxsw_sp_acl_tcam_vchunk {
+	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_chunk *chunk2; /* Used during migration */
+	struct list_head list; /* Member of a TCAM vregion */
+	struct rhash_head ht_node; /* Member of a chunk HT */
+	struct list_head ventry_list;
+	unsigned int priority; /* Priority within the vregion and group */
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	unsigned int ref_count;
+};
+
 struct mlxsw_sp_acl_tcam_entry {
+	struct mlxsw_sp_acl_tcam_ventry *ventry;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
 
-static const struct rhashtable_params mlxsw_sp_acl_tcam_chunk_ht_params = {
+struct mlxsw_sp_acl_tcam_ventry {
+	struct mlxsw_sp_acl_tcam_entry *entry;
+	struct list_head list; /* Member of a TCAM vchunk */
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct mlxsw_sp_acl_rule_info *rulei;
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_tcam_vchunk_ht_params = {
 	.key_len = sizeof(unsigned int),
-	.key_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, priority),
-	.head_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, ht_node),
+	.key_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, priority),
+	.head_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, ht_node),
 	.automatic_shrinking = true,
 };
 
@@ -195,55 +269,90 @@ static int mlxsw_sp_acl_tcam_group_update(struct mlxsw_sp *mlxsw_sp,
 	int acl_index = 0;
 
 	mlxsw_reg_pagt_pack(pagt_pl, group->id);
-	list_for_each_entry(region, &group->region_list, list)
-		mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, region->id);
+	list_for_each_entry(region, &group->region_list, list) {
+		bool multi = false;
+
+		/* Check if the next entry in the list has the same vregion. */
+		if (region->list.next != &group->region_list &&
+		    list_next_entry(region, list)->vregion == region->vregion)
+			multi = true;
+		mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++,
+					   region->id, multi);
+	}
 	mlxsw_reg_pagt_size_set(pagt_pl, acl_index);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pagt), pagt_pl);
 }
 
 static int
-mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_tcam *tcam,
-			    struct mlxsw_sp_acl_tcam_group *group,
-			    const struct mlxsw_sp_acl_tcam_pattern *patterns,
-			    unsigned int patterns_count,
-			    struct mlxsw_afk_element_usage *tmplt_elusage)
+mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp_acl_tcam *tcam,
+			    struct mlxsw_sp_acl_tcam_group *group)
 {
 	int err;
 
 	group->tcam = tcam;
-	group->patterns = patterns;
-	group->patterns_count = patterns_count;
-	if (tmplt_elusage) {
-		group->tmplt_elusage_set = true;
-		memcpy(&group->tmplt_elusage, tmplt_elusage,
-		       sizeof(group->tmplt_elusage));
-	}
+	mutex_init(&group->lock);
 	INIT_LIST_HEAD(&group->region_list);
+
 	err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id);
 	if (err)
 		return err;
 
-	err = rhashtable_init(&group->chunk_ht,
-			      &mlxsw_sp_acl_tcam_chunk_ht_params);
+	return 0;
+}
+
+static void mlxsw_sp_acl_tcam_group_del(struct mlxsw_sp_acl_tcam_group *group)
+{
+	struct mlxsw_sp_acl_tcam *tcam = group->tcam;
+
+	mutex_destroy(&group->lock);
+	mlxsw_sp_acl_tcam_group_id_put(tcam, group->id);
+	WARN_ON(!list_empty(&group->region_list));
+}
+
+static int
+mlxsw_sp_acl_tcam_vgroup_add(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_tcam *tcam,
+			     struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+			     const struct mlxsw_sp_acl_tcam_pattern *patterns,
+			     unsigned int patterns_count,
+			     struct mlxsw_afk_element_usage *tmplt_elusage,
+			     bool vregion_rehash_enabled)
+{
+	int err;
+
+	vgroup->patterns = patterns;
+	vgroup->patterns_count = patterns_count;
+	vgroup->vregion_rehash_enabled = vregion_rehash_enabled;
+
+	if (tmplt_elusage) {
+		vgroup->tmplt_elusage_set = true;
+		memcpy(&vgroup->tmplt_elusage, tmplt_elusage,
+		       sizeof(vgroup->tmplt_elusage));
+	}
+	INIT_LIST_HEAD(&vgroup->vregion_list);
+
+	err = mlxsw_sp_acl_tcam_group_add(tcam, &vgroup->group);
+	if (err)
+		return err;
+
+	err = rhashtable_init(&vgroup->vchunk_ht,
+			      &mlxsw_sp_acl_tcam_vchunk_ht_params);
 	if (err)
 		goto err_rhashtable_init;
 
 	return 0;
 
 err_rhashtable_init:
-	mlxsw_sp_acl_tcam_group_id_put(tcam, group->id);
+	mlxsw_sp_acl_tcam_group_del(&vgroup->group);
 	return err;
 }
 
-static void mlxsw_sp_acl_tcam_group_del(struct mlxsw_sp *mlxsw_sp,
-					struct mlxsw_sp_acl_tcam_group *group)
+static void
+mlxsw_sp_acl_tcam_vgroup_del(struct mlxsw_sp_acl_tcam_vgroup *vgroup)
 {
-	struct mlxsw_sp_acl_tcam *tcam = group->tcam;
-
-	rhashtable_destroy(&group->chunk_ht);
-	mlxsw_sp_acl_tcam_group_id_put(tcam, group->id);
-	WARN_ON(!list_empty(&group->region_list));
+	rhashtable_destroy(&vgroup->vchunk_ht);
+	mlxsw_sp_acl_tcam_group_del(&vgroup->group);
+	WARN_ON(!list_empty(&vgroup->vregion_list));
 }
 
 static int
@@ -283,146 +392,194 @@ mlxsw_sp_acl_tcam_group_id(struct mlxsw_sp_acl_tcam_group *group)
 }
 
 static unsigned int
-mlxsw_sp_acl_tcam_region_prio(struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vregion_prio(struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 
-	if (list_empty(&region->chunk_list))
+	if (list_empty(&vregion->vchunk_list))
 		return 0;
-	/* As a priority of a region, return priority of the first chunk */
-	chunk = list_first_entry(&region->chunk_list, typeof(*chunk), list);
-	return chunk->priority;
+	/* As a priority of a vregion, return priority of the first vchunk */
+	vchunk = list_first_entry(&vregion->vchunk_list,
+				  typeof(*vchunk), list);
+	return vchunk->priority;
 }
 
 static unsigned int
-mlxsw_sp_acl_tcam_region_max_prio(struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vregion_max_prio(struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 
-	if (list_empty(&region->chunk_list))
+	if (list_empty(&vregion->vchunk_list))
 		return 0;
-	chunk = list_last_entry(&region->chunk_list, typeof(*chunk), list);
-	return chunk->priority;
+	vchunk = list_last_entry(&vregion->vchunk_list,
+				 typeof(*vchunk), list);
+	return vchunk->priority;
 }
 
-static void
-mlxsw_sp_acl_tcam_group_list_add(struct mlxsw_sp_acl_tcam_group *group,
-				 struct mlxsw_sp_acl_tcam_region *region)
+static int
+mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_acl_tcam_group *group,
+				      struct mlxsw_sp_acl_tcam_region *region,
+				      unsigned int priority,
+				      struct mlxsw_sp_acl_tcam_region *next_region)
 {
 	struct mlxsw_sp_acl_tcam_region *region2;
 	struct list_head *pos;
+	int err;
 
-	/* Position the region inside the list according to priority */
-	list_for_each(pos, &group->region_list) {
-		region2 = list_entry(pos, typeof(*region2), list);
-		if (mlxsw_sp_acl_tcam_region_prio(region2) >
-		    mlxsw_sp_acl_tcam_region_prio(region))
-			break;
+	mutex_lock(&group->lock);
+	if (group->region_count == group->tcam->max_group_size) {
+		err = -ENOBUFS;
+		goto err_region_count_check;
+	}
+
+	if (next_region) {
+		/* If the next region is defined, place the new one
+		 * before it. The next one is a sibling.
+		 */
+		pos = &next_region->list;
+	} else {
+		/* Position the region inside the list according to priority */
+		list_for_each(pos, &group->region_list) {
+			region2 = list_entry(pos, typeof(*region2), list);
+			if (mlxsw_sp_acl_tcam_vregion_prio(region2->vregion) >
+			    priority)
+				break;
+		}
 	}
 	list_add_tail(&region->list, pos);
+	region->group = group;
+
+	err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	if (err)
+		goto err_group_update;
+
 	group->region_count++;
+	mutex_unlock(&group->lock);
+	return 0;
+
+err_group_update:
+	list_del(&region->list);
+err_region_count_check:
+	mutex_unlock(&group->lock);
+	return err;
 }
 
 static void
-mlxsw_sp_acl_tcam_group_list_del(struct mlxsw_sp_acl_tcam_group *group,
-				 struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_acl_tcam_region *region)
 {
-	group->region_count--;
+	struct mlxsw_sp_acl_tcam_group *group = region->group;
+
+	mutex_lock(&group->lock);
 	list_del(&region->list);
+	group->region_count--;
+	mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	mutex_unlock(&group->lock);
 }
 
 static int
-mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_group *group,
-				      struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vgroup_vregion_attach(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+					struct mlxsw_sp_acl_tcam_vregion *vregion,
+					unsigned int priority)
 {
+	struct mlxsw_sp_acl_tcam_vregion *vregion2;
+	struct list_head *pos;
 	int err;
 
-	if (group->region_count == group->tcam->max_group_size)
-		return -ENOBUFS;
-
-	mlxsw_sp_acl_tcam_group_list_add(group, region);
+	/* Position the vregion inside the list according to priority */
+	list_for_each(pos, &vgroup->vregion_list) {
+		vregion2 = list_entry(pos, typeof(*vregion2), list);
+		if (mlxsw_sp_acl_tcam_vregion_prio(vregion2) > priority)
+			break;
+	}
+	list_add_tail(&vregion->list, pos);
 
-	err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, &vgroup->group,
+						    vregion->region,
+						    priority, NULL);
 	if (err)
-		goto err_group_update;
-	region->group = group;
+		goto err_region_attach;
 
 	return 0;
 
-err_group_update:
-	mlxsw_sp_acl_tcam_group_list_del(group, region);
-	mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+err_region_attach:
+	list_del(&vregion->list);
 	return err;
 }
 
 static void
-mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vgroup_vregion_detach(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_group *group = region->group;
-
-	mlxsw_sp_acl_tcam_group_list_del(group, region);
-	mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	list_del(&vregion->list);
+	if (vregion->region2)
+		mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp,
+						      vregion->region2);
+	mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, vregion->region);
 }
 
-static struct mlxsw_sp_acl_tcam_region *
-mlxsw_sp_acl_tcam_group_region_find(struct mlxsw_sp_acl_tcam_group *group,
-				    unsigned int priority,
-				    struct mlxsw_afk_element_usage *elusage,
-				    bool *p_need_split)
+static struct mlxsw_sp_acl_tcam_vregion *
+mlxsw_sp_acl_tcam_vgroup_vregion_find(struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				      unsigned int priority,
+				      struct mlxsw_afk_element_usage *elusage,
+				      bool *p_need_split)
 {
-	struct mlxsw_sp_acl_tcam_region *region, *region2;
+	struct mlxsw_sp_acl_tcam_vregion *vregion, *vregion2;
 	struct list_head *pos;
 	bool issubset;
 
-	list_for_each(pos, &group->region_list) {
-		region = list_entry(pos, typeof(*region), list);
+	list_for_each(pos, &vgroup->vregion_list) {
+		vregion = list_entry(pos, typeof(*vregion), list);
 
 		/* First, check if the requested priority does not rather belong
-		 * under some of the next regions.
+		 * under some of the next vregions.
 		 */
-		if (pos->next != &group->region_list) { /* not last */
-			region2 = list_entry(pos->next, typeof(*region2), list);
-			if (priority >= mlxsw_sp_acl_tcam_region_prio(region2))
+		if (pos->next != &vgroup->vregion_list) { /* not last */
+			vregion2 = list_entry(pos->next, typeof(*vregion2),
+					      list);
+			if (priority >=
+			    mlxsw_sp_acl_tcam_vregion_prio(vregion2))
 				continue;
 		}
 
-		issubset = mlxsw_afk_key_info_subset(region->key_info, elusage);
+		issubset = mlxsw_afk_key_info_subset(vregion->key_info,
+						     elusage);
 
 		/* If requested element usage would not fit and the priority
-		 * is lower than the currently inspected region we cannot
-		 * use this region, so return NULL to indicate new region has
+		 * is lower than the currently inspected vregion we cannot
+		 * use this region, so return NULL to indicate new vregion has
 		 * to be created.
 		 */
 		if (!issubset &&
-		    priority < mlxsw_sp_acl_tcam_region_prio(region))
+		    priority < mlxsw_sp_acl_tcam_vregion_prio(vregion))
 			return NULL;
 
 		/* If requested element usage would not fit and the priority
-		 * is higher than the currently inspected region we cannot
-		 * use this region. There is still some hope that the next
-		 * region would be the fit. So let it be processed and
+		 * is higher than the currently inspected vregion we cannot
+		 * use this vregion. There is still some hope that the next
+		 * vregion would be the fit. So let it be processed and
 		 * eventually break at the check right above this.
 		 */
 		if (!issubset &&
-		    priority > mlxsw_sp_acl_tcam_region_max_prio(region))
+		    priority > mlxsw_sp_acl_tcam_vregion_max_prio(vregion))
 			continue;
 
-		/* Indicate if the region needs to be split in order to add
+		/* Indicate if the vregion needs to be split in order to add
 		 * the requested priority. Split is needed when requested
-		 * element usage won't fit into the found region.
+		 * element usage won't fit into the found vregion.
 		 */
 		*p_need_split = !issubset;
-		return region;
+		return vregion;
 	}
-	return NULL; /* New region has to be created. */
+	return NULL; /* New vregion has to be created. */
 }
 
 static void
-mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
-				     struct mlxsw_afk_element_usage *elusage,
-				     struct mlxsw_afk_element_usage *out)
+mlxsw_sp_acl_tcam_vgroup_use_patterns(struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				      struct mlxsw_afk_element_usage *elusage,
+				      struct mlxsw_afk_element_usage *out)
 {
 	const struct mlxsw_sp_acl_tcam_pattern *pattern;
 	int i;
@@ -430,14 +587,14 @@ mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
 	/* In case the template is set, we don't have to look up the pattern
 	 * and just use the template.
 	 */
-	if (group->tmplt_elusage_set) {
-		memcpy(out, &group->tmplt_elusage, sizeof(*out));
+	if (vgroup->tmplt_elusage_set) {
+		memcpy(out, &vgroup->tmplt_elusage, sizeof(*out));
 		WARN_ON(!mlxsw_afk_element_usage_subset(elusage, out));
 		return;
 	}
 
-	for (i = 0; i < group->patterns_count; i++) {
-		pattern = &group->patterns[i];
+	for (i = 0; i < vgroup->patterns_count; i++) {
+		pattern = &vgroup->patterns[i];
 		mlxsw_afk_element_usage_fill(out, pattern->elements,
 					     pattern->elements_count);
 		if (mlxsw_afk_element_usage_subset(elusage, out))
@@ -511,24 +668,19 @@ mlxsw_sp_acl_tcam_region_disable(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_acl_tcam_region *
 mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam *tcam,
-				struct mlxsw_afk_element_usage *elusage)
+				struct mlxsw_sp_acl_tcam_vregion *vregion,
+				void *hints_priv)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	struct mlxsw_sp_acl_tcam_region *region;
 	int err;
 
 	region = kzalloc(sizeof(*region) + ops->region_priv_size, GFP_KERNEL);
 	if (!region)
 		return ERR_PTR(-ENOMEM);
-	INIT_LIST_HEAD(&region->chunk_list);
 	region->mlxsw_sp = mlxsw_sp;
-
-	region->key_info = mlxsw_afk_key_info_get(afk, elusage);
-	if (IS_ERR(region->key_info)) {
-		err = PTR_ERR(region->key_info);
-		goto err_key_info_get;
-	}
+	region->vregion = vregion;
+	region->key_info = vregion->key_info;
 
 	err = mlxsw_sp_acl_tcam_region_id_get(tcam, &region->id);
 	if (err)
@@ -547,7 +699,8 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_tcam_region_enable;
 
-	err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, region);
+	err = ops->region_init(mlxsw_sp, region->priv, tcam->priv,
+			       region, hints_priv);
 	if (err)
 		goto err_tcam_region_init;
 
@@ -561,8 +714,6 @@ err_tcam_region_alloc:
 err_tcam_region_associate:
 	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 err_region_id_get:
-	mlxsw_afk_key_info_put(region->key_info);
-err_key_info_get:
 	kfree(region);
 	return ERR_PTR(err);
 }
@@ -576,220 +727,415 @@ mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
-	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, region->id);
-	mlxsw_afk_key_info_put(region->key_info);
+	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam,
+					region->id);
 	kfree(region);
 }
 
-static int
-mlxsw_sp_acl_tcam_chunk_assoc(struct mlxsw_sp *mlxsw_sp,
-			      struct mlxsw_sp_acl_tcam_group *group,
-			      unsigned int priority,
-			      struct mlxsw_afk_element_usage *elusage,
-			      struct mlxsw_sp_acl_tcam_chunk *chunk)
+static void
+mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_region *region;
-	bool region_created = false;
-	bool need_split;
-	int err;
+	unsigned long interval = vregion->tcam->vregion_rehash_intrvl;
+
+	if (!interval)
+		return;
+	mlxsw_core_schedule_dw(&vregion->rehash.dw,
+			       msecs_to_jiffies(interval));
+}
+
+static void
+mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vregion *vregion,
+				 int *credits);
 
-	region = mlxsw_sp_acl_tcam_group_region_find(group, priority, elusage,
-						     &need_split);
-	if (region && need_split) {
-		/* According to priority, the chunk should belong to an
-		 * existing region. However, this chunk needs elements
-		 * that region does not contain. We need to split the existing
-		 * region into two and create a new region for this chunk
-		 * in between. This is not supported now.
+static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion =
+		container_of(work, struct mlxsw_sp_acl_tcam_vregion,
+			     rehash.dw.work);
+	int credits = MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS;
+
+	mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion, &credits);
+	if (credits < 0)
+		/* Rehash gone out of credits so it was interrupted.
+		 * Schedule the work as soon as possible to continue.
 		 */
-		return -EOPNOTSUPP;
-	}
-	if (!region) {
-		struct mlxsw_afk_element_usage region_elusage;
-
-		mlxsw_sp_acl_tcam_group_use_patterns(group, elusage,
-						     &region_elusage);
-		region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, group->tcam,
-							 &region_elusage);
-		if (IS_ERR(region))
-			return PTR_ERR(region);
-		region_created = true;
+		mlxsw_core_schedule_dw(&vregion->rehash.dw, 0);
+	else
+		mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion);
+}
+
+static void
+mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(struct mlxsw_sp_acl_tcam_vchunk *vchunk)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion;
+
+	/* If a rule was added or deleted from vchunk which is currently
+	 * under rehash migration, we have to reset the ventry pointers
+	 * to make sure all rules are properly migrated.
+	 */
+	if (vregion->rehash.ctx.current_vchunk == vchunk) {
+		vregion->rehash.ctx.start_ventry = NULL;
+		vregion->rehash.ctx.stop_ventry = NULL;
 	}
+}
 
-	chunk->region = region;
-	list_add_tail(&chunk->list, &region->chunk_list);
+static void
+mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(struct mlxsw_sp_acl_tcam_vregion *vregion)
+{
+	/* If a chunk was added or deleted from vregion we have to reset
+	 * the current chunk pointer to make sure all chunks
+	 * are properly migrated.
+	 */
+	vregion->rehash.ctx.current_vchunk = NULL;
+}
 
-	if (!region_created)
-		return 0;
+static struct mlxsw_sp_acl_tcam_vregion *
+mlxsw_sp_acl_tcam_vregion_create(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				 unsigned int priority,
+				 struct mlxsw_afk_element_usage *elusage)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	struct mlxsw_sp_acl_tcam *tcam = vgroup->group.tcam;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	int err;
+
+	vregion = kzalloc(sizeof(*vregion), GFP_KERNEL);
+	if (!vregion)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&vregion->vchunk_list);
+	mutex_init(&vregion->lock);
+	vregion->tcam = tcam;
+	vregion->mlxsw_sp = mlxsw_sp;
+	vregion->vgroup = vgroup;
+	vregion->ref_count = 1;
+
+	vregion->key_info = mlxsw_afk_key_info_get(afk, elusage);
+	if (IS_ERR(vregion->key_info)) {
+		err = PTR_ERR(vregion->key_info);
+		goto err_key_info_get;
+	}
+
+	vregion->region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, tcam,
+							  vregion, NULL);
+	if (IS_ERR(vregion->region)) {
+		err = PTR_ERR(vregion->region);
+		goto err_region_create;
+	}
 
-	err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, group, region);
+	err = mlxsw_sp_acl_tcam_vgroup_vregion_attach(mlxsw_sp, vgroup, vregion,
+						      priority);
 	if (err)
-		goto err_group_region_attach;
+		goto err_vgroup_vregion_attach;
+
+	if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) {
+		/* Create the delayed work for vregion periodic rehash */
+		INIT_DELAYED_WORK(&vregion->rehash.dw,
+				  mlxsw_sp_acl_tcam_vregion_rehash_work);
+		mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion);
+		mutex_lock(&tcam->lock);
+		list_add_tail(&vregion->tlist, &tcam->vregion_list);
+		mutex_unlock(&tcam->lock);
+	}
 
-	return 0;
+	return vregion;
 
-err_group_region_attach:
-	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region);
-	return err;
+err_vgroup_vregion_attach:
+	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region);
+err_region_create:
+	mlxsw_afk_key_info_put(vregion->key_info);
+err_key_info_get:
+	kfree(vregion);
+	return ERR_PTR(err);
 }
 
 static void
-mlxsw_sp_acl_tcam_chunk_deassoc(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_acl_tcam_chunk *chunk)
+mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_tcam_vregion *vregion)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup = vregion->vgroup;
+	struct mlxsw_sp_acl_tcam *tcam = vregion->tcam;
+
+	if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) {
+		mutex_lock(&tcam->lock);
+		list_del(&vregion->tlist);
+		mutex_unlock(&tcam->lock);
+		cancel_delayed_work_sync(&vregion->rehash.dw);
+	}
+	mlxsw_sp_acl_tcam_vgroup_vregion_detach(mlxsw_sp, vregion);
+	if (vregion->region2)
+		mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region2);
+	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region);
+	mlxsw_afk_key_info_put(vregion->key_info);
+	mutex_destroy(&vregion->lock);
+	kfree(vregion);
+}
+
+u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	u32 vregion_rehash_intrvl;
+
+	if (WARN_ON(!ops->region_rehash_hints_get))
+		return 0;
+	vregion_rehash_intrvl = tcam->vregion_rehash_intrvl;
+	return vregion_rehash_intrvl;
+}
+
+int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam,
+						u32 val)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+
+	if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val)
+		return -EINVAL;
+	if (WARN_ON(!ops->region_rehash_hints_get))
+		return -EOPNOTSUPP;
+	tcam->vregion_rehash_intrvl = val;
+	mutex_lock(&tcam->lock);
+	list_for_each_entry(vregion, &tcam->vregion_list, tlist) {
+		if (val)
+			mlxsw_core_schedule_dw(&vregion->rehash.dw, 0);
+		else
+			cancel_delayed_work_sync(&vregion->rehash.dw);
+	}
+	mutex_unlock(&tcam->lock);
+	return 0;
+}
+
+static struct mlxsw_sp_acl_tcam_vregion *
+mlxsw_sp_acl_tcam_vregion_get(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+			      unsigned int priority,
+			      struct mlxsw_afk_element_usage *elusage)
 {
-	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
+	struct mlxsw_afk_element_usage vregion_elusage;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	bool need_split;
 
-	list_del(&chunk->list);
-	if (list_empty(&region->chunk_list)) {
-		mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, region);
-		mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region);
+	vregion = mlxsw_sp_acl_tcam_vgroup_vregion_find(vgroup, priority,
+							elusage, &need_split);
+	if (vregion) {
+		if (need_split) {
+			/* According to priority, new vchunk should belong to
+			 * an existing vregion. However, this vchunk needs
+			 * elements that vregion does not contain. We need
+			 * to split the existing vregion into two and create
+			 * a new vregion for the new vchunk in between.
+			 * This is not supported now.
+			 */
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+		vregion->ref_count++;
+		return vregion;
 	}
+
+	mlxsw_sp_acl_tcam_vgroup_use_patterns(vgroup, elusage,
+					      &vregion_elusage);
+
+	return mlxsw_sp_acl_tcam_vregion_create(mlxsw_sp, vgroup, priority,
+						&vregion_elusage);
+}
+
+static void
+mlxsw_sp_acl_tcam_vregion_put(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_acl_tcam_vregion *vregion)
+{
+	if (--vregion->ref_count)
+		return;
+	mlxsw_sp_acl_tcam_vregion_destroy(mlxsw_sp, vregion);
 }
 
 static struct mlxsw_sp_acl_tcam_chunk *
 mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
-			       struct mlxsw_sp_acl_tcam_group *group,
-			       unsigned int priority,
-			       struct mlxsw_afk_element_usage *elusage)
+			       struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+			       struct mlxsw_sp_acl_tcam_region *region)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
+
+	chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL);
+	if (!chunk)
+		return ERR_PTR(-ENOMEM);
+	chunk->vchunk = vchunk;
+	chunk->region = region;
+
+	ops->chunk_init(region->priv, chunk->priv, vchunk->priority);
+	return chunk;
+}
+
+static void
+mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_tcam_chunk *chunk)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	ops->chunk_fini(chunk->priv);
+	kfree(chunk);
+}
+
+static struct mlxsw_sp_acl_tcam_vchunk *
+mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				unsigned int priority,
+				struct mlxsw_afk_element_usage *elusage)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
 		return ERR_PTR(-EINVAL);
 
-	chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL);
-	if (!chunk)
+	vchunk = kzalloc(sizeof(*vchunk), GFP_KERNEL);
+	if (!vchunk)
 		return ERR_PTR(-ENOMEM);
-	chunk->priority = priority;
-	chunk->group = group;
-	chunk->ref_count = 1;
-
-	err = mlxsw_sp_acl_tcam_chunk_assoc(mlxsw_sp, group, priority,
-					    elusage, chunk);
-	if (err)
-		goto err_chunk_assoc;
+	INIT_LIST_HEAD(&vchunk->ventry_list);
+	vchunk->priority = priority;
+	vchunk->vgroup = vgroup;
+	vchunk->ref_count = 1;
+
+	vregion = mlxsw_sp_acl_tcam_vregion_get(mlxsw_sp, vgroup,
+						priority, elusage);
+	if (IS_ERR(vregion)) {
+		err = PTR_ERR(vregion);
+		goto err_vregion_get;
+	}
 
-	ops->chunk_init(chunk->region->priv, chunk->priv, priority);
+	vchunk->vregion = vregion;
 
-	err = rhashtable_insert_fast(&group->chunk_ht, &chunk->ht_node,
-				     mlxsw_sp_acl_tcam_chunk_ht_params);
+	err = rhashtable_insert_fast(&vgroup->vchunk_ht, &vchunk->ht_node,
+				     mlxsw_sp_acl_tcam_vchunk_ht_params);
 	if (err)
 		goto err_rhashtable_insert;
 
-	return chunk;
+	mutex_lock(&vregion->lock);
+	vchunk->chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk,
+						       vchunk->vregion->region);
+	if (IS_ERR(vchunk->chunk)) {
+		mutex_unlock(&vregion->lock);
+		err = PTR_ERR(vchunk->chunk);
+		goto err_chunk_create;
+	}
+
+	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
+	list_add_tail(&vchunk->list, &vregion->vchunk_list);
+	mutex_unlock(&vregion->lock);
+
+	return vchunk;
 
+err_chunk_create:
+	rhashtable_remove_fast(&vgroup->vchunk_ht, &vchunk->ht_node,
+			       mlxsw_sp_acl_tcam_vchunk_ht_params);
 err_rhashtable_insert:
-	ops->chunk_fini(chunk->priv);
-	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
-err_chunk_assoc:
-	kfree(chunk);
+	mlxsw_sp_acl_tcam_vregion_put(mlxsw_sp, vregion);
+err_vregion_get:
+	kfree(vchunk);
 	return ERR_PTR(err);
 }
 
 static void
-mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_acl_tcam_chunk *chunk)
+mlxsw_sp_acl_tcam_vchunk_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vchunk *vchunk)
 {
-	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_group *group = chunk->group;
-
-	rhashtable_remove_fast(&group->chunk_ht, &chunk->ht_node,
-			       mlxsw_sp_acl_tcam_chunk_ht_params);
-	ops->chunk_fini(chunk->priv);
-	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
-	kfree(chunk);
+	struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion;
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup = vchunk->vgroup;
+
+	mutex_lock(&vregion->lock);
+	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
+	list_del(&vchunk->list);
+	if (vchunk->chunk2)
+		mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2);
+	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk);
+	mutex_unlock(&vregion->lock);
+	rhashtable_remove_fast(&vgroup->vchunk_ht, &vchunk->ht_node,
+			       mlxsw_sp_acl_tcam_vchunk_ht_params);
+	mlxsw_sp_acl_tcam_vregion_put(mlxsw_sp, vchunk->vregion);
+	kfree(vchunk);
 }
 
-static struct mlxsw_sp_acl_tcam_chunk *
-mlxsw_sp_acl_tcam_chunk_get(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_tcam_group *group,
-			    unsigned int priority,
-			    struct mlxsw_afk_element_usage *elusage)
+static struct mlxsw_sp_acl_tcam_vchunk *
+mlxsw_sp_acl_tcam_vchunk_get(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+			     unsigned int priority,
+			     struct mlxsw_afk_element_usage *elusage)
 {
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 
-	chunk = rhashtable_lookup_fast(&group->chunk_ht, &priority,
-				       mlxsw_sp_acl_tcam_chunk_ht_params);
-	if (chunk) {
-		if (WARN_ON(!mlxsw_afk_key_info_subset(chunk->region->key_info,
+	vchunk = rhashtable_lookup_fast(&vgroup->vchunk_ht, &priority,
+					mlxsw_sp_acl_tcam_vchunk_ht_params);
+	if (vchunk) {
+		if (WARN_ON(!mlxsw_afk_key_info_subset(vchunk->vregion->key_info,
 						       elusage)))
 			return ERR_PTR(-EINVAL);
-		chunk->ref_count++;
-		return chunk;
+		vchunk->ref_count++;
+		return vchunk;
 	}
-	return mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, group,
-					      priority, elusage);
+	return mlxsw_sp_acl_tcam_vchunk_create(mlxsw_sp, vgroup,
+					       priority, elusage);
 }
 
-static void mlxsw_sp_acl_tcam_chunk_put(struct mlxsw_sp *mlxsw_sp,
-					struct mlxsw_sp_acl_tcam_chunk *chunk)
+static void
+mlxsw_sp_acl_tcam_vchunk_put(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_tcam_vchunk *vchunk)
 {
-	if (--chunk->ref_count)
+	if (--vchunk->ref_count)
 		return;
-	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, chunk);
-}
-
-static size_t mlxsw_sp_acl_tcam_entry_priv_size(struct mlxsw_sp *mlxsw_sp)
-{
-	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-
-	return ops->entry_priv_size;
+	mlxsw_sp_acl_tcam_vchunk_destroy(mlxsw_sp, vchunk);
 }
 
-static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
-				       struct mlxsw_sp_acl_tcam_group *group,
-				       struct mlxsw_sp_acl_tcam_entry *entry,
-				       struct mlxsw_sp_acl_rule_info *rulei)
+static struct mlxsw_sp_acl_tcam_entry *
+mlxsw_sp_acl_tcam_entry_create(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_tcam_ventry *ventry,
+			       struct mlxsw_sp_acl_tcam_chunk *chunk)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
-	struct mlxsw_sp_acl_tcam_region *region;
+	struct mlxsw_sp_acl_tcam_entry *entry;
 	int err;
 
-	chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, group, rulei->priority,
-					    &rulei->values.elusage);
-	if (IS_ERR(chunk))
-		return PTR_ERR(chunk);
-
-	region = chunk->region;
+	entry = kzalloc(sizeof(*entry) + ops->entry_priv_size, GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+	entry->ventry = ventry;
+	entry->chunk = chunk;
 
-	err = ops->entry_add(mlxsw_sp, region->priv, chunk->priv,
-			     entry->priv, rulei);
+	err = ops->entry_add(mlxsw_sp, chunk->region->priv, chunk->priv,
+			     entry->priv, ventry->rulei);
 	if (err)
 		goto err_entry_add;
-	entry->chunk = chunk;
 
-	return 0;
+	return entry;
 
 err_entry_add:
-	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
-	return err;
+	kfree(entry);
+	return ERR_PTR(err);
 }
 
-static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
-					struct mlxsw_sp_acl_tcam_entry *entry)
+static void mlxsw_sp_acl_tcam_entry_destroy(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_tcam_entry *entry)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
-	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	ops->entry_del(mlxsw_sp, region->priv, chunk->priv, entry->priv);
-	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
+	ops->entry_del(mlxsw_sp, entry->chunk->region->priv,
+		       entry->chunk->priv, entry->priv);
+	kfree(entry);
 }
 
 static int
 mlxsw_sp_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
-				       struct mlxsw_sp_acl_tcam_group *group,
+				       struct mlxsw_sp_acl_tcam_region *region,
 				       struct mlxsw_sp_acl_tcam_entry *entry,
 				       struct mlxsw_sp_acl_rule_info *rulei)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
-	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	return ops->entry_action_replace(mlxsw_sp, region->priv, chunk->priv,
+	return ops->entry_action_replace(mlxsw_sp, region->priv,
 					 entry->priv, rulei);
 }
 
@@ -799,13 +1145,374 @@ mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 				     bool *activity)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
-	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	return ops->entry_activity_get(mlxsw_sp, region->priv,
+	return ops->entry_activity_get(mlxsw_sp, entry->chunk->region->priv,
 				       entry->priv, activity);
 }
 
+static int mlxsw_sp_acl_tcam_ventry_add(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+					struct mlxsw_sp_acl_tcam_ventry *ventry,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	int err;
+
+	vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp, vgroup, rulei->priority,
+					      &rulei->values.elusage);
+	if (IS_ERR(vchunk))
+		return PTR_ERR(vchunk);
+
+	ventry->vchunk = vchunk;
+	ventry->rulei = rulei;
+	vregion = vchunk->vregion;
+
+	mutex_lock(&vregion->lock);
+	ventry->entry = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry,
+						       vchunk->chunk);
+	if (IS_ERR(ventry->entry)) {
+		mutex_unlock(&vregion->lock);
+		err = PTR_ERR(ventry->entry);
+		goto err_entry_create;
+	}
+
+	list_add_tail(&ventry->list, &vchunk->ventry_list);
+	mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(vchunk);
+	mutex_unlock(&vregion->lock);
+
+	return 0;
+
+err_entry_create:
+	mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk);
+	return err;
+}
+
+static void mlxsw_sp_acl_tcam_ventry_del(struct mlxsw_sp *mlxsw_sp,
+					 struct mlxsw_sp_acl_tcam_ventry *ventry)
+{
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk;
+	struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion;
+
+	mutex_lock(&vregion->lock);
+	mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(vchunk);
+	list_del(&ventry->list);
+	mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry);
+	mutex_unlock(&vregion->lock);
+	mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk);
+}
+
+static int
+mlxsw_sp_acl_tcam_ventry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_ventry *ventry,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk;
+
+	return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp,
+						      vchunk->vregion->region,
+						      ventry->entry, rulei);
+}
+
+static int
+mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_acl_tcam_ventry *ventry,
+				      bool *activity)
+{
+	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp,
+						    ventry->entry, activity);
+}
+
+static int
+mlxsw_sp_acl_tcam_ventry_migrate(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_ventry *ventry,
+				 struct mlxsw_sp_acl_tcam_chunk *chunk,
+				 int *credits)
+{
+	struct mlxsw_sp_acl_tcam_entry *new_entry;
+
+	/* First check if the entry is not already where we want it to be. */
+	if (ventry->entry->chunk == chunk)
+		return 0;
+
+	if (--(*credits) < 0)
+		return 0;
+
+	new_entry = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry, chunk);
+	if (IS_ERR(new_entry))
+		return PTR_ERR(new_entry);
+	mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry);
+	ventry->entry = new_entry;
+	return 0;
+}
+
+static int
+mlxsw_sp_acl_tcam_vchunk_migrate_start(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+				       struct mlxsw_sp_acl_tcam_region *region,
+				       struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	struct mlxsw_sp_acl_tcam_chunk *new_chunk;
+
+	new_chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region);
+	if (IS_ERR(new_chunk))
+		return PTR_ERR(new_chunk);
+	vchunk->chunk2 = vchunk->chunk;
+	vchunk->chunk = new_chunk;
+	ctx->current_vchunk = vchunk;
+	ctx->start_ventry = NULL;
+	ctx->stop_ventry = NULL;
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_tcam_vchunk_migrate_end(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2);
+	vchunk->chunk2 = NULL;
+	ctx->current_vchunk = NULL;
+}
+
+static int
+mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+				     struct mlxsw_sp_acl_tcam_region *region,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx,
+				     int *credits)
+{
+	struct mlxsw_sp_acl_tcam_ventry *ventry;
+	int err;
+
+	if (vchunk->chunk->region != region) {
+		err = mlxsw_sp_acl_tcam_vchunk_migrate_start(mlxsw_sp, vchunk,
+							     region, ctx);
+		if (err)
+			return err;
+	} else if (!vchunk->chunk2) {
+		/* The chunk is already as it should be, nothing to do. */
+		return 0;
+	}
+
+	/* If the migration got interrupted, we have the ventry to start from
+	 * stored in context.
+	 */
+	if (ctx->start_ventry)
+		ventry = ctx->start_ventry;
+	else
+		ventry = list_first_entry(&vchunk->ventry_list,
+					  typeof(*ventry), list);
+
+	list_for_each_entry_from(ventry, &vchunk->ventry_list, list) {
+		/* During rollback, once we reach the ventry that failed
+		 * to migrate, we are done.
+		 */
+		if (ventry == ctx->stop_ventry)
+			break;
+
+		err = mlxsw_sp_acl_tcam_ventry_migrate(mlxsw_sp, ventry,
+						       vchunk->chunk, credits);
+		if (err) {
+			if (ctx->this_is_rollback) {
+				/* Save the ventry which we ended with and try
+				 * to continue later on.
+				 */
+				ctx->start_ventry = ventry;
+				return err;
+			}
+			/* Swap the chunk and chunk2 pointers so the follow-up
+			 * rollback call will see the original chunk pointer
+			 * in vchunk->chunk.
+			 */
+			swap(vchunk->chunk, vchunk->chunk2);
+			/* The rollback has to be done from beginning of the
+			 * chunk, that is why we have to null the start_ventry.
+			 * However, we know where to stop the rollback,
+			 * at the current ventry.
+			 */
+			ctx->start_ventry = NULL;
+			ctx->stop_ventry = ventry;
+			return err;
+		} else if (*credits < 0) {
+			/* We are out of credits, the rest of the ventries
+			 * will be migrated later. Save the ventry
+			 * which we ended with.
+			 */
+			ctx->start_ventry = ventry;
+			return 0;
+		}
+	}
+
+	mlxsw_sp_acl_tcam_vchunk_migrate_end(mlxsw_sp, vchunk, ctx);
+	return 0;
+}
+
+static int
+mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vregion *vregion,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx,
+				     int *credits)
+{
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	int err;
+
+	/* If the migration got interrupted, we have the vchunk
+	 * we are working on stored in context.
+	 */
+	if (ctx->current_vchunk)
+		vchunk = ctx->current_vchunk;
+	else
+		vchunk = list_first_entry(&vregion->vchunk_list,
+					  typeof(*vchunk), list);
+
+	list_for_each_entry_from(vchunk, &vregion->vchunk_list, list) {
+		err = mlxsw_sp_acl_tcam_vchunk_migrate_one(mlxsw_sp, vchunk,
+							   vregion->region,
+							   ctx, credits);
+		if (err || *credits < 0)
+			return err;
+	}
+	return 0;
+}
+
+static int
+mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_tcam_vregion *vregion,
+				  struct mlxsw_sp_acl_tcam_rehash_ctx *ctx,
+				  int *credits)
+{
+	int err, err2;
+
+	trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion);
+	mutex_lock(&vregion->lock);
+	err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
+						   ctx, credits);
+	if (err) {
+		/* In case migration was not successful, we need to swap
+		 * so the original region pointer is assigned again
+		 * to vregion->region.
+		 */
+		swap(vregion->region, vregion->region2);
+		ctx->current_vchunk = NULL;
+		ctx->this_is_rollback = true;
+		err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
+							    ctx, credits);
+		if (err2) {
+			trace_mlxsw_sp_acl_tcam_vregion_rehash_rollback_failed(mlxsw_sp,
+									       vregion);
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to rollback during vregion migration fail\n");
+			/* Let the rollback to be continued later on. */
+		}
+	}
+	mutex_unlock(&vregion->lock);
+	trace_mlxsw_sp_acl_tcam_vregion_migrate_end(mlxsw_sp, vregion);
+	return err;
+}
+
+static bool
+mlxsw_sp_acl_tcam_vregion_rehash_in_progress(const struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	return ctx->hints_priv;
+}
+
+static int
+mlxsw_sp_acl_tcam_vregion_rehash_start(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_vregion *vregion,
+				       struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	unsigned int priority = mlxsw_sp_acl_tcam_vregion_prio(vregion);
+	struct mlxsw_sp_acl_tcam_region *new_region;
+	void *hints_priv;
+	int err;
+
+	trace_mlxsw_sp_acl_tcam_vregion_rehash(mlxsw_sp, vregion);
+
+	hints_priv = ops->region_rehash_hints_get(vregion->region->priv);
+	if (IS_ERR(hints_priv))
+		return PTR_ERR(hints_priv);
+
+	new_region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, vregion->tcam,
+						     vregion, hints_priv);
+	if (IS_ERR(new_region)) {
+		err = PTR_ERR(new_region);
+		goto err_region_create;
+	}
+
+	/* vregion->region contains the pointer to the new region
+	 * we are going to migrate to.
+	 */
+	vregion->region2 = vregion->region;
+	vregion->region = new_region;
+	err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp,
+						    vregion->region2->group,
+						    new_region, priority,
+						    vregion->region2);
+	if (err)
+		goto err_group_region_attach;
+
+	ctx->hints_priv = hints_priv;
+	ctx->this_is_rollback = false;
+
+	return 0;
+
+err_group_region_attach:
+	vregion->region = vregion->region2;
+	vregion->region2 = NULL;
+	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, new_region);
+err_region_create:
+	ops->region_rehash_hints_put(hints_priv);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_tcam_vregion_rehash_end(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vregion *vregion,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	struct mlxsw_sp_acl_tcam_region *unused_region = vregion->region2;
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	vregion->region2 = NULL;
+	mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, unused_region);
+	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, unused_region);
+	ops->region_rehash_hints_put(ctx->hints_priv);
+	ctx->hints_priv = NULL;
+}
+
+static void
+mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vregion *vregion,
+				 int *credits)
+{
+	struct mlxsw_sp_acl_tcam_rehash_ctx *ctx = &vregion->rehash.ctx;
+	int err;
+
+	/* Check if the previous rehash work was interrupted
+	 * which means we have to continue it now.
+	 * If not, start a new rehash.
+	 */
+	if (!mlxsw_sp_acl_tcam_vregion_rehash_in_progress(ctx)) {
+		err = mlxsw_sp_acl_tcam_vregion_rehash_start(mlxsw_sp,
+							     vregion, ctx);
+		if (err) {
+			if (err != -EAGAIN)
+				dev_err(mlxsw_sp->bus_info->dev, "Failed get rehash hints\n");
+			return;
+		}
+	}
+
+	err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion,
+						ctx, credits);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n");
+	}
+
+	if (*credits >= 0)
+		mlxsw_sp_acl_tcam_vregion_rehash_end(mlxsw_sp, vregion, ctx);
+}
+
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 	MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
 	MLXSW_AFK_ELEMENT_DMAC_32_47,
@@ -856,20 +1563,11 @@ static const struct mlxsw_sp_acl_tcam_pattern mlxsw_sp_acl_tcam_patterns[] = {
 	ARRAY_SIZE(mlxsw_sp_acl_tcam_patterns)
 
 struct mlxsw_sp_acl_tcam_flower_ruleset {
-	struct mlxsw_sp_acl_tcam_group group;
+	struct mlxsw_sp_acl_tcam_vgroup vgroup;
 };
 
 struct mlxsw_sp_acl_tcam_flower_rule {
-	struct mlxsw_sp_acl_tcam_entry entry;
-};
-
-struct mlxsw_sp_acl_tcam_mr_ruleset {
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
-	struct mlxsw_sp_acl_tcam_group group;
-};
-
-struct mlxsw_sp_acl_tcam_mr_rule {
-	struct mlxsw_sp_acl_tcam_entry entry;
+	struct mlxsw_sp_acl_tcam_ventry ventry;
 };
 
 static int
@@ -880,10 +1578,10 @@ mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	return mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
-					   mlxsw_sp_acl_tcam_patterns,
-					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
-					   tmplt_elusage);
+	return mlxsw_sp_acl_tcam_vgroup_add(mlxsw_sp, tcam, &ruleset->vgroup,
+					    mlxsw_sp_acl_tcam_patterns,
+					    MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+					    tmplt_elusage, true);
 }
 
 static void
@@ -892,7 +1590,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_del(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group);
+	mlxsw_sp_acl_tcam_vgroup_del(&ruleset->vgroup);
 }
 
 static int
@@ -903,7 +1601,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	return mlxsw_sp_acl_tcam_group_bind(mlxsw_sp, &ruleset->group,
+	return mlxsw_sp_acl_tcam_group_bind(mlxsw_sp, &ruleset->vgroup.group,
 					    mlxsw_sp_port, ingress);
 }
 
@@ -915,7 +1613,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	mlxsw_sp_acl_tcam_group_unbind(mlxsw_sp, &ruleset->group,
+	mlxsw_sp_acl_tcam_group_unbind(mlxsw_sp, &ruleset->vgroup.group,
 				       mlxsw_sp_port, ingress);
 }
 
@@ -924,13 +1622,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_group_id(void *ruleset_priv)
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	return mlxsw_sp_acl_tcam_group_id(&ruleset->group);
-}
-
-static size_t mlxsw_sp_acl_tcam_flower_rule_priv_size(struct mlxsw_sp *mlxsw_sp)
-{
-	return sizeof(struct mlxsw_sp_acl_tcam_flower_rule) +
-	       mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp);
+	return mlxsw_sp_acl_tcam_group_id(&ruleset->vgroup.group);
 }
 
 static int
@@ -941,8 +1633,8 @@ mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
 
-	return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group,
-					   &rule->entry, rulei);
+	return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->vgroup,
+					    &rule->ventry, rulei);
 }
 
 static void
@@ -950,12 +1642,11 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
 {
 	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
 
-	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
+	mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry);
 }
 
 static int
 mlxsw_sp_acl_tcam_flower_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
-					     void *ruleset_priv,
 					     void *rule_priv,
 					     struct mlxsw_sp_acl_rule_info *rulei)
 {
@@ -968,8 +1659,8 @@ mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
 
-	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry,
-						    activity);
+	return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry,
+						     activity);
 }
 
 static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
@@ -979,13 +1670,22 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.ruleset_bind		= mlxsw_sp_acl_tcam_flower_ruleset_bind,
 	.ruleset_unbind		= mlxsw_sp_acl_tcam_flower_ruleset_unbind,
 	.ruleset_group_id	= mlxsw_sp_acl_tcam_flower_ruleset_group_id,
-	.rule_priv_size		= mlxsw_sp_acl_tcam_flower_rule_priv_size,
+	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
 	.rule_add		= mlxsw_sp_acl_tcam_flower_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_flower_rule_del,
 	.rule_action_replace	= mlxsw_sp_acl_tcam_flower_rule_action_replace,
 	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
 };
 
+struct mlxsw_sp_acl_tcam_mr_ruleset {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct mlxsw_sp_acl_tcam_vgroup vgroup;
+};
+
+struct mlxsw_sp_acl_tcam_mr_rule {
+	struct mlxsw_sp_acl_tcam_ventry ventry;
+};
+
 static int
 mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam *tcam,
@@ -995,10 +1695,10 @@ mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
 	int err;
 
-	err = mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
-					  mlxsw_sp_acl_tcam_patterns,
-					  MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
-					  tmplt_elusage);
+	err = mlxsw_sp_acl_tcam_vgroup_add(mlxsw_sp, tcam, &ruleset->vgroup,
+					   mlxsw_sp_acl_tcam_patterns,
+					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+					   tmplt_elusage, false);
 	if (err)
 		return err;
 
@@ -1008,17 +1708,18 @@ mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 	 * specific ACL Group ID which must exist in HW before multicast router
 	 * is initialized.
 	 */
-	ruleset->chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, &ruleset->group,
-						     1, tmplt_elusage);
-	if (IS_ERR(ruleset->chunk)) {
-		err = PTR_ERR(ruleset->chunk);
+	ruleset->vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp,
+						       &ruleset->vgroup, 1,
+						       tmplt_elusage);
+	if (IS_ERR(ruleset->vchunk)) {
+		err = PTR_ERR(ruleset->vchunk);
 		goto err_chunk_get;
 	}
 
 	return 0;
 
 err_chunk_get:
-	mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group);
+	mlxsw_sp_acl_tcam_vgroup_del(&ruleset->vgroup);
 	return err;
 }
 
@@ -1027,8 +1728,8 @@ mlxsw_sp_acl_tcam_mr_ruleset_del(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv)
 {
 	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
 
-	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, ruleset->chunk);
-	mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group);
+	mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, ruleset->vchunk);
+	mlxsw_sp_acl_tcam_vgroup_del(&ruleset->vgroup);
 }
 
 static int
@@ -1053,13 +1754,7 @@ mlxsw_sp_acl_tcam_mr_ruleset_group_id(void *ruleset_priv)
 {
 	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
 
-	return mlxsw_sp_acl_tcam_group_id(&ruleset->group);
-}
-
-static size_t mlxsw_sp_acl_tcam_mr_rule_priv_size(struct mlxsw_sp *mlxsw_sp)
-{
-	return sizeof(struct mlxsw_sp_acl_tcam_mr_rule) +
-	       mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp);
+	return mlxsw_sp_acl_tcam_group_id(&ruleset->vgroup.group);
 }
 
 static int
@@ -1070,8 +1765,8 @@ mlxsw_sp_acl_tcam_mr_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
 	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
 	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
 
-	return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group,
-					   &rule->entry, rulei);
+	return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->vgroup,
+					   &rule->ventry, rulei);
 }
 
 static void
@@ -1079,19 +1774,18 @@ mlxsw_sp_acl_tcam_mr_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
 {
 	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
 
-	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
+	mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry);
 }
 
 static int
 mlxsw_sp_acl_tcam_mr_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
-					 void *ruleset_priv, void *rule_priv,
+					 void *rule_priv,
 					 struct mlxsw_sp_acl_rule_info *rulei)
 {
-	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
 	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
 
-	return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp, &ruleset->group,
-						      &rule->entry, rulei);
+	return mlxsw_sp_acl_tcam_ventry_action_replace(mlxsw_sp, &rule->ventry,
+						       rulei);
 }
 
 static int
@@ -1100,8 +1794,8 @@ mlxsw_sp_acl_tcam_mr_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
 
-	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry,
-						    activity);
+	return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry,
+						     activity);
 }
 
 static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = {
@@ -1111,7 +1805,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = {
 	.ruleset_bind		= mlxsw_sp_acl_tcam_mr_ruleset_bind,
 	.ruleset_unbind		= mlxsw_sp_acl_tcam_mr_ruleset_unbind,
 	.ruleset_group_id	= mlxsw_sp_acl_tcam_mr_ruleset_group_id,
-	.rule_priv_size		= mlxsw_sp_acl_tcam_mr_rule_priv_size,
+	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_mr_rule),
 	.rule_add		= mlxsw_sp_acl_tcam_mr_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_mr_rule_del,
 	.rule_action_replace	= mlxsw_sp_acl_tcam_mr_rule_action_replace,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 0f1a9dee63de..5965913565a5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -17,6 +17,9 @@ struct mlxsw_sp_acl_tcam {
 	unsigned long *used_groups;  /* bit array */
 	unsigned int max_groups;
 	unsigned int max_group_size;
+	struct mutex lock; /* guards vregion list */
+	struct list_head vregion_list;
+	u32 vregion_rehash_intrvl;   /* ms */
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
@@ -26,6 +29,11 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_tcam *tcam);
 void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_tcam *tcam);
+u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam);
+int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam,
+						u32 val);
 int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_rule_info *rulei,
 				   u32 *priority, bool fillup_priority);
@@ -43,13 +51,12 @@ struct mlxsw_sp_acl_profile_ops {
 			       struct mlxsw_sp_port *mlxsw_sp_port,
 			       bool ingress);
 	u16 (*ruleset_group_id)(void *ruleset_priv);
-	size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp);
+	size_t rule_priv_size;
 	int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
 			void *ruleset_priv, void *rule_priv,
 			struct mlxsw_sp_acl_rule_info *rulei);
 	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
-	int (*rule_action_replace)(struct mlxsw_sp *mlxsw_sp,
-				   void *ruleset_priv, void *rule_priv,
+	int (*rule_action_replace)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
 				   struct mlxsw_sp_acl_rule_info *rulei);
 	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
 				 bool *activity);
@@ -68,11 +75,12 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
 	(MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN * BITS_PER_BYTE)
 
 struct mlxsw_sp_acl_tcam_group;
+struct mlxsw_sp_acl_tcam_vregion;
 
 struct mlxsw_sp_acl_tcam_region {
-	struct list_head list; /* Member of a TCAM group */
-	struct list_head chunk_list; /* List of chunks under this region */
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
 	struct mlxsw_sp_acl_tcam_group *group;
+	struct list_head list; /* Member of a TCAM group */
 	enum mlxsw_reg_ptar_key_type key_type;
 	u16 id; /* ACL ID and region ID - they are same */
 	char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
@@ -126,7 +134,6 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_ctcam_entry *centry);
 int mlxsw_sp_acl_ctcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 					    struct mlxsw_sp_acl_ctcam_region *cregion,
-					    struct mlxsw_sp_acl_ctcam_chunk *cchunk,
 					    struct mlxsw_sp_acl_ctcam_entry *centry,
 					    struct mlxsw_sp_acl_rule_info *rulei);
 static inline unsigned int
@@ -163,9 +170,9 @@ struct mlxsw_sp_acl_atcam_region {
 };
 
 struct mlxsw_sp_acl_atcam_entry_ht_key {
-	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key,
-							    * minus delta bits.
-							    */
+	char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded
+								 * key.
+								 */
 	u8 erp_id;
 };
 
@@ -177,7 +184,9 @@ struct mlxsw_sp_acl_atcam_entry {
 	struct rhash_head ht_node;
 	struct list_head list; /* Member in entries_list */
 	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
-	char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key,
+							    * minus delta bits.
+							    */
 	struct {
 		u16 start;
 		u8 mask;
@@ -207,6 +216,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam *atcam,
 			       struct mlxsw_sp_acl_atcam_region *aregion,
 			       struct mlxsw_sp_acl_tcam_region *region,
+			       void *hints_priv,
 			       const struct mlxsw_sp_acl_ctcam_region_ops *ops);
 void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
@@ -224,13 +234,15 @@ void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_atcam_entry *aentry);
 int mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
 					    struct mlxsw_sp_acl_atcam_region *aregion,
-					    struct mlxsw_sp_acl_atcam_chunk *achunk,
 					    struct mlxsw_sp_acl_atcam_entry *aentry,
 					    struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam);
 void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_atcam *atcam);
+void *
+mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv);
 
 struct mlxsw_sp_acl_erp_delta;
 
@@ -261,7 +273,11 @@ void mlxsw_sp_acl_erp_bf_remove(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_atcam_region *aregion,
 				struct mlxsw_sp_acl_erp_mask *erp_mask,
 				struct mlxsw_sp_acl_atcam_entry *aentry);
-int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion);
+void *
+mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv);
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				 void *hints_priv);
 void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_atcam *atcam);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 12c61e0cc570..1537f70bc26d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -6,6 +6,7 @@
 #include <linux/dcbnl.h>
 #include <linux/if_ether.h>
 #include <linux/list.h>
+#include <linux/netlink.h>
 
 #include "spectrum.h"
 #include "core.h"
@@ -15,6 +16,8 @@
 struct mlxsw_sp_sb_pr {
 	enum mlxsw_reg_sbpr_mode mode;
 	u32 size;
+	u8 freeze_mode:1,
+	   freeze_size:1;
 };
 
 struct mlxsw_cp_sb_occ {
@@ -27,6 +30,8 @@ struct mlxsw_sp_sb_cm {
 	u32 max_buff;
 	u16 pool_index;
 	struct mlxsw_cp_sb_occ occ;
+	u8 freeze_pool:1,
+	   freeze_thresh:1;
 };
 
 #define MLXSW_SP_SB_INFI -1U
@@ -37,13 +42,24 @@ struct mlxsw_sp_sb_pm {
 	struct mlxsw_cp_sb_occ occ;
 };
 
+struct mlxsw_sp_sb_mm {
+	u32 min_buff;
+	u32 max_buff;
+	u16 pool_index;
+};
+
 struct mlxsw_sp_sb_pool_des {
 	enum mlxsw_reg_sbxx_dir dir;
 	u8 pool;
 };
 
-/* Order ingress pools before egress pools. */
-static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = {
+#define MLXSW_SP_SB_POOL_ING		0
+#define MLXSW_SP_SB_POOL_EGR		4
+#define MLXSW_SP_SB_POOL_EGR_MC		8
+#define MLXSW_SP_SB_POOL_ING_CPU	9
+#define MLXSW_SP_SB_POOL_EGR_CPU	10
+
+static const struct mlxsw_sp_sb_pool_des mlxsw_sp1_sb_pool_dess[] = {
 	{MLXSW_REG_SBXX_DIR_INGRESS, 0},
 	{MLXSW_REG_SBXX_DIR_INGRESS, 1},
 	{MLXSW_REG_SBXX_DIR_INGRESS, 2},
@@ -53,9 +69,23 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = {
 	{MLXSW_REG_SBXX_DIR_EGRESS, 2},
 	{MLXSW_REG_SBXX_DIR_EGRESS, 3},
 	{MLXSW_REG_SBXX_DIR_EGRESS, 15},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 4},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 4},
 };
 
-#define MLXSW_SP_SB_POOL_DESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pool_dess)
+static const struct mlxsw_sp_sb_pool_des mlxsw_sp2_sb_pool_dess[] = {
+	{MLXSW_REG_SBXX_DIR_INGRESS, 0},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 1},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 2},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 3},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 0},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 1},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 2},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 3},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 15},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 4},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 4},
+};
 
 #define MLXSW_SP_SB_ING_TC_COUNT 8
 #define MLXSW_SP_SB_EG_TC_COUNT 16
@@ -63,16 +93,33 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = {
 struct mlxsw_sp_sb_port {
 	struct mlxsw_sp_sb_cm ing_cms[MLXSW_SP_SB_ING_TC_COUNT];
 	struct mlxsw_sp_sb_cm eg_cms[MLXSW_SP_SB_EG_TC_COUNT];
-	struct mlxsw_sp_sb_pm pms[MLXSW_SP_SB_POOL_DESS_LEN];
+	struct mlxsw_sp_sb_pm *pms;
 };
 
 struct mlxsw_sp_sb {
-	struct mlxsw_sp_sb_pr prs[MLXSW_SP_SB_POOL_DESS_LEN];
+	struct mlxsw_sp_sb_pr *prs;
 	struct mlxsw_sp_sb_port *ports;
 	u32 cell_size;
+	u32 max_headroom_cells;
 	u64 sb_size;
 };
 
+struct mlxsw_sp_sb_vals {
+	unsigned int pool_count;
+	const struct mlxsw_sp_sb_pool_des *pool_dess;
+	const struct mlxsw_sp_sb_pm *pms;
+	const struct mlxsw_sp_sb_pm *pms_cpu;
+	const struct mlxsw_sp_sb_pr *prs;
+	const struct mlxsw_sp_sb_mm *mms;
+	const struct mlxsw_sp_sb_cm *cms_ingress;
+	const struct mlxsw_sp_sb_cm *cms_egress;
+	const struct mlxsw_sp_sb_cm *cms_cpu;
+	unsigned int mms_count;
+	unsigned int cms_ingress_count;
+	unsigned int cms_egress_count;
+	unsigned int cms_cpu_count;
+};
+
 u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp, u32 cells)
 {
 	return mlxsw_sp->sb->cell_size * cells;
@@ -83,6 +130,11 @@ u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp, u32 bytes)
 	return DIV_ROUND_UP(bytes, mlxsw_sp->sb->cell_size);
 }
 
+u32 mlxsw_sp_sb_max_headroom_cells(const struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_sp->sb->max_headroom_cells;
+}
+
 static struct mlxsw_sp_sb_pr *mlxsw_sp_sb_pr_get(struct mlxsw_sp *mlxsw_sp,
 						 u16 pool_index)
 {
@@ -121,7 +173,7 @@ static int mlxsw_sp_sb_pr_write(struct mlxsw_sp *mlxsw_sp, u16 pool_index,
 				u32 size, bool infi_size)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpr_pl[MLXSW_REG_SBPR_LEN];
 	struct mlxsw_sp_sb_pr *pr;
 	int err;
@@ -145,7 +197,7 @@ static int mlxsw_sp_sb_cm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				bool infi_max, u16 pool_index)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbcm_pl[MLXSW_REG_SBCM_LEN];
 	struct mlxsw_sp_sb_cm *cm;
 	int err;
@@ -174,7 +226,7 @@ static int mlxsw_sp_sb_pm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				u16 pool_index, u32 min_buff, u32 max_buff)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpm_pl[MLXSW_REG_SBPM_LEN];
 	struct mlxsw_sp_sb_pm *pm;
 	int err;
@@ -195,7 +247,7 @@ static int mlxsw_sp_sb_pm_occ_clear(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				    u16 pool_index, struct list_head *bulk_list)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpm_pl[MLXSW_REG_SBPM_LEN];
 
 	mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir,
@@ -217,7 +269,7 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				    u16 pool_index, struct list_head *bulk_list)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpm_pl[MLXSW_REG_SBPM_LEN];
 	struct mlxsw_sp_sb_pm *pm;
 
@@ -230,24 +282,24 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				     (unsigned long) pm);
 }
 
-static const u16 mlxsw_sp_pbs[] = {
-	[0] = 2 * ETH_FRAME_LEN,
-	[9] = 2 * MLXSW_PORT_MAX_MTU,
-};
-
-#define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs)
+/* 1/4 of a headroom necessary for 100Gbps port and 100m cable. */
+#define MLXSW_SP_PB_HEADROOM 25632
 #define MLXSW_SP_PB_UNUSED 8
 
 static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	const u32 pbs[] = {
+		[0] = MLXSW_SP_PB_HEADROOM * mlxsw_sp_port->mapping.width,
+		[9] = MLXSW_PORT_MAX_MTU,
+	};
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pbmc_pl[MLXSW_REG_PBMC_LEN];
 	int i;
 
 	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port,
 			    0xffff, 0xffff / 2);
-	for (i = 0; i < MLXSW_SP_PBS_LEN; i++) {
-		u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, mlxsw_sp_pbs[i]);
+	for (i = 0; i < ARRAY_SIZE(pbs); i++) {
+		u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, pbs[i]);
 
 		if (i == MLXSW_SP_PB_UNUSED)
 			continue;
@@ -280,50 +332,134 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return mlxsw_sp_port_pb_prio_init(mlxsw_sp_port);
 }
 
+static int mlxsw_sp_sb_port_init(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_sb_port *sb_port)
+{
+	struct mlxsw_sp_sb_pm *pms;
+
+	pms = kcalloc(mlxsw_sp->sb_vals->pool_count, sizeof(*pms),
+		      GFP_KERNEL);
+	if (!pms)
+		return -ENOMEM;
+	sb_port->pms = pms;
+	return 0;
+}
+
+static void mlxsw_sp_sb_port_fini(struct mlxsw_sp_sb_port *sb_port)
+{
+	kfree(sb_port->pms);
+}
+
 static int mlxsw_sp_sb_ports_init(struct mlxsw_sp *mlxsw_sp)
 {
 	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+	struct mlxsw_sp_sb_pr *prs;
+	int i;
+	int err;
 
 	mlxsw_sp->sb->ports = kcalloc(max_ports,
 				      sizeof(struct mlxsw_sp_sb_port),
 				      GFP_KERNEL);
 	if (!mlxsw_sp->sb->ports)
 		return -ENOMEM;
+
+	prs = kcalloc(mlxsw_sp->sb_vals->pool_count, sizeof(*prs),
+		      GFP_KERNEL);
+	if (!prs) {
+		err = -ENOMEM;
+		goto err_alloc_prs;
+	}
+	mlxsw_sp->sb->prs = prs;
+
+	for (i = 0; i < max_ports; i++) {
+		err = mlxsw_sp_sb_port_init(mlxsw_sp, &mlxsw_sp->sb->ports[i]);
+		if (err)
+			goto err_sb_port_init;
+	}
+
 	return 0;
+
+err_sb_port_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_sb_port_fini(&mlxsw_sp->sb->ports[i]);
+	kfree(mlxsw_sp->sb->prs);
+err_alloc_prs:
+	kfree(mlxsw_sp->sb->ports);
+	return err;
 }
 
 static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp)
 {
+	int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+	int i;
+
+	for (i = max_ports - 1; i >= 0; i--)
+		mlxsw_sp_sb_port_fini(&mlxsw_sp->sb->ports[i]);
+	kfree(mlxsw_sp->sb->prs);
 	kfree(mlxsw_sp->sb->ports);
 }
 
-#define MLXSW_SP_SB_PR_INGRESS_SIZE	12440000
-#define MLXSW_SP_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
-#define MLXSW_SP_SB_PR_EGRESS_SIZE	13232000
-
 #define MLXSW_SP_SB_PR(_mode, _size)	\
 	{				\
 		.mode = _mode,		\
 		.size = _size,		\
 	}
 
-static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs[] = {
-	/* Ingress pools. */
+#define MLXSW_SP_SB_PR_EXT(_mode, _size, _freeze_mode, _freeze_size)	\
+	{								\
+		.mode = _mode,						\
+		.size = _size,						\
+		.freeze_mode = _freeze_mode,				\
+		.freeze_size = _freeze_size,				\
+	}
+
+#define MLXSW_SP1_SB_PR_INGRESS_SIZE	12440000
+#define MLXSW_SP1_SB_PR_EGRESS_SIZE	13232000
+#define MLXSW_SP1_SB_PR_CPU_SIZE	(256 * 1000)
+
+/* Order according to mlxsw_sp1_sb_pool_dess */
+static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = {
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_SB_PR_INGRESS_SIZE),
+		       MLXSW_SP1_SB_PR_INGRESS_SIZE),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
-	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_SB_PR_INGRESS_MNG_SIZE),
-	/* Egress pools. */
-	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_EGRESS_SIZE),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC,
+			   MLXSW_SP1_SB_PR_EGRESS_SIZE, true, false),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
-	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI,
+			   true, true),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC,
+			   MLXSW_SP1_SB_PR_CPU_SIZE, true, false),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC,
+			   MLXSW_SP1_SB_PR_CPU_SIZE, true, false),
 };
 
-#define MLXSW_SP_SB_PRS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs)
+#define MLXSW_SP2_SB_PR_INGRESS_SIZE	38128752
+#define MLXSW_SP2_SB_PR_EGRESS_SIZE	38128752
+#define MLXSW_SP2_SB_PR_CPU_SIZE	(256 * 1000)
+
+/* Order according to mlxsw_sp2_sb_pool_dess */
+static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = {
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP2_SB_PR_INGRESS_SIZE),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC,
+			   MLXSW_SP2_SB_PR_EGRESS_SIZE, true, false),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI,
+			   true, true),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC,
+			   MLXSW_SP2_SB_PR_CPU_SIZE, true, false),
+	MLXSW_SP_SB_PR_EXT(MLXSW_REG_SBPR_MODE_DYNAMIC,
+			   MLXSW_SP2_SB_PR_CPU_SIZE, true, false),
+};
 
 static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
 				const struct mlxsw_sp_sb_pr *prs,
@@ -357,54 +493,106 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
 		.pool_index = _pool,			\
 	}
 
-static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
-	MLXSW_SP_SB_CM(10000, 8, 0),
-	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
-	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
-	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
-	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
-	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
-	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
-	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
-	MLXSW_SP_SB_CM(0, 0, 0), /* dummy, this PG does not exist */
-	MLXSW_SP_SB_CM(20000, 1, 3),
+#define MLXSW_SP_SB_CM_ING(_min_buff, _max_buff)	\
+	{						\
+		.min_buff = _min_buff,			\
+		.max_buff = _max_buff,			\
+		.pool_index = MLXSW_SP_SB_POOL_ING,	\
+	}
+
+#define MLXSW_SP_SB_CM_EGR(_min_buff, _max_buff)	\
+	{						\
+		.min_buff = _min_buff,			\
+		.max_buff = _max_buff,			\
+		.pool_index = MLXSW_SP_SB_POOL_EGR,	\
+	}
+
+#define MLXSW_SP_SB_CM_EGR_MC(_min_buff, _max_buff)	\
+	{						\
+		.min_buff = _min_buff,			\
+		.max_buff = _max_buff,			\
+		.pool_index = MLXSW_SP_SB_POOL_EGR_MC,	\
+		.freeze_pool = true,			\
+		.freeze_thresh = true,			\
+	}
+
+static const struct mlxsw_sp_sb_cm mlxsw_sp1_sb_cms_ingress[] = {
+	MLXSW_SP_SB_CM_ING(10000, 8),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, 0), /* dummy, this PG does not exist */
+	MLXSW_SP_SB_CM(10000, 8, MLXSW_SP_SB_POOL_ING_CPU),
 };
 
-#define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress)
-
-static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(1500, 9, 4),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
-	MLXSW_SP_SB_CM(1, 0xff, 4),
+static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_ingress[] = {
+	MLXSW_SP_SB_CM_ING(0, 7),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+	MLXSW_SP_SB_CM_ING(0, 0), /* dummy, this PG does not exist */
+	MLXSW_SP_SB_CM(10000, 8, MLXSW_SP_SB_POOL_ING_CPU),
 };
 
-#define MLXSW_SP_SB_CMS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_egress)
+static const struct mlxsw_sp_sb_cm mlxsw_sp1_sb_cms_egress[] = {
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR(1500, 9),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR(1, 0xff),
+};
 
-#define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, 4)
+static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_egress[] = {
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR(0, 7),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR_MC(0, MLXSW_SP_SB_INFI),
+	MLXSW_SP_SB_CM_EGR(1, 0xff),
+};
+
+#define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, MLXSW_SP_SB_POOL_EGR_CPU)
 
 static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
 	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4),
-	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4),
-	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4),
-	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4),
-	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4),
+	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
+	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
+	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
+	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
+	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
 	MLXSW_SP_CPU_PORT_SB_CM,
-	MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 4),
+	MLXSW_SP_SB_CM(1000, 8, MLXSW_SP_SB_POOL_EGR_CPU),
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
 	MLXSW_SP_CPU_PORT_SB_CM,
@@ -431,9 +619,6 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
 	MLXSW_SP_CPU_PORT_SB_CM,
 };
 
-#define MLXSW_SP_CPU_PORT_SB_MCS_LEN \
-	ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms)
-
 static bool
 mlxsw_sp_sb_pool_is_static(struct mlxsw_sp *mlxsw_sp, u16 pool_index)
 {
@@ -447,6 +632,7 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				  const struct mlxsw_sp_sb_cm *cms,
 				  size_t cms_len)
 {
+	const struct mlxsw_sp_sb_vals *sb_vals = mlxsw_sp->sb_vals;
 	int i;
 	int err;
 
@@ -458,7 +644,7 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS)
 			continue; /* PG number 8 does not exist, skip it */
 		cm = &cms[i];
-		if (WARN_ON(mlxsw_sp_sb_pool_dess[cm->pool_index].dir != dir))
+		if (WARN_ON(sb_vals->pool_dess[cm->pool_index].dir != dir))
 			continue;
 
 		min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, cm->min_buff);
@@ -484,27 +670,28 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 static int mlxsw_sp_port_sb_cms_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	int err;
 
-	err = __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp,
+	err = __mlxsw_sp_sb_cms_init(mlxsw_sp,
 				     mlxsw_sp_port->local_port,
 				     MLXSW_REG_SBXX_DIR_INGRESS,
-				     mlxsw_sp_sb_cms_ingress,
-				     MLXSW_SP_SB_CMS_INGRESS_LEN);
+				     mlxsw_sp->sb_vals->cms_ingress,
+				     mlxsw_sp->sb_vals->cms_ingress_count);
 	if (err)
 		return err;
 	return __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp,
 				      mlxsw_sp_port->local_port,
 				      MLXSW_REG_SBXX_DIR_EGRESS,
-				      mlxsw_sp_sb_cms_egress,
-				      MLXSW_SP_SB_CMS_EGRESS_LEN);
+				      mlxsw_sp->sb_vals->cms_egress,
+				      mlxsw_sp->sb_vals->cms_egress_count);
 }
 
 static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp)
 {
 	return __mlxsw_sp_sb_cms_init(mlxsw_sp, 0, MLXSW_REG_SBXX_DIR_EGRESS,
-				      mlxsw_sp_cpu_port_sb_cms,
-				      MLXSW_SP_CPU_PORT_SB_MCS_LEN);
+				      mlxsw_sp->sb_vals->cms_cpu,
+				      mlxsw_sp->sb_vals->cms_cpu_count);
 }
 
 #define MLXSW_SP_SB_PM(_min_buff, _max_buff)	\
@@ -513,91 +700,131 @@ static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp)
 		.max_buff = _max_buff,		\
 	}
 
-static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = {
-	/* Ingress pools. */
+/* Order according to mlxsw_sp1_sb_pool_dess */
+static const struct mlxsw_sp_sb_pm mlxsw_sp1_sb_pms[] = {
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX),
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
-	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX),
-	/* Egress pools. */
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
 	MLXSW_SP_SB_PM(0, 7),
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
 	MLXSW_SP_SB_PM(10000, 90000),
+	MLXSW_SP_SB_PM(0, 8),	/* 50% occupancy */
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
 };
 
-#define MLXSW_SP_SB_PMS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms)
+/* Order according to mlxsw_sp2_sb_pool_dess */
+static const struct mlxsw_sp_sb_pm mlxsw_sp2_sb_pms[] = {
+	MLXSW_SP_SB_PM(0, 7),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 7),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(10000, 90000),
+	MLXSW_SP_SB_PM(0, 8),	/* 50% occupancy */
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
+};
 
-static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
+/* Order according to mlxsw_sp*_sb_pool_dess */
+static const struct mlxsw_sp_sb_pm mlxsw_sp_cpu_port_sb_pms[] = {
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 90000),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX),
+};
+
+static int mlxsw_sp_sb_pms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+				const struct mlxsw_sp_sb_pm *pms,
+				bool skip_ingress)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	int i;
-	int err;
+	int i, err;
 
-	for (i = 0; i < MLXSW_SP_SB_PMS_LEN; i++) {
-		const struct mlxsw_sp_sb_pm *pm = &mlxsw_sp_sb_pms[i];
+	for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
+		const struct mlxsw_sp_sb_pm *pm = &pms[i];
+		const struct mlxsw_sp_sb_pool_des *des;
 		u32 max_buff;
 		u32 min_buff;
 
+		des = &mlxsw_sp->sb_vals->pool_dess[i];
+		if (skip_ingress && des->dir == MLXSW_REG_SBXX_DIR_INGRESS)
+			continue;
+
 		min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, pm->min_buff);
 		max_buff = pm->max_buff;
 		if (mlxsw_sp_sb_pool_is_static(mlxsw_sp, i))
 			max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, max_buff);
-		err = mlxsw_sp_sb_pm_write(mlxsw_sp, mlxsw_sp_port->local_port,
-					   i, min_buff, max_buff);
+		err = mlxsw_sp_sb_pm_write(mlxsw_sp, local_port, i, min_buff,
+					   max_buff);
 		if (err)
 			return err;
 	}
 	return 0;
 }
 
-struct mlxsw_sp_sb_mm {
-	u32 min_buff;
-	u32 max_buff;
-	u16 pool_index;
-};
+static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+
+	return mlxsw_sp_sb_pms_init(mlxsw_sp, mlxsw_sp_port->local_port,
+				    mlxsw_sp->sb_vals->pms, false);
+}
 
-#define MLXSW_SP_SB_MM(_min_buff, _max_buff, _pool)	\
+static int mlxsw_sp_cpu_port_sb_pms_init(struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_sp_sb_pms_init(mlxsw_sp, 0, mlxsw_sp->sb_vals->pms_cpu,
+				    true);
+}
+
+#define MLXSW_SP_SB_MM(_min_buff, _max_buff)		\
 	{						\
 		.min_buff = _min_buff,			\
 		.max_buff = _max_buff,			\
-		.pool_index = _pool,			\
+		.pool_index = MLXSW_SP_SB_POOL_EGR,	\
 	}
 
 static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = {
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
-	MLXSW_SP_SB_MM(0, 6, 4),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
+	MLXSW_SP_SB_MM(0, 6),
 };
 
-#define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms)
-
 static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 {
 	char sbmm_pl[MLXSW_REG_SBMM_LEN];
 	int i;
 	int err;
 
-	for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) {
+	for (i = 0; i < mlxsw_sp->sb_vals->mms_count; i++) {
 		const struct mlxsw_sp_sb_pool_des *des;
 		const struct mlxsw_sp_sb_mm *mc;
 		u32 min_buff;
 
-		mc = &mlxsw_sp_sb_mms[i];
-		des = &mlxsw_sp_sb_pool_dess[mc->pool_index];
+		mc = &mlxsw_sp->sb_vals->mms[i];
+		des = &mlxsw_sp->sb_vals->pool_dess[mc->pool_index];
 		/* All pools used by sb_mm's are initialized using dynamic
 		 * thresholds, therefore 'max_buff' isn't specified in cells.
 		 */
@@ -611,24 +838,59 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 }
 
-static void mlxsw_sp_pool_count(u16 *p_ingress_len, u16 *p_egress_len)
+static void mlxsw_sp_pool_count(struct mlxsw_sp *mlxsw_sp,
+				u16 *p_ingress_len, u16 *p_egress_len)
 {
 	int i;
 
-	for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; ++i)
-		if (mlxsw_sp_sb_pool_dess[i].dir == MLXSW_REG_SBXX_DIR_EGRESS)
-			goto out;
-	WARN(1, "No egress pools\n");
+	for (i = 0; i < mlxsw_sp->sb_vals->pool_count; ++i) {
+		if (mlxsw_sp->sb_vals->pool_dess[i].dir ==
+		    MLXSW_REG_SBXX_DIR_INGRESS)
+			(*p_ingress_len)++;
+		else
+			(*p_egress_len)++;
+	}
 
-out:
-	*p_ingress_len = i;
-	*p_egress_len = MLXSW_SP_SB_POOL_DESS_LEN - i;
+	WARN(*p_egress_len == 0, "No egress pools\n");
 }
 
+const struct mlxsw_sp_sb_vals mlxsw_sp1_sb_vals = {
+	.pool_count = ARRAY_SIZE(mlxsw_sp1_sb_pool_dess),
+	.pool_dess = mlxsw_sp1_sb_pool_dess,
+	.pms = mlxsw_sp1_sb_pms,
+	.pms_cpu = mlxsw_sp_cpu_port_sb_pms,
+	.prs = mlxsw_sp1_sb_prs,
+	.mms = mlxsw_sp_sb_mms,
+	.cms_ingress = mlxsw_sp1_sb_cms_ingress,
+	.cms_egress = mlxsw_sp1_sb_cms_egress,
+	.cms_cpu = mlxsw_sp_cpu_port_sb_cms,
+	.mms_count = ARRAY_SIZE(mlxsw_sp_sb_mms),
+	.cms_ingress_count = ARRAY_SIZE(mlxsw_sp1_sb_cms_ingress),
+	.cms_egress_count = ARRAY_SIZE(mlxsw_sp1_sb_cms_egress),
+	.cms_cpu_count = ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms),
+};
+
+const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals = {
+	.pool_count = ARRAY_SIZE(mlxsw_sp2_sb_pool_dess),
+	.pool_dess = mlxsw_sp2_sb_pool_dess,
+	.pms = mlxsw_sp2_sb_pms,
+	.pms_cpu = mlxsw_sp_cpu_port_sb_pms,
+	.prs = mlxsw_sp2_sb_prs,
+	.mms = mlxsw_sp_sb_mms,
+	.cms_ingress = mlxsw_sp2_sb_cms_ingress,
+	.cms_egress = mlxsw_sp2_sb_cms_egress,
+	.cms_cpu = mlxsw_sp_cpu_port_sb_cms,
+	.mms_count = ARRAY_SIZE(mlxsw_sp_sb_mms),
+	.cms_ingress_count = ARRAY_SIZE(mlxsw_sp2_sb_cms_ingress),
+	.cms_egress_count = ARRAY_SIZE(mlxsw_sp2_sb_cms_egress),
+	.cms_cpu_count = ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms),
+};
+
 int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 {
-	u16 ing_pool_count;
-	u16 eg_pool_count;
+	u32 max_headroom_size;
+	u16 ing_pool_count = 0;
+	u16 eg_pool_count = 0;
 	int err;
 
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, CELL_SIZE))
@@ -637,27 +899,38 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE))
 		return -EIO;
 
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_HEADROOM_SIZE))
+		return -EIO;
+
 	mlxsw_sp->sb = kzalloc(sizeof(*mlxsw_sp->sb), GFP_KERNEL);
 	if (!mlxsw_sp->sb)
 		return -ENOMEM;
 	mlxsw_sp->sb->cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE);
 	mlxsw_sp->sb->sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						   MAX_BUFFER_SIZE);
+	max_headroom_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+					       MAX_HEADROOM_SIZE);
+	/* Round down, because this limit must not be overstepped. */
+	mlxsw_sp->sb->max_headroom_cells = max_headroom_size /
+						mlxsw_sp->sb->cell_size;
 
 	err = mlxsw_sp_sb_ports_init(mlxsw_sp);
 	if (err)
 		goto err_sb_ports_init;
-	err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp_sb_prs,
-				   MLXSW_SP_SB_PRS_LEN);
+	err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp->sb_vals->prs,
+				   mlxsw_sp->sb_vals->pool_count);
 	if (err)
 		goto err_sb_prs_init;
 	err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp);
 	if (err)
 		goto err_sb_cpu_port_sb_cms_init;
+	err = mlxsw_sp_cpu_port_sb_pms_init(mlxsw_sp);
+	if (err)
+		goto err_sb_cpu_port_pms_init;
 	err = mlxsw_sp_sb_mms_init(mlxsw_sp);
 	if (err)
 		goto err_sb_mms_init;
-	mlxsw_sp_pool_count(&ing_pool_count, &eg_pool_count);
+	mlxsw_sp_pool_count(mlxsw_sp, &ing_pool_count, &eg_pool_count);
 	err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0,
 				  mlxsw_sp->sb->sb_size,
 				  ing_pool_count,
@@ -671,6 +944,7 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 
 err_devlink_sb_register:
 err_sb_mms_init:
+err_sb_cpu_port_pms_init:
 err_sb_cpu_port_sb_cms_init:
 err_sb_prs_init:
 	mlxsw_sp_sb_ports_fini(mlxsw_sp);
@@ -705,29 +979,47 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
 			 unsigned int sb_index, u16 pool_index,
 			 struct devlink_sb_pool_info *pool_info)
 {
-	enum mlxsw_reg_sbxx_dir dir = mlxsw_sp_sb_pool_dess[pool_index].dir;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	enum mlxsw_reg_sbxx_dir dir;
 	struct mlxsw_sp_sb_pr *pr;
 
+	dir = mlxsw_sp->sb_vals->pool_dess[pool_index].dir;
 	pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index);
 	pool_info->pool_type = (enum devlink_sb_pool_type) dir;
 	pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size);
 	pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode;
+	pool_info->cell_size = mlxsw_sp->sb->cell_size;
 	return 0;
 }
 
 int mlxsw_sp_sb_pool_set(struct mlxsw_core *mlxsw_core,
 			 unsigned int sb_index, u16 pool_index, u32 size,
-			 enum devlink_sb_threshold_type threshold_type)
+			 enum devlink_sb_threshold_type threshold_type,
+			 struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	u32 pool_size = mlxsw_sp_bytes_cells(mlxsw_sp, size);
+	const struct mlxsw_sp_sb_pr *pr;
 	enum mlxsw_reg_sbpr_mode mode;
 
-	if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE))
+	mode = (enum mlxsw_reg_sbpr_mode) threshold_type;
+	pr = &mlxsw_sp->sb_vals->prs[pool_index];
+
+	if (size > MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_BUFFER_SIZE)) {
+		NL_SET_ERR_MSG_MOD(extack, "Exceeded shared buffer size");
 		return -EINVAL;
+	}
+
+	if (pr->freeze_mode && pr->mode != mode) {
+		NL_SET_ERR_MSG_MOD(extack, "Changing this pool's threshold type is forbidden");
+		return -EINVAL;
+	};
+
+	if (pr->freeze_size && pr->size != size) {
+		NL_SET_ERR_MSG_MOD(extack, "Changing this pool's size is forbidden");
+		return -EINVAL;
+	};
 
-	mode = (enum mlxsw_reg_sbpr_mode) threshold_type;
 	return mlxsw_sp_sb_pr_write(mlxsw_sp, pool_index, mode,
 				    pool_size, false);
 }
@@ -745,7 +1037,8 @@ static u32 mlxsw_sp_sb_threshold_out(struct mlxsw_sp *mlxsw_sp, u16 pool_index,
 }
 
 static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u16 pool_index,
-				    u32 threshold, u32 *p_max_buff)
+				    u32 threshold, u32 *p_max_buff,
+				    struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_sb_pr *pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index);
 
@@ -754,8 +1047,10 @@ static int mlxsw_sp_sb_threshold_in(struct mlxsw_sp *mlxsw_sp, u16 pool_index,
 
 		val = threshold + MLXSW_SP_SB_THRESHOLD_TO_ALPHA_OFFSET;
 		if (val < MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN ||
-		    val > MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX)
+		    val > MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX) {
+			NL_SET_ERR_MSG_MOD(extack, "Invalid dynamic threshold value");
 			return -EINVAL;
+		}
 		*p_max_buff = val;
 	} else {
 		*p_max_buff = mlxsw_sp_bytes_cells(mlxsw_sp, threshold);
@@ -781,7 +1076,7 @@ int mlxsw_sp_sb_port_pool_get(struct mlxsw_core_port *mlxsw_core_port,
 
 int mlxsw_sp_sb_port_pool_set(struct mlxsw_core_port *mlxsw_core_port,
 			      unsigned int sb_index, u16 pool_index,
-			      u32 threshold)
+			      u32 threshold, struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port =
 			mlxsw_core_port_driver_priv(mlxsw_core_port);
@@ -791,7 +1086,7 @@ int mlxsw_sp_sb_port_pool_set(struct mlxsw_core_port *mlxsw_core_port,
 	int err;
 
 	err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool_index,
-				       threshold, &max_buff);
+				       threshold, &max_buff, extack);
 	if (err)
 		return err;
 
@@ -822,22 +1117,41 @@ int mlxsw_sp_sb_tc_pool_bind_get(struct mlxsw_core_port *mlxsw_core_port,
 int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port,
 				 unsigned int sb_index, u16 tc_index,
 				 enum devlink_sb_pool_type pool_type,
-				 u16 pool_index, u32 threshold)
+				 u16 pool_index, u32 threshold,
+				 struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port =
 			mlxsw_core_port_driver_priv(mlxsw_core_port);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	u8 local_port = mlxsw_sp_port->local_port;
+	const struct mlxsw_sp_sb_cm *cm;
 	u8 pg_buff = tc_index;
 	enum mlxsw_reg_sbxx_dir dir = (enum mlxsw_reg_sbxx_dir) pool_type;
 	u32 max_buff;
 	int err;
 
-	if (dir != mlxsw_sp_sb_pool_dess[pool_index].dir)
+	if (dir != mlxsw_sp->sb_vals->pool_dess[pool_index].dir) {
+		NL_SET_ERR_MSG_MOD(extack, "Binding egress TC to ingress pool and vice versa is forbidden");
 		return -EINVAL;
+	}
+
+	if (dir == MLXSW_REG_SBXX_DIR_INGRESS)
+		cm = &mlxsw_sp->sb_vals->cms_ingress[tc_index];
+	else
+		cm = &mlxsw_sp->sb_vals->cms_egress[tc_index];
+
+	if (cm->freeze_pool && cm->pool_index != pool_index) {
+		NL_SET_ERR_MSG_MOD(extack, "Binding this TC to a different pool is forbidden");
+		return -EINVAL;
+	}
+
+	if (cm->freeze_thresh && cm->max_buff != threshold) {
+		NL_SET_ERR_MSG_MOD(extack, "Changing this TC's threshold is forbidden");
+		return -EINVAL;
+	}
 
 	err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool_index,
-				       threshold, &max_buff);
+				       threshold, &max_buff, extack);
 	if (err)
 		return err;
 
@@ -931,7 +1245,7 @@ next_batch:
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
 		mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
-		for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) {
+		for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
 			err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i,
 						       &bulk_list);
 			if (err)
@@ -990,7 +1304,7 @@ next_batch:
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
 		mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
-		for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) {
+		for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
 			err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i,
 						       &bulk_list);
 			if (err)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index 41e607a14846..49933818c6f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -220,7 +220,7 @@ start_again:
 	for (; i < rif_count; i++) {
 		struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i);
 
-		if (!rif)
+		if (!rif || !mlxsw_sp_rif_dev(rif))
 			continue;
 		err = mlxsw_sp_erif_entry_get(mlxsw_sp, &entry, rif,
 					      counters_enabled);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
index e689576231ab..246dbb3c0e1b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -4,24 +4,9 @@
 #ifndef _MLXSW_PIPELINE_H_
 #define _MLXSW_PIPELINE_H_
 
-#if IS_ENABLED(CONFIG_NET_DEVLINK)
-
 int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp);
 
-#else
-
-static inline int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp)
-{
-	return 0;
-}
-
-static inline void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp)
-{
-}
-
-#endif
-
 #define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif"
 #define MLXSW_SP_DPIPE_TABLE_NAME_HOST4 "mlxsw_host4"
 #define MLXSW_SP_DPIPE_TABLE_NAME_HOST6 "mlxsw_host6"
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 9d9aa28684af..46baf3b44309 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -1188,8 +1188,7 @@ static int mlxsw_sp_fid_family_register(struct mlxsw_sp *mlxsw_sp,
 
 	fid_family->mlxsw_sp = mlxsw_sp;
 	INIT_LIST_HEAD(&fid_family->fids_list);
-	fid_family->fids_bitmap = kcalloc(BITS_TO_LONGS(nr_fids),
-					  sizeof(unsigned long), GFP_KERNEL);
+	fid_family->fids_bitmap = bitmap_zalloc(nr_fids, GFP_KERNEL);
 	if (!fid_family->fids_bitmap) {
 		err = -ENOMEM;
 		goto err_alloc_fids_bitmap;
@@ -1206,7 +1205,7 @@ static int mlxsw_sp_fid_family_register(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_fid_flood_tables_init:
-	kfree(fid_family->fids_bitmap);
+	bitmap_free(fid_family->fids_bitmap);
 err_alloc_fids_bitmap:
 	kfree(fid_family);
 	return err;
@@ -1217,7 +1216,7 @@ mlxsw_sp_fid_family_unregister(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_fid_family *fid_family)
 {
 	mlxsw_sp->fid_core->fid_family_arr[fid_family->type] = NULL;
-	kfree(fid_family->fids_bitmap);
+	bitmap_free(fid_family->fids_bitmap);
 	WARN_ON_ONCE(!list_empty(&fid_family->fids_list));
 	kfree(fid_family);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index ff072358d950..202e9a246019 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -17,13 +17,13 @@
 static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_acl_block *block,
 					 struct mlxsw_sp_acl_rule_info *rulei,
-					 struct tcf_exts *exts,
+					 struct flow_action *flow_action,
 					 struct netlink_ext_ack *extack)
 {
-	const struct tc_action *a;
+	const struct flow_action_entry *act;
 	int err, i;
 
-	if (!tcf_exts_has_actions(exts))
+	if (!flow_action_has_entries(flow_action))
 		return 0;
 
 	/* Count action is inserted first */
@@ -31,27 +31,31 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	tcf_exts_for_each_action(i, a, exts) {
-		if (is_tcf_gact_ok(a)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
 			err = mlxsw_sp_acl_rulei_act_terminate(rulei);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append terminate action");
 				return err;
 			}
-		} else if (is_tcf_gact_shot(a)) {
+			break;
+		case FLOW_ACTION_DROP:
 			err = mlxsw_sp_acl_rulei_act_drop(rulei);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append drop action");
 				return err;
 			}
-		} else if (is_tcf_gact_trap(a)) {
+			break;
+		case FLOW_ACTION_TRAP:
 			err = mlxsw_sp_acl_rulei_act_trap(rulei);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append trap action");
 				return err;
 			}
-		} else if (is_tcf_gact_goto_chain(a)) {
-			u32 chain_index = tcf_gact_goto_chain_index(a);
+			break;
+		case FLOW_ACTION_GOTO: {
+			u32 chain_index = act->chain_index;
 			struct mlxsw_sp_acl_ruleset *ruleset;
 			u16 group_id;
 
@@ -67,7 +71,9 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append jump action");
 				return err;
 			}
-		} else if (is_tcf_mirred_egress_redirect(a)) {
+			}
+			break;
+		case FLOW_ACTION_REDIRECT: {
 			struct net_device *out_dev;
 			struct mlxsw_sp_fid *fid;
 			u16 fid_index;
@@ -79,29 +85,33 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			if (err)
 				return err;
 
-			out_dev = tcf_mirred_dev(a);
+			out_dev = act->dev;
 			err = mlxsw_sp_acl_rulei_act_fwd(mlxsw_sp, rulei,
 							 out_dev, extack);
 			if (err)
 				return err;
-		} else if (is_tcf_mirred_egress_mirror(a)) {
-			struct net_device *out_dev = tcf_mirred_dev(a);
+			}
+			break;
+		case FLOW_ACTION_MIRRED: {
+			struct net_device *out_dev = act->dev;
 
 			err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei,
 							    block, out_dev,
 							    extack);
 			if (err)
 				return err;
-		} else if (is_tcf_vlan(a)) {
-			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
-			u32 action = tcf_vlan_action(a);
-			u8 prio = tcf_vlan_push_prio(a);
-			u16 vid = tcf_vlan_push_vid(a);
+			}
+			break;
+		case FLOW_ACTION_VLAN_MANGLE: {
+			u16 proto = be16_to_cpu(act->vlan.proto);
+			u8 prio = act->vlan.prio;
+			u16 vid = act->vlan.vid;
 
 			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
-							   action, vid,
+							   act->id, vid,
 							   proto, prio, extack);
-		} else {
+			}
+		default:
 			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
 			return -EOPNOTSUPP;
@@ -110,72 +120,106 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
+static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei,
+				      struct flow_cls_offload *f,
+				      struct mlxsw_sp_acl_block *block)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct net_device *ingress_dev;
+	struct flow_match_meta match;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+		return 0;
+
+	flow_rule_match_meta(rule, &match);
+	if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported ingress ifindex mask");
+		return -EINVAL;
+	}
+
+	ingress_dev = __dev_get_by_index(block->net,
+					 match.key->ingress_ifindex);
+	if (!ingress_dev) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Can't find specified ingress port to match on");
+		return -EINVAL;
+	}
+
+	if (!mlxsw_sp_port_dev_check(ingress_dev)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on non-mlxsw ingress port");
+		return -EINVAL;
+	}
+
+	mlxsw_sp_port = netdev_priv(ingress_dev);
+	if (mlxsw_sp_port->mlxsw_sp != block->mlxsw_sp) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on a port from different device");
+		return -EINVAL;
+	}
+
+	mlxsw_sp_acl_rulei_keymask_u32(rulei,
+				       MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
+				       mlxsw_sp_port->local_port,
+				       0xFFFFFFFF);
+	return 0;
+}
+
 static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei,
-				       struct tc_cls_flower_offload *f)
+				       struct flow_cls_offload *f)
 {
-	struct flow_dissector_key_ipv4_addrs *key =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-					  f->key);
-	struct flow_dissector_key_ipv4_addrs *mask =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-					  f->mask);
+	struct flow_match_ipv4_addrs match;
+
+	flow_rule_match_ipv4_addrs(f->rule, &match);
 
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
-				       (char *) &key->src,
-				       (char *) &mask->src, 4);
+				       (char *) &match.key->src,
+				       (char *) &match.mask->src, 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
-				       (char *) &key->dst,
-				       (char *) &mask->dst, 4);
+				       (char *) &match.key->dst,
+				       (char *) &match.mask->dst, 4);
 }
 
 static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
-				       struct tc_cls_flower_offload *f)
+				       struct flow_cls_offload *f)
 {
-	struct flow_dissector_key_ipv6_addrs *key =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-					  f->key);
-	struct flow_dissector_key_ipv6_addrs *mask =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-					  f->mask);
+	struct flow_match_ipv6_addrs match;
+
+	flow_rule_match_ipv6_addrs(f->rule, &match);
 
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127,
-				       &key->src.s6_addr[0x0],
-				       &mask->src.s6_addr[0x0], 4);
+				       &match.key->src.s6_addr[0x0],
+				       &match.mask->src.s6_addr[0x0], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95,
-				       &key->src.s6_addr[0x4],
-				       &mask->src.s6_addr[0x4], 4);
+				       &match.key->src.s6_addr[0x4],
+				       &match.mask->src.s6_addr[0x4], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63,
-				       &key->src.s6_addr[0x8],
-				       &mask->src.s6_addr[0x8], 4);
+				       &match.key->src.s6_addr[0x8],
+				       &match.mask->src.s6_addr[0x8], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
-				       &key->src.s6_addr[0xC],
-				       &mask->src.s6_addr[0xC], 4);
+				       &match.key->src.s6_addr[0xC],
+				       &match.mask->src.s6_addr[0xC], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127,
-				       &key->dst.s6_addr[0x0],
-				       &mask->dst.s6_addr[0x0], 4);
+				       &match.key->dst.s6_addr[0x0],
+				       &match.mask->dst.s6_addr[0x0], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95,
-				       &key->dst.s6_addr[0x4],
-				       &mask->dst.s6_addr[0x4], 4);
+				       &match.key->dst.s6_addr[0x4],
+				       &match.mask->dst.s6_addr[0x4], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63,
-				       &key->dst.s6_addr[0x8],
-				       &mask->dst.s6_addr[0x8], 4);
+				       &match.key->dst.s6_addr[0x8],
+				       &match.mask->dst.s6_addr[0x8], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
-				       &key->dst.s6_addr[0xC],
-				       &mask->dst.s6_addr[0xC], 4);
+				       &match.key->dst.s6_addr[0xC],
+				       &match.mask->dst.s6_addr[0xC], 4);
 }
 
 static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_acl_rule_info *rulei,
-				       struct tc_cls_flower_offload *f,
+				       struct flow_cls_offload *f,
 				       u8 ip_proto)
 {
-	struct flow_dissector_key_ports *key, *mask;
+	const struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_match_ports match;
 
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS))
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS))
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
@@ -184,27 +228,25 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 	}
 
-	key = skb_flow_dissector_target(f->dissector,
-					FLOW_DISSECTOR_KEY_PORTS,
-					f->key);
-	mask = skb_flow_dissector_target(f->dissector,
-					 FLOW_DISSECTOR_KEY_PORTS,
-					 f->mask);
+	flow_rule_match_ports(rule, &match);
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_DST_L4_PORT,
-				       ntohs(key->dst), ntohs(mask->dst));
+				       ntohs(match.key->dst),
+				       ntohs(match.mask->dst));
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_SRC_L4_PORT,
-				       ntohs(key->src), ntohs(mask->src));
+				       ntohs(match.key->src),
+				       ntohs(match.mask->src));
 	return 0;
 }
 
 static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_rule_info *rulei,
-				     struct tc_cls_flower_offload *f,
+				     struct flow_cls_offload *f,
 				     u8 ip_proto)
 {
-	struct flow_dissector_key_tcp *key, *mask;
+	const struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_match_tcp match;
 
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP))
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP))
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP) {
@@ -213,25 +255,23 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 	}
 
-	key = skb_flow_dissector_target(f->dissector,
-					FLOW_DISSECTOR_KEY_TCP,
-					f->key);
-	mask = skb_flow_dissector_target(f->dissector,
-					 FLOW_DISSECTOR_KEY_TCP,
-					 f->mask);
+	flow_rule_match_tcp(rule, &match);
+
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_TCP_FLAGS,
-				       ntohs(key->flags), ntohs(mask->flags));
+				       ntohs(match.key->flags),
+				       ntohs(match.mask->flags));
 	return 0;
 }
 
 static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 				    struct mlxsw_sp_acl_rule_info *rulei,
-				    struct tc_cls_flower_offload *f,
+				    struct flow_cls_offload *f,
 				    u16 n_proto)
 {
-	struct flow_dissector_key_ip *key, *mask;
+	const struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_match_ip match;
 
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP))
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP))
 		return 0;
 
 	if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) {
@@ -240,20 +280,18 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 	}
 
-	key = skb_flow_dissector_target(f->dissector,
-					FLOW_DISSECTOR_KEY_IP,
-					f->key);
-	mask = skb_flow_dissector_target(f->dissector,
-					 FLOW_DISSECTOR_KEY_IP,
-					 f->mask);
+	flow_rule_match_ip(rule, &match);
+
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_TTL_,
-				       key->ttl, mask->ttl);
+				       match.key->ttl, match.mask->ttl);
 
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_ECN,
-				       key->tos & 0x3, mask->tos & 0x3);
+				       match.key->tos & 0x3,
+				       match.mask->tos & 0x3);
 
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_DSCP,
-				       key->tos >> 6, mask->tos >> 6);
+				       match.key->tos >> 2,
+				       match.mask->tos >> 2);
 
 	return 0;
 }
@@ -261,16 +299,19 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_block *block,
 				 struct mlxsw_sp_acl_rule_info *rulei,
-				 struct tc_cls_flower_offload *f)
+				 struct flow_cls_offload *f)
 {
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0;
 	u16 n_proto_key = 0;
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 	int err;
 
-	if (f->dissector->used_keys &
-	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	if (dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_META) |
+	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
@@ -286,25 +327,23 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_sp_acl_rulei_priority(rulei, f->common.prio);
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
-		addr_type = key->addr_type;
+	err = mlxsw_sp_flower_parse_meta(rulei, f, block);
+	if (err)
+		return err;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
-		n_proto_key = ntohs(key->n_proto);
-		n_proto_mask = ntohs(mask->n_proto);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		n_proto_key = ntohs(match.key->n_proto);
+		n_proto_mask = ntohs(match.mask->n_proto);
 
 		if (n_proto_key == ETH_P_ALL) {
 			n_proto_key = 0;
@@ -314,60 +353,53 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 					       MLXSW_AFK_ELEMENT_ETHERTYPE,
 					       n_proto_key, n_proto_mask);
 
-		ip_proto = key->ip_proto;
+		ip_proto = match.key->ip_proto;
 		mlxsw_sp_acl_rulei_keymask_u32(rulei,
 					       MLXSW_AFK_ELEMENT_IP_PROTO,
-					       key->ip_proto, mask->ip_proto);
+					       match.key->ip_proto,
+					       match.mask->ip_proto);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
+		flow_rule_match_eth_addrs(rule, &match);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_DMAC_32_47,
-					       key->dst, mask->dst, 2);
+					       match.key->dst,
+					       match.mask->dst, 2);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_DMAC_0_31,
-					       key->dst + 2, mask->dst + 2, 4);
+					       match.key->dst + 2,
+					       match.mask->dst + 2, 4);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_SMAC_32_47,
-					       key->src, mask->src, 2);
+					       match.key->src,
+					       match.mask->src, 2);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_SMAC_0_31,
-					       key->src + 2, mask->src + 2, 4);
+					       match.key->src + 2,
+					       match.mask->src + 2, 4);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
+		flow_rule_match_vlan(rule, &match);
 		if (mlxsw_sp_acl_block_is_egress_bound(block)) {
 			NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress");
 			return -EOPNOTSUPP;
 		}
-		if (mask->vlan_id != 0)
+		if (match.mask->vlan_id != 0)
 			mlxsw_sp_acl_rulei_keymask_u32(rulei,
 						       MLXSW_AFK_ELEMENT_VID,
-						       key->vlan_id,
-						       mask->vlan_id);
-		if (mask->vlan_priority != 0)
+						       match.key->vlan_id,
+						       match.mask->vlan_id);
+		if (match.mask->vlan_priority != 0)
 			mlxsw_sp_acl_rulei_keymask_u32(rulei,
 						       MLXSW_AFK_ELEMENT_PCP,
-						       key->vlan_priority,
-						       mask->vlan_priority);
+						       match.key->vlan_priority,
+						       match.mask->vlan_priority);
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS)
@@ -387,13 +419,14 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, f->exts,
+	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei,
+					     &f->rule->action,
 					     f->common.extack);
 }
 
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block,
-			    struct tc_cls_flower_offload *f)
+			    struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_rule_info *rulei;
 	struct mlxsw_sp_acl_ruleset *ruleset;
@@ -440,7 +473,7 @@ err_rule_create:
 
 void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_block *block,
-			     struct tc_cls_flower_offload *f)
+			     struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule *rule;
@@ -462,7 +495,7 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_block *block,
-			  struct tc_cls_flower_offload *f)
+			  struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule *rule;
@@ -486,7 +519,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rule_get_stats;
 
-	tcf_exts_stats_update(f->exts, bytes, packets, lastuse);
+	flow_stats_update(&f->stats, bytes, packets, lastuse);
 
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 	return 0;
@@ -498,7 +531,7 @@ err_rule_get_stats:
 
 int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_block *block,
-				 struct tc_cls_flower_offload *f)
+				 struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule_info rulei;
@@ -519,7 +552,7 @@ int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_block *block,
-				   struct tc_cls_flower_offload *f)
+				   struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 00db26c96bf5..6400cd644b7a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -145,6 +145,7 @@ mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_ipip_entry *ipip_entry)
 {
 	u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb);
+	u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb);
 	char rtdp_pl[MLXSW_REG_RTDP_LEN];
 	struct ip_tunnel_parm parms;
 	unsigned int type_check;
@@ -157,6 +158,7 @@ mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp,
 	ikey = mlxsw_sp_ipip_parms4_ikey(parms);
 
 	mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index);
+	mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_id);
 
 	type_check = has_ikey ?
 		MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY :
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index fb1c48c698f2..1df164a4b06d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -267,8 +267,8 @@ mlxsw_sp_nve_mc_record_create(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_nve_mc_record *mc_record;
 	int err;
 
-	mc_record = kzalloc(sizeof(*mc_record) + num_max_entries *
-			    sizeof(struct mlxsw_sp_nve_mc_entry), GFP_KERNEL);
+	mc_record = kzalloc(struct_size(mc_record, entries, num_max_entries),
+			    GFP_KERNEL);
 	if (!mc_record)
 		return ERR_PTR(-ENOMEM);
 
@@ -841,11 +841,9 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 
 	nve->config = config;
 
-	err = ops->fdb_replay(params->dev, params->vni);
-	if (err) {
-		NL_SET_ERR_MSG_MOD(extack, "Failed to offload the FDB");
+	err = ops->fdb_replay(params->dev, params->vni, extack);
+	if (err)
 		goto err_fdb_replay;
-	}
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
index 02937ea95bc3..0035640156a1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
@@ -28,6 +28,7 @@ struct mlxsw_sp_nve {
 	unsigned int num_nve_tunnels;	/* Protected by RTNL */
 	unsigned int num_max_mc_entries[MLXSW_SP_L3_PROTO_MAX];
 	u32 tunnel_index;
+	u16 ul_rif_index;	/* Reserved for Spectrum */
 };
 
 struct mlxsw_sp_nve_ops {
@@ -41,7 +42,8 @@ struct mlxsw_sp_nve_ops {
 	int (*init)(struct mlxsw_sp_nve *nve,
 		    const struct mlxsw_sp_nve_config *config);
 	void (*fini)(struct mlxsw_sp_nve *nve);
-	int (*fdb_replay)(const struct net_device *nve_dev, __be32 vni);
+	int (*fdb_replay)(const struct net_device *nve_dev, __be32 vni,
+			  struct netlink_ext_ack *extack);
 	void (*fdb_clear_offload)(const struct net_device *nve_dev, __be32 vni);
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
index 74e564c4ac19..93ccd9fc2266 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
@@ -7,6 +7,7 @@
 #include <net/vxlan.h>
 
 #include "reg.h"
+#include "spectrum.h"
 #include "spectrum_nve.h"
 
 /* Eth (18B) | IPv6 (40B) | UDP (8B) | VxLAN (8B) | Eth (14B) | IPv6 (40B)
@@ -20,9 +21,9 @@
 #define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS	(VXLAN_F_UDP_ZERO_CSUM_TX | \
 						 VXLAN_F_LEARN)
 
-static bool mlxsw_sp1_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
-					    const struct net_device *dev,
-					    struct netlink_ext_ack *extack)
+static bool mlxsw_sp_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
+					   const struct net_device *dev,
+					   struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_config *cfg = &vxlan->cfg;
@@ -112,13 +113,30 @@ static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl);
 }
 
+static void
+mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl,
+				  const struct mlxsw_sp_nve_config *config)
+{
+	u8 udp_sport;
+
+	mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, true,
+			     config->ttl);
+	/* VxLAN driver's default UDP source port range is 32768 (0x8000)
+	 * to 60999 (0xee47). Set the upper 8 bits of the UDP source port
+	 * to a random number between 0x80 and 0xee
+	 */
+	get_random_bytes(&udp_sport, sizeof(udp_sport));
+	udp_sport = (udp_sport % (0xee - 0x80 + 1)) + 0x80;
+	mlxsw_reg_tngcr_nve_udp_sport_prefix_set(tngcr_pl, udp_sport);
+	mlxsw_reg_tngcr_usipv4_set(tngcr_pl, be32_to_cpu(config->ul_sip.addr4));
+}
+
 static int
 mlxsw_sp1_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp,
 			       const struct mlxsw_sp_nve_config *config)
 {
 	char tngcr_pl[MLXSW_REG_TNGCR_LEN];
 	u16 ul_vr_id;
-	u8 udp_sport;
 	int err;
 
 	err = mlxsw_sp_router_tb_id_vr_id(mlxsw_sp, config->ul_tb_id,
@@ -126,18 +144,9 @@ mlxsw_sp1_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, true,
-			     config->ttl);
-	/* VxLAN driver's default UDP source port range is 32768 (0x8000)
-	 * to 60999 (0xee47). Set the upper 8 bits of the UDP source port
-	 * to a random number between 0x80 and 0xee
-	 */
-	get_random_bytes(&udp_sport, sizeof(udp_sport));
-	udp_sport = (udp_sport % (0xee - 0x80 + 1)) + 0x80;
-	mlxsw_reg_tngcr_nve_udp_sport_prefix_set(tngcr_pl, udp_sport);
+	mlxsw_sp_nve_vxlan_config_prepare(tngcr_pl, config);
 	mlxsw_reg_tngcr_learn_enable_set(tngcr_pl, config->learning_en);
 	mlxsw_reg_tngcr_underlay_virtual_router_set(tngcr_pl, ul_vr_id);
-	mlxsw_reg_tngcr_usipv4_set(tngcr_pl, be32_to_cpu(config->ul_sip.addr4));
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl);
 }
@@ -212,11 +221,13 @@ static void mlxsw_sp1_nve_vxlan_fini(struct mlxsw_sp_nve *nve)
 }
 
 static int
-mlxsw_sp_nve_vxlan_fdb_replay(const struct net_device *nve_dev, __be32 vni)
+mlxsw_sp_nve_vxlan_fdb_replay(const struct net_device *nve_dev, __be32 vni,
+			      struct netlink_ext_ack *extack)
 {
 	if (WARN_ON(!netif_is_vxlan(nve_dev)))
 		return -EINVAL;
-	return vxlan_fdb_replay(nve_dev, vni, &mlxsw_sp_switchdev_notifier);
+	return vxlan_fdb_replay(nve_dev, vni, &mlxsw_sp_switchdev_notifier,
+				extack);
 }
 
 static void
@@ -229,7 +240,7 @@ mlxsw_sp_nve_vxlan_clear_offload(const struct net_device *nve_dev, __be32 vni)
 
 const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops = {
 	.type		= MLXSW_SP_NVE_TYPE_VXLAN,
-	.can_offload	= mlxsw_sp1_nve_vxlan_can_offload,
+	.can_offload	= mlxsw_sp_nve_vxlan_can_offload,
 	.nve_config	= mlxsw_sp_nve_vxlan_config,
 	.init		= mlxsw_sp1_nve_vxlan_init,
 	.fini		= mlxsw_sp1_nve_vxlan_fini,
@@ -237,26 +248,126 @@ const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops = {
 	.fdb_clear_offload = mlxsw_sp_nve_vxlan_clear_offload,
 };
 
-static bool mlxsw_sp2_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
-					    const struct net_device *dev,
-					    struct netlink_ext_ack *extack)
+static bool mlxsw_sp2_nve_vxlan_learning_set(struct mlxsw_sp *mlxsw_sp,
+					     bool learning_en)
 {
-	return false;
+	char tnpc_pl[MLXSW_REG_TNPC_LEN];
+
+	mlxsw_reg_tnpc_pack(tnpc_pl, MLXSW_REG_TNPC_TUNNEL_PORT_NVE,
+			    learning_en);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tnpc), tnpc_pl);
+}
+
+static int
+mlxsw_sp2_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp,
+			       const struct mlxsw_sp_nve_config *config)
+{
+	char tngcr_pl[MLXSW_REG_TNGCR_LEN];
+	u16 ul_rif_index;
+	int err;
+
+	err = mlxsw_sp_router_ul_rif_get(mlxsw_sp, config->ul_tb_id,
+					 &ul_rif_index);
+	if (err)
+		return err;
+	mlxsw_sp->nve->ul_rif_index = ul_rif_index;
+
+	err = mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, config->learning_en);
+	if (err)
+		goto err_vxlan_learning_set;
+
+	mlxsw_sp_nve_vxlan_config_prepare(tngcr_pl, config);
+	mlxsw_reg_tngcr_underlay_rif_set(tngcr_pl, ul_rif_index);
+
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl);
+	if (err)
+		goto err_tngcr_write;
+
+	return 0;
+
+err_tngcr_write:
+	mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, false);
+err_vxlan_learning_set:
+	mlxsw_sp_router_ul_rif_put(mlxsw_sp, ul_rif_index);
+	return err;
+}
+
+static void mlxsw_sp2_nve_vxlan_config_clear(struct mlxsw_sp *mlxsw_sp)
+{
+	char tngcr_pl[MLXSW_REG_TNGCR_LEN];
+
+	mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, false, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl);
+	mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, false);
+	mlxsw_sp_router_ul_rif_put(mlxsw_sp, mlxsw_sp->nve->ul_rif_index);
+}
+
+static int mlxsw_sp2_nve_vxlan_rtdp_set(struct mlxsw_sp *mlxsw_sp,
+					unsigned int tunnel_index,
+					u16 ul_rif_index)
+{
+	char rtdp_pl[MLXSW_REG_RTDP_LEN];
+
+	mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_NVE, tunnel_index);
+	mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_index);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl);
 }
 
 static int mlxsw_sp2_nve_vxlan_init(struct mlxsw_sp_nve *nve,
 				    const struct mlxsw_sp_nve_config *config)
 {
-	return -EOPNOTSUPP;
+	struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
+	int err;
+
+	err = mlxsw_sp_nve_parsing_set(mlxsw_sp,
+				       MLXSW_SP_NVE_VXLAN_PARSING_DEPTH,
+				       config->udp_dport);
+	if (err)
+		return err;
+
+	err = mlxsw_sp2_nve_vxlan_config_set(mlxsw_sp, config);
+	if (err)
+		goto err_config_set;
+
+	err = mlxsw_sp2_nve_vxlan_rtdp_set(mlxsw_sp, nve->tunnel_index,
+					   nve->ul_rif_index);
+	if (err)
+		goto err_rtdp_set;
+
+	err = mlxsw_sp_router_nve_promote_decap(mlxsw_sp, config->ul_tb_id,
+						config->ul_proto,
+						&config->ul_sip,
+						nve->tunnel_index);
+	if (err)
+		goto err_promote_decap;
+
+	return 0;
+
+err_promote_decap:
+err_rtdp_set:
+	mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
+err_config_set:
+	mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
+				 config->udp_dport);
+	return err;
 }
 
 static void mlxsw_sp2_nve_vxlan_fini(struct mlxsw_sp_nve *nve)
 {
+	struct mlxsw_sp_nve_config *config = &nve->config;
+	struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
+
+	mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id,
+					 config->ul_proto, &config->ul_sip);
+	mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
+	mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
+				 config->udp_dport);
 }
 
 const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = {
 	.type		= MLXSW_SP_NVE_TYPE_VXLAN,
-	.can_offload	= mlxsw_sp2_nve_vxlan_can_offload,
+	.can_offload	= mlxsw_sp_nve_vxlan_can_offload,
 	.nve_config	= mlxsw_sp_nve_vxlan_config,
 	.init		= mlxsw_sp2_nve_vxlan_init,
 	.fini		= mlxsw_sp2_nve_vxlan_fini,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
new file mode 100644
index 000000000000..bd9c2bc2d5d6
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -0,0 +1,1111 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */
+
+#include <linux/ptp_clock_kernel.h>
+#include <linux/clocksource.h>
+#include <linux/timecounter.h>
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/rhashtable.h>
+#include <linux/ptp_classify.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/net_tstamp.h>
+
+#include "spectrum.h"
+#include "spectrum_ptp.h"
+#include "core.h"
+
+#define MLXSW_SP1_PTP_CLOCK_CYCLES_SHIFT	29
+#define MLXSW_SP1_PTP_CLOCK_FREQ_KHZ		156257 /* 6.4nSec */
+#define MLXSW_SP1_PTP_CLOCK_MASK		64
+
+#define MLXSW_SP1_PTP_HT_GC_INTERVAL		500 /* ms */
+
+/* How long, approximately, should the unmatched entries stay in the hash table
+ * before they are collected. Should be evenly divisible by the GC interval.
+ */
+#define MLXSW_SP1_PTP_HT_GC_TIMEOUT		1000 /* ms */
+
+struct mlxsw_sp_ptp_state {
+	struct mlxsw_sp *mlxsw_sp;
+	struct rhashtable unmatched_ht;
+	spinlock_t unmatched_lock; /* protects the HT */
+	struct delayed_work ht_gc_dw;
+	u32 gc_cycle;
+};
+
+struct mlxsw_sp1_ptp_key {
+	u8 local_port;
+	u8 message_type;
+	u16 sequence_id;
+	u8 domain_number;
+	bool ingress;
+};
+
+struct mlxsw_sp1_ptp_unmatched {
+	struct mlxsw_sp1_ptp_key key;
+	struct rhash_head ht_node;
+	struct rcu_head rcu;
+	struct sk_buff *skb;
+	u64 timestamp;
+	u32 gc_cycle;
+};
+
+static const struct rhashtable_params mlxsw_sp1_ptp_unmatched_ht_params = {
+	.key_len = sizeof_field(struct mlxsw_sp1_ptp_unmatched, key),
+	.key_offset = offsetof(struct mlxsw_sp1_ptp_unmatched, key),
+	.head_offset = offsetof(struct mlxsw_sp1_ptp_unmatched, ht_node),
+};
+
+struct mlxsw_sp_ptp_clock {
+	struct mlxsw_core *core;
+	spinlock_t lock; /* protect this structure */
+	struct cyclecounter cycles;
+	struct timecounter tc;
+	u32 nominal_c_mult;
+	struct ptp_clock *ptp;
+	struct ptp_clock_info ptp_info;
+	unsigned long overflow_period;
+	struct delayed_work overflow_work;
+};
+
+static u64 __mlxsw_sp1_ptp_read_frc(struct mlxsw_sp_ptp_clock *clock,
+				    struct ptp_system_timestamp *sts)
+{
+	struct mlxsw_core *mlxsw_core = clock->core;
+	u32 frc_h1, frc_h2, frc_l;
+
+	frc_h1 = mlxsw_core_read_frc_h(mlxsw_core);
+	ptp_read_system_prets(sts);
+	frc_l = mlxsw_core_read_frc_l(mlxsw_core);
+	ptp_read_system_postts(sts);
+	frc_h2 = mlxsw_core_read_frc_h(mlxsw_core);
+
+	if (frc_h1 != frc_h2) {
+		/* wrap around */
+		ptp_read_system_prets(sts);
+		frc_l = mlxsw_core_read_frc_l(mlxsw_core);
+		ptp_read_system_postts(sts);
+	}
+
+	return (u64) frc_l | (u64) frc_h2 << 32;
+}
+
+static u64 mlxsw_sp1_ptp_read_frc(const struct cyclecounter *cc)
+{
+	struct mlxsw_sp_ptp_clock *clock =
+		container_of(cc, struct mlxsw_sp_ptp_clock, cycles);
+
+	return __mlxsw_sp1_ptp_read_frc(clock, NULL) & cc->mask;
+}
+
+static int
+mlxsw_sp1_ptp_phc_adjfreq(struct mlxsw_sp_ptp_clock *clock, int freq_adj)
+{
+	struct mlxsw_core *mlxsw_core = clock->core;
+	char mtutc_pl[MLXSW_REG_MTUTC_LEN];
+
+	mlxsw_reg_mtutc_pack(mtutc_pl, MLXSW_REG_MTUTC_OPERATION_ADJUST_FREQ,
+			     freq_adj, 0);
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtutc), mtutc_pl);
+}
+
+static u64 mlxsw_sp1_ptp_ns2cycles(const struct timecounter *tc, u64 nsec)
+{
+	u64 cycles = (u64) nsec;
+
+	cycles <<= tc->cc->shift;
+	cycles = div_u64(cycles, tc->cc->mult);
+
+	return cycles;
+}
+
+static int
+mlxsw_sp1_ptp_phc_settime(struct mlxsw_sp_ptp_clock *clock, u64 nsec)
+{
+	struct mlxsw_core *mlxsw_core = clock->core;
+	u64 next_sec, next_sec_in_nsec, cycles;
+	char mtutc_pl[MLXSW_REG_MTUTC_LEN];
+	char mtpps_pl[MLXSW_REG_MTPPS_LEN];
+	int err;
+
+	next_sec = div_u64(nsec, NSEC_PER_SEC) + 1;
+	next_sec_in_nsec = next_sec * NSEC_PER_SEC;
+
+	spin_lock_bh(&clock->lock);
+	cycles = mlxsw_sp1_ptp_ns2cycles(&clock->tc, next_sec_in_nsec);
+	spin_unlock_bh(&clock->lock);
+
+	mlxsw_reg_mtpps_vpin_pack(mtpps_pl, cycles);
+	err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtpps), mtpps_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mtutc_pack(mtutc_pl,
+			     MLXSW_REG_MTUTC_OPERATION_SET_TIME_AT_NEXT_SEC,
+			     0, next_sec);
+	return mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtutc), mtutc_pl);
+}
+
+static int mlxsw_sp1_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct mlxsw_sp_ptp_clock *clock =
+		container_of(ptp, struct mlxsw_sp_ptp_clock, ptp_info);
+	int neg_adj = 0;
+	u32 diff;
+	u64 adj;
+	s32 ppb;
+
+	ppb = scaled_ppm_to_ppb(scaled_ppm);
+
+	if (ppb < 0) {
+		neg_adj = 1;
+		ppb = -ppb;
+	}
+
+	adj = clock->nominal_c_mult;
+	adj *= ppb;
+	diff = div_u64(adj, NSEC_PER_SEC);
+
+	spin_lock_bh(&clock->lock);
+	timecounter_read(&clock->tc);
+	clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff :
+				       clock->nominal_c_mult + diff;
+	spin_unlock_bh(&clock->lock);
+
+	return mlxsw_sp1_ptp_phc_adjfreq(clock, neg_adj ? -ppb : ppb);
+}
+
+static int mlxsw_sp1_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct mlxsw_sp_ptp_clock *clock =
+		container_of(ptp, struct mlxsw_sp_ptp_clock, ptp_info);
+	u64 nsec;
+
+	spin_lock_bh(&clock->lock);
+	timecounter_adjtime(&clock->tc, delta);
+	nsec = timecounter_read(&clock->tc);
+	spin_unlock_bh(&clock->lock);
+
+	return mlxsw_sp1_ptp_phc_settime(clock, nsec);
+}
+
+static int mlxsw_sp1_ptp_gettimex(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	struct mlxsw_sp_ptp_clock *clock =
+		container_of(ptp, struct mlxsw_sp_ptp_clock, ptp_info);
+	u64 cycles, nsec;
+
+	spin_lock_bh(&clock->lock);
+	cycles = __mlxsw_sp1_ptp_read_frc(clock, sts);
+	nsec = timecounter_cyc2time(&clock->tc, cycles);
+	spin_unlock_bh(&clock->lock);
+
+	*ts = ns_to_timespec64(nsec);
+
+	return 0;
+}
+
+static int mlxsw_sp1_ptp_settime(struct ptp_clock_info *ptp,
+				 const struct timespec64 *ts)
+{
+	struct mlxsw_sp_ptp_clock *clock =
+		container_of(ptp, struct mlxsw_sp_ptp_clock, ptp_info);
+	u64 nsec = timespec64_to_ns(ts);
+
+	spin_lock_bh(&clock->lock);
+	timecounter_init(&clock->tc, &clock->cycles, nsec);
+	nsec = timecounter_read(&clock->tc);
+	spin_unlock_bh(&clock->lock);
+
+	return mlxsw_sp1_ptp_phc_settime(clock, nsec);
+}
+
+static const struct ptp_clock_info mlxsw_sp1_ptp_clock_info = {
+	.owner		= THIS_MODULE,
+	.name		= "mlxsw_sp_clock",
+	.max_adj	= 100000000,
+	.adjfine	= mlxsw_sp1_ptp_adjfine,
+	.adjtime	= mlxsw_sp1_ptp_adjtime,
+	.gettimex64	= mlxsw_sp1_ptp_gettimex,
+	.settime64	= mlxsw_sp1_ptp_settime,
+};
+
+static void mlxsw_sp1_ptp_clock_overflow(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct mlxsw_sp_ptp_clock *clock;
+
+	clock = container_of(dwork, struct mlxsw_sp_ptp_clock, overflow_work);
+
+	spin_lock_bh(&clock->lock);
+	timecounter_read(&clock->tc);
+	spin_unlock_bh(&clock->lock);
+	mlxsw_core_schedule_dw(&clock->overflow_work, clock->overflow_period);
+}
+
+struct mlxsw_sp_ptp_clock *
+mlxsw_sp1_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev)
+{
+	u64 overflow_cycles, nsec, frac = 0;
+	struct mlxsw_sp_ptp_clock *clock;
+	int err;
+
+	clock = kzalloc(sizeof(*clock), GFP_KERNEL);
+	if (!clock)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&clock->lock);
+	clock->cycles.read = mlxsw_sp1_ptp_read_frc;
+	clock->cycles.shift = MLXSW_SP1_PTP_CLOCK_CYCLES_SHIFT;
+	clock->cycles.mult = clocksource_khz2mult(MLXSW_SP1_PTP_CLOCK_FREQ_KHZ,
+						  clock->cycles.shift);
+	clock->nominal_c_mult = clock->cycles.mult;
+	clock->cycles.mask = CLOCKSOURCE_MASK(MLXSW_SP1_PTP_CLOCK_MASK);
+	clock->core = mlxsw_sp->core;
+
+	timecounter_init(&clock->tc, &clock->cycles,
+			 ktime_to_ns(ktime_get_real()));
+
+	/* Calculate period in seconds to call the overflow watchdog - to make
+	 * sure counter is checked at least twice every wrap around.
+	 * The period is calculated as the minimum between max HW cycles count
+	 * (The clock source mask) and max amount of cycles that can be
+	 * multiplied by clock multiplier where the result doesn't exceed
+	 * 64bits.
+	 */
+	overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
+	overflow_cycles = min(overflow_cycles, div_u64(clock->cycles.mask, 3));
+
+	nsec = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles, 0, &frac);
+	clock->overflow_period = nsecs_to_jiffies(nsec);
+
+	INIT_DELAYED_WORK(&clock->overflow_work, mlxsw_sp1_ptp_clock_overflow);
+	mlxsw_core_schedule_dw(&clock->overflow_work, 0);
+
+	clock->ptp_info = mlxsw_sp1_ptp_clock_info;
+	clock->ptp = ptp_clock_register(&clock->ptp_info, dev);
+	if (IS_ERR(clock->ptp)) {
+		err = PTR_ERR(clock->ptp);
+		dev_err(dev, "ptp_clock_register failed %d\n", err);
+		goto err_ptp_clock_register;
+	}
+
+	return clock;
+
+err_ptp_clock_register:
+	cancel_delayed_work_sync(&clock->overflow_work);
+	kfree(clock);
+	return ERR_PTR(err);
+}
+
+void mlxsw_sp1_ptp_clock_fini(struct mlxsw_sp_ptp_clock *clock)
+{
+	ptp_clock_unregister(clock->ptp);
+	cancel_delayed_work_sync(&clock->overflow_work);
+	kfree(clock);
+}
+
+static int mlxsw_sp_ptp_parse(struct sk_buff *skb,
+			      u8 *p_domain_number,
+			      u8 *p_message_type,
+			      u16 *p_sequence_id)
+{
+	unsigned int offset = 0;
+	unsigned int ptp_class;
+	u8 *data;
+
+	data = skb_mac_header(skb);
+	ptp_class = ptp_classify_raw(skb);
+
+	switch (ptp_class & PTP_CLASS_VMASK) {
+	case PTP_CLASS_V1:
+	case PTP_CLASS_V2:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (ptp_class & PTP_CLASS_VLAN)
+		offset += VLAN_HLEN;
+
+	switch (ptp_class & PTP_CLASS_PMASK) {
+	case PTP_CLASS_IPV4:
+		offset += ETH_HLEN + IPV4_HLEN(data + offset) + UDP_HLEN;
+		break;
+	case PTP_CLASS_IPV6:
+		offset += ETH_HLEN + IP6_HLEN + UDP_HLEN;
+		break;
+	case PTP_CLASS_L2:
+		offset += ETH_HLEN;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	/* PTP header is 34 bytes. */
+	if (skb->len < offset + 34)
+		return -EINVAL;
+
+	*p_message_type = data[offset] & 0x0f;
+	*p_domain_number = data[offset + 4];
+	*p_sequence_id = (u16)(data[offset + 30]) << 8 | data[offset + 31];
+	return 0;
+}
+
+/* Returns NULL on successful insertion, a pointer on conflict, or an ERR_PTR on
+ * error.
+ */
+static struct mlxsw_sp1_ptp_unmatched *
+mlxsw_sp1_ptp_unmatched_save(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp1_ptp_key key,
+			     struct sk_buff *skb,
+			     u64 timestamp)
+{
+	int cycles = MLXSW_SP1_PTP_HT_GC_TIMEOUT / MLXSW_SP1_PTP_HT_GC_INTERVAL;
+	struct mlxsw_sp_ptp_state *ptp_state = mlxsw_sp->ptp_state;
+	struct mlxsw_sp1_ptp_unmatched *unmatched;
+	struct mlxsw_sp1_ptp_unmatched *conflict;
+
+	unmatched = kzalloc(sizeof(*unmatched), GFP_ATOMIC);
+	if (!unmatched)
+		return ERR_PTR(-ENOMEM);
+
+	unmatched->key = key;
+	unmatched->skb = skb;
+	unmatched->timestamp = timestamp;
+	unmatched->gc_cycle = mlxsw_sp->ptp_state->gc_cycle + cycles;
+
+	conflict = rhashtable_lookup_get_insert_fast(&ptp_state->unmatched_ht,
+					    &unmatched->ht_node,
+					    mlxsw_sp1_ptp_unmatched_ht_params);
+	if (conflict)
+		kfree(unmatched);
+
+	return conflict;
+}
+
+static struct mlxsw_sp1_ptp_unmatched *
+mlxsw_sp1_ptp_unmatched_lookup(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp1_ptp_key key)
+{
+	return rhashtable_lookup(&mlxsw_sp->ptp_state->unmatched_ht, &key,
+				 mlxsw_sp1_ptp_unmatched_ht_params);
+}
+
+static int
+mlxsw_sp1_ptp_unmatched_remove(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp1_ptp_unmatched *unmatched)
+{
+	return rhashtable_remove_fast(&mlxsw_sp->ptp_state->unmatched_ht,
+				      &unmatched->ht_node,
+				      mlxsw_sp1_ptp_unmatched_ht_params);
+}
+
+/* This function is called in the following scenarios:
+ *
+ * 1) When a packet is matched with its timestamp.
+ * 2) In several situation when it is necessary to immediately pass on
+ *    an SKB without a timestamp.
+ * 3) From GC indirectly through mlxsw_sp1_ptp_unmatched_finish().
+ *    This case is similar to 2) above.
+ */
+static void mlxsw_sp1_ptp_packet_finish(struct mlxsw_sp *mlxsw_sp,
+					struct sk_buff *skb, u8 local_port,
+					bool ingress,
+					struct skb_shared_hwtstamps *hwtstamps)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+
+	/* Between capturing the packet and finishing it, there is a window of
+	 * opportunity for the originating port to go away (e.g. due to a
+	 * split). Also make sure the SKB device reference is still valid.
+	 */
+	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	if (!(mlxsw_sp_port && (!skb->dev || skb->dev == mlxsw_sp_port->dev))) {
+		dev_kfree_skb_any(skb);
+		return;
+	}
+
+	if (ingress) {
+		if (hwtstamps)
+			*skb_hwtstamps(skb) = *hwtstamps;
+		mlxsw_sp_rx_listener_no_mark_func(skb, local_port, mlxsw_sp);
+	} else {
+		/* skb_tstamp_tx() allows hwtstamps to be NULL. */
+		skb_tstamp_tx(skb, hwtstamps);
+		dev_kfree_skb_any(skb);
+	}
+}
+
+static void mlxsw_sp1_packet_timestamp(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp1_ptp_key key,
+				       struct sk_buff *skb,
+				       u64 timestamp)
+{
+	struct skb_shared_hwtstamps hwtstamps;
+	u64 nsec;
+
+	spin_lock_bh(&mlxsw_sp->clock->lock);
+	nsec = timecounter_cyc2time(&mlxsw_sp->clock->tc, timestamp);
+	spin_unlock_bh(&mlxsw_sp->clock->lock);
+
+	hwtstamps.hwtstamp = ns_to_ktime(nsec);
+	mlxsw_sp1_ptp_packet_finish(mlxsw_sp, skb,
+				    key.local_port, key.ingress, &hwtstamps);
+}
+
+static void
+mlxsw_sp1_ptp_unmatched_finish(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp1_ptp_unmatched *unmatched)
+{
+	if (unmatched->skb && unmatched->timestamp)
+		mlxsw_sp1_packet_timestamp(mlxsw_sp, unmatched->key,
+					   unmatched->skb,
+					   unmatched->timestamp);
+	else if (unmatched->skb)
+		mlxsw_sp1_ptp_packet_finish(mlxsw_sp, unmatched->skb,
+					    unmatched->key.local_port,
+					    unmatched->key.ingress, NULL);
+	kfree_rcu(unmatched, rcu);
+}
+
+static void mlxsw_sp1_ptp_unmatched_free_fn(void *ptr, void *arg)
+{
+	struct mlxsw_sp1_ptp_unmatched *unmatched = ptr;
+
+	/* This is invoked at a point where the ports are gone already. Nothing
+	 * to do with whatever is left in the HT but to free it.
+	 */
+	if (unmatched->skb)
+		dev_kfree_skb_any(unmatched->skb);
+	kfree_rcu(unmatched, rcu);
+}
+
+static void mlxsw_sp1_ptp_got_piece(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp1_ptp_key key,
+				    struct sk_buff *skb, u64 timestamp)
+{
+	struct mlxsw_sp1_ptp_unmatched *unmatched, *conflict;
+	int err;
+
+	rcu_read_lock();
+
+	unmatched = mlxsw_sp1_ptp_unmatched_lookup(mlxsw_sp, key);
+
+	spin_lock(&mlxsw_sp->ptp_state->unmatched_lock);
+
+	if (unmatched) {
+		/* There was an unmatched entry when we looked, but it may have
+		 * been removed before we took the lock.
+		 */
+		err = mlxsw_sp1_ptp_unmatched_remove(mlxsw_sp, unmatched);
+		if (err)
+			unmatched = NULL;
+	}
+
+	if (!unmatched) {
+		/* We have no unmatched entry, but one may have been added after
+		 * we looked, but before we took the lock.
+		 */
+		unmatched = mlxsw_sp1_ptp_unmatched_save(mlxsw_sp, key,
+							 skb, timestamp);
+		if (IS_ERR(unmatched)) {
+			if (skb)
+				mlxsw_sp1_ptp_packet_finish(mlxsw_sp, skb,
+							    key.local_port,
+							    key.ingress, NULL);
+			unmatched = NULL;
+		} else if (unmatched) {
+			/* Save just told us, under lock, that the entry is
+			 * there, so this has to work.
+			 */
+			err = mlxsw_sp1_ptp_unmatched_remove(mlxsw_sp,
+							     unmatched);
+			WARN_ON_ONCE(err);
+		}
+	}
+
+	/* If unmatched is non-NULL here, it comes either from the lookup, or
+	 * from the save attempt above. In either case the entry was removed
+	 * from the hash table. If unmatched is NULL, a new unmatched entry was
+	 * added to the hash table, and there was no conflict.
+	 */
+
+	if (skb && unmatched && unmatched->timestamp) {
+		unmatched->skb = skb;
+	} else if (timestamp && unmatched && unmatched->skb) {
+		unmatched->timestamp = timestamp;
+	} else if (unmatched) {
+		/* unmatched holds an older entry of the same type: either an
+		 * skb if we are handling skb, or a timestamp if we are handling
+		 * timestamp. We can't match that up, so save what we have.
+		 */
+		conflict = mlxsw_sp1_ptp_unmatched_save(mlxsw_sp, key,
+							skb, timestamp);
+		if (IS_ERR(conflict)) {
+			if (skb)
+				mlxsw_sp1_ptp_packet_finish(mlxsw_sp, skb,
+							    key.local_port,
+							    key.ingress, NULL);
+		} else {
+			/* Above, we removed an object with this key from the
+			 * hash table, under lock, so conflict can not be a
+			 * valid pointer.
+			 */
+			WARN_ON_ONCE(conflict);
+		}
+	}
+
+	spin_unlock(&mlxsw_sp->ptp_state->unmatched_lock);
+
+	if (unmatched)
+		mlxsw_sp1_ptp_unmatched_finish(mlxsw_sp, unmatched);
+
+	rcu_read_unlock();
+}
+
+static void mlxsw_sp1_ptp_got_packet(struct mlxsw_sp *mlxsw_sp,
+				     struct sk_buff *skb, u8 local_port,
+				     bool ingress)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct mlxsw_sp1_ptp_key key;
+	u8 types;
+	int err;
+
+	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	if (!mlxsw_sp_port)
+		goto immediate;
+
+	types = ingress ? mlxsw_sp_port->ptp.ing_types :
+			  mlxsw_sp_port->ptp.egr_types;
+	if (!types)
+		goto immediate;
+
+	memset(&key, 0, sizeof(key));
+	key.local_port = local_port;
+	key.ingress = ingress;
+
+	err = mlxsw_sp_ptp_parse(skb, &key.domain_number, &key.message_type,
+				 &key.sequence_id);
+	if (err)
+		goto immediate;
+
+	/* For packets whose timestamping was not enabled on this port, don't
+	 * bother trying to match the timestamp.
+	 */
+	if (!((1 << key.message_type) & types))
+		goto immediate;
+
+	mlxsw_sp1_ptp_got_piece(mlxsw_sp, key, skb, 0);
+	return;
+
+immediate:
+	mlxsw_sp1_ptp_packet_finish(mlxsw_sp, skb, local_port, ingress, NULL);
+}
+
+void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
+				 u8 local_port, u8 message_type,
+				 u8 domain_number, u16 sequence_id,
+				 u64 timestamp)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	struct mlxsw_sp1_ptp_key key;
+	u8 types;
+
+	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	if (!mlxsw_sp_port)
+		return;
+
+	types = ingress ? mlxsw_sp_port->ptp.ing_types :
+			  mlxsw_sp_port->ptp.egr_types;
+
+	/* For message types whose timestamping was not enabled on this port,
+	 * don't bother with the timestamp.
+	 */
+	if (!((1 << message_type) & types))
+		return;
+
+	memset(&key, 0, sizeof(key));
+	key.local_port = local_port;
+	key.domain_number = domain_number;
+	key.message_type = message_type;
+	key.sequence_id = sequence_id;
+	key.ingress = ingress;
+
+	mlxsw_sp1_ptp_got_piece(mlxsw_sp, key, NULL, timestamp);
+}
+
+void mlxsw_sp1_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			   u8 local_port)
+{
+	skb_reset_mac_header(skb);
+	mlxsw_sp1_ptp_got_packet(mlxsw_sp, skb, local_port, true);
+}
+
+void mlxsw_sp1_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
+			       struct sk_buff *skb, u8 local_port)
+{
+	mlxsw_sp1_ptp_got_packet(mlxsw_sp, skb, local_port, false);
+}
+
+static void
+mlxsw_sp1_ptp_ht_gc_collect(struct mlxsw_sp_ptp_state *ptp_state,
+			    struct mlxsw_sp1_ptp_unmatched *unmatched)
+{
+	int err;
+
+	/* If an unmatched entry has an SKB, it has to be handed over to the
+	 * networking stack. This is usually done from a trap handler, which is
+	 * invoked in a softirq context. Here we are going to do it in process
+	 * context. If that were to be interrupted by a softirq, it could cause
+	 * a deadlock when an attempt is made to take an already-taken lock
+	 * somewhere along the sending path. Disable softirqs to prevent this.
+	 */
+	local_bh_disable();
+
+	spin_lock(&ptp_state->unmatched_lock);
+	err = rhashtable_remove_fast(&ptp_state->unmatched_ht,
+				     &unmatched->ht_node,
+				     mlxsw_sp1_ptp_unmatched_ht_params);
+	spin_unlock(&ptp_state->unmatched_lock);
+
+	if (err)
+		/* The packet was matched with timestamp during the walk. */
+		goto out;
+
+	/* mlxsw_sp1_ptp_unmatched_finish() invokes netif_receive_skb(). While
+	 * the comment at that function states that it can only be called in
+	 * soft IRQ context, this pattern of local_bh_disable() +
+	 * netif_receive_skb(), in process context, is seen elsewhere in the
+	 * kernel, notably in pktgen.
+	 */
+	mlxsw_sp1_ptp_unmatched_finish(ptp_state->mlxsw_sp, unmatched);
+
+out:
+	local_bh_enable();
+}
+
+static void mlxsw_sp1_ptp_ht_gc(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct mlxsw_sp1_ptp_unmatched *unmatched;
+	struct mlxsw_sp_ptp_state *ptp_state;
+	struct rhashtable_iter iter;
+	u32 gc_cycle;
+	void *obj;
+
+	ptp_state = container_of(dwork, struct mlxsw_sp_ptp_state, ht_gc_dw);
+	gc_cycle = ptp_state->gc_cycle++;
+
+	rhashtable_walk_enter(&ptp_state->unmatched_ht, &iter);
+	rhashtable_walk_start(&iter);
+	while ((obj = rhashtable_walk_next(&iter))) {
+		if (IS_ERR(obj))
+			continue;
+
+		unmatched = obj;
+		if (unmatched->gc_cycle <= gc_cycle)
+			mlxsw_sp1_ptp_ht_gc_collect(ptp_state, unmatched);
+	}
+	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
+
+	mlxsw_core_schedule_dw(&ptp_state->ht_gc_dw,
+			       MLXSW_SP1_PTP_HT_GC_INTERVAL);
+}
+
+static int mlxsw_sp_ptp_mtptpt_set(struct mlxsw_sp *mlxsw_sp,
+				   enum mlxsw_reg_mtptpt_trap_id trap_id,
+				   u16 message_type)
+{
+	char mtptpt_pl[MLXSW_REG_MTPTPT_LEN];
+
+	mlxsw_reg_mtptptp_pack(mtptpt_pl, trap_id, message_type);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mtptpt), mtptpt_pl);
+}
+
+static int mlxsw_sp1_ptp_set_fifo_clr_on_trap(struct mlxsw_sp *mlxsw_sp,
+					      bool clr)
+{
+	char mogcr_pl[MLXSW_REG_MOGCR_LEN] = {0};
+	int err;
+
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mogcr), mogcr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mogcr_ptp_iftc_set(mogcr_pl, clr);
+	mlxsw_reg_mogcr_ptp_eftc_set(mogcr_pl, clr);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mogcr), mogcr_pl);
+}
+
+static int mlxsw_sp1_ptp_mtpppc_set(struct mlxsw_sp *mlxsw_sp,
+				    u16 ing_types, u16 egr_types)
+{
+	char mtpppc_pl[MLXSW_REG_MTPPPC_LEN];
+
+	mlxsw_reg_mtpppc_pack(mtpppc_pl, ing_types, egr_types);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mtpppc), mtpppc_pl);
+}
+
+struct mlxsw_sp1_ptp_shaper_params {
+	u32 ethtool_speed;
+	enum mlxsw_reg_qpsc_port_speed port_speed;
+	u8 shaper_time_exp;
+	u8 shaper_time_mantissa;
+	u8 shaper_inc;
+	u8 shaper_bs;
+	u8 port_to_shaper_credits;
+	int ing_timestamp_inc;
+	int egr_timestamp_inc;
+};
+
+static const struct mlxsw_sp1_ptp_shaper_params
+mlxsw_sp1_ptp_shaper_params[] = {
+	{
+		.ethtool_speed		= SPEED_100,
+		.port_speed		= MLXSW_REG_QPSC_PORT_SPEED_100M,
+		.shaper_time_exp	= 4,
+		.shaper_time_mantissa	= 12,
+		.shaper_inc		= 9,
+		.shaper_bs		= 1,
+		.port_to_shaper_credits	= 1,
+		.ing_timestamp_inc	= -313,
+		.egr_timestamp_inc	= 313,
+	},
+	{
+		.ethtool_speed		= SPEED_1000,
+		.port_speed		= MLXSW_REG_QPSC_PORT_SPEED_1G,
+		.shaper_time_exp	= 0,
+		.shaper_time_mantissa	= 12,
+		.shaper_inc		= 6,
+		.shaper_bs		= 0,
+		.port_to_shaper_credits	= 1,
+		.ing_timestamp_inc	= -35,
+		.egr_timestamp_inc	= 35,
+	},
+	{
+		.ethtool_speed		= SPEED_10000,
+		.port_speed		= MLXSW_REG_QPSC_PORT_SPEED_10G,
+		.shaper_time_exp	= 0,
+		.shaper_time_mantissa	= 2,
+		.shaper_inc		= 14,
+		.shaper_bs		= 1,
+		.port_to_shaper_credits	= 1,
+		.ing_timestamp_inc	= -11,
+		.egr_timestamp_inc	= 11,
+	},
+	{
+		.ethtool_speed		= SPEED_25000,
+		.port_speed		= MLXSW_REG_QPSC_PORT_SPEED_25G,
+		.shaper_time_exp	= 0,
+		.shaper_time_mantissa	= 0,
+		.shaper_inc		= 11,
+		.shaper_bs		= 1,
+		.port_to_shaper_credits	= 1,
+		.ing_timestamp_inc	= -14,
+		.egr_timestamp_inc	= 14,
+	},
+};
+
+#define MLXSW_SP1_PTP_SHAPER_PARAMS_LEN ARRAY_SIZE(mlxsw_sp1_ptp_shaper_params)
+
+static int mlxsw_sp1_ptp_shaper_params_set(struct mlxsw_sp *mlxsw_sp)
+{
+	const struct mlxsw_sp1_ptp_shaper_params *params;
+	char qpsc_pl[MLXSW_REG_QPSC_LEN];
+	int i, err;
+
+	for (i = 0; i < MLXSW_SP1_PTP_SHAPER_PARAMS_LEN; i++) {
+		params = &mlxsw_sp1_ptp_shaper_params[i];
+		mlxsw_reg_qpsc_pack(qpsc_pl, params->port_speed,
+				    params->shaper_time_exp,
+				    params->shaper_time_mantissa,
+				    params->shaper_inc, params->shaper_bs,
+				    params->port_to_shaper_credits,
+				    params->ing_timestamp_inc,
+				    params->egr_timestamp_inc);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpsc), qpsc_pl);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+struct mlxsw_sp_ptp_state *mlxsw_sp1_ptp_init(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_ptp_state *ptp_state;
+	u16 message_type;
+	int err;
+
+	err = mlxsw_sp1_ptp_shaper_params_set(mlxsw_sp);
+	if (err)
+		return ERR_PTR(err);
+
+	ptp_state = kzalloc(sizeof(*ptp_state), GFP_KERNEL);
+	if (!ptp_state)
+		return ERR_PTR(-ENOMEM);
+	ptp_state->mlxsw_sp = mlxsw_sp;
+
+	spin_lock_init(&ptp_state->unmatched_lock);
+
+	err = rhashtable_init(&ptp_state->unmatched_ht,
+			      &mlxsw_sp1_ptp_unmatched_ht_params);
+	if (err)
+		goto err_hashtable_init;
+
+	/* Delive these message types as PTP0. */
+	message_type = BIT(MLXSW_SP_PTP_MESSAGE_TYPE_SYNC) |
+		       BIT(MLXSW_SP_PTP_MESSAGE_TYPE_DELAY_REQ) |
+		       BIT(MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_REQ) |
+		       BIT(MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_RESP);
+	err = mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP0,
+				      message_type);
+	if (err)
+		goto err_mtptpt_set;
+
+	/* Everything else is PTP1. */
+	message_type = ~message_type;
+	err = mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP1,
+				      message_type);
+	if (err)
+		goto err_mtptpt1_set;
+
+	err = mlxsw_sp1_ptp_set_fifo_clr_on_trap(mlxsw_sp, true);
+	if (err)
+		goto err_fifo_clr;
+
+	INIT_DELAYED_WORK(&ptp_state->ht_gc_dw, mlxsw_sp1_ptp_ht_gc);
+	mlxsw_core_schedule_dw(&ptp_state->ht_gc_dw,
+			       MLXSW_SP1_PTP_HT_GC_INTERVAL);
+	return ptp_state;
+
+err_fifo_clr:
+	mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP1, 0);
+err_mtptpt1_set:
+	mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP0, 0);
+err_mtptpt_set:
+	rhashtable_destroy(&ptp_state->unmatched_ht);
+err_hashtable_init:
+	kfree(ptp_state);
+	return ERR_PTR(err);
+}
+
+void mlxsw_sp1_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state)
+{
+	struct mlxsw_sp *mlxsw_sp = ptp_state->mlxsw_sp;
+
+	cancel_delayed_work_sync(&ptp_state->ht_gc_dw);
+	mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp, 0, 0);
+	mlxsw_sp1_ptp_set_fifo_clr_on_trap(mlxsw_sp, false);
+	mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP1, 0);
+	mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP0, 0);
+	rhashtable_free_and_destroy(&ptp_state->unmatched_ht,
+				    &mlxsw_sp1_ptp_unmatched_free_fn, NULL);
+	kfree(ptp_state);
+}
+
+int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
+			       struct hwtstamp_config *config)
+{
+	*config = mlxsw_sp_port->ptp.hwtstamp_config;
+	return 0;
+}
+
+static int mlxsw_sp_ptp_get_message_types(const struct hwtstamp_config *config,
+					  u16 *p_ing_types, u16 *p_egr_types,
+					  enum hwtstamp_rx_filters *p_rx_filter)
+{
+	enum hwtstamp_rx_filters rx_filter = config->rx_filter;
+	enum hwtstamp_tx_types tx_type = config->tx_type;
+	u16 ing_types = 0x00;
+	u16 egr_types = 0x00;
+
+	switch (tx_type) {
+	case HWTSTAMP_TX_OFF:
+		egr_types = 0x00;
+		break;
+	case HWTSTAMP_TX_ON:
+		egr_types = 0xff;
+		break;
+	case HWTSTAMP_TX_ONESTEP_SYNC:
+		return -ERANGE;
+	}
+
+	switch (rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		ing_types = 0x00;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+		ing_types = 0x01;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		ing_types = 0x02;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+		ing_types = 0x0f;
+		break;
+	case HWTSTAMP_FILTER_ALL:
+		ing_types = 0xff;
+		break;
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_NTP_ALL:
+		return -ERANGE;
+	}
+
+	*p_ing_types = ing_types;
+	*p_egr_types = egr_types;
+	*p_rx_filter = rx_filter;
+	return 0;
+}
+
+static int mlxsw_sp1_ptp_mtpppc_update(struct mlxsw_sp_port *mlxsw_sp_port,
+				       u16 ing_types, u16 egr_types)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_port *tmp;
+	int i;
+
+	/* MTPPPC configures timestamping globally, not per port. Find the
+	 * configuration that contains all configured timestamping requests.
+	 */
+	for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) {
+		tmp = mlxsw_sp->ports[i];
+		if (tmp && tmp != mlxsw_sp_port) {
+			ing_types |= tmp->ptp.ing_types;
+			egr_types |= tmp->ptp.egr_types;
+		}
+	}
+
+	return mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp_port->mlxsw_sp,
+				       ing_types, egr_types);
+}
+
+static bool mlxsw_sp1_ptp_hwtstamp_enabled(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	return mlxsw_sp_port->ptp.ing_types || mlxsw_sp_port->ptp.egr_types;
+}
+
+static int
+mlxsw_sp1_ptp_port_shaper_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qeec_pl[MLXSW_REG_QEEC_LEN];
+
+	mlxsw_reg_qeec_ptps_pack(qeec_pl, mlxsw_sp_port->local_port, enable);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl);
+}
+
+static int mlxsw_sp1_ptp_port_shaper_check(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	const struct mlxsw_sp_port_type_speed_ops *port_type_speed_ops;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char ptys_pl[MLXSW_REG_PTYS_LEN];
+	u32 eth_proto_oper, speed;
+	bool ptps = false;
+	int err, i;
+
+	if (!mlxsw_sp1_ptp_hwtstamp_enabled(mlxsw_sp_port))
+		return mlxsw_sp1_ptp_port_shaper_set(mlxsw_sp_port, false);
+
+	port_type_speed_ops = mlxsw_sp->port_type_speed_ops;
+	port_type_speed_ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl,
+					       mlxsw_sp_port->local_port, 0,
+					       false);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
+	if (err)
+		return err;
+	port_type_speed_ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, NULL, NULL,
+						 &eth_proto_oper);
+
+	speed = port_type_speed_ops->from_ptys_speed(mlxsw_sp, eth_proto_oper);
+	for (i = 0; i < MLXSW_SP1_PTP_SHAPER_PARAMS_LEN; i++) {
+		if (mlxsw_sp1_ptp_shaper_params[i].ethtool_speed == speed) {
+			ptps = true;
+			break;
+		}
+	}
+
+	return mlxsw_sp1_ptp_port_shaper_set(mlxsw_sp_port, ptps);
+}
+
+void mlxsw_sp1_ptp_shaper_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	int err;
+
+	mlxsw_sp_port = container_of(dwork, struct mlxsw_sp_port,
+				     ptp.shaper_dw);
+
+	if (!mlxsw_sp1_ptp_hwtstamp_enabled(mlxsw_sp_port))
+		return;
+
+	err = mlxsw_sp1_ptp_port_shaper_check(mlxsw_sp_port);
+	if (err)
+		netdev_err(mlxsw_sp_port->dev, "Failed to set up PTP shaper\n");
+}
+
+int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			       struct hwtstamp_config *config)
+{
+	enum hwtstamp_rx_filters rx_filter;
+	u16 ing_types;
+	u16 egr_types;
+	int err;
+
+	err = mlxsw_sp_ptp_get_message_types(config, &ing_types, &egr_types,
+					     &rx_filter);
+	if (err)
+		return err;
+
+	err = mlxsw_sp1_ptp_mtpppc_update(mlxsw_sp_port, ing_types, egr_types);
+	if (err)
+		return err;
+
+	mlxsw_sp_port->ptp.hwtstamp_config = *config;
+	mlxsw_sp_port->ptp.ing_types = ing_types;
+	mlxsw_sp_port->ptp.egr_types = egr_types;
+
+	err = mlxsw_sp1_ptp_port_shaper_check(mlxsw_sp_port);
+	if (err)
+		return err;
+
+	/* Notify the ioctl caller what we are actually timestamping. */
+	config->rx_filter = rx_filter;
+
+	return 0;
+}
+
+int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
+			      struct ethtool_ts_info *info)
+{
+	info->phc_index = ptp_clock_index(mlxsw_sp->clock->ptp);
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
+			 BIT(HWTSTAMP_TX_ON);
+
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_ALL);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
new file mode 100644
index 000000000000..72e55f6926b9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */
+
+#ifndef _MLXSW_SPECTRUM_PTP_H
+#define _MLXSW_SPECTRUM_PTP_H
+
+#include <linux/device.h>
+#include <linux/rhashtable.h>
+
+struct mlxsw_sp;
+struct mlxsw_sp_port;
+struct mlxsw_sp_ptp_clock;
+
+enum {
+	MLXSW_SP_PTP_MESSAGE_TYPE_SYNC,
+	MLXSW_SP_PTP_MESSAGE_TYPE_DELAY_REQ,
+	MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_REQ,
+	MLXSW_SP_PTP_MESSAGE_TYPE_PDELAY_RESP,
+};
+
+static inline int mlxsw_sp_ptp_get_ts_info_noptp(struct ethtool_ts_info *info)
+{
+	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
+				SOF_TIMESTAMPING_SOFTWARE;
+	info->phc_index = -1;
+	return 0;
+}
+
+#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
+
+struct mlxsw_sp_ptp_clock *
+mlxsw_sp1_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev);
+
+void mlxsw_sp1_ptp_clock_fini(struct mlxsw_sp_ptp_clock *clock);
+
+struct mlxsw_sp_ptp_state *mlxsw_sp1_ptp_init(struct mlxsw_sp *mlxsw_sp);
+
+void mlxsw_sp1_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state);
+
+void mlxsw_sp1_ptp_receive(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb,
+			   u8 local_port);
+
+void mlxsw_sp1_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
+			       struct sk_buff *skb, u8 local_port);
+
+void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
+				 u8 local_port, u8 message_type,
+				 u8 domain_number, u16 sequence_id,
+				 u64 timestamp);
+
+int mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
+			       struct hwtstamp_config *config);
+
+int mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			       struct hwtstamp_config *config);
+
+void mlxsw_sp1_ptp_shaper_work(struct work_struct *work);
+
+int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
+			      struct ethtool_ts_info *info);
+
+#else
+
+static inline struct mlxsw_sp_ptp_clock *
+mlxsw_sp1_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev)
+{
+	return NULL;
+}
+
+static inline void mlxsw_sp1_ptp_clock_fini(struct mlxsw_sp_ptp_clock *clock)
+{
+}
+
+static inline struct mlxsw_sp_ptp_state *
+mlxsw_sp1_ptp_init(struct mlxsw_sp *mlxsw_sp)
+{
+	return NULL;
+}
+
+static inline void mlxsw_sp1_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state)
+{
+}
+
+static inline void mlxsw_sp1_ptp_receive(struct mlxsw_sp *mlxsw_sp,
+					 struct sk_buff *skb, u8 local_port)
+{
+	mlxsw_sp_rx_listener_no_mark_func(skb, local_port, mlxsw_sp);
+}
+
+static inline void mlxsw_sp1_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
+					     struct sk_buff *skb, u8 local_port)
+{
+	dev_kfree_skb_any(skb);
+}
+
+static inline void
+mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress,
+			    u8 local_port, u8 message_type,
+			    u8 domain_number,
+			    u16 sequence_id, u64 timestamp)
+{
+}
+
+static inline int
+mlxsw_sp1_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+mlxsw_sp1_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void mlxsw_sp1_ptp_shaper_work(struct work_struct *work)
+{
+}
+
+static inline int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
+					    struct ethtool_ts_info *info)
+{
+	return mlxsw_sp_ptp_get_ts_info_noptp(info);
+}
+
+#endif
+
+static inline struct mlxsw_sp_ptp_clock *
+mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev)
+{
+	return NULL;
+}
+
+static inline void mlxsw_sp2_ptp_clock_fini(struct mlxsw_sp_ptp_clock *clock)
+{
+}
+
+static inline struct mlxsw_sp_ptp_state *
+mlxsw_sp2_ptp_init(struct mlxsw_sp *mlxsw_sp)
+{
+	return NULL;
+}
+
+static inline void mlxsw_sp2_ptp_fini(struct mlxsw_sp_ptp_state *ptp_state)
+{
+}
+
+static inline void mlxsw_sp2_ptp_receive(struct mlxsw_sp *mlxsw_sp,
+					 struct sk_buff *skb, u8 local_port)
+{
+	mlxsw_sp_rx_listener_no_mark_func(skb, local_port, mlxsw_sp);
+}
+
+static inline void mlxsw_sp2_ptp_transmitted(struct mlxsw_sp *mlxsw_sp,
+					     struct sk_buff *skb, u8 local_port)
+{
+	dev_kfree_skb_any(skb);
+}
+
+static inline int
+mlxsw_sp2_ptp_hwtstamp_get(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void mlxsw_sp2_ptp_shaper_work(struct work_struct *work)
+{
+}
+
+static inline int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
+					    struct ethtool_ts_info *info)
+{
+	return mlxsw_sp_ptp_get_ts_info_noptp(info);
+}
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 98e5ffd71b91..e618be7ce6c6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -13,14 +13,15 @@
 #include <linux/socket.h>
 #include <linux/route.h>
 #include <linux/gcd.h>
-#include <linux/random.h>
 #include <linux/if_macvlan.h>
 #include <linux/refcount.h>
+#include <linux/jhash.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
 #include <net/ip_fib.h>
 #include <net/ip6_fib.h>
+#include <net/nexthop.h>
 #include <net/fib_rules.h>
 #include <net/ip_tunnels.h>
 #include <net/l3mdev.h>
@@ -80,7 +81,7 @@ struct mlxsw_sp_router {
 struct mlxsw_sp_rif {
 	struct list_head nexthop_list;
 	struct list_head neigh_list;
-	struct net_device *dev;
+	struct net_device *dev; /* NULL for underlay RIF */
 	struct mlxsw_sp_fid *fid;
 	unsigned char addr[ETH_ALEN];
 	int mtu;
@@ -120,6 +121,7 @@ struct mlxsw_sp_rif_ipip_lb {
 	struct mlxsw_sp_rif common;
 	struct mlxsw_sp_rif_ipip_lb_config lb_config;
 	u16 ul_vr_id; /* Reserved for Spectrum-2. */
+	u16 ul_rif_id; /* Reserved for Spectrum. */
 };
 
 struct mlxsw_sp_rif_params_ipip_lb {
@@ -363,6 +365,7 @@ enum mlxsw_sp_fib_entry_type {
 	MLXSW_SP_FIB_ENTRY_TYPE_REMOTE,
 	MLXSW_SP_FIB_ENTRY_TYPE_LOCAL,
 	MLXSW_SP_FIB_ENTRY_TYPE_TRAP,
+	MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE,
 
 	/* This is a special case of local delivery, where a packet should be
 	 * decapsulated on reception. Note that there is no corresponding ENCAP,
@@ -440,6 +443,8 @@ struct mlxsw_sp_vr {
 	struct mlxsw_sp_fib *fib4;
 	struct mlxsw_sp_fib *fib6;
 	struct mlxsw_sp_mr_table *mr_table[MLXSW_SP_L3_PROTO_MAX];
+	struct mlxsw_sp_rif *ul_rif;
+	refcount_t ul_rif_refcnt;
 };
 
 static const struct rhashtable_params mlxsw_sp_fib_ht_params;
@@ -1437,8 +1442,8 @@ mlxsw_sp_ipip_entry_ol_up_event(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int
-mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif,
-			struct mlxsw_sp_vr *ul_vr, bool enable)
+mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, u16 ul_vr_id,
+			u16 ul_rif_id, bool enable)
 {
 	struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config;
 	struct mlxsw_sp_rif *rif = &lb_rif->common;
@@ -1453,7 +1458,7 @@ mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif,
 				    rif->rif_index, rif->vr_id, rif->dev->mtu);
 		mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt,
 			    MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET,
-			    ul_vr->id, saddr4, lb_cf.okey);
+			    ul_vr_id, ul_rif_id, saddr4, lb_cf.okey);
 		break;
 
 	case MLXSW_SP_L3_PROTO_IPV6:
@@ -1468,14 +1473,13 @@ static int mlxsw_sp_netdevice_ipip_ol_update_mtu(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_ipip_entry *ipip_entry;
 	struct mlxsw_sp_rif_ipip_lb *lb_rif;
-	struct mlxsw_sp_vr *ul_vr;
 	int err = 0;
 
 	ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
 	if (ipip_entry) {
 		lb_rif = ipip_entry->ol_lb;
-		ul_vr = &mlxsw_sp->router->vrs[lb_rif->ul_vr_id];
-		err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, true);
+		err = mlxsw_sp_rif_ipip_lb_op(lb_rif, lb_rif->ul_vr_id,
+					      lb_rif->ul_rif_id, true);
 		if (err)
 			goto out;
 		lb_rif->common.mtu = ol_dev->mtu;
@@ -2360,7 +2364,7 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work)
 static void
 mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_neigh_entry *neigh_entry,
-			      bool removing);
+			      bool removing, bool dead);
 
 static enum mlxsw_reg_rauht_op mlxsw_sp_rauht_op(bool adding)
 {
@@ -2368,7 +2372,7 @@ static enum mlxsw_reg_rauht_op mlxsw_sp_rauht_op(bool adding)
 			MLXSW_REG_RAUHT_OP_WRITE_DELETE;
 }
 
-static void
+static int
 mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_neigh_entry *neigh_entry,
 				enum mlxsw_reg_rauht_op op)
@@ -2382,10 +2386,10 @@ mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp,
 	if (neigh_entry->counter_valid)
 		mlxsw_reg_rauht_pack_counter(rauht_pl,
 					     neigh_entry->counter_index);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
 }
 
-static void
+static int
 mlxsw_sp_router_neigh_entry_op6(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_neigh_entry *neigh_entry,
 				enum mlxsw_reg_rauht_op op)
@@ -2399,7 +2403,7 @@ mlxsw_sp_router_neigh_entry_op6(struct mlxsw_sp *mlxsw_sp,
 	if (neigh_entry->counter_valid)
 		mlxsw_reg_rauht_pack_counter(rauht_pl,
 					     neigh_entry->counter_index);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
 }
 
 bool mlxsw_sp_neigh_ipv6_ignore(struct mlxsw_sp_neigh_entry *neigh_entry)
@@ -2421,20 +2425,33 @@ mlxsw_sp_neigh_entry_update(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_neigh_entry *neigh_entry,
 			    bool adding)
 {
+	enum mlxsw_reg_rauht_op op = mlxsw_sp_rauht_op(adding);
+	int err;
+
 	if (!adding && !neigh_entry->connected)
 		return;
 	neigh_entry->connected = adding;
 	if (neigh_entry->key.n->tbl->family == AF_INET) {
-		mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry,
-						mlxsw_sp_rauht_op(adding));
+		err = mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry,
+						      op);
+		if (err)
+			return;
 	} else if (neigh_entry->key.n->tbl->family == AF_INET6) {
 		if (mlxsw_sp_neigh_ipv6_ignore(neigh_entry))
 			return;
-		mlxsw_sp_router_neigh_entry_op6(mlxsw_sp, neigh_entry,
-						mlxsw_sp_rauht_op(adding));
+		err = mlxsw_sp_router_neigh_entry_op6(mlxsw_sp, neigh_entry,
+						      op);
+		if (err)
+			return;
 	} else {
 		WARN_ON_ONCE(1);
+		return;
 	}
+
+	if (adding)
+		neigh_entry->key.n->flags |= NTF_OFFLOADED;
+	else
+		neigh_entry->key.n->flags &= ~NTF_OFFLOADED;
 }
 
 void
@@ -2491,7 +2508,8 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work)
 
 	memcpy(neigh_entry->ha, ha, ETH_ALEN);
 	mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, entry_connected);
-	mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected);
+	mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected,
+				      dead);
 
 	if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list))
 		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
@@ -2870,12 +2888,13 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp,
 		return false;
 
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
+		struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
 		struct in6_addr *gw;
 		int ifindex, weight;
 
-		ifindex = mlxsw_sp_rt6->rt->fib6_nh.nh_dev->ifindex;
-		weight = mlxsw_sp_rt6->rt->fib6_nh.nh_weight;
-		gw = &mlxsw_sp_rt6->rt->fib6_nh.nh_gw;
+		ifindex = fib6_nh->fib_nh_dev->ifindex;
+		weight = fib6_nh->fib_nh_weight;
+		gw = &fib6_nh->fib_nh_gw6;
 		if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex,
 							 weight))
 			return false;
@@ -2941,7 +2960,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed)
 	struct net_device *dev;
 
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
-		dev = mlxsw_sp_rt6->rt->fib6_nh.nh_dev;
+		dev = mlxsw_sp_rt6->rt->fib6_nh->fib_nh_dev;
 		val ^= dev->ifindex;
 	}
 
@@ -3455,13 +3474,79 @@ static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
 	nh->update = 1;
 }
 
+static int
+mlxsw_sp_nexthop_dead_neigh_replace(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_neigh_entry *neigh_entry)
+{
+	struct neighbour *n, *old_n = neigh_entry->key.n;
+	struct mlxsw_sp_nexthop *nh;
+	bool entry_connected;
+	u8 nud_state, dead;
+	int err;
+
+	nh = list_first_entry(&neigh_entry->nexthop_list,
+			      struct mlxsw_sp_nexthop, neigh_list_node);
+
+	n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev);
+	if (!n) {
+		n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr,
+				 nh->rif->dev);
+		if (IS_ERR(n))
+			return PTR_ERR(n);
+		neigh_event_send(n, NULL);
+	}
+
+	mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry);
+	neigh_entry->key.n = n;
+	err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
+	if (err)
+		goto err_neigh_entry_insert;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	dead = n->dead;
+	read_unlock_bh(&n->lock);
+	entry_connected = nud_state & NUD_VALID && !dead;
+
+	list_for_each_entry(nh, &neigh_entry->nexthop_list,
+			    neigh_list_node) {
+		neigh_release(old_n);
+		neigh_clone(n);
+		__mlxsw_sp_nexthop_neigh_update(nh, !entry_connected);
+		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
+	}
+
+	neigh_release(n);
+
+	return 0;
+
+err_neigh_entry_insert:
+	neigh_entry->key.n = old_n;
+	mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
+	neigh_release(n);
+	return err;
+}
+
 static void
 mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_neigh_entry *neigh_entry,
-			      bool removing)
+			      bool removing, bool dead)
 {
 	struct mlxsw_sp_nexthop *nh;
 
+	if (list_empty(&neigh_entry->nexthop_list))
+		return;
+
+	if (dead) {
+		int err;
+
+		err = mlxsw_sp_nexthop_dead_neigh_replace(mlxsw_sp,
+							  neigh_entry);
+		if (err)
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to replace dead neigh\n");
+		return;
+	}
+
 	list_for_each_entry(nh, &neigh_entry->nexthop_list,
 			    neigh_list_node) {
 		__mlxsw_sp_nexthop_neigh_update(nh, removing);
@@ -3607,7 +3692,7 @@ static bool mlxsw_sp_nexthop4_ipip_type(const struct mlxsw_sp *mlxsw_sp,
 					const struct fib_nh *fib_nh,
 					enum mlxsw_sp_ipip_type *p_ipipt)
 {
-	struct net_device *dev = fib_nh->nh_dev;
+	struct net_device *dev = fib_nh->fib_nh_dev;
 
 	return dev &&
 	       fib_nh->nh_parent->fib_type == RTN_UNICAST &&
@@ -3634,7 +3719,7 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp,
 				       struct fib_nh *fib_nh)
 {
 	const struct mlxsw_sp_ipip_ops *ipip_ops;
-	struct net_device *dev = fib_nh->nh_dev;
+	struct net_device *dev = fib_nh->fib_nh_dev;
 	struct mlxsw_sp_ipip_entry *ipip_entry;
 	struct mlxsw_sp_rif *rif;
 	int err;
@@ -3678,18 +3763,18 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_nexthop *nh,
 				  struct fib_nh *fib_nh)
 {
-	struct net_device *dev = fib_nh->nh_dev;
+	struct net_device *dev = fib_nh->fib_nh_dev;
 	struct in_device *in_dev;
 	int err;
 
 	nh->nh_grp = nh_grp;
 	nh->key.fib_nh = fib_nh;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	nh->nh_weight = fib_nh->nh_weight;
+	nh->nh_weight = fib_nh->fib_nh_weight;
 #else
 	nh->nh_weight = 1;
 #endif
-	memcpy(&nh->gw_addr, &fib_nh->nh_gw, sizeof(fib_nh->nh_gw));
+	memcpy(&nh->gw_addr, &fib_nh->fib_nh_gw4, sizeof(fib_nh->fib_nh_gw4));
 	err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh);
 	if (err)
 		return err;
@@ -3702,7 +3787,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
 
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-	    fib_nh->nh_flags & RTNH_F_LINKDOWN)
+	    fib_nh->fib_nh_flags & RTNH_F_LINKDOWN)
 		return 0;
 
 	err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh);
@@ -3799,25 +3884,25 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
 }
 
 static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,
-				   const struct fib_info *fi)
+				   struct fib_info *fi)
 {
-	return fi->fib_nh->nh_scope == RT_SCOPE_LINK ||
-	       mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, fi->fib_nh, NULL);
+	const struct fib_nh *nh = fib_info_nh(fi, 0);
+
+	return nh->fib_nh_scope == RT_SCOPE_LINK ||
+	       mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, nh, NULL);
 }
 
 static struct mlxsw_sp_nexthop_group *
 mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
 {
+	unsigned int nhs = fib_info_num_path(fi);
 	struct mlxsw_sp_nexthop_group *nh_grp;
 	struct mlxsw_sp_nexthop *nh;
 	struct fib_nh *fib_nh;
-	size_t alloc_size;
 	int i;
 	int err;
 
-	alloc_size = sizeof(*nh_grp) +
-		     fi->fib_nhs * sizeof(struct mlxsw_sp_nexthop);
-	nh_grp = kzalloc(alloc_size, GFP_KERNEL);
+	nh_grp = kzalloc(struct_size(nh_grp, nexthops, nhs), GFP_KERNEL);
 	if (!nh_grp)
 		return ERR_PTR(-ENOMEM);
 	nh_grp->priv = fi;
@@ -3825,11 +3910,11 @@ mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
 	nh_grp->neigh_tbl = &arp_tbl;
 
 	nh_grp->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, fi);
-	nh_grp->count = fi->fib_nhs;
+	nh_grp->count = nhs;
 	fib_info_hold(fi);
 	for (i = 0; i < nh_grp->count; i++) {
 		nh = &nh_grp->nexthops[i];
-		fib_nh = &fi->fib_nh[i];
+		fib_nh = fib_info_nh(fi, i);
 		err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh);
 		if (err)
 			goto err_nexthop4_init;
@@ -3926,6 +4011,7 @@ mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry)
 		return !!nh_group->adj_index_valid;
 	case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL:
 		return !!nh_group->nh_rif;
+	case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE:
 	case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP:
 	case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP:
 		return true;
@@ -3944,9 +4030,9 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 		struct fib6_info *rt = mlxsw_sp_rt6->rt;
 
-		if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev &&
+		if (nh->rif && nh->rif->dev == rt->fib6_nh->fib_nh_dev &&
 		    ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr,
-				    &rt->fib6_nh.nh_gw))
+				    &rt->fib6_nh->fib_nh_gw6))
 			return nh;
 		continue;
 	}
@@ -3961,9 +4047,10 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 	int i;
 
 	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
+	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE ||
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP ||
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP) {
-		nh_grp->nexthops->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+		nh_grp->nexthops->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 		return;
 	}
 
@@ -3971,9 +4058,9 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 
 		if (nh->offloaded)
-			nh->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+			nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 		else
-			nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+			nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
@@ -3989,7 +4076,7 @@ mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 	for (i = 0; i < nh_grp->count; i++) {
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 
-		nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+		nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
@@ -4002,21 +4089,23 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 	fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
 				  common);
 
-	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) {
+	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
+	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE) {
 		list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
-				 list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
+				 list)->rt->fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 		return;
 	}
 
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
 		struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
+		struct fib6_nh *fib6_nh = mlxsw_sp_rt6->rt->fib6_nh;
 		struct mlxsw_sp_nexthop *nh;
 
 		nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
 		if (nh && nh->offloaded)
-			mlxsw_sp_rt6->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
+			fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 		else
-			mlxsw_sp_rt6->rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
+			fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
@@ -4031,7 +4120,7 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
 		struct fib6_info *rt = mlxsw_sp_rt6->rt;
 
-		rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
+		rt->fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
@@ -4170,6 +4259,19 @@ static int mlxsw_sp_fib_entry_op_trap(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
 }
 
+static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp,
+					   struct mlxsw_sp_fib_entry *fib_entry,
+					   enum mlxsw_reg_ralue_op op)
+{
+	enum mlxsw_reg_ralue_trap_action trap_action;
+	char ralue_pl[MLXSW_REG_RALUE_LEN];
+
+	trap_action = MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR;
+	mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
+	mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, 0, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+}
+
 static int
 mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_fib_entry *fib_entry,
@@ -4209,6 +4311,8 @@ static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
 		return mlxsw_sp_fib_entry_op_local(mlxsw_sp, fib_entry, op);
 	case MLXSW_SP_FIB_ENTRY_TYPE_TRAP:
 		return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op);
+	case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE:
+		return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op);
 	case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP:
 		return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp,
 							fib_entry, op);
@@ -4248,9 +4352,9 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 			     const struct fib_entry_notifier_info *fen_info,
 			     struct mlxsw_sp_fib_entry *fib_entry)
 {
+	struct net_device *dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
 	union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) };
 	u32 tb_id = mlxsw_sp_fix_tb_id(fen_info->tb_id);
-	struct net_device *dev = fen_info->fi->fib_dev;
 	struct mlxsw_sp_ipip_entry *ipip_entry;
 	struct fib_info *fi = fen_info->fi;
 
@@ -4277,8 +4381,10 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 	case RTN_BROADCAST:
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
 		return 0;
+	case RTN_BLACKHOLE:
+		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE;
+		return 0;
 	case RTN_UNREACHABLE: /* fall through */
-	case RTN_BLACKHOLE: /* fall through */
 	case RTN_PROHIBIT:
 		/* Packets hitting these routes need to be trapped, but
 		 * can do so with a lower priority than packets directed
@@ -4892,7 +4998,8 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
 static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
 {
 	/* RTF_CACHE routes are ignored */
-	return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY;
+	return !(rt->fib6_flags & RTF_ADDRCONF) &&
+		rt->fib6_nh->fib_nh_gw_family;
 }
 
 static struct fib6_info *
@@ -4951,8 +5058,8 @@ static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp,
 					const struct fib6_info *rt,
 					enum mlxsw_sp_ipip_type *ret)
 {
-	return rt->fib6_nh.nh_dev &&
-	       mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.nh_dev, ret);
+	return rt->fib6_nh->fib_nh_dev &&
+	       mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh->fib_nh_dev, ret);
 }
 
 static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
@@ -4962,7 +5069,7 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
 {
 	const struct mlxsw_sp_ipip_ops *ipip_ops;
 	struct mlxsw_sp_ipip_entry *ipip_entry;
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh->fib_nh_dev;
 	struct mlxsw_sp_rif *rif;
 	int err;
 
@@ -5005,11 +5112,11 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_nexthop *nh,
 				  const struct fib6_info *rt)
 {
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh->fib_nh_dev;
 
 	nh->nh_grp = nh_grp;
-	nh->nh_weight = rt->fib6_nh.nh_weight;
-	memcpy(&nh->gw_addr, &rt->fib6_nh.nh_gw, sizeof(nh->gw_addr));
+	nh->nh_weight = rt->fib6_nh->fib_nh_weight;
+	memcpy(&nh->gw_addr, &rt->fib6_nh->fib_nh_gw6, sizeof(nh->gw_addr));
 	mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
 
 	list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
@@ -5032,7 +5139,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
 static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
 				    const struct fib6_info *rt)
 {
-	return rt->fib6_flags & RTF_GATEWAY ||
+	return rt->fib6_nh->fib_nh_gw_family ||
 	       mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL);
 }
 
@@ -5043,13 +5150,11 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_nexthop_group *nh_grp;
 	struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
 	struct mlxsw_sp_nexthop *nh;
-	size_t alloc_size;
 	int i = 0;
 	int err;
 
-	alloc_size = sizeof(*nh_grp) +
-		     fib6_entry->nrt6 * sizeof(struct mlxsw_sp_nexthop);
-	nh_grp = kzalloc(alloc_size, GFP_KERNEL);
+	nh_grp = kzalloc(struct_size(nh_grp, nexthops, fib6_entry->nrt6),
+			 GFP_KERNEL);
 	if (!nh_grp)
 		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&nh_grp->fib_list);
@@ -5173,17 +5278,21 @@ err_nexthop6_group_get:
 static int
 mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_fib6_entry *fib6_entry,
-				struct fib6_info *rt)
+				struct fib6_info **rt_arr, unsigned int nrt6)
 {
 	struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
-	int err;
+	int err, i;
 
-	mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt);
-	if (IS_ERR(mlxsw_sp_rt6))
-		return PTR_ERR(mlxsw_sp_rt6);
+	for (i = 0; i < nrt6; i++) {
+		mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt_arr[i]);
+		if (IS_ERR(mlxsw_sp_rt6)) {
+			err = PTR_ERR(mlxsw_sp_rt6);
+			goto err_rt6_create;
+		}
 
-	list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list);
-	fib6_entry->nrt6++;
+		list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list);
+		fib6_entry->nrt6++;
+	}
 
 	err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry);
 	if (err)
@@ -5192,27 +5301,38 @@ mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_nexthop6_group_update:
-	fib6_entry->nrt6--;
-	list_del(&mlxsw_sp_rt6->list);
-	mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
+	i = nrt6;
+err_rt6_create:
+	for (i--; i >= 0; i--) {
+		fib6_entry->nrt6--;
+		mlxsw_sp_rt6 = list_last_entry(&fib6_entry->rt6_list,
+					       struct mlxsw_sp_rt6, list);
+		list_del(&mlxsw_sp_rt6->list);
+		mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
+	}
 	return err;
 }
 
 static void
 mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_fib6_entry *fib6_entry,
-				struct fib6_info *rt)
+				struct fib6_info **rt_arr, unsigned int nrt6)
 {
 	struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
+	int i;
 
-	mlxsw_sp_rt6 = mlxsw_sp_fib6_entry_rt_find(fib6_entry, rt);
-	if (WARN_ON(!mlxsw_sp_rt6))
-		return;
+	for (i = 0; i < nrt6; i++) {
+		mlxsw_sp_rt6 = mlxsw_sp_fib6_entry_rt_find(fib6_entry,
+							   rt_arr[i]);
+		if (WARN_ON_ONCE(!mlxsw_sp_rt6))
+			continue;
+
+		fib6_entry->nrt6--;
+		list_del(&mlxsw_sp_rt6->list);
+		mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
+	}
 
-	fib6_entry->nrt6--;
-	list_del(&mlxsw_sp_rt6->list);
 	mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry);
-	mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
 }
 
 static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp,
@@ -5227,6 +5347,8 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 	 */
 	if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
+	else if (rt->fib6_type == RTN_BLACKHOLE)
+		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE;
 	else if (rt->fib6_flags & RTF_REJECT)
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
 	else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt))
@@ -5251,29 +5373,32 @@ mlxsw_sp_fib6_entry_rt_destroy_all(struct mlxsw_sp_fib6_entry *fib6_entry)
 static struct mlxsw_sp_fib6_entry *
 mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_fib_node *fib_node,
-			   struct fib6_info *rt)
+			   struct fib6_info **rt_arr, unsigned int nrt6)
 {
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 	struct mlxsw_sp_fib_entry *fib_entry;
 	struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
-	int err;
+	int err, i;
 
 	fib6_entry = kzalloc(sizeof(*fib6_entry), GFP_KERNEL);
 	if (!fib6_entry)
 		return ERR_PTR(-ENOMEM);
 	fib_entry = &fib6_entry->common;
 
-	mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt);
-	if (IS_ERR(mlxsw_sp_rt6)) {
-		err = PTR_ERR(mlxsw_sp_rt6);
-		goto err_rt6_create;
+	INIT_LIST_HEAD(&fib6_entry->rt6_list);
+
+	for (i = 0; i < nrt6; i++) {
+		mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt_arr[i]);
+		if (IS_ERR(mlxsw_sp_rt6)) {
+			err = PTR_ERR(mlxsw_sp_rt6);
+			goto err_rt6_create;
+		}
+		list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list);
+		fib6_entry->nrt6++;
 	}
 
-	mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, mlxsw_sp_rt6->rt);
+	mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]);
 
-	INIT_LIST_HEAD(&fib6_entry->rt6_list);
-	list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list);
-	fib6_entry->nrt6 = 1;
 	err = mlxsw_sp_nexthop6_group_get(mlxsw_sp, fib6_entry);
 	if (err)
 		goto err_nexthop6_group_get;
@@ -5283,9 +5408,15 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp,
 	return fib6_entry;
 
 err_nexthop6_group_get:
-	list_del(&mlxsw_sp_rt6->list);
-	mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
+	i = nrt6;
 err_rt6_create:
+	for (i--; i >= 0; i--) {
+		fib6_entry->nrt6--;
+		mlxsw_sp_rt6 = list_last_entry(&fib6_entry->rt6_list,
+					       struct mlxsw_sp_rt6, list);
+		list_del(&mlxsw_sp_rt6->list);
+		mlxsw_sp_rt6_destroy(mlxsw_sp_rt6);
+	}
 	kfree(fib6_entry);
 	return ERR_PTR(err);
 }
@@ -5328,16 +5459,16 @@ mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
 
 static int
 mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry,
-			       bool replace)
+			       bool *p_replace)
 {
 	struct mlxsw_sp_fib_node *fib_node = new6_entry->common.fib_node;
 	struct fib6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry);
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 
-	fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, replace);
+	fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, *p_replace);
 
-	if (replace && WARN_ON(!fib6_entry))
-		return -EINVAL;
+	if (*p_replace && !fib6_entry)
+		*p_replace = false;
 
 	if (fib6_entry) {
 		list_add_tail(&new6_entry->common.list,
@@ -5372,11 +5503,11 @@ mlxsw_sp_fib6_node_list_remove(struct mlxsw_sp_fib6_entry *fib6_entry)
 
 static int mlxsw_sp_fib6_node_entry_link(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_fib6_entry *fib6_entry,
-					 bool replace)
+					 bool *p_replace)
 {
 	int err;
 
-	err = mlxsw_sp_fib6_node_list_insert(fib6_entry, replace);
+	err = mlxsw_sp_fib6_node_list_insert(fib6_entry, p_replace);
 	if (err)
 		return err;
 
@@ -5449,10 +5580,12 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
-				    struct fib6_info *rt, bool replace)
+				    struct fib6_info **rt_arr,
+				    unsigned int nrt6, bool replace)
 {
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 	struct mlxsw_sp_fib_node *fib_node;
+	struct fib6_info *rt = rt_arr[0];
 	int err;
 
 	if (mlxsw_sp->router->aborted)
@@ -5477,19 +5610,21 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
 	 */
 	fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace);
 	if (fib6_entry) {
-		err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt);
+		err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry,
+						      rt_arr, nrt6);
 		if (err)
 			goto err_fib6_entry_nexthop_add;
 		return 0;
 	}
 
-	fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt);
+	fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt_arr,
+						nrt6);
 	if (IS_ERR(fib6_entry)) {
 		err = PTR_ERR(fib6_entry);
 		goto err_fib6_entry_create;
 	}
 
-	err = mlxsw_sp_fib6_node_entry_link(mlxsw_sp, fib6_entry, replace);
+	err = mlxsw_sp_fib6_node_entry_link(mlxsw_sp, fib6_entry, &replace);
 	if (err)
 		goto err_fib6_node_entry_link;
 
@@ -5506,10 +5641,12 @@ err_fib6_entry_nexthop_add:
 }
 
 static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
-				     struct fib6_info *rt)
+				     struct fib6_info **rt_arr,
+				     unsigned int nrt6)
 {
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 	struct mlxsw_sp_fib_node *fib_node;
+	struct fib6_info *rt = rt_arr[0];
 
 	if (mlxsw_sp->router->aborted)
 		return;
@@ -5521,11 +5658,12 @@ static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
 	if (WARN_ON(!fib6_entry))
 		return;
 
-	/* If route is part of a multipath entry, but not the last one
-	 * removed, then only reduce its nexthop group.
+	/* If not all the nexthops are deleted, then only reduce the nexthop
+	 * group.
 	 */
-	if (!list_is_singular(&fib6_entry->rt6_list)) {
-		mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt);
+	if (nrt6 != fib6_entry->nrt6) {
+		mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt_arr,
+						nrt6);
 		return;
 	}
 
@@ -5786,10 +5924,15 @@ static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp)
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n");
 }
 
+struct mlxsw_sp_fib6_event_work {
+	struct fib6_info **rt_arr;
+	unsigned int nrt6;
+};
+
 struct mlxsw_sp_fib_event_work {
 	struct work_struct work;
 	union {
-		struct fib6_entry_notifier_info fen6_info;
+		struct mlxsw_sp_fib6_event_work fib6_work;
 		struct fib_entry_notifier_info fen_info;
 		struct fib_rule_notifier_info fr_info;
 		struct fib_nh_notifier_info fnh_info;
@@ -5800,6 +5943,54 @@ struct mlxsw_sp_fib_event_work {
 	unsigned long event;
 };
 
+static int
+mlxsw_sp_router_fib6_work_init(struct mlxsw_sp_fib6_event_work *fib6_work,
+			       struct fib6_entry_notifier_info *fen6_info)
+{
+	struct fib6_info *rt = fen6_info->rt;
+	struct fib6_info **rt_arr;
+	struct fib6_info *iter;
+	unsigned int nrt6;
+	int i = 0;
+
+	nrt6 = fen6_info->nsiblings + 1;
+
+	rt_arr = kcalloc(nrt6, sizeof(struct fib6_info *), GFP_ATOMIC);
+	if (!rt_arr)
+		return -ENOMEM;
+
+	fib6_work->rt_arr = rt_arr;
+	fib6_work->nrt6 = nrt6;
+
+	rt_arr[0] = rt;
+	fib6_info_hold(rt);
+
+	if (!fen6_info->nsiblings)
+		return 0;
+
+	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
+		if (i == fen6_info->nsiblings)
+			break;
+
+		rt_arr[i + 1] = iter;
+		fib6_info_hold(iter);
+		i++;
+	}
+	WARN_ON_ONCE(i != fen6_info->nsiblings);
+
+	return 0;
+}
+
+static void
+mlxsw_sp_router_fib6_work_fini(struct mlxsw_sp_fib6_event_work *fib6_work)
+{
+	int i;
+
+	for (i = 0; i < fib6_work->nrt6; i++)
+		mlxsw_sp_rt6_release(fib6_work->rt_arr[i]);
+	kfree(fib6_work->rt_arr);
+}
+
 static void mlxsw_sp_router_fib4_event_work(struct work_struct *work)
 {
 	struct mlxsw_sp_fib_event_work *fib_work =
@@ -5858,18 +6049,21 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 
 	switch (fib_work->event) {
 	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
-	case FIB_EVENT_ENTRY_APPEND: /* fall through */
 	case FIB_EVENT_ENTRY_ADD:
 		replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
 		err = mlxsw_sp_router_fib6_add(mlxsw_sp,
-					       fib_work->fen6_info.rt, replace);
+					       fib_work->fib6_work.rt_arr,
+					       fib_work->fib6_work.nrt6,
+					       replace);
 		if (err)
 			mlxsw_sp_router_fib_abort(mlxsw_sp);
-		mlxsw_sp_rt6_release(fib_work->fen6_info.rt);
+		mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work);
 		break;
 	case FIB_EVENT_ENTRY_DEL:
-		mlxsw_sp_router_fib6_del(mlxsw_sp, fib_work->fen6_info.rt);
-		mlxsw_sp_rt6_release(fib_work->fen6_info.rt);
+		mlxsw_sp_router_fib6_del(mlxsw_sp,
+					 fib_work->fib6_work.rt_arr,
+					 fib_work->fib6_work.nrt6);
+		mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work);
 		break;
 	case FIB_EVENT_RULE_ADD:
 		/* if we get here, a rule was added that we do not support.
@@ -5958,22 +6152,26 @@ static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work,
 	}
 }
 
-static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
-				       struct fib_notifier_info *info)
+static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
+				      struct fib_notifier_info *info)
 {
 	struct fib6_entry_notifier_info *fen6_info;
+	int err;
 
 	switch (fib_work->event) {
 	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
-	case FIB_EVENT_ENTRY_APPEND: /* fall through */
 	case FIB_EVENT_ENTRY_ADD: /* fall through */
 	case FIB_EVENT_ENTRY_DEL:
 		fen6_info = container_of(info, struct fib6_entry_notifier_info,
 					 info);
-		fib_work->fen6_info = *fen6_info;
-		fib6_info_hold(fib_work->fen6_info.rt);
+		err = mlxsw_sp_router_fib6_work_init(&fib_work->fib6_work,
+						     fen6_info);
+		if (err)
+			return err;
 		break;
 	}
+
+	return 0;
 }
 
 static void
@@ -6014,6 +6212,10 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event,
 	fr_info = container_of(info, struct fib_rule_notifier_info, info);
 	rule = fr_info->rule;
 
+	/* Rule only affects locally generated traffic */
+	if (rule->iifindex == info->net->loopback_dev->ifindex)
+		return 0;
+
 	switch (info->family) {
 	case AF_INET:
 		if (!fib4_rule_default(rule) && !rule->l3mdev)
@@ -6065,10 +6267,34 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 			return notifier_from_errno(err);
 		break;
 	case FIB_EVENT_ENTRY_ADD:
+	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_APPEND:  /* fall through */
 		if (router->aborted) {
 			NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route");
 			return notifier_from_errno(-EINVAL);
 		}
+		if (info->family == AF_INET) {
+			struct fib_entry_notifier_info *fen_info = ptr;
+
+			if (fen_info->fi->fib_nh_is_v6) {
+				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+				return notifier_from_errno(-EINVAL);
+			}
+			if (fen_info->fi->nh) {
+				NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
+				return notifier_from_errno(-EINVAL);
+			}
+		} else if (info->family == AF_INET6) {
+			struct fib6_entry_notifier_info *fen6_info;
+
+			fen6_info = container_of(info,
+						 struct fib6_entry_notifier_info,
+						 info);
+			if (fen6_info->rt->nh) {
+				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported");
+				return notifier_from_errno(-EINVAL);
+			}
+		}
 		break;
 	}
 
@@ -6086,7 +6312,9 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 		break;
 	case AF_INET6:
 		INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work);
-		mlxsw_sp_router_fib6_event(fib_work, info);
+		err = mlxsw_sp_router_fib6_event(fib_work, info);
+		if (err)
+			goto err_fib_event;
 		break;
 	case RTNL_FAMILY_IP6MR:
 	case RTNL_FAMILY_IPMR:
@@ -6098,6 +6326,10 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	mlxsw_core_schedule_work(&fib_work->work);
 
 	return NOTIFY_DONE;
+
+err_fib_event:
+	kfree(fib_work);
+	return NOTIFY_BAD;
 }
 
 struct mlxsw_sp_rif *
@@ -6121,7 +6353,7 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 
 	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-	if (WARN_ON_ONCE(err))
+	if (err)
 		return err;
 
 	mlxsw_reg_ritr_enable_set(ritr_pl, false);
@@ -6224,10 +6456,12 @@ static struct mlxsw_sp_rif *mlxsw_sp_rif_alloc(size_t rif_size, u16 rif_index,
 
 	INIT_LIST_HEAD(&rif->nexthop_list);
 	INIT_LIST_HEAD(&rif->neigh_list);
-	ether_addr_copy(rif->addr, l3_dev->dev_addr);
-	rif->mtu = l3_dev->mtu;
+	if (l3_dev) {
+		ether_addr_copy(rif->addr, l3_dev->dev_addr);
+		rif->mtu = l3_dev->mtu;
+		rif->dev = l3_dev;
+	}
 	rif->vr_id = vr_id;
-	rif->dev = l3_dev;
 	rif->rif_index = rif_index;
 
 	return rif;
@@ -6251,7 +6485,19 @@ u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 
 u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 {
-	return lb_rif->ul_vr_id;
+	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(lb_rif->common.dev);
+	struct mlxsw_sp_vr *ul_vr;
+
+	ul_vr = mlxsw_sp_vr_get(lb_rif->common.mlxsw_sp, ul_tb_id, NULL);
+	if (WARN_ON(IS_ERR(ul_vr)))
+		return 0;
+
+	return ul_vr->id;
+}
+
+u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
+{
+	return lb_rif->ul_rif_id;
 }
 
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif)
@@ -6284,7 +6530,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	int i, err;
 
 	type = mlxsw_sp_dev_rif_type(mlxsw_sp, params->dev);
-	ops = mlxsw_sp->router->rif_ops_arr[type];
+	ops = mlxsw_sp->rif_ops_arr[type];
 
 	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN, extack);
 	if (IS_ERR(vr))
@@ -6303,6 +6549,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		goto err_rif_alloc;
 	}
 	dev_hold(rif->dev);
+	mlxsw_sp->router->rifs[rif_index] = rif;
 	rif->mlxsw_sp = mlxsw_sp;
 	rif->ops = ops;
 
@@ -6329,7 +6576,6 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_sp_rif_counters_alloc(rif);
-	mlxsw_sp->router->rifs[rif_index] = rif;
 
 	return rif;
 
@@ -6341,6 +6587,7 @@ err_configure:
 	if (fid)
 		mlxsw_sp_fid_put(fid);
 err_fid_get:
+	mlxsw_sp->router->rifs[rif_index] = NULL;
 	dev_put(rif->dev);
 	kfree(rif);
 err_rif_alloc:
@@ -6361,7 +6608,6 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
 	vr = &mlxsw_sp->router->vrs[rif->vr_id];
 
-	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
 	mlxsw_sp_rif_counters_free(rif);
 	for (i = 0; i < MLXSW_SP_L3_PROTO_MAX; i++)
 		mlxsw_sp_mr_rif_del(vr->mr_table[i], rif);
@@ -6369,6 +6615,7 @@ static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	if (fid)
 		/* Loopback RIFs are not associated with a FID. */
 		mlxsw_sp_fid_put(fid);
+	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
 	dev_put(rif->dev);
 	kfree(rif);
 	vr->rif_count--;
@@ -6745,12 +6992,12 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
 	/* A RIF is not created for macvlan netdevs. Their MAC is used to
 	 * populate the FDB
 	 */
-	if (netif_is_macvlan(dev))
+	if (netif_is_macvlan(dev) || netif_is_l3_master(dev))
 		return 0;
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
 		rif = mlxsw_sp->router->rifs[i];
-		if (rif && rif->dev != dev &&
+		if (rif && rif->dev && rif->dev != dev &&
 		    !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr,
 					     mlxsw_sp->mac_mask)) {
 			NL_SET_ERR_MSG_MOD(extack, "All router interface MAC addresses must have the same prefix");
@@ -7294,7 +7541,8 @@ static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
 
 	info.addr = mac;
 	info.vid = vid;
-	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info,
+				 NULL);
 }
 
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_ops = {
@@ -7381,7 +7629,8 @@ static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
 
 	info.addr = mac;
 	info.vid = 0;
-	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info,
+				 NULL);
 }
 
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
@@ -7422,7 +7671,7 @@ mlxsw_sp_rif_ipip_lb_setup(struct mlxsw_sp_rif *rif,
 }
 
 static int
-mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
+mlxsw_sp1_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
 	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev);
@@ -7434,11 +7683,12 @@ mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
 	if (IS_ERR(ul_vr))
 		return PTR_ERR(ul_vr);
 
-	err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, true);
+	err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr->id, 0, true);
 	if (err)
 		goto err_loopback_op;
 
 	lb_rif->ul_vr_id = ul_vr->id;
+	lb_rif->ul_rif_id = 0;
 	++ul_vr->rif_count;
 	return 0;
 
@@ -7447,32 +7697,213 @@ err_loopback_op:
 	return err;
 }
 
-static void mlxsw_sp_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif)
+static void mlxsw_sp1_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
 	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
 	struct mlxsw_sp_vr *ul_vr;
 
 	ul_vr = &mlxsw_sp->router->vrs[lb_rif->ul_vr_id];
-	mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, false);
+	mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr->id, 0, false);
 
 	--ul_vr->rif_count;
 	mlxsw_sp_vr_put(mlxsw_sp, ul_vr);
 }
 
-static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_ipip_lb_ops = {
+static const struct mlxsw_sp_rif_ops mlxsw_sp1_rif_ipip_lb_ops = {
 	.type			= MLXSW_SP_RIF_TYPE_IPIP_LB,
 	.rif_size		= sizeof(struct mlxsw_sp_rif_ipip_lb),
 	.setup                  = mlxsw_sp_rif_ipip_lb_setup,
-	.configure		= mlxsw_sp_rif_ipip_lb_configure,
-	.deconfigure		= mlxsw_sp_rif_ipip_lb_deconfigure,
+	.configure		= mlxsw_sp1_rif_ipip_lb_configure,
+	.deconfigure		= mlxsw_sp1_rif_ipip_lb_deconfigure,
 };
 
-static const struct mlxsw_sp_rif_ops *mlxsw_sp_rif_ops_arr[] = {
+const struct mlxsw_sp_rif_ops *mlxsw_sp1_rif_ops_arr[] = {
 	[MLXSW_SP_RIF_TYPE_SUBPORT]	= &mlxsw_sp_rif_subport_ops,
 	[MLXSW_SP_RIF_TYPE_VLAN]	= &mlxsw_sp_rif_vlan_emu_ops,
 	[MLXSW_SP_RIF_TYPE_FID]		= &mlxsw_sp_rif_fid_ops,
-	[MLXSW_SP_RIF_TYPE_IPIP_LB]	= &mlxsw_sp_rif_ipip_lb_ops,
+	[MLXSW_SP_RIF_TYPE_IPIP_LB]	= &mlxsw_sp1_rif_ipip_lb_ops,
+};
+
+static int
+mlxsw_sp_rif_ipip_lb_ul_rif_op(struct mlxsw_sp_rif *ul_rif, bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = ul_rif->mlxsw_sp;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+
+	mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF,
+			    ul_rif->rif_index, ul_rif->vr_id, IP_MAX_MTU);
+	mlxsw_reg_ritr_loopback_protocol_set(ritr_pl,
+					     MLXSW_REG_RITR_LOOPBACK_GENERIC);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_ul_rif_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
+		       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif *ul_rif;
+	u16 rif_index;
+	int err;
+
+	err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported router interfaces");
+		return ERR_PTR(err);
+	}
+
+	ul_rif = mlxsw_sp_rif_alloc(sizeof(*ul_rif), rif_index, vr->id, NULL);
+	if (!ul_rif)
+		return ERR_PTR(-ENOMEM);
+
+	mlxsw_sp->router->rifs[rif_index] = ul_rif;
+	ul_rif->mlxsw_sp = mlxsw_sp;
+	err = mlxsw_sp_rif_ipip_lb_ul_rif_op(ul_rif, true);
+	if (err)
+		goto ul_rif_op_err;
+
+	return ul_rif;
+
+ul_rif_op_err:
+	mlxsw_sp->router->rifs[rif_index] = NULL;
+	kfree(ul_rif);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_ul_rif_destroy(struct mlxsw_sp_rif *ul_rif)
+{
+	struct mlxsw_sp *mlxsw_sp = ul_rif->mlxsw_sp;
+
+	mlxsw_sp_rif_ipip_lb_ul_rif_op(ul_rif, false);
+	mlxsw_sp->router->rifs[ul_rif->rif_index] = NULL;
+	kfree(ul_rif);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id,
+		    struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_vr *vr;
+	int err;
+
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id, extack);
+	if (IS_ERR(vr))
+		return ERR_CAST(vr);
+
+	if (refcount_inc_not_zero(&vr->ul_rif_refcnt))
+		return vr->ul_rif;
+
+	vr->ul_rif = mlxsw_sp_ul_rif_create(mlxsw_sp, vr, extack);
+	if (IS_ERR(vr->ul_rif)) {
+		err = PTR_ERR(vr->ul_rif);
+		goto err_ul_rif_create;
+	}
+
+	vr->rif_count++;
+	refcount_set(&vr->ul_rif_refcnt, 1);
+
+	return vr->ul_rif;
+
+err_ul_rif_create:
+	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_ul_rif_put(struct mlxsw_sp_rif *ul_rif)
+{
+	struct mlxsw_sp *mlxsw_sp = ul_rif->mlxsw_sp;
+	struct mlxsw_sp_vr *vr;
+
+	vr = &mlxsw_sp->router->vrs[ul_rif->vr_id];
+
+	if (!refcount_dec_and_test(&vr->ul_rif_refcnt))
+		return;
+
+	vr->rif_count--;
+	mlxsw_sp_ul_rif_destroy(ul_rif);
+	mlxsw_sp_vr_put(mlxsw_sp, vr);
+}
+
+int mlxsw_sp_router_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
+			       u16 *ul_rif_index)
+{
+	struct mlxsw_sp_rif *ul_rif;
+
+	ASSERT_RTNL();
+
+	ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL);
+	if (IS_ERR(ul_rif))
+		return PTR_ERR(ul_rif);
+	*ul_rif_index = ul_rif->rif_index;
+
+	return 0;
+}
+
+void mlxsw_sp_router_ul_rif_put(struct mlxsw_sp *mlxsw_sp, u16 ul_rif_index)
+{
+	struct mlxsw_sp_rif *ul_rif;
+
+	ASSERT_RTNL();
+
+	ul_rif = mlxsw_sp->router->rifs[ul_rif_index];
+	if (WARN_ON(!ul_rif))
+		return;
+
+	mlxsw_sp_ul_rif_put(ul_rif);
+}
+
+static int
+mlxsw_sp2_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
+	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev);
+	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+	struct mlxsw_sp_rif *ul_rif;
+	int err;
+
+	ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL);
+	if (IS_ERR(ul_rif))
+		return PTR_ERR(ul_rif);
+
+	err = mlxsw_sp_rif_ipip_lb_op(lb_rif, 0, ul_rif->rif_index, true);
+	if (err)
+		goto err_loopback_op;
+
+	lb_rif->ul_vr_id = 0;
+	lb_rif->ul_rif_id = ul_rif->rif_index;
+
+	return 0;
+
+err_loopback_op:
+	mlxsw_sp_ul_rif_put(ul_rif);
+	return err;
+}
+
+static void mlxsw_sp2_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
+	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+	struct mlxsw_sp_rif *ul_rif;
+
+	ul_rif = mlxsw_sp_rif_by_index(mlxsw_sp, lb_rif->ul_rif_id);
+	mlxsw_sp_rif_ipip_lb_op(lb_rif, 0, lb_rif->ul_rif_id, false);
+	mlxsw_sp_ul_rif_put(ul_rif);
+}
+
+static const struct mlxsw_sp_rif_ops mlxsw_sp2_rif_ipip_lb_ops = {
+	.type			= MLXSW_SP_RIF_TYPE_IPIP_LB,
+	.rif_size		= sizeof(struct mlxsw_sp_rif_ipip_lb),
+	.setup                  = mlxsw_sp_rif_ipip_lb_setup,
+	.configure		= mlxsw_sp2_rif_ipip_lb_configure,
+	.deconfigure		= mlxsw_sp2_rif_ipip_lb_deconfigure,
+};
+
+const struct mlxsw_sp_rif_ops *mlxsw_sp2_rif_ops_arr[] = {
+	[MLXSW_SP_RIF_TYPE_SUBPORT]	= &mlxsw_sp_rif_subport_ops,
+	[MLXSW_SP_RIF_TYPE_VLAN]	= &mlxsw_sp_rif_vlan_emu_ops,
+	[MLXSW_SP_RIF_TYPE_FID]		= &mlxsw_sp_rif_fid_ops,
+	[MLXSW_SP_RIF_TYPE_IPIP_LB]	= &mlxsw_sp2_rif_ipip_lb_ops,
 };
 
 static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp)
@@ -7485,8 +7916,6 @@ static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp)
 	if (!mlxsw_sp->router->rifs)
 		return -ENOMEM;
 
-	mlxsw_sp->router->rif_ops_arr = mlxsw_sp_rif_ops_arr;
-
 	return 0;
 }
 
@@ -7590,7 +8019,7 @@ static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)
 	char recr2_pl[MLXSW_REG_RECR2_LEN];
 	u32 seed;
 
-	get_random_bytes(&seed, sizeof(seed));
+	seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0);
 	mlxsw_reg_recr2_pack(recr2_pl, seed);
 	mlxsw_sp_mp4_hash_init(recr2_pl);
 	mlxsw_sp_mp6_hash_init(recr2_pl);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 3dbafdeaab2b..cc1de91e8217 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -29,6 +29,7 @@ struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
 u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
 u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
+u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif);
 u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
 const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index ad5a9b9e1466..560a60e522f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -305,7 +305,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, parms.link, tun->fwmark);
+			    0, 0, parms.link, tun->fwmark, 0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))
@@ -316,7 +316,11 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	dev = rt->dst.dev;
 	*saddrp = fl4.saddr;
-	*daddrp = rt->rt_gateway;
+	if (rt->rt_gw_family == AF_INET)
+		*daddrp = rt->rt_gw4;
+	/* can not offload if route has an IPv6 gateway */
+	else if (rt->rt_gw_family == AF_INET6)
+		dev = NULL;
 
 out:
 	ip_rt_put(rt);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index c772109b638d..50111f228d77 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -431,46 +431,6 @@ static void mlxsw_sp_bridge_vlan_put(struct mlxsw_sp_bridge_vlan *bridge_vlan)
 		mlxsw_sp_bridge_vlan_destroy(bridge_vlan);
 }
 
-static void mlxsw_sp_port_bridge_flags_get(struct mlxsw_sp_bridge *bridge,
-					   struct net_device *dev,
-					   unsigned long *brport_flags)
-{
-	struct mlxsw_sp_bridge_port *bridge_port;
-
-	bridge_port = mlxsw_sp_bridge_port_find(bridge, dev);
-	if (WARN_ON(!bridge_port))
-		return;
-
-	memcpy(brport_flags, &bridge_port->flags, sizeof(*brport_flags));
-}
-
-static int mlxsw_sp_port_attr_get(struct net_device *dev,
-				  struct switchdev_attr *attr)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(mlxsw_sp->base_mac);
-		memcpy(&attr->u.ppid.id, &mlxsw_sp->base_mac,
-		       attr->u.ppid.id_len);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
-		mlxsw_sp_port_bridge_flags_get(mlxsw_sp->bridge, attr->orig_dev,
-					       &attr->u.brport_flags);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
-		attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD |
-					       BR_MCAST_FLOOD;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 static int
 mlxsw_sp_port_bridge_vlan_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct mlxsw_sp_bridge_vlan *bridge_vlan,
@@ -620,6 +580,17 @@ err_port_bridge_vlan_learning_set:
 	return err;
 }
 
+static int mlxsw_sp_port_attr_br_pre_flags_set(struct mlxsw_sp_port
+					       *mlxsw_sp_port,
+					       struct switchdev_trans *trans,
+					       unsigned long brport_flags)
+{
+	if (brport_flags & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
 					   struct switchdev_trans *trans,
 					   struct net_device *orig_dev,
@@ -866,6 +837,11 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 						       attr->orig_dev,
 						       attr->u.stp_state);
 		break;
+	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+		err = mlxsw_sp_port_attr_br_pre_flags_set(mlxsw_sp_port,
+							  trans,
+							  attr->u.brport_flags);
+		break;
 	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
 		err = mlxsw_sp_port_attr_br_flags_set(mlxsw_sp_port, trans,
 						      attr->orig_dev,
@@ -1654,7 +1630,7 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	u16 fid_index;
 	int err = 0;
 
-	if (switchdev_trans_ph_prepare(trans))
+	if (switchdev_trans_ph_commit(trans))
 		return 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
@@ -1962,11 +1938,6 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
-	.switchdev_port_attr_get	= mlxsw_sp_port_attr_get,
-	.switchdev_port_attr_set	= mlxsw_sp_port_attr_set,
-};
-
 static int
 mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 				struct mlxsw_sp_bridge_port *bridge_port,
@@ -2027,6 +1998,7 @@ mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
 		return 0;
 
 	if (mlxsw_sp_fid_vni_is_set(fid)) {
+		NL_SET_ERR_MSG_MOD(extack, "VNI is already set on FID");
 		err = -EINVAL;
 		goto err_vni_exists;
 	}
@@ -2213,10 +2185,13 @@ mlxsw_sp_bridge_8021d_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
 	int err;
 
 	fid = mlxsw_sp_fid_8021d_lookup(mlxsw_sp, bridge_device->dev->ifindex);
-	if (!fid)
+	if (!fid) {
+		NL_SET_ERR_MSG_MOD(extack, "Did not find a corresponding FID");
 		return -EINVAL;
+	}
 
 	if (mlxsw_sp_fid_vni_is_set(fid)) {
+		NL_SET_ERR_MSG_MOD(extack, "VNI is already set on FID");
 		err = -EINVAL;
 		goto err_vni_exists;
 	}
@@ -2443,7 +2418,7 @@ static void mlxsw_sp_fdb_vxlan_call_notifiers(struct net_device *dev,
 	ether_addr_copy(info.eth_addr, mac);
 	info.vni = vni;
 	info.offloaded = adding;
-	call_switchdev_notifiers(type, dev, &info.info);
+	call_switchdev_notifiers(type, dev, &info.info, NULL);
 }
 
 static void mlxsw_sp_fdb_nve_call_notifiers(struct net_device *dev,
@@ -2468,7 +2443,7 @@ mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type,
 	info.addr = mac;
 	info.vid = vid;
 	info.offloaded = offloaded;
-	call_switchdev_notifiers(type, dev, &info.info);
+	call_switchdev_notifiers(type, dev, &info.info, NULL);
 }
 
 static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
@@ -2819,7 +2794,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp,
 			return;
 		vxlan_fdb_info.offloaded = true;
 		call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-					 &vxlan_fdb_info.info);
+					 &vxlan_fdb_info.info, NULL);
 		mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED,
 					    vxlan_fdb_info.eth_addr,
 					    fdb_info->vid, dev, true);
@@ -2832,7 +2807,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp,
 						     false);
 		vxlan_fdb_info.offloaded = false;
 		call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-					 &vxlan_fdb_info.info);
+					 &vxlan_fdb_info.info, NULL);
 		break;
 	}
 }
@@ -2977,7 +2952,7 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp,
 		}
 		vxlan_fdb_info->offloaded = true;
 		call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-					 &vxlan_fdb_info->info);
+					 &vxlan_fdb_info->info, NULL);
 		mlxsw_sp_fid_put(fid);
 		return;
 	}
@@ -2998,7 +2973,7 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp,
 		goto err_fdb_tunnel_uc_op;
 	vxlan_fdb_info->offloaded = true;
 	call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-				 &vxlan_fdb_info->info);
+				 &vxlan_fdb_info->info, NULL);
 	mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED,
 				    vxlan_fdb_info->eth_addr, vid, dev, true);
 
@@ -3099,23 +3074,34 @@ mlxsw_sp_switchdev_vxlan_work_prepare(struct mlxsw_sp_switchdev_event_work *
 	struct vxlan_dev *vxlan = netdev_priv(switchdev_work->dev);
 	struct switchdev_notifier_vxlan_fdb_info *vxlan_fdb_info;
 	struct vxlan_config *cfg = &vxlan->cfg;
+	struct netlink_ext_ack *extack;
 
+	extack = switchdev_notifier_info_to_extack(info);
 	vxlan_fdb_info = container_of(info,
 				      struct switchdev_notifier_vxlan_fdb_info,
 				      info);
 
-	if (vxlan_fdb_info->remote_port != cfg->dst_port)
+	if (vxlan_fdb_info->remote_port != cfg->dst_port) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Non-default remote port is not supported");
 		return -EOPNOTSUPP;
-	if (vxlan_fdb_info->remote_vni != cfg->vni)
-		return -EOPNOTSUPP;
-	if (vxlan_fdb_info->vni != cfg->vni)
+	}
+	if (vxlan_fdb_info->remote_vni != cfg->vni ||
+	    vxlan_fdb_info->vni != cfg->vni) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Non-default VNI is not supported");
 		return -EOPNOTSUPP;
-	if (vxlan_fdb_info->remote_ifindex)
+	}
+	if (vxlan_fdb_info->remote_ifindex) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Local interface is not supported");
 		return -EOPNOTSUPP;
-	if (is_multicast_ether_addr(vxlan_fdb_info->eth_addr))
+	}
+	if (is_multicast_ether_addr(vxlan_fdb_info->eth_addr)) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Multicast MAC addresses not supported");
 		return -EOPNOTSUPP;
-	if (vxlan_addr_multicast(&vxlan_fdb_info->remote_ip))
+	}
+	if (vxlan_addr_multicast(&vxlan_fdb_info->remote_ip)) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Multicast destination IP is not supported");
 		return -EOPNOTSUPP;
+	}
 
 	switchdev_work->vxlan_fdb_info = *vxlan_fdb_info;
 
@@ -3133,6 +3119,13 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused,
 	struct net_device *br_dev;
 	int err;
 
+	if (event == SWITCHDEV_PORT_ATTR_SET) {
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     mlxsw_sp_port_dev_check,
+						     mlxsw_sp_port_attr_set);
+		return notifier_from_errno(err);
+	}
+
 	/* Tunnel devices are not our uppers, so check their master instead */
 	br_dev = netdev_master_upper_dev_get_rcu(dev);
 	if (!br_dev)
@@ -3220,8 +3213,10 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 	 * the lookup function to return 'vxlan_dev'
 	 */
 	if (flag_untagged && flag_pvid &&
-	    mlxsw_sp_bridge_8021q_vxlan_dev_find(bridge_device->dev, vid))
+	    mlxsw_sp_bridge_8021q_vxlan_dev_find(bridge_device->dev, vid)) {
+		NL_SET_ERR_MSG_MOD(extack, "VLAN already mapped to a different VNI");
 		return -EINVAL;
+	}
 
 	if (!netif_running(vxlan_dev))
 		return 0;
@@ -3454,6 +3449,11 @@ static int mlxsw_sp_switchdev_blocking_event(struct notifier_block *unused,
 							mlxsw_sp_port_dev_check,
 							mlxsw_sp_port_obj_del);
 		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     mlxsw_sp_port_dev_check,
+						     mlxsw_sp_port_attr_set);
+		return notifier_from_errno(err);
 	}
 
 	return NOTIFY_DONE;
@@ -3541,11 +3541,3 @@ void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
 	kfree(mlxsw_sp->bridge);
 }
 
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops;
-}
-
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
index bcf2e79a21c8..0d9356b3f65d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
@@ -30,6 +30,7 @@ struct mlxsw_sib {
 	struct mlxsw_sib_port **ports;
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
+	u8 hw_id[ETH_ALEN];
 };
 
 struct mlxsw_sib_port {
@@ -102,6 +103,18 @@ mlxsw_sib_tx_v1_hdr_construct(struct sk_buff *skb,
 	mlxsw_tx_v1_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL);
 }
 
+static int mlxsw_sib_hw_id_get(struct mlxsw_sib *mlxsw_sib)
+{
+	char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
+	int err;
+
+	err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(spad), spad_pl);
+	if (err)
+		return err;
+	mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_sib->hw_id);
+	return 0;
+}
+
 static int
 mlxsw_sib_port_admin_status_set(struct mlxsw_sib_port *mlxsw_sib_port,
 				bool is_up)
@@ -267,7 +280,9 @@ static int mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port,
 {
 	int err;
 
-	err = mlxsw_core_port_init(mlxsw_sib->core, local_port);
+	err = mlxsw_core_port_init(mlxsw_sib->core, local_port,
+				   module + 1, false, 0,
+				   mlxsw_sib->hw_id, sizeof(mlxsw_sib->hw_id));
 	if (err) {
 		dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to init core port\n",
 			local_port);
@@ -439,6 +454,12 @@ static int mlxsw_sib_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sib->core = mlxsw_core;
 	mlxsw_sib->bus_info = mlxsw_bus_info;
 
+	err = mlxsw_sib_hw_id_get(mlxsw_sib);
+	if (err) {
+		dev_err(mlxsw_sib->bus_info->dev, "Failed to get switch HW ID\n");
+		return err;
+	}
+
 	err = mlxsw_sib_ports_create(mlxsw_sib);
 	if (err) {
 		dev_err(mlxsw_sib->bus_info->dev, "Failed to create ports\n");
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 2d4f213e154d..bdab96f5bc70 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -11,7 +11,6 @@
 #include <linux/device.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
-#include <net/switchdev.h>
 
 #include "pci.h"
 #include "core.h"
@@ -300,6 +299,8 @@ static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb,
 	u64 len;
 	int err;
 
+	memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb));
+
 	if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info))
 		return NETDEV_TX_BUSY;
 
@@ -380,14 +381,14 @@ mlxsw_sx_port_get_stats64(struct net_device *dev,
 	stats->tx_dropped	= tx_dropped;
 }
 
-static int mlxsw_sx_port_get_phys_port_name(struct net_device *dev, char *name,
-					    size_t len)
+static struct devlink_port *
+mlxsw_sx_port_get_devlink_port(struct net_device *dev)
 {
 	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
+	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
 
-	return mlxsw_core_port_get_phys_port_name(mlxsw_sx_port->mlxsw_sx->core,
-						  mlxsw_sx_port->local_port,
-						  name, len);
+	return mlxsw_core_port_devlink_port_get(mlxsw_sx->core,
+						mlxsw_sx_port->local_port);
 }
 
 static const struct net_device_ops mlxsw_sx_port_netdev_ops = {
@@ -396,7 +397,7 @@ static const struct net_device_ops mlxsw_sx_port_netdev_ops = {
 	.ndo_start_xmit		= mlxsw_sx_port_xmit,
 	.ndo_change_mtu		= mlxsw_sx_port_change_mtu,
 	.ndo_get_stats64	= mlxsw_sx_port_get_stats64,
-	.ndo_get_phys_port_name = mlxsw_sx_port_get_phys_port_name,
+	.ndo_get_devlink_port	= mlxsw_sx_port_get_devlink_port,
 };
 
 static void mlxsw_sx_port_get_drvinfo(struct net_device *dev,
@@ -901,28 +902,6 @@ static const struct ethtool_ops mlxsw_sx_port_ethtool_ops = {
 	.set_link_ksettings	= mlxsw_sx_port_set_link_ksettings,
 };
 
-static int mlxsw_sx_port_attr_get(struct net_device *dev,
-				  struct switchdev_attr *attr)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(mlxsw_sx->hw_id);
-		memcpy(&attr->u.ppid.id, &mlxsw_sx->hw_id, attr->u.ppid.id_len);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static const struct switchdev_ops mlxsw_sx_port_switchdev_ops = {
-	.switchdev_port_attr_get	= mlxsw_sx_port_attr_get,
-};
-
 static int mlxsw_sx_hw_id_get(struct mlxsw_sx *mlxsw_sx)
 {
 	char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
@@ -1034,7 +1013,6 @@ static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
 
 	dev->netdev_ops = &mlxsw_sx_port_netdev_ops;
 	dev->ethtool_ops = &mlxsw_sx_port_ethtool_ops;
-	dev->switchdev_ops = &mlxsw_sx_port_switchdev_ops;
 
 	err = mlxsw_sx_port_dev_addr_get(mlxsw_sx_port);
 	if (err) {
@@ -1113,7 +1091,7 @@ static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
 	}
 
 	mlxsw_core_port_eth_set(mlxsw_sx->core, mlxsw_sx_port->local_port,
-				mlxsw_sx_port, dev, module + 1, false, 0);
+				mlxsw_sx_port, dev);
 	mlxsw_sx->ports[local_port] = mlxsw_sx_port;
 	return 0;
 
@@ -1138,7 +1116,9 @@ static int mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
 {
 	int err;
 
-	err = mlxsw_core_port_init(mlxsw_sx->core, local_port);
+	err = mlxsw_core_port_init(mlxsw_sx->core, local_port,
+				   module + 1, false, 0,
+				   mlxsw_sx->hw_id, sizeof(mlxsw_sx->hw_id));
 	if (err) {
 		dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n",
 			local_port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 451216dd7f6b..19202bdb5105 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -17,6 +17,8 @@ enum {
 	MLXSW_TRAP_ID_MVRP = 0x15,
 	MLXSW_TRAP_ID_RPVST = 0x16,
 	MLXSW_TRAP_ID_DHCP = 0x19,
+	MLXSW_TRAP_ID_PTP0 = 0x28,
+	MLXSW_TRAP_ID_PTP1 = 0x29,
 	MLXSW_TRAP_ID_IGMP_QUERY = 0x30,
 	MLXSW_TRAP_ID_IGMP_V1_REPORT = 0x31,
 	MLXSW_TRAP_ID_IGMP_V2_REPORT = 0x32,
@@ -76,6 +78,10 @@ enum {
 enum mlxsw_event_trap_id {
 	/* Port Up/Down event generated by hardware */
 	MLXSW_TRAP_ID_PUDE = 0x8,
+	/* PTP Ingress FIFO has a new entry */
+	MLXSW_TRAP_ID_PTP_ING_FIFO = 0x2D,
+	/* PTP Egress FIFO has a new entry */
+	MLXSW_TRAP_ID_PTP_EGR_FIFO = 0x2E,
 };
 
 #endif /* _MLXSW_TRAP_H */
diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig
index b7e2f49696b7..90a8c6bead56 100644
--- a/drivers/net/ethernet/micrel/Kconfig
+++ b/drivers/net/ethernet/micrel/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Micrel device configuration
 #
diff --git a/drivers/net/ethernet/micrel/ks8695net.c b/drivers/net/ethernet/micrel/ks8695net.c
index b881f5d4a7f9..1390ef5323a2 100644
--- a/drivers/net/ethernet/micrel/ks8695net.c
+++ b/drivers/net/ethernet/micrel/ks8695net.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Micrel KS8695 (Centaur) Ethernet.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the GNU
- * General Public License for more details.
- *
  * Copyright 2008 Simtec Electronics
  *		  Daniel Silverstone <dsilvers@simtec.co.uk>
  *		  Vincent Sanders <vince@simtec.co.uk>
@@ -391,7 +382,7 @@ ks8695_tx_irq(int irq, void *dev_id)
 					 ksp->tx_buffers[buff_n].dma_ptr,
 					 ksp->tx_buffers[buff_n].length,
 					 DMA_TO_DEVICE);
-			dev_kfree_skb_irq(ksp->tx_buffers[buff_n].skb);
+			dev_consume_skb_irq(ksp->tx_buffers[buff_n].skb);
 			ksp->tx_buffers[buff_n].skb = NULL;
 			ksp->tx_ring_used--;
 		}
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index e3d7c74d47bb..ccd06702cc56 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * ks8842.c timberdale KS8842 ethernet driver
  * Copyright (c) 2009 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 /* Supports:
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index bd6e9014bc74..33305c9c5a62 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* drivers/net/ethernet/micrel/ks8851.c
  *
  * Copyright 2009 Simtec Electronics
  *	http://www.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -142,6 +139,12 @@ struct ks8851_net {
 
 static int msg_enable;
 
+/* SPI frame opcodes */
+#define KS_SPIOP_RD	(0x00)
+#define KS_SPIOP_WR	(0x40)
+#define KS_SPIOP_RXFIFO	(0x80)
+#define KS_SPIOP_TXFIFO	(0xC0)
+
 /* shift for byte-enable data */
 #define BYTE_EN(_x)	((_x) << 2)
 
@@ -419,8 +422,8 @@ static void ks8851_init_mac(struct ks8851_net *ks)
 	const u8 *mac_addr;
 
 	mac_addr = of_get_mac_address(ks->spidev->dev.of_node);
-	if (mac_addr) {
-		memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr)) {
+		ether_addr_copy(dev->dev_addr, mac_addr);
 		ks8851_write_mac_addr(dev);
 		return;
 	}
@@ -535,9 +538,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 		/* set dma read address */
 		ks8851_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI | 0x00);
 
-		/* start the packet dma process, and set auto-dequeue rx */
-		ks8851_wrreg16(ks, KS_RXQCR,
-			       ks->rc_rxqcr | RXQCR_SDA | RXQCR_ADRFE);
+		/* start DMA access */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 
 		if (rxlen > 4) {
 			unsigned int rxalign;
@@ -568,7 +570,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 			}
 		}
 
-		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
+		/* end DMA access and dequeue packet */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_RRXEF);
 	}
 }
 
@@ -785,6 +788,15 @@ static void ks8851_tx_work(struct work_struct *work)
 static int ks8851_net_open(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	int ret;
+
+	ret = request_threaded_irq(dev->irq, NULL, ks8851_irq,
+				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				   dev->name, ks);
+	if (ret < 0) {
+		netdev_err(dev, "failed to get irq\n");
+		return ret;
+	}
 
 	/* lock the card, even if we may not actually be doing anything
 	 * else at the moment */
@@ -849,6 +861,7 @@ static int ks8851_net_open(struct net_device *dev)
 	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
 
 	mutex_unlock(&ks->lock);
+	mii_check_link(&ks->mii);
 	return 0;
 }
 
@@ -899,6 +912,8 @@ static int ks8851_net_stop(struct net_device *dev)
 		dev_kfree_skb(txb);
 	}
 
+	free_irq(dev->irq, ks);
+
 	return 0;
 }
 
@@ -1508,6 +1523,7 @@ static int ks8851_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, ks);
 
+	netif_carrier_off(ks->netdev);
 	ndev->if_port = IF_PORT_100BASET;
 	ndev->netdev_ops = &ks8851_netdev_ops;
 	ndev->irq = spi->irq;
@@ -1529,14 +1545,6 @@ static int ks8851_probe(struct spi_device *spi)
 	ks8851_read_selftest(ks);
 	ks8851_init_mac(ks);
 
-	ret = request_threaded_irq(spi->irq, NULL, ks8851_irq,
-				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				   ndev->name, ks);
-	if (ret < 0) {
-		dev_err(&spi->dev, "failed to get irq\n");
-		goto err_irq;
-	}
-
 	ret = register_netdev(ndev);
 	if (ret) {
 		dev_err(&spi->dev, "failed to register network device\n");
@@ -1549,14 +1557,10 @@ static int ks8851_probe(struct spi_device *spi)
 
 	return 0;
 
-
 err_netdev:
-	free_irq(ndev->irq, ks);
-
-err_irq:
+err_id:
 	if (gpio_is_valid(gpio))
 		gpio_set_value(gpio, 0);
-err_id:
 	regulator_disable(ks->vdd_reg);
 err_reg:
 	regulator_disable(ks->vdd_io);
@@ -1574,7 +1578,6 @@ static int ks8851_remove(struct spi_device *spi)
 		dev_info(&spi->dev, "remove\n");
 
 	unregister_netdev(priv->netdev);
-	free_irq(spi->irq, priv);
 	if (gpio_is_valid(priv->gpio))
 		gpio_set_value(priv->gpio, 0);
 	regulator_disable(priv->vdd_reg);
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index 852256ef1f22..8f834aef8e32 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -1,19 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* drivers/net/ethernet/micrel/ks8851.h
  *
  * Copyright 2009 Simtec Electronics
  *      Ben Dooks <ben@simtec.co.uk>
  *
  * KS8851 register definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
 */
 
 #define KS_CCR					0x08
+#define CCR_LE					(1 << 10)   /* KSZ8851-16MLL */
 #define CCR_EEPROM				(1 << 9)
-#define CCR_SPI					(1 << 8)
-#define CCR_32PIN				(1 << 0)
+#define CCR_SPI					(1 << 8)    /* KSZ8851SNL    */
+#define CCR_8BIT				(1 << 7)    /* KSZ8851-16MLL */
+#define CCR_16BIT				(1 << 6)    /* KSZ8851-16MLL */
+#define CCR_32BIT				(1 << 5)    /* KSZ8851-16MLL */
+#define CCR_SHARED				(1 << 4)    /* KSZ8851-16MLL */
+#define CCR_48PIN				(1 << 1)    /* KSZ8851-16MLL */
+#define CCR_32PIN				(1 << 0)    /* KSZ8851SNL    */
 
 /* MAC address registers */
 #define KS_MAR(_m)				(0x15 - (_m))
@@ -112,13 +115,13 @@
 #define RXCR1_RXE				(1 << 0)
 
 #define KS_RXCR2				0x76
-#define RXCR2_SRDBL_MASK			(0x7 << 5)
-#define RXCR2_SRDBL_SHIFT			(5)
-#define RXCR2_SRDBL_4B				(0x0 << 5)
-#define RXCR2_SRDBL_8B				(0x1 << 5)
-#define RXCR2_SRDBL_16B				(0x2 << 5)
-#define RXCR2_SRDBL_32B				(0x3 << 5)
-#define RXCR2_SRDBL_FRAME			(0x4 << 5)
+#define RXCR2_SRDBL_MASK			(0x7 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_SHIFT			(5)	    /* KSZ8851SNL    */
+#define RXCR2_SRDBL_4B				(0x0 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_8B				(0x1 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_16B				(0x2 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_32B				(0x3 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_FRAME			(0x4 << 5)  /* KSZ8851SNL    */
 #define RXCR2_IUFFP				(1 << 4)
 #define RXCR2_RXIUFCEZ				(1 << 3)
 #define RXCR2_UDPLFE				(1 << 2)
@@ -143,8 +146,10 @@
 #define RXFSHR_RXCE				(1 << 0)
 
 #define KS_RXFHBCR				0x7E
+#define RXFHBCR_CNT_MASK			(0xfff << 0)
+
 #define KS_TXQCR				0x80
-#define TXQCR_AETFE				(1 << 2)
+#define TXQCR_AETFE				(1 << 2)    /* KSZ8851SNL    */
 #define TXQCR_TXQMAM				(1 << 1)
 #define TXQCR_METFE				(1 << 0)
 
@@ -167,6 +172,10 @@
 
 #define KS_RXFDPR				0x86
 #define RXFDPR_RXFPAI				(1 << 14)
+#define RXFDPR_WST				(1 << 12)   /* KSZ8851-16MLL */
+#define RXFDPR_EMS				(1 << 11)   /* KSZ8851-16MLL */
+#define RXFDPR_RXFP_MASK			(0x7ff << 0)
+#define RXFDPR_RXFP_SHIFT			(0)
 
 #define KS_RXDTTR				0x8C
 #define KS_RXDBCTR				0x8E
@@ -184,7 +193,7 @@
 #define IRQ_RXMPDI				(1 << 4)
 #define IRQ_LDI					(1 << 3)
 #define IRQ_EDI					(1 << 2)
-#define IRQ_SPIBEI				(1 << 1)
+#define IRQ_SPIBEI				(1 << 1)    /* KSZ8851SNL    */
 #define IRQ_DEDI				(1 << 0)
 
 #define KS_RXFCTR				0x9C
@@ -257,42 +266,37 @@
 #define KS_P1ANLPR				0xEE
 
 #define KS_P1SCLMD				0xF4
-#define P1SCLMD_LEDOFF				(1 << 15)
-#define P1SCLMD_TXIDS				(1 << 14)
-#define P1SCLMD_RESTARTAN			(1 << 13)
-#define P1SCLMD_DISAUTOMDIX			(1 << 10)
-#define P1SCLMD_FORCEMDIX			(1 << 9)
-#define P1SCLMD_AUTONEGEN			(1 << 7)
-#define P1SCLMD_FORCE100			(1 << 6)
-#define P1SCLMD_FORCEFDX			(1 << 5)
-#define P1SCLMD_ADV_FLOW			(1 << 4)
-#define P1SCLMD_ADV_100BT_FDX			(1 << 3)
-#define P1SCLMD_ADV_100BT_HDX			(1 << 2)
-#define P1SCLMD_ADV_10BT_FDX			(1 << 1)
-#define P1SCLMD_ADV_10BT_HDX			(1 << 0)
 
 #define KS_P1CR					0xF6
-#define P1CR_HP_MDIX				(1 << 15)
-#define P1CR_REV_POL				(1 << 13)
-#define P1CR_OP_100M				(1 << 10)
-#define P1CR_OP_FDX				(1 << 9)
-#define P1CR_OP_MDI				(1 << 7)
-#define P1CR_AN_DONE				(1 << 6)
-#define P1CR_LINK_GOOD				(1 << 5)
-#define P1CR_PNTR_FLOW				(1 << 4)
-#define P1CR_PNTR_100BT_FDX			(1 << 3)
-#define P1CR_PNTR_100BT_HDX			(1 << 2)
-#define P1CR_PNTR_10BT_FDX			(1 << 1)
-#define P1CR_PNTR_10BT_HDX			(1 << 0)
+#define P1CR_LEDOFF				(1 << 15)
+#define P1CR_TXIDS				(1 << 14)
+#define P1CR_RESTARTAN				(1 << 13)
+#define P1CR_DISAUTOMDIX			(1 << 10)
+#define P1CR_FORCEMDIX				(1 << 9)
+#define P1CR_AUTONEGEN				(1 << 7)
+#define P1CR_FORCE100				(1 << 6)
+#define P1CR_FORCEFDX				(1 << 5)
+#define P1CR_ADV_FLOW				(1 << 4)
+#define P1CR_ADV_100BT_FDX			(1 << 3)
+#define P1CR_ADV_100BT_HDX			(1 << 2)
+#define P1CR_ADV_10BT_FDX			(1 << 1)
+#define P1CR_ADV_10BT_HDX			(1 << 0)
+
+#define KS_P1SR					0xF8
+#define P1SR_HP_MDIX				(1 << 15)
+#define P1SR_REV_POL				(1 << 13)
+#define P1SR_OP_100M				(1 << 10)
+#define P1SR_OP_FDX				(1 << 9)
+#define P1SR_OP_MDI				(1 << 7)
+#define P1SR_AN_DONE				(1 << 6)
+#define P1SR_LINK_GOOD				(1 << 5)
+#define P1SR_PNTR_FLOW				(1 << 4)
+#define P1SR_PNTR_100BT_FDX			(1 << 3)
+#define P1SR_PNTR_100BT_HDX			(1 << 2)
+#define P1SR_PNTR_10BT_FDX			(1 << 1)
+#define P1SR_PNTR_10BT_HDX			(1 << 0)
 
 /* TX Frame control */
-
 #define TXFR_TXIC				(1 << 15)
 #define TXFR_TXFID_MASK				(0x3f << 0)
 #define TXFR_TXFID_SHIFT			(0)
-
-/* SPI frame opcodes */
-#define KS_SPIOP_RD				(0x00)
-#define KS_SPIOP_WR				(0x40)
-#define KS_SPIOP_RXFIFO				(0x80)
-#define KS_SPIOP_TXFIFO				(0xC0)
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index 35f8c9ef204d..e52b015e31a9 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /**
  * drivers/net/ethernet/micrel/ks8851_mll.c
  * Copyright (c) 2009 Micrel Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 /* Supports:
@@ -40,6 +28,8 @@
 #include <linux/of_device.h>
 #include <linux/of_net.h>
 
+#include "ks8851.h"
+
 #define	DRV_NAME	"ks8851_mll"
 
 static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
@@ -48,319 +38,10 @@ static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
 #define TX_BUF_SIZE			2000
 #define RX_BUF_SIZE			2000
 
-#define KS_CCR				0x08
-#define CCR_EEPROM			(1 << 9)
-#define CCR_SPI				(1 << 8)
-#define CCR_8BIT			(1 << 7)
-#define CCR_16BIT			(1 << 6)
-#define CCR_32BIT			(1 << 5)
-#define CCR_SHARED			(1 << 4)
-#define CCR_32PIN			(1 << 0)
-
-/* MAC address registers */
-#define KS_MARL				0x10
-#define KS_MARM				0x12
-#define KS_MARH				0x14
-
-#define KS_OBCR				0x20
-#define OBCR_ODS_16MA			(1 << 6)
-
-#define KS_EEPCR			0x22
-#define EEPCR_EESA			(1 << 4)
-#define EEPCR_EESB			(1 << 3)
-#define EEPCR_EEDO			(1 << 2)
-#define EEPCR_EESCK			(1 << 1)
-#define EEPCR_EECS			(1 << 0)
-
-#define KS_MBIR				0x24
-#define MBIR_TXMBF			(1 << 12)
-#define MBIR_TXMBFA			(1 << 11)
-#define MBIR_RXMBF			(1 << 4)
-#define MBIR_RXMBFA			(1 << 3)
-
-#define KS_GRR				0x26
-#define GRR_QMU				(1 << 1)
-#define GRR_GSR				(1 << 0)
-
-#define KS_WFCR				0x2A
-#define WFCR_MPRXE			(1 << 7)
-#define WFCR_WF3E			(1 << 3)
-#define WFCR_WF2E			(1 << 2)
-#define WFCR_WF1E			(1 << 1)
-#define WFCR_WF0E			(1 << 0)
-
-#define KS_WF0CRC0			0x30
-#define KS_WF0CRC1			0x32
-#define KS_WF0BM0			0x34
-#define KS_WF0BM1			0x36
-#define KS_WF0BM2			0x38
-#define KS_WF0BM3			0x3A
-
-#define KS_WF1CRC0			0x40
-#define KS_WF1CRC1			0x42
-#define KS_WF1BM0			0x44
-#define KS_WF1BM1			0x46
-#define KS_WF1BM2			0x48
-#define KS_WF1BM3			0x4A
-
-#define KS_WF2CRC0			0x50
-#define KS_WF2CRC1			0x52
-#define KS_WF2BM0			0x54
-#define KS_WF2BM1			0x56
-#define KS_WF2BM2			0x58
-#define KS_WF2BM3			0x5A
-
-#define KS_WF3CRC0			0x60
-#define KS_WF3CRC1			0x62
-#define KS_WF3BM0			0x64
-#define KS_WF3BM1			0x66
-#define KS_WF3BM2			0x68
-#define KS_WF3BM3			0x6A
-
-#define KS_TXCR				0x70
-#define TXCR_TCGICMP			(1 << 8)
-#define TXCR_TCGUDP			(1 << 7)
-#define TXCR_TCGTCP			(1 << 6)
-#define TXCR_TCGIP			(1 << 5)
-#define TXCR_FTXQ			(1 << 4)
-#define TXCR_TXFCE			(1 << 3)
-#define TXCR_TXPE			(1 << 2)
-#define TXCR_TXCRC			(1 << 1)
-#define TXCR_TXE			(1 << 0)
-
-#define KS_TXSR				0x72
-#define TXSR_TXLC			(1 << 13)
-#define TXSR_TXMC			(1 << 12)
-#define TXSR_TXFID_MASK			(0x3f << 0)
-#define TXSR_TXFID_SHIFT		(0)
-#define TXSR_TXFID_GET(_v)		(((_v) >> 0) & 0x3f)
-
-
-#define KS_RXCR1			0x74
-#define RXCR1_FRXQ			(1 << 15)
-#define RXCR1_RXUDPFCC			(1 << 14)
-#define RXCR1_RXTCPFCC			(1 << 13)
-#define RXCR1_RXIPFCC			(1 << 12)
-#define RXCR1_RXPAFMA			(1 << 11)
-#define RXCR1_RXFCE			(1 << 10)
-#define RXCR1_RXEFE			(1 << 9)
-#define RXCR1_RXMAFMA			(1 << 8)
-#define RXCR1_RXBE			(1 << 7)
-#define RXCR1_RXME			(1 << 6)
-#define RXCR1_RXUE			(1 << 5)
-#define RXCR1_RXAE			(1 << 4)
-#define RXCR1_RXINVF			(1 << 1)
-#define RXCR1_RXE			(1 << 0)
 #define RXCR1_FILTER_MASK    		(RXCR1_RXINVF | RXCR1_RXAE | \
 					 RXCR1_RXMAFMA | RXCR1_RXPAFMA)
-
-#define KS_RXCR2			0x76
-#define RXCR2_SRDBL_MASK		(0x7 << 5)
-#define RXCR2_SRDBL_SHIFT		(5)
-#define RXCR2_SRDBL_4B			(0x0 << 5)
-#define RXCR2_SRDBL_8B			(0x1 << 5)
-#define RXCR2_SRDBL_16B			(0x2 << 5)
-#define RXCR2_SRDBL_32B			(0x3 << 5)
-/* #define RXCR2_SRDBL_FRAME		(0x4 << 5) */
-#define RXCR2_IUFFP			(1 << 4)
-#define RXCR2_RXIUFCEZ			(1 << 3)
-#define RXCR2_UDPLFE			(1 << 2)
-#define RXCR2_RXICMPFCC			(1 << 1)
-#define RXCR2_RXSAF			(1 << 0)
-
-#define KS_TXMIR			0x78
-
-#define KS_RXFHSR			0x7C
-#define RXFSHR_RXFV			(1 << 15)
-#define RXFSHR_RXICMPFCS		(1 << 13)
-#define RXFSHR_RXIPFCS			(1 << 12)
-#define RXFSHR_RXTCPFCS			(1 << 11)
-#define RXFSHR_RXUDPFCS			(1 << 10)
-#define RXFSHR_RXBF			(1 << 7)
-#define RXFSHR_RXMF			(1 << 6)
-#define RXFSHR_RXUF			(1 << 5)
-#define RXFSHR_RXMR			(1 << 4)
-#define RXFSHR_RXFT			(1 << 3)
-#define RXFSHR_RXFTL			(1 << 2)
-#define RXFSHR_RXRF			(1 << 1)
-#define RXFSHR_RXCE			(1 << 0)
-#define	RXFSHR_ERR			(RXFSHR_RXCE | RXFSHR_RXRF |\
-					RXFSHR_RXFTL | RXFSHR_RXMR |\
-					RXFSHR_RXICMPFCS | RXFSHR_RXIPFCS |\
-					RXFSHR_RXTCPFCS)
-#define KS_RXFHBCR			0x7E
-#define RXFHBCR_CNT_MASK		0x0FFF
-
-#define KS_TXQCR			0x80
-#define TXQCR_AETFE			(1 << 2)
-#define TXQCR_TXQMAM			(1 << 1)
-#define TXQCR_METFE			(1 << 0)
-
-#define KS_RXQCR			0x82
-#define RXQCR_RXDTTS			(1 << 12)
-#define RXQCR_RXDBCTS			(1 << 11)
-#define RXQCR_RXFCTS			(1 << 10)
-#define RXQCR_RXIPHTOE			(1 << 9)
-#define RXQCR_RXDTTE			(1 << 7)
-#define RXQCR_RXDBCTE			(1 << 6)
-#define RXQCR_RXFCTE			(1 << 5)
-#define RXQCR_ADRFE			(1 << 4)
-#define RXQCR_SDA			(1 << 3)
-#define RXQCR_RRXEF			(1 << 0)
 #define RXQCR_CMD_CNTL                	(RXQCR_RXFCTE|RXQCR_ADRFE)
 
-#define KS_TXFDPR			0x84
-#define TXFDPR_TXFPAI			(1 << 14)
-#define TXFDPR_TXFP_MASK		(0x7ff << 0)
-#define TXFDPR_TXFP_SHIFT		(0)
-
-#define KS_RXFDPR			0x86
-#define RXFDPR_RXFPAI			(1 << 14)
-
-#define KS_RXDTTR			0x8C
-#define KS_RXDBCTR			0x8E
-
-#define KS_IER				0x90
-#define KS_ISR				0x92
-#define IRQ_LCI				(1 << 15)
-#define IRQ_TXI				(1 << 14)
-#define IRQ_RXI				(1 << 13)
-#define IRQ_RXOI			(1 << 11)
-#define IRQ_TXPSI			(1 << 9)
-#define IRQ_RXPSI			(1 << 8)
-#define IRQ_TXSAI			(1 << 6)
-#define IRQ_RXWFDI			(1 << 5)
-#define IRQ_RXMPDI			(1 << 4)
-#define IRQ_LDI				(1 << 3)
-#define IRQ_EDI				(1 << 2)
-#define IRQ_SPIBEI			(1 << 1)
-#define IRQ_DEDI			(1 << 0)
-
-#define KS_RXFCTR			0x9C
-#define RXFCTR_THRESHOLD_MASK     	0x00FF
-
-#define KS_RXFC				0x9D
-#define RXFCTR_RXFC_MASK		(0xff << 8)
-#define RXFCTR_RXFC_SHIFT		(8)
-#define RXFCTR_RXFC_GET(_v)		(((_v) >> 8) & 0xff)
-#define RXFCTR_RXFCT_MASK		(0xff << 0)
-#define RXFCTR_RXFCT_SHIFT		(0)
-
-#define KS_TXNTFSR			0x9E
-
-#define KS_MAHTR0			0xA0
-#define KS_MAHTR1			0xA2
-#define KS_MAHTR2			0xA4
-#define KS_MAHTR3			0xA6
-
-#define KS_FCLWR			0xB0
-#define KS_FCHWR			0xB2
-#define KS_FCOWR			0xB4
-
-#define KS_CIDER			0xC0
-#define CIDER_ID			0x8870
-#define CIDER_REV_MASK			(0x7 << 1)
-#define CIDER_REV_SHIFT			(1)
-#define CIDER_REV_GET(_v)		(((_v) >> 1) & 0x7)
-
-#define KS_CGCR				0xC6
-#define KS_IACR				0xC8
-#define IACR_RDEN			(1 << 12)
-#define IACR_TSEL_MASK			(0x3 << 10)
-#define IACR_TSEL_SHIFT			(10)
-#define IACR_TSEL_MIB			(0x3 << 10)
-#define IACR_ADDR_MASK			(0x1f << 0)
-#define IACR_ADDR_SHIFT			(0)
-
-#define KS_IADLR			0xD0
-#define KS_IAHDR			0xD2
-
-#define KS_PMECR			0xD4
-#define PMECR_PME_DELAY			(1 << 14)
-#define PMECR_PME_POL			(1 << 12)
-#define PMECR_WOL_WAKEUP		(1 << 11)
-#define PMECR_WOL_MAGICPKT		(1 << 10)
-#define PMECR_WOL_LINKUP		(1 << 9)
-#define PMECR_WOL_ENERGY		(1 << 8)
-#define PMECR_AUTO_WAKE_EN		(1 << 7)
-#define PMECR_WAKEUP_NORMAL		(1 << 6)
-#define PMECR_WKEVT_MASK		(0xf << 2)
-#define PMECR_WKEVT_SHIFT		(2)
-#define PMECR_WKEVT_GET(_v)		(((_v) >> 2) & 0xf)
-#define PMECR_WKEVT_ENERGY		(0x1 << 2)
-#define PMECR_WKEVT_LINK		(0x2 << 2)
-#define PMECR_WKEVT_MAGICPKT		(0x4 << 2)
-#define PMECR_WKEVT_FRAME		(0x8 << 2)
-#define PMECR_PM_MASK			(0x3 << 0)
-#define PMECR_PM_SHIFT			(0)
-#define PMECR_PM_NORMAL			(0x0 << 0)
-#define PMECR_PM_ENERGY			(0x1 << 0)
-#define PMECR_PM_SOFTDOWN		(0x2 << 0)
-#define PMECR_PM_POWERSAVE		(0x3 << 0)
-
-/* Standard MII PHY data */
-#define KS_P1MBCR			0xE4
-#define P1MBCR_FORCE_FDX		(1 << 8)
-
-#define KS_P1MBSR			0xE6
-#define P1MBSR_AN_COMPLETE		(1 << 5)
-#define P1MBSR_AN_CAPABLE		(1 << 3)
-#define P1MBSR_LINK_UP			(1 << 2)
-
-#define KS_PHY1ILR			0xE8
-#define KS_PHY1IHR			0xEA
-#define KS_P1ANAR			0xEC
-#define KS_P1ANLPR			0xEE
-
-#define KS_P1SCLMD			0xF4
-#define P1SCLMD_LEDOFF			(1 << 15)
-#define P1SCLMD_TXIDS			(1 << 14)
-#define P1SCLMD_RESTARTAN		(1 << 13)
-#define P1SCLMD_DISAUTOMDIX		(1 << 10)
-#define P1SCLMD_FORCEMDIX		(1 << 9)
-#define P1SCLMD_AUTONEGEN		(1 << 7)
-#define P1SCLMD_FORCE100		(1 << 6)
-#define P1SCLMD_FORCEFDX		(1 << 5)
-#define P1SCLMD_ADV_FLOW		(1 << 4)
-#define P1SCLMD_ADV_100BT_FDX		(1 << 3)
-#define P1SCLMD_ADV_100BT_HDX		(1 << 2)
-#define P1SCLMD_ADV_10BT_FDX		(1 << 1)
-#define P1SCLMD_ADV_10BT_HDX		(1 << 0)
-
-#define KS_P1CR				0xF6
-#define P1CR_HP_MDIX			(1 << 15)
-#define P1CR_REV_POL			(1 << 13)
-#define P1CR_OP_100M			(1 << 10)
-#define P1CR_OP_FDX			(1 << 9)
-#define P1CR_OP_MDI			(1 << 7)
-#define P1CR_AN_DONE			(1 << 6)
-#define P1CR_LINK_GOOD			(1 << 5)
-#define P1CR_PNTR_FLOW			(1 << 4)
-#define P1CR_PNTR_100BT_FDX		(1 << 3)
-#define P1CR_PNTR_100BT_HDX		(1 << 2)
-#define P1CR_PNTR_10BT_FDX		(1 << 1)
-#define P1CR_PNTR_10BT_HDX		(1 << 0)
-
-/* TX Frame control */
-
-#define TXFR_TXIC			(1 << 15)
-#define TXFR_TXFID_MASK			(0x3f << 0)
-#define TXFR_TXFID_SHIFT		(0)
-
-#define KS_P1SR				0xF8
-#define P1SR_HP_MDIX			(1 << 15)
-#define P1SR_REV_POL			(1 << 13)
-#define P1SR_OP_100M			(1 << 10)
-#define P1SR_OP_FDX			(1 << 9)
-#define P1SR_OP_MDI			(1 << 7)
-#define P1SR_AN_DONE			(1 << 6)
-#define P1SR_LINK_GOOD			(1 << 5)
-#define P1SR_PNTR_FLOW			(1 << 4)
-#define P1SR_PNTR_100BT_FDX		(1 << 3)
-#define P1SR_PNTR_100BT_HDX		(1 << 2)
-#define P1SR_PNTR_10BT_FDX		(1 << 1)
-#define P1SR_PNTR_10BT_HDX		(1 << 0)
-
 #define	ENUM_BUS_NONE			0
 #define	ENUM_BUS_8BIT			1
 #define	ENUM_BUS_16BIT			2
@@ -1475,7 +1156,7 @@ static void ks_setup(struct ks_net *ks)
 	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
 
 	/* Setup Receive Frame Threshold - 1 frame (RXFCTFC) */
-	ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_THRESHOLD_MASK);
+	ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_RXFCT_MASK);
 
 	/* Setup RxQ Command Control (RXQCR) */
 	ks->rc_rxqcr = RXQCR_CMD_CNTL;
@@ -1488,7 +1169,7 @@ static void ks_setup(struct ks_net *ks)
 	 */
 
 	w = ks_rdreg16(ks, KS_P1MBCR);
-	w &= ~P1MBCR_FORCE_FDX;
+	w &= ~BMCR_FULLDPLX;
 	ks_wrreg16(ks, KS_P1MBCR, w);
 
 	w = TXCR_TXFCE | TXCR_TXPE | TXCR_TXCRC | TXCR_TCGIP;
@@ -1629,13 +1310,13 @@ static int ks8851_probe(struct platform_device *pdev)
 	ks_setup_int(ks);
 
 	data = ks_rdreg16(ks, KS_OBCR);
-	ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16MA);
+	ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16mA);
 
 	/* overwriting the default MAC address */
 	if (pdev->dev.of_node) {
 		mac = of_get_mac_address(pdev->dev.of_node);
-		if (mac)
-			memcpy(ks->mac_addr, mac, ETH_ALEN);
+		if (!IS_ERR(mac))
+			ether_addr_copy(ks->mac_addr, mac);
 	} else {
 		struct ks8851_mll_platform_data *pdata;
 
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index ebbdfb908745..3103446f018c 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /**
  * drivers/net/ethernet/micrel/ksx884x.c - Micrel KSZ8841/2 PCI Ethernet driver
  *
  * Copyright (c) 2009-2010 Micrel, Inc.
  * 	Tristram Ha <Tristram.Ha@micrel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index cf1d49149cc8..45fe41f3d9f3 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Microchip network device configuration
 #
diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile
index 538926d2b43f..da603540ca57 100644
--- a/drivers/net/ethernet/microchip/Makefile
+++ b/drivers/net/ethernet/microchip/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Microchip network device drivers.
 #
diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c
index f6ecfa778660..0567e4f387a5 100644
--- a/drivers/net/ethernet/microchip/enc28j60.c
+++ b/drivers/net/ethernet/microchip/enc28j60.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Microchip ENC28J60 ethernet driver (MAC + PHY)
  *
@@ -5,11 +6,6 @@
  * Author: Claudio Lanconelli <lanconelli.claudio@eptar.com>
  * based on enc28j60.c written by David Anders for 2.4 kernel version
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  * $Id: enc28j60.c,v 1.22 2007/12/20 10:47:01 claudio Exp $
  */
 
@@ -18,9 +14,9 @@
 #include <linux/types.h>
 #include <linux/fcntl.h>
 #include <linux/interrupt.h>
+#include <linux/property.h>
 #include <linux/string.h>
 #include <linux/errno.h>
-#include <linux/init.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
@@ -28,7 +24,6 @@
 #include <linux/skbuff.h>
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
-#include <linux/of_net.h>
 
 #include "enc28j60_hw.h"
 
@@ -41,10 +36,11 @@
 	(NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN | NETIF_MSG_LINK)
 
 /* Buffer size required for the largest SPI transfer (i.e., reading a
- * frame). */
+ * frame).
+ */
 #define SPI_TRANSFER_BUF_LEN	(4 + MAX_FRAMELEN)
 
-#define TX_TIMEOUT	(4 * HZ)
+#define TX_TIMEOUT		(4 * HZ)
 
 /* Max TX retries in case of collision as suggested by errata datasheet */
 #define MAX_TX_RETRYCOUNT	16
@@ -83,11 +79,12 @@ static struct {
 
 /*
  * SPI read buffer
- * wait for the SPI transfer and copy received data to destination
+ * Wait for the SPI transfer and copy received data to destination.
  */
 static int
 spi_read_buf(struct enc28j60_net *priv, int len, u8 *data)
 {
+	struct device *dev = &priv->spi->dev;
 	u8 *rx_buf = priv->spi_transfer_buf + 4;
 	u8 *tx_buf = priv->spi_transfer_buf;
 	struct spi_transfer tx = {
@@ -113,8 +110,8 @@ spi_read_buf(struct enc28j60_net *priv, int len, u8 *data)
 		ret = msg.status;
 	}
 	if (ret && netif_msg_drv(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() failed: ret = %d\n",
-			__func__, ret);
+		dev_printk(KERN_DEBUG, dev, "%s() failed: ret = %d\n",
+			   __func__, ret);
 
 	return ret;
 }
@@ -122,9 +119,9 @@ spi_read_buf(struct enc28j60_net *priv, int len, u8 *data)
 /*
  * SPI write buffer
  */
-static int spi_write_buf(struct enc28j60_net *priv, int len,
-			 const u8 *data)
+static int spi_write_buf(struct enc28j60_net *priv, int len, const u8 *data)
 {
+	struct device *dev = &priv->spi->dev;
 	int ret;
 
 	if (len > SPI_TRANSFER_BUF_LEN - 1 || len <= 0)
@@ -134,8 +131,8 @@ static int spi_write_buf(struct enc28j60_net *priv, int len,
 		memcpy(&priv->spi_transfer_buf[1], data, len);
 		ret = spi_write(priv->spi, priv->spi_transfer_buf, len + 1);
 		if (ret && netif_msg_drv(priv))
-			printk(KERN_DEBUG DRV_NAME ": %s() failed: ret = %d\n",
-				__func__, ret);
+			dev_printk(KERN_DEBUG, dev, "%s() failed: ret = %d\n",
+				   __func__, ret);
 	}
 	return ret;
 }
@@ -143,9 +140,9 @@ static int spi_write_buf(struct enc28j60_net *priv, int len,
 /*
  * basic SPI read operation
  */
-static u8 spi_read_op(struct enc28j60_net *priv, u8 op,
-			   u8 addr)
+static u8 spi_read_op(struct enc28j60_net *priv, u8 op, u8 addr)
 {
+	struct device *dev = &priv->spi->dev;
 	u8 tx_buf[2];
 	u8 rx_buf[4];
 	u8 val = 0;
@@ -159,8 +156,8 @@ static u8 spi_read_op(struct enc28j60_net *priv, u8 op,
 	tx_buf[0] = op | (addr & ADDR_MASK);
 	ret = spi_write_then_read(priv->spi, tx_buf, 1, rx_buf, slen);
 	if (ret)
-		printk(KERN_DEBUG DRV_NAME ": %s() failed: ret = %d\n",
-			__func__, ret);
+		dev_printk(KERN_DEBUG, dev, "%s() failed: ret = %d\n",
+			   __func__, ret);
 	else
 		val = rx_buf[slen - 1];
 
@@ -170,28 +167,25 @@ static u8 spi_read_op(struct enc28j60_net *priv, u8 op,
 /*
  * basic SPI write operation
  */
-static int spi_write_op(struct enc28j60_net *priv, u8 op,
-			u8 addr, u8 val)
+static int spi_write_op(struct enc28j60_net *priv, u8 op, u8 addr, u8 val)
 {
+	struct device *dev = &priv->spi->dev;
 	int ret;
 
 	priv->spi_transfer_buf[0] = op | (addr & ADDR_MASK);
 	priv->spi_transfer_buf[1] = val;
 	ret = spi_write(priv->spi, priv->spi_transfer_buf, 2);
 	if (ret && netif_msg_drv(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() failed: ret = %d\n",
-			__func__, ret);
+		dev_printk(KERN_DEBUG, dev, "%s() failed: ret = %d\n",
+			   __func__, ret);
 	return ret;
 }
 
 static void enc28j60_soft_reset(struct enc28j60_net *priv)
 {
-	if (netif_msg_hw(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() enter\n", __func__);
-
 	spi_write_op(priv, ENC28J60_SOFT_RESET, 0, ENC28J60_SOFT_RESET);
 	/* Errata workaround #1, CLKRDY check is unreliable,
-	 * delay at least 1 mS instead */
+	 * delay at least 1 ms instead */
 	udelay(2000);
 }
 
@@ -203,7 +197,7 @@ static void enc28j60_set_bank(struct enc28j60_net *priv, u8 addr)
 	u8 b = (addr & BANK_MASK) >> 5;
 
 	/* These registers (EIE, EIR, ESTAT, ECON2, ECON1)
-	 * are present in all banks, no need to switch bank
+	 * are present in all banks, no need to switch bank.
 	 */
 	if (addr >= EIE && addr <= ECON1)
 		return;
@@ -242,15 +236,13 @@ static void enc28j60_set_bank(struct enc28j60_net *priv, u8 addr)
 /*
  * Register bit field Set
  */
-static void nolock_reg_bfset(struct enc28j60_net *priv,
-				      u8 addr, u8 mask)
+static void nolock_reg_bfset(struct enc28j60_net *priv, u8 addr, u8 mask)
 {
 	enc28j60_set_bank(priv, addr);
 	spi_write_op(priv, ENC28J60_BIT_FIELD_SET, addr, mask);
 }
 
-static void locked_reg_bfset(struct enc28j60_net *priv,
-				      u8 addr, u8 mask)
+static void locked_reg_bfset(struct enc28j60_net *priv, u8 addr, u8 mask)
 {
 	mutex_lock(&priv->lock);
 	nolock_reg_bfset(priv, addr, mask);
@@ -260,15 +252,13 @@ static void locked_reg_bfset(struct enc28j60_net *priv,
 /*
  * Register bit field Clear
  */
-static void nolock_reg_bfclr(struct enc28j60_net *priv,
-				      u8 addr, u8 mask)
+static void nolock_reg_bfclr(struct enc28j60_net *priv, u8 addr, u8 mask)
 {
 	enc28j60_set_bank(priv, addr);
 	spi_write_op(priv, ENC28J60_BIT_FIELD_CLR, addr, mask);
 }
 
-static void locked_reg_bfclr(struct enc28j60_net *priv,
-				      u8 addr, u8 mask)
+static void locked_reg_bfclr(struct enc28j60_net *priv, u8 addr, u8 mask)
 {
 	mutex_lock(&priv->lock);
 	nolock_reg_bfclr(priv, addr, mask);
@@ -278,15 +268,13 @@ static void locked_reg_bfclr(struct enc28j60_net *priv,
 /*
  * Register byte read
  */
-static int nolock_regb_read(struct enc28j60_net *priv,
-				     u8 address)
+static int nolock_regb_read(struct enc28j60_net *priv, u8 address)
 {
 	enc28j60_set_bank(priv, address);
 	return spi_read_op(priv, ENC28J60_READ_CTRL_REG, address);
 }
 
-static int locked_regb_read(struct enc28j60_net *priv,
-				     u8 address)
+static int locked_regb_read(struct enc28j60_net *priv, u8 address)
 {
 	int ret;
 
@@ -300,8 +288,7 @@ static int locked_regb_read(struct enc28j60_net *priv,
 /*
  * Register word read
  */
-static int nolock_regw_read(struct enc28j60_net *priv,
-				     u8 address)
+static int nolock_regw_read(struct enc28j60_net *priv, u8 address)
 {
 	int rl, rh;
 
@@ -312,8 +299,7 @@ static int nolock_regw_read(struct enc28j60_net *priv,
 	return (rh << 8) | rl;
 }
 
-static int locked_regw_read(struct enc28j60_net *priv,
-				     u8 address)
+static int locked_regw_read(struct enc28j60_net *priv, u8 address)
 {
 	int ret;
 
@@ -327,15 +313,13 @@ static int locked_regw_read(struct enc28j60_net *priv,
 /*
  * Register byte write
  */
-static void nolock_regb_write(struct enc28j60_net *priv,
-				       u8 address, u8 data)
+static void nolock_regb_write(struct enc28j60_net *priv, u8 address, u8 data)
 {
 	enc28j60_set_bank(priv, address);
 	spi_write_op(priv, ENC28J60_WRITE_CTRL_REG, address, data);
 }
 
-static void locked_regb_write(struct enc28j60_net *priv,
-				       u8 address, u8 data)
+static void locked_regb_write(struct enc28j60_net *priv, u8 address, u8 data)
 {
 	mutex_lock(&priv->lock);
 	nolock_regb_write(priv, address, data);
@@ -345,8 +329,7 @@ static void locked_regb_write(struct enc28j60_net *priv,
 /*
  * Register word write
  */
-static void nolock_regw_write(struct enc28j60_net *priv,
-				       u8 address, u16 data)
+static void nolock_regw_write(struct enc28j60_net *priv, u8 address, u16 data)
 {
 	enc28j60_set_bank(priv, address);
 	spi_write_op(priv, ENC28J60_WRITE_CTRL_REG, address, (u8) data);
@@ -354,8 +337,7 @@ static void nolock_regw_write(struct enc28j60_net *priv,
 		     (u8) (data >> 8));
 }
 
-static void locked_regw_write(struct enc28j60_net *priv,
-				       u8 address, u16 data)
+static void locked_regw_write(struct enc28j60_net *priv, u8 address, u16 data)
 {
 	mutex_lock(&priv->lock);
 	nolock_regw_write(priv, address, data);
@@ -364,20 +346,23 @@ static void locked_regw_write(struct enc28j60_net *priv,
 
 /*
  * Buffer memory read
- * Select the starting address and execute a SPI buffer read
+ * Select the starting address and execute a SPI buffer read.
  */
-static void enc28j60_mem_read(struct enc28j60_net *priv,
-				     u16 addr, int len, u8 *data)
+static void enc28j60_mem_read(struct enc28j60_net *priv, u16 addr, int len,
+			      u8 *data)
 {
 	mutex_lock(&priv->lock);
 	nolock_regw_write(priv, ERDPTL, addr);
 #ifdef CONFIG_ENC28J60_WRITEVERIFY
 	if (netif_msg_drv(priv)) {
+		struct device *dev = &priv->spi->dev;
 		u16 reg;
+
 		reg = nolock_regw_read(priv, ERDPTL);
 		if (reg != addr)
-			printk(KERN_DEBUG DRV_NAME ": %s() error writing ERDPT "
-				"(0x%04x - 0x%04x)\n", __func__, reg, addr);
+			dev_printk(KERN_DEBUG, dev,
+				   "%s() error writing ERDPT (0x%04x - 0x%04x)\n",
+				   __func__, reg, addr);
 	}
 #endif
 	spi_read_buf(priv, len, data);
@@ -390,6 +375,8 @@ static void enc28j60_mem_read(struct enc28j60_net *priv,
 static void
 enc28j60_packet_write(struct enc28j60_net *priv, int len, const u8 *data)
 {
+	struct device *dev = &priv->spi->dev;
+
 	mutex_lock(&priv->lock);
 	/* Set the write pointer to start of transmit buffer area */
 	nolock_regw_write(priv, EWRPTL, TXSTART_INIT);
@@ -398,9 +385,9 @@ enc28j60_packet_write(struct enc28j60_net *priv, int len, const u8 *data)
 		u16 reg;
 		reg = nolock_regw_read(priv, EWRPTL);
 		if (reg != TXSTART_INIT)
-			printk(KERN_DEBUG DRV_NAME
-				": %s() ERWPT:0x%04x != 0x%04x\n",
-				__func__, reg, TXSTART_INIT);
+			dev_printk(KERN_DEBUG, dev,
+				   "%s() ERWPT:0x%04x != 0x%04x\n",
+				   __func__, reg, TXSTART_INIT);
 	}
 #endif
 	/* Set the TXND pointer to correspond to the packet size given */
@@ -408,30 +395,28 @@ enc28j60_packet_write(struct enc28j60_net *priv, int len, const u8 *data)
 	/* write per-packet control byte */
 	spi_write_op(priv, ENC28J60_WRITE_BUF_MEM, 0, 0x00);
 	if (netif_msg_hw(priv))
-		printk(KERN_DEBUG DRV_NAME
-			": %s() after control byte ERWPT:0x%04x\n",
-			__func__, nolock_regw_read(priv, EWRPTL));
+		dev_printk(KERN_DEBUG, dev,
+			   "%s() after control byte ERWPT:0x%04x\n",
+			   __func__, nolock_regw_read(priv, EWRPTL));
 	/* copy the packet into the transmit buffer */
 	spi_write_buf(priv, len, data);
 	if (netif_msg_hw(priv))
-		printk(KERN_DEBUG DRV_NAME
-			 ": %s() after write packet ERWPT:0x%04x, len=%d\n",
-			 __func__, nolock_regw_read(priv, EWRPTL), len);
+		dev_printk(KERN_DEBUG, dev,
+			   "%s() after write packet ERWPT:0x%04x, len=%d\n",
+			   __func__, nolock_regw_read(priv, EWRPTL), len);
 	mutex_unlock(&priv->lock);
 }
 
-static unsigned long msec20_to_jiffies;
-
 static int poll_ready(struct enc28j60_net *priv, u8 reg, u8 mask, u8 val)
 {
-	unsigned long timeout = jiffies + msec20_to_jiffies;
+	struct device *dev = &priv->spi->dev;
+	unsigned long timeout = jiffies + msecs_to_jiffies(20);
 
 	/* 20 msec timeout read */
 	while ((nolock_regb_read(priv, reg) & mask) != val) {
 		if (time_after(jiffies, timeout)) {
 			if (netif_msg_drv(priv))
-				dev_dbg(&priv->spi->dev,
-					"reg %02x ready timeout!\n", reg);
+				dev_dbg(dev, "reg %02x ready timeout!\n", reg);
 			return -ETIMEDOUT;
 		}
 		cpu_relax();
@@ -449,7 +434,7 @@ static int wait_phy_ready(struct enc28j60_net *priv)
 
 /*
  * PHY register read
- * PHY registers are not accessed directly, but through the MII
+ * PHY registers are not accessed directly, but through the MII.
  */
 static u16 enc28j60_phy_read(struct enc28j60_net *priv, u8 address)
 {
@@ -465,7 +450,7 @@ static u16 enc28j60_phy_read(struct enc28j60_net *priv, u8 address)
 	/* quit reading */
 	nolock_regb_write(priv, MICMD, 0x00);
 	/* return the data */
-	ret  = nolock_regw_read(priv, MIRDL);
+	ret = nolock_regw_read(priv, MIRDL);
 	mutex_unlock(&priv->lock);
 
 	return ret;
@@ -494,13 +479,13 @@ static int enc28j60_set_hw_macaddr(struct net_device *ndev)
 {
 	int ret;
 	struct enc28j60_net *priv = netdev_priv(ndev);
+	struct device *dev = &priv->spi->dev;
 
 	mutex_lock(&priv->lock);
 	if (!priv->hw_enable) {
 		if (netif_msg_drv(priv))
-			printk(KERN_INFO DRV_NAME
-				": %s: Setting MAC address to %pM\n",
-				ndev->name, ndev->dev_addr);
+			dev_info(dev, "%s: Setting MAC address to %pM\n",
+				 ndev->name, ndev->dev_addr);
 		/* NOTE: MAC address in ENC28J60 is byte-backward */
 		nolock_regb_write(priv, MAADR5, ndev->dev_addr[0]);
 		nolock_regb_write(priv, MAADR4, ndev->dev_addr[1]);
@@ -511,9 +496,9 @@ static int enc28j60_set_hw_macaddr(struct net_device *ndev)
 		ret = 0;
 	} else {
 		if (netif_msg_drv(priv))
-			printk(KERN_DEBUG DRV_NAME
-				": %s() Hardware must be disabled to set "
-				"Mac address\n", __func__);
+			dev_printk(KERN_DEBUG, dev,
+				   "%s() Hardware must be disabled to set Mac address\n",
+				   __func__);
 		ret = -EBUSY;
 	}
 	mutex_unlock(&priv->lock);
@@ -532,7 +517,7 @@ static int enc28j60_set_mac_address(struct net_device *dev, void *addr)
 	if (!is_valid_ether_addr(address->sa_data))
 		return -EADDRNOTAVAIL;
 
-	memcpy(dev->dev_addr, address->sa_data, dev->addr_len);
+	ether_addr_copy(dev->dev_addr, address->sa_data);
 	return enc28j60_set_hw_macaddr(dev);
 }
 
@@ -541,33 +526,36 @@ static int enc28j60_set_mac_address(struct net_device *dev, void *addr)
  */
 static void enc28j60_dump_regs(struct enc28j60_net *priv, const char *msg)
 {
+	struct device *dev = &priv->spi->dev;
+
 	mutex_lock(&priv->lock);
-	printk(KERN_DEBUG DRV_NAME " %s\n"
-		"HwRevID: 0x%02x\n"
-		"Cntrl: ECON1 ECON2 ESTAT  EIR  EIE\n"
-		"       0x%02x  0x%02x  0x%02x  0x%02x  0x%02x\n"
-		"MAC  : MACON1 MACON3 MACON4\n"
-		"       0x%02x   0x%02x   0x%02x\n"
-		"Rx   : ERXST  ERXND  ERXWRPT ERXRDPT ERXFCON EPKTCNT MAMXFL\n"
-		"       0x%04x 0x%04x 0x%04x  0x%04x  "
-		"0x%02x    0x%02x    0x%04x\n"
-		"Tx   : ETXST  ETXND  MACLCON1 MACLCON2 MAPHSUP\n"
-		"       0x%04x 0x%04x 0x%02x     0x%02x     0x%02x\n",
-		msg, nolock_regb_read(priv, EREVID),
-		nolock_regb_read(priv, ECON1), nolock_regb_read(priv, ECON2),
-		nolock_regb_read(priv, ESTAT), nolock_regb_read(priv, EIR),
-		nolock_regb_read(priv, EIE), nolock_regb_read(priv, MACON1),
-		nolock_regb_read(priv, MACON3), nolock_regb_read(priv, MACON4),
-		nolock_regw_read(priv, ERXSTL), nolock_regw_read(priv, ERXNDL),
-		nolock_regw_read(priv, ERXWRPTL),
-		nolock_regw_read(priv, ERXRDPTL),
-		nolock_regb_read(priv, ERXFCON),
-		nolock_regb_read(priv, EPKTCNT),
-		nolock_regw_read(priv, MAMXFLL), nolock_regw_read(priv, ETXSTL),
-		nolock_regw_read(priv, ETXNDL),
-		nolock_regb_read(priv, MACLCON1),
-		nolock_regb_read(priv, MACLCON2),
-		nolock_regb_read(priv, MAPHSUP));
+	dev_printk(KERN_DEBUG, dev,
+		   " %s\n"
+		   "HwRevID: 0x%02x\n"
+		   "Cntrl: ECON1 ECON2 ESTAT  EIR  EIE\n"
+		   "       0x%02x  0x%02x  0x%02x  0x%02x  0x%02x\n"
+		   "MAC  : MACON1 MACON3 MACON4\n"
+		   "       0x%02x   0x%02x   0x%02x\n"
+		   "Rx   : ERXST  ERXND  ERXWRPT ERXRDPT ERXFCON EPKTCNT MAMXFL\n"
+		   "       0x%04x 0x%04x 0x%04x  0x%04x  "
+		   "0x%02x    0x%02x    0x%04x\n"
+		   "Tx   : ETXST  ETXND  MACLCON1 MACLCON2 MAPHSUP\n"
+		   "       0x%04x 0x%04x 0x%02x     0x%02x     0x%02x\n",
+		   msg, nolock_regb_read(priv, EREVID),
+		   nolock_regb_read(priv, ECON1), nolock_regb_read(priv, ECON2),
+		   nolock_regb_read(priv, ESTAT), nolock_regb_read(priv, EIR),
+		   nolock_regb_read(priv, EIE), nolock_regb_read(priv, MACON1),
+		   nolock_regb_read(priv, MACON3), nolock_regb_read(priv, MACON4),
+		   nolock_regw_read(priv, ERXSTL), nolock_regw_read(priv, ERXNDL),
+		   nolock_regw_read(priv, ERXWRPTL),
+		   nolock_regw_read(priv, ERXRDPTL),
+		   nolock_regb_read(priv, ERXFCON),
+		   nolock_regb_read(priv, EPKTCNT),
+		   nolock_regw_read(priv, MAMXFLL), nolock_regw_read(priv, ETXSTL),
+		   nolock_regw_read(priv, ETXNDL),
+		   nolock_regb_read(priv, MACLCON1),
+		   nolock_regb_read(priv, MACLCON2),
+		   nolock_regb_read(priv, MAPHSUP));
 	mutex_unlock(&priv->lock);
 }
 
@@ -599,12 +587,13 @@ static u16 rx_packet_start(u16 ptr)
 
 static void nolock_rxfifo_init(struct enc28j60_net *priv, u16 start, u16 end)
 {
+	struct device *dev = &priv->spi->dev;
 	u16 erxrdpt;
 
 	if (start > 0x1FFF || end > 0x1FFF || start > end) {
 		if (netif_msg_drv(priv))
-			printk(KERN_ERR DRV_NAME ": %s(%d, %d) RXFIFO "
-				"bad parameters!\n", __func__, start, end);
+			dev_err(dev, "%s(%d, %d) RXFIFO bad parameters!\n",
+				__func__, start, end);
 		return;
 	}
 	/* set receive buffer start + end */
@@ -617,10 +606,12 @@ static void nolock_rxfifo_init(struct enc28j60_net *priv, u16 start, u16 end)
 
 static void nolock_txfifo_init(struct enc28j60_net *priv, u16 start, u16 end)
 {
+	struct device *dev = &priv->spi->dev;
+
 	if (start > 0x1FFF || end > 0x1FFF || start > end) {
 		if (netif_msg_drv(priv))
-			printk(KERN_ERR DRV_NAME ": %s(%d, %d) TXFIFO "
-				"bad parameters!\n", __func__, start, end);
+			dev_err(dev, "%s(%d, %d) TXFIFO bad parameters!\n",
+				__func__, start, end);
 		return;
 	}
 	/* set transmit buffer start + end */
@@ -630,14 +621,15 @@ static void nolock_txfifo_init(struct enc28j60_net *priv, u16 start, u16 end)
 
 /*
  * Low power mode shrinks power consumption about 100x, so we'd like
- * the chip to be in that mode whenever it's inactive.  (However, we
- * can't stay in lowpower mode during suspend with WOL active.)
+ * the chip to be in that mode whenever it's inactive. (However, we
+ * can't stay in low power mode during suspend with WOL active.)
  */
 static void enc28j60_lowpower(struct enc28j60_net *priv, bool is_low)
 {
+	struct device *dev = &priv->spi->dev;
+
 	if (netif_msg_drv(priv))
-		dev_dbg(&priv->spi->dev, "%s power...\n",
-				is_low ? "low" : "high");
+		dev_dbg(dev, "%s power...\n", is_low ? "low" : "high");
 
 	mutex_lock(&priv->lock);
 	if (is_low) {
@@ -656,11 +648,12 @@ static void enc28j60_lowpower(struct enc28j60_net *priv, bool is_low)
 
 static int enc28j60_hw_init(struct enc28j60_net *priv)
 {
+	struct device *dev = &priv->spi->dev;
 	u8 reg;
 
 	if (netif_msg_drv(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() - %s\n", __func__,
-			priv->full_duplex ? "FullDuplex" : "HalfDuplex");
+		dev_printk(KERN_DEBUG, dev, "%s() - %s\n", __func__,
+			   priv->full_duplex ? "FullDuplex" : "HalfDuplex");
 
 	mutex_lock(&priv->lock);
 	/* first reset the chip */
@@ -682,15 +675,15 @@ static int enc28j60_hw_init(struct enc28j60_net *priv)
 	/*
 	 * Check the RevID.
 	 * If it's 0x00 or 0xFF probably the enc28j60 is not mounted or
-	 * damaged
+	 * damaged.
 	 */
 	reg = locked_regb_read(priv, EREVID);
 	if (netif_msg_drv(priv))
-		printk(KERN_INFO DRV_NAME ": chip RevID: 0x%02x\n", reg);
+		dev_info(dev, "chip RevID: 0x%02x\n", reg);
 	if (reg == 0x00 || reg == 0xff) {
 		if (netif_msg_drv(priv))
-			printk(KERN_DEBUG DRV_NAME ": %s() Invalid RevId %d\n",
-				__func__, reg);
+			dev_printk(KERN_DEBUG, dev, "%s() Invalid RevId %d\n",
+				   __func__, reg);
 		return 0;
 	}
 
@@ -723,7 +716,7 @@ static int enc28j60_hw_init(struct enc28j60_net *priv)
 	/*
 	 * MACLCON1 (default)
 	 * MACLCON2 (default)
-	 * Set the maximum packet size which the controller will accept
+	 * Set the maximum packet size which the controller will accept.
 	 */
 	locked_regw_write(priv, MAMXFLL, MAX_FRAMELEN);
 
@@ -750,10 +743,12 @@ static int enc28j60_hw_init(struct enc28j60_net *priv)
 
 static void enc28j60_hw_enable(struct enc28j60_net *priv)
 {
+	struct device *dev = &priv->spi->dev;
+
 	/* enable interrupts */
 	if (netif_msg_hw(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() enabling interrupts.\n",
-			__func__);
+		dev_printk(KERN_DEBUG, dev, "%s() enabling interrupts.\n",
+			   __func__);
 
 	enc28j60_phy_write(priv, PHIE, PHIE_PGEIE | PHIE_PLNKIE);
 
@@ -772,7 +767,7 @@ static void enc28j60_hw_enable(struct enc28j60_net *priv)
 static void enc28j60_hw_disable(struct enc28j60_net *priv)
 {
 	mutex_lock(&priv->lock);
-	/* disable interrutps and packet reception */
+	/* disable interrupts and packet reception */
 	nolock_regb_write(priv, EIE, 0x00);
 	nolock_reg_bfclr(priv, ECON1, ECON1_RXEN);
 	priv->hw_enable = false;
@@ -793,14 +788,12 @@ enc28j60_setlink(struct net_device *ndev, u8 autoneg, u16 speed, u8 duplex)
 			priv->full_duplex = (duplex == DUPLEX_FULL);
 		else {
 			if (netif_msg_link(priv))
-				dev_warn(&ndev->dev,
-					"unsupported link setting\n");
+				netdev_warn(ndev, "unsupported link setting\n");
 			ret = -EOPNOTSUPP;
 		}
 	} else {
 		if (netif_msg_link(priv))
-			dev_warn(&ndev->dev, "Warning: hw must be disabled "
-				"to set link mode\n");
+			netdev_warn(ndev, "Warning: hw must be disabled to set link mode\n");
 		ret = -EBUSY;
 	}
 	return ret;
@@ -811,21 +804,23 @@ enc28j60_setlink(struct net_device *ndev, u8 autoneg, u16 speed, u8 duplex)
  */
 static void enc28j60_read_tsv(struct enc28j60_net *priv, u8 tsv[TSV_SIZE])
 {
+	struct device *dev = &priv->spi->dev;
 	int endptr;
 
 	endptr = locked_regw_read(priv, ETXNDL);
 	if (netif_msg_hw(priv))
-		printk(KERN_DEBUG DRV_NAME ": reading TSV at addr:0x%04x\n",
-			 endptr + 1);
+		dev_printk(KERN_DEBUG, dev, "reading TSV at addr:0x%04x\n",
+			   endptr + 1);
 	enc28j60_mem_read(priv, endptr + 1, TSV_SIZE, tsv);
 }
 
 static void enc28j60_dump_tsv(struct enc28j60_net *priv, const char *msg,
-				u8 tsv[TSV_SIZE])
+			      u8 tsv[TSV_SIZE])
 {
+	struct device *dev = &priv->spi->dev;
 	u16 tmp1, tmp2;
 
-	printk(KERN_DEBUG DRV_NAME ": %s - TSV:\n", msg);
+	dev_printk(KERN_DEBUG, dev, "%s - TSV:\n", msg);
 	tmp1 = tsv[1];
 	tmp1 <<= 8;
 	tmp1 |= tsv[0];
@@ -834,30 +829,32 @@ static void enc28j60_dump_tsv(struct enc28j60_net *priv, const char *msg,
 	tmp2 <<= 8;
 	tmp2 |= tsv[4];
 
-	printk(KERN_DEBUG DRV_NAME ": ByteCount: %d, CollisionCount: %d,"
-		" TotByteOnWire: %d\n", tmp1, tsv[2] & 0x0f, tmp2);
-	printk(KERN_DEBUG DRV_NAME ": TxDone: %d, CRCErr:%d, LenChkErr: %d,"
-		" LenOutOfRange: %d\n", TSV_GETBIT(tsv, TSV_TXDONE),
-		TSV_GETBIT(tsv, TSV_TXCRCERROR),
-		TSV_GETBIT(tsv, TSV_TXLENCHKERROR),
-		TSV_GETBIT(tsv, TSV_TXLENOUTOFRANGE));
-	printk(KERN_DEBUG DRV_NAME ": Multicast: %d, Broadcast: %d, "
-		"PacketDefer: %d, ExDefer: %d\n",
-		TSV_GETBIT(tsv, TSV_TXMULTICAST),
-		TSV_GETBIT(tsv, TSV_TXBROADCAST),
-		TSV_GETBIT(tsv, TSV_TXPACKETDEFER),
-		TSV_GETBIT(tsv, TSV_TXEXDEFER));
-	printk(KERN_DEBUG DRV_NAME ": ExCollision: %d, LateCollision: %d, "
-		 "Giant: %d, Underrun: %d\n",
-		 TSV_GETBIT(tsv, TSV_TXEXCOLLISION),
-		 TSV_GETBIT(tsv, TSV_TXLATECOLLISION),
-		 TSV_GETBIT(tsv, TSV_TXGIANT), TSV_GETBIT(tsv, TSV_TXUNDERRUN));
-	printk(KERN_DEBUG DRV_NAME ": ControlFrame: %d, PauseFrame: %d, "
-		 "BackPressApp: %d, VLanTagFrame: %d\n",
-		 TSV_GETBIT(tsv, TSV_TXCONTROLFRAME),
-		 TSV_GETBIT(tsv, TSV_TXPAUSEFRAME),
-		 TSV_GETBIT(tsv, TSV_BACKPRESSUREAPP),
-		 TSV_GETBIT(tsv, TSV_TXVLANTAGFRAME));
+	dev_printk(KERN_DEBUG, dev,
+		   "ByteCount: %d, CollisionCount: %d, TotByteOnWire: %d\n",
+		   tmp1, tsv[2] & 0x0f, tmp2);
+	dev_printk(KERN_DEBUG, dev,
+		   "TxDone: %d, CRCErr:%d, LenChkErr: %d, LenOutOfRange: %d\n",
+		   TSV_GETBIT(tsv, TSV_TXDONE),
+		   TSV_GETBIT(tsv, TSV_TXCRCERROR),
+		   TSV_GETBIT(tsv, TSV_TXLENCHKERROR),
+		   TSV_GETBIT(tsv, TSV_TXLENOUTOFRANGE));
+	dev_printk(KERN_DEBUG, dev,
+		   "Multicast: %d, Broadcast: %d, PacketDefer: %d, ExDefer: %d\n",
+		   TSV_GETBIT(tsv, TSV_TXMULTICAST),
+		   TSV_GETBIT(tsv, TSV_TXBROADCAST),
+		   TSV_GETBIT(tsv, TSV_TXPACKETDEFER),
+		   TSV_GETBIT(tsv, TSV_TXEXDEFER));
+	dev_printk(KERN_DEBUG, dev,
+		   "ExCollision: %d, LateCollision: %d, Giant: %d, Underrun: %d\n",
+		   TSV_GETBIT(tsv, TSV_TXEXCOLLISION),
+		   TSV_GETBIT(tsv, TSV_TXLATECOLLISION),
+		   TSV_GETBIT(tsv, TSV_TXGIANT), TSV_GETBIT(tsv, TSV_TXUNDERRUN));
+	dev_printk(KERN_DEBUG, dev,
+		   "ControlFrame: %d, PauseFrame: %d, BackPressApp: %d, VLanTagFrame: %d\n",
+		   TSV_GETBIT(tsv, TSV_TXCONTROLFRAME),
+		   TSV_GETBIT(tsv, TSV_TXPAUSEFRAME),
+		   TSV_GETBIT(tsv, TSV_BACKPRESSUREAPP),
+		   TSV_GETBIT(tsv, TSV_TXVLANTAGFRAME));
 }
 
 /*
@@ -866,27 +863,29 @@ static void enc28j60_dump_tsv(struct enc28j60_net *priv, const char *msg,
 static void enc28j60_dump_rsv(struct enc28j60_net *priv, const char *msg,
 			      u16 pk_ptr, int len, u16 sts)
 {
-	printk(KERN_DEBUG DRV_NAME ": %s - NextPk: 0x%04x - RSV:\n",
-		msg, pk_ptr);
-	printk(KERN_DEBUG DRV_NAME ": ByteCount: %d, DribbleNibble: %d\n", len,
-		 RSV_GETBIT(sts, RSV_DRIBBLENIBBLE));
-	printk(KERN_DEBUG DRV_NAME ": RxOK: %d, CRCErr:%d, LenChkErr: %d,"
-		 " LenOutOfRange: %d\n", RSV_GETBIT(sts, RSV_RXOK),
-		 RSV_GETBIT(sts, RSV_CRCERROR),
-		 RSV_GETBIT(sts, RSV_LENCHECKERR),
-		 RSV_GETBIT(sts, RSV_LENOUTOFRANGE));
-	printk(KERN_DEBUG DRV_NAME ": Multicast: %d, Broadcast: %d, "
-		 "LongDropEvent: %d, CarrierEvent: %d\n",
-		 RSV_GETBIT(sts, RSV_RXMULTICAST),
-		 RSV_GETBIT(sts, RSV_RXBROADCAST),
-		 RSV_GETBIT(sts, RSV_RXLONGEVDROPEV),
-		 RSV_GETBIT(sts, RSV_CARRIEREV));
-	printk(KERN_DEBUG DRV_NAME ": ControlFrame: %d, PauseFrame: %d,"
-		 " UnknownOp: %d, VLanTagFrame: %d\n",
-		 RSV_GETBIT(sts, RSV_RXCONTROLFRAME),
-		 RSV_GETBIT(sts, RSV_RXPAUSEFRAME),
-		 RSV_GETBIT(sts, RSV_RXUNKNOWNOPCODE),
-		 RSV_GETBIT(sts, RSV_RXTYPEVLAN));
+	struct device *dev = &priv->spi->dev;
+
+	dev_printk(KERN_DEBUG, dev, "%s - NextPk: 0x%04x - RSV:\n", msg, pk_ptr);
+	dev_printk(KERN_DEBUG, dev, "ByteCount: %d, DribbleNibble: %d\n",
+		   len, RSV_GETBIT(sts, RSV_DRIBBLENIBBLE));
+	dev_printk(KERN_DEBUG, dev,
+		   "RxOK: %d, CRCErr:%d, LenChkErr: %d, LenOutOfRange: %d\n",
+		   RSV_GETBIT(sts, RSV_RXOK),
+		   RSV_GETBIT(sts, RSV_CRCERROR),
+		   RSV_GETBIT(sts, RSV_LENCHECKERR),
+		   RSV_GETBIT(sts, RSV_LENOUTOFRANGE));
+	dev_printk(KERN_DEBUG, dev,
+		   "Multicast: %d, Broadcast: %d, LongDropEvent: %d, CarrierEvent: %d\n",
+		   RSV_GETBIT(sts, RSV_RXMULTICAST),
+		   RSV_GETBIT(sts, RSV_RXBROADCAST),
+		   RSV_GETBIT(sts, RSV_RXLONGEVDROPEV),
+		   RSV_GETBIT(sts, RSV_CARRIEREV));
+	dev_printk(KERN_DEBUG, dev,
+		   "ControlFrame: %d, PauseFrame: %d, UnknownOp: %d, VLanTagFrame: %d\n",
+		   RSV_GETBIT(sts, RSV_RXCONTROLFRAME),
+		   RSV_GETBIT(sts, RSV_RXPAUSEFRAME),
+		   RSV_GETBIT(sts, RSV_RXUNKNOWNOPCODE),
+		   RSV_GETBIT(sts, RSV_RXTYPEVLAN));
 }
 
 static void dump_packet(const char *msg, int len, const char *data)
@@ -904,20 +903,20 @@ static void dump_packet(const char *msg, int len, const char *data)
 static void enc28j60_hw_rx(struct net_device *ndev)
 {
 	struct enc28j60_net *priv = netdev_priv(ndev);
+	struct device *dev = &priv->spi->dev;
 	struct sk_buff *skb = NULL;
 	u16 erxrdpt, next_packet, rxstat;
 	u8 rsv[RSV_SIZE];
 	int len;
 
 	if (netif_msg_rx_status(priv))
-		printk(KERN_DEBUG DRV_NAME ": RX pk_addr:0x%04x\n",
-			priv->next_pk_ptr);
+		netdev_printk(KERN_DEBUG, ndev, "RX pk_addr:0x%04x\n",
+			      priv->next_pk_ptr);
 
 	if (unlikely(priv->next_pk_ptr > RXEND_INIT)) {
 		if (netif_msg_rx_err(priv))
-			dev_err(&ndev->dev,
-				"%s() Invalid packet address!! 0x%04x\n",
-				__func__, priv->next_pk_ptr);
+			netdev_err(ndev, "%s() Invalid packet address!! 0x%04x\n",
+				   __func__, priv->next_pk_ptr);
 		/* packet address corrupted: reset RX logic */
 		mutex_lock(&priv->lock);
 		nolock_reg_bfclr(priv, ECON1, ECON1_RXEN);
@@ -950,7 +949,7 @@ static void enc28j60_hw_rx(struct net_device *ndev)
 
 	if (!RSV_GETBIT(rxstat, RSV_RXOK) || len > MAX_FRAMELEN) {
 		if (netif_msg_rx_err(priv))
-			dev_err(&ndev->dev, "Rx Error (%04x)\n", rxstat);
+			netdev_err(ndev, "Rx Error (%04x)\n", rxstat);
 		ndev->stats.rx_errors++;
 		if (RSV_GETBIT(rxstat, RSV_CRCERROR))
 			ndev->stats.rx_crc_errors++;
@@ -962,8 +961,7 @@ static void enc28j60_hw_rx(struct net_device *ndev)
 		skb = netdev_alloc_skb(ndev, len + NET_IP_ALIGN);
 		if (!skb) {
 			if (netif_msg_rx_err(priv))
-				dev_err(&ndev->dev,
-					"out of memory for Rx'd frame\n");
+				netdev_err(ndev, "out of memory for Rx'd frame\n");
 			ndev->stats.rx_dropped++;
 		} else {
 			skb_reserve(skb, NET_IP_ALIGN);
@@ -983,12 +981,12 @@ static void enc28j60_hw_rx(struct net_device *ndev)
 	/*
 	 * Move the RX read pointer to the start of the next
 	 * received packet.
-	 * This frees the memory we just read out
+	 * This frees the memory we just read out.
 	 */
 	erxrdpt = erxrdpt_workaround(next_packet, RXSTART_INIT, RXEND_INIT);
 	if (netif_msg_hw(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() ERXRDPT:0x%04x\n",
-			__func__, erxrdpt);
+		dev_printk(KERN_DEBUG, dev, "%s() ERXRDPT:0x%04x\n",
+			   __func__, erxrdpt);
 
 	mutex_lock(&priv->lock);
 	nolock_regw_write(priv, ERXRDPTL, erxrdpt);
@@ -997,9 +995,9 @@ static void enc28j60_hw_rx(struct net_device *ndev)
 		u16 reg;
 		reg = nolock_regw_read(priv, ERXRDPTL);
 		if (reg != erxrdpt)
-			printk(KERN_DEBUG DRV_NAME ": %s() ERXRDPT verify "
-				"error (0x%04x - 0x%04x)\n", __func__,
-				reg, erxrdpt);
+			dev_printk(KERN_DEBUG, dev,
+				   "%s() ERXRDPT verify error (0x%04x - 0x%04x)\n",
+				   __func__, reg, erxrdpt);
 	}
 #endif
 	priv->next_pk_ptr = next_packet;
@@ -1013,6 +1011,7 @@ static void enc28j60_hw_rx(struct net_device *ndev)
  */
 static int enc28j60_get_free_rxfifo(struct enc28j60_net *priv)
 {
+	struct net_device *ndev = priv->netdev;
 	int epkcnt, erxst, erxnd, erxwr, erxrd;
 	int free_space;
 
@@ -1035,8 +1034,8 @@ static int enc28j60_get_free_rxfifo(struct enc28j60_net *priv)
 	}
 	mutex_unlock(&priv->lock);
 	if (netif_msg_rx_status(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() free_space = %d\n",
-			__func__, free_space);
+		netdev_printk(KERN_DEBUG, ndev, "%s() free_space = %d\n",
+			      __func__, free_space);
 	return free_space;
 }
 
@@ -1046,24 +1045,25 @@ static int enc28j60_get_free_rxfifo(struct enc28j60_net *priv)
 static void enc28j60_check_link_status(struct net_device *ndev)
 {
 	struct enc28j60_net *priv = netdev_priv(ndev);
+	struct device *dev = &priv->spi->dev;
 	u16 reg;
 	int duplex;
 
 	reg = enc28j60_phy_read(priv, PHSTAT2);
 	if (netif_msg_hw(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() PHSTAT1: %04x, "
-			"PHSTAT2: %04x\n", __func__,
-			enc28j60_phy_read(priv, PHSTAT1), reg);
+		dev_printk(KERN_DEBUG, dev,
+			   "%s() PHSTAT1: %04x, PHSTAT2: %04x\n", __func__,
+			   enc28j60_phy_read(priv, PHSTAT1), reg);
 	duplex = reg & PHSTAT2_DPXSTAT;
 
 	if (reg & PHSTAT2_LSTAT) {
 		netif_carrier_on(ndev);
 		if (netif_msg_ifup(priv))
-			dev_info(&ndev->dev, "link up - %s\n",
-				duplex ? "Full duplex" : "Half duplex");
+			netdev_info(ndev, "link up - %s\n",
+				    duplex ? "Full duplex" : "Half duplex");
 	} else {
 		if (netif_msg_ifdown(priv))
-			dev_info(&ndev->dev, "link down\n");
+			netdev_info(ndev, "link down\n");
 		netif_carrier_off(ndev);
 	}
 }
@@ -1089,8 +1089,8 @@ static void enc28j60_tx_clear(struct net_device *ndev, bool err)
 
 /*
  * RX handler
- * ignore PKTIF because is unreliable! (look at the errata datasheet)
- * check EPKTCNT is the suggested workaround.
+ * Ignore PKTIF because is unreliable! (Look at the errata datasheet)
+ * Check EPKTCNT is the suggested workaround.
  * We don't need to clear interrupt flag, automatically done when
  * enc28j60_hw_rx() decrements the packet counter.
  * Returns how many packet processed.
@@ -1102,13 +1102,14 @@ static int enc28j60_rx_interrupt(struct net_device *ndev)
 
 	pk_counter = locked_regb_read(priv, EPKTCNT);
 	if (pk_counter && netif_msg_intr(priv))
-		printk(KERN_DEBUG DRV_NAME ": intRX, pk_cnt: %d\n", pk_counter);
+		netdev_printk(KERN_DEBUG, ndev, "intRX, pk_cnt: %d\n",
+			      pk_counter);
 	if (pk_counter > priv->max_pk_counter) {
 		/* update statistics */
 		priv->max_pk_counter = pk_counter;
 		if (netif_msg_rx_status(priv) && priv->max_pk_counter > 1)
-			printk(KERN_DEBUG DRV_NAME ": RX max_pk_cnt: %d\n",
-				priv->max_pk_counter);
+			netdev_printk(KERN_DEBUG, ndev, "RX max_pk_cnt: %d\n",
+				      priv->max_pk_counter);
 	}
 	ret = pk_counter;
 	while (pk_counter-- > 0)
@@ -1124,8 +1125,6 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 	struct net_device *ndev = priv->netdev;
 	int intflags, loop;
 
-	if (netif_msg_intr(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() enter\n", __func__);
 	/* disable further interrupts */
 	locked_reg_bfclr(priv, EIE, EIE_INTIE);
 
@@ -1136,16 +1135,16 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 		if ((intflags & EIR_DMAIF) != 0) {
 			loop++;
 			if (netif_msg_intr(priv))
-				printk(KERN_DEBUG DRV_NAME
-					": intDMA(%d)\n", loop);
+				netdev_printk(KERN_DEBUG, ndev, "intDMA(%d)\n",
+					      loop);
 			locked_reg_bfclr(priv, EIR, EIR_DMAIF);
 		}
 		/* LINK changed handler */
 		if ((intflags & EIR_LINKIF) != 0) {
 			loop++;
 			if (netif_msg_intr(priv))
-				printk(KERN_DEBUG DRV_NAME
-					": intLINK(%d)\n", loop);
+				netdev_printk(KERN_DEBUG, ndev, "intLINK(%d)\n",
+					      loop);
 			enc28j60_check_link_status(ndev);
 			/* read PHIR to clear the flag */
 			enc28j60_phy_read(priv, PHIR);
@@ -1156,13 +1155,12 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 			bool err = false;
 			loop++;
 			if (netif_msg_intr(priv))
-				printk(KERN_DEBUG DRV_NAME
-					": intTX(%d)\n", loop);
+				netdev_printk(KERN_DEBUG, ndev, "intTX(%d)\n",
+					      loop);
 			priv->tx_retry_count = 0;
 			if (locked_regb_read(priv, ESTAT) & ESTAT_TXABRT) {
 				if (netif_msg_tx_err(priv))
-					dev_err(&ndev->dev,
-						"Tx Error (aborted)\n");
+					netdev_err(ndev, "Tx Error (aborted)\n");
 				err = true;
 			}
 			if (netif_msg_tx_done(priv)) {
@@ -1179,8 +1177,8 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 
 			loop++;
 			if (netif_msg_intr(priv))
-				printk(KERN_DEBUG DRV_NAME
-					": intTXErr(%d)\n", loop);
+				netdev_printk(KERN_DEBUG, ndev, "intTXErr(%d)\n",
+					      loop);
 			locked_reg_bfclr(priv, ECON1, ECON1_TXRTS);
 			enc28j60_read_tsv(priv, tsv);
 			if (netif_msg_tx_err(priv))
@@ -1194,9 +1192,9 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 			/* Transmit Late collision check for retransmit */
 			if (TSV_GETBIT(tsv, TSV_TXLATECOLLISION)) {
 				if (netif_msg_tx_err(priv))
-					printk(KERN_DEBUG DRV_NAME
-						": LateCollision TXErr (%d)\n",
-						priv->tx_retry_count);
+					netdev_printk(KERN_DEBUG, ndev,
+						      "LateCollision TXErr (%d)\n",
+						      priv->tx_retry_count);
 				if (priv->tx_retry_count++ < MAX_TX_RETRYCOUNT)
 					locked_reg_bfset(priv, ECON1,
 							   ECON1_TXRTS);
@@ -1210,13 +1208,12 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 		if ((intflags & EIR_RXERIF) != 0) {
 			loop++;
 			if (netif_msg_intr(priv))
-				printk(KERN_DEBUG DRV_NAME
-					": intRXErr(%d)\n", loop);
+				netdev_printk(KERN_DEBUG, ndev, "intRXErr(%d)\n",
+					      loop);
 			/* Check free FIFO space to flag RX overrun */
 			if (enc28j60_get_free_rxfifo(priv) <= 0) {
 				if (netif_msg_rx_err(priv))
-					printk(KERN_DEBUG DRV_NAME
-						": RX Overrun\n");
+					netdev_printk(KERN_DEBUG, ndev, "RX Overrun\n");
 				ndev->stats.rx_dropped++;
 			}
 			locked_reg_bfclr(priv, EIR, EIR_RXERIF);
@@ -1228,8 +1225,6 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
 
 	/* re-enable interrupts */
 	locked_reg_bfset(priv, EIE, EIE_INTIE);
-	if (netif_msg_intr(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() exit\n", __func__);
 }
 
 /*
@@ -1239,11 +1234,13 @@ static void enc28j60_irq_work_handler(struct work_struct *work)
  */
 static void enc28j60_hw_tx(struct enc28j60_net *priv)
 {
+	struct net_device *ndev = priv->netdev;
+
 	BUG_ON(!priv->tx_skb);
 
 	if (netif_msg_tx_queued(priv))
-		printk(KERN_DEBUG DRV_NAME
-			": Tx Packet Len:%d\n", priv->tx_skb->len);
+		netdev_printk(KERN_DEBUG, ndev, "Tx Packet Len:%d\n",
+			      priv->tx_skb->len);
 
 	if (netif_msg_pktdata(priv))
 		dump_packet(__func__,
@@ -1253,6 +1250,7 @@ static void enc28j60_hw_tx(struct enc28j60_net *priv)
 #ifdef CONFIG_ENC28J60_WRITEVERIFY
 	/* readback and verify written data */
 	if (netif_msg_drv(priv)) {
+		struct device *dev = &priv->spi->dev;
 		int test_len, k;
 		u8 test_buf[64]; /* limit the test to the first 64 bytes */
 		int okflag;
@@ -1266,16 +1264,14 @@ static void enc28j60_hw_tx(struct enc28j60_net *priv)
 		okflag = 1;
 		for (k = 0; k < test_len; k++) {
 			if (priv->tx_skb->data[k] != test_buf[k]) {
-				printk(KERN_DEBUG DRV_NAME
-					 ": Error, %d location differ: "
-					 "0x%02x-0x%02x\n", k,
-					 priv->tx_skb->data[k], test_buf[k]);
+				dev_printk(KERN_DEBUG, dev,
+					   "Error, %d location differ: 0x%02x-0x%02x\n",
+					   k, priv->tx_skb->data[k], test_buf[k]);
 				okflag = 0;
 			}
 		}
 		if (!okflag)
-			printk(KERN_DEBUG DRV_NAME ": Tx write buffer, "
-				"verify ERROR!\n");
+			dev_printk(KERN_DEBUG, dev, "Tx write buffer, verify ERROR!\n");
 	}
 #endif
 	/* set TX request flag */
@@ -1287,14 +1283,11 @@ static netdev_tx_t enc28j60_send_packet(struct sk_buff *skb,
 {
 	struct enc28j60_net *priv = netdev_priv(dev);
 
-	if (netif_msg_tx_queued(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() enter\n", __func__);
-
 	/* If some error occurs while trying to transmit this
 	 * packet, you should return '1' from this function.
 	 * In such a case you _may not_ do anything to the
 	 * SKB, it is still owned by the network queueing
-	 * layer when an error is returned.  This means you
+	 * layer when an error is returned. This means you
 	 * may not modify any SKB fields, you may not free
 	 * the SKB, etc.
 	 */
@@ -1337,7 +1330,7 @@ static void enc28j60_tx_timeout(struct net_device *ndev)
 	struct enc28j60_net *priv = netdev_priv(ndev);
 
 	if (netif_msg_timer(priv))
-		dev_err(&ndev->dev, DRV_NAME " tx timeout\n");
+		netdev_err(ndev, "tx timeout\n");
 
 	ndev->stats.tx_errors++;
 	/* can't restart safely under softirq */
@@ -1356,13 +1349,9 @@ static int enc28j60_net_open(struct net_device *dev)
 {
 	struct enc28j60_net *priv = netdev_priv(dev);
 
-	if (netif_msg_drv(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() enter\n", __func__);
-
 	if (!is_valid_ether_addr(dev->dev_addr)) {
 		if (netif_msg_ifup(priv))
-			dev_err(&dev->dev, "invalid MAC address %pM\n",
-				dev->dev_addr);
+			netdev_err(dev, "invalid MAC address %pM\n", dev->dev_addr);
 		return -EADDRNOTAVAIL;
 	}
 	/* Reset the hardware here (and take it out of low power mode) */
@@ -1370,7 +1359,7 @@ static int enc28j60_net_open(struct net_device *dev)
 	enc28j60_hw_disable(priv);
 	if (!enc28j60_hw_init(priv)) {
 		if (netif_msg_ifup(priv))
-			dev_err(&dev->dev, "hw_reset() failed\n");
+			netdev_err(dev, "hw_reset() failed\n");
 		return -EINVAL;
 	}
 	/* Update the MAC address (in case user has changed it) */
@@ -1392,9 +1381,6 @@ static int enc28j60_net_close(struct net_device *dev)
 {
 	struct enc28j60_net *priv = netdev_priv(dev);
 
-	if (netif_msg_drv(priv))
-		printk(KERN_DEBUG DRV_NAME ": %s() enter\n", __func__);
-
 	enc28j60_hw_disable(priv);
 	enc28j60_lowpower(priv, true);
 	netif_stop_queue(dev);
@@ -1415,16 +1401,16 @@ static void enc28j60_set_multicast_list(struct net_device *dev)
 
 	if (dev->flags & IFF_PROMISC) {
 		if (netif_msg_link(priv))
-			dev_info(&dev->dev, "promiscuous mode\n");
+			netdev_info(dev, "promiscuous mode\n");
 		priv->rxfilter = RXFILTER_PROMISC;
 	} else if ((dev->flags & IFF_ALLMULTI) || !netdev_mc_empty(dev)) {
 		if (netif_msg_link(priv))
-			dev_info(&dev->dev, "%smulticast mode\n",
-				(dev->flags & IFF_ALLMULTI) ? "all-" : "");
+			netdev_info(dev, "%smulticast mode\n",
+				    (dev->flags & IFF_ALLMULTI) ? "all-" : "");
 		priv->rxfilter = RXFILTER_MULTI;
 	} else {
 		if (netif_msg_link(priv))
-			dev_info(&dev->dev, "normal mode\n");
+			netdev_info(dev, "normal mode\n");
 		priv->rxfilter = RXFILTER_NORMAL;
 	}
 
@@ -1436,20 +1422,21 @@ static void enc28j60_setrx_work_handler(struct work_struct *work)
 {
 	struct enc28j60_net *priv =
 		container_of(work, struct enc28j60_net, setrx_work);
+	struct device *dev = &priv->spi->dev;
 
 	if (priv->rxfilter == RXFILTER_PROMISC) {
 		if (netif_msg_drv(priv))
-			printk(KERN_DEBUG DRV_NAME ": promiscuous mode\n");
+			dev_printk(KERN_DEBUG, dev, "promiscuous mode\n");
 		locked_regb_write(priv, ERXFCON, 0x00);
 	} else if (priv->rxfilter == RXFILTER_MULTI) {
 		if (netif_msg_drv(priv))
-			printk(KERN_DEBUG DRV_NAME ": multicast mode\n");
+			dev_printk(KERN_DEBUG, dev, "multicast mode\n");
 		locked_regb_write(priv, ERXFCON,
 					ERXFCON_UCEN | ERXFCON_CRCEN |
 					ERXFCON_BCEN | ERXFCON_MCEN);
 	} else {
 		if (netif_msg_drv(priv))
-			printk(KERN_DEBUG DRV_NAME ": normal mode\n");
+			dev_printk(KERN_DEBUG, dev, "normal mode\n");
 		locked_regb_write(priv, ERXFCON,
 					ERXFCON_UCEN | ERXFCON_CRCEN |
 					ERXFCON_BCEN);
@@ -1468,7 +1455,7 @@ static void enc28j60_restart_work_handler(struct work_struct *work)
 		enc28j60_net_close(ndev);
 		ret = enc28j60_net_open(ndev);
 		if (unlikely(ret)) {
-			dev_info(&ndev->dev, " could not restart %d\n", ret);
+			netdev_info(ndev, "could not restart %d\n", ret);
 			dev_close(ndev);
 		}
 	}
@@ -1552,14 +1539,13 @@ static const struct net_device_ops enc28j60_netdev_ops = {
 
 static int enc28j60_probe(struct spi_device *spi)
 {
+	unsigned char macaddr[ETH_ALEN];
 	struct net_device *dev;
 	struct enc28j60_net *priv;
-	const void *macaddr;
 	int ret = 0;
 
 	if (netif_msg_drv(&debug))
-		dev_info(&spi->dev, DRV_NAME " Ethernet driver %s loaded\n",
-			DRV_VERSION);
+		dev_info(&spi->dev, "Ethernet driver %s loaded\n", DRV_VERSION);
 
 	dev = alloc_etherdev(sizeof(struct enc28j60_net));
 	if (!dev) {
@@ -1570,8 +1556,7 @@ static int enc28j60_probe(struct spi_device *spi)
 
 	priv->netdev = dev;	/* priv to netdev reference */
 	priv->spi = spi;	/* priv to spi reference */
-	priv->msg_enable = netif_msg_init(debug.msg_enable,
-						ENC28J60_MSG_DEFAULT);
+	priv->msg_enable = netif_msg_init(debug.msg_enable, ENC28J60_MSG_DEFAULT);
 	mutex_init(&priv->lock);
 	INIT_WORK(&priv->tx_work, enc28j60_tx_work_handler);
 	INIT_WORK(&priv->setrx_work, enc28j60_setrx_work_handler);
@@ -1582,13 +1567,12 @@ static int enc28j60_probe(struct spi_device *spi)
 
 	if (!enc28j60_chipset_init(dev)) {
 		if (netif_msg_probe(priv))
-			dev_info(&spi->dev, DRV_NAME " chip not found\n");
+			dev_info(&spi->dev, "chip not found\n");
 		ret = -EIO;
 		goto error_irq;
 	}
 
-	macaddr = of_get_mac_address(spi->dev.of_node);
-	if (macaddr)
+	if (device_get_mac_address(&spi->dev, macaddr, sizeof(macaddr)))
 		ether_addr_copy(dev->dev_addr, macaddr);
 	else
 		eth_hw_addr_random(dev);
@@ -1600,8 +1584,8 @@ static int enc28j60_probe(struct spi_device *spi)
 	ret = request_irq(spi->irq, enc28j60_irq, 0, DRV_NAME, priv);
 	if (ret < 0) {
 		if (netif_msg_probe(priv))
-			dev_err(&spi->dev, DRV_NAME ": request irq %d failed "
-				"(ret = %d)\n", spi->irq, ret);
+			dev_err(&spi->dev, "request irq %d failed (ret = %d)\n",
+				spi->irq, ret);
 		goto error_irq;
 	}
 
@@ -1616,11 +1600,10 @@ static int enc28j60_probe(struct spi_device *spi)
 	ret = register_netdev(dev);
 	if (ret) {
 		if (netif_msg_probe(priv))
-			dev_err(&spi->dev, "register netdev " DRV_NAME
-				" failed (ret = %d)\n", ret);
+			dev_err(&spi->dev, "register netdev failed (ret = %d)\n",
+				ret);
 		goto error_register;
 	}
-	dev_info(&dev->dev, DRV_NAME " driver registered\n");
 
 	return 0;
 
@@ -1636,9 +1619,6 @@ static int enc28j60_remove(struct spi_device *spi)
 {
 	struct enc28j60_net *priv = spi_get_drvdata(spi);
 
-	if (netif_msg_drv(priv))
-		printk(KERN_DEBUG DRV_NAME ": remove\n");
-
 	unregister_netdev(priv->netdev);
 	free_irq(spi->irq, priv);
 	free_netdev(priv->netdev);
@@ -1660,26 +1640,11 @@ static struct spi_driver enc28j60_driver = {
 	.probe = enc28j60_probe,
 	.remove = enc28j60_remove,
 };
-
-static int __init enc28j60_init(void)
-{
-	msec20_to_jiffies = msecs_to_jiffies(20);
-
-	return spi_register_driver(&enc28j60_driver);
-}
-
-module_init(enc28j60_init);
-
-static void __exit enc28j60_exit(void)
-{
-	spi_unregister_driver(&enc28j60_driver);
-}
-
-module_exit(enc28j60_exit);
+module_spi_driver(enc28j60_driver);
 
 MODULE_DESCRIPTION(DRV_NAME " ethernet driver");
 MODULE_AUTHOR("Claudio Lanconelli <lanconelli.claudio@eptar.com>");
 MODULE_LICENSE("GPL");
 module_param_named(debug, debug.msg_enable, int, 0);
-MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., ffff=all)");
+MODULE_PARM_DESC(debug, "Debug verbosity level in amount of bits set (0=none, ..., 31=all)");
 MODULE_ALIAS("spi:" DRV_NAME);
diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c
index 44bb04d4d21b..1f496fac7033 100644
--- a/drivers/net/ethernet/microchip/encx24j600-regmap.c
+++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /**
  * Register map access API - ENCX24J600 support
  *
  * Copyright 2015 Gridpoint
  *
  * Author: Jon Ringle <jringle@gridpoint.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c
index f831238d9793..52c41d11f565 100644
--- a/drivers/net/ethernet/microchip/encx24j600.c
+++ b/drivers/net/ethernet/microchip/encx24j600.c
@@ -1,14 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**
  * Microchip ENCX24J600 ethernet driver
  *
  * Copyright (C) 2015 Gridpoint
  * Author: Jon Ringle <jringle@gridpoint.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  */
 
 #include <linux/device.h>
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 07c1eb63415a..3a0b289d9771 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -14,61 +14,138 @@
 #define EEPROM_INDICATOR_1		    (0xA5)
 #define EEPROM_INDICATOR_2		    (0xAA)
 #define EEPROM_MAC_OFFSET		    (0x01)
-#define MAX_EEPROM_SIZE			    512
+#define MAX_EEPROM_SIZE			    (512)
+#define MAX_OTP_SIZE			    (1024)
 #define OTP_INDICATOR_1			    (0xF3)
 #define OTP_INDICATOR_2			    (0xF7)
 
-static int lan743x_otp_write(struct lan743x_adapter *adapter, u32 offset,
-			     u32 length, u8 *data)
+static int lan743x_otp_power_up(struct lan743x_adapter *adapter)
+{
+	u32 reg_value;
+
+	reg_value = lan743x_csr_read(adapter, OTP_PWR_DN);
+
+	if (reg_value & OTP_PWR_DN_PWRDN_N_) {
+		/* clear it and wait to be cleared */
+		reg_value &= ~OTP_PWR_DN_PWRDN_N_;
+		lan743x_csr_write(adapter, OTP_PWR_DN, reg_value);
+
+		usleep_range(100, 20000);
+	}
+
+	return 0;
+}
+
+static void lan743x_otp_power_down(struct lan743x_adapter *adapter)
+{
+	u32 reg_value;
+
+	reg_value = lan743x_csr_read(adapter, OTP_PWR_DN);
+	if (!(reg_value & OTP_PWR_DN_PWRDN_N_)) {
+		/* set power down bit */
+		reg_value |= OTP_PWR_DN_PWRDN_N_;
+		lan743x_csr_write(adapter, OTP_PWR_DN, reg_value);
+	}
+}
+
+static void lan743x_otp_set_address(struct lan743x_adapter *adapter,
+				    u32 address)
+{
+	lan743x_csr_write(adapter, OTP_ADDR_HIGH, (address >> 8) & 0x03);
+	lan743x_csr_write(adapter, OTP_ADDR_LOW, address & 0xFF);
+}
+
+static void lan743x_otp_read_go(struct lan743x_adapter *adapter)
+{
+	lan743x_csr_write(adapter, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_);
+	lan743x_csr_write(adapter, OTP_CMD_GO, OTP_CMD_GO_GO_);
+}
+
+static int lan743x_otp_wait_till_not_busy(struct lan743x_adapter *adapter)
 {
 	unsigned long timeout;
-	u32 buf;
+	u32 reg_val;
+
+	timeout = jiffies + HZ;
+	do {
+		if (time_after(jiffies, timeout)) {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "Timeout on OTP_STATUS completion\n");
+			return -EIO;
+		}
+		udelay(1);
+		reg_val = lan743x_csr_read(adapter, OTP_STATUS);
+	} while (reg_val & OTP_STATUS_BUSY_);
+
+	return 0;
+}
+
+static int lan743x_otp_read(struct lan743x_adapter *adapter, u32 offset,
+			    u32 length, u8 *data)
+{
+	int ret;
 	int i;
 
-	buf = lan743x_csr_read(adapter, OTP_PWR_DN);
+	if (offset + length > MAX_OTP_SIZE)
+		return -EINVAL;
 
-	if (buf & OTP_PWR_DN_PWRDN_N_) {
-		/* clear it and wait to be cleared */
-		lan743x_csr_write(adapter, OTP_PWR_DN, 0);
-
-		timeout = jiffies + HZ;
-		do {
-			udelay(1);
-			buf = lan743x_csr_read(adapter, OTP_PWR_DN);
-			if (time_after(jiffies, timeout)) {
-				netif_warn(adapter, drv, adapter->netdev,
-					   "timeout on OTP_PWR_DN completion\n");
-				return -EIO;
-			}
-		} while (buf & OTP_PWR_DN_PWRDN_N_);
+	ret = lan743x_otp_power_up(adapter);
+	if (ret < 0)
+		return ret;
+
+	ret = lan743x_otp_wait_till_not_busy(adapter);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < length; i++) {
+		lan743x_otp_set_address(adapter, offset + i);
+
+		lan743x_otp_read_go(adapter);
+		ret = lan743x_otp_wait_till_not_busy(adapter);
+		if (ret < 0)
+			return ret;
+		data[i] = lan743x_csr_read(adapter, OTP_READ_DATA);
 	}
 
+	lan743x_otp_power_down(adapter);
+
+	return 0;
+}
+
+static int lan743x_otp_write(struct lan743x_adapter *adapter, u32 offset,
+			     u32 length, u8 *data)
+{
+	int ret;
+	int i;
+
+	if (offset + length > MAX_OTP_SIZE)
+		return -EINVAL;
+
+	ret = lan743x_otp_power_up(adapter);
+	if (ret < 0)
+		return ret;
+
+	ret = lan743x_otp_wait_till_not_busy(adapter);
+	if (ret < 0)
+		return ret;
+
 	/* set to BYTE program mode */
 	lan743x_csr_write(adapter, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_);
 
 	for (i = 0; i < length; i++) {
-		lan743x_csr_write(adapter, OTP_ADDR1,
-				  ((offset + i) >> 8) &
-				  OTP_ADDR1_15_11_MASK_);
-		lan743x_csr_write(adapter, OTP_ADDR2,
-				  ((offset + i) &
-				  OTP_ADDR2_10_3_MASK_));
+		lan743x_otp_set_address(adapter, offset + i);
+
 		lan743x_csr_write(adapter, OTP_PRGM_DATA, data[i]);
 		lan743x_csr_write(adapter, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_);
 		lan743x_csr_write(adapter, OTP_CMD_GO, OTP_CMD_GO_GO_);
 
-		timeout = jiffies + HZ;
-		do {
-			udelay(1);
-			buf = lan743x_csr_read(adapter, OTP_STATUS);
-			if (time_after(jiffies, timeout)) {
-				netif_warn(adapter, drv, adapter->netdev,
-					   "Timeout on OTP_STATUS completion\n");
-				return -EIO;
-			}
-		} while (buf & OTP_STATUS_BUSY_);
+		ret = lan743x_otp_wait_till_not_busy(adapter);
+		if (ret < 0)
+			return ret;
 	}
 
+	lan743x_otp_power_down(adapter);
+
 	return 0;
 }
 
@@ -120,6 +197,9 @@ static int lan743x_eeprom_read(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_eeprom_confirm_not_busy(adapter);
 	if (retval)
 		return retval;
@@ -148,6 +228,9 @@ static int lan743x_eeprom_write(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_eeprom_confirm_not_busy(adapter);
 	if (retval)
 		return retval;
@@ -207,6 +290,11 @@ static void lan743x_ethtool_set_msglevel(struct net_device *netdev,
 
 static int lan743x_ethtool_get_eeprom_len(struct net_device *netdev)
 {
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP)
+		return MAX_OTP_SIZE;
+
 	return MAX_EEPROM_SIZE;
 }
 
@@ -214,8 +302,14 @@ static int lan743x_ethtool_get_eeprom(struct net_device *netdev,
 				      struct ethtool_eeprom *ee, u8 *data)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret = 0;
+
+	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP)
+		ret = lan743x_otp_read(adapter, ee->offset, ee->len, data);
+	else
+		ret = lan743x_eeprom_read(adapter, ee->offset, ee->len, data);
 
-	return lan743x_eeprom_read(adapter, ee->offset, ee->len, data);
+	return ret;
 }
 
 static int lan743x_ethtool_set_eeprom(struct net_device *netdev,
@@ -224,17 +318,18 @@ static int lan743x_ethtool_set_eeprom(struct net_device *netdev,
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 	int ret = -EINVAL;
 
-	if (ee->magic == LAN743X_EEPROM_MAGIC)
-		ret = lan743x_eeprom_write(adapter, ee->offset, ee->len,
-					   data);
-	/* Beware!  OTP is One Time Programming ONLY!
-	 * So do some strict condition check before messing up
-	 */
-	else if ((ee->magic == LAN743X_OTP_MAGIC) &&
-		 (ee->offset == 0) &&
-		 (ee->len == MAX_EEPROM_SIZE) &&
-		 (data[0] == OTP_INDICATOR_1))
-		ret = lan743x_otp_write(adapter, ee->offset, ee->len, data);
+	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP) {
+		/* Beware!  OTP is One Time Programming ONLY! */
+		if (ee->magic == LAN743X_OTP_MAGIC) {
+			ret = lan743x_otp_write(adapter, ee->offset,
+						ee->len, data);
+		}
+	} else {
+		if (ee->magic == LAN743X_EEPROM_MAGIC) {
+			ret = lan743x_eeprom_write(adapter, ee->offset,
+						   ee->len, data);
+		}
+	}
 
 	return ret;
 }
@@ -360,6 +455,10 @@ static const u32 lan743x_set2_hw_cnt_addr[] = {
 	STAT_TX_COUNTER_ROLLOVER_STATUS
 };
 
+static const char lan743x_priv_flags_strings[][ETH_GSTRING_LEN] = {
+	"OTP_ACCESS",
+};
+
 static void lan743x_ethtool_get_strings(struct net_device *netdev,
 					u32 stringset, u8 *data)
 {
@@ -375,6 +474,10 @@ static void lan743x_ethtool_get_strings(struct net_device *netdev,
 		       lan743x_set2_hw_cnt_strings,
 		       sizeof(lan743x_set2_hw_cnt_strings));
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, lan743x_priv_flags_strings,
+		       sizeof(lan743x_priv_flags_strings));
+		break;
 	}
 }
 
@@ -399,6 +502,22 @@ static void lan743x_ethtool_get_ethtool_stats(struct net_device *netdev,
 	}
 }
 
+static u32 lan743x_ethtool_get_priv_flags(struct net_device *netdev)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->flags;
+}
+
+static int lan743x_ethtool_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	adapter->flags = flags;
+
+	return 0;
+}
+
 static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 {
 	switch (sset) {
@@ -411,6 +530,8 @@ static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 		ret += ARRAY_SIZE(lan743x_set2_hw_cnt_strings);
 		return ret;
 	}
+	case ETH_SS_PRIV_FLAGS:
+		return ARRAY_SIZE(lan743x_priv_flags_strings);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -705,6 +826,8 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.set_eeprom = lan743x_ethtool_set_eeprom,
 	.get_strings = lan743x_ethtool_get_strings,
 	.get_ethtool_stats = lan743x_ethtool_get_ethtool_stats,
+	.get_priv_flags = lan743x_ethtool_get_priv_flags,
+	.set_priv_flags = lan743x_ethtool_set_priv_flags,
 	.get_sset_count = lan743x_ethtool_get_sset_count,
 	.get_rxnfc = lan743x_ethtool_get_rxnfc,
 	.get_rxfh_key_size = lan743x_ethtool_get_rxfh_key_size,
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 310807ef328b..13e6bf13ac4d 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -585,8 +585,7 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 
 		if (adapter->csr.flags &
 		   LAN743X_CSR_FLAG_SUPPORTS_INTR_AUTO_SET_CLR) {
-			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR |
-				LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
+			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_CLEAR |
 				LAN743X_VECTOR_FLAG_SOURCE_STATUS_AUTO_CLEAR;
@@ -599,12 +598,6 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 			/* map TX interrupt to vector */
 			int_vec_map1 |= INT_VEC_MAP1_TX_VEC_(index, vector);
 			lan743x_csr_write(adapter, INT_VEC_MAP1, int_vec_map1);
-			if (flags &
-			    LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR) {
-				int_vec_en_auto_clr |= INT_VEC_EN_(vector);
-				lan743x_csr_write(adapter, INT_VEC_EN_AUTO_CLR,
-						  int_vec_en_auto_clr);
-			}
 
 			/* Remove TX interrupt from shared mask */
 			intr->vector_list[0].int_mask &= ~int_bit;
@@ -1400,7 +1393,8 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx,
 }
 
 static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
-				     unsigned int frame_length)
+				     unsigned int frame_length,
+				     int nr_frags)
 {
 	/* called only from within lan743x_tx_xmit_frame.
 	 * assuming tx->ring_lock has already been acquired.
@@ -1410,6 +1404,10 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
 
 	/* wrap up previous descriptor */
 	tx->frame_data0 |= TX_DESC_DATA0_EXT_;
+	if (nr_frags <= 0) {
+		tx->frame_data0 |= TX_DESC_DATA0_LS_;
+		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	}
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = tx->frame_data0;
 
@@ -1514,8 +1512,11 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	u32 tx_tail_flags = 0;
 
 	/* wrap up previous descriptor */
-	tx->frame_data0 |= TX_DESC_DATA0_LS_;
-	tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	if ((tx->frame_data0 & TX_DESC_DATA0_DTYPE_MASK_) ==
+	    TX_DESC_DATA0_DTYPE_DATA_) {
+		tx->frame_data0 |= TX_DESC_DATA0_LS_;
+		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	}
 
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	buffer_info = &tx->buffer_info[tx->frame_tail];
@@ -1600,7 +1601,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	}
 
 	if (gso)
-		lan743x_tx_frame_add_lso(tx, frame_length);
+		lan743x_tx_frame_add_lso(tx, frame_length, nr_frags);
 
 	if (nr_frags <= 0)
 		goto finish;
@@ -1894,7 +1895,17 @@ static int lan743x_rx_next_index(struct lan743x_rx *rx, int index)
 	return ((++index) % rx->ring_size);
 }
 
-static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
+static struct sk_buff *lan743x_rx_allocate_skb(struct lan743x_rx *rx)
+{
+	int length = 0;
+
+	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
+	return __netdev_alloc_skb(rx->adapter->netdev,
+				  length, GFP_ATOMIC | GFP_DMA);
+}
+
+static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index,
+					struct sk_buff *skb)
 {
 	struct lan743x_rx_buffer_info *buffer_info;
 	struct lan743x_rx_descriptor *descriptor;
@@ -1903,9 +1914,7 @@ static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
 	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
 	descriptor = &rx->ring_cpu_ptr[index];
 	buffer_info = &rx->buffer_info[index];
-	buffer_info->skb = __netdev_alloc_skb(rx->adapter->netdev,
-					      length,
-					      GFP_ATOMIC | GFP_DMA);
+	buffer_info->skb = skb;
 	if (!(buffer_info->skb))
 		return -ENOMEM;
 	buffer_info->dma_ptr = dma_map_single(&rx->adapter->pdev->dev,
@@ -2052,8 +2061,19 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 		/* packet is available */
 		if (first_index == last_index) {
 			/* single buffer packet */
+			struct sk_buff *new_skb = NULL;
 			int packet_length;
 
+			new_skb = lan743x_rx_allocate_skb(rx);
+			if (!new_skb) {
+				/* failed to allocate next skb.
+				 * Memory is very low.
+				 * Drop this packet and reuse buffer.
+				 */
+				lan743x_rx_reuse_ring_element(rx, first_index);
+				goto process_extension;
+			}
+
 			buffer_info = &rx->buffer_info[first_index];
 			skb = buffer_info->skb;
 			descriptor = &rx->ring_cpu_ptr[first_index];
@@ -2073,7 +2093,7 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			skb_put(skb, packet_length - 4);
 			skb->protocol = eth_type_trans(skb,
 						       rx->adapter->netdev);
-			lan743x_rx_allocate_ring_element(rx, first_index);
+			lan743x_rx_init_ring_element(rx, first_index, new_skb);
 		} else {
 			int index = first_index;
 
@@ -2086,26 +2106,23 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			if (first_index <= last_index) {
 				while ((index >= first_index) &&
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			} else {
 				while ((index >= first_index) ||
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			}
 		}
 
+process_extension:
 		if (extension_index >= 0) {
 			descriptor = &rx->ring_cpu_ptr[extension_index];
 			buffer_info = &rx->buffer_info[extension_index];
@@ -2282,7 +2299,9 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
 
 	rx->last_head = 0;
 	for (index = 0; index < rx->ring_size; index++) {
-		ret = lan743x_rx_allocate_ring_element(rx, index);
+		struct sk_buff *new_skb = lan743x_rx_allocate_skb(rx);
+
+		ret = lan743x_rx_init_ring_element(rx, index, new_skb);
 		if (ret)
 			goto cleanup;
 	}
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 2d6eea18973e..3b02eeae5f45 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -26,6 +26,8 @@
 #define FPGA_REV_GET_MAJOR_(fpga_rev)	((fpga_rev) & 0x000000FF)
 
 #define HW_CFG					(0x010)
+#define HW_CFG_RELOAD_TYPE_ALL_			(0x00000FC0)
+#define HW_CFG_EE_OTP_RELOAD_			BIT(4)
 #define HW_CFG_LRST_				BIT(1)
 
 #define PMT_CTL					(0x014)
@@ -453,17 +455,19 @@
 #define OTP_PWR_DN				(0x1000)
 #define OTP_PWR_DN_PWRDN_N_			BIT(0)
 
-#define OTP_ADDR1				(0x1004)
-#define OTP_ADDR1_15_11_MASK_			(0x1F)
-
-#define OTP_ADDR2				(0x1008)
-#define OTP_ADDR2_10_3_MASK_			(0xFF)
+#define OTP_ADDR_HIGH				(0x1004)
+#define OTP_ADDR_LOW				(0x1008)
 
 #define OTP_PRGM_DATA				(0x1010)
 
 #define OTP_PRGM_MODE				(0x1014)
 #define OTP_PRGM_MODE_BYTE_			BIT(0)
 
+#define OTP_READ_DATA				(0x1018)
+
+#define OTP_FUNC_CMD				(0x1020)
+#define OTP_FUNC_CMD_READ_			BIT(0)
+
 #define OTP_TST_CMD				(0x1024)
 #define OTP_TST_CMD_PRGVRFY_			BIT(3)
 
@@ -713,6 +717,9 @@ struct lan743x_adapter {
 	struct lan743x_phy      phy;
 	struct lan743x_tx       tx[LAN743X_MAX_TX_CHANNELS];
 	struct lan743x_rx       rx[LAN743X_MAX_RX_CHANNELS];
+
+#define LAN743X_ADAPTER_FLAG_OTP		BIT(0)
+	u32			flags;
 };
 
 #define LAN743X_COMPONENT_FLAG_RX(channel)  BIT(20 + (channel))
diff --git a/drivers/net/ethernet/moxa/Kconfig b/drivers/net/ethernet/moxa/Kconfig
index 5b531da36933..1a7cacbc0c59 100644
--- a/drivers/net/ethernet/moxa/Kconfig
+++ b/drivers/net/ethernet/moxa/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # MOXART device configuration
 #
diff --git a/drivers/net/ethernet/moxa/Makefile b/drivers/net/ethernet/moxa/Makefile
index aa3c73e9e952..864e17984f9f 100644
--- a/drivers/net/ethernet/moxa/Makefile
+++ b/drivers/net/ethernet/moxa/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the MOXART network device drivers.
 #
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index b34055ac476f..e1651756bf9d 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -81,11 +81,13 @@ static void moxart_mac_free_memory(struct net_device *ndev)
 				 priv->rx_buf_size, DMA_FROM_DEVICE);
 
 	if (priv->tx_desc_base)
-		dma_free_coherent(NULL, TX_REG_DESC_SIZE * TX_DESC_NUM,
+		dma_free_coherent(&priv->pdev->dev,
+				  TX_REG_DESC_SIZE * TX_DESC_NUM,
 				  priv->tx_desc_base, priv->tx_base);
 
 	if (priv->rx_desc_base)
-		dma_free_coherent(NULL, RX_REG_DESC_SIZE * RX_DESC_NUM,
+		dma_free_coherent(&priv->pdev->dev,
+				  RX_REG_DESC_SIZE * RX_DESC_NUM,
 				  priv->rx_desc_base, priv->rx_base);
 
 	kfree(priv->tx_buf_base);
@@ -298,7 +300,7 @@ static void moxart_tx_finished(struct net_device *ndev)
 		ndev->stats.tx_packets++;
 		ndev->stats.tx_bytes += priv->tx_skb[tx_tail]->len;
 
-		dev_kfree_skb_irq(priv->tx_skb[tx_tail]);
+		dev_consume_skb_irq(priv->tx_skb[tx_tail]);
 		priv->tx_skb[tx_tail] = NULL;
 
 		tx_tail = TX_NEXT(tx_tail);
@@ -476,6 +478,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 
 	priv = netdev_priv(ndev);
 	priv->ndev = ndev;
+	priv->pdev = pdev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ndev->base_addr = res->start;
@@ -491,7 +494,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	priv->tx_buf_size = TX_BUF_SIZE;
 	priv->rx_buf_size = RX_BUF_SIZE;
 
-	priv->tx_desc_base = dma_alloc_coherent(NULL, TX_REG_DESC_SIZE *
+	priv->tx_desc_base = dma_alloc_coherent(&pdev->dev, TX_REG_DESC_SIZE *
 						TX_DESC_NUM, &priv->tx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->tx_desc_base) {
@@ -499,7 +502,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 		goto init_fail;
 	}
 
-	priv->rx_desc_base = dma_alloc_coherent(NULL, RX_REG_DESC_SIZE *
+	priv->rx_desc_base = dma_alloc_coherent(&pdev->dev, RX_REG_DESC_SIZE *
 						RX_DESC_NUM, &priv->rx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->rx_desc_base) {
diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h
index bee608b547d1..bf4c3029cd0c 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.h
+++ b/drivers/net/ethernet/moxa/moxart_ether.h
@@ -292,6 +292,7 @@
 #define LINK_STATUS		0x4
 
 struct moxart_mac_priv_t {
+	struct platform_device *pdev;
 	void __iomem *base;
 	unsigned int reg_maccr;
 	unsigned int reg_imr;
diff --git a/drivers/net/ethernet/mscc/Makefile b/drivers/net/ethernet/mscc/Makefile
index cb52a3b128ae..9a36c26095c8 100644
--- a/drivers/net/ethernet/mscc/Makefile
+++ b/drivers/net/ethernet/mscc/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: (GPL-2.0 OR MIT)
 obj-$(CONFIG_MSCC_OCELOT_SWITCH) += mscc_ocelot_common.o
 mscc_ocelot_common-y := ocelot.o ocelot_io.o
-mscc_ocelot_common-y += ocelot_regs.o
+mscc_ocelot_common-y += ocelot_regs.o ocelot_tc.o ocelot_police.o ocelot_ace.o ocelot_flower.o
 obj-$(CONFIG_MSCC_OCELOT_SWITCH_OCELOT) += ocelot_board.o
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 215a45374d7b..b71e4ecbe469 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -22,6 +22,7 @@
 #include <net/switchdev.h>
 
 #include "ocelot.h"
+#include "ocelot_ace.h"
 
 #define TABLE_UPDATE_SLEEP_US 10
 #define TABLE_UPDATE_TIMEOUT_US 100000
@@ -130,6 +131,13 @@ static void ocelot_mact_init(struct ocelot *ocelot)
 	ocelot_write(ocelot, MACACCESS_CMD_INIT, ANA_TABLES_MACACCESS);
 }
 
+static void ocelot_vcap_enable(struct ocelot *ocelot, struct ocelot_port *port)
+{
+	ocelot_write_gix(ocelot, ANA_PORT_VCAP_S2_CFG_S2_ENA |
+			 ANA_PORT_VCAP_S2_CFG_S2_IP6_CFG(0xa),
+			 ANA_PORT_VCAP_S2_CFG, port->chip_port);
+}
+
 static inline u32 ocelot_vlant_read_vlanaccess(struct ocelot *ocelot)
 {
 	return ocelot_read(ocelot, ANA_TABLES_VLANACCESS);
@@ -593,45 +601,25 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-static void ocelot_mact_mc_reset(struct ocelot_port *port)
+static int ocelot_mc_unsync(struct net_device *dev, const unsigned char *addr)
 {
-	struct ocelot *ocelot = port->ocelot;
-	struct netdev_hw_addr *ha, *n;
+	struct ocelot_port *port = netdev_priv(dev);
 
-	/* Free and forget all the MAC addresses stored in the port private mc
-	 * list. These are mc addresses that were previously added by calling
-	 * ocelot_mact_mc_add().
-	 */
-	list_for_each_entry_safe(ha, n, &port->mc, list) {
-		ocelot_mact_forget(ocelot, ha->addr, port->pvid);
-		list_del(&ha->list);
-		kfree(ha);
-	}
+	return ocelot_mact_forget(port->ocelot, addr, port->pvid);
 }
 
-static int ocelot_mact_mc_add(struct ocelot_port *port,
-			      struct netdev_hw_addr *hw_addr)
+static int ocelot_mc_sync(struct net_device *dev, const unsigned char *addr)
 {
-	struct ocelot *ocelot = port->ocelot;
-	struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_KERNEL);
-
-	if (!ha)
-		return -ENOMEM;
-
-	memcpy(ha, hw_addr, sizeof(*ha));
-	list_add_tail(&ha->list, &port->mc);
-
-	ocelot_mact_learn(ocelot, PGID_CPU, ha->addr, port->pvid,
-			  ENTRYTYPE_LOCKED);
+	struct ocelot_port *port = netdev_priv(dev);
 
-	return 0;
+	return ocelot_mact_learn(port->ocelot, PGID_CPU, addr, port->pvid,
+				 ENTRYTYPE_LOCKED);
 }
 
 static void ocelot_set_rx_mode(struct net_device *dev)
 {
 	struct ocelot_port *port = netdev_priv(dev);
 	struct ocelot *ocelot = port->ocelot;
-	struct netdev_hw_addr *ha;
 	int i;
 	u32 val;
 
@@ -643,13 +631,7 @@ static void ocelot_set_rx_mode(struct net_device *dev)
 	for (i = ocelot->num_phys_ports + 1; i < PGID_CPU; i++)
 		ocelot_write_rix(ocelot, val, ANA_PGID_PGID, i);
 
-	/* Handle the device multicast addresses. First remove all the
-	 * previously installed addresses and then add the latest ones to the
-	 * mac table.
-	 */
-	ocelot_mact_mc_reset(port);
-	netdev_for_each_mc_addr(ha, dev)
-		ocelot_mact_mc_add(port, ha);
+	__dev_mc_sync(dev, ocelot_mc_sync, ocelot_mc_unsync);
 }
 
 static int ocelot_port_get_phys_port_name(struct net_device *dev,
@@ -721,7 +703,8 @@ static void ocelot_get_stats64(struct net_device *dev,
 
 static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			  struct net_device *dev, const unsigned char *addr,
-			  u16 vid, u16 flags)
+			  u16 vid, u16 flags,
+			  struct netlink_ext_ack *extack)
 {
 	struct ocelot_port *port = netdev_priv(dev);
 	struct ocelot *ocelot = port->ocelot;
@@ -909,12 +892,31 @@ static int ocelot_set_features(struct net_device *dev,
 	struct ocelot_port *port = netdev_priv(dev);
 	netdev_features_t changed = dev->features ^ features;
 
+	if ((dev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC) &&
+	    port->tc.offload_cnt) {
+		netdev_err(dev,
+			   "Cannot disable HW TC offload while offloads active\n");
+		return -EBUSY;
+	}
+
 	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER)
 		ocelot_vlan_mode(port, features);
 
 	return 0;
 }
 
+static int ocelot_get_port_parent_id(struct net_device *dev,
+				     struct netdev_phys_item_id *ppid)
+{
+	struct ocelot_port *ocelot_port = netdev_priv(dev);
+	struct ocelot *ocelot = ocelot_port->ocelot;
+
+	ppid->id_len = sizeof(ocelot->base_mac);
+	memcpy(&ppid->id, &ocelot->base_mac, ppid->id_len);
+
+	return 0;
+}
+
 static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_open			= ocelot_port_open,
 	.ndo_stop			= ocelot_port_stop,
@@ -929,6 +931,8 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_vlan_rx_add_vid		= ocelot_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid		= ocelot_vlan_rx_kill_vid,
 	.ndo_set_features		= ocelot_set_features,
+	.ndo_get_port_parent_id		= ocelot_get_port_parent_id,
+	.ndo_setup_tc			= ocelot_setup_tc,
 };
 
 static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
@@ -945,10 +949,8 @@ static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 		       ETH_GSTRING_LEN);
 }
 
-static void ocelot_check_stats(struct work_struct *work)
+static void ocelot_update_stats(struct ocelot *ocelot)
 {
-	struct delayed_work *del_work = to_delayed_work(work);
-	struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work);
 	int i, j;
 
 	mutex_lock(&ocelot->stats_lock);
@@ -972,11 +974,19 @@ static void ocelot_check_stats(struct work_struct *work)
 		}
 	}
 
-	cancel_delayed_work(&ocelot->stats_work);
+	mutex_unlock(&ocelot->stats_lock);
+}
+
+static void ocelot_check_stats_work(struct work_struct *work)
+{
+	struct delayed_work *del_work = to_delayed_work(work);
+	struct ocelot *ocelot = container_of(del_work, struct ocelot,
+					     stats_work);
+
+	ocelot_update_stats(ocelot);
+
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
-
-	mutex_unlock(&ocelot->stats_lock);
 }
 
 static void ocelot_get_ethtool_stats(struct net_device *dev,
@@ -987,7 +997,7 @@ static void ocelot_get_ethtool_stats(struct net_device *dev,
 	int i;
 
 	/* check and update now */
-	ocelot_check_stats(&ocelot->stats_work.work);
+	ocelot_update_stats(ocelot);
 
 	/* Copy all counters */
 	for (i = 0; i < ocelot->num_stats; i++)
@@ -1012,25 +1022,6 @@ static const struct ethtool_ops ocelot_ethtool_ops = {
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
-static int ocelot_port_attr_get(struct net_device *dev,
-				struct switchdev_attr *attr)
-{
-	struct ocelot_port *ocelot_port = netdev_priv(dev);
-	struct ocelot *ocelot = ocelot_port->ocelot;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(ocelot->base_mac);
-		memcpy(&attr->u.ppid.id, &ocelot->base_mac,
-		       attr->u.ppid.id_len);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 static int ocelot_port_attr_stp_state_set(struct ocelot_port *ocelot_port,
 					  struct switchdev_trans *trans,
 					  u8 state)
@@ -1329,11 +1320,6 @@ static int ocelot_port_obj_del(struct net_device *dev,
 	return ret;
 }
 
-static const struct switchdev_ops ocelot_port_switchdev_ops = {
-	.switchdev_port_attr_get	= ocelot_port_attr_get,
-	.switchdev_port_attr_set	= ocelot_port_attr_set,
-};
-
 static int ocelot_port_bridge_join(struct ocelot_port *ocelot_port,
 				   struct net_device *bridge)
 {
@@ -1588,6 +1574,28 @@ struct notifier_block ocelot_netdevice_nb __read_mostly = {
 };
 EXPORT_SYMBOL(ocelot_netdevice_nb);
 
+static int ocelot_switchdev_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     ocelot_netdevice_dev_check,
+						     ocelot_port_attr_set);
+		return notifier_from_errno(err);
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ocelot_switchdev_nb __read_mostly = {
+	.notifier_call = ocelot_switchdev_event,
+};
+EXPORT_SYMBOL(ocelot_switchdev_nb);
+
 static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
 					   unsigned long event, void *ptr)
 {
@@ -1606,6 +1614,11 @@ static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
 						    ocelot_netdevice_dev_check,
 						    ocelot_port_obj_del);
 		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     ocelot_netdevice_dev_check,
+						     ocelot_port_attr_set);
+		return notifier_from_errno(err);
 	}
 
 	return NOTIFY_DONE;
@@ -1634,15 +1647,14 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 	ocelot_port->regs = regs;
 	ocelot_port->chip_port = port;
 	ocelot_port->phy = phy;
-	INIT_LIST_HEAD(&ocelot_port->mc);
 	ocelot->ports[port] = ocelot_port;
 
 	dev->netdev_ops = &ocelot_port_netdev_ops;
 	dev->ethtool_ops = &ocelot_ethtool_ops;
-	dev->switchdev_ops = &ocelot_port_switchdev_ops;
 
-	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXFCS;
-	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXFCS |
+		NETIF_F_HW_TC;
+	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC;
 
 	memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN);
 	dev->dev_addr[ETH_ALEN - 1] += port;
@@ -1658,6 +1670,9 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 	/* Basic L2 initialization */
 	ocelot_vlan_port_apply(ocelot, ocelot_port);
 
+	/* Enable vcap lookups */
+	ocelot_vcap_enable(ocelot, ocelot_port);
+
 	return 0;
 
 err_register_netdev:
@@ -1692,6 +1707,7 @@ int ocelot_init(struct ocelot *ocelot)
 
 	ocelot_mact_init(ocelot);
 	ocelot_vlan_init(ocelot);
+	ocelot_ace_init(ocelot);
 
 	for (port = 0; port < ocelot->num_phys_ports; port++) {
 		/* Clear all counters (5 groups) */
@@ -1793,7 +1809,7 @@ int ocelot_init(struct ocelot *ocelot)
 				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
 				 ANA_CPUQ_8021_CFG, i);
 
-	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats);
+	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
 	return 0;
@@ -1804,6 +1820,7 @@ void ocelot_deinit(struct ocelot *ocelot)
 {
 	destroy_workqueue(ocelot->stats_queue);
 	mutex_destroy(&ocelot->stats_lock);
+	ocelot_ace_deinit();
 }
 EXPORT_SYMBOL(ocelot_deinit);
 
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 086775f7b52f..f7eeb4806897 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -22,6 +22,7 @@
 #include "ocelot_rew.h"
 #include "ocelot_sys.h"
 #include "ocelot_qs.h"
+#include "ocelot_tc.h"
 
 #define PGID_AGGR    64
 #define PGID_SRC     80
@@ -68,6 +69,7 @@ enum ocelot_target {
 	QSYS,
 	REW,
 	SYS,
+	S2,
 	HSIO,
 	TARGET_MAX,
 };
@@ -334,6 +336,13 @@ enum ocelot_reg {
 	SYS_CM_DATA_RD,
 	SYS_CM_OP,
 	SYS_CM_DATA,
+	S2_CORE_UPDATE_CTRL = S2 << TARGET_OFFSET,
+	S2_CORE_MV_CFG,
+	S2_CACHE_ENTRY_DAT,
+	S2_CACHE_MASK_DAT,
+	S2_CACHE_ACTION_DAT,
+	S2_CACHE_CNT_DAT,
+	S2_CACHE_TG_DAT,
 };
 
 enum ocelot_regfield {
@@ -441,10 +450,6 @@ struct ocelot_port {
 	struct phy_device *phy;
 	void __iomem *regs;
 	u8 chip_port;
-	/* Keep a track of the mc addresses added to the mac table, so that they
-	 * can be removed when needed.
-	 */
-	struct list_head mc;
 
 	/* Ingress default VLAN (pvid) */
 	u16 pvid;
@@ -458,6 +463,8 @@ struct ocelot_port {
 
 	phy_interface_t phy_mode;
 	struct phy *serdes;
+
+	struct ocelot_port_tc tc;
 };
 
 u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset);
@@ -499,6 +506,7 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 		      struct phy_device *phy);
 
 extern struct notifier_block ocelot_netdevice_nb;
+extern struct notifier_block ocelot_switchdev_nb;
 extern struct notifier_block ocelot_switchdev_blocking_nb;
 
 #endif
diff --git a/drivers/net/ethernet/mscc/ocelot_ace.c b/drivers/net/ethernet/mscc/ocelot_ace.c
new file mode 100644
index 000000000000..39aca1ab4687
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_ace.c
@@ -0,0 +1,782 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Microsemi Ocelot Switch driver
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#include <linux/iopoll.h>
+#include <linux/proc_fs.h>
+
+#include "ocelot_ace.h"
+#include "ocelot_vcap.h"
+#include "ocelot_s2.h"
+
+#define OCELOT_POLICER_DISCARD 0x17f
+
+static struct ocelot_acl_block *acl_block;
+
+struct vcap_props {
+	const char *name; /* Symbolic name */
+	u16 tg_width; /* Type-group width (in bits) */
+	u16 sw_count; /* Sub word count */
+	u16 entry_count; /* Entry count */
+	u16 entry_words; /* Number of entry words */
+	u16 entry_width; /* Entry width (in bits) */
+	u16 action_count; /* Action count */
+	u16 action_words; /* Number of action words */
+	u16 action_width; /* Action width (in bits) */
+	u16 action_type_width; /* Action type width (in bits) */
+	struct {
+		u16 width; /* Action type width (in bits) */
+		u16 count; /* Action type sub word count */
+	} action_table[2];
+	u16 counter_words; /* Number of counter words */
+	u16 counter_width; /* Counter width (in bits) */
+};
+
+#define ENTRY_WIDTH 32
+#define BITS_TO_32BIT(x) (1 + (((x) - 1) / ENTRY_WIDTH))
+
+static const struct vcap_props vcap_is2 = {
+	.name = "IS2",
+	.tg_width = 2,
+	.sw_count = 4,
+	.entry_count = VCAP_IS2_CNT,
+	.entry_words = BITS_TO_32BIT(VCAP_IS2_ENTRY_WIDTH),
+	.entry_width = VCAP_IS2_ENTRY_WIDTH,
+	.action_count = (VCAP_IS2_CNT + VCAP_PORT_CNT + 2),
+	.action_words = BITS_TO_32BIT(VCAP_IS2_ACTION_WIDTH),
+	.action_width = (VCAP_IS2_ACTION_WIDTH),
+	.action_type_width = 1,
+	.action_table = {
+		{
+			.width = (IS2_AO_ACL_ID + IS2_AL_ACL_ID),
+			.count = 2
+		},
+		{
+			.width = 6,
+			.count = 4
+		},
+	},
+	.counter_words = BITS_TO_32BIT(4 * ENTRY_WIDTH),
+	.counter_width = ENTRY_WIDTH,
+};
+
+enum vcap_sel {
+	VCAP_SEL_ENTRY = 0x1,
+	VCAP_SEL_ACTION = 0x2,
+	VCAP_SEL_COUNTER = 0x4,
+	VCAP_SEL_ALL = 0x7,
+};
+
+enum vcap_cmd {
+	VCAP_CMD_WRITE = 0, /* Copy from Cache to TCAM */
+	VCAP_CMD_READ = 1, /* Copy from TCAM to Cache */
+	VCAP_CMD_MOVE_UP = 2, /* Move <count> up */
+	VCAP_CMD_MOVE_DOWN = 3, /* Move <count> down */
+	VCAP_CMD_INITIALIZE = 4, /* Write all (from cache) */
+};
+
+#define VCAP_ENTRY_WIDTH 12 /* Max entry width (32bit words) */
+#define VCAP_COUNTER_WIDTH 4 /* Max counter width (32bit words) */
+
+struct vcap_data {
+	u32 entry[VCAP_ENTRY_WIDTH]; /* ENTRY_DAT */
+	u32 mask[VCAP_ENTRY_WIDTH]; /* MASK_DAT */
+	u32 action[VCAP_ENTRY_WIDTH]; /* ACTION_DAT */
+	u32 counter[VCAP_COUNTER_WIDTH]; /* CNT_DAT */
+	u32 tg; /* TG_DAT */
+	u32 type; /* Action type */
+	u32 tg_sw; /* Current type-group */
+	u32 cnt; /* Current counter */
+	u32 key_offset; /* Current entry offset */
+	u32 action_offset; /* Current action offset */
+	u32 counter_offset; /* Current counter offset */
+	u32 tg_value; /* Current type-group value */
+	u32 tg_mask; /* Current type-group mask */
+};
+
+static u32 vcap_s2_read_update_ctrl(struct ocelot *oc)
+{
+	return ocelot_read(oc, S2_CORE_UPDATE_CTRL);
+}
+
+static void vcap_cmd(struct ocelot *oc, u16 ix, int cmd, int sel)
+{
+	u32 value = (S2_CORE_UPDATE_CTRL_UPDATE_CMD(cmd) |
+		     S2_CORE_UPDATE_CTRL_UPDATE_ADDR(ix) |
+		     S2_CORE_UPDATE_CTRL_UPDATE_SHOT);
+
+	if ((sel & VCAP_SEL_ENTRY) && ix >= vcap_is2.entry_count)
+		return;
+
+	if (!(sel & VCAP_SEL_ENTRY))
+		value |= S2_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS;
+
+	if (!(sel & VCAP_SEL_ACTION))
+		value |= S2_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS;
+
+	if (!(sel & VCAP_SEL_COUNTER))
+		value |= S2_CORE_UPDATE_CTRL_UPDATE_CNT_DIS;
+
+	ocelot_write(oc, value, S2_CORE_UPDATE_CTRL);
+	readx_poll_timeout(vcap_s2_read_update_ctrl, oc, value,
+				(value & S2_CORE_UPDATE_CTRL_UPDATE_SHOT) == 0,
+				10, 100000);
+}
+
+/* Convert from 0-based row to VCAP entry row and run command */
+static void vcap_row_cmd(struct ocelot *oc, u32 row, int cmd, int sel)
+{
+	vcap_cmd(oc, vcap_is2.entry_count - row - 1, cmd, sel);
+}
+
+static void vcap_entry2cache(struct ocelot *oc, struct vcap_data *data)
+{
+	u32 i;
+
+	for (i = 0; i < vcap_is2.entry_words; i++) {
+		ocelot_write_rix(oc, data->entry[i], S2_CACHE_ENTRY_DAT, i);
+		ocelot_write_rix(oc, ~data->mask[i], S2_CACHE_MASK_DAT, i);
+	}
+	ocelot_write(oc, data->tg, S2_CACHE_TG_DAT);
+}
+
+static void vcap_cache2entry(struct ocelot *oc, struct vcap_data *data)
+{
+	u32 i;
+
+	for (i = 0; i < vcap_is2.entry_words; i++) {
+		data->entry[i] = ocelot_read_rix(oc, S2_CACHE_ENTRY_DAT, i);
+		// Invert mask
+		data->mask[i] = ~ocelot_read_rix(oc, S2_CACHE_MASK_DAT, i);
+	}
+	data->tg = ocelot_read(oc, S2_CACHE_TG_DAT);
+}
+
+static void vcap_action2cache(struct ocelot *oc, struct vcap_data *data)
+{
+	u32 i, width, mask;
+
+	/* Encode action type */
+	width = vcap_is2.action_type_width;
+	if (width) {
+		mask = GENMASK(width, 0);
+		data->action[0] = ((data->action[0] & ~mask) | data->type);
+	}
+
+	for (i = 0; i < vcap_is2.action_words; i++)
+		ocelot_write_rix(oc, data->action[i], S2_CACHE_ACTION_DAT, i);
+
+	for (i = 0; i < vcap_is2.counter_words; i++)
+		ocelot_write_rix(oc, data->counter[i], S2_CACHE_CNT_DAT, i);
+}
+
+static void vcap_cache2action(struct ocelot *oc, struct vcap_data *data)
+{
+	u32 i, width;
+
+	for (i = 0; i < vcap_is2.action_words; i++)
+		data->action[i] = ocelot_read_rix(oc, S2_CACHE_ACTION_DAT, i);
+
+	for (i = 0; i < vcap_is2.counter_words; i++)
+		data->counter[i] = ocelot_read_rix(oc, S2_CACHE_CNT_DAT, i);
+
+	/* Extract action type */
+	width = vcap_is2.action_type_width;
+	data->type = (width ? (data->action[0] & GENMASK(width, 0)) : 0);
+}
+
+/* Calculate offsets for entry */
+static void is2_data_get(struct vcap_data *data, int ix)
+{
+	u32 i, col, offset, count, cnt, base, width = vcap_is2.tg_width;
+
+	count = (data->tg_sw == VCAP_TG_HALF ? 2 : 4);
+	col = (ix % 2);
+	cnt = (vcap_is2.sw_count / count);
+	base = (vcap_is2.sw_count - col * cnt - cnt);
+	data->tg_value = 0;
+	data->tg_mask = 0;
+	for (i = 0; i < cnt; i++) {
+		offset = ((base + i) * width);
+		data->tg_value |= (data->tg_sw << offset);
+		data->tg_mask |= GENMASK(offset + width - 1, offset);
+	}
+
+	/* Calculate key/action/counter offsets */
+	col = (count - col - 1);
+	data->key_offset = (base * vcap_is2.entry_width) / vcap_is2.sw_count;
+	data->counter_offset = (cnt * col * vcap_is2.counter_width);
+	i = data->type;
+	width = vcap_is2.action_table[i].width;
+	cnt = vcap_is2.action_table[i].count;
+	data->action_offset =
+		(((cnt * col * width) / count) + vcap_is2.action_type_width);
+}
+
+static void vcap_data_set(u32 *data, u32 offset, u32 len, u32 value)
+{
+	u32 i, v, m;
+
+	for (i = 0; i < len; i++, offset++) {
+		v = data[offset / ENTRY_WIDTH];
+		m = (1 << (offset % ENTRY_WIDTH));
+		if (value & (1 << i))
+			v |= m;
+		else
+			v &= ~m;
+		data[offset / ENTRY_WIDTH] = v;
+	}
+}
+
+static u32 vcap_data_get(u32 *data, u32 offset, u32 len)
+{
+	u32 i, v, m, value = 0;
+
+	for (i = 0; i < len; i++, offset++) {
+		v = data[offset / ENTRY_WIDTH];
+		m = (1 << (offset % ENTRY_WIDTH));
+		if (v & m)
+			value |= (1 << i);
+	}
+	return value;
+}
+
+static void vcap_key_set(struct vcap_data *data, u32 offset, u32 width,
+			 u32 value, u32 mask)
+{
+	vcap_data_set(data->entry, offset + data->key_offset, width, value);
+	vcap_data_set(data->mask, offset + data->key_offset, width, mask);
+}
+
+static void vcap_key_bytes_set(struct vcap_data *data, u32 offset, u8 *val,
+			       u8 *msk, u32 count)
+{
+	u32 i, j, n = 0, value = 0, mask = 0;
+
+	/* Data wider than 32 bits are split up in chunks of maximum 32 bits.
+	 * The 32 LSB of the data are written to the 32 MSB of the TCAM.
+	 */
+	offset += (count * 8);
+	for (i = 0; i < count; i++) {
+		j = (count - i - 1);
+		value += (val[j] << n);
+		mask += (msk[j] << n);
+		n += 8;
+		if (n == ENTRY_WIDTH || (i + 1) == count) {
+			offset -= n;
+			vcap_key_set(data, offset, n, value, mask);
+			n = 0;
+			value = 0;
+			mask = 0;
+		}
+	}
+}
+
+static void vcap_key_l4_port_set(struct vcap_data *data, u32 offset,
+				 struct ocelot_vcap_udp_tcp *port)
+{
+	vcap_key_set(data, offset, 16, port->value, port->mask);
+}
+
+static void vcap_key_bit_set(struct vcap_data *data, u32 offset,
+			     enum ocelot_vcap_bit val)
+{
+	vcap_key_set(data, offset, 1, val == OCELOT_VCAP_BIT_1 ? 1 : 0,
+		     val == OCELOT_VCAP_BIT_ANY ? 0 : 1);
+}
+
+#define VCAP_KEY_SET(fld, val, msk) \
+	vcap_key_set(&data, IS2_HKO_##fld, IS2_HKL_##fld, val, msk)
+#define VCAP_KEY_ANY_SET(fld) \
+	vcap_key_set(&data, IS2_HKO_##fld, IS2_HKL_##fld, 0, 0)
+#define VCAP_KEY_BIT_SET(fld, val) vcap_key_bit_set(&data, IS2_HKO_##fld, val)
+#define VCAP_KEY_BYTES_SET(fld, val, msk) \
+	vcap_key_bytes_set(&data, IS2_HKO_##fld, val, msk, IS2_HKL_##fld / 8)
+
+static void vcap_action_set(struct vcap_data *data, u32 offset, u32 width,
+			    u32 value)
+{
+	vcap_data_set(data->action, offset + data->action_offset, width, value);
+}
+
+#define VCAP_ACT_SET(fld, val) \
+	vcap_action_set(data, IS2_AO_##fld, IS2_AL_##fld, val)
+
+static void is2_action_set(struct vcap_data *data,
+			   enum ocelot_ace_action action)
+{
+	switch (action) {
+	case OCELOT_ACL_ACTION_DROP:
+		VCAP_ACT_SET(PORT_MASK, 0x0);
+		VCAP_ACT_SET(MASK_MODE, 0x1);
+		VCAP_ACT_SET(POLICE_ENA, 0x1);
+		VCAP_ACT_SET(POLICE_IDX, OCELOT_POLICER_DISCARD);
+		VCAP_ACT_SET(CPU_QU_NUM, 0x0);
+		VCAP_ACT_SET(CPU_COPY_ENA, 0x0);
+		break;
+	case OCELOT_ACL_ACTION_TRAP:
+		VCAP_ACT_SET(PORT_MASK, 0x0);
+		VCAP_ACT_SET(MASK_MODE, 0x0);
+		VCAP_ACT_SET(POLICE_ENA, 0x0);
+		VCAP_ACT_SET(POLICE_IDX, 0x0);
+		VCAP_ACT_SET(CPU_QU_NUM, 0x0);
+		VCAP_ACT_SET(CPU_COPY_ENA, 0x1);
+		break;
+	}
+}
+
+static void is2_entry_set(struct ocelot *ocelot, int ix,
+			  struct ocelot_ace_rule *ace)
+{
+	u32 val, msk, type, type_mask = 0xf, i, count;
+	struct ocelot_ace_vlan *tag = &ace->vlan;
+	struct ocelot_vcap_u64 payload;
+	struct vcap_data data;
+	int row = (ix / 2);
+
+	memset(&payload, 0, sizeof(payload));
+	memset(&data, 0, sizeof(data));
+
+	/* Read row */
+	vcap_row_cmd(ocelot, row, VCAP_CMD_READ, VCAP_SEL_ALL);
+	vcap_cache2entry(ocelot, &data);
+	vcap_cache2action(ocelot, &data);
+
+	data.tg_sw = VCAP_TG_HALF;
+	is2_data_get(&data, ix);
+	data.tg = (data.tg & ~data.tg_mask);
+	if (ace->prio != 0)
+		data.tg |= data.tg_value;
+
+	data.type = IS2_ACTION_TYPE_NORMAL;
+
+	VCAP_KEY_ANY_SET(PAG);
+	VCAP_KEY_SET(IGR_PORT_MASK, 0, ~BIT(ace->chip_port));
+	VCAP_KEY_BIT_SET(FIRST, OCELOT_VCAP_BIT_1);
+	VCAP_KEY_BIT_SET(HOST_MATCH, OCELOT_VCAP_BIT_ANY);
+	VCAP_KEY_BIT_SET(L2_MC, ace->dmac_mc);
+	VCAP_KEY_BIT_SET(L2_BC, ace->dmac_bc);
+	VCAP_KEY_BIT_SET(VLAN_TAGGED, tag->tagged);
+	VCAP_KEY_SET(VID, tag->vid.value, tag->vid.mask);
+	VCAP_KEY_SET(PCP, tag->pcp.value[0], tag->pcp.mask[0]);
+	VCAP_KEY_BIT_SET(DEI, tag->dei);
+
+	switch (ace->type) {
+	case OCELOT_ACE_TYPE_ETYPE: {
+		struct ocelot_ace_frame_etype *etype = &ace->frame.etype;
+
+		type = IS2_TYPE_ETYPE;
+		VCAP_KEY_BYTES_SET(L2_DMAC, etype->dmac.value,
+				   etype->dmac.mask);
+		VCAP_KEY_BYTES_SET(L2_SMAC, etype->smac.value,
+				   etype->smac.mask);
+		VCAP_KEY_BYTES_SET(MAC_ETYPE_ETYPE, etype->etype.value,
+				   etype->etype.mask);
+		VCAP_KEY_ANY_SET(MAC_ETYPE_L2_PAYLOAD); // Clear unused bits
+		vcap_key_bytes_set(&data, IS2_HKO_MAC_ETYPE_L2_PAYLOAD,
+				   etype->data.value, etype->data.mask, 2);
+		break;
+	}
+	case OCELOT_ACE_TYPE_LLC: {
+		struct ocelot_ace_frame_llc *llc = &ace->frame.llc;
+
+		type = IS2_TYPE_LLC;
+		VCAP_KEY_BYTES_SET(L2_DMAC, llc->dmac.value, llc->dmac.mask);
+		VCAP_KEY_BYTES_SET(L2_SMAC, llc->smac.value, llc->smac.mask);
+		for (i = 0; i < 4; i++) {
+			payload.value[i] = llc->llc.value[i];
+			payload.mask[i] = llc->llc.mask[i];
+		}
+		VCAP_KEY_BYTES_SET(MAC_LLC_L2_LLC, payload.value, payload.mask);
+		break;
+	}
+	case OCELOT_ACE_TYPE_SNAP: {
+		struct ocelot_ace_frame_snap *snap = &ace->frame.snap;
+
+		type = IS2_TYPE_SNAP;
+		VCAP_KEY_BYTES_SET(L2_DMAC, snap->dmac.value, snap->dmac.mask);
+		VCAP_KEY_BYTES_SET(L2_SMAC, snap->smac.value, snap->smac.mask);
+		VCAP_KEY_BYTES_SET(MAC_SNAP_L2_SNAP,
+				   ace->frame.snap.snap.value,
+				   ace->frame.snap.snap.mask);
+		break;
+	}
+	case OCELOT_ACE_TYPE_ARP: {
+		struct ocelot_ace_frame_arp *arp = &ace->frame.arp;
+
+		type = IS2_TYPE_ARP;
+		VCAP_KEY_BYTES_SET(MAC_ARP_L2_SMAC, arp->smac.value,
+				   arp->smac.mask);
+		VCAP_KEY_BIT_SET(MAC_ARP_ARP_ADDR_SPACE_OK, arp->ethernet);
+		VCAP_KEY_BIT_SET(MAC_ARP_ARP_PROTO_SPACE_OK, arp->ip);
+		VCAP_KEY_BIT_SET(MAC_ARP_ARP_LEN_OK, arp->length);
+		VCAP_KEY_BIT_SET(MAC_ARP_ARP_TGT_MATCH, arp->dmac_match);
+		VCAP_KEY_BIT_SET(MAC_ARP_ARP_SENDER_MATCH, arp->smac_match);
+		VCAP_KEY_BIT_SET(MAC_ARP_ARP_OPCODE_UNKNOWN, arp->unknown);
+
+		/* OPCODE is inverse, bit 0 is reply flag, bit 1 is RARP flag */
+		val = ((arp->req == OCELOT_VCAP_BIT_0 ? 1 : 0) |
+		       (arp->arp == OCELOT_VCAP_BIT_0 ? 2 : 0));
+		msk = ((arp->req == OCELOT_VCAP_BIT_ANY ? 0 : 1) |
+		       (arp->arp == OCELOT_VCAP_BIT_ANY ? 0 : 2));
+		VCAP_KEY_SET(MAC_ARP_ARP_OPCODE, val, msk);
+		vcap_key_bytes_set(&data, IS2_HKO_MAC_ARP_L3_IP4_DIP,
+				   arp->dip.value.addr, arp->dip.mask.addr, 4);
+		vcap_key_bytes_set(&data, IS2_HKO_MAC_ARP_L3_IP4_SIP,
+				   arp->sip.value.addr, arp->sip.mask.addr, 4);
+		VCAP_KEY_ANY_SET(MAC_ARP_DIP_EQ_SIP);
+		break;
+	}
+	case OCELOT_ACE_TYPE_IPV4:
+	case OCELOT_ACE_TYPE_IPV6: {
+		enum ocelot_vcap_bit sip_eq_dip, sport_eq_dport, seq_zero, tcp;
+		enum ocelot_vcap_bit ttl, fragment, options, tcp_ack, tcp_urg;
+		enum ocelot_vcap_bit tcp_fin, tcp_syn, tcp_rst, tcp_psh;
+		struct ocelot_ace_frame_ipv4 *ipv4 = NULL;
+		struct ocelot_ace_frame_ipv6 *ipv6 = NULL;
+		struct ocelot_vcap_udp_tcp *sport, *dport;
+		struct ocelot_vcap_ipv4 sip, dip;
+		struct ocelot_vcap_u8 proto, ds;
+		struct ocelot_vcap_u48 *ip_data;
+
+		if (ace->type == OCELOT_ACE_TYPE_IPV4) {
+			ipv4 = &ace->frame.ipv4;
+			ttl = ipv4->ttl;
+			fragment = ipv4->fragment;
+			options = ipv4->options;
+			proto = ipv4->proto;
+			ds = ipv4->ds;
+			ip_data = &ipv4->data;
+			sip = ipv4->sip;
+			dip = ipv4->dip;
+			sport = &ipv4->sport;
+			dport = &ipv4->dport;
+			tcp_fin = ipv4->tcp_fin;
+			tcp_syn = ipv4->tcp_syn;
+			tcp_rst = ipv4->tcp_rst;
+			tcp_psh = ipv4->tcp_psh;
+			tcp_ack = ipv4->tcp_ack;
+			tcp_urg = ipv4->tcp_urg;
+			sip_eq_dip = ipv4->sip_eq_dip;
+			sport_eq_dport = ipv4->sport_eq_dport;
+			seq_zero = ipv4->seq_zero;
+		} else {
+			ipv6 = &ace->frame.ipv6;
+			ttl = ipv6->ttl;
+			fragment = OCELOT_VCAP_BIT_ANY;
+			options = OCELOT_VCAP_BIT_ANY;
+			proto = ipv6->proto;
+			ds = ipv6->ds;
+			ip_data = &ipv6->data;
+			for (i = 0; i < 8; i++) {
+				val = ipv6->sip.value[i + 8];
+				msk = ipv6->sip.mask[i + 8];
+				if (i < 4) {
+					dip.value.addr[i] = val;
+					dip.mask.addr[i] = msk;
+				} else {
+					sip.value.addr[i - 4] = val;
+					sip.mask.addr[i - 4] = msk;
+				}
+			}
+			sport = &ipv6->sport;
+			dport = &ipv6->dport;
+			tcp_fin = ipv6->tcp_fin;
+			tcp_syn = ipv6->tcp_syn;
+			tcp_rst = ipv6->tcp_rst;
+			tcp_psh = ipv6->tcp_psh;
+			tcp_ack = ipv6->tcp_ack;
+			tcp_urg = ipv6->tcp_urg;
+			sip_eq_dip = ipv6->sip_eq_dip;
+			sport_eq_dport = ipv6->sport_eq_dport;
+			seq_zero = ipv6->seq_zero;
+		}
+
+		VCAP_KEY_BIT_SET(IP4,
+				 ipv4 ? OCELOT_VCAP_BIT_1 : OCELOT_VCAP_BIT_0);
+		VCAP_KEY_BIT_SET(L3_FRAGMENT, fragment);
+		VCAP_KEY_ANY_SET(L3_FRAG_OFS_GT0);
+		VCAP_KEY_BIT_SET(L3_OPTIONS, options);
+		VCAP_KEY_BIT_SET(L3_TTL_GT0, ttl);
+		VCAP_KEY_BYTES_SET(L3_TOS, ds.value, ds.mask);
+		vcap_key_bytes_set(&data, IS2_HKO_L3_IP4_DIP, dip.value.addr,
+				   dip.mask.addr, 4);
+		vcap_key_bytes_set(&data, IS2_HKO_L3_IP4_SIP, sip.value.addr,
+				   sip.mask.addr, 4);
+		VCAP_KEY_BIT_SET(DIP_EQ_SIP, sip_eq_dip);
+		val = proto.value[0];
+		msk = proto.mask[0];
+		type = IS2_TYPE_IP_UDP_TCP;
+		if (msk == 0xff && (val == 6 || val == 17)) {
+			/* UDP/TCP protocol match */
+			tcp = (val == 6 ?
+			       OCELOT_VCAP_BIT_1 : OCELOT_VCAP_BIT_0);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_TCP, tcp);
+			vcap_key_l4_port_set(&data,
+					     IS2_HKO_IP4_TCP_UDP_L4_DPORT,
+					     dport);
+			vcap_key_l4_port_set(&data,
+					     IS2_HKO_IP4_TCP_UDP_L4_SPORT,
+					     sport);
+			VCAP_KEY_ANY_SET(IP4_TCP_UDP_L4_RNG);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_SPORT_EQ_DPORT,
+					 sport_eq_dport);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_SEQUENCE_EQ0, seq_zero);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_L4_FIN, tcp_fin);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_L4_SYN, tcp_syn);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_L4_RST, tcp_rst);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_L4_PSH, tcp_psh);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_L4_ACK, tcp_ack);
+			VCAP_KEY_BIT_SET(IP4_TCP_UDP_L4_URG, tcp_urg);
+			VCAP_KEY_ANY_SET(IP4_TCP_UDP_L4_1588_DOM);
+			VCAP_KEY_ANY_SET(IP4_TCP_UDP_L4_1588_VER);
+		} else {
+			if (msk == 0) {
+				/* Any IP protocol match */
+				type_mask = IS2_TYPE_MASK_IP_ANY;
+			} else {
+				/* Non-UDP/TCP protocol match */
+				type = IS2_TYPE_IP_OTHER;
+				for (i = 0; i < 6; i++) {
+					payload.value[i] = ip_data->value[i];
+					payload.mask[i] = ip_data->mask[i];
+				}
+			}
+			VCAP_KEY_BYTES_SET(IP4_OTHER_L3_PROTO, proto.value,
+					   proto.mask);
+			VCAP_KEY_BYTES_SET(IP4_OTHER_L3_PAYLOAD, payload.value,
+					   payload.mask);
+		}
+		break;
+	}
+	case OCELOT_ACE_TYPE_ANY:
+	default:
+		type = 0;
+		type_mask = 0;
+		count = (vcap_is2.entry_width / 2);
+		for (i = (IS2_HKO_PCP + IS2_HKL_PCP); i < count;
+		     i += ENTRY_WIDTH) {
+			/* Clear entry data */
+			vcap_key_set(&data, i, min(32u, count - i), 0, 0);
+		}
+		break;
+	}
+
+	VCAP_KEY_SET(TYPE, type, type_mask);
+	is2_action_set(&data, ace->action);
+	vcap_data_set(data.counter, data.counter_offset, vcap_is2.counter_width,
+		      ace->stats.pkts);
+
+	/* Write row */
+	vcap_entry2cache(ocelot, &data);
+	vcap_action2cache(ocelot, &data);
+	vcap_row_cmd(ocelot, row, VCAP_CMD_WRITE, VCAP_SEL_ALL);
+}
+
+static void is2_entry_get(struct ocelot_ace_rule *rule, int ix)
+{
+	struct ocelot *op = rule->port->ocelot;
+	struct vcap_data data;
+	int row = (ix / 2);
+	u32 cnt;
+
+	vcap_row_cmd(op, row, VCAP_CMD_READ, VCAP_SEL_COUNTER);
+	vcap_cache2action(op, &data);
+	data.tg_sw = VCAP_TG_HALF;
+	is2_data_get(&data, ix);
+	cnt = vcap_data_get(data.counter, data.counter_offset,
+			    vcap_is2.counter_width);
+
+	rule->stats.pkts = cnt;
+}
+
+static void ocelot_ace_rule_add(struct ocelot_acl_block *block,
+				struct ocelot_ace_rule *rule)
+{
+	struct ocelot_ace_rule *tmp;
+	struct list_head *pos, *n;
+
+	block->count++;
+
+	if (list_empty(&block->rules)) {
+		list_add(&rule->list, &block->rules);
+		return;
+	}
+
+	list_for_each_safe(pos, n, &block->rules) {
+		tmp = list_entry(pos, struct ocelot_ace_rule, list);
+		if (rule->prio < tmp->prio)
+			break;
+	}
+	list_add(&rule->list, pos->prev);
+}
+
+static int ocelot_ace_rule_get_index_id(struct ocelot_acl_block *block,
+					struct ocelot_ace_rule *rule)
+{
+	struct ocelot_ace_rule *tmp;
+	int index = -1;
+
+	list_for_each_entry(tmp, &block->rules, list) {
+		++index;
+		if (rule->id == tmp->id)
+			break;
+	}
+	return index;
+}
+
+static struct ocelot_ace_rule*
+ocelot_ace_rule_get_rule_index(struct ocelot_acl_block *block, int index)
+{
+	struct ocelot_ace_rule *tmp;
+	int i = 0;
+
+	list_for_each_entry(tmp, &block->rules, list) {
+		if (i == index)
+			return tmp;
+		++i;
+	}
+
+	return NULL;
+}
+
+int ocelot_ace_rule_offload_add(struct ocelot_ace_rule *rule)
+{
+	struct ocelot_ace_rule *ace;
+	int i, index;
+
+	/* Add rule to the linked list */
+	ocelot_ace_rule_add(acl_block, rule);
+
+	/* Get the index of the inserted rule */
+	index = ocelot_ace_rule_get_index_id(acl_block, rule);
+
+	/* Move down the rules to make place for the new rule */
+	for (i = acl_block->count - 1; i > index; i--) {
+		ace = ocelot_ace_rule_get_rule_index(acl_block, i);
+		is2_entry_set(rule->port->ocelot, i, ace);
+	}
+
+	/* Now insert the new rule */
+	is2_entry_set(rule->port->ocelot, index, rule);
+	return 0;
+}
+
+static void ocelot_ace_rule_del(struct ocelot_acl_block *block,
+				struct ocelot_ace_rule *rule)
+{
+	struct ocelot_ace_rule *tmp;
+	struct list_head *pos, *q;
+
+	list_for_each_safe(pos, q, &block->rules) {
+		tmp = list_entry(pos, struct ocelot_ace_rule, list);
+		if (tmp->id == rule->id) {
+			list_del(pos);
+			kfree(tmp);
+		}
+	}
+
+	block->count--;
+}
+
+int ocelot_ace_rule_offload_del(struct ocelot_ace_rule *rule)
+{
+	struct ocelot_ace_rule del_ace;
+	struct ocelot_ace_rule *ace;
+	int i, index;
+
+	memset(&del_ace, 0, sizeof(del_ace));
+
+	/* Gets index of the rule */
+	index = ocelot_ace_rule_get_index_id(acl_block, rule);
+
+	/* Delete rule */
+	ocelot_ace_rule_del(acl_block, rule);
+
+	/* Move up all the blocks over the deleted rule */
+	for (i = index; i < acl_block->count; i++) {
+		ace = ocelot_ace_rule_get_rule_index(acl_block, i);
+		is2_entry_set(rule->port->ocelot, i, ace);
+	}
+
+	/* Now delete the last rule, because it is duplicated */
+	is2_entry_set(rule->port->ocelot, acl_block->count, &del_ace);
+
+	return 0;
+}
+
+int ocelot_ace_rule_stats_update(struct ocelot_ace_rule *rule)
+{
+	struct ocelot_ace_rule *tmp;
+	int index;
+
+	index = ocelot_ace_rule_get_index_id(acl_block, rule);
+	is2_entry_get(rule, index);
+
+	/* After we get the result we need to clear the counters */
+	tmp = ocelot_ace_rule_get_rule_index(acl_block, index);
+	tmp->stats.pkts = 0;
+	is2_entry_set(rule->port->ocelot, index, tmp);
+
+	return 0;
+}
+
+static struct ocelot_acl_block *ocelot_acl_block_create(struct ocelot *ocelot)
+{
+	struct ocelot_acl_block *block;
+
+	block = kzalloc(sizeof(*block), GFP_KERNEL);
+	if (!block)
+		return NULL;
+
+	INIT_LIST_HEAD(&block->rules);
+	block->count = 0;
+	block->ocelot = ocelot;
+
+	return block;
+}
+
+static void ocelot_acl_block_destroy(struct ocelot_acl_block *block)
+{
+	kfree(block);
+}
+
+int ocelot_ace_init(struct ocelot *ocelot)
+{
+	struct vcap_data data;
+
+	memset(&data, 0, sizeof(data));
+	vcap_entry2cache(ocelot, &data);
+	ocelot_write(ocelot, vcap_is2.entry_count, S2_CORE_MV_CFG);
+	vcap_cmd(ocelot, 0, VCAP_CMD_INITIALIZE, VCAP_SEL_ENTRY);
+
+	vcap_action2cache(ocelot, &data);
+	ocelot_write(ocelot, vcap_is2.action_count, S2_CORE_MV_CFG);
+	vcap_cmd(ocelot, 0, VCAP_CMD_INITIALIZE,
+		 VCAP_SEL_ACTION | VCAP_SEL_COUNTER);
+
+	/* Create a policer that will drop the frames for the cpu.
+	 * This policer will be used as action in the acl rules to drop
+	 * frames.
+	 */
+	ocelot_write_gix(ocelot, 0x299, ANA_POL_MODE_CFG,
+			 OCELOT_POLICER_DISCARD);
+	ocelot_write_gix(ocelot, 0x1, ANA_POL_PIR_CFG,
+			 OCELOT_POLICER_DISCARD);
+	ocelot_write_gix(ocelot, 0x3fffff, ANA_POL_PIR_STATE,
+			 OCELOT_POLICER_DISCARD);
+	ocelot_write_gix(ocelot, 0x0, ANA_POL_CIR_CFG,
+			 OCELOT_POLICER_DISCARD);
+	ocelot_write_gix(ocelot, 0x3fffff, ANA_POL_CIR_STATE,
+			 OCELOT_POLICER_DISCARD);
+
+	acl_block = ocelot_acl_block_create(ocelot);
+
+	return 0;
+}
+
+void ocelot_ace_deinit(void)
+{
+	ocelot_acl_block_destroy(acl_block);
+}
diff --git a/drivers/net/ethernet/mscc/ocelot_ace.h b/drivers/net/ethernet/mscc/ocelot_ace.h
new file mode 100644
index 000000000000..e98944c87259
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_ace.h
@@ -0,0 +1,232 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/* Microsemi Ocelot Switch driver
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_ACE_H_
+#define _MSCC_OCELOT_ACE_H_
+
+#include "ocelot.h"
+#include <net/sch_generic.h>
+#include <net/pkt_cls.h>
+
+struct ocelot_ipv4 {
+	u8 addr[4];
+};
+
+enum ocelot_vcap_bit {
+	OCELOT_VCAP_BIT_ANY,
+	OCELOT_VCAP_BIT_0,
+	OCELOT_VCAP_BIT_1
+};
+
+struct ocelot_vcap_u8 {
+	u8 value[1];
+	u8 mask[1];
+};
+
+struct ocelot_vcap_u16 {
+	u8 value[2];
+	u8 mask[2];
+};
+
+struct ocelot_vcap_u24 {
+	u8 value[3];
+	u8 mask[3];
+};
+
+struct ocelot_vcap_u32 {
+	u8 value[4];
+	u8 mask[4];
+};
+
+struct ocelot_vcap_u40 {
+	u8 value[5];
+	u8 mask[5];
+};
+
+struct ocelot_vcap_u48 {
+	u8 value[6];
+	u8 mask[6];
+};
+
+struct ocelot_vcap_u64 {
+	u8 value[8];
+	u8 mask[8];
+};
+
+struct ocelot_vcap_u128 {
+	u8 value[16];
+	u8 mask[16];
+};
+
+struct ocelot_vcap_vid {
+	u16 value;
+	u16 mask;
+};
+
+struct ocelot_vcap_ipv4 {
+	struct ocelot_ipv4 value;
+	struct ocelot_ipv4 mask;
+};
+
+struct ocelot_vcap_udp_tcp {
+	u16 value;
+	u16 mask;
+};
+
+enum ocelot_ace_type {
+	OCELOT_ACE_TYPE_ANY,
+	OCELOT_ACE_TYPE_ETYPE,
+	OCELOT_ACE_TYPE_LLC,
+	OCELOT_ACE_TYPE_SNAP,
+	OCELOT_ACE_TYPE_ARP,
+	OCELOT_ACE_TYPE_IPV4,
+	OCELOT_ACE_TYPE_IPV6
+};
+
+struct ocelot_ace_vlan {
+	struct ocelot_vcap_vid vid;    /* VLAN ID (12 bit) */
+	struct ocelot_vcap_u8  pcp;    /* PCP (3 bit) */
+	enum ocelot_vcap_bit dei;    /* DEI */
+	enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */
+};
+
+struct ocelot_ace_frame_etype {
+	struct ocelot_vcap_u48 dmac;
+	struct ocelot_vcap_u48 smac;
+	struct ocelot_vcap_u16 etype;
+	struct ocelot_vcap_u16 data; /* MAC data */
+};
+
+struct ocelot_ace_frame_llc {
+	struct ocelot_vcap_u48 dmac;
+	struct ocelot_vcap_u48 smac;
+
+	/* LLC header: DSAP at byte 0, SSAP at byte 1, Control at byte 2 */
+	struct ocelot_vcap_u32 llc;
+};
+
+struct ocelot_ace_frame_snap {
+	struct ocelot_vcap_u48 dmac;
+	struct ocelot_vcap_u48 smac;
+
+	/* SNAP header: Organization Code at byte 0, Type at byte 3 */
+	struct ocelot_vcap_u40 snap;
+};
+
+struct ocelot_ace_frame_arp {
+	struct ocelot_vcap_u48 smac;
+	enum ocelot_vcap_bit arp;	/* Opcode ARP/RARP */
+	enum ocelot_vcap_bit req;	/* Opcode request/reply */
+	enum ocelot_vcap_bit unknown;    /* Opcode unknown */
+	enum ocelot_vcap_bit smac_match; /* Sender MAC matches SMAC */
+	enum ocelot_vcap_bit dmac_match; /* Target MAC matches DMAC */
+
+	/**< Protocol addr. length 4, hardware length 6 */
+	enum ocelot_vcap_bit length;
+
+	enum ocelot_vcap_bit ip;       /* Protocol address type IP */
+	enum  ocelot_vcap_bit ethernet; /* Hardware address type Ethernet */
+	struct ocelot_vcap_ipv4 sip;     /* Sender IP address */
+	struct ocelot_vcap_ipv4 dip;     /* Target IP address */
+};
+
+struct ocelot_ace_frame_ipv4 {
+	enum ocelot_vcap_bit ttl;      /* TTL zero */
+	enum ocelot_vcap_bit fragment; /* Fragment */
+	enum ocelot_vcap_bit options;  /* Header options */
+	struct ocelot_vcap_u8 ds;
+	struct ocelot_vcap_u8 proto;      /* Protocol */
+	struct ocelot_vcap_ipv4 sip;      /* Source IP address */
+	struct ocelot_vcap_ipv4 dip;      /* Destination IP address */
+	struct ocelot_vcap_u48 data;      /* Not UDP/TCP: IP data */
+	struct ocelot_vcap_udp_tcp sport; /* UDP/TCP: Source port */
+	struct ocelot_vcap_udp_tcp dport; /* UDP/TCP: Destination port */
+	enum ocelot_vcap_bit tcp_fin;
+	enum ocelot_vcap_bit tcp_syn;
+	enum ocelot_vcap_bit tcp_rst;
+	enum ocelot_vcap_bit tcp_psh;
+	enum ocelot_vcap_bit tcp_ack;
+	enum ocelot_vcap_bit tcp_urg;
+	enum ocelot_vcap_bit sip_eq_dip;     /* SIP equals DIP  */
+	enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT  */
+	enum ocelot_vcap_bit seq_zero;       /* TCP sequence number is zero */
+};
+
+struct ocelot_ace_frame_ipv6 {
+	struct ocelot_vcap_u8 proto; /* IPv6 protocol */
+	struct ocelot_vcap_u128 sip; /* IPv6 source (byte 0-7 ignored) */
+	enum ocelot_vcap_bit ttl;  /* TTL zero */
+	struct ocelot_vcap_u8 ds;
+	struct ocelot_vcap_u48 data; /* Not UDP/TCP: IP data */
+	struct ocelot_vcap_udp_tcp sport;
+	struct ocelot_vcap_udp_tcp dport;
+	enum ocelot_vcap_bit tcp_fin;
+	enum ocelot_vcap_bit tcp_syn;
+	enum ocelot_vcap_bit tcp_rst;
+	enum ocelot_vcap_bit tcp_psh;
+	enum ocelot_vcap_bit tcp_ack;
+	enum ocelot_vcap_bit tcp_urg;
+	enum ocelot_vcap_bit sip_eq_dip;     /* SIP equals DIP  */
+	enum ocelot_vcap_bit sport_eq_dport; /* SPORT equals DPORT  */
+	enum ocelot_vcap_bit seq_zero;       /* TCP sequence number is zero */
+};
+
+enum ocelot_ace_action {
+	OCELOT_ACL_ACTION_DROP,
+	OCELOT_ACL_ACTION_TRAP,
+};
+
+struct ocelot_ace_stats {
+	u64 bytes;
+	u64 pkts;
+	u64 used;
+};
+
+struct ocelot_ace_rule {
+	struct list_head list;
+	struct ocelot_port *port;
+
+	u16 prio;
+	u32 id;
+
+	enum ocelot_ace_action action;
+	struct ocelot_ace_stats stats;
+	int chip_port;
+
+	enum ocelot_vcap_bit dmac_mc;
+	enum ocelot_vcap_bit dmac_bc;
+	struct ocelot_ace_vlan vlan;
+
+	enum ocelot_ace_type type;
+	union {
+		/* ocelot_ACE_TYPE_ANY: No specific fields */
+		struct ocelot_ace_frame_etype etype;
+		struct ocelot_ace_frame_llc llc;
+		struct ocelot_ace_frame_snap snap;
+		struct ocelot_ace_frame_arp arp;
+		struct ocelot_ace_frame_ipv4 ipv4;
+		struct ocelot_ace_frame_ipv6 ipv6;
+	} frame;
+};
+
+struct ocelot_acl_block {
+	struct list_head rules;
+	struct ocelot *ocelot;
+	int count;
+};
+
+int ocelot_ace_rule_offload_add(struct ocelot_ace_rule *rule);
+int ocelot_ace_rule_offload_del(struct ocelot_ace_rule *rule);
+int ocelot_ace_rule_stats_update(struct ocelot_ace_rule *rule);
+
+int ocelot_ace_init(struct ocelot *ocelot);
+void ocelot_ace_deinit(void);
+
+int ocelot_setup_tc_block_flower_bind(struct ocelot_port *port,
+				      struct flow_block_offload *f);
+void ocelot_setup_tc_block_flower_unbind(struct ocelot_port *port,
+					 struct flow_block_offload *f);
+
+#endif /* _MSCC_OCELOT_ACE_H_ */
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index ca3ea2fbfcd0..58bde1a9eacb 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -188,6 +188,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		{ QSYS, "qsys" },
 		{ ANA, "ana" },
 		{ QS, "qs" },
+		{ S2, "s2" },
 	};
 
 	if (!np && !pdev->dev.platform_data)
@@ -267,6 +268,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		struct phy *serdes;
 		void __iomem *regs;
 		char res_name[8];
+		int phy_mode;
 		u32 port;
 
 		if (of_property_read_u32(portnp, "reg", &port))
@@ -292,11 +294,11 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		if (err)
 			return err;
 
-		err = of_get_phy_mode(portnp);
-		if (err < 0)
+		phy_mode = of_get_phy_mode(portnp);
+		if (phy_mode < 0)
 			ocelot->ports[port]->phy_mode = PHY_INTERFACE_MODE_NA;
 		else
-			ocelot->ports[port]->phy_mode = err;
+			ocelot->ports[port]->phy_mode = phy_mode;
 
 		switch (ocelot->ports[port]->phy_mode) {
 		case PHY_INTERFACE_MODE_NA:
@@ -304,6 +306,13 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		case PHY_INTERFACE_MODE_SGMII:
 			break;
 		case PHY_INTERFACE_MODE_QSGMII:
+			/* Ensure clock signals and speed is set on all
+			 * QSGMII links
+			 */
+			ocelot_port_writel(ocelot->ports[port],
+					   DEV_CLOCK_CFG_LINK_SPEED
+					   (OCELOT_SPEED_1000),
+					   DEV_CLOCK_CFG);
 			break;
 		default:
 			dev_err(ocelot->dev,
@@ -329,6 +338,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	}
 
 	register_netdevice_notifier(&ocelot_netdevice_nb);
+	register_switchdev_notifier(&ocelot_switchdev_nb);
 	register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
 
 	dev_info(&pdev->dev, "Ocelot switch probed\n");
@@ -345,6 +355,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev)
 
 	ocelot_deinit(ocelot);
 	unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
+	unregister_switchdev_notifier(&ocelot_switchdev_nb);
 	unregister_netdevice_notifier(&ocelot_netdevice_nb);
 
 	return 0;
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
new file mode 100644
index 000000000000..7aaddc09c185
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Microsemi Ocelot Switch driver
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+
+#include "ocelot_ace.h"
+
+struct ocelot_port_block {
+	struct ocelot_acl_block *block;
+	struct ocelot_port *port;
+};
+
+static u16 get_prio(u32 prio)
+{
+	/* prio starts from 0x1000 while the ids starts from 0 */
+	return prio >> 16;
+}
+
+static int ocelot_flower_parse_action(struct flow_cls_offload *f,
+				      struct ocelot_ace_rule *rule)
+{
+	const struct flow_action_entry *a;
+	int i;
+
+	if (f->rule->action.num_entries != 1)
+		return -EOPNOTSUPP;
+
+	flow_action_for_each(i, a, &f->rule->action) {
+		switch (a->id) {
+		case FLOW_ACTION_DROP:
+			rule->action = OCELOT_ACL_ACTION_DROP;
+			break;
+		case FLOW_ACTION_TRAP:
+			rule->action = OCELOT_ACL_ACTION_TRAP;
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int ocelot_flower_parse(struct flow_cls_offload *f,
+			       struct ocelot_ace_rule *ocelot_rule)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
+
+	if (dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
+	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS))) {
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
+		u16 proto = ntohs(f->common.protocol);
+
+		/* The hw support mac matches only for MAC_ETYPE key,
+		 * therefore if other matches(port, tcp flags, etc) are added
+		 * then just bail out
+		 */
+		if ((dissector->used_keys &
+		    (BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+		     BIT(FLOW_DISSECTOR_KEY_BASIC) |
+		     BIT(FLOW_DISSECTOR_KEY_CONTROL))) !=
+		    (BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
+		     BIT(FLOW_DISSECTOR_KEY_BASIC) |
+		     BIT(FLOW_DISSECTOR_KEY_CONTROL)))
+			return -EOPNOTSUPP;
+
+		if (proto == ETH_P_IP ||
+		    proto == ETH_P_IPV6 ||
+		    proto == ETH_P_ARP)
+			return -EOPNOTSUPP;
+
+		flow_rule_match_eth_addrs(rule, &match);
+		ocelot_rule->type = OCELOT_ACE_TYPE_ETYPE;
+		ether_addr_copy(ocelot_rule->frame.etype.dmac.value,
+				match.key->dst);
+		ether_addr_copy(ocelot_rule->frame.etype.smac.value,
+				match.key->src);
+		ether_addr_copy(ocelot_rule->frame.etype.dmac.mask,
+				match.mask->dst);
+		ether_addr_copy(ocelot_rule->frame.etype.smac.mask,
+				match.mask->src);
+		goto finished_key_parsing;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		if (ntohs(match.key->n_proto) == ETH_P_IP) {
+			ocelot_rule->type = OCELOT_ACE_TYPE_IPV4;
+			ocelot_rule->frame.ipv4.proto.value[0] =
+				match.key->ip_proto;
+			ocelot_rule->frame.ipv4.proto.mask[0] =
+				match.mask->ip_proto;
+		}
+		if (ntohs(match.key->n_proto) == ETH_P_IPV6) {
+			ocelot_rule->type = OCELOT_ACE_TYPE_IPV6;
+			ocelot_rule->frame.ipv6.proto.value[0] =
+				match.key->ip_proto;
+			ocelot_rule->frame.ipv6.proto.mask[0] =
+				match.mask->ip_proto;
+		}
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) &&
+	    ntohs(f->common.protocol) == ETH_P_IP) {
+		struct flow_match_ipv4_addrs match;
+		u8 *tmp;
+
+		flow_rule_match_ipv4_addrs(rule, &match);
+		tmp = &ocelot_rule->frame.ipv4.sip.value.addr[0];
+		memcpy(tmp, &match.key->src, 4);
+
+		tmp = &ocelot_rule->frame.ipv4.sip.mask.addr[0];
+		memcpy(tmp, &match.mask->src, 4);
+
+		tmp = &ocelot_rule->frame.ipv4.dip.value.addr[0];
+		memcpy(tmp, &match.key->dst, 4);
+
+		tmp = &ocelot_rule->frame.ipv4.dip.mask.addr[0];
+		memcpy(tmp, &match.mask->dst, 4);
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) &&
+	    ntohs(f->common.protocol) == ETH_P_IPV6) {
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(rule, &match);
+		ocelot_rule->frame.ipv4.sport.value = ntohs(match.key->src);
+		ocelot_rule->frame.ipv4.sport.mask = ntohs(match.mask->src);
+		ocelot_rule->frame.ipv4.dport.value = ntohs(match.key->dst);
+		ocelot_rule->frame.ipv4.dport.mask = ntohs(match.mask->dst);
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(rule, &match);
+		ocelot_rule->type = OCELOT_ACE_TYPE_ANY;
+		ocelot_rule->vlan.vid.value = match.key->vlan_id;
+		ocelot_rule->vlan.vid.mask = match.mask->vlan_id;
+		ocelot_rule->vlan.pcp.value[0] = match.key->vlan_priority;
+		ocelot_rule->vlan.pcp.mask[0] = match.mask->vlan_priority;
+	}
+
+finished_key_parsing:
+	ocelot_rule->prio = get_prio(f->common.prio);
+	ocelot_rule->id = f->cookie;
+	return ocelot_flower_parse_action(f, ocelot_rule);
+}
+
+static
+struct ocelot_ace_rule *ocelot_ace_rule_create(struct flow_cls_offload *f,
+					       struct ocelot_port_block *block)
+{
+	struct ocelot_ace_rule *rule;
+
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return NULL;
+
+	rule->port = block->port;
+	rule->chip_port = block->port->chip_port;
+	return rule;
+}
+
+static int ocelot_flower_replace(struct flow_cls_offload *f,
+				 struct ocelot_port_block *port_block)
+{
+	struct ocelot_ace_rule *rule;
+	int ret;
+
+	rule = ocelot_ace_rule_create(f, port_block);
+	if (!rule)
+		return -ENOMEM;
+
+	ret = ocelot_flower_parse(f, rule);
+	if (ret) {
+		kfree(rule);
+		return ret;
+	}
+
+	ret = ocelot_ace_rule_offload_add(rule);
+	if (ret)
+		return ret;
+
+	port_block->port->tc.offload_cnt++;
+	return 0;
+}
+
+static int ocelot_flower_destroy(struct flow_cls_offload *f,
+				 struct ocelot_port_block *port_block)
+{
+	struct ocelot_ace_rule rule;
+	int ret;
+
+	rule.prio = get_prio(f->common.prio);
+	rule.port = port_block->port;
+	rule.id = f->cookie;
+
+	ret = ocelot_ace_rule_offload_del(&rule);
+	if (ret)
+		return ret;
+
+	port_block->port->tc.offload_cnt--;
+	return 0;
+}
+
+static int ocelot_flower_stats_update(struct flow_cls_offload *f,
+				      struct ocelot_port_block *port_block)
+{
+	struct ocelot_ace_rule rule;
+	int ret;
+
+	rule.prio = get_prio(f->common.prio);
+	rule.port = port_block->port;
+	rule.id = f->cookie;
+	ret = ocelot_ace_rule_stats_update(&rule);
+	if (ret)
+		return ret;
+
+	flow_stats_update(&f->stats, 0x0, rule.stats.pkts, 0x0);
+	return 0;
+}
+
+static int ocelot_setup_tc_cls_flower(struct flow_cls_offload *f,
+				      struct ocelot_port_block *port_block)
+{
+	switch (f->command) {
+	case FLOW_CLS_REPLACE:
+		return ocelot_flower_replace(f, port_block);
+	case FLOW_CLS_DESTROY:
+		return ocelot_flower_destroy(f, port_block);
+	case FLOW_CLS_STATS:
+		return ocelot_flower_stats_update(f, port_block);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int ocelot_setup_tc_block_cb_flower(enum tc_setup_type type,
+					   void *type_data, void *cb_priv)
+{
+	struct ocelot_port_block *port_block = cb_priv;
+
+	if (!tc_cls_can_offload_and_chain0(port_block->port->dev, type_data))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return ocelot_setup_tc_cls_flower(type_data, cb_priv);
+	case TC_SETUP_CLSMATCHALL:
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static struct ocelot_port_block*
+ocelot_port_block_create(struct ocelot_port *port)
+{
+	struct ocelot_port_block *port_block;
+
+	port_block = kzalloc(sizeof(*port_block), GFP_KERNEL);
+	if (!port_block)
+		return NULL;
+
+	port_block->port = port;
+
+	return port_block;
+}
+
+static void ocelot_port_block_destroy(struct ocelot_port_block *block)
+{
+	kfree(block);
+}
+
+static void ocelot_tc_block_unbind(void *cb_priv)
+{
+	struct ocelot_port_block *port_block = cb_priv;
+
+	ocelot_port_block_destroy(port_block);
+}
+
+int ocelot_setup_tc_block_flower_bind(struct ocelot_port *port,
+				      struct flow_block_offload *f)
+{
+	struct ocelot_port_block *port_block;
+	struct flow_block_cb *block_cb;
+	int ret;
+
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		return -EOPNOTSUPP;
+
+	block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
+					port);
+	if (!block_cb) {
+		port_block = ocelot_port_block_create(port);
+		if (!port_block)
+			return -ENOMEM;
+
+		block_cb = flow_block_cb_alloc(f->net,
+					       ocelot_setup_tc_block_cb_flower,
+					       port, port_block,
+					       ocelot_tc_block_unbind);
+		if (IS_ERR(block_cb)) {
+			ret = PTR_ERR(block_cb);
+			goto err_cb_register;
+		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, f->driver_block_list);
+	} else {
+		port_block = flow_block_cb_priv(block_cb);
+	}
+
+	flow_block_cb_incref(block_cb);
+	return 0;
+
+err_cb_register:
+	ocelot_port_block_destroy(port_block);
+
+	return ret;
+}
+
+void ocelot_setup_tc_block_flower_unbind(struct ocelot_port *port,
+					 struct flow_block_offload *f)
+{
+	struct flow_block_cb *block_cb;
+
+	block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
+					port);
+	if (!block_cb)
+		return;
+
+	if (!flow_block_cb_decref(block_cb)) {
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
+	}
+}
diff --git a/drivers/net/ethernet/mscc/ocelot_police.c b/drivers/net/ethernet/mscc/ocelot_police.c
new file mode 100644
index 000000000000..701e82dd749a
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_police.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#include "ocelot_police.h"
+
+enum mscc_qos_rate_mode {
+	MSCC_QOS_RATE_MODE_DISABLED, /* Policer/shaper disabled */
+	MSCC_QOS_RATE_MODE_LINE, /* Measure line rate in kbps incl. IPG */
+	MSCC_QOS_RATE_MODE_DATA, /* Measures data rate in kbps excl. IPG */
+	MSCC_QOS_RATE_MODE_FRAME, /* Measures frame rate in fps */
+	__MSCC_QOS_RATE_MODE_END,
+	NUM_MSCC_QOS_RATE_MODE = __MSCC_QOS_RATE_MODE_END,
+	MSCC_QOS_RATE_MODE_MAX = __MSCC_QOS_RATE_MODE_END - 1,
+};
+
+/* Types for ANA:POL[0-192]:POL_MODE_CFG.FRM_MODE */
+#define POL_MODE_LINERATE   0 /* Incl IPG. Unit: 33 1/3 kbps, 4096 bytes */
+#define POL_MODE_DATARATE   1 /* Excl IPG. Unit: 33 1/3 kbps, 4096 bytes  */
+#define POL_MODE_FRMRATE_HI 2 /* Unit: 33 1/3 fps, 32.8 frames */
+#define POL_MODE_FRMRATE_LO 3 /* Unit: 1/3 fps, 0.3 frames */
+
+/* Policer indexes */
+#define POL_IX_PORT    0    /* 0-11    : Port policers */
+#define POL_IX_QUEUE   32   /* 32-127  : Queue policers  */
+
+/* Default policer order */
+#define POL_ORDER 0x1d3 /* Ocelot policer order: Serial (QoS -> Port -> VCAP) */
+
+struct qos_policer_conf {
+	enum mscc_qos_rate_mode mode;
+	bool dlb; /* Enable DLB (dual leaky bucket mode */
+	bool cf;  /* Coupling flag (ignored in SLB mode) */
+	u32  cir; /* CIR in kbps/fps (ignored in SLB mode) */
+	u32  cbs; /* CBS in bytes/frames (ignored in SLB mode) */
+	u32  pir; /* PIR in kbps/fps */
+	u32  pbs; /* PBS in bytes/frames */
+	u8   ipg; /* Size of IPG when MSCC_QOS_RATE_MODE_LINE is chosen */
+};
+
+static int qos_policer_conf_set(struct ocelot_port *port, u32 pol_ix,
+				struct qos_policer_conf *conf)
+{
+	u32 cf = 0, cir_ena = 0, frm_mode = POL_MODE_LINERATE;
+	u32 cir = 0, cbs = 0, pir = 0, pbs = 0;
+	bool cir_discard = 0, pir_discard = 0;
+	struct ocelot *ocelot = port->ocelot;
+	u32 pbs_max = 0, cbs_max = 0;
+	u8 ipg = 20;
+	u32 value;
+
+	pir = conf->pir;
+	pbs = conf->pbs;
+
+	switch (conf->mode) {
+	case MSCC_QOS_RATE_MODE_LINE:
+	case MSCC_QOS_RATE_MODE_DATA:
+		if (conf->mode == MSCC_QOS_RATE_MODE_LINE) {
+			frm_mode = POL_MODE_LINERATE;
+			ipg = min_t(u8, GENMASK(4, 0), conf->ipg);
+		} else {
+			frm_mode = POL_MODE_DATARATE;
+		}
+		if (conf->dlb) {
+			cir_ena = 1;
+			cir = conf->cir;
+			cbs = conf->cbs;
+			if (cir == 0 && cbs == 0) {
+				/* Discard cir frames */
+				cir_discard = 1;
+			} else {
+				cir = DIV_ROUND_UP(cir, 100);
+				cir *= 3; /* 33 1/3 kbps */
+				cbs = DIV_ROUND_UP(cbs, 4096);
+				cbs = (cbs ? cbs : 1); /* No zero burst size */
+				cbs_max = 60; /* Limit burst size */
+				cf = conf->cf;
+				if (cf)
+					pir += conf->cir;
+			}
+		}
+		if (pir == 0 && pbs == 0) {
+			/* Discard PIR frames */
+			pir_discard = 1;
+		} else {
+			pir = DIV_ROUND_UP(pir, 100);
+			pir *= 3;  /* 33 1/3 kbps */
+			pbs = DIV_ROUND_UP(pbs, 4096);
+			pbs = (pbs ? pbs : 1); /* No zero burst size */
+			pbs_max = 60; /* Limit burst size */
+		}
+		break;
+	case MSCC_QOS_RATE_MODE_FRAME:
+		if (pir >= 100) {
+			frm_mode = POL_MODE_FRMRATE_HI;
+			pir = DIV_ROUND_UP(pir, 100);
+			pir *= 3;  /* 33 1/3 fps */
+			pbs = (pbs * 10) / 328; /* 32.8 frames */
+			pbs = (pbs ? pbs : 1); /* No zero burst size */
+			pbs_max = GENMASK(6, 0); /* Limit burst size */
+		} else {
+			frm_mode = POL_MODE_FRMRATE_LO;
+			if (pir == 0 && pbs == 0) {
+				/* Discard all frames */
+				pir_discard = 1;
+				cir_discard = 1;
+			} else {
+				pir *= 3; /* 1/3 fps */
+				pbs = (pbs * 10) / 3; /* 0.3 frames */
+				pbs = (pbs ? pbs : 1); /* No zero burst size */
+				pbs_max = 61; /* Limit burst size */
+			}
+		}
+		break;
+	default: /* MSCC_QOS_RATE_MODE_DISABLED */
+		/* Disable policer using maximum rate and zero burst */
+		pir = GENMASK(15, 0);
+		pbs = 0;
+		break;
+	}
+
+	/* Check limits */
+	if (pir > GENMASK(15, 0)) {
+		netdev_err(port->dev, "Invalid pir\n");
+		return -EINVAL;
+	}
+
+	if (cir > GENMASK(15, 0)) {
+		netdev_err(port->dev, "Invalid cir\n");
+		return -EINVAL;
+	}
+
+	if (pbs > pbs_max) {
+		netdev_err(port->dev, "Invalid pbs\n");
+		return -EINVAL;
+	}
+
+	if (cbs > cbs_max) {
+		netdev_err(port->dev, "Invalid cbs\n");
+		return -EINVAL;
+	}
+
+	value = (ANA_POL_MODE_CFG_IPG_SIZE(ipg) |
+		 ANA_POL_MODE_CFG_FRM_MODE(frm_mode) |
+		 (cf ? ANA_POL_MODE_CFG_DLB_COUPLED : 0) |
+		 (cir_ena ? ANA_POL_MODE_CFG_CIR_ENA : 0) |
+		 ANA_POL_MODE_CFG_OVERSHOOT_ENA);
+
+	ocelot_write_gix(ocelot, value, ANA_POL_MODE_CFG, pol_ix);
+
+	ocelot_write_gix(ocelot,
+			 ANA_POL_PIR_CFG_PIR_RATE(pir) |
+			 ANA_POL_PIR_CFG_PIR_BURST(pbs),
+			 ANA_POL_PIR_CFG, pol_ix);
+
+	ocelot_write_gix(ocelot,
+			 (pir_discard ? GENMASK(22, 0) : 0),
+			 ANA_POL_PIR_STATE, pol_ix);
+
+	ocelot_write_gix(ocelot,
+			 ANA_POL_CIR_CFG_CIR_RATE(cir) |
+			 ANA_POL_CIR_CFG_CIR_BURST(cbs),
+			 ANA_POL_CIR_CFG, pol_ix);
+
+	ocelot_write_gix(ocelot,
+			 (cir_discard ? GENMASK(22, 0) : 0),
+			 ANA_POL_CIR_STATE, pol_ix);
+
+	return 0;
+}
+
+int ocelot_port_policer_add(struct ocelot_port *port,
+			    struct ocelot_policer *pol)
+{
+	struct ocelot *ocelot = port->ocelot;
+	struct qos_policer_conf pp = { 0 };
+	int err;
+
+	if (!pol)
+		return -EINVAL;
+
+	pp.mode = MSCC_QOS_RATE_MODE_DATA;
+	pp.pir = pol->rate;
+	pp.pbs = pol->burst;
+
+	netdev_dbg(port->dev,
+		   "%s: port %u pir %u kbps, pbs %u bytes\n",
+		   __func__, port->chip_port, pp.pir, pp.pbs);
+
+	err = qos_policer_conf_set(port, POL_IX_PORT + port->chip_port, &pp);
+	if (err)
+		return err;
+
+	ocelot_rmw_gix(ocelot,
+		       ANA_PORT_POL_CFG_PORT_POL_ENA |
+		       ANA_PORT_POL_CFG_POL_ORDER(POL_ORDER),
+		       ANA_PORT_POL_CFG_PORT_POL_ENA |
+		       ANA_PORT_POL_CFG_POL_ORDER_M,
+		       ANA_PORT_POL_CFG, port->chip_port);
+
+	return 0;
+}
+
+int ocelot_port_policer_del(struct ocelot_port *port)
+{
+	struct ocelot *ocelot = port->ocelot;
+	struct qos_policer_conf pp = { 0 };
+	int err;
+
+	netdev_dbg(port->dev, "%s: port %u\n", __func__, port->chip_port);
+
+	pp.mode = MSCC_QOS_RATE_MODE_DISABLED;
+
+	err = qos_policer_conf_set(port, POL_IX_PORT + port->chip_port, &pp);
+	if (err)
+		return err;
+
+	ocelot_rmw_gix(ocelot,
+		       ANA_PORT_POL_CFG_POL_ORDER(POL_ORDER),
+		       ANA_PORT_POL_CFG_PORT_POL_ENA |
+		       ANA_PORT_POL_CFG_POL_ORDER_M,
+		       ANA_PORT_POL_CFG, port->chip_port);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mscc/ocelot_police.h b/drivers/net/ethernet/mscc/ocelot_police.h
new file mode 100644
index 000000000000..d1137f79efda
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_police.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/* Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_POLICE_H_
+#define _MSCC_OCELOT_POLICE_H_
+
+#include "ocelot.h"
+
+struct ocelot_policer {
+	u32 rate; /* kilobit per second */
+	u32 burst; /* bytes */
+};
+
+int ocelot_port_policer_add(struct ocelot_port *port,
+			    struct ocelot_policer *pol);
+
+int ocelot_port_policer_del(struct ocelot_port *port);
+
+#endif /* _MSCC_OCELOT_POLICE_H_ */
diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c
index 9271af18b93b..6c387f994ec5 100644
--- a/drivers/net/ethernet/mscc/ocelot_regs.c
+++ b/drivers/net/ethernet/mscc/ocelot_regs.c
@@ -224,12 +224,23 @@ static const u32 ocelot_sys_regmap[] = {
 	REG(SYS_PTP_CFG,                   0x0006c4),
 };
 
+static const u32 ocelot_s2_regmap[] = {
+	REG(S2_CORE_UPDATE_CTRL,           0x000000),
+	REG(S2_CORE_MV_CFG,                0x000004),
+	REG(S2_CACHE_ENTRY_DAT,            0x000008),
+	REG(S2_CACHE_MASK_DAT,             0x000108),
+	REG(S2_CACHE_ACTION_DAT,           0x000208),
+	REG(S2_CACHE_CNT_DAT,              0x000308),
+	REG(S2_CACHE_TG_DAT,               0x000388),
+};
+
 static const u32 *ocelot_regmap[] = {
 	[ANA] = ocelot_ana_regmap,
 	[QS] = ocelot_qs_regmap,
 	[QSYS] = ocelot_qsys_regmap,
 	[REW] = ocelot_rew_regmap,
 	[SYS] = ocelot_sys_regmap,
+	[S2] = ocelot_s2_regmap,
 };
 
 static const struct reg_field ocelot_regfields[] = {
diff --git a/drivers/net/ethernet/mscc/ocelot_s2.h b/drivers/net/ethernet/mscc/ocelot_s2.h
new file mode 100644
index 000000000000..80107bec2e45
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_s2.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/* Microsemi Ocelot Switch driver
+ * Copyright (c) 2018 Microsemi Corporation
+ */
+
+#ifndef _OCELOT_S2_CORE_H_
+#define _OCELOT_S2_CORE_H_
+
+#define S2_CORE_UPDATE_CTRL_UPDATE_CMD(x)      (((x) << 22) & GENMASK(24, 22))
+#define S2_CORE_UPDATE_CTRL_UPDATE_CMD_M       GENMASK(24, 22)
+#define S2_CORE_UPDATE_CTRL_UPDATE_CMD_X(x)    (((x) & GENMASK(24, 22)) >> 22)
+#define S2_CORE_UPDATE_CTRL_UPDATE_ENTRY_DIS   BIT(21)
+#define S2_CORE_UPDATE_CTRL_UPDATE_ACTION_DIS  BIT(20)
+#define S2_CORE_UPDATE_CTRL_UPDATE_CNT_DIS     BIT(19)
+#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR(x)     (((x) << 3) & GENMASK(18, 3))
+#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR_M      GENMASK(18, 3)
+#define S2_CORE_UPDATE_CTRL_UPDATE_ADDR_X(x)   (((x) & GENMASK(18, 3)) >> 3)
+#define S2_CORE_UPDATE_CTRL_UPDATE_SHOT        BIT(2)
+#define S2_CORE_UPDATE_CTRL_CLEAR_CACHE        BIT(1)
+#define S2_CORE_UPDATE_CTRL_MV_TRAFFIC_IGN     BIT(0)
+
+#define S2_CORE_MV_CFG_MV_NUM_POS(x)           (((x) << 16) & GENMASK(31, 16))
+#define S2_CORE_MV_CFG_MV_NUM_POS_M            GENMASK(31, 16)
+#define S2_CORE_MV_CFG_MV_NUM_POS_X(x)         (((x) & GENMASK(31, 16)) >> 16)
+#define S2_CORE_MV_CFG_MV_SIZE(x)              ((x) & GENMASK(15, 0))
+#define S2_CORE_MV_CFG_MV_SIZE_M               GENMASK(15, 0)
+
+#define S2_CACHE_ENTRY_DAT_RSZ                 0x4
+
+#define S2_CACHE_MASK_DAT_RSZ                  0x4
+
+#define S2_CACHE_ACTION_DAT_RSZ                0x4
+
+#define S2_CACHE_CNT_DAT_RSZ                   0x4
+
+#define S2_STICKY_VCAP_ROW_DELETED_STICKY      BIT(0)
+
+#define S2_BIST_CTRL_TCAM_BIST                 BIT(1)
+#define S2_BIST_CTRL_TCAM_INIT                 BIT(0)
+
+#define S2_BIST_CFG_TCAM_BIST_SOE_ENA          BIT(8)
+#define S2_BIST_CFG_TCAM_HCG_DIS               BIT(7)
+#define S2_BIST_CFG_TCAM_CG_DIS                BIT(6)
+#define S2_BIST_CFG_TCAM_BIAS(x)               ((x) & GENMASK(5, 0))
+#define S2_BIST_CFG_TCAM_BIAS_M                GENMASK(5, 0)
+
+#define S2_BIST_STAT_BIST_RT_ERR               BIT(15)
+#define S2_BIST_STAT_BIST_PENC_ERR             BIT(14)
+#define S2_BIST_STAT_BIST_COMP_ERR             BIT(13)
+#define S2_BIST_STAT_BIST_ADDR_ERR             BIT(12)
+#define S2_BIST_STAT_BIST_BL1E_ERR             BIT(11)
+#define S2_BIST_STAT_BIST_BL1_ERR              BIT(10)
+#define S2_BIST_STAT_BIST_BL0E_ERR             BIT(9)
+#define S2_BIST_STAT_BIST_BL0_ERR              BIT(8)
+#define S2_BIST_STAT_BIST_PH1_ERR              BIT(7)
+#define S2_BIST_STAT_BIST_PH0_ERR              BIT(6)
+#define S2_BIST_STAT_BIST_PV1_ERR              BIT(5)
+#define S2_BIST_STAT_BIST_PV0_ERR              BIT(4)
+#define S2_BIST_STAT_BIST_RUN                  BIT(3)
+#define S2_BIST_STAT_BIST_ERR                  BIT(2)
+#define S2_BIST_STAT_BIST_BUSY                 BIT(1)
+#define S2_BIST_STAT_TCAM_RDY                  BIT(0)
+
+#endif /* _OCELOT_S2_CORE_H_ */
diff --git a/drivers/net/ethernet/mscc/ocelot_tc.c b/drivers/net/ethernet/mscc/ocelot_tc.c
new file mode 100644
index 000000000000..9e6464ffae5d
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_tc.c
@@ -0,0 +1,197 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/* Microsemi Ocelot Switch TC driver
+ *
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#include "ocelot_tc.h"
+#include "ocelot_police.h"
+#include "ocelot_ace.h"
+#include <net/pkt_cls.h>
+
+static int ocelot_setup_tc_cls_matchall(struct ocelot_port *port,
+					struct tc_cls_matchall_offload *f,
+					bool ingress)
+{
+	struct netlink_ext_ack *extack = f->common.extack;
+	struct ocelot_policer pol = { 0 };
+	struct flow_action_entry *action;
+	int err;
+
+	netdev_dbg(port->dev, "%s: port %u command %d cookie %lu\n",
+		   __func__, port->chip_port, f->command, f->cookie);
+
+	if (!ingress) {
+		NL_SET_ERR_MSG_MOD(extack, "Only ingress is supported");
+		return -EOPNOTSUPP;
+	}
+
+	switch (f->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		if (!flow_offload_has_one_action(&f->rule->action)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only one action is supported");
+			return -EOPNOTSUPP;
+		}
+
+		if (port->tc.block_shared) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Rate limit is not supported on shared blocks");
+			return -EOPNOTSUPP;
+		}
+
+		action = &f->rule->action.entries[0];
+
+		if (action->id != FLOW_ACTION_POLICE) {
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
+			return -EOPNOTSUPP;
+		}
+
+		if (port->tc.police_id && port->tc.police_id != f->cookie) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only one policer per port is supported\n");
+			return -EEXIST;
+		}
+
+		pol.rate = (u32)div_u64(action->police.rate_bytes_ps, 1000) * 8;
+		pol.burst = (u32)div_u64(action->police.rate_bytes_ps *
+					 PSCHED_NS2TICKS(action->police.burst),
+					 PSCHED_TICKS_PER_SEC);
+
+		err = ocelot_port_policer_add(port, &pol);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Could not add policer\n");
+			return err;
+		}
+
+		port->tc.police_id = f->cookie;
+		port->tc.offload_cnt++;
+		return 0;
+	case TC_CLSMATCHALL_DESTROY:
+		if (port->tc.police_id != f->cookie)
+			return -ENOENT;
+
+		err = ocelot_port_policer_del(port);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Could not delete policer\n");
+			return err;
+		}
+		port->tc.police_id = 0;
+		port->tc.offload_cnt--;
+		return 0;
+	case TC_CLSMATCHALL_STATS: /* fall through */
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int ocelot_setup_tc_block_cb(enum tc_setup_type type,
+				    void *type_data,
+				    void *cb_priv, bool ingress)
+{
+	struct ocelot_port *port = cb_priv;
+
+	if (!tc_cls_can_offload_and_chain0(port->dev, type_data))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSMATCHALL:
+		netdev_dbg(port->dev, "tc_block_cb: TC_SETUP_CLSMATCHALL %s\n",
+			   ingress ? "ingress" : "egress");
+
+		return ocelot_setup_tc_cls_matchall(port, type_data, ingress);
+	case TC_SETUP_CLSFLOWER:
+		return 0;
+	default:
+		netdev_dbg(port->dev, "tc_block_cb: type %d %s\n",
+			   type,
+			   ingress ? "ingress" : "egress");
+
+		return -EOPNOTSUPP;
+	}
+}
+
+static int ocelot_setup_tc_block_cb_ig(enum tc_setup_type type,
+				       void *type_data,
+				       void *cb_priv)
+{
+	return ocelot_setup_tc_block_cb(type, type_data,
+					cb_priv, true);
+}
+
+static int ocelot_setup_tc_block_cb_eg(enum tc_setup_type type,
+				       void *type_data,
+				       void *cb_priv)
+{
+	return ocelot_setup_tc_block_cb(type, type_data,
+					cb_priv, false);
+}
+
+static LIST_HEAD(ocelot_block_cb_list);
+
+static int ocelot_setup_tc_block(struct ocelot_port *port,
+				 struct flow_block_offload *f)
+{
+	struct flow_block_cb *block_cb;
+	tc_setup_cb_t *cb;
+	int err;
+
+	netdev_dbg(port->dev, "tc_block command %d, binder_type %d\n",
+		   f->command, f->binder_type);
+
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
+		cb = ocelot_setup_tc_block_cb_ig;
+		port->tc.block_shared = f->block_shared;
+	} else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
+		cb = ocelot_setup_tc_block_cb_eg;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	f->driver_block_list = &ocelot_block_cb_list;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		if (flow_block_cb_is_busy(cb, port, &ocelot_block_cb_list))
+			return -EBUSY;
+
+		block_cb = flow_block_cb_alloc(f->net, cb, port, port, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		err = ocelot_setup_tc_block_flower_bind(port, f);
+		if (err < 0) {
+			flow_block_cb_free(block_cb);
+			return err;
+		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, f->driver_block_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
+		block_cb = flow_block_cb_lookup(f, cb, port);
+		if (!block_cb)
+			return -ENOENT;
+
+		ocelot_setup_tc_block_flower_unbind(port, f);
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int ocelot_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		    void *type_data)
+{
+	struct ocelot_port *port = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return ocelot_setup_tc_block(port, type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
diff --git a/drivers/net/ethernet/mscc/ocelot_tc.h b/drivers/net/ethernet/mscc/ocelot_tc.h
new file mode 100644
index 000000000000..61757c2250a6
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_tc.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/* Microsemi Ocelot Switch driver
+ *
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#ifndef _MSCC_OCELOT_TC_H_
+#define _MSCC_OCELOT_TC_H_
+
+#include <linux/netdevice.h>
+
+struct ocelot_port_tc {
+	bool block_shared;
+	unsigned long offload_cnt;
+
+	unsigned long police_id;
+};
+
+int ocelot_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		    void *type_data);
+
+#endif /* _MSCC_OCELOT_TC_H_ */
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.h b/drivers/net/ethernet/mscc/ocelot_vcap.h
new file mode 100644
index 000000000000..e22eac1da783
--- /dev/null
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.h
@@ -0,0 +1,403 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ * Microsemi Ocelot Switch driver
+ * Copyright (c) 2019 Microsemi Corporation
+ */
+
+#ifndef _OCELOT_VCAP_H_
+#define _OCELOT_VCAP_H_
+
+/* =================================================================
+ *  VCAP Common
+ * =================================================================
+ */
+
+/* VCAP Type-Group values */
+#define VCAP_TG_NONE 0 /* Entry is invalid */
+#define VCAP_TG_FULL 1 /* Full entry */
+#define VCAP_TG_HALF 2 /* Half entry */
+#define VCAP_TG_QUARTER 3 /* Quarter entry */
+
+/* =================================================================
+ *  VCAP IS2
+ * =================================================================
+ */
+
+#define VCAP_IS2_CNT 64
+#define VCAP_IS2_ENTRY_WIDTH 376
+#define VCAP_IS2_ACTION_WIDTH 99
+#define VCAP_PORT_CNT 11
+
+/* IS2 half key types */
+#define IS2_TYPE_ETYPE 0
+#define IS2_TYPE_LLC 1
+#define IS2_TYPE_SNAP 2
+#define IS2_TYPE_ARP 3
+#define IS2_TYPE_IP_UDP_TCP 4
+#define IS2_TYPE_IP_OTHER 5
+#define IS2_TYPE_IPV6 6
+#define IS2_TYPE_OAM 7
+#define IS2_TYPE_SMAC_SIP6 8
+#define IS2_TYPE_ANY 100 /* Pseudo type */
+
+/* IS2 half key type mask for matching any IP */
+#define IS2_TYPE_MASK_IP_ANY 0xe
+
+/* IS2 action types */
+#define IS2_ACTION_TYPE_NORMAL 0
+#define IS2_ACTION_TYPE_SMAC_SIP 1
+
+/* IS2 MASK_MODE values */
+#define IS2_ACT_MASK_MODE_NONE 0
+#define IS2_ACT_MASK_MODE_FILTER 1
+#define IS2_ACT_MASK_MODE_POLICY 2
+#define IS2_ACT_MASK_MODE_REDIR 3
+
+/* IS2 REW_OP values */
+#define IS2_ACT_REW_OP_NONE 0
+#define IS2_ACT_REW_OP_PTP_ONE 2
+#define IS2_ACT_REW_OP_PTP_TWO 3
+#define IS2_ACT_REW_OP_SPECIAL 8
+#define IS2_ACT_REW_OP_PTP_ORG 9
+#define IS2_ACT_REW_OP_PTP_ONE_SUB_DELAY_1 (IS2_ACT_REW_OP_PTP_ONE | (1 << 3))
+#define IS2_ACT_REW_OP_PTP_ONE_SUB_DELAY_2 (IS2_ACT_REW_OP_PTP_ONE | (2 << 3))
+#define IS2_ACT_REW_OP_PTP_ONE_ADD_DELAY (IS2_ACT_REW_OP_PTP_ONE | (1 << 5))
+#define IS2_ACT_REW_OP_PTP_ONE_ADD_SUB BIT(7)
+
+#define VCAP_PORT_WIDTH 4
+
+/* IS2 quarter key - SMAC_SIP4 */
+#define IS2_QKO_IGR_PORT 0
+#define IS2_QKL_IGR_PORT VCAP_PORT_WIDTH
+#define IS2_QKO_L2_SMAC (IS2_QKO_IGR_PORT + IS2_QKL_IGR_PORT)
+#define IS2_QKL_L2_SMAC 48
+#define IS2_QKO_L3_IP4_SIP (IS2_QKO_L2_SMAC + IS2_QKL_L2_SMAC)
+#define IS2_QKL_L3_IP4_SIP 32
+
+/* IS2 half key - common */
+#define IS2_HKO_TYPE 0
+#define IS2_HKL_TYPE 4
+#define IS2_HKO_FIRST (IS2_HKO_TYPE + IS2_HKL_TYPE)
+#define IS2_HKL_FIRST 1
+#define IS2_HKO_PAG (IS2_HKO_FIRST + IS2_HKL_FIRST)
+#define IS2_HKL_PAG 8
+#define IS2_HKO_IGR_PORT_MASK (IS2_HKO_PAG + IS2_HKL_PAG)
+#define IS2_HKL_IGR_PORT_MASK (VCAP_PORT_CNT + 1)
+#define IS2_HKO_SERVICE_FRM (IS2_HKO_IGR_PORT_MASK + IS2_HKL_IGR_PORT_MASK)
+#define IS2_HKL_SERVICE_FRM 1
+#define IS2_HKO_HOST_MATCH (IS2_HKO_SERVICE_FRM + IS2_HKL_SERVICE_FRM)
+#define IS2_HKL_HOST_MATCH 1
+#define IS2_HKO_L2_MC (IS2_HKO_HOST_MATCH + IS2_HKL_HOST_MATCH)
+#define IS2_HKL_L2_MC 1
+#define IS2_HKO_L2_BC (IS2_HKO_L2_MC + IS2_HKL_L2_MC)
+#define IS2_HKL_L2_BC 1
+#define IS2_HKO_VLAN_TAGGED (IS2_HKO_L2_BC + IS2_HKL_L2_BC)
+#define IS2_HKL_VLAN_TAGGED 1
+#define IS2_HKO_VID (IS2_HKO_VLAN_TAGGED + IS2_HKL_VLAN_TAGGED)
+#define IS2_HKL_VID 12
+#define IS2_HKO_DEI (IS2_HKO_VID + IS2_HKL_VID)
+#define IS2_HKL_DEI 1
+#define IS2_HKO_PCP (IS2_HKO_DEI + IS2_HKL_DEI)
+#define IS2_HKL_PCP 3
+
+/* IS2 half key - MAC_ETYPE/MAC_LLC/MAC_SNAP/OAM common */
+#define IS2_HKO_L2_DMAC (IS2_HKO_PCP + IS2_HKL_PCP)
+#define IS2_HKL_L2_DMAC 48
+#define IS2_HKO_L2_SMAC (IS2_HKO_L2_DMAC + IS2_HKL_L2_DMAC)
+#define IS2_HKL_L2_SMAC 48
+
+/* IS2 half key - MAC_ETYPE */
+#define IS2_HKO_MAC_ETYPE_ETYPE (IS2_HKO_L2_SMAC + IS2_HKL_L2_SMAC)
+#define IS2_HKL_MAC_ETYPE_ETYPE 16
+#define IS2_HKO_MAC_ETYPE_L2_PAYLOAD                                           \
+	(IS2_HKO_MAC_ETYPE_ETYPE + IS2_HKL_MAC_ETYPE_ETYPE)
+#define IS2_HKL_MAC_ETYPE_L2_PAYLOAD 27
+
+/* IS2 half key - MAC_LLC */
+#define IS2_HKO_MAC_LLC_L2_LLC IS2_HKO_MAC_ETYPE_ETYPE
+#define IS2_HKL_MAC_LLC_L2_LLC 40
+
+/* IS2 half key - MAC_SNAP */
+#define IS2_HKO_MAC_SNAP_L2_SNAP IS2_HKO_MAC_ETYPE_ETYPE
+#define IS2_HKL_MAC_SNAP_L2_SNAP 40
+
+/* IS2 half key - ARP */
+#define IS2_HKO_MAC_ARP_L2_SMAC IS2_HKO_L2_DMAC
+#define IS2_HKL_MAC_ARP_L2_SMAC 48
+#define IS2_HKO_MAC_ARP_ARP_ADDR_SPACE_OK                                      \
+	(IS2_HKO_MAC_ARP_L2_SMAC + IS2_HKL_MAC_ARP_L2_SMAC)
+#define IS2_HKL_MAC_ARP_ARP_ADDR_SPACE_OK 1
+#define IS2_HKO_MAC_ARP_ARP_PROTO_SPACE_OK                                     \
+	(IS2_HKO_MAC_ARP_ARP_ADDR_SPACE_OK + IS2_HKL_MAC_ARP_ARP_ADDR_SPACE_OK)
+#define IS2_HKL_MAC_ARP_ARP_PROTO_SPACE_OK 1
+#define IS2_HKO_MAC_ARP_ARP_LEN_OK                                             \
+	(IS2_HKO_MAC_ARP_ARP_PROTO_SPACE_OK +                                  \
+	 IS2_HKL_MAC_ARP_ARP_PROTO_SPACE_OK)
+#define IS2_HKL_MAC_ARP_ARP_LEN_OK 1
+#define IS2_HKO_MAC_ARP_ARP_TGT_MATCH                                          \
+	(IS2_HKO_MAC_ARP_ARP_LEN_OK + IS2_HKL_MAC_ARP_ARP_LEN_OK)
+#define IS2_HKL_MAC_ARP_ARP_TGT_MATCH 1
+#define IS2_HKO_MAC_ARP_ARP_SENDER_MATCH                                       \
+	(IS2_HKO_MAC_ARP_ARP_TGT_MATCH + IS2_HKL_MAC_ARP_ARP_TGT_MATCH)
+#define IS2_HKL_MAC_ARP_ARP_SENDER_MATCH 1
+#define IS2_HKO_MAC_ARP_ARP_OPCODE_UNKNOWN                                     \
+	(IS2_HKO_MAC_ARP_ARP_SENDER_MATCH + IS2_HKL_MAC_ARP_ARP_SENDER_MATCH)
+#define IS2_HKL_MAC_ARP_ARP_OPCODE_UNKNOWN 1
+#define IS2_HKO_MAC_ARP_ARP_OPCODE                                             \
+	(IS2_HKO_MAC_ARP_ARP_OPCODE_UNKNOWN +                                  \
+	 IS2_HKL_MAC_ARP_ARP_OPCODE_UNKNOWN)
+#define IS2_HKL_MAC_ARP_ARP_OPCODE 2
+#define IS2_HKO_MAC_ARP_L3_IP4_DIP                                             \
+	(IS2_HKO_MAC_ARP_ARP_OPCODE + IS2_HKL_MAC_ARP_ARP_OPCODE)
+#define IS2_HKL_MAC_ARP_L3_IP4_DIP 32
+#define IS2_HKO_MAC_ARP_L3_IP4_SIP                                             \
+	(IS2_HKO_MAC_ARP_L3_IP4_DIP + IS2_HKL_MAC_ARP_L3_IP4_DIP)
+#define IS2_HKL_MAC_ARP_L3_IP4_SIP 32
+#define IS2_HKO_MAC_ARP_DIP_EQ_SIP                                             \
+	(IS2_HKO_MAC_ARP_L3_IP4_SIP + IS2_HKL_MAC_ARP_L3_IP4_SIP)
+#define IS2_HKL_MAC_ARP_DIP_EQ_SIP 1
+
+/* IS2 half key - IP4_TCP_UDP/IP4_OTHER common */
+#define IS2_HKO_IP4 IS2_HKO_L2_DMAC
+#define IS2_HKL_IP4 1
+#define IS2_HKO_L3_FRAGMENT (IS2_HKO_IP4 + IS2_HKL_IP4)
+#define IS2_HKL_L3_FRAGMENT 1
+#define IS2_HKO_L3_FRAG_OFS_GT0 (IS2_HKO_L3_FRAGMENT + IS2_HKL_L3_FRAGMENT)
+#define IS2_HKL_L3_FRAG_OFS_GT0 1
+#define IS2_HKO_L3_OPTIONS (IS2_HKO_L3_FRAG_OFS_GT0 + IS2_HKL_L3_FRAG_OFS_GT0)
+#define IS2_HKL_L3_OPTIONS 1
+#define IS2_HKO_L3_TTL_GT0 (IS2_HKO_L3_OPTIONS + IS2_HKL_L3_OPTIONS)
+#define IS2_HKL_L3_TTL_GT0 1
+#define IS2_HKO_L3_TOS (IS2_HKO_L3_TTL_GT0 + IS2_HKL_L3_TTL_GT0)
+#define IS2_HKL_L3_TOS 8
+#define IS2_HKO_L3_IP4_DIP (IS2_HKO_L3_TOS + IS2_HKL_L3_TOS)
+#define IS2_HKL_L3_IP4_DIP 32
+#define IS2_HKO_L3_IP4_SIP (IS2_HKO_L3_IP4_DIP + IS2_HKL_L3_IP4_DIP)
+#define IS2_HKL_L3_IP4_SIP 32
+#define IS2_HKO_DIP_EQ_SIP (IS2_HKO_L3_IP4_SIP + IS2_HKL_L3_IP4_SIP)
+#define IS2_HKL_DIP_EQ_SIP 1
+
+/* IS2 half key - IP4_TCP_UDP */
+#define IS2_HKO_IP4_TCP_UDP_TCP (IS2_HKO_DIP_EQ_SIP + IS2_HKL_DIP_EQ_SIP)
+#define IS2_HKL_IP4_TCP_UDP_TCP 1
+#define IS2_HKO_IP4_TCP_UDP_L4_DPORT                                           \
+	(IS2_HKO_IP4_TCP_UDP_TCP + IS2_HKL_IP4_TCP_UDP_TCP)
+#define IS2_HKL_IP4_TCP_UDP_L4_DPORT 16
+#define IS2_HKO_IP4_TCP_UDP_L4_SPORT                                           \
+	(IS2_HKO_IP4_TCP_UDP_L4_DPORT + IS2_HKL_IP4_TCP_UDP_L4_DPORT)
+#define IS2_HKL_IP4_TCP_UDP_L4_SPORT 16
+#define IS2_HKO_IP4_TCP_UDP_L4_RNG                                             \
+	(IS2_HKO_IP4_TCP_UDP_L4_SPORT + IS2_HKL_IP4_TCP_UDP_L4_SPORT)
+#define IS2_HKL_IP4_TCP_UDP_L4_RNG 8
+#define IS2_HKO_IP4_TCP_UDP_SPORT_EQ_DPORT                                     \
+	(IS2_HKO_IP4_TCP_UDP_L4_RNG + IS2_HKL_IP4_TCP_UDP_L4_RNG)
+#define IS2_HKL_IP4_TCP_UDP_SPORT_EQ_DPORT 1
+#define IS2_HKO_IP4_TCP_UDP_SEQUENCE_EQ0                                       \
+	(IS2_HKO_IP4_TCP_UDP_SPORT_EQ_DPORT +                                  \
+	 IS2_HKL_IP4_TCP_UDP_SPORT_EQ_DPORT)
+#define IS2_HKL_IP4_TCP_UDP_SEQUENCE_EQ0 1
+#define IS2_HKO_IP4_TCP_UDP_L4_FIN                                             \
+	(IS2_HKO_IP4_TCP_UDP_SEQUENCE_EQ0 + IS2_HKL_IP4_TCP_UDP_SEQUENCE_EQ0)
+#define IS2_HKL_IP4_TCP_UDP_L4_FIN 1
+#define IS2_HKO_IP4_TCP_UDP_L4_SYN                                             \
+	(IS2_HKO_IP4_TCP_UDP_L4_FIN + IS2_HKL_IP4_TCP_UDP_L4_FIN)
+#define IS2_HKL_IP4_TCP_UDP_L4_SYN 1
+#define IS2_HKO_IP4_TCP_UDP_L4_RST                                             \
+	(IS2_HKO_IP4_TCP_UDP_L4_SYN + IS2_HKL_IP4_TCP_UDP_L4_SYN)
+#define IS2_HKL_IP4_TCP_UDP_L4_RST 1
+#define IS2_HKO_IP4_TCP_UDP_L4_PSH                                             \
+	(IS2_HKO_IP4_TCP_UDP_L4_RST + IS2_HKL_IP4_TCP_UDP_L4_RST)
+#define IS2_HKL_IP4_TCP_UDP_L4_PSH 1
+#define IS2_HKO_IP4_TCP_UDP_L4_ACK                                             \
+	(IS2_HKO_IP4_TCP_UDP_L4_PSH + IS2_HKL_IP4_TCP_UDP_L4_PSH)
+#define IS2_HKL_IP4_TCP_UDP_L4_ACK 1
+#define IS2_HKO_IP4_TCP_UDP_L4_URG                                             \
+	(IS2_HKO_IP4_TCP_UDP_L4_ACK + IS2_HKL_IP4_TCP_UDP_L4_ACK)
+#define IS2_HKL_IP4_TCP_UDP_L4_URG 1
+#define IS2_HKO_IP4_TCP_UDP_L4_1588_DOM                                        \
+	(IS2_HKO_IP4_TCP_UDP_L4_URG + IS2_HKL_IP4_TCP_UDP_L4_URG)
+#define IS2_HKL_IP4_TCP_UDP_L4_1588_DOM 8
+#define IS2_HKO_IP4_TCP_UDP_L4_1588_VER                                        \
+	(IS2_HKO_IP4_TCP_UDP_L4_1588_DOM + IS2_HKL_IP4_TCP_UDP_L4_1588_DOM)
+#define IS2_HKL_IP4_TCP_UDP_L4_1588_VER 4
+
+/* IS2 half key - IP4_OTHER */
+#define IS2_HKO_IP4_OTHER_L3_PROTO IS2_HKO_IP4_TCP_UDP_TCP
+#define IS2_HKL_IP4_OTHER_L3_PROTO 8
+#define IS2_HKO_IP4_OTHER_L3_PAYLOAD                                           \
+	(IS2_HKO_IP4_OTHER_L3_PROTO + IS2_HKL_IP4_OTHER_L3_PROTO)
+#define IS2_HKL_IP4_OTHER_L3_PAYLOAD 56
+
+/* IS2 half key - IP6_STD */
+#define IS2_HKO_IP6_STD_L3_TTL_GT0 IS2_HKO_L2_DMAC
+#define IS2_HKL_IP6_STD_L3_TTL_GT0 1
+#define IS2_HKO_IP6_STD_L3_IP6_SIP                                             \
+	(IS2_HKO_IP6_STD_L3_TTL_GT0 + IS2_HKL_IP6_STD_L3_TTL_GT0)
+#define IS2_HKL_IP6_STD_L3_IP6_SIP 128
+#define IS2_HKO_IP6_STD_L3_PROTO                                               \
+	(IS2_HKO_IP6_STD_L3_IP6_SIP + IS2_HKL_IP6_STD_L3_IP6_SIP)
+#define IS2_HKL_IP6_STD_L3_PROTO 8
+
+/* IS2 half key - OAM */
+#define IS2_HKO_OAM_OAM_MEL_FLAGS IS2_HKO_MAC_ETYPE_ETYPE
+#define IS2_HKL_OAM_OAM_MEL_FLAGS 7
+#define IS2_HKO_OAM_OAM_VER                                                    \
+	(IS2_HKO_OAM_OAM_MEL_FLAGS + IS2_HKL_OAM_OAM_MEL_FLAGS)
+#define IS2_HKL_OAM_OAM_VER 5
+#define IS2_HKO_OAM_OAM_OPCODE (IS2_HKO_OAM_OAM_VER + IS2_HKL_OAM_OAM_VER)
+#define IS2_HKL_OAM_OAM_OPCODE 8
+#define IS2_HKO_OAM_OAM_FLAGS (IS2_HKO_OAM_OAM_OPCODE + IS2_HKL_OAM_OAM_OPCODE)
+#define IS2_HKL_OAM_OAM_FLAGS 8
+#define IS2_HKO_OAM_OAM_MEPID (IS2_HKO_OAM_OAM_FLAGS + IS2_HKL_OAM_OAM_FLAGS)
+#define IS2_HKL_OAM_OAM_MEPID 16
+#define IS2_HKO_OAM_OAM_CCM_CNTS_EQ0                                           \
+	(IS2_HKO_OAM_OAM_MEPID + IS2_HKL_OAM_OAM_MEPID)
+#define IS2_HKL_OAM_OAM_CCM_CNTS_EQ0 1
+
+/* IS2 half key - SMAC_SIP6 */
+#define IS2_HKO_SMAC_SIP6_IGR_PORT IS2_HKL_TYPE
+#define IS2_HKL_SMAC_SIP6_IGR_PORT VCAP_PORT_WIDTH
+#define IS2_HKO_SMAC_SIP6_L2_SMAC                                              \
+	(IS2_HKO_SMAC_SIP6_IGR_PORT + IS2_HKL_SMAC_SIP6_IGR_PORT)
+#define IS2_HKL_SMAC_SIP6_L2_SMAC 48
+#define IS2_HKO_SMAC_SIP6_L3_IP6_SIP                                           \
+	(IS2_HKO_SMAC_SIP6_L2_SMAC + IS2_HKL_SMAC_SIP6_L2_SMAC)
+#define IS2_HKL_SMAC_SIP6_L3_IP6_SIP 128
+
+/* IS2 full key - common */
+#define IS2_FKO_TYPE 0
+#define IS2_FKL_TYPE 2
+#define IS2_FKO_FIRST (IS2_FKO_TYPE + IS2_FKL_TYPE)
+#define IS2_FKL_FIRST 1
+#define IS2_FKO_PAG (IS2_FKO_FIRST + IS2_FKL_FIRST)
+#define IS2_FKL_PAG 8
+#define IS2_FKO_IGR_PORT_MASK (IS2_FKO_PAG + IS2_FKL_PAG)
+#define IS2_FKL_IGR_PORT_MASK (VCAP_PORT_CNT + 1)
+#define IS2_FKO_SERVICE_FRM (IS2_FKO_IGR_PORT_MASK + IS2_FKL_IGR_PORT_MASK)
+#define IS2_FKL_SERVICE_FRM 1
+#define IS2_FKO_HOST_MATCH (IS2_FKO_SERVICE_FRM + IS2_FKL_SERVICE_FRM)
+#define IS2_FKL_HOST_MATCH 1
+#define IS2_FKO_L2_MC (IS2_FKO_HOST_MATCH + IS2_FKL_HOST_MATCH)
+#define IS2_FKL_L2_MC 1
+#define IS2_FKO_L2_BC (IS2_FKO_L2_MC + IS2_FKL_L2_MC)
+#define IS2_FKL_L2_BC 1
+#define IS2_FKO_VLAN_TAGGED (IS2_FKO_L2_BC + IS2_FKL_L2_BC)
+#define IS2_FKL_VLAN_TAGGED 1
+#define IS2_FKO_VID (IS2_FKO_VLAN_TAGGED + IS2_FKL_VLAN_TAGGED)
+#define IS2_FKL_VID 12
+#define IS2_FKO_DEI (IS2_FKO_VID + IS2_FKL_VID)
+#define IS2_FKL_DEI 1
+#define IS2_FKO_PCP (IS2_FKO_DEI + IS2_FKL_DEI)
+#define IS2_FKL_PCP 3
+
+/* IS2 full key - IP6_TCP_UDP/IP6_OTHER common */
+#define IS2_FKO_L3_TTL_GT0 (IS2_FKO_PCP + IS2_FKL_PCP)
+#define IS2_FKL_L3_TTL_GT0 1
+#define IS2_FKO_L3_TOS (IS2_FKO_L3_TTL_GT0 + IS2_FKL_L3_TTL_GT0)
+#define IS2_FKL_L3_TOS 8
+#define IS2_FKO_L3_IP6_DIP (IS2_FKO_L3_TOS + IS2_FKL_L3_TOS)
+#define IS2_FKL_L3_IP6_DIP 128
+#define IS2_FKO_L3_IP6_SIP (IS2_FKO_L3_IP6_DIP + IS2_FKL_L3_IP6_DIP)
+#define IS2_FKL_L3_IP6_SIP 128
+#define IS2_FKO_DIP_EQ_SIP (IS2_FKO_L3_IP6_SIP + IS2_FKL_L3_IP6_SIP)
+#define IS2_FKL_DIP_EQ_SIP 1
+
+/* IS2 full key - IP6_TCP_UDP */
+#define IS2_FKO_IP6_TCP_UDP_TCP (IS2_FKO_DIP_EQ_SIP + IS2_FKL_DIP_EQ_SIP)
+#define IS2_FKL_IP6_TCP_UDP_TCP 1
+#define IS2_FKO_IP6_TCP_UDP_L4_DPORT                                           \
+	(IS2_FKO_IP6_TCP_UDP_TCP + IS2_FKL_IP6_TCP_UDP_TCP)
+#define IS2_FKL_IP6_TCP_UDP_L4_DPORT 16
+#define IS2_FKO_IP6_TCP_UDP_L4_SPORT                                           \
+	(IS2_FKO_IP6_TCP_UDP_L4_DPORT + IS2_FKL_IP6_TCP_UDP_L4_DPORT)
+#define IS2_FKL_IP6_TCP_UDP_L4_SPORT 16
+#define IS2_FKO_IP6_TCP_UDP_L4_RNG                                             \
+	(IS2_FKO_IP6_TCP_UDP_L4_SPORT + IS2_FKL_IP6_TCP_UDP_L4_SPORT)
+#define IS2_FKL_IP6_TCP_UDP_L4_RNG 8
+#define IS2_FKO_IP6_TCP_UDP_SPORT_EQ_DPORT                                     \
+	(IS2_FKO_IP6_TCP_UDP_L4_RNG + IS2_FKL_IP6_TCP_UDP_L4_RNG)
+#define IS2_FKL_IP6_TCP_UDP_SPORT_EQ_DPORT 1
+#define IS2_FKO_IP6_TCP_UDP_SEQUENCE_EQ0                                       \
+	(IS2_FKO_IP6_TCP_UDP_SPORT_EQ_DPORT +                                  \
+	 IS2_FKL_IP6_TCP_UDP_SPORT_EQ_DPORT)
+#define IS2_FKL_IP6_TCP_UDP_SEQUENCE_EQ0 1
+#define IS2_FKO_IP6_TCP_UDP_L4_FIN                                             \
+	(IS2_FKO_IP6_TCP_UDP_SEQUENCE_EQ0 + IS2_FKL_IP6_TCP_UDP_SEQUENCE_EQ0)
+#define IS2_FKL_IP6_TCP_UDP_L4_FIN 1
+#define IS2_FKO_IP6_TCP_UDP_L4_SYN                                             \
+	(IS2_FKO_IP6_TCP_UDP_L4_FIN + IS2_FKL_IP6_TCP_UDP_L4_FIN)
+#define IS2_FKL_IP6_TCP_UDP_L4_SYN 1
+#define IS2_FKO_IP6_TCP_UDP_L4_RST                                             \
+	(IS2_FKO_IP6_TCP_UDP_L4_SYN + IS2_FKL_IP6_TCP_UDP_L4_SYN)
+#define IS2_FKL_IP6_TCP_UDP_L4_RST 1
+#define IS2_FKO_IP6_TCP_UDP_L4_PSH                                             \
+	(IS2_FKO_IP6_TCP_UDP_L4_RST + IS2_FKL_IP6_TCP_UDP_L4_RST)
+#define IS2_FKL_IP6_TCP_UDP_L4_PSH 1
+#define IS2_FKO_IP6_TCP_UDP_L4_ACK                                             \
+	(IS2_FKO_IP6_TCP_UDP_L4_PSH + IS2_FKL_IP6_TCP_UDP_L4_PSH)
+#define IS2_FKL_IP6_TCP_UDP_L4_ACK 1
+#define IS2_FKO_IP6_TCP_UDP_L4_URG                                             \
+	(IS2_FKO_IP6_TCP_UDP_L4_ACK + IS2_FKL_IP6_TCP_UDP_L4_ACK)
+#define IS2_FKL_IP6_TCP_UDP_L4_URG 1
+#define IS2_FKO_IP6_TCP_UDP_L4_1588_DOM                                        \
+	(IS2_FKO_IP6_TCP_UDP_L4_URG + IS2_FKL_IP6_TCP_UDP_L4_URG)
+#define IS2_FKL_IP6_TCP_UDP_L4_1588_DOM 8
+#define IS2_FKO_IP6_TCP_UDP_L4_1588_VER                                        \
+	(IS2_FKO_IP6_TCP_UDP_L4_1588_DOM + IS2_FKL_IP6_TCP_UDP_L4_1588_DOM)
+#define IS2_FKL_IP6_TCP_UDP_L4_1588_VER 4
+
+/* IS2 full key - IP6_OTHER */
+#define IS2_FKO_IP6_OTHER_L3_PROTO IS2_FKO_IP6_TCP_UDP_TCP
+#define IS2_FKL_IP6_OTHER_L3_PROTO 8
+#define IS2_FKO_IP6_OTHER_L3_PAYLOAD                                           \
+	(IS2_FKO_IP6_OTHER_L3_PROTO + IS2_FKL_IP6_OTHER_L3_PROTO)
+#define IS2_FKL_IP6_OTHER_L3_PAYLOAD 56
+
+/* IS2 full key - CUSTOM */
+#define IS2_FKO_CUSTOM_CUSTOM_TYPE IS2_FKO_L3_TTL_GT0
+#define IS2_FKL_CUSTOM_CUSTOM_TYPE 1
+#define IS2_FKO_CUSTOM_CUSTOM                                                  \
+	(IS2_FKO_CUSTOM_CUSTOM_TYPE + IS2_FKL_CUSTOM_CUSTOM_TYPE)
+#define IS2_FKL_CUSTOM_CUSTOM 320
+
+/* IS2 action - BASE_TYPE */
+#define IS2_AO_HIT_ME_ONCE 0
+#define IS2_AL_HIT_ME_ONCE 1
+#define IS2_AO_CPU_COPY_ENA (IS2_AO_HIT_ME_ONCE + IS2_AL_HIT_ME_ONCE)
+#define IS2_AL_CPU_COPY_ENA 1
+#define IS2_AO_CPU_QU_NUM (IS2_AO_CPU_COPY_ENA + IS2_AL_CPU_COPY_ENA)
+#define IS2_AL_CPU_QU_NUM 3
+#define IS2_AO_MASK_MODE (IS2_AO_CPU_QU_NUM + IS2_AL_CPU_QU_NUM)
+#define IS2_AL_MASK_MODE 2
+#define IS2_AO_MIRROR_ENA (IS2_AO_MASK_MODE + IS2_AL_MASK_MODE)
+#define IS2_AL_MIRROR_ENA 1
+#define IS2_AO_LRN_DIS (IS2_AO_MIRROR_ENA + IS2_AL_MIRROR_ENA)
+#define IS2_AL_LRN_DIS 1
+#define IS2_AO_POLICE_ENA (IS2_AO_LRN_DIS + IS2_AL_LRN_DIS)
+#define IS2_AL_POLICE_ENA 1
+#define IS2_AO_POLICE_IDX (IS2_AO_POLICE_ENA + IS2_AL_POLICE_ENA)
+#define IS2_AL_POLICE_IDX 9
+#define IS2_AO_POLICE_VCAP_ONLY (IS2_AO_POLICE_IDX + IS2_AL_POLICE_IDX)
+#define IS2_AL_POLICE_VCAP_ONLY 1
+#define IS2_AO_PORT_MASK (IS2_AO_POLICE_VCAP_ONLY + IS2_AL_POLICE_VCAP_ONLY)
+#define IS2_AL_PORT_MASK VCAP_PORT_CNT
+#define IS2_AO_REW_OP (IS2_AO_PORT_MASK + IS2_AL_PORT_MASK)
+#define IS2_AL_REW_OP 9
+#define IS2_AO_LM_CNT_DIS (IS2_AO_REW_OP + IS2_AL_REW_OP)
+#define IS2_AL_LM_CNT_DIS 1
+#define IS2_AO_ISDX_ENA                                                        \
+	(IS2_AO_LM_CNT_DIS + IS2_AL_LM_CNT_DIS + 1) /* Reserved bit */
+#define IS2_AL_ISDX_ENA 1
+#define IS2_AO_ACL_ID (IS2_AO_ISDX_ENA + IS2_AL_ISDX_ENA)
+#define IS2_AL_ACL_ID 6
+
+/* IS2 action - SMAC_SIP */
+#define IS2_AO_SMAC_SIP_CPU_COPY_ENA 0
+#define IS2_AL_SMAC_SIP_CPU_COPY_ENA 1
+#define IS2_AO_SMAC_SIP_CPU_QU_NUM 1
+#define IS2_AL_SMAC_SIP_CPU_QU_NUM 3
+#define IS2_AO_SMAC_SIP_FWD_KILL_ENA 4
+#define IS2_AL_SMAC_SIP_FWD_KILL_ENA 1
+#define IS2_AO_SMAC_SIP_HOST_MATCH 5
+#define IS2_AL_SMAC_SIP_HOST_MATCH 1
+
+#endif /* _OCELOT_VCAP_H_ */
diff --git a/drivers/net/ethernet/myricom/Kconfig b/drivers/net/ethernet/myricom/Kconfig
index 9645c7245bbf..6bc993eae4c4 100644
--- a/drivers/net/ethernet/myricom/Kconfig
+++ b/drivers/net/ethernet/myricom/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Myricom device configuration
 #
diff --git a/drivers/net/ethernet/myricom/Makefile b/drivers/net/ethernet/myricom/Makefile
index 296c0a10056b..122fbd94a372 100644
--- a/drivers/net/ethernet/myricom/Makefile
+++ b/drivers/net/ethernet/myricom/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Myricom network device drivers.
 #
diff --git a/drivers/net/ethernet/myricom/myri10ge/Makefile b/drivers/net/ethernet/myricom/myri10ge/Makefile
index 5df891647aee..8d9585c9db69 100644
--- a/drivers/net/ethernet/myricom/myri10ge/Makefile
+++ b/drivers/net/ethernet/myricom/myri10ge/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Myricom Myri-10G ethernet driver
 #
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 19ce0e605096..d8b7fba96d58 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -1408,7 +1408,7 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index)
 		if (skb) {
 			ss->stats.tx_bytes += skb->len;
 			ss->stats.tx_packets++;
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 			if (len)
 				pci_unmap_single(pdev,
 						 dma_unmap_addr(&tx->info[idx],
@@ -1439,7 +1439,6 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index)
 			tx->queue_active = 0;
 			put_be32(htonl(1), tx->send_stop);
 			mb();
-			mmiowb();
 		}
 		__netif_tx_unlock(dev_queue);
 	}
@@ -2861,7 +2860,6 @@ again:
 		tx->queue_active = 1;
 		put_be32(htonl(1), tx->send_go);
 		mb();
-		mmiowb();
 	}
 	tx->pkt_start++;
 	if ((avail - count) < MXGEFW_MAX_SEND_DESC) {
diff --git a/drivers/net/ethernet/natsemi/Kconfig b/drivers/net/ethernet/natsemi/Kconfig
index 017fb2322589..c519c1f30225 100644
--- a/drivers/net/ethernet/natsemi/Kconfig
+++ b/drivers/net/ethernet/natsemi/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # National Semiconductor device configuration
 #
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index b9a1a9f999ea..1a2634cbbb69 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -2173,7 +2173,7 @@ static void netdev_tx_done(struct net_device *dev)
 					np->tx_skbuff[entry]->len,
 					PCI_DMA_TODEVICE);
 		/* Free the original skb. */
-		dev_kfree_skb_irq(np->tx_skbuff[entry]);
+		dev_consume_skb_irq(np->tx_skbuff[entry]);
 		np->tx_skbuff[entry] = NULL;
 	}
 	if (netif_queue_stopped(dev) &&
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 958fced4dacf..6af9a7eee114 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 #define VERSION "0.23"
 /* ns83820.c by Benjamin LaHaise with contributions.
  *
@@ -10,21 +11,6 @@
  *
  * Mmmm, chocolate vanilla mocha...
  *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- *
  * ChangeLog
  * =========
  *	20010414	0.1 - created
@@ -1003,7 +989,7 @@ static void do_tx_done(struct net_device *ndev)
 					addr,
 					len,
 					PCI_DMA_TODEVICE);
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 			atomic_dec(&dev->nr_tx_skbs);
 		} else
 			pci_unmap_page(dev->pci_dev,
@@ -1869,56 +1855,28 @@ static unsigned ns83820_mii_write_reg(struct ns83820 *dev, unsigned phy, unsigne
 static void ns83820_probe_phy(struct net_device *ndev)
 {
 	struct ns83820 *dev = PRIV(ndev);
-	static int first;
-	int i;
-#define MII_PHYIDR1	0x02
-#define MII_PHYIDR2	0x03
-
-#if 0
-	if (!first) {
-		unsigned tmp;
-		ns83820_mii_read_reg(dev, 1, 0x09);
-		ns83820_mii_write_reg(dev, 1, 0x10, 0x0d3e);
-
-		tmp = ns83820_mii_read_reg(dev, 1, 0x00);
-		ns83820_mii_write_reg(dev, 1, 0x00, tmp | 0x8000);
-		udelay(1300);
-		ns83820_mii_read_reg(dev, 1, 0x09);
-	}
-#endif
-	first = 1;
-
-	for (i=1; i<2; i++) {
-		int j;
-		unsigned a, b;
-		a = ns83820_mii_read_reg(dev, i, MII_PHYIDR1);
-		b = ns83820_mii_read_reg(dev, i, MII_PHYIDR2);
-
-		//printk("%s: phy %d: 0x%04x 0x%04x\n",
-		//	ndev->name, i, a, b);
-
-		for (j=0; j<0x16; j+=4) {
-			dprintk("%s: [0x%02x] %04x %04x %04x %04x\n",
-				ndev->name, j,
-				ns83820_mii_read_reg(dev, i, 0 + j),
-				ns83820_mii_read_reg(dev, i, 1 + j),
-				ns83820_mii_read_reg(dev, i, 2 + j),
-				ns83820_mii_read_reg(dev, i, 3 + j)
-				);
-		}
-	}
-	{
-		unsigned a, b;
-		/* read firmware version: memory addr is 0x8402 and 0x8403 */
-		ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
-		ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
-		a = ns83820_mii_read_reg(dev, 1, 0x1d);
-
-		ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
-		ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
-		b = ns83820_mii_read_reg(dev, 1, 0x1d);
-		dprintk("version: 0x%04x 0x%04x\n", a, b);
+	int j;
+	unsigned a, b;
+
+	for (j = 0; j < 0x16; j += 4) {
+		dprintk("%s: [0x%02x] %04x %04x %04x %04x\n",
+			ndev->name, j,
+			ns83820_mii_read_reg(dev, 1, 0 + j),
+			ns83820_mii_read_reg(dev, 1, 1 + j),
+			ns83820_mii_read_reg(dev, 1, 2 + j),
+			ns83820_mii_read_reg(dev, 1, 3 + j)
+			);
 	}
+
+	/* read firmware version: memory addr is 0x8402 and 0x8403 */
+	ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
+	ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
+	a = ns83820_mii_read_reg(dev, 1, 0x1d);
+
+	ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
+	ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
+	b = ns83820_mii_read_reg(dev, 1, 0x1d);
+	dprintk("version: 0x%04x 0x%04x\n", a, b);
 }
 #endif
 
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index c805dcbebd02..d0a01e8f000a 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * sonic.c
  *
@@ -328,7 +329,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 				}
 
 				/* We must free the original skb */
-				dev_kfree_skb_irq(lp->tx_skb[entry]);
+				dev_consume_skb_irq(lp->tx_skb[entry]);
 				lp->tx_skb[entry] = NULL;
 				/* and unmap DMA buffer */
 				dma_unmap_single(lp->device, lp->tx_laddr[entry], lp->tx_len[entry], DMA_TO_DEVICE);
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index 7df20561e3fa..5e630f3a0189 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Exar device configuration
 #
diff --git a/drivers/net/ethernet/neterion/Makefile b/drivers/net/ethernet/neterion/Makefile
index 70c8058a601a..87ede8a47bb8 100644
--- a/drivers/net/ethernet/neterion/Makefile
+++ b/drivers/net/ethernet/neterion/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Exar network device drivers.
 #
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 82be90075695..3b2ae1a21678 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -3055,7 +3055,7 @@ static void tx_intr_handler(struct fifo_info *fifo_data)
 
 		/* Updating the statistics block */
 		swstats->mem_freed += skb->truesize;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 
 		get_info.offset++;
 		if (get_info.offset == get_info.fifo_len + 1)
@@ -4153,8 +4153,6 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	writeq(val64, &tx_fifo->List_Control);
 
-	mmiowb();
-
 	put_off++;
 	if (put_off == fifo->tx_curr_put_info.fifo_len + 1)
 		put_off = 0;
diff --git a/drivers/net/ethernet/neterion/vxge/Makefile b/drivers/net/ethernet/neterion/vxge/Makefile
index b625e2c503f5..0820e81ca7fb 100644
--- a/drivers/net/ethernet/neterion/vxge/Makefile
+++ b/drivers/net/ethernet/neterion/vxge/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for Exar Corp's X3100 Series 10 GbE PCIe I/O
 # Virtualized Server Adapter linux driver
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 7cde387e5ec6..51cd57ab3d95 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -2366,6 +2366,7 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 				dma_object->addr))) {
 			vxge_os_dma_free(devh->pdev, memblock,
 				&dma_object->acc_handle);
+			memblock = NULL;
 			goto exit;
 		}
 
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 5ae3fa82909f..1d334f2e0a56 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -114,7 +114,7 @@ static inline void VXGE_COMPLETE_VPATH_TX(struct vxge_fifo *fifo)
 
 		/* free SKBs */
 		for (temp = completed; temp != skb_ptr; temp++)
-			dev_kfree_skb_irq(*temp);
+			dev_consume_skb_irq(*temp);
 	} while (more);
 }
 
@@ -1826,7 +1826,6 @@ static int vxge_poll_msix(struct napi_struct *napi, int budget)
 		vxge_hw_channel_msix_unmask(
 				(struct __vxge_hw_channel *)ring->handle,
 				ring->rx_vector_no);
-		mmiowb();
 	}
 
 	/* We are copying and returning the local variable, in case if after
@@ -2234,8 +2233,6 @@ static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id)
 	vxge_hw_channel_msix_unmask((struct __vxge_hw_channel *)fifo->handle,
 				    fifo->tx_vector_no);
 
-	mmiowb();
-
 	return IRQ_HANDLED;
 }
 
@@ -2272,14 +2269,12 @@ vxge_alarm_msix_handle(int irq, void *dev_id)
 		 */
 		vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle, msix_id);
 		vxge_hw_vpath_msix_clear(vdev->vpaths[i].handle, msix_id);
-		mmiowb();
 
 		status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle,
 			vdev->exec_mode);
 		if (status == VXGE_HW_OK) {
 			vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle,
 						  msix_id);
-			mmiowb();
 			continue;
 		}
 		vxge_debug_intr(VXGE_ERR,
@@ -2553,7 +2548,7 @@ static int vxge_add_isr(struct vxgedev *vdev)
 			vxge_debug_init(VXGE_ERR,
 				"%s: Defaulting to INTA",
 				vdev->ndev->name);
-				goto INTA_MODE;
+			goto INTA_MODE;
 		}
 
 		msix_idx = (vdev->vpaths[0].handle->vpath->vp_id *
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index 59e77e3086bb..709d20d9938f 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -1399,11 +1399,7 @@ static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo,
 		VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop),
 		&fifo->nofl_db->control_0);
 
-	mmiowb();
-
 	writeq(txdl_ptr, &fifo->nofl_db->txdl_ptr);
-
-	mmiowb();
 }
 
 /**
diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig
index 66f15b05b65e..bac5be4d4f43 100644
--- a/drivers/net/ethernet/netronome/Kconfig
+++ b/drivers/net/ethernet/netronome/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Netronome device configuration
 #
@@ -19,7 +20,8 @@ config NFP
 	tristate "Netronome(R) NFP4000/NFP6000 NIC driver"
 	depends on PCI && PCI_MSI
 	depends on VXLAN || VXLAN=n
-	depends on MAY_USE_DEVLINK
+	depends on TLS && TLS_DEVICE || TLS_DEVICE=n
+	select NET_DEVLINK
 	---help---
 	  This driver supports the Netronome(R) NFP4000/NFP6000 based
 	  cards working as a advanced Ethernet NIC.  It works with both
diff --git a/drivers/net/ethernet/netronome/Makefile b/drivers/net/ethernet/netronome/Makefile
index 7fb3b84b5556..d9a3948e8bde 100644
--- a/drivers/net/ethernet/netronome/Makefile
+++ b/drivers/net/ethernet/netronome/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Netronome network device drivers
 #
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 47c708f08ade..2805641965f3 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -15,6 +15,8 @@ nfp-objs := \
 	    nfpcore/nfp_resource.o \
 	    nfpcore/nfp_rtsym.o \
 	    nfpcore/nfp_target.o \
+	    ccm.o \
+	    ccm_mbox.o \
 	    nfp_asm.o \
 	    nfp_app.o \
 	    nfp_app_nic.o \
@@ -33,6 +35,11 @@ nfp-objs := \
 	    nfp_shared_buf.o \
 	    nic/main.o
 
+ifeq ($(CONFIG_TLS_DEVICE),y)
+nfp-objs += \
+	    crypto/tls.o
+endif
+
 ifeq ($(CONFIG_NFP_APP_FLOWER),y)
 nfp-objs += \
 	    flower/action.o \
@@ -42,7 +49,8 @@ nfp-objs += \
 	    flower/match.o \
 	    flower/metadata.o \
 	    flower/offload.o \
-	    flower/tunnel_conf.o
+	    flower/tunnel_conf.o \
+	    flower/qos_conf.o
 endif
 
 ifeq ($(CONFIG_BPF_SYSCALL),y)
diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c
index 9852080cf454..23ebddfb9532 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/cls.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c
@@ -39,7 +39,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode,
 	}
 	if (knode->sel->off || knode->sel->offshift || knode->sel->offmask ||
 	    knode->sel->offoff || knode->fshift) {
-		NL_SET_ERR_MSG_MOD(extack, "variable offseting not supported");
+		NL_SET_ERR_MSG_MOD(extack, "variable offsetting not supported");
 		return false;
 	}
 	if (knode->sel->hoff || knode->sel->hmask) {
@@ -78,7 +78,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode,
 
 	k = &knode->sel->keys[0];
 	if (k->offmask) {
-		NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offseting not supported");
+		NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offsetting not supported");
 		return false;
 	}
 	if (k->off) {
@@ -262,22 +262,12 @@ static int nfp_abm_setup_tc_block_cb(enum tc_setup_type type,
 	}
 }
 
+static LIST_HEAD(nfp_abm_block_cb_list);
+
 int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
-			    struct tc_block_offload *f)
+			    struct flow_block_offload *f)
 {
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     nfp_abm_setup_tc_block_cb,
-					     repr, repr, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, nfp_abm_setup_tc_block_cb,
-					repr);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
+	return flow_block_cb_setup_simple(f, &nfp_abm_block_cb_list,
+					  nfp_abm_setup_tc_block_cb,
+					  repr, repr, true);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 9584f03f3efa..69e84ff7f2e5 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -261,10 +261,15 @@ int nfp_abm_ctrl_qm_disable(struct nfp_abm *abm)
 
 int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed)
 {
+	const u32 cmd = NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET;
 	struct nfp_net *nn = alink->vnic;
 	unsigned int i;
 	int err;
 
+	err = nfp_net_mbox_lock(nn, alink->abm->prio_map_len);
+	if (err)
+		return err;
+
 	/* Write data_len and wipe reserved */
 	nn_writeq(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATALEN,
 		  alink->abm->prio_map_len);
@@ -273,8 +278,7 @@ int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed)
 		nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATA + i,
 			  packed[i / sizeof(u32)]);
 
-	err = nfp_net_reconfig_mbox(nn,
-				    NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET);
+	err = nfp_net_mbox_reconfig_and_unlock(nn, cmd);
 	if (err)
 		nfp_err(alink->abm->app->cpp,
 			"setting DSCP -> VQ map failed with error %d\n", err);
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 4d4ff5844c47..9183b3e85d21 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -53,7 +53,8 @@ nfp_abm_setup_tc(struct nfp_app *app, struct net_device *netdev,
 	}
 }
 
-static struct net_device *nfp_abm_repr_get(struct nfp_app *app, u32 port_id)
+static struct net_device *
+nfp_abm_repr_get(struct nfp_app *app, u32 port_id, bool *redir_egress)
 {
 	enum nfp_repr_type rtype;
 	struct nfp_reprs *reprs;
@@ -549,5 +550,5 @@ const struct nfp_app_type app_abm = {
 	.eswitch_mode_get	= nfp_abm_eswitch_mode_get,
 	.eswitch_mode_set	= nfp_abm_eswitch_mode_set,
 
-	.repr_get	= nfp_abm_repr_get,
+	.dev_get	= nfp_abm_repr_get,
 };
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 49749c60885e..48746c9c6224 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -247,7 +247,7 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
 			  struct tc_gred_qopt_offload *opt);
 int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
-			    struct tc_block_offload *opt);
+			    struct flow_block_offload *opt);
 
 int nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 9b6cfa697879..bc9850e4ec5e 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -6,48 +6,13 @@
 #include <linux/bug.h>
 #include <linux/jiffies.h>
 #include <linux/skbuff.h>
-#include <linux/wait.h>
 
+#include "../ccm.h"
 #include "../nfp_app.h"
 #include "../nfp_net.h"
 #include "fw.h"
 #include "main.h"
 
-#define NFP_BPF_TAG_ALLOC_SPAN	(U16_MAX / 4)
-
-static bool nfp_bpf_all_tags_busy(struct nfp_app_bpf *bpf)
-{
-	u16 used_tags;
-
-	used_tags = bpf->tag_alloc_next - bpf->tag_alloc_last;
-
-	return used_tags > NFP_BPF_TAG_ALLOC_SPAN;
-}
-
-static int nfp_bpf_alloc_tag(struct nfp_app_bpf *bpf)
-{
-	/* All FW communication for BPF is request-reply.  To make sure we
-	 * don't reuse the message ID too early after timeout - limit the
-	 * number of requests in flight.
-	 */
-	if (nfp_bpf_all_tags_busy(bpf)) {
-		cmsg_warn(bpf, "all FW request contexts busy!\n");
-		return -EAGAIN;
-	}
-
-	WARN_ON(__test_and_set_bit(bpf->tag_alloc_next, bpf->tag_allocator));
-	return bpf->tag_alloc_next++;
-}
-
-static void nfp_bpf_free_tag(struct nfp_app_bpf *bpf, u16 tag)
-{
-	WARN_ON(!__test_and_clear_bit(tag, bpf->tag_allocator));
-
-	while (!test_bit(bpf->tag_alloc_last, bpf->tag_allocator) &&
-	       bpf->tag_alloc_last != bpf->tag_alloc_next)
-		bpf->tag_alloc_last++;
-}
-
 static struct sk_buff *
 nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size)
 {
@@ -87,149 +52,6 @@ nfp_bpf_cmsg_map_reply_size(struct nfp_app_bpf *bpf, unsigned int n)
 	return size;
 }
 
-static u8 nfp_bpf_cmsg_get_type(struct sk_buff *skb)
-{
-	struct cmsg_hdr *hdr;
-
-	hdr = (struct cmsg_hdr *)skb->data;
-
-	return hdr->type;
-}
-
-static unsigned int nfp_bpf_cmsg_get_tag(struct sk_buff *skb)
-{
-	struct cmsg_hdr *hdr;
-
-	hdr = (struct cmsg_hdr *)skb->data;
-
-	return be16_to_cpu(hdr->tag);
-}
-
-static struct sk_buff *__nfp_bpf_reply(struct nfp_app_bpf *bpf, u16 tag)
-{
-	unsigned int msg_tag;
-	struct sk_buff *skb;
-
-	skb_queue_walk(&bpf->cmsg_replies, skb) {
-		msg_tag = nfp_bpf_cmsg_get_tag(skb);
-		if (msg_tag == tag) {
-			nfp_bpf_free_tag(bpf, tag);
-			__skb_unlink(skb, &bpf->cmsg_replies);
-			return skb;
-		}
-	}
-
-	return NULL;
-}
-
-static struct sk_buff *nfp_bpf_reply(struct nfp_app_bpf *bpf, u16 tag)
-{
-	struct sk_buff *skb;
-
-	nfp_ctrl_lock(bpf->app->ctrl);
-	skb = __nfp_bpf_reply(bpf, tag);
-	nfp_ctrl_unlock(bpf->app->ctrl);
-
-	return skb;
-}
-
-static struct sk_buff *nfp_bpf_reply_drop_tag(struct nfp_app_bpf *bpf, u16 tag)
-{
-	struct sk_buff *skb;
-
-	nfp_ctrl_lock(bpf->app->ctrl);
-	skb = __nfp_bpf_reply(bpf, tag);
-	if (!skb)
-		nfp_bpf_free_tag(bpf, tag);
-	nfp_ctrl_unlock(bpf->app->ctrl);
-
-	return skb;
-}
-
-static struct sk_buff *
-nfp_bpf_cmsg_wait_reply(struct nfp_app_bpf *bpf, enum nfp_bpf_cmsg_type type,
-			int tag)
-{
-	struct sk_buff *skb;
-	int i, err;
-
-	for (i = 0; i < 50; i++) {
-		udelay(4);
-		skb = nfp_bpf_reply(bpf, tag);
-		if (skb)
-			return skb;
-	}
-
-	err = wait_event_interruptible_timeout(bpf->cmsg_wq,
-					       skb = nfp_bpf_reply(bpf, tag),
-					       msecs_to_jiffies(5000));
-	/* We didn't get a response - try last time and atomically drop
-	 * the tag even if no response is matched.
-	 */
-	if (!skb)
-		skb = nfp_bpf_reply_drop_tag(bpf, tag);
-	if (err < 0) {
-		cmsg_warn(bpf, "%s waiting for response to 0x%02x: %d\n",
-			  err == ERESTARTSYS ? "interrupted" : "error",
-			  type, err);
-		return ERR_PTR(err);
-	}
-	if (!skb) {
-		cmsg_warn(bpf, "timeout waiting for response to 0x%02x\n",
-			  type);
-		return ERR_PTR(-ETIMEDOUT);
-	}
-
-	return skb;
-}
-
-static struct sk_buff *
-nfp_bpf_cmsg_communicate(struct nfp_app_bpf *bpf, struct sk_buff *skb,
-			 enum nfp_bpf_cmsg_type type, unsigned int reply_size)
-{
-	struct cmsg_hdr *hdr;
-	int tag;
-
-	nfp_ctrl_lock(bpf->app->ctrl);
-	tag = nfp_bpf_alloc_tag(bpf);
-	if (tag < 0) {
-		nfp_ctrl_unlock(bpf->app->ctrl);
-		dev_kfree_skb_any(skb);
-		return ERR_PTR(tag);
-	}
-
-	hdr = (void *)skb->data;
-	hdr->ver = CMSG_MAP_ABI_VERSION;
-	hdr->type = type;
-	hdr->tag = cpu_to_be16(tag);
-
-	__nfp_app_ctrl_tx(bpf->app, skb);
-
-	nfp_ctrl_unlock(bpf->app->ctrl);
-
-	skb = nfp_bpf_cmsg_wait_reply(bpf, type, tag);
-	if (IS_ERR(skb))
-		return skb;
-
-	hdr = (struct cmsg_hdr *)skb->data;
-	if (hdr->type != __CMSG_REPLY(type)) {
-		cmsg_warn(bpf, "cmsg drop - wrong type 0x%02x != 0x%02lx!\n",
-			  hdr->type, __CMSG_REPLY(type));
-		goto err_free;
-	}
-	/* 0 reply_size means caller will do the validation */
-	if (reply_size && skb->len != reply_size) {
-		cmsg_warn(bpf, "cmsg drop - type 0x%02x wrong size %d != %d!\n",
-			  type, skb->len, reply_size);
-		goto err_free;
-	}
-
-	return skb;
-err_free:
-	dev_kfree_skb_any(skb);
-	return ERR_PTR(-EIO);
-}
-
 static int
 nfp_bpf_ctrl_rc_to_errno(struct nfp_app_bpf *bpf,
 			 struct cmsg_reply_map_simple *reply)
@@ -275,8 +97,8 @@ nfp_bpf_ctrl_alloc_map(struct nfp_app_bpf *bpf, struct bpf_map *map)
 	req->map_type = cpu_to_be32(map->map_type);
 	req->map_flags = 0;
 
-	skb = nfp_bpf_cmsg_communicate(bpf, skb, CMSG_TYPE_MAP_ALLOC,
-				       sizeof(*reply));
+	skb = nfp_ccm_communicate(&bpf->ccm, skb, NFP_CCM_TYPE_BPF_MAP_ALLOC,
+				  sizeof(*reply));
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
@@ -310,8 +132,8 @@ void nfp_bpf_ctrl_free_map(struct nfp_app_bpf *bpf, struct nfp_bpf_map *nfp_map)
 	req = (void *)skb->data;
 	req->tid = cpu_to_be32(nfp_map->tid);
 
-	skb = nfp_bpf_cmsg_communicate(bpf, skb, CMSG_TYPE_MAP_FREE,
-				       sizeof(*reply));
+	skb = nfp_ccm_communicate(&bpf->ccm, skb, NFP_CCM_TYPE_BPF_MAP_FREE,
+				  sizeof(*reply));
 	if (IS_ERR(skb)) {
 		cmsg_warn(bpf, "leaking map - I/O error\n");
 		return;
@@ -354,8 +176,7 @@ nfp_bpf_ctrl_reply_val(struct nfp_app_bpf *bpf, struct cmsg_reply_map_op *reply,
 }
 
 static int
-nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap,
-		      enum nfp_bpf_cmsg_type op,
+nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
 		      u8 *key, u8 *value, u64 flags, u8 *out_key, u8 *out_value)
 {
 	struct nfp_bpf_map *nfp_map = offmap->dev_priv;
@@ -386,8 +207,8 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap,
 		memcpy(nfp_bpf_ctrl_req_val(bpf, req, 0), value,
 		       map->value_size);
 
-	skb = nfp_bpf_cmsg_communicate(bpf, skb, op,
-				       nfp_bpf_cmsg_map_reply_size(bpf, 1));
+	skb = nfp_ccm_communicate(&bpf->ccm, skb, op,
+				  nfp_bpf_cmsg_map_reply_size(bpf, 1));
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
@@ -415,34 +236,34 @@ err_free:
 int nfp_bpf_ctrl_update_entry(struct bpf_offloaded_map *offmap,
 			      void *key, void *value, u64 flags)
 {
-	return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_UPDATE,
+	return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_UPDATE,
 				     key, value, flags, NULL, NULL);
 }
 
 int nfp_bpf_ctrl_del_entry(struct bpf_offloaded_map *offmap, void *key)
 {
-	return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_DELETE,
+	return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_DELETE,
 				     key, NULL, 0, NULL, NULL);
 }
 
 int nfp_bpf_ctrl_lookup_entry(struct bpf_offloaded_map *offmap,
 			      void *key, void *value)
 {
-	return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_LOOKUP,
+	return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_LOOKUP,
 				     key, NULL, 0, NULL, value);
 }
 
 int nfp_bpf_ctrl_getfirst_entry(struct bpf_offloaded_map *offmap,
 				void *next_key)
 {
-	return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_GETFIRST,
+	return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_GETFIRST,
 				     NULL, NULL, 0, next_key, NULL);
 }
 
 int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap,
 			       void *key, void *next_key)
 {
-	return nfp_bpf_ctrl_entry_op(offmap, CMSG_TYPE_MAP_GETNEXT,
+	return nfp_bpf_ctrl_entry_op(offmap, NFP_CCM_TYPE_BPF_MAP_GETNEXT,
 				     key, NULL, 0, next_key, NULL);
 }
 
@@ -456,54 +277,35 @@ unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf)
 void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
 {
 	struct nfp_app_bpf *bpf = app->priv;
-	unsigned int tag;
 
 	if (unlikely(skb->len < sizeof(struct cmsg_reply_map_simple))) {
 		cmsg_warn(bpf, "cmsg drop - too short %d!\n", skb->len);
-		goto err_free;
+		dev_kfree_skb_any(skb);
+		return;
 	}
 
-	if (nfp_bpf_cmsg_get_type(skb) == CMSG_TYPE_BPF_EVENT) {
+	if (nfp_ccm_get_type(skb) == NFP_CCM_TYPE_BPF_BPF_EVENT) {
 		if (!nfp_bpf_event_output(bpf, skb->data, skb->len))
 			dev_consume_skb_any(skb);
 		else
 			dev_kfree_skb_any(skb);
-		return;
 	}
 
-	nfp_ctrl_lock(bpf->app->ctrl);
-
-	tag = nfp_bpf_cmsg_get_tag(skb);
-	if (unlikely(!test_bit(tag, bpf->tag_allocator))) {
-		cmsg_warn(bpf, "cmsg drop - no one is waiting for tag %u!\n",
-			  tag);
-		goto err_unlock;
-	}
-
-	__skb_queue_tail(&bpf->cmsg_replies, skb);
-	wake_up_interruptible_all(&bpf->cmsg_wq);
-
-	nfp_ctrl_unlock(bpf->app->ctrl);
-
-	return;
-err_unlock:
-	nfp_ctrl_unlock(bpf->app->ctrl);
-err_free:
-	dev_kfree_skb_any(skb);
+	nfp_ccm_rx(&bpf->ccm, skb);
 }
 
 void
 nfp_bpf_ctrl_msg_rx_raw(struct nfp_app *app, const void *data, unsigned int len)
 {
+	const struct nfp_ccm_hdr *hdr = data;
 	struct nfp_app_bpf *bpf = app->priv;
-	const struct cmsg_hdr *hdr = data;
 
 	if (unlikely(len < sizeof(struct cmsg_reply_map_simple))) {
 		cmsg_warn(bpf, "cmsg drop - too short %d!\n", len);
 		return;
 	}
 
-	if (hdr->type == CMSG_TYPE_BPF_EVENT)
+	if (hdr->type == NFP_CCM_TYPE_BPF_BPF_EVENT)
 		nfp_bpf_event_output(bpf, data, len);
 	else
 		cmsg_warn(bpf, "cmsg drop - msg type %d with raw buffer!\n",
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
index 721921bcf120..06c4286bd79e 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
@@ -6,6 +6,7 @@
 
 #include <linux/bitops.h>
 #include <linux/types.h>
+#include "../ccm.h"
 
 /* Kernel's enum bpf_reg_type is not uABI so people may change it breaking
  * our FW ABI.  In that case we will do translation in the driver.
@@ -52,22 +53,6 @@ struct nfp_bpf_cap_tlv_maps {
 /*
  * Types defined for map related control messages
  */
-#define CMSG_MAP_ABI_VERSION		1
-
-enum nfp_bpf_cmsg_type {
-	CMSG_TYPE_MAP_ALLOC	= 1,
-	CMSG_TYPE_MAP_FREE	= 2,
-	CMSG_TYPE_MAP_LOOKUP	= 3,
-	CMSG_TYPE_MAP_UPDATE	= 4,
-	CMSG_TYPE_MAP_DELETE	= 5,
-	CMSG_TYPE_MAP_GETNEXT	= 6,
-	CMSG_TYPE_MAP_GETFIRST	= 7,
-	CMSG_TYPE_BPF_EVENT	= 8,
-	__CMSG_TYPE_MAP_MAX,
-};
-
-#define CMSG_TYPE_MAP_REPLY_BIT		7
-#define __CMSG_REPLY(req)		(BIT(CMSG_TYPE_MAP_REPLY_BIT) | (req))
 
 /* BPF ABIv2 fixed-length control message fields */
 #define CMSG_MAP_KEY_LW			16
@@ -84,19 +69,13 @@ enum nfp_bpf_cmsg_status {
 	CMSG_RC_ERR_MAP_E2BIG		= 7,
 };
 
-struct cmsg_hdr {
-	u8 type;
-	u8 ver;
-	__be16 tag;
-};
-
 struct cmsg_reply_map_simple {
-	struct cmsg_hdr hdr;
+	struct nfp_ccm_hdr hdr;
 	__be32 rc;
 };
 
 struct cmsg_req_map_alloc_tbl {
-	struct cmsg_hdr hdr;
+	struct nfp_ccm_hdr hdr;
 	__be32 key_size;		/* in bytes */
 	__be32 value_size;		/* in bytes */
 	__be32 max_entries;
@@ -110,7 +89,7 @@ struct cmsg_reply_map_alloc_tbl {
 };
 
 struct cmsg_req_map_free_tbl {
-	struct cmsg_hdr hdr;
+	struct nfp_ccm_hdr hdr;
 	__be32 tid;
 };
 
@@ -120,7 +99,7 @@ struct cmsg_reply_map_free_tbl {
 };
 
 struct cmsg_req_map_op {
-	struct cmsg_hdr hdr;
+	struct nfp_ccm_hdr hdr;
 	__be32 tid;
 	__be32 count;
 	__be32 flags;
@@ -135,7 +114,7 @@ struct cmsg_reply_map_op {
 };
 
 struct cmsg_bpf_event {
-	struct cmsg_hdr hdr;
+	struct nfp_ccm_hdr hdr;
 	__be32 cpu_id;
 	__be64 map_ptr;
 	__be32 data_size;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index e23ca90289f7..4054b70d7719 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -328,7 +328,18 @@ __emit_shf(struct nfp_prog *nfp_prog, u16 dst, enum alu_dst_ab dst_ab,
 		return;
 	}
 
-	if (sc == SHF_SC_L_SHF)
+	/* NFP shift instruction has something special. If shift direction is
+	 * left then shift amount of 1 to 31 is specified as 32 minus the amount
+	 * to shift.
+	 *
+	 * But no need to do this for indirect shift which has shift amount be
+	 * 0. Even after we do this subtraction, shift amount 0 will be turned
+	 * into 32 which will eventually be encoded the same as 0 because only
+	 * low 5 bits are encoded, but shift amount be 32 will fail the
+	 * FIELD_PREP check done later on shift mask (0x1f), due to 32 is out of
+	 * mask range.
+	 */
+	if (sc == SHF_SC_L_SHF && shift)
 		shift = 32 - shift;
 
 	insn = OP_SHF_BASE |
@@ -612,6 +623,13 @@ static void wrp_immed(struct nfp_prog *nfp_prog, swreg dst, u32 imm)
 }
 
 static void
+wrp_zext(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, u8 dst)
+{
+	if (meta->flags & FLAG_INSN_DO_ZEXT)
+		wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+}
+
+static void
 wrp_immed_relo(struct nfp_prog *nfp_prog, swreg dst, u32 imm,
 	       enum nfp_relo_type relo)
 {
@@ -847,7 +865,8 @@ static int nfp_cpp_memcpy(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 }
 
 static int
-data_ld(struct nfp_prog *nfp_prog, swreg offset, u8 dst_gpr, int size)
+data_ld(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, swreg offset,
+	u8 dst_gpr, int size)
 {
 	unsigned int i;
 	u16 shift, sz;
@@ -870,14 +889,15 @@ data_ld(struct nfp_prog *nfp_prog, swreg offset, u8 dst_gpr, int size)
 			wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i));
 
 	if (i < 2)
-		wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0);
+		wrp_zext(nfp_prog, meta, dst_gpr);
 
 	return 0;
 }
 
 static int
-data_ld_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr,
-		   swreg lreg, swreg rreg, int size, enum cmd_mode mode)
+data_ld_host_order(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		   u8 dst_gpr, swreg lreg, swreg rreg, int size,
+		   enum cmd_mode mode)
 {
 	unsigned int i;
 	u8 mask, sz;
@@ -900,33 +920,34 @@ data_ld_host_order(struct nfp_prog *nfp_prog, u8 dst_gpr,
 			wrp_mov(nfp_prog, reg_both(dst_gpr + i), reg_xfer(i));
 
 	if (i < 2)
-		wrp_immed(nfp_prog, reg_both(dst_gpr + 1), 0);
+		wrp_zext(nfp_prog, meta, dst_gpr);
 
 	return 0;
 }
 
 static int
-data_ld_host_order_addr32(struct nfp_prog *nfp_prog, u8 src_gpr, swreg offset,
-			  u8 dst_gpr, u8 size)
+data_ld_host_order_addr32(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+			  u8 src_gpr, swreg offset, u8 dst_gpr, u8 size)
 {
-	return data_ld_host_order(nfp_prog, dst_gpr, reg_a(src_gpr), offset,
-				  size, CMD_MODE_32b);
+	return data_ld_host_order(nfp_prog, meta, dst_gpr, reg_a(src_gpr),
+				  offset, size, CMD_MODE_32b);
 }
 
 static int
-data_ld_host_order_addr40(struct nfp_prog *nfp_prog, u8 src_gpr, swreg offset,
-			  u8 dst_gpr, u8 size)
+data_ld_host_order_addr40(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+			  u8 src_gpr, swreg offset, u8 dst_gpr, u8 size)
 {
 	swreg rega, regb;
 
 	addr40_offset(nfp_prog, src_gpr, offset, &rega, &regb);
 
-	return data_ld_host_order(nfp_prog, dst_gpr, rega, regb,
+	return data_ld_host_order(nfp_prog, meta, dst_gpr, rega, regb,
 				  size, CMD_MODE_40b_BA);
 }
 
 static int
-construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, u16 src, u8 size)
+construct_data_ind_ld(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		      u16 offset, u16 src, u8 size)
 {
 	swreg tmp_reg;
 
@@ -942,10 +963,12 @@ construct_data_ind_ld(struct nfp_prog *nfp_prog, u16 offset, u16 src, u8 size)
 	emit_br_relo(nfp_prog, BR_BLO, BR_OFF_RELO, 0, RELO_BR_GO_ABORT);
 
 	/* Load data */
-	return data_ld(nfp_prog, imm_b(nfp_prog), 0, size);
+	return data_ld(nfp_prog, meta, imm_b(nfp_prog), 0, size);
 }
 
-static int construct_data_ld(struct nfp_prog *nfp_prog, u16 offset, u8 size)
+static int
+construct_data_ld(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		  u16 offset, u8 size)
 {
 	swreg tmp_reg;
 
@@ -956,7 +979,7 @@ static int construct_data_ld(struct nfp_prog *nfp_prog, u16 offset, u8 size)
 
 	/* Load data */
 	tmp_reg = re_load_imm_any(nfp_prog, offset, imm_b(nfp_prog));
-	return data_ld(nfp_prog, tmp_reg, 0, size);
+	return data_ld(nfp_prog, meta, tmp_reg, 0, size);
 }
 
 static int
@@ -1193,7 +1216,7 @@ mem_op_stack(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	}
 
 	if (clr_gpr && size < 8)
-		wrp_immed(nfp_prog, reg_both(gpr + 1), 0);
+		wrp_zext(nfp_prog, meta, gpr);
 
 	while (size) {
 		u32 slice_end;
@@ -1266,7 +1289,7 @@ wrp_alu64_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	u64 imm = insn->imm; /* sign extend */
 
 	if (skip) {
-		meta->skip = true;
+		meta->flags |= FLAG_INSN_SKIP_NOOP;
 		return 0;
 	}
 
@@ -1291,17 +1314,13 @@ wrp_alu64_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 static int
 wrp_alu32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-	      enum alu_op alu_op, bool skip)
+	      enum alu_op alu_op)
 {
 	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
 
-	if (skip) {
-		meta->skip = true;
-		return 0;
-	}
-
-	wrp_alu_imm(nfp_prog, insn->dst_reg * 2, alu_op, insn->imm);
-	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0);
+	wrp_alu_imm(nfp_prog, dst, alu_op, insn->imm);
+	wrp_zext(nfp_prog, meta, dst);
 
 	return 0;
 }
@@ -1313,7 +1332,7 @@ wrp_alu32_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	u8 dst = meta->insn.dst_reg * 2, src = meta->insn.src_reg * 2;
 
 	emit_alu(nfp_prog, reg_both(dst), reg_a(dst), alu_op, reg_b(src));
-	wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
+	wrp_zext(nfp_prog, meta, dst);
 
 	return 0;
 }
@@ -1334,8 +1353,9 @@ wrp_test_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2, alu_op,
 			 insn->src_reg * 2, br_mask, insn->off);
-	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2 + 1, alu_op,
-			 insn->src_reg * 2 + 1, br_mask, insn->off);
+	if (is_mbpf_jmp64(meta))
+		wrp_test_reg_one(nfp_prog, insn->dst_reg * 2 + 1, alu_op,
+				 insn->src_reg * 2 + 1, br_mask, insn->off);
 
 	return 0;
 }
@@ -1390,13 +1410,15 @@ static int cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	else
 		emit_alu(nfp_prog, reg_none(), tmp_reg, alu_op, reg_a(reg));
 
-	tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
-	if (!code->swap)
-		emit_alu(nfp_prog, reg_none(),
-			 reg_a(reg + 1), carry_op, tmp_reg);
-	else
-		emit_alu(nfp_prog, reg_none(),
-			 tmp_reg, carry_op, reg_a(reg + 1));
+	if (is_mbpf_jmp64(meta)) {
+		tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
+		if (!code->swap)
+			emit_alu(nfp_prog, reg_none(),
+				 reg_a(reg + 1), carry_op, tmp_reg);
+		else
+			emit_alu(nfp_prog, reg_none(),
+				 tmp_reg, carry_op, reg_a(reg + 1));
+	}
 
 	emit_br(nfp_prog, code->br_mask, insn->off, 0);
 
@@ -1423,8 +1445,9 @@ static int cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	}
 
 	emit_alu(nfp_prog, reg_none(), reg_a(areg), ALU_OP_SUB, reg_b(breg));
-	emit_alu(nfp_prog, reg_none(),
-		 reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
+	if (is_mbpf_jmp64(meta))
+		emit_alu(nfp_prog, reg_none(),
+			 reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
 	emit_br(nfp_prog, code->br_mask, insn->off, 0);
 
 	return 0;
@@ -1963,6 +1986,9 @@ static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
  */
 static int __shl_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
 {
+	if (!shift_amt)
+		return 0;
+
 	if (shift_amt < 32) {
 		emit_shf(nfp_prog, reg_both(dst + 1), reg_a(dst + 1),
 			 SHF_OP_NONE, reg_b(dst), SHF_SC_R_DSHF,
@@ -2075,6 +2101,9 @@ static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
  */
 static int __shr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
 {
+	if (!shift_amt)
+		return 0;
+
 	if (shift_amt < 32) {
 		emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE,
 			 reg_b(dst), SHF_SC_R_DSHF, shift_amt);
@@ -2176,6 +2205,9 @@ static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
  */
 static int __ashr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
 {
+	if (!shift_amt)
+		return 0;
+
 	if (shift_amt < 32) {
 		emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE,
 			 reg_b(dst), SHF_SC_R_DSHF, shift_amt);
@@ -2309,7 +2341,7 @@ static int xor_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int xor_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR);
 }
 
 static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2319,7 +2351,7 @@ static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int and_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND);
 }
 
 static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2329,7 +2361,7 @@ static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int or_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR);
 }
 
 static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2339,7 +2371,7 @@ static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int add_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD);
 }
 
 static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2349,7 +2381,7 @@ static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB);
 }
 
 static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2377,18 +2409,23 @@ static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst = meta->insn.dst_reg * 2;
 
 	emit_alu(nfp_prog, reg_both(dst), reg_imm(0), ALU_OP_SUB, reg_b(dst));
-	wrp_immed(nfp_prog, reg_both(meta->insn.dst_reg * 2 + 1), 0);
+	wrp_zext(nfp_prog, meta, dst);
 
 	return 0;
 }
 
-static int __ashr_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+static int
+__ashr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, u8 dst,
+	   u8 shift_amt)
 {
-	/* Set signedness bit (MSB of result). */
-	emit_alu(nfp_prog, reg_none(), reg_a(dst), ALU_OP_OR, reg_imm(0));
-	emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR, reg_b(dst),
-		 SHF_SC_R_SHF, shift_amt);
-	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	if (shift_amt) {
+		/* Set signedness bit (MSB of result). */
+		emit_alu(nfp_prog, reg_none(), reg_a(dst), ALU_OP_OR,
+			 reg_imm(0));
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
+			 reg_b(dst), SHF_SC_R_SHF, shift_amt);
+	}
+	wrp_zext(nfp_prog, meta, dst);
 
 	return 0;
 }
@@ -2403,7 +2440,7 @@ static int ashr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	umin = meta->umin_src;
 	umax = meta->umax_src;
 	if (umin == umax)
-		return __ashr_imm(nfp_prog, dst, umin);
+		return __ashr_imm(nfp_prog, meta, dst, umin);
 
 	src = insn->src_reg * 2;
 	/* NOTE: the first insn will set both indirect shift amount (source A)
@@ -2412,7 +2449,7 @@ static int ashr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_b(dst));
 	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
 		       reg_b(dst), SHF_SC_R_SHF);
-	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	wrp_zext(nfp_prog, meta, dst);
 
 	return 0;
 }
@@ -2422,21 +2459,82 @@ static int ashr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	const struct bpf_insn *insn = &meta->insn;
 	u8 dst = insn->dst_reg * 2;
 
-	return __ashr_imm(nfp_prog, dst, insn->imm);
+	return __ashr_imm(nfp_prog, meta, dst, insn->imm);
+}
+
+static int
+__shr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, u8 dst,
+	  u8 shift_amt)
+{
+	if (shift_amt)
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_R_SHF, shift_amt);
+	wrp_zext(nfp_prog, meta, dst);
+	return 0;
+}
+
+static int shr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	return __shr_imm(nfp_prog, meta, dst, insn->imm);
+}
+
+static int shr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
+	if (umin == umax)
+		return __shr_imm(nfp_prog, meta, dst, umin);
+
+	src = insn->src_reg * 2;
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+		       reg_b(dst), SHF_SC_R_SHF);
+	wrp_zext(nfp_prog, meta, dst);
+	return 0;
+}
+
+static int
+__shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, u8 dst,
+	  u8 shift_amt)
+{
+	if (shift_amt)
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_L_SHF, shift_amt);
+	wrp_zext(nfp_prog, meta, dst);
+	return 0;
 }
 
 static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
 
-	if (!insn->imm)
-		return 1; /* TODO: zero shift means indirect */
+	return __shl_imm(nfp_prog, meta, dst, insn->imm);
+}
 
-	emit_shf(nfp_prog, reg_both(insn->dst_reg * 2),
-		 reg_none(), SHF_OP_NONE, reg_b(insn->dst_reg * 2),
-		 SHF_SC_L_SHF, insn->imm);
-	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0);
+static int shl_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
 
+	dst = insn->dst_reg * 2;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
+	if (umin == umax)
+		return __shl_imm(nfp_prog, meta, dst, umin);
+
+	src = insn->src_reg * 2;
+	shl_reg64_lt32_low(nfp_prog, dst, src);
+	wrp_zext(nfp_prog, meta, dst);
 	return 0;
 }
 
@@ -2498,34 +2596,34 @@ static int imm_ld8(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int data_ld1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return construct_data_ld(nfp_prog, meta->insn.imm, 1);
+	return construct_data_ld(nfp_prog, meta, meta->insn.imm, 1);
 }
 
 static int data_ld2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return construct_data_ld(nfp_prog, meta->insn.imm, 2);
+	return construct_data_ld(nfp_prog, meta, meta->insn.imm, 2);
 }
 
 static int data_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return construct_data_ld(nfp_prog, meta->insn.imm, 4);
+	return construct_data_ld(nfp_prog, meta, meta->insn.imm, 4);
 }
 
 static int data_ind_ld1(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return construct_data_ind_ld(nfp_prog, meta->insn.imm,
+	return construct_data_ind_ld(nfp_prog, meta, meta->insn.imm,
 				     meta->insn.src_reg * 2, 1);
 }
 
 static int data_ind_ld2(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return construct_data_ind_ld(nfp_prog, meta->insn.imm,
+	return construct_data_ind_ld(nfp_prog, meta, meta->insn.imm,
 				     meta->insn.src_reg * 2, 2);
 }
 
 static int data_ind_ld4(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return construct_data_ind_ld(nfp_prog, meta->insn.imm,
+	return construct_data_ind_ld(nfp_prog, meta, meta->insn.imm,
 				     meta->insn.src_reg * 2, 4);
 }
 
@@ -2603,7 +2701,7 @@ mem_ldx_data(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 	tmp_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog));
 
-	return data_ld_host_order_addr32(nfp_prog, meta->insn.src_reg * 2,
+	return data_ld_host_order_addr32(nfp_prog, meta, meta->insn.src_reg * 2,
 					 tmp_reg, meta->insn.dst_reg * 2, size);
 }
 
@@ -2615,7 +2713,7 @@ mem_ldx_emem(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 	tmp_reg = re_load_imm_any(nfp_prog, meta->insn.off, imm_b(nfp_prog));
 
-	return data_ld_host_order_addr40(nfp_prog, meta->insn.src_reg * 2,
+	return data_ld_host_order_addr40(nfp_prog, meta, meta->insn.src_reg * 2,
 					 tmp_reg, meta->insn.dst_reg * 2, size);
 }
 
@@ -2676,7 +2774,7 @@ mem_ldx_data_from_pktcache_unaligned(struct nfp_prog *nfp_prog,
 	wrp_reg_subpart(nfp_prog, dst_lo, src_lo, len_lo, off);
 
 	if (!len_mid) {
-		wrp_immed(nfp_prog, dst_hi, 0);
+		wrp_zext(nfp_prog, meta, dst_gpr);
 		return 0;
 	}
 
@@ -2684,7 +2782,7 @@ mem_ldx_data_from_pktcache_unaligned(struct nfp_prog *nfp_prog,
 
 	if (size <= REG_WIDTH) {
 		wrp_reg_or_subpart(nfp_prog, dst_lo, src_mid, len_mid, len_lo);
-		wrp_immed(nfp_prog, dst_hi, 0);
+		wrp_zext(nfp_prog, meta, dst_gpr);
 	} else {
 		swreg src_hi = reg_xfer(idx + 2);
 
@@ -2715,10 +2813,10 @@ mem_ldx_data_from_pktcache_aligned(struct nfp_prog *nfp_prog,
 
 	if (size < REG_WIDTH) {
 		wrp_reg_subpart(nfp_prog, dst_lo, src_lo, size, 0);
-		wrp_immed(nfp_prog, dst_hi, 0);
+		wrp_zext(nfp_prog, meta, dst_gpr);
 	} else if (size == REG_WIDTH) {
 		wrp_mov(nfp_prog, dst_lo, src_lo);
-		wrp_immed(nfp_prog, dst_hi, 0);
+		wrp_zext(nfp_prog, meta, dst_gpr);
 	} else {
 		swreg src_hi = reg_xfer(idx + 1);
 
@@ -3048,6 +3146,19 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int jeq32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	swreg tmp_reg;
+
+	tmp_reg = ur_load_imm_any(nfp_prog, insn->imm, imm_b(nfp_prog));
+	emit_alu(nfp_prog, reg_none(),
+		 reg_a(insn->dst_reg * 2), ALU_OP_XOR, tmp_reg);
+	emit_br(nfp_prog, BR_BEQ, insn->off, 0);
+
+	return 0;
+}
+
 static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -3061,9 +3172,10 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	/* Upper word of the mask can only be 0 or ~0 from sign extension,
 	 * so either ignore it or OR the whole thing in.
 	 */
-	if (imm >> 32)
+	if (is_mbpf_jmp64(meta) && imm >> 32) {
 		emit_alu(nfp_prog, reg_none(),
 			 reg_a(dst_gpr + 1), ALU_OP_OR, imm_b(nfp_prog));
+	}
 	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
 	return 0;
@@ -3073,11 +3185,16 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
+	bool is_jmp32 = is_mbpf_jmp32(meta);
 	swreg tmp_reg;
 
 	if (!imm) {
-		emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
-			 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
+		if (is_jmp32)
+			emit_alu(nfp_prog, reg_none(), reg_none(), ALU_OP_NONE,
+				 reg_b(insn->dst_reg * 2));
+		else
+			emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
+				 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
 		emit_br(nfp_prog, BR_BNE, insn->off, 0);
 		return 0;
 	}
@@ -3087,6 +3204,9 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		 reg_a(insn->dst_reg * 2), ALU_OP_XOR, tmp_reg);
 	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
+	if (is_jmp32)
+		return 0;
+
 	tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
 	emit_alu(nfp_prog, reg_none(),
 		 reg_a(insn->dst_reg * 2 + 1), ALU_OP_XOR, tmp_reg);
@@ -3101,10 +3221,13 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 	emit_alu(nfp_prog, imm_a(nfp_prog), reg_a(insn->dst_reg * 2),
 		 ALU_OP_XOR, reg_b(insn->src_reg * 2));
-	emit_alu(nfp_prog, imm_b(nfp_prog), reg_a(insn->dst_reg * 2 + 1),
-		 ALU_OP_XOR, reg_b(insn->src_reg * 2 + 1));
-	emit_alu(nfp_prog, reg_none(),
-		 imm_a(nfp_prog), ALU_OP_OR, imm_b(nfp_prog));
+	if (is_mbpf_jmp64(meta)) {
+		emit_alu(nfp_prog, imm_b(nfp_prog),
+			 reg_a(insn->dst_reg * 2 + 1), ALU_OP_XOR,
+			 reg_b(insn->src_reg * 2 + 1));
+		emit_alu(nfp_prog, reg_none(), imm_a(nfp_prog), ALU_OP_OR,
+			 imm_b(nfp_prog));
+	}
 	emit_br(nfp_prog, BR_BEQ, insn->off, 0);
 
 	return 0;
@@ -3182,7 +3305,7 @@ bpf_to_bpf_call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		wrp_immed_relo(nfp_prog, imm_b(nfp_prog), 0, RELO_IMMED_REL);
 	} else {
 		ret_tgt = nfp_prog_current_offset(nfp_prog) + 2;
-		emit_br(nfp_prog, BR_UNC, meta->n + 1 + meta->insn.imm, 1);
+		emit_br(nfp_prog, BR_UNC, meta->insn.imm, 1);
 		offset_br = nfp_prog_current_offset(nfp_prog);
 	}
 	wrp_immed_relo(nfp_prog, ret_reg(nfp_prog), ret_tgt, RELO_IMMED_REL);
@@ -3321,7 +3444,10 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_DIV | BPF_X] =	div_reg,
 	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
+	[BPF_ALU | BPF_LSH | BPF_X] =	shl_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
+	[BPF_ALU | BPF_RSH | BPF_X] =	shr_reg,
+	[BPF_ALU | BPF_RSH | BPF_K] =	shr_imm,
 	[BPF_ALU | BPF_ARSH | BPF_X] =	ashr_reg,
 	[BPF_ALU | BPF_ARSH | BPF_K] =	ashr_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
@@ -3369,6 +3495,28 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_JMP | BPF_JSLE | BPF_X] =  cmp_reg,
 	[BPF_JMP | BPF_JSET | BPF_X] =	jset_reg,
 	[BPF_JMP | BPF_JNE | BPF_X] =	jne_reg,
+	[BPF_JMP32 | BPF_JEQ | BPF_K] =	jeq32_imm,
+	[BPF_JMP32 | BPF_JGT | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JGE | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JLT | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JLE | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JSGT | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSGE | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSLT | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSLE | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSET | BPF_K] =jset_imm,
+	[BPF_JMP32 | BPF_JNE | BPF_K] =	jne_imm,
+	[BPF_JMP32 | BPF_JEQ | BPF_X] =	jeq_reg,
+	[BPF_JMP32 | BPF_JGT | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JGE | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JLT | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JLE | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JSGT | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSGE | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSLT | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSLE | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSET | BPF_X] =jset_reg,
+	[BPF_JMP32 | BPF_JNE | BPF_X] =	jne_reg,
 	[BPF_JMP | BPF_CALL] =		call,
 	[BPF_JMP | BPF_EXIT] =		jmp_exit,
 };
@@ -3395,9 +3543,9 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 	int err;
 
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
-		if (BPF_CLASS(meta->insn.code) != BPF_JMP)
+		if (!is_mbpf_jmp(meta))
 			continue;
 		if (meta->insn.code == (BPF_JMP | BPF_EXIT) &&
 		    !nfp_is_main_function(meta))
@@ -3439,7 +3587,7 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 
 		jmp_dst = meta->jmp_dst;
 
-		if (jmp_dst->skip) {
+		if (jmp_dst->flags & FLAG_INSN_SKIP_PREC_DEPENDENT) {
 			pr_err("Branch landing on removed instruction!!\n");
 			return -ELOOP;
 		}
@@ -3689,7 +3837,7 @@ static int nfp_translate(struct nfp_prog *nfp_prog)
 				return nfp_prog->error;
 		}
 
-		if (meta->skip) {
+		if (meta->flags & FLAG_INSN_SKIP_MASK) {
 			nfp_prog->n_translated++;
 			continue;
 		}
@@ -3737,10 +3885,10 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog)
 		/* Programs start with R6 = R1 but we ignore the skb pointer */
 		if (insn.code == (BPF_ALU64 | BPF_MOV | BPF_X) &&
 		    insn.src_reg == 1 && insn.dst_reg == 6)
-			meta->skip = true;
+			meta->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 
 		/* Return as soon as something doesn't match */
-		if (!meta->skip)
+		if (!(meta->flags & FLAG_INSN_SKIP_MASK))
 			return;
 	}
 }
@@ -3755,19 +3903,17 @@ static void nfp_bpf_opt_neg_add_sub(struct nfp_prog *nfp_prog)
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
 		struct bpf_insn insn = meta->insn;
 
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
-		if (BPF_CLASS(insn.code) != BPF_ALU &&
-		    BPF_CLASS(insn.code) != BPF_ALU64 &&
-		    BPF_CLASS(insn.code) != BPF_JMP)
+		if (!is_mbpf_alu(meta) && !is_mbpf_jmp(meta))
 			continue;
 		if (BPF_SRC(insn.code) != BPF_K)
 			continue;
 		if (insn.imm >= 0)
 			continue;
 
-		if (BPF_CLASS(insn.code) == BPF_JMP) {
+		if (is_mbpf_jmp(meta)) {
 			switch (BPF_OP(insn.code)) {
 			case BPF_JGE:
 			case BPF_JSGE:
@@ -3829,7 +3975,7 @@ static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog)
 		if (meta2->flags & FLAG_INSN_IS_JUMP_DST)
 			continue;
 
-		meta2->skip = true;
+		meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 	}
 }
 
@@ -3869,8 +4015,8 @@ static void nfp_bpf_opt_ld_shift(struct nfp_prog *nfp_prog)
 		    meta3->flags & FLAG_INSN_IS_JUMP_DST)
 			continue;
 
-		meta2->skip = true;
-		meta3->skip = true;
+		meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
+		meta3->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 	}
 }
 
@@ -4065,7 +4211,8 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
 				}
 
 				head_ld_meta->paired_st = &head_st_meta->insn;
-				head_st_meta->skip = true;
+				head_st_meta->flags |=
+					FLAG_INSN_SKIP_PREC_DEPENDENT;
 			} else {
 				head_ld_meta->ldst_gather_len = 0;
 			}
@@ -4098,8 +4245,8 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
 			head_ld_meta = meta1;
 			head_st_meta = meta2;
 		} else {
-			meta1->skip = true;
-			meta2->skip = true;
+			meta1->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
+			meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 		}
 
 		head_ld_meta->ldst_gather_len += BPF_LDST_BYTES(ld);
@@ -4124,7 +4271,7 @@ static void nfp_bpf_opt_pkt_cache(struct nfp_prog *nfp_prog)
 		if (meta->flags & FLAG_INSN_IS_JUMP_DST)
 			cache_avail = false;
 
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		insn = &meta->insn;
@@ -4210,7 +4357,7 @@ start_new:
 	}
 
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		if (is_mbpf_load_pkt(meta) && !meta->ldst_gather_len) {
@@ -4246,7 +4393,8 @@ static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
 	u32 id;
 
 	nfp_for_each_insn_walk2(nfp_prog, meta1, meta2) {
-		if (meta1->skip || meta2->skip)
+		if (meta1->flags & FLAG_INSN_SKIP_MASK ||
+		    meta2->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		if (meta1->insn.code != (BPF_LD | BPF_IMM | BPF_DW) ||
@@ -4325,7 +4473,7 @@ int nfp_bpf_jit(struct nfp_prog *nfp_prog)
 	return ret;
 }
 
-void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
+void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta;
 
@@ -4336,7 +4484,7 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
 		unsigned int dst_idx;
 		bool pseudo_call;
 
-		if (BPF_CLASS(code) != BPF_JMP)
+		if (!is_mbpf_jmp(meta))
 			continue;
 		if (BPF_OP(code) == BPF_EXIT)
 			continue;
@@ -4353,7 +4501,7 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
 		else
 			dst_idx = meta->n + 1 + meta->insn.off;
 
-		dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_idx, cnt);
+		dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_idx);
 
 		if (pseudo_call)
 			dst_meta->flags |= FLAG_INSN_IS_SUBPROG_START;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index dccae0319204..1c9fb11470df 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -160,35 +160,19 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type,
 	return 0;
 }
 
-static int nfp_bpf_setup_tc_block(struct net_device *netdev,
-				  struct tc_block_offload *f)
-{
-	struct nfp_net *nn = netdev_priv(netdev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     nfp_bpf_setup_tc_block_cb,
-					     nn, nn, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block,
-					nfp_bpf_setup_tc_block_cb,
-					nn);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(nfp_bpf_block_cb_list);
 
 static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev,
 			    enum tc_setup_type type, void *type_data)
 {
+	struct nfp_net *nn = netdev_priv(netdev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return nfp_bpf_setup_tc_block(netdev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &nfp_bpf_block_cb_list,
+						  nfp_bpf_setup_tc_block_cb,
+						  nn, nn, true);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -442,14 +426,16 @@ static int nfp_bpf_init(struct nfp_app *app)
 	bpf->app = app;
 	app->priv = bpf;
 
-	skb_queue_head_init(&bpf->cmsg_replies);
-	init_waitqueue_head(&bpf->cmsg_wq);
 	INIT_LIST_HEAD(&bpf->map_list);
 
-	err = rhashtable_init(&bpf->maps_neutral, &nfp_bpf_maps_neutral_params);
+	err = nfp_ccm_init(&bpf->ccm, app);
 	if (err)
 		goto err_free_bpf;
 
+	err = rhashtable_init(&bpf->maps_neutral, &nfp_bpf_maps_neutral_params);
+	if (err)
+		goto err_clean_ccm;
+
 	nfp_bpf_init_capabilities(bpf);
 
 	err = nfp_bpf_parse_capabilities(app);
@@ -465,7 +451,7 @@ static int nfp_bpf_init(struct nfp_app *app)
 		app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf);
 	}
 
-	bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops);
+	bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops, bpf);
 	err = PTR_ERR_OR_ZERO(bpf->bpf_dev);
 	if (err)
 		goto err_free_neutral_maps;
@@ -474,6 +460,8 @@ static int nfp_bpf_init(struct nfp_app *app)
 
 err_free_neutral_maps:
 	rhashtable_destroy(&bpf->maps_neutral);
+err_clean_ccm:
+	nfp_ccm_clean(&bpf->ccm);
 err_free_bpf:
 	kfree(bpf);
 	return err;
@@ -484,7 +472,7 @@ static void nfp_bpf_clean(struct nfp_app *app)
 	struct nfp_app_bpf *bpf = app->priv;
 
 	bpf_offload_dev_destroy(bpf->bpf_dev);
-	WARN_ON(!skb_queue_empty(&bpf->cmsg_replies));
+	nfp_ccm_clean(&bpf->ccm);
 	WARN_ON(!list_empty(&bpf->map_list));
 	WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use);
 	rhashtable_free_and_destroy(&bpf->maps_neutral,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 941277936475..57d6ff51e980 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 
+#include "../ccm.h"
 #include "../nfp_asm.h"
 #include "fw.h"
 
@@ -84,16 +85,10 @@ enum pkt_vec {
 /**
  * struct nfp_app_bpf - bpf app priv structure
  * @app:		backpointer to the app
+ * @ccm:		common control message handler data
  *
  * @bpf_dev:		BPF offload device handle
  *
- * @tag_allocator:	bitmap of control message tags in use
- * @tag_alloc_next:	next tag bit to allocate
- * @tag_alloc_last:	next tag bit to be freed
- *
- * @cmsg_replies:	received cmsg replies waiting to be consumed
- * @cmsg_wq:		work queue for waiting for cmsg replies
- *
  * @cmsg_key_sz:	size of key in cmsg element array
  * @cmsg_val_sz:	size of value in cmsg element array
  *
@@ -132,16 +127,10 @@ enum pkt_vec {
  */
 struct nfp_app_bpf {
 	struct nfp_app *app;
+	struct nfp_ccm ccm;
 
 	struct bpf_offload_dev *bpf_dev;
 
-	DECLARE_BITMAP(tag_allocator, U16_MAX + 1);
-	u16 tag_alloc_next;
-	u16 tag_alloc_last;
-
-	struct sk_buff_head cmsg_replies;
-	struct wait_queue_head cmsg_wq;
-
 	unsigned int cmsg_key_sz;
 	unsigned int cmsg_val_sz;
 
@@ -243,6 +232,18 @@ struct nfp_bpf_reg_state {
 #define FLAG_INSN_IS_JUMP_DST			BIT(0)
 #define FLAG_INSN_IS_SUBPROG_START		BIT(1)
 #define FLAG_INSN_PTR_CALLER_STACK_FRAME	BIT(2)
+/* Instruction is pointless, noop even on its own */
+#define FLAG_INSN_SKIP_NOOP			BIT(3)
+/* Instruction is optimized out based on preceding instructions */
+#define FLAG_INSN_SKIP_PREC_DEPENDENT		BIT(4)
+/* Instruction is optimized by the verifier */
+#define FLAG_INSN_SKIP_VERIFIER_OPT		BIT(5)
+/* Instruction needs to zero extend to high 32-bit */
+#define FLAG_INSN_DO_ZEXT			BIT(6)
+
+#define FLAG_INSN_SKIP_MASK		(FLAG_INSN_SKIP_NOOP | \
+					 FLAG_INSN_SKIP_PREC_DEPENDENT | \
+					 FLAG_INSN_SKIP_VERIFIER_OPT)
 
 /**
  * struct nfp_insn_meta - BPF instruction wrapper
@@ -271,7 +272,6 @@ struct nfp_bpf_reg_state {
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
  * @subprog_idx: index of subprogram to which the instruction belongs
- * @skip: skip this instruction (optimized out)
  * @double_cb: callback for second part of the instruction
  * @l: link on nfp_prog->insns list
  */
@@ -319,7 +319,6 @@ struct nfp_insn_meta {
 	unsigned short n;
 	unsigned short flags;
 	unsigned short subprog_idx;
-	bool skip;
 	instr_cb_t double_cb;
 
 	struct list_head l;
@@ -357,6 +356,21 @@ static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
 }
 
+static inline bool is_mbpf_jmp32(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_JMP32;
+}
+
+static inline bool is_mbpf_jmp64(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_JMP;
+}
+
+static inline bool is_mbpf_jmp(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_jmp32(meta) || is_mbpf_jmp64(meta);
+}
+
 static inline bool is_mbpf_store(const struct nfp_insn_meta *meta)
 {
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_MEM);
@@ -407,6 +421,20 @@ static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
 	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
 }
 
+static inline bool is_mbpf_cond_jump(const struct nfp_insn_meta *meta)
+{
+	u8 op;
+
+	if (is_mbpf_jmp32(meta))
+		return true;
+
+	if (!is_mbpf_jmp64(meta))
+		return false;
+
+	op = mbpf_op(meta);
+	return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
+}
+
 static inline bool is_mbpf_helper_call(const struct nfp_insn_meta *meta)
 {
 	struct bpf_insn insn = meta->insn;
@@ -457,6 +485,7 @@ struct nfp_bpf_subprog_info {
  * @subprog_cnt: number of sub-programs, including main function
  * @map_records: the map record pointers from bpf->maps_neutral
  * @subprog: pointer to an array of objects holding info about sub-programs
+ * @n_insns: number of instructions on @insns list
  * @insns: list of BPF instruction wrappers (struct nfp_insn_meta)
  */
 struct nfp_prog {
@@ -489,6 +518,7 @@ struct nfp_prog {
 	struct nfp_bpf_neutral_map **map_records;
 	struct nfp_bpf_subprog_info *subprog;
 
+	unsigned int n_insns;
 	struct list_head insns;
 };
 
@@ -505,7 +535,7 @@ struct nfp_bpf_vnic {
 };
 
 bool nfp_is_subprog_start(struct nfp_insn_meta *meta);
-void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt);
+void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog);
 int nfp_bpf_jit(struct nfp_prog *prog);
 bool nfp_bpf_supported_opcode(u8 code);
 
@@ -513,6 +543,10 @@ int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
 		    int prev_insn_idx);
 int nfp_bpf_finalize(struct bpf_verifier_env *env);
 
+int nfp_bpf_opt_replace_insn(struct bpf_verifier_env *env, u32 off,
+			     struct bpf_insn *insn);
+int nfp_bpf_opt_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
+
 extern const struct bpf_prog_offload_ops nfp_bpf_dev_ops;
 
 struct netdev_bpf;
@@ -526,7 +560,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 
 struct nfp_insn_meta *
 nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-		  unsigned int insn_idx, unsigned int n_insns);
+		  unsigned int insn_idx);
 
 void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv);
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index f0283854fade..39c9fec222b4 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -22,6 +22,7 @@
 #include <net/tc_act/tc_mirred.h>
 
 #include "main.h"
+#include "../ccm.h"
 #include "../nfp_app.h"
 #include "../nfp_net_ctrl.h"
 #include "../nfp_net.h"
@@ -163,8 +164,9 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
+	nfp_prog->n_insns = cnt;
 
-	nfp_bpf_jit_prepare(nfp_prog, cnt);
+	nfp_bpf_jit_prepare(nfp_prog);
 
 	return 0;
 }
@@ -184,8 +186,6 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
 
 static int nfp_bpf_verifier_prep(struct bpf_prog *prog)
 {
-	struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev);
-	struct nfp_app *app = nn->app;
 	struct nfp_prog *nfp_prog;
 	int ret;
 
@@ -196,7 +196,7 @@ static int nfp_bpf_verifier_prep(struct bpf_prog *prog)
 
 	INIT_LIST_HEAD(&nfp_prog->insns);
 	nfp_prog->type = prog->type;
-	nfp_prog->bpf = app->priv;
+	nfp_prog->bpf = bpf_offload_dev_priv(prog->aux->offload->offdev);
 
 	ret = nfp_prog_prepare(nfp_prog, prog->insnsi, prog->len);
 	if (ret)
@@ -219,6 +219,10 @@ static int nfp_bpf_translate(struct bpf_prog *prog)
 	unsigned int max_instr;
 	int err;
 
+	/* We depend on dead code elimination succeeding */
+	if (prog->aux->offload->opt_failed)
+		return -EINVAL;
+
 	max_instr = nn_readw(nn, NFP_NET_CFG_BPF_MAX_LEN);
 	nfp_prog->__prog_alloc_len = max_instr * sizeof(u64);
 
@@ -449,7 +453,7 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
 
 	if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
 		return -EINVAL;
-	if (cbe->hdr.ver != CMSG_MAP_ABI_VERSION)
+	if (cbe->hdr.ver != NFP_CCM_ABI_VERSION)
 		return -EINVAL;
 
 	rcu_read_lock();
@@ -591,6 +595,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
 	.insn_hook	= nfp_verify_insn,
 	.finalize	= nfp_bpf_finalize,
+	.replace_insn	= nfp_bpf_opt_replace_insn,
+	.remove_insns	= nfp_bpf_opt_remove_insns,
 	.prepare	= nfp_bpf_verifier_prep,
 	.translate	= nfp_bpf_translate,
 	.destroy	= nfp_bpf_destroy,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 337bb862ec1d..e92ee510fd52 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -18,15 +18,15 @@
 
 struct nfp_insn_meta *
 nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-		  unsigned int insn_idx, unsigned int n_insns)
+		  unsigned int insn_idx)
 {
 	unsigned int forward, backward, i;
 
 	backward = meta->n - insn_idx;
 	forward = insn_idx - meta->n;
 
-	if (min(forward, backward) > n_insns - insn_idx - 1) {
-		backward = n_insns - insn_idx - 1;
+	if (min(forward, backward) > nfp_prog->n_insns - insn_idx - 1) {
+		backward = nfp_prog->n_insns - insn_idx - 1;
 		meta = nfp_prog_last_meta(nfp_prog);
 	}
 	if (min(forward, backward) > insn_idx && backward > insn_idx) {
@@ -629,7 +629,7 @@ int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
 	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
 	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
 
-	meta = nfp_bpf_goto_meta(nfp_prog, meta, insn_idx, env->prog->len);
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, insn_idx);
 	nfp_prog->verifier_meta = meta;
 
 	if (!nfp_bpf_supported_opcode(meta->insn.code)) {
@@ -690,8 +690,7 @@ nfp_assign_subprog_idx_and_regs(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static unsigned int
-nfp_bpf_get_stack_usage(struct nfp_prog *nfp_prog, unsigned int cnt)
+static unsigned int nfp_bpf_get_stack_usage(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta = nfp_prog_first_meta(nfp_prog);
 	unsigned int max_depth = 0, depth = 0, frame = 0;
@@ -726,7 +725,7 @@ continue_subprog:
 
 		/* Find the callee and start processing it. */
 		meta = nfp_bpf_goto_meta(nfp_prog, meta,
-					 meta->n + 1 + meta->insn.imm, cnt);
+					 meta->n + 1 + meta->insn.imm);
 		idx = meta->subprog_idx;
 		frame++;
 		goto process_subprog;
@@ -745,6 +744,17 @@ continue_subprog:
 	goto continue_subprog;
 }
 
+static void nfp_bpf_insn_flag_zext(struct nfp_prog *nfp_prog,
+				   struct bpf_insn_aux_data *aux)
+{
+	struct nfp_insn_meta *meta;
+
+	list_for_each_entry(meta, &nfp_prog->insns, l) {
+		if (aux[meta->n].zext_dst)
+			meta->flags |= FLAG_INSN_DO_ZEXT;
+	}
+}
+
 int nfp_bpf_finalize(struct bpf_verifier_env *env)
 {
 	struct bpf_subprog_info *info;
@@ -778,13 +788,71 @@ int nfp_bpf_finalize(struct bpf_verifier_env *env)
 
 	nn = netdev_priv(env->prog->aux->offload->netdev);
 	max_stack = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
-	nfp_prog->stack_size = nfp_bpf_get_stack_usage(nfp_prog,
-						       env->prog->len);
+	nfp_prog->stack_size = nfp_bpf_get_stack_usage(nfp_prog);
 	if (nfp_prog->stack_size > max_stack) {
 		pr_vlog(env, "stack too large: program %dB > FW stack %dB\n",
 			nfp_prog->stack_size, max_stack);
 		return -EOPNOTSUPP;
 	}
 
+	nfp_bpf_insn_flag_zext(nfp_prog, env->insn_aux_data);
+	return 0;
+}
+
+int nfp_bpf_opt_replace_insn(struct bpf_verifier_env *env, u32 off,
+			     struct bpf_insn *insn)
+{
+	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
+
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, aux_data[off].orig_idx);
+	nfp_prog->verifier_meta = meta;
+
+	/* conditional jump to jump conversion */
+	if (is_mbpf_cond_jump(meta) &&
+	    insn->code == (BPF_JMP | BPF_JA | BPF_K)) {
+		unsigned int tgt_off;
+
+		tgt_off = off + insn->off + 1;
+
+		if (!insn->off) {
+			meta->jmp_dst = list_next_entry(meta, l);
+			meta->jump_neg_op = false;
+		} else if (meta->jmp_dst->n != aux_data[tgt_off].orig_idx) {
+			pr_vlog(env, "branch hard wire at %d changes target %d -> %d\n",
+				off, meta->jmp_dst->n,
+				aux_data[tgt_off].orig_idx);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	pr_vlog(env, "unsupported instruction replacement %hhx -> %hhx\n",
+		meta->insn.code, insn->code);
+	return -EINVAL;
+}
+
+int nfp_bpf_opt_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
+	unsigned int i;
+
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, aux_data[off].orig_idx);
+
+	for (i = 0; i < cnt; i++) {
+		if (WARN_ON_ONCE(&meta->l == &nfp_prog->insns))
+			return -EINVAL;
+
+		/* doesn't count if it already has the flag */
+		if (meta->flags & FLAG_INSN_SKIP_VERIFIER_OPT)
+			i--;
+
+		meta->flags |= FLAG_INSN_SKIP_VERIFIER_OPT;
+		meta = list_next_entry(meta, l);
+	}
+
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/ccm.c b/drivers/net/ethernet/netronome/nfp/ccm.c
new file mode 100644
index 000000000000..71afd111bae3
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/ccm.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2016-2019 Netronome Systems, Inc. */
+
+#include <linux/bitops.h>
+
+#include "ccm.h"
+#include "nfp_app.h"
+#include "nfp_net.h"
+
+#define ccm_warn(app, msg...)	nn_dp_warn(&(app)->ctrl->dp, msg)
+
+#define NFP_CCM_TAG_ALLOC_SPAN	(U16_MAX / 4)
+
+static bool nfp_ccm_all_tags_busy(struct nfp_ccm *ccm)
+{
+	u16 used_tags;
+
+	used_tags = ccm->tag_alloc_next - ccm->tag_alloc_last;
+
+	return used_tags > NFP_CCM_TAG_ALLOC_SPAN;
+}
+
+static int nfp_ccm_alloc_tag(struct nfp_ccm *ccm)
+{
+	/* CCM is for FW communication which is request-reply.  To make sure
+	 * we don't reuse the message ID too early after timeout - limit the
+	 * number of requests in flight.
+	 */
+	if (unlikely(nfp_ccm_all_tags_busy(ccm))) {
+		ccm_warn(ccm->app, "all FW request contexts busy!\n");
+		return -EAGAIN;
+	}
+
+	WARN_ON(__test_and_set_bit(ccm->tag_alloc_next, ccm->tag_allocator));
+	return ccm->tag_alloc_next++;
+}
+
+static void nfp_ccm_free_tag(struct nfp_ccm *ccm, u16 tag)
+{
+	WARN_ON(!__test_and_clear_bit(tag, ccm->tag_allocator));
+
+	while (!test_bit(ccm->tag_alloc_last, ccm->tag_allocator) &&
+	       ccm->tag_alloc_last != ccm->tag_alloc_next)
+		ccm->tag_alloc_last++;
+}
+
+static struct sk_buff *__nfp_ccm_reply(struct nfp_ccm *ccm, u16 tag)
+{
+	unsigned int msg_tag;
+	struct sk_buff *skb;
+
+	skb_queue_walk(&ccm->replies, skb) {
+		msg_tag = nfp_ccm_get_tag(skb);
+		if (msg_tag == tag) {
+			nfp_ccm_free_tag(ccm, tag);
+			__skb_unlink(skb, &ccm->replies);
+			return skb;
+		}
+	}
+
+	return NULL;
+}
+
+static struct sk_buff *
+nfp_ccm_reply(struct nfp_ccm *ccm, struct nfp_app *app, u16 tag)
+{
+	struct sk_buff *skb;
+
+	nfp_ctrl_lock(app->ctrl);
+	skb = __nfp_ccm_reply(ccm, tag);
+	nfp_ctrl_unlock(app->ctrl);
+
+	return skb;
+}
+
+static struct sk_buff *
+nfp_ccm_reply_drop_tag(struct nfp_ccm *ccm, struct nfp_app *app, u16 tag)
+{
+	struct sk_buff *skb;
+
+	nfp_ctrl_lock(app->ctrl);
+	skb = __nfp_ccm_reply(ccm, tag);
+	if (!skb)
+		nfp_ccm_free_tag(ccm, tag);
+	nfp_ctrl_unlock(app->ctrl);
+
+	return skb;
+}
+
+static struct sk_buff *
+nfp_ccm_wait_reply(struct nfp_ccm *ccm, struct nfp_app *app,
+		   enum nfp_ccm_type type, int tag)
+{
+	struct sk_buff *skb;
+	int i, err;
+
+	for (i = 0; i < 50; i++) {
+		udelay(4);
+		skb = nfp_ccm_reply(ccm, app, tag);
+		if (skb)
+			return skb;
+	}
+
+	err = wait_event_interruptible_timeout(ccm->wq,
+					       skb = nfp_ccm_reply(ccm, app,
+								   tag),
+					       msecs_to_jiffies(5000));
+	/* We didn't get a response - try last time and atomically drop
+	 * the tag even if no response is matched.
+	 */
+	if (!skb)
+		skb = nfp_ccm_reply_drop_tag(ccm, app, tag);
+	if (err < 0) {
+		ccm_warn(app, "%s waiting for response to 0x%02x: %d\n",
+			 err == ERESTARTSYS ? "interrupted" : "error",
+			 type, err);
+		return ERR_PTR(err);
+	}
+	if (!skb) {
+		ccm_warn(app, "timeout waiting for response to 0x%02x\n", type);
+		return ERR_PTR(-ETIMEDOUT);
+	}
+
+	return skb;
+}
+
+struct sk_buff *
+nfp_ccm_communicate(struct nfp_ccm *ccm, struct sk_buff *skb,
+		    enum nfp_ccm_type type, unsigned int reply_size)
+{
+	struct nfp_app *app = ccm->app;
+	struct nfp_ccm_hdr *hdr;
+	int reply_type, tag;
+
+	nfp_ctrl_lock(app->ctrl);
+	tag = nfp_ccm_alloc_tag(ccm);
+	if (tag < 0) {
+		nfp_ctrl_unlock(app->ctrl);
+		dev_kfree_skb_any(skb);
+		return ERR_PTR(tag);
+	}
+
+	hdr = (void *)skb->data;
+	hdr->ver = NFP_CCM_ABI_VERSION;
+	hdr->type = type;
+	hdr->tag = cpu_to_be16(tag);
+
+	__nfp_app_ctrl_tx(app, skb);
+
+	nfp_ctrl_unlock(app->ctrl);
+
+	skb = nfp_ccm_wait_reply(ccm, app, type, tag);
+	if (IS_ERR(skb))
+		return skb;
+
+	reply_type = nfp_ccm_get_type(skb);
+	if (reply_type != __NFP_CCM_REPLY(type)) {
+		ccm_warn(app, "cmsg drop - wrong type 0x%02x != 0x%02lx!\n",
+			 reply_type, __NFP_CCM_REPLY(type));
+		goto err_free;
+	}
+	/* 0 reply_size means caller will do the validation */
+	if (reply_size && skb->len != reply_size) {
+		ccm_warn(app, "cmsg drop - type 0x%02x wrong size %d != %d!\n",
+			 type, skb->len, reply_size);
+		goto err_free;
+	}
+
+	return skb;
+err_free:
+	dev_kfree_skb_any(skb);
+	return ERR_PTR(-EIO);
+}
+
+void nfp_ccm_rx(struct nfp_ccm *ccm, struct sk_buff *skb)
+{
+	struct nfp_app *app = ccm->app;
+	unsigned int tag;
+
+	if (unlikely(skb->len < sizeof(struct nfp_ccm_hdr))) {
+		ccm_warn(app, "cmsg drop - too short %d!\n", skb->len);
+		goto err_free;
+	}
+
+	nfp_ctrl_lock(app->ctrl);
+
+	tag = nfp_ccm_get_tag(skb);
+	if (unlikely(!test_bit(tag, ccm->tag_allocator))) {
+		ccm_warn(app, "cmsg drop - no one is waiting for tag %u!\n",
+			 tag);
+		goto err_unlock;
+	}
+
+	__skb_queue_tail(&ccm->replies, skb);
+	wake_up_interruptible_all(&ccm->wq);
+
+	nfp_ctrl_unlock(app->ctrl);
+	return;
+
+err_unlock:
+	nfp_ctrl_unlock(app->ctrl);
+err_free:
+	dev_kfree_skb_any(skb);
+}
+
+int nfp_ccm_init(struct nfp_ccm *ccm, struct nfp_app *app)
+{
+	ccm->app = app;
+	skb_queue_head_init(&ccm->replies);
+	init_waitqueue_head(&ccm->wq);
+	return 0;
+}
+
+void nfp_ccm_clean(struct nfp_ccm *ccm)
+{
+	WARN_ON(!skb_queue_empty(&ccm->replies));
+}
diff --git a/drivers/net/ethernet/netronome/nfp/ccm.h b/drivers/net/ethernet/netronome/nfp/ccm.h
new file mode 100644
index 000000000000..a460c75522be
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/ccm.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2016-2019 Netronome Systems, Inc. */
+
+#ifndef NFP_CCM_H
+#define NFP_CCM_H 1
+
+#include <linux/bitmap.h>
+#include <linux/skbuff.h>
+#include <linux/wait.h>
+
+struct nfp_app;
+struct nfp_net;
+
+/* Firmware ABI */
+
+enum nfp_ccm_type {
+	NFP_CCM_TYPE_BPF_MAP_ALLOC	= 1,
+	NFP_CCM_TYPE_BPF_MAP_FREE	= 2,
+	NFP_CCM_TYPE_BPF_MAP_LOOKUP	= 3,
+	NFP_CCM_TYPE_BPF_MAP_UPDATE	= 4,
+	NFP_CCM_TYPE_BPF_MAP_DELETE	= 5,
+	NFP_CCM_TYPE_BPF_MAP_GETNEXT	= 6,
+	NFP_CCM_TYPE_BPF_MAP_GETFIRST	= 7,
+	NFP_CCM_TYPE_BPF_BPF_EVENT	= 8,
+	NFP_CCM_TYPE_CRYPTO_RESET	= 9,
+	NFP_CCM_TYPE_CRYPTO_ADD		= 10,
+	NFP_CCM_TYPE_CRYPTO_DEL		= 11,
+	NFP_CCM_TYPE_CRYPTO_UPDATE	= 12,
+	__NFP_CCM_TYPE_MAX,
+};
+
+#define NFP_CCM_ABI_VERSION		1
+
+#define NFP_CCM_TYPE_REPLY_BIT		7
+#define __NFP_CCM_REPLY(req)		(BIT(NFP_CCM_TYPE_REPLY_BIT) | (req))
+
+struct nfp_ccm_hdr {
+	union {
+		struct {
+			u8 type;
+			u8 ver;
+			__be16 tag;
+		};
+		__be32 raw;
+	};
+};
+
+static inline u8 nfp_ccm_get_type(struct sk_buff *skb)
+{
+	struct nfp_ccm_hdr *hdr;
+
+	hdr = (struct nfp_ccm_hdr *)skb->data;
+
+	return hdr->type;
+}
+
+static inline __be16 __nfp_ccm_get_tag(struct sk_buff *skb)
+{
+	struct nfp_ccm_hdr *hdr;
+
+	hdr = (struct nfp_ccm_hdr *)skb->data;
+
+	return hdr->tag;
+}
+
+static inline unsigned int nfp_ccm_get_tag(struct sk_buff *skb)
+{
+	return be16_to_cpu(__nfp_ccm_get_tag(skb));
+}
+
+#define NFP_NET_MBOX_TLV_TYPE		GENMASK(31, 16)
+#define NFP_NET_MBOX_TLV_LEN		GENMASK(15, 0)
+
+enum nfp_ccm_mbox_tlv_type {
+	NFP_NET_MBOX_TLV_TYPE_UNKNOWN	= 0,
+	NFP_NET_MBOX_TLV_TYPE_END	= 1,
+	NFP_NET_MBOX_TLV_TYPE_MSG	= 2,
+	NFP_NET_MBOX_TLV_TYPE_MSG_NOSUP	= 3,
+	NFP_NET_MBOX_TLV_TYPE_RESV	= 4,
+};
+
+/* Implementation */
+
+/**
+ * struct nfp_ccm - common control message handling
+ * @app:		APP handle
+ *
+ * @tag_allocator:	bitmap of control message tags in use
+ * @tag_alloc_next:	next tag bit to allocate
+ * @tag_alloc_last:	next tag bit to be freed
+ *
+ * @replies:		received cmsg replies waiting to be consumed
+ * @wq:			work queue for waiting for cmsg replies
+ */
+struct nfp_ccm {
+	struct nfp_app *app;
+
+	DECLARE_BITMAP(tag_allocator, U16_MAX + 1);
+	u16 tag_alloc_next;
+	u16 tag_alloc_last;
+
+	struct sk_buff_head replies;
+	wait_queue_head_t wq;
+};
+
+int nfp_ccm_init(struct nfp_ccm *ccm, struct nfp_app *app);
+void nfp_ccm_clean(struct nfp_ccm *ccm);
+void nfp_ccm_rx(struct nfp_ccm *ccm, struct sk_buff *skb);
+struct sk_buff *
+nfp_ccm_communicate(struct nfp_ccm *ccm, struct sk_buff *skb,
+		    enum nfp_ccm_type type, unsigned int reply_size);
+
+int nfp_ccm_mbox_alloc(struct nfp_net *nn);
+void nfp_ccm_mbox_free(struct nfp_net *nn);
+int nfp_ccm_mbox_init(struct nfp_net *nn);
+void nfp_ccm_mbox_clean(struct nfp_net *nn);
+bool nfp_ccm_mbox_fits(struct nfp_net *nn, unsigned int size);
+struct sk_buff *
+nfp_ccm_mbox_msg_alloc(struct nfp_net *nn, unsigned int req_size,
+		       unsigned int reply_size, gfp_t flags);
+int __nfp_ccm_mbox_communicate(struct nfp_net *nn, struct sk_buff *skb,
+			       enum nfp_ccm_type type,
+			       unsigned int reply_size,
+			       unsigned int max_reply_size, bool critical);
+int nfp_ccm_mbox_communicate(struct nfp_net *nn, struct sk_buff *skb,
+			     enum nfp_ccm_type type,
+			     unsigned int reply_size,
+			     unsigned int max_reply_size);
+int nfp_ccm_mbox_post(struct nfp_net *nn, struct sk_buff *skb,
+		      enum nfp_ccm_type type, unsigned int max_reply_size);
+#endif
diff --git a/drivers/net/ethernet/netronome/nfp/ccm_mbox.c b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c
new file mode 100644
index 000000000000..f0783aa9e66e
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c
@@ -0,0 +1,743 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <linux/bitfield.h>
+#include <linux/io.h>
+#include <linux/skbuff.h>
+
+#include "ccm.h"
+#include "nfp_net.h"
+
+/* CCM messages via the mailbox.  CMSGs get wrapped into simple TLVs
+ * and copied into the mailbox.  Multiple messages can be copied to
+ * form a batch.  Threads come in with CMSG formed in an skb, then
+ * enqueue that skb onto the request queue.  If threads skb is first
+ * in queue this thread will handle the mailbox operation.  It copies
+ * up to 64 messages into the mailbox (making sure that both requests
+ * and replies will fit.  After FW is done processing the batch it
+ * copies the data out and wakes waiting threads.
+ * If a thread is waiting it either gets its the message completed
+ * (response is copied into the same skb as the request, overwriting
+ * it), or becomes the first in queue.
+ * Completions and next-to-run are signaled via the control buffer
+ * to limit potential cache line bounces.
+ */
+
+#define NFP_CCM_MBOX_BATCH_LIMIT	64
+#define NFP_CCM_TIMEOUT			(NFP_NET_POLL_TIMEOUT * 1000)
+#define NFP_CCM_MAX_QLEN		1024
+
+enum nfp_net_mbox_cmsg_state {
+	NFP_NET_MBOX_CMSG_STATE_QUEUED,
+	NFP_NET_MBOX_CMSG_STATE_NEXT,
+	NFP_NET_MBOX_CMSG_STATE_BUSY,
+	NFP_NET_MBOX_CMSG_STATE_REPLY_FOUND,
+	NFP_NET_MBOX_CMSG_STATE_DONE,
+};
+
+/**
+ * struct nfp_ccm_mbox_skb_cb - CCM mailbox specific info
+ * @state:	processing state (/stage) of the message
+ * @err:	error encountered during processing if any
+ * @max_len:	max(request_len, reply_len)
+ * @exp_reply:	expected reply length (0 means don't validate)
+ * @posted:	the message was posted and nobody waits for the reply
+ */
+struct nfp_ccm_mbox_cmsg_cb {
+	enum nfp_net_mbox_cmsg_state state;
+	int err;
+	unsigned int max_len;
+	unsigned int exp_reply;
+	bool posted;
+};
+
+static u32 nfp_ccm_mbox_max_msg(struct nfp_net *nn)
+{
+	return round_down(nn->tlv_caps.mbox_len, 4) -
+		NFP_NET_CFG_MBOX_SIMPLE_VAL - /* common mbox command header */
+		4 * 2; /* Msg TLV plus End TLV headers */
+}
+
+static void
+nfp_ccm_mbox_msg_init(struct sk_buff *skb, unsigned int exp_reply, int max_len)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	cb->state = NFP_NET_MBOX_CMSG_STATE_QUEUED;
+	cb->err = 0;
+	cb->max_len = max_len;
+	cb->exp_reply = exp_reply;
+	cb->posted = false;
+}
+
+static int nfp_ccm_mbox_maxlen(const struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	return cb->max_len;
+}
+
+static bool nfp_ccm_mbox_done(struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	return cb->state == NFP_NET_MBOX_CMSG_STATE_DONE;
+}
+
+static bool nfp_ccm_mbox_in_progress(struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	return cb->state != NFP_NET_MBOX_CMSG_STATE_QUEUED &&
+	       cb->state != NFP_NET_MBOX_CMSG_STATE_NEXT;
+}
+
+static void nfp_ccm_mbox_set_busy(struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	cb->state = NFP_NET_MBOX_CMSG_STATE_BUSY;
+}
+
+static bool nfp_ccm_mbox_is_posted(struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	return cb->posted;
+}
+
+static void nfp_ccm_mbox_mark_posted(struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	cb->posted = true;
+}
+
+static bool nfp_ccm_mbox_is_first(struct nfp_net *nn, struct sk_buff *skb)
+{
+	return skb_queue_is_first(&nn->mbox_cmsg.queue, skb);
+}
+
+static bool nfp_ccm_mbox_should_run(struct nfp_net *nn, struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	return cb->state == NFP_NET_MBOX_CMSG_STATE_NEXT;
+}
+
+static void nfp_ccm_mbox_mark_next_runner(struct nfp_net *nn)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb;
+	struct sk_buff *skb;
+
+	skb = skb_peek(&nn->mbox_cmsg.queue);
+	if (!skb)
+		return;
+
+	cb = (void *)skb->cb;
+	cb->state = NFP_NET_MBOX_CMSG_STATE_NEXT;
+	if (cb->posted)
+		queue_work(nn->mbox_cmsg.workq, &nn->mbox_cmsg.runq_work);
+}
+
+static void
+nfp_ccm_mbox_write_tlv(struct nfp_net *nn, u32 off, u32 type, u32 len)
+{
+	nn_writel(nn, off,
+		  FIELD_PREP(NFP_NET_MBOX_TLV_TYPE, type) |
+		  FIELD_PREP(NFP_NET_MBOX_TLV_LEN, len));
+}
+
+static void nfp_ccm_mbox_copy_in(struct nfp_net *nn, struct sk_buff *last)
+{
+	struct sk_buff *skb;
+	int reserve, i, cnt;
+	__be32 *data;
+	u32 off, len;
+
+	off = nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL;
+	skb = __skb_peek(&nn->mbox_cmsg.queue);
+	while (true) {
+		nfp_ccm_mbox_write_tlv(nn, off, NFP_NET_MBOX_TLV_TYPE_MSG,
+				       skb->len);
+		off += 4;
+
+		/* Write data word by word, skb->data should be aligned */
+		data = (__be32 *)skb->data;
+		cnt = skb->len / 4;
+		for (i = 0 ; i < cnt; i++) {
+			nn_writel(nn, off, be32_to_cpu(data[i]));
+			off += 4;
+		}
+		if (skb->len & 3) {
+			__be32 tmp = 0;
+
+			memcpy(&tmp, &data[i], skb->len & 3);
+			nn_writel(nn, off, be32_to_cpu(tmp));
+			off += 4;
+		}
+
+		/* Reserve space if reply is bigger */
+		len = round_up(skb->len, 4);
+		reserve = nfp_ccm_mbox_maxlen(skb) - len;
+		if (reserve > 0) {
+			nfp_ccm_mbox_write_tlv(nn, off,
+					       NFP_NET_MBOX_TLV_TYPE_RESV,
+					       reserve);
+			off += 4 + reserve;
+		}
+
+		if (skb == last)
+			break;
+		skb = skb_queue_next(&nn->mbox_cmsg.queue, skb);
+	}
+
+	nfp_ccm_mbox_write_tlv(nn, off, NFP_NET_MBOX_TLV_TYPE_END, 0);
+}
+
+static struct sk_buff *
+nfp_ccm_mbox_find_req(struct nfp_net *nn, __be16 tag, struct sk_buff *last)
+{
+	struct sk_buff *skb;
+
+	skb = __skb_peek(&nn->mbox_cmsg.queue);
+	while (true) {
+		if (__nfp_ccm_get_tag(skb) == tag)
+			return skb;
+
+		if (skb == last)
+			return NULL;
+		skb = skb_queue_next(&nn->mbox_cmsg.queue, skb);
+	}
+}
+
+static void nfp_ccm_mbox_copy_out(struct nfp_net *nn, struct sk_buff *last)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb;
+	u8 __iomem *data, *end;
+	struct sk_buff *skb;
+
+	data = nn->dp.ctrl_bar + nn->tlv_caps.mbox_off +
+		NFP_NET_CFG_MBOX_SIMPLE_VAL;
+	end = data + nn->tlv_caps.mbox_len;
+
+	while (true) {
+		unsigned int length, offset, type;
+		struct nfp_ccm_hdr hdr;
+		u32 tlv_hdr;
+
+		tlv_hdr = readl(data);
+		type = FIELD_GET(NFP_NET_MBOX_TLV_TYPE, tlv_hdr);
+		length = FIELD_GET(NFP_NET_MBOX_TLV_LEN, tlv_hdr);
+		offset = data - nn->dp.ctrl_bar;
+
+		/* Advance past the header */
+		data += 4;
+
+		if (data + length > end) {
+			nn_dp_warn(&nn->dp, "mailbox oversized TLV type:%d offset:%u len:%u\n",
+				   type, offset, length);
+			break;
+		}
+
+		if (type == NFP_NET_MBOX_TLV_TYPE_END)
+			break;
+		if (type == NFP_NET_MBOX_TLV_TYPE_RESV)
+			goto next_tlv;
+		if (type != NFP_NET_MBOX_TLV_TYPE_MSG &&
+		    type != NFP_NET_MBOX_TLV_TYPE_MSG_NOSUP) {
+			nn_dp_warn(&nn->dp, "mailbox unknown TLV type:%d offset:%u len:%u\n",
+				   type, offset, length);
+			break;
+		}
+
+		if (length < 4) {
+			nn_dp_warn(&nn->dp, "mailbox msg too short to contain header TLV type:%d offset:%u len:%u\n",
+				   type, offset, length);
+			break;
+		}
+
+		hdr.raw = cpu_to_be32(readl(data));
+
+		skb = nfp_ccm_mbox_find_req(nn, hdr.tag, last);
+		if (!skb) {
+			nn_dp_warn(&nn->dp, "mailbox request not found:%u\n",
+				   be16_to_cpu(hdr.tag));
+			break;
+		}
+		cb = (void *)skb->cb;
+
+		if (type == NFP_NET_MBOX_TLV_TYPE_MSG_NOSUP) {
+			nn_dp_warn(&nn->dp,
+				   "mailbox msg not supported type:%d\n",
+				   nfp_ccm_get_type(skb));
+			cb->err = -EIO;
+			goto next_tlv;
+		}
+
+		if (hdr.type != __NFP_CCM_REPLY(nfp_ccm_get_type(skb))) {
+			nn_dp_warn(&nn->dp, "mailbox msg reply wrong type:%u expected:%lu\n",
+				   hdr.type,
+				   __NFP_CCM_REPLY(nfp_ccm_get_type(skb)));
+			cb->err = -EIO;
+			goto next_tlv;
+		}
+		if (cb->exp_reply && length != cb->exp_reply) {
+			nn_dp_warn(&nn->dp, "mailbox msg reply wrong size type:%u expected:%u have:%u\n",
+				   hdr.type, length, cb->exp_reply);
+			cb->err = -EIO;
+			goto next_tlv;
+		}
+		if (length > cb->max_len) {
+			nn_dp_warn(&nn->dp, "mailbox msg oversized reply type:%u max:%u have:%u\n",
+				   hdr.type, cb->max_len, length);
+			cb->err = -EIO;
+			goto next_tlv;
+		}
+
+		if (!cb->posted) {
+			__be32 *skb_data;
+			int i, cnt;
+
+			if (length <= skb->len)
+				__skb_trim(skb, length);
+			else
+				skb_put(skb, length - skb->len);
+
+			/* We overcopy here slightly, but that's okay,
+			 * the skb is large enough, and the garbage will
+			 * be ignored (beyond skb->len).
+			 */
+			skb_data = (__be32 *)skb->data;
+			memcpy(skb_data, &hdr, 4);
+
+			cnt = DIV_ROUND_UP(length, 4);
+			for (i = 1 ; i < cnt; i++)
+				skb_data[i] = cpu_to_be32(readl(data + i * 4));
+		}
+
+		cb->state = NFP_NET_MBOX_CMSG_STATE_REPLY_FOUND;
+next_tlv:
+		data += round_up(length, 4);
+		if (data + 4 > end) {
+			nn_dp_warn(&nn->dp,
+				   "reached end of MBOX without END TLV\n");
+			break;
+		}
+	}
+
+	smp_wmb(); /* order the skb->data vs. cb->state */
+	spin_lock_bh(&nn->mbox_cmsg.queue.lock);
+	do {
+		skb = __skb_dequeue(&nn->mbox_cmsg.queue);
+		cb = (void *)skb->cb;
+
+		if (cb->state != NFP_NET_MBOX_CMSG_STATE_REPLY_FOUND) {
+			cb->err = -ENOENT;
+			smp_wmb(); /* order the cb->err vs. cb->state */
+		}
+		cb->state = NFP_NET_MBOX_CMSG_STATE_DONE;
+
+		if (cb->posted) {
+			if (cb->err)
+				nn_dp_warn(&nn->dp,
+					   "mailbox posted msg failed type:%u err:%d\n",
+					   nfp_ccm_get_type(skb), cb->err);
+			dev_consume_skb_any(skb);
+		}
+	} while (skb != last);
+
+	nfp_ccm_mbox_mark_next_runner(nn);
+	spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+}
+
+static void
+nfp_ccm_mbox_mark_all_err(struct nfp_net *nn, struct sk_buff *last, int err)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb;
+	struct sk_buff *skb;
+
+	spin_lock_bh(&nn->mbox_cmsg.queue.lock);
+	do {
+		skb = __skb_dequeue(&nn->mbox_cmsg.queue);
+		cb = (void *)skb->cb;
+
+		cb->err = err;
+		smp_wmb(); /* order the cb->err vs. cb->state */
+		cb->state = NFP_NET_MBOX_CMSG_STATE_DONE;
+	} while (skb != last);
+
+	nfp_ccm_mbox_mark_next_runner(nn);
+	spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+}
+
+static void nfp_ccm_mbox_run_queue_unlock(struct nfp_net *nn)
+	__releases(&nn->mbox_cmsg.queue.lock)
+{
+	int space = nn->tlv_caps.mbox_len - NFP_NET_CFG_MBOX_SIMPLE_VAL;
+	struct sk_buff *skb, *last;
+	int cnt, err;
+
+	space -= 4; /* for End TLV */
+
+	/* First skb must fit, because it's ours and we checked it fits */
+	cnt = 1;
+	last = skb = __skb_peek(&nn->mbox_cmsg.queue);
+	space -= 4 + nfp_ccm_mbox_maxlen(skb);
+
+	while (!skb_queue_is_last(&nn->mbox_cmsg.queue, last)) {
+		skb = skb_queue_next(&nn->mbox_cmsg.queue, last);
+		space -= 4 + nfp_ccm_mbox_maxlen(skb);
+		if (space < 0)
+			break;
+		last = skb;
+		nfp_ccm_mbox_set_busy(skb);
+		cnt++;
+		if (cnt == NFP_CCM_MBOX_BATCH_LIMIT)
+			break;
+	}
+	spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+
+	/* Now we own all skb's marked in progress, new requests may arrive
+	 * at the end of the queue.
+	 */
+
+	nn_ctrl_bar_lock(nn);
+
+	nfp_ccm_mbox_copy_in(nn, last);
+
+	err = nfp_net_mbox_reconfig(nn, NFP_NET_CFG_MBOX_CMD_TLV_CMSG);
+	if (!err)
+		nfp_ccm_mbox_copy_out(nn, last);
+	else
+		nfp_ccm_mbox_mark_all_err(nn, last, -EIO);
+
+	nn_ctrl_bar_unlock(nn);
+
+	wake_up_all(&nn->mbox_cmsg.wq);
+}
+
+static int nfp_ccm_mbox_skb_return(struct sk_buff *skb)
+{
+	struct nfp_ccm_mbox_cmsg_cb *cb = (void *)skb->cb;
+
+	if (cb->err)
+		dev_kfree_skb_any(skb);
+	return cb->err;
+}
+
+/* If wait timed out but the command is already in progress we have
+ * to wait until it finishes.  Runners has ownership of the skbs marked
+ * as busy.
+ */
+static int
+nfp_ccm_mbox_unlink_unlock(struct nfp_net *nn, struct sk_buff *skb,
+			   enum nfp_ccm_type type)
+	__releases(&nn->mbox_cmsg.queue.lock)
+{
+	bool was_first;
+
+	if (nfp_ccm_mbox_in_progress(skb)) {
+		spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+
+		wait_event(nn->mbox_cmsg.wq, nfp_ccm_mbox_done(skb));
+		smp_rmb(); /* pairs with smp_wmb() after data is written */
+		return nfp_ccm_mbox_skb_return(skb);
+	}
+
+	was_first = nfp_ccm_mbox_should_run(nn, skb);
+	__skb_unlink(skb, &nn->mbox_cmsg.queue);
+	if (was_first)
+		nfp_ccm_mbox_mark_next_runner(nn);
+
+	spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+
+	if (was_first)
+		wake_up_all(&nn->mbox_cmsg.wq);
+
+	nn_dp_warn(&nn->dp, "time out waiting for mbox response to 0x%02x\n",
+		   type);
+	return -ETIMEDOUT;
+}
+
+static int
+nfp_ccm_mbox_msg_prepare(struct nfp_net *nn, struct sk_buff *skb,
+			 enum nfp_ccm_type type,
+			 unsigned int reply_size, unsigned int max_reply_size,
+			 gfp_t flags)
+{
+	const unsigned int mbox_max = nfp_ccm_mbox_max_msg(nn);
+	unsigned int max_len;
+	ssize_t undersize;
+	int err;
+
+	if (unlikely(!(nn->tlv_caps.mbox_cmsg_types & BIT(type)))) {
+		nn_dp_warn(&nn->dp,
+			   "message type %d not supported by mailbox\n", type);
+		return -EINVAL;
+	}
+
+	/* If the reply size is unknown assume it will take the entire
+	 * mailbox, the callers should do their best for this to never
+	 * happen.
+	 */
+	if (!max_reply_size)
+		max_reply_size = mbox_max;
+	max_reply_size = round_up(max_reply_size, 4);
+
+	/* Make sure we can fit the entire reply into the skb,
+	 * and that we don't have to slow down the mbox handler
+	 * with allocations.
+	 */
+	undersize = max_reply_size - (skb_end_pointer(skb) - skb->data);
+	if (undersize > 0) {
+		err = pskb_expand_head(skb, 0, undersize, flags);
+		if (err) {
+			nn_dp_warn(&nn->dp,
+				   "can't allocate reply buffer for mailbox\n");
+			return err;
+		}
+	}
+
+	/* Make sure that request and response both fit into the mailbox */
+	max_len = max(max_reply_size, round_up(skb->len, 4));
+	if (max_len > mbox_max) {
+		nn_dp_warn(&nn->dp,
+			   "message too big for tha mailbox: %u/%u vs %u\n",
+			   skb->len, max_reply_size, mbox_max);
+		return -EMSGSIZE;
+	}
+
+	nfp_ccm_mbox_msg_init(skb, reply_size, max_len);
+
+	return 0;
+}
+
+static int
+nfp_ccm_mbox_msg_enqueue(struct nfp_net *nn, struct sk_buff *skb,
+			 enum nfp_ccm_type type, bool critical)
+{
+	struct nfp_ccm_hdr *hdr;
+
+	assert_spin_locked(&nn->mbox_cmsg.queue.lock);
+
+	if (!critical && nn->mbox_cmsg.queue.qlen >= NFP_CCM_MAX_QLEN) {
+		nn_dp_warn(&nn->dp, "mailbox request queue too long\n");
+		return -EBUSY;
+	}
+
+	hdr = (void *)skb->data;
+	hdr->ver = NFP_CCM_ABI_VERSION;
+	hdr->type = type;
+	hdr->tag = cpu_to_be16(nn->mbox_cmsg.tag++);
+
+	__skb_queue_tail(&nn->mbox_cmsg.queue, skb);
+
+	return 0;
+}
+
+int __nfp_ccm_mbox_communicate(struct nfp_net *nn, struct sk_buff *skb,
+			       enum nfp_ccm_type type,
+			       unsigned int reply_size,
+			       unsigned int max_reply_size, bool critical)
+{
+	int err;
+
+	err = nfp_ccm_mbox_msg_prepare(nn, skb, type, reply_size,
+				       max_reply_size, GFP_KERNEL);
+	if (err)
+		goto err_free_skb;
+
+	spin_lock_bh(&nn->mbox_cmsg.queue.lock);
+
+	err = nfp_ccm_mbox_msg_enqueue(nn, skb, type, critical);
+	if (err)
+		goto err_unlock;
+
+	/* First in queue takes the mailbox lock and processes the batch */
+	if (!nfp_ccm_mbox_is_first(nn, skb)) {
+		bool to;
+
+		spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+
+		to = !wait_event_timeout(nn->mbox_cmsg.wq,
+					 nfp_ccm_mbox_done(skb) ||
+					 nfp_ccm_mbox_should_run(nn, skb),
+					 msecs_to_jiffies(NFP_CCM_TIMEOUT));
+
+		/* fast path for those completed by another thread */
+		if (nfp_ccm_mbox_done(skb)) {
+			smp_rmb(); /* pairs with wmb after data is written */
+			return nfp_ccm_mbox_skb_return(skb);
+		}
+
+		spin_lock_bh(&nn->mbox_cmsg.queue.lock);
+
+		if (!nfp_ccm_mbox_is_first(nn, skb)) {
+			WARN_ON(!to);
+
+			err = nfp_ccm_mbox_unlink_unlock(nn, skb, type);
+			if (err)
+				goto err_free_skb;
+			return 0;
+		}
+	}
+
+	/* run queue expects the lock held */
+	nfp_ccm_mbox_run_queue_unlock(nn);
+	return nfp_ccm_mbox_skb_return(skb);
+
+err_unlock:
+	spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+err_free_skb:
+	dev_kfree_skb_any(skb);
+	return err;
+}
+
+int nfp_ccm_mbox_communicate(struct nfp_net *nn, struct sk_buff *skb,
+			     enum nfp_ccm_type type,
+			     unsigned int reply_size,
+			     unsigned int max_reply_size)
+{
+	return __nfp_ccm_mbox_communicate(nn, skb, type, reply_size,
+					  max_reply_size, false);
+}
+
+static void nfp_ccm_mbox_post_runq_work(struct work_struct *work)
+{
+	struct sk_buff *skb;
+	struct nfp_net *nn;
+
+	nn = container_of(work, struct nfp_net, mbox_cmsg.runq_work);
+
+	spin_lock_bh(&nn->mbox_cmsg.queue.lock);
+
+	skb = __skb_peek(&nn->mbox_cmsg.queue);
+	if (WARN_ON(!skb || !nfp_ccm_mbox_is_posted(skb) ||
+		    !nfp_ccm_mbox_should_run(nn, skb))) {
+		spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+		return;
+	}
+
+	nfp_ccm_mbox_run_queue_unlock(nn);
+}
+
+static void nfp_ccm_mbox_post_wait_work(struct work_struct *work)
+{
+	struct sk_buff *skb;
+	struct nfp_net *nn;
+	int err;
+
+	nn = container_of(work, struct nfp_net, mbox_cmsg.wait_work);
+
+	skb = skb_peek(&nn->mbox_cmsg.queue);
+	if (WARN_ON(!skb || !nfp_ccm_mbox_is_posted(skb)))
+		/* Should never happen so it's unclear what to do here.. */
+		goto exit_unlock_wake;
+
+	err = nfp_net_mbox_reconfig_wait_posted(nn);
+	if (!err)
+		nfp_ccm_mbox_copy_out(nn, skb);
+	else
+		nfp_ccm_mbox_mark_all_err(nn, skb, -EIO);
+exit_unlock_wake:
+	nn_ctrl_bar_unlock(nn);
+	wake_up_all(&nn->mbox_cmsg.wq);
+}
+
+int nfp_ccm_mbox_post(struct nfp_net *nn, struct sk_buff *skb,
+		      enum nfp_ccm_type type, unsigned int max_reply_size)
+{
+	int err;
+
+	err = nfp_ccm_mbox_msg_prepare(nn, skb, type, 0, max_reply_size,
+				       GFP_ATOMIC);
+	if (err)
+		goto err_free_skb;
+
+	nfp_ccm_mbox_mark_posted(skb);
+
+	spin_lock_bh(&nn->mbox_cmsg.queue.lock);
+
+	err = nfp_ccm_mbox_msg_enqueue(nn, skb, type, false);
+	if (err)
+		goto err_unlock;
+
+	if (nfp_ccm_mbox_is_first(nn, skb)) {
+		if (nn_ctrl_bar_trylock(nn)) {
+			nfp_ccm_mbox_copy_in(nn, skb);
+			nfp_net_mbox_reconfig_post(nn,
+						   NFP_NET_CFG_MBOX_CMD_TLV_CMSG);
+			queue_work(nn->mbox_cmsg.workq,
+				   &nn->mbox_cmsg.wait_work);
+		} else {
+			nfp_ccm_mbox_mark_next_runner(nn);
+		}
+	}
+
+	spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+
+	return 0;
+
+err_unlock:
+	spin_unlock_bh(&nn->mbox_cmsg.queue.lock);
+err_free_skb:
+	dev_kfree_skb_any(skb);
+	return err;
+}
+
+struct sk_buff *
+nfp_ccm_mbox_msg_alloc(struct nfp_net *nn, unsigned int req_size,
+		       unsigned int reply_size, gfp_t flags)
+{
+	unsigned int max_size;
+	struct sk_buff *skb;
+
+	if (!reply_size)
+		max_size = nfp_ccm_mbox_max_msg(nn);
+	else
+		max_size = max(req_size, reply_size);
+	max_size = round_up(max_size, 4);
+
+	skb = alloc_skb(max_size, flags);
+	if (!skb)
+		return NULL;
+
+	skb_put(skb, req_size);
+
+	return skb;
+}
+
+bool nfp_ccm_mbox_fits(struct nfp_net *nn, unsigned int size)
+{
+	return nfp_ccm_mbox_max_msg(nn) >= size;
+}
+
+int nfp_ccm_mbox_init(struct nfp_net *nn)
+{
+	return 0;
+}
+
+void nfp_ccm_mbox_clean(struct nfp_net *nn)
+{
+	drain_workqueue(nn->mbox_cmsg.workq);
+}
+
+int nfp_ccm_mbox_alloc(struct nfp_net *nn)
+{
+	skb_queue_head_init(&nn->mbox_cmsg.queue);
+	init_waitqueue_head(&nn->mbox_cmsg.wq);
+	INIT_WORK(&nn->mbox_cmsg.wait_work, nfp_ccm_mbox_post_wait_work);
+	INIT_WORK(&nn->mbox_cmsg.runq_work, nfp_ccm_mbox_post_runq_work);
+
+	nn->mbox_cmsg.workq = alloc_workqueue("nfp-ccm-mbox", WQ_UNBOUND, 0);
+	if (!nn->mbox_cmsg.workq)
+		return -ENOMEM;
+	return 0;
+}
+
+void nfp_ccm_mbox_free(struct nfp_net *nn)
+{
+	destroy_workqueue(nn->mbox_cmsg.workq);
+	WARN_ON(!skb_queue_empty(&nn->mbox_cmsg.queue));
+}
diff --git a/drivers/net/ethernet/netronome/nfp/crypto/crypto.h b/drivers/net/ethernet/netronome/nfp/crypto/crypto.h
new file mode 100644
index 000000000000..60372ddf69f0
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/crypto/crypto.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#ifndef NFP_CRYPTO_H
+#define NFP_CRYPTO_H 1
+
+struct nfp_net_tls_offload_ctx {
+	__be32 fw_handle[2];
+
+	u8 rx_end[0];
+	/* Tx only fields follow - Rx side does not have enough driver state
+	 * to fit these
+	 */
+
+	u32 next_seq;
+};
+
+#ifdef CONFIG_TLS_DEVICE
+int nfp_net_tls_init(struct nfp_net *nn);
+#else
+static inline int nfp_net_tls_init(struct nfp_net *nn)
+{
+	return 0;
+}
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/netronome/nfp/crypto/fw.h b/drivers/net/ethernet/netronome/nfp/crypto/fw.h
new file mode 100644
index 000000000000..67413d946c4a
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/crypto/fw.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#ifndef NFP_CRYPTO_FW_H
+#define NFP_CRYPTO_FW_H 1
+
+#include "../ccm.h"
+
+#define NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_ENC	0
+#define NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_DEC	1
+
+struct nfp_crypto_reply_simple {
+	struct nfp_ccm_hdr hdr;
+	__be32 error;
+};
+
+struct nfp_crypto_req_reset {
+	struct nfp_ccm_hdr hdr;
+	__be32 ep_id;
+};
+
+#define NFP_NET_TLS_IPVER		GENMASK(15, 12)
+#define NFP_NET_TLS_VLAN		GENMASK(11, 0)
+#define NFP_NET_TLS_VLAN_UNUSED			4095
+
+struct nfp_crypto_req_add_front {
+	struct nfp_ccm_hdr hdr;
+	__be32 ep_id;
+	u8 resv[3];
+	u8 opcode;
+	u8 key_len;
+	__be16 ipver_vlan __packed;
+	u8 l4_proto;
+#define NFP_NET_TLS_NON_ADDR_KEY_LEN	8
+	u8 l3_addrs[0];
+};
+
+struct nfp_crypto_req_add_back {
+	__be16 src_port;
+	__be16 dst_port;
+	__be32 key[8];
+	__be32 salt;
+	__be32 iv[2];
+	__be32 counter;
+	__be32 rec_no[2];
+	__be32 tcp_seq;
+};
+
+struct nfp_crypto_req_add_v4 {
+	struct nfp_crypto_req_add_front front;
+	__be32 src_ip;
+	__be32 dst_ip;
+	struct nfp_crypto_req_add_back back;
+};
+
+struct nfp_crypto_req_add_v6 {
+	struct nfp_crypto_req_add_front front;
+	__be32 src_ip[4];
+	__be32 dst_ip[4];
+	struct nfp_crypto_req_add_back back;
+};
+
+struct nfp_crypto_reply_add {
+	struct nfp_ccm_hdr hdr;
+	__be32 error;
+	__be32 handle[2];
+};
+
+struct nfp_crypto_req_del {
+	struct nfp_ccm_hdr hdr;
+	__be32 ep_id;
+	__be32 handle[2];
+};
+
+struct nfp_crypto_req_update {
+	struct nfp_ccm_hdr hdr;
+	__be32 ep_id;
+	u8 resv[3];
+	u8 opcode;
+	__be32 handle[2];
+	__be32 rec_no[2];
+	__be32 tcp_seq;
+};
+#endif
diff --git a/drivers/net/ethernet/netronome/nfp/crypto/tls.c b/drivers/net/ethernet/netronome/nfp/crypto/tls.c
new file mode 100644
index 000000000000..96a96b35c0ca
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/crypto/tls.c
@@ -0,0 +1,522 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <linux/bitfield.h>
+#include <linux/ipv6.h>
+#include <linux/skbuff.h>
+#include <linux/string.h>
+#include <net/tls.h>
+
+#include "../ccm.h"
+#include "../nfp_net.h"
+#include "crypto.h"
+#include "fw.h"
+
+#define NFP_NET_TLS_CCM_MBOX_OPS_MASK		\
+	(BIT(NFP_CCM_TYPE_CRYPTO_RESET) |	\
+	 BIT(NFP_CCM_TYPE_CRYPTO_ADD) |		\
+	 BIT(NFP_CCM_TYPE_CRYPTO_DEL) |		\
+	 BIT(NFP_CCM_TYPE_CRYPTO_UPDATE))
+
+#define NFP_NET_TLS_OPCODE_MASK_RX			\
+	BIT(NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_DEC)
+
+#define NFP_NET_TLS_OPCODE_MASK_TX			\
+	BIT(NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_ENC)
+
+#define NFP_NET_TLS_OPCODE_MASK						\
+	(NFP_NET_TLS_OPCODE_MASK_RX | NFP_NET_TLS_OPCODE_MASK_TX)
+
+static void nfp_net_crypto_set_op(struct nfp_net *nn, u8 opcode, bool on)
+{
+	u32 off, val;
+
+	off = nn->tlv_caps.crypto_enable_off + round_down(opcode / 8, 4);
+
+	val = nn_readl(nn, off);
+	if (on)
+		val |= BIT(opcode & 31);
+	else
+		val &= ~BIT(opcode & 31);
+	nn_writel(nn, off, val);
+}
+
+static bool
+__nfp_net_tls_conn_cnt_changed(struct nfp_net *nn, int add,
+			       enum tls_offload_ctx_dir direction)
+{
+	u8 opcode;
+	int cnt;
+
+	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
+		opcode = NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_ENC;
+		nn->ktls_tx_conn_cnt += add;
+		cnt = nn->ktls_tx_conn_cnt;
+		nn->dp.ktls_tx = !!nn->ktls_tx_conn_cnt;
+	} else {
+		opcode = NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_DEC;
+		nn->ktls_rx_conn_cnt += add;
+		cnt = nn->ktls_rx_conn_cnt;
+	}
+
+	/* Care only about 0 -> 1 and 1 -> 0 transitions */
+	if (cnt > 1)
+		return false;
+
+	nfp_net_crypto_set_op(nn, opcode, cnt);
+	return true;
+}
+
+static int
+nfp_net_tls_conn_cnt_changed(struct nfp_net *nn, int add,
+			     enum tls_offload_ctx_dir direction)
+{
+	int ret = 0;
+
+	/* Use the BAR lock to protect the connection counts */
+	nn_ctrl_bar_lock(nn);
+	if (__nfp_net_tls_conn_cnt_changed(nn, add, direction)) {
+		ret = __nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_CRYPTO);
+		/* Undo the cnt adjustment if failed */
+		if (ret)
+			__nfp_net_tls_conn_cnt_changed(nn, -add, direction);
+	}
+	nn_ctrl_bar_unlock(nn);
+
+	return ret;
+}
+
+static int
+nfp_net_tls_conn_add(struct nfp_net *nn, enum tls_offload_ctx_dir direction)
+{
+	return nfp_net_tls_conn_cnt_changed(nn, 1, direction);
+}
+
+static int
+nfp_net_tls_conn_remove(struct nfp_net *nn, enum tls_offload_ctx_dir direction)
+{
+	return nfp_net_tls_conn_cnt_changed(nn, -1, direction);
+}
+
+static struct sk_buff *
+nfp_net_tls_alloc_simple(struct nfp_net *nn, size_t req_sz, gfp_t flags)
+{
+	return nfp_ccm_mbox_msg_alloc(nn, req_sz,
+				      sizeof(struct nfp_crypto_reply_simple),
+				      flags);
+}
+
+static int
+nfp_net_tls_communicate_simple(struct nfp_net *nn, struct sk_buff *skb,
+			       const char *name, enum nfp_ccm_type type)
+{
+	struct nfp_crypto_reply_simple *reply;
+	int err;
+
+	err = __nfp_ccm_mbox_communicate(nn, skb, type,
+					 sizeof(*reply), sizeof(*reply),
+					 type == NFP_CCM_TYPE_CRYPTO_DEL);
+	if (err) {
+		nn_dp_warn(&nn->dp, "failed to %s TLS: %d\n", name, err);
+		return err;
+	}
+
+	reply = (void *)skb->data;
+	err = -be32_to_cpu(reply->error);
+	if (err)
+		nn_dp_warn(&nn->dp, "failed to %s TLS, fw replied: %d\n",
+			   name, err);
+	dev_consume_skb_any(skb);
+
+	return err;
+}
+
+static void nfp_net_tls_del_fw(struct nfp_net *nn, __be32 *fw_handle)
+{
+	struct nfp_crypto_req_del *req;
+	struct sk_buff *skb;
+
+	skb = nfp_net_tls_alloc_simple(nn, sizeof(*req), GFP_KERNEL);
+	if (!skb)
+		return;
+
+	req = (void *)skb->data;
+	req->ep_id = 0;
+	memcpy(req->handle, fw_handle, sizeof(req->handle));
+
+	nfp_net_tls_communicate_simple(nn, skb, "delete",
+				       NFP_CCM_TYPE_CRYPTO_DEL);
+}
+
+static void
+nfp_net_tls_set_ipver_vlan(struct nfp_crypto_req_add_front *front, u8 ipver)
+{
+	front->ipver_vlan = cpu_to_be16(FIELD_PREP(NFP_NET_TLS_IPVER, ipver) |
+					FIELD_PREP(NFP_NET_TLS_VLAN,
+						   NFP_NET_TLS_VLAN_UNUSED));
+}
+
+static void
+nfp_net_tls_assign_conn_id(struct nfp_net *nn,
+			   struct nfp_crypto_req_add_front *front)
+{
+	u32 len;
+	u64 id;
+
+	id = atomic64_inc_return(&nn->ktls_conn_id_gen);
+	len = front->key_len - NFP_NET_TLS_NON_ADDR_KEY_LEN;
+
+	memcpy(front->l3_addrs, &id, sizeof(id));
+	memset(front->l3_addrs + sizeof(id), 0, len - sizeof(id));
+}
+
+static struct nfp_crypto_req_add_back *
+nfp_net_tls_set_ipv4(struct nfp_net *nn, struct nfp_crypto_req_add_v4 *req,
+		     struct sock *sk, int direction)
+{
+	struct inet_sock *inet = inet_sk(sk);
+
+	req->front.key_len += sizeof(__be32) * 2;
+
+	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
+		nfp_net_tls_assign_conn_id(nn, &req->front);
+	} else {
+		req->src_ip = inet->inet_daddr;
+		req->dst_ip = inet->inet_saddr;
+	}
+
+	return &req->back;
+}
+
+static struct nfp_crypto_req_add_back *
+nfp_net_tls_set_ipv6(struct nfp_net *nn, struct nfp_crypto_req_add_v6 *req,
+		     struct sock *sk, int direction)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	req->front.key_len += sizeof(struct in6_addr) * 2;
+
+	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
+		nfp_net_tls_assign_conn_id(nn, &req->front);
+	} else {
+		memcpy(req->src_ip, &sk->sk_v6_daddr, sizeof(req->src_ip));
+		memcpy(req->dst_ip, &np->saddr, sizeof(req->dst_ip));
+	}
+
+#endif
+	return &req->back;
+}
+
+static void
+nfp_net_tls_set_l4(struct nfp_crypto_req_add_front *front,
+		   struct nfp_crypto_req_add_back *back, struct sock *sk,
+		   int direction)
+{
+	struct inet_sock *inet = inet_sk(sk);
+
+	front->l4_proto = IPPROTO_TCP;
+
+	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
+		back->src_port = 0;
+		back->dst_port = 0;
+	} else {
+		back->src_port = inet->inet_dport;
+		back->dst_port = inet->inet_sport;
+	}
+}
+
+static u8 nfp_tls_1_2_dir_to_opcode(enum tls_offload_ctx_dir direction)
+{
+	switch (direction) {
+	case TLS_OFFLOAD_CTX_DIR_TX:
+		return NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_ENC;
+	case TLS_OFFLOAD_CTX_DIR_RX:
+		return NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_DEC;
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+}
+
+static bool
+nfp_net_cipher_supported(struct nfp_net *nn, u16 cipher_type,
+			 enum tls_offload_ctx_dir direction)
+{
+	u8 bit;
+
+	switch (cipher_type) {
+	case TLS_CIPHER_AES_GCM_128:
+		if (direction == TLS_OFFLOAD_CTX_DIR_TX)
+			bit = NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_ENC;
+		else
+			bit = NFP_NET_CRYPTO_OP_TLS_1_2_AES_GCM_128_DEC;
+		break;
+	default:
+		return false;
+	}
+
+	return nn->tlv_caps.crypto_ops & BIT(bit);
+}
+
+static int
+nfp_net_tls_add(struct net_device *netdev, struct sock *sk,
+		enum tls_offload_ctx_dir direction,
+		struct tls_crypto_info *crypto_info,
+		u32 start_offload_tcp_sn)
+{
+	struct tls12_crypto_info_aes_gcm_128 *tls_ci;
+	struct nfp_net *nn = netdev_priv(netdev);
+	struct nfp_crypto_req_add_front *front;
+	struct nfp_net_tls_offload_ctx *ntls;
+	struct nfp_crypto_req_add_back *back;
+	struct nfp_crypto_reply_add *reply;
+	struct sk_buff *skb;
+	size_t req_sz;
+	void *req;
+	bool ipv6;
+	int err;
+
+	BUILD_BUG_ON(sizeof(struct nfp_net_tls_offload_ctx) >
+		     TLS_DRIVER_STATE_SIZE_TX);
+	BUILD_BUG_ON(offsetof(struct nfp_net_tls_offload_ctx, rx_end) >
+		     TLS_DRIVER_STATE_SIZE_RX);
+
+	if (!nfp_net_cipher_supported(nn, crypto_info->cipher_type, direction))
+		return -EOPNOTSUPP;
+
+	switch (sk->sk_family) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		if (sk->sk_ipv6only ||
+		    ipv6_addr_type(&sk->sk_v6_daddr) != IPV6_ADDR_MAPPED) {
+			req_sz = sizeof(struct nfp_crypto_req_add_v6);
+			ipv6 = true;
+			break;
+		}
+#endif
+		/* fall through */
+	case AF_INET:
+		req_sz = sizeof(struct nfp_crypto_req_add_v4);
+		ipv6 = false;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	err = nfp_net_tls_conn_add(nn, direction);
+	if (err)
+		return err;
+
+	skb = nfp_ccm_mbox_msg_alloc(nn, req_sz, sizeof(*reply), GFP_KERNEL);
+	if (!skb) {
+		err = -ENOMEM;
+		goto err_conn_remove;
+	}
+
+	front = (void *)skb->data;
+	front->ep_id = 0;
+	front->key_len = NFP_NET_TLS_NON_ADDR_KEY_LEN;
+	front->opcode = nfp_tls_1_2_dir_to_opcode(direction);
+	memset(front->resv, 0, sizeof(front->resv));
+
+	nfp_net_tls_set_ipver_vlan(front, ipv6 ? 6 : 4);
+
+	req = (void *)skb->data;
+	if (ipv6)
+		back = nfp_net_tls_set_ipv6(nn, req, sk, direction);
+	else
+		back = nfp_net_tls_set_ipv4(nn, req, sk, direction);
+
+	nfp_net_tls_set_l4(front, back, sk, direction);
+
+	back->counter = 0;
+	back->tcp_seq = cpu_to_be32(start_offload_tcp_sn);
+
+	tls_ci = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
+	memcpy(back->key, tls_ci->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE);
+	memset(&back->key[TLS_CIPHER_AES_GCM_128_KEY_SIZE / 4], 0,
+	       sizeof(back->key) - TLS_CIPHER_AES_GCM_128_KEY_SIZE);
+	memcpy(back->iv, tls_ci->iv, TLS_CIPHER_AES_GCM_128_IV_SIZE);
+	memcpy(&back->salt, tls_ci->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+	memcpy(back->rec_no, tls_ci->rec_seq, sizeof(tls_ci->rec_seq));
+
+	/* Get an extra ref on the skb so we can wipe the key after */
+	skb_get(skb);
+
+	err = nfp_ccm_mbox_communicate(nn, skb, NFP_CCM_TYPE_CRYPTO_ADD,
+				       sizeof(*reply), sizeof(*reply));
+	reply = (void *)skb->data;
+
+	/* We depend on CCM MBOX code not reallocating skb we sent
+	 * so we can clear the key material out of the memory.
+	 */
+	if (!WARN_ON_ONCE((u8 *)back < skb->head ||
+			  (u8 *)back > skb_end_pointer(skb)) &&
+	    !WARN_ON_ONCE((u8 *)&reply[1] > (u8 *)back))
+		memzero_explicit(back, sizeof(*back));
+	dev_consume_skb_any(skb); /* the extra ref from skb_get() above */
+
+	if (err) {
+		nn_dp_warn(&nn->dp, "failed to add TLS: %d (%d)\n",
+			   err, direction == TLS_OFFLOAD_CTX_DIR_TX);
+		/* communicate frees skb on error */
+		goto err_conn_remove;
+	}
+
+	err = -be32_to_cpu(reply->error);
+	if (err) {
+		if (err == -ENOSPC) {
+			if (!atomic_fetch_inc(&nn->ktls_no_space))
+				nn_info(nn, "HW TLS table full\n");
+		} else {
+			nn_dp_warn(&nn->dp,
+				   "failed to add TLS, FW replied: %d\n", err);
+		}
+		goto err_free_skb;
+	}
+
+	if (!reply->handle[0] && !reply->handle[1]) {
+		nn_dp_warn(&nn->dp, "FW returned NULL handle\n");
+		err = -EINVAL;
+		goto err_fw_remove;
+	}
+
+	ntls = tls_driver_ctx(sk, direction);
+	memcpy(ntls->fw_handle, reply->handle, sizeof(ntls->fw_handle));
+	if (direction == TLS_OFFLOAD_CTX_DIR_TX)
+		ntls->next_seq = start_offload_tcp_sn;
+	dev_consume_skb_any(skb);
+
+	if (direction == TLS_OFFLOAD_CTX_DIR_TX)
+		return 0;
+
+	tls_offload_rx_resync_set_type(sk,
+				       TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT);
+	return 0;
+
+err_fw_remove:
+	nfp_net_tls_del_fw(nn, reply->handle);
+err_free_skb:
+	dev_consume_skb_any(skb);
+err_conn_remove:
+	nfp_net_tls_conn_remove(nn, direction);
+	return err;
+}
+
+static void
+nfp_net_tls_del(struct net_device *netdev, struct tls_context *tls_ctx,
+		enum tls_offload_ctx_dir direction)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	struct nfp_net_tls_offload_ctx *ntls;
+
+	nfp_net_tls_conn_remove(nn, direction);
+
+	ntls = __tls_driver_ctx(tls_ctx, direction);
+	nfp_net_tls_del_fw(nn, ntls->fw_handle);
+}
+
+static int
+nfp_net_tls_resync(struct net_device *netdev, struct sock *sk, u32 seq,
+		   u8 *rcd_sn, enum tls_offload_ctx_dir direction)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	struct nfp_net_tls_offload_ctx *ntls;
+	struct nfp_crypto_req_update *req;
+	struct sk_buff *skb;
+	gfp_t flags;
+	int err;
+
+	flags = direction == TLS_OFFLOAD_CTX_DIR_TX ? GFP_KERNEL : GFP_ATOMIC;
+	skb = nfp_net_tls_alloc_simple(nn, sizeof(*req), flags);
+	if (!skb)
+		return -ENOMEM;
+
+	ntls = tls_driver_ctx(sk, direction);
+	req = (void *)skb->data;
+	req->ep_id = 0;
+	req->opcode = nfp_tls_1_2_dir_to_opcode(direction);
+	memset(req->resv, 0, sizeof(req->resv));
+	memcpy(req->handle, ntls->fw_handle, sizeof(ntls->fw_handle));
+	req->tcp_seq = cpu_to_be32(seq);
+	memcpy(req->rec_no, rcd_sn, sizeof(req->rec_no));
+
+	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
+		err = nfp_net_tls_communicate_simple(nn, skb, "sync",
+						     NFP_CCM_TYPE_CRYPTO_UPDATE);
+		if (err)
+			return err;
+		ntls->next_seq = seq;
+	} else {
+		nfp_ccm_mbox_post(nn, skb, NFP_CCM_TYPE_CRYPTO_UPDATE,
+				  sizeof(struct nfp_crypto_reply_simple));
+	}
+
+	return 0;
+}
+
+static const struct tlsdev_ops nfp_net_tls_ops = {
+	.tls_dev_add = nfp_net_tls_add,
+	.tls_dev_del = nfp_net_tls_del,
+	.tls_dev_resync = nfp_net_tls_resync,
+};
+
+static int nfp_net_tls_reset(struct nfp_net *nn)
+{
+	struct nfp_crypto_req_reset *req;
+	struct sk_buff *skb;
+
+	skb = nfp_net_tls_alloc_simple(nn, sizeof(*req), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	req = (void *)skb->data;
+	req->ep_id = 0;
+
+	return nfp_net_tls_communicate_simple(nn, skb, "reset",
+					      NFP_CCM_TYPE_CRYPTO_RESET);
+}
+
+int nfp_net_tls_init(struct nfp_net *nn)
+{
+	struct net_device *netdev = nn->dp.netdev;
+	int err;
+
+	if (!(nn->tlv_caps.crypto_ops & NFP_NET_TLS_OPCODE_MASK))
+		return 0;
+
+	if ((nn->tlv_caps.mbox_cmsg_types & NFP_NET_TLS_CCM_MBOX_OPS_MASK) !=
+	    NFP_NET_TLS_CCM_MBOX_OPS_MASK)
+		return 0;
+
+	if (!nfp_ccm_mbox_fits(nn, sizeof(struct nfp_crypto_req_add_v6))) {
+		nn_warn(nn, "disabling TLS offload - mbox too small: %d\n",
+			nn->tlv_caps.mbox_len);
+		return 0;
+	}
+
+	err = nfp_net_tls_reset(nn);
+	if (err)
+		return err;
+
+	nn_ctrl_bar_lock(nn);
+	nn_writel(nn, nn->tlv_caps.crypto_enable_off, 0);
+	err = __nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_CRYPTO);
+	nn_ctrl_bar_unlock(nn);
+	if (err)
+		return err;
+
+	if (nn->tlv_caps.crypto_ops & NFP_NET_TLS_OPCODE_MASK_RX) {
+		netdev->hw_features |= NETIF_F_HW_TLS_RX;
+		netdev->features |= NETIF_F_HW_TLS_RX;
+	}
+	if (nn->tlv_caps.crypto_ops & NFP_NET_TLS_OPCODE_MASK_TX) {
+		netdev->hw_features |= NETIF_F_HW_TLS_TX;
+		netdev->features |= NETIF_F_HW_TLS_TX;
+	}
+
+	netdev->tlsdev_ops = &nfp_net_tls_ops;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 8d54b36afee8..5a54fe848de4 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -3,7 +3,6 @@
 
 #include <linux/bitfield.h>
 #include <net/pkt_cls.h>
-#include <net/switchdev.h>
 #include <net/tc_act/tc_csum.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
@@ -37,7 +36,7 @@ static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan)
 
 static void
 nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
-		 const struct tc_action *action)
+		 const struct flow_action_entry *act)
 {
 	size_t act_size = sizeof(struct nfp_fl_push_vlan);
 	u16 tmp_push_vlan_tci;
@@ -45,30 +44,32 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 	push_vlan->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_VLAN;
 	push_vlan->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 	push_vlan->reserved = 0;
-	push_vlan->vlan_tpid = tcf_vlan_push_proto(action);
+	push_vlan->vlan_tpid = act->vlan.proto;
 
 	tmp_push_vlan_tci =
-		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, tcf_vlan_push_prio(action)) |
-		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action)) |
-		NFP_FL_PUSH_VLAN_CFI;
+		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, act->vlan.prio) |
+		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid);
 	push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
 }
 
 static int
-nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
-	       struct nfp_fl_payload *nfp_flow, int act_len)
+nfp_fl_pre_lag(struct nfp_app *app, const struct flow_action_entry *act,
+	       struct nfp_fl_payload *nfp_flow, int act_len,
+	       struct netlink_ext_ack *extack)
 {
 	size_t act_size = sizeof(struct nfp_fl_pre_lag);
 	struct nfp_fl_pre_lag *pre_lag;
 	struct net_device *out_dev;
 	int err;
 
-	out_dev = tcf_mirred_dev(action);
+	out_dev = act->dev;
 	if (!out_dev || !netif_is_lag_master(out_dev))
 		return 0;
 
-	if (act_len + act_size > NFP_FL_MAX_A_SIZ)
+	if (act_len + act_size > NFP_FL_MAX_A_SIZ) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at LAG action");
 		return -EOPNOTSUPP;
+	}
 
 	/* Pre_lag action must be first on action list.
 	 * If other actions already exist they need pushed forward.
@@ -78,7 +79,7 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
 			nfp_flow->action_data, act_len);
 
 	pre_lag = (struct nfp_fl_pre_lag *)nfp_flow->action_data;
-	err = nfp_flower_lag_populate_pre_action(app, out_dev, pre_lag);
+	err = nfp_flower_lag_populate_pre_action(app, out_dev, pre_lag, extack);
 	if (err)
 		return err;
 
@@ -92,9 +93,11 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
 
 static int
 nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
-	      const struct tc_action *action, struct nfp_fl_payload *nfp_flow,
+	      const struct flow_action_entry *act,
+	      struct nfp_fl_payload *nfp_flow,
 	      bool last, struct net_device *in_dev,
-	      enum nfp_flower_tun_type tun_type, int *tun_out_cnt)
+	      enum nfp_flower_tun_type tun_type, int *tun_out_cnt,
+	      struct netlink_ext_ack *extack)
 {
 	size_t act_size = sizeof(struct nfp_fl_output);
 	struct nfp_flower_priv *priv = app->priv;
@@ -104,19 +107,25 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 	output->head.jump_id = NFP_FL_ACTION_OPCODE_OUTPUT;
 	output->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 
-	out_dev = tcf_mirred_dev(action);
-	if (!out_dev)
+	out_dev = act->dev;
+	if (!out_dev) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid egress interface for mirred action");
 		return -EOPNOTSUPP;
+	}
 
 	tmp_flags = last ? NFP_FL_OUT_FLAGS_LAST : 0;
 
 	if (tun_type) {
 		/* Verify the egress netdev matches the tunnel type. */
-		if (!nfp_fl_netdev_is_tunnel_type(out_dev, tun_type))
+		if (!nfp_fl_netdev_is_tunnel_type(out_dev, tun_type)) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: egress interface does not match the required tunnel type");
 			return -EOPNOTSUPP;
+		}
 
-		if (*tun_out_cnt)
+		if (*tun_out_cnt) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: cannot offload more than one tunnel mirred output per filter");
 			return -EOPNOTSUPP;
+		}
 		(*tun_out_cnt)++;
 
 		output->flags = cpu_to_be16(tmp_flags |
@@ -128,8 +137,10 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 
 		output->flags = cpu_to_be16(tmp_flags);
 		gid = nfp_flower_lag_get_output_id(app, out_dev);
-		if (gid < 0)
+		if (gid < 0) {
+			NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot find group id for LAG action");
 			return gid;
+		}
 		output->port = cpu_to_be32(NFP_FL_LAG_OUT | gid);
 	} else {
 		/* Set action output parameters. */
@@ -137,33 +148,62 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 
 		if (nfp_netdev_is_nfp_repr(in_dev)) {
 			/* Confirm ingress and egress are on same device. */
-			if (!switchdev_port_same_parent_id(in_dev, out_dev))
+			if (!netdev_port_same_parent_id(in_dev, out_dev)) {
+				NL_SET_ERR_MSG_MOD(extack, "unsupported offload: ingress and egress interfaces are on different devices");
 				return -EOPNOTSUPP;
+			}
 		}
 
-		if (!nfp_netdev_is_nfp_repr(out_dev))
+		if (!nfp_netdev_is_nfp_repr(out_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: egress interface is not an nfp port");
 			return -EOPNOTSUPP;
+		}
 
 		output->port = cpu_to_be32(nfp_repr_get_port_id(out_dev));
-		if (!output->port)
+		if (!output->port) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid port id for egress interface");
 			return -EOPNOTSUPP;
+		}
 	}
 	nfp_flow->meta.shortcut = output->port;
 
 	return 0;
 }
 
+static bool
+nfp_flower_tun_is_gre(struct flow_cls_offload *flow, int start_idx)
+{
+	struct flow_action_entry *act = flow->rule->action.entries;
+	int num_act = flow->rule->action.num_entries;
+	int act_idx;
+
+	/* Preparse action list for next mirred or redirect action */
+	for (act_idx = start_idx + 1; act_idx < num_act; act_idx++)
+		if (act[act_idx].id == FLOW_ACTION_REDIRECT ||
+		    act[act_idx].id == FLOW_ACTION_MIRRED)
+			return netif_is_gretap(act[act_idx].dev);
+
+	return false;
+}
+
 static enum nfp_flower_tun_type
-nfp_fl_get_tun_from_act_l4_port(struct nfp_app *app,
-				const struct tc_action *action)
+nfp_fl_get_tun_from_act(struct nfp_app *app,
+			struct flow_cls_offload *flow,
+			const struct flow_action_entry *act, int act_idx)
 {
-	struct ip_tunnel_info *tun = tcf_tunnel_info(action);
+	const struct ip_tunnel_info *tun = act->tunnel;
 	struct nfp_flower_priv *priv = app->priv;
 
+	/* Determine the tunnel type based on the egress netdev
+	 * in the mirred action for tunnels without l4.
+	 */
+	if (nfp_flower_tun_is_gre(flow, act_idx))
+		return NFP_FL_TUNNEL_GRE;
+
 	switch (tun->key.tp_dst) {
-	case htons(NFP_FL_VXLAN_PORT):
+	case htons(IANA_VXLAN_UDP_PORT):
 		return NFP_FL_TUNNEL_VXLAN;
-	case htons(NFP_FL_GENEVE_PORT):
+	case htons(GENEVE_UDP_PORT):
 		if (priv->flower_ext_feats & NFP_FL_FEATS_GENEVE)
 			return NFP_FL_TUNNEL_GENEVE;
 		/* FALLTHROUGH */
@@ -195,9 +235,10 @@ static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len)
 
 static int
 nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
-			   const struct tc_action *action)
+			   const struct flow_action_entry *act,
+			   struct netlink_ext_ack *extack)
 {
-	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	struct ip_tunnel_info *ip_tun = (struct ip_tunnel_info *)act->tunnel;
 	int opt_len, opt_cnt, act_start, tot_push_len;
 	u8 *src = ip_tunnel_info_opts(ip_tun);
 
@@ -213,20 +254,26 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
 		struct geneve_opt *opt = (struct geneve_opt *)src;
 
 		opt_cnt++;
-		if (opt_cnt > NFP_FL_MAX_GENEVE_OPT_CNT)
+		if (opt_cnt > NFP_FL_MAX_GENEVE_OPT_CNT) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed number of geneve options exceeded");
 			return -EOPNOTSUPP;
+		}
 
 		tot_push_len += sizeof(struct nfp_fl_push_geneve) +
 			       opt->length * 4;
-		if (tot_push_len > NFP_FL_MAX_GENEVE_OPT_ACT)
+		if (tot_push_len > NFP_FL_MAX_GENEVE_OPT_ACT) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at push geneve options");
 			return -EOPNOTSUPP;
+		}
 
 		opt_len -= sizeof(struct geneve_opt) + opt->length * 4;
 		src += sizeof(struct geneve_opt) + opt->length * 4;
 	}
 
-	if (*list_len + tot_push_len > NFP_FL_MAX_A_SIZ)
+	if (*list_len + tot_push_len > NFP_FL_MAX_A_SIZ) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at push geneve options");
 		return -EOPNOTSUPP;
+	}
 
 	act_start = *list_len;
 	*list_len += tot_push_len;
@@ -257,15 +304,14 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
 }
 
 static int
-nfp_fl_set_ipv4_udp_tun(struct nfp_app *app,
-			struct nfp_fl_set_ipv4_udp_tun *set_tun,
-			const struct tc_action *action,
-			struct nfp_fl_pre_tunnel *pre_tun,
-			enum nfp_flower_tun_type tun_type,
-			struct net_device *netdev)
+nfp_fl_set_ipv4_tun(struct nfp_app *app, struct nfp_fl_set_ipv4_tun *set_tun,
+		    const struct flow_action_entry *act,
+		    struct nfp_fl_pre_tunnel *pre_tun,
+		    enum nfp_flower_tun_type tun_type,
+		    struct net_device *netdev, struct netlink_ext_ack *extack)
 {
-	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
-	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	size_t act_size = sizeof(struct nfp_fl_set_ipv4_tun);
+	const struct ip_tunnel_info *ip_tun = act->tunnel;
 	struct nfp_flower_priv *priv = app->priv;
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
@@ -276,8 +322,10 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_app *app,
 		     NFP_FL_TUNNEL_GENEVE_OPT != TUNNEL_GENEVE_OPT);
 	if (ip_tun->options_len &&
 	    (tun_type != NFP_FL_TUNNEL_GENEVE ||
-	    !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT)))
+	    !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support geneve options offload");
 		return -EOPNOTSUPP;
+	}
 
 	set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
 	set_tun->head.len_lw = act_size >> NFP_FL_LW_SIZ;
@@ -317,8 +365,10 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_app *app,
 	set_tun->tos = ip_tun->key.tos;
 
 	if (!(ip_tun->key.tun_flags & NFP_FL_TUNNEL_KEY) ||
-	    ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS)
+	    ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support tunnel flag offload");
 		return -EOPNOTSUPP;
+	}
 	set_tun->tun_flags = ip_tun->key.tun_flags;
 
 	if (tun_type == NFP_FL_TUNNEL_GENEVE) {
@@ -345,19 +395,23 @@ static void nfp_fl_set_helper32(u32 value, u32 mask, u8 *p_exact, u8 *p_mask)
 }
 
 static int
-nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off,
-	       struct nfp_fl_set_eth *set_eth)
+nfp_fl_set_eth(const struct flow_action_entry *act, u32 off,
+	       struct nfp_fl_set_eth *set_eth, struct netlink_ext_ack *extack)
 {
 	u32 exact, mask;
 
-	if (off + 4 > ETH_ALEN * 2)
+	if (off + 4 > ETH_ALEN * 2) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit ethernet action");
 		return -EOPNOTSUPP;
+	}
 
-	mask = ~tcf_pedit_mask(action, idx);
-	exact = tcf_pedit_val(action, idx);
+	mask = ~act->mangle.mask;
+	exact = act->mangle.val;
 
-	if (exact & ~mask)
+	if (exact & ~mask) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit ethernet action");
 		return -EOPNOTSUPP;
+	}
 
 	nfp_fl_set_helper32(exact, mask, &set_eth->eth_addr_val[off],
 			    &set_eth->eth_addr_mask[off]);
@@ -376,9 +430,10 @@ struct ipv4_ttl_word {
 };
 
 static int
-nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
+nfp_fl_set_ip4(const struct flow_action_entry *act, u32 off,
 	       struct nfp_fl_set_ip4_addrs *set_ip_addr,
-	       struct nfp_fl_set_ip4_ttl_tos *set_ip_ttl_tos)
+	       struct nfp_fl_set_ip4_ttl_tos *set_ip_ttl_tos,
+	       struct netlink_ext_ack *extack)
 {
 	struct ipv4_ttl_word *ttl_word_mask;
 	struct ipv4_ttl_word *ttl_word;
@@ -387,11 +442,13 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
 	__be32 exact, mask;
 
 	/* We are expecting tcf_pedit to return a big endian value */
-	mask = (__force __be32)~tcf_pedit_mask(action, idx);
-	exact = (__force __be32)tcf_pedit_val(action, idx);
+	mask = (__force __be32)~act->mangle.mask;
+	exact = (__force __be32)act->mangle.val;
 
-	if (exact & ~mask)
+	if (exact & ~mask) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv4 action");
 		return -EOPNOTSUPP;
+	}
 
 	switch (off) {
 	case offsetof(struct iphdr, daddr):
@@ -414,8 +471,10 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
 		ttl_word_mask = (struct ipv4_ttl_word *)&mask;
 		ttl_word = (struct ipv4_ttl_word *)&exact;
 
-		if (ttl_word_mask->protocol || ttl_word_mask->check)
+		if (ttl_word_mask->protocol || ttl_word_mask->check) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv4 ttl action");
 			return -EOPNOTSUPP;
+		}
 
 		set_ip_ttl_tos->ipv4_ttl_mask |= ttl_word_mask->ttl;
 		set_ip_ttl_tos->ipv4_ttl &= ~ttl_word_mask->ttl;
@@ -430,8 +489,10 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
 		tos_word = (struct iphdr *)&exact;
 
 		if (tos_word_mask->version || tos_word_mask->ihl ||
-		    tos_word_mask->tot_len)
+		    tos_word_mask->tot_len) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv4 tos action");
 			return -EOPNOTSUPP;
+		}
 
 		set_ip_ttl_tos->ipv4_tos_mask |= tos_word_mask->tos;
 		set_ip_ttl_tos->ipv4_tos &= ~tos_word_mask->tos;
@@ -442,6 +503,7 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
 					      NFP_FL_LW_SIZ;
 		break;
 	default:
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pedit on unsupported section of IPv4 header");
 		return -EOPNOTSUPP;
 	}
 
@@ -469,7 +531,8 @@ struct ipv6_hop_limit_word {
 
 static int
 nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask,
-				    struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl)
+				    struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl,
+				    struct netlink_ext_ack *extack)
 {
 	struct ipv6_hop_limit_word *fl_hl_mask;
 	struct ipv6_hop_limit_word *fl_hl;
@@ -479,8 +542,10 @@ nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask,
 		fl_hl_mask = (struct ipv6_hop_limit_word *)&mask;
 		fl_hl = (struct ipv6_hop_limit_word *)&exact;
 
-		if (fl_hl_mask->nexthdr || fl_hl_mask->payload_len)
+		if (fl_hl_mask->nexthdr || fl_hl_mask->payload_len) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv6 hop limit action");
 			return -EOPNOTSUPP;
+		}
 
 		ip_hl_fl->ipv6_hop_limit_mask |= fl_hl_mask->hop_limit;
 		ip_hl_fl->ipv6_hop_limit &= ~fl_hl_mask->hop_limit;
@@ -489,8 +554,10 @@ nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask,
 		break;
 	case round_down(offsetof(struct ipv6hdr, flow_lbl), 4):
 		if (mask & ~IPV6_FLOW_LABEL_MASK ||
-		    exact & ~IPV6_FLOW_LABEL_MASK)
+		    exact & ~IPV6_FLOW_LABEL_MASK) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv6 flow label action");
 			return -EOPNOTSUPP;
+		}
 
 		ip_hl_fl->ipv6_label_mask |= mask;
 		ip_hl_fl->ipv6_label &= ~mask;
@@ -505,25 +572,28 @@ nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask,
 }
 
 static int
-nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
+nfp_fl_set_ip6(const struct flow_action_entry *act, u32 off,
 	       struct nfp_fl_set_ipv6_addr *ip_dst,
 	       struct nfp_fl_set_ipv6_addr *ip_src,
-	       struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl)
+	       struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl,
+	       struct netlink_ext_ack *extack)
 {
 	__be32 exact, mask;
 	int err = 0;
 	u8 word;
 
 	/* We are expecting tcf_pedit to return a big endian value */
-	mask = (__force __be32)~tcf_pedit_mask(action, idx);
-	exact = (__force __be32)tcf_pedit_val(action, idx);
+	mask = (__force __be32)~act->mangle.mask;
+	exact = (__force __be32)act->mangle.val;
 
-	if (exact & ~mask)
+	if (exact & ~mask) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv6 action");
 		return -EOPNOTSUPP;
+	}
 
 	if (off < offsetof(struct ipv6hdr, saddr)) {
 		err = nfp_fl_set_ip6_hop_limit_flow_label(off, exact, mask,
-							  ip_hl_fl);
+							  ip_hl_fl, extack);
 	} else if (off < offsetof(struct ipv6hdr, daddr)) {
 		word = (off - offsetof(struct ipv6hdr, saddr)) / sizeof(exact);
 		nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_SRC, word,
@@ -534,6 +604,7 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
 		nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_DST, word,
 				      exact, mask, ip_dst);
 	} else {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pedit on unsupported section of IPv6 header");
 		return -EOPNOTSUPP;
 	}
 
@@ -541,19 +612,24 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
 }
 
 static int
-nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off,
-		 struct nfp_fl_set_tport *set_tport, int opcode)
+nfp_fl_set_tport(const struct flow_action_entry *act, u32 off,
+		 struct nfp_fl_set_tport *set_tport, int opcode,
+		 struct netlink_ext_ack *extack)
 {
 	u32 exact, mask;
 
-	if (off)
+	if (off) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pedit on unsupported section of L4 header");
 		return -EOPNOTSUPP;
+	}
 
-	mask = ~tcf_pedit_mask(action, idx);
-	exact = tcf_pedit_val(action, idx);
+	mask = ~act->mangle.mask;
+	exact = act->mangle.val;
 
-	if (exact & ~mask)
+	if (exact & ~mask) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit L4 action");
 		return -EOPNOTSUPP;
+	}
 
 	nfp_fl_set_helper32(exact, mask, set_tport->tp_port_val,
 			    set_tport->tp_port_mask);
@@ -583,146 +659,107 @@ static u32 nfp_fl_csum_l4_to_flag(u8 ip_proto)
 	}
 }
 
-static int
-nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
-	     char *nfp_action, int *a_len, u32 *csum_updated)
-{
+struct nfp_flower_pedit_acts {
 	struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
 	struct nfp_fl_set_ipv6_tc_hl_fl set_ip6_tc_hl_fl;
 	struct nfp_fl_set_ip4_ttl_tos set_ip_ttl_tos;
 	struct nfp_fl_set_ip4_addrs set_ip_addr;
 	struct nfp_fl_set_tport set_tport;
 	struct nfp_fl_set_eth set_eth;
-	enum pedit_header_type htype;
-	int idx, nkeys, err;
+};
+
+static int
+nfp_fl_commit_mangle(struct flow_cls_offload *flow, char *nfp_action,
+		     int *a_len, struct nfp_flower_pedit_acts *set_act,
+		     u32 *csum_updated)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	size_t act_size = 0;
-	u32 offset, cmd;
 	u8 ip_proto = 0;
 
-	memset(&set_ip6_tc_hl_fl, 0, sizeof(set_ip6_tc_hl_fl));
-	memset(&set_ip_ttl_tos, 0, sizeof(set_ip_ttl_tos));
-	memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
-	memset(&set_ip6_src, 0, sizeof(set_ip6_src));
-	memset(&set_ip_addr, 0, sizeof(set_ip_addr));
-	memset(&set_tport, 0, sizeof(set_tport));
-	memset(&set_eth, 0, sizeof(set_eth));
-	nkeys = tcf_pedit_nkeys(action);
-
-	for (idx = 0; idx < nkeys; idx++) {
-		cmd = tcf_pedit_cmd(action, idx);
-		htype = tcf_pedit_htype(action, idx);
-		offset = tcf_pedit_offset(action, idx);
-
-		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET)
-			return -EOPNOTSUPP;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		switch (htype) {
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
-			err = nfp_fl_set_eth(action, idx, offset, &set_eth);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
-			err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr,
-					     &set_ip_ttl_tos);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
-			err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst,
-					     &set_ip6_src, &set_ip6_tc_hl_fl);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
-			err = nfp_fl_set_tport(action, idx, offset, &set_tport,
-					       NFP_FL_ACTION_OPCODE_SET_TCP);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
-			err = nfp_fl_set_tport(action, idx, offset, &set_tport,
-					       NFP_FL_ACTION_OPCODE_SET_UDP);
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-		if (err)
-			return err;
+		flow_rule_match_basic(rule, &match);
+		ip_proto = match.key->ip_proto;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *basic;
-
-		basic = skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  flow->key);
-		ip_proto = basic->ip_proto;
-	}
-
-	if (set_eth.head.len_lw) {
-		act_size = sizeof(set_eth);
-		memcpy(nfp_action, &set_eth, act_size);
+	if (set_act->set_eth.head.len_lw) {
+		act_size = sizeof(set_act->set_eth);
+		memcpy(nfp_action, &set_act->set_eth, act_size);
 		*a_len += act_size;
 	}
-	if (set_ip_ttl_tos.head.len_lw) {
+
+	if (set_act->set_ip_ttl_tos.head.len_lw) {
 		nfp_action += act_size;
-		act_size = sizeof(set_ip_ttl_tos);
-		memcpy(nfp_action, &set_ip_ttl_tos, act_size);
+		act_size = sizeof(set_act->set_ip_ttl_tos);
+		memcpy(nfp_action, &set_act->set_ip_ttl_tos, act_size);
 		*a_len += act_size;
 
 		/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
 		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
 				nfp_fl_csum_l4_to_flag(ip_proto);
 	}
-	if (set_ip_addr.head.len_lw) {
+
+	if (set_act->set_ip_addr.head.len_lw) {
 		nfp_action += act_size;
-		act_size = sizeof(set_ip_addr);
-		memcpy(nfp_action, &set_ip_addr, act_size);
+		act_size = sizeof(set_act->set_ip_addr);
+		memcpy(nfp_action, &set_act->set_ip_addr, act_size);
 		*a_len += act_size;
 
 		/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
 		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
 				nfp_fl_csum_l4_to_flag(ip_proto);
 	}
-	if (set_ip6_tc_hl_fl.head.len_lw) {
+
+	if (set_act->set_ip6_tc_hl_fl.head.len_lw) {
 		nfp_action += act_size;
-		act_size = sizeof(set_ip6_tc_hl_fl);
-		memcpy(nfp_action, &set_ip6_tc_hl_fl, act_size);
+		act_size = sizeof(set_act->set_ip6_tc_hl_fl);
+		memcpy(nfp_action, &set_act->set_ip6_tc_hl_fl, act_size);
 		*a_len += act_size;
 
 		/* Hardware will automatically fix TCP/UDP checksum. */
 		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	}
-	if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
+
+	if (set_act->set_ip6_dst.head.len_lw &&
+	    set_act->set_ip6_src.head.len_lw) {
 		/* TC compiles set src and dst IPv6 address as a single action,
 		 * the hardware requires this to be 2 separate actions.
 		 */
 		nfp_action += act_size;
-		act_size = sizeof(set_ip6_src);
-		memcpy(nfp_action, &set_ip6_src, act_size);
+		act_size = sizeof(set_act->set_ip6_src);
+		memcpy(nfp_action, &set_act->set_ip6_src, act_size);
 		*a_len += act_size;
 
-		act_size = sizeof(set_ip6_dst);
-		memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst,
-		       act_size);
+		act_size = sizeof(set_act->set_ip6_dst);
+		memcpy(&nfp_action[sizeof(set_act->set_ip6_src)],
+		       &set_act->set_ip6_dst, act_size);
 		*a_len += act_size;
 
 		/* Hardware will automatically fix TCP/UDP checksum. */
 		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
-	} else if (set_ip6_dst.head.len_lw) {
+	} else if (set_act->set_ip6_dst.head.len_lw) {
 		nfp_action += act_size;
-		act_size = sizeof(set_ip6_dst);
-		memcpy(nfp_action, &set_ip6_dst, act_size);
+		act_size = sizeof(set_act->set_ip6_dst);
+		memcpy(nfp_action, &set_act->set_ip6_dst, act_size);
 		*a_len += act_size;
 
 		/* Hardware will automatically fix TCP/UDP checksum. */
 		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
-	} else if (set_ip6_src.head.len_lw) {
+	} else if (set_act->set_ip6_src.head.len_lw) {
 		nfp_action += act_size;
-		act_size = sizeof(set_ip6_src);
-		memcpy(nfp_action, &set_ip6_src, act_size);
+		act_size = sizeof(set_act->set_ip6_src);
+		memcpy(nfp_action, &set_act->set_ip6_src, act_size);
 		*a_len += act_size;
 
 		/* Hardware will automatically fix TCP/UDP checksum. */
 		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	}
-	if (set_tport.head.len_lw) {
+	if (set_act->set_tport.head.len_lw) {
 		nfp_action += act_size;
-		act_size = sizeof(set_tport);
-		memcpy(nfp_action, &set_tport, act_size);
+		act_size = sizeof(set_act->set_tport);
+		memcpy(nfp_action, &set_act->set_tport, act_size);
 		*a_len += act_size;
 
 		/* Hardware will automatically fix TCP/UDP checksum. */
@@ -733,11 +770,47 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 }
 
 static int
-nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
+nfp_fl_pedit(const struct flow_action_entry *act,
+	     struct flow_cls_offload *flow, char *nfp_action, int *a_len,
+	     u32 *csum_updated, struct nfp_flower_pedit_acts *set_act,
+	     struct netlink_ext_ack *extack)
+{
+	enum flow_action_mangle_base htype;
+	u32 offset;
+
+	htype = act->mangle.htype;
+	offset = act->mangle.offset;
+
+	switch (htype) {
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+		return nfp_fl_set_eth(act, offset, &set_act->set_eth, extack);
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+		return nfp_fl_set_ip4(act, offset, &set_act->set_ip_addr,
+				      &set_act->set_ip_ttl_tos, extack);
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+		return nfp_fl_set_ip6(act, offset, &set_act->set_ip6_dst,
+				      &set_act->set_ip6_src,
+				      &set_act->set_ip6_tc_hl_fl, extack);
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+		return nfp_fl_set_tport(act, offset, &set_act->set_tport,
+					NFP_FL_ACTION_OPCODE_SET_TCP, extack);
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+		return nfp_fl_set_tport(act, offset, &set_act->set_tport,
+					NFP_FL_ACTION_OPCODE_SET_UDP, extack);
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pedit on unsupported header");
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nfp_flower_output_action(struct nfp_app *app,
+			 const struct flow_action_entry *act,
 			 struct nfp_fl_payload *nfp_fl, int *a_len,
 			 struct net_device *netdev, bool last,
 			 enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
-			 int *out_cnt, u32 *csum_updated)
+			 int *out_cnt, u32 *csum_updated,
+			 struct netlink_ext_ack *extack)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_output *output;
@@ -746,15 +819,19 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 	/* If csum_updated has not been reset by now, it means HW will
 	 * incorrectly update csums when they are not requested.
 	 */
-	if (*csum_updated)
+	if (*csum_updated) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: set actions without updating checksums are not supported");
 		return -EOPNOTSUPP;
+	}
 
-	if (*a_len + sizeof(struct nfp_fl_output) > NFP_FL_MAX_A_SIZ)
+	if (*a_len + sizeof(struct nfp_fl_output) > NFP_FL_MAX_A_SIZ) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: mirred output increases action list size beyond the allowed maximum");
 		return -EOPNOTSUPP;
+	}
 
 	output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len];
-	err = nfp_fl_output(app, output, a, nfp_fl, last, netdev, *tun_type,
-			    tun_out_cnt);
+	err = nfp_fl_output(app, output, act, nfp_fl, last, netdev, *tun_type,
+			    tun_out_cnt, extack);
 	if (err)
 		return err;
 
@@ -764,11 +841,13 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 		/* nfp_fl_pre_lag returns -err or size of prelag action added.
 		 * This will be 0 if it is not egressing to a lag dev.
 		 */
-		prelag_size = nfp_fl_pre_lag(app, a, nfp_fl, *a_len);
-		if (prelag_size < 0)
+		prelag_size = nfp_fl_pre_lag(app, act, nfp_fl, *a_len, extack);
+		if (prelag_size < 0) {
 			return prelag_size;
-		else if (prelag_size > 0 && (!last || *out_cnt))
+		} else if (prelag_size > 0 && (!last || *out_cnt)) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: LAG action has to be last action in action list");
 			return -EOPNOTSUPP;
+		}
 
 		*a_len += prelag_size;
 	}
@@ -778,116 +857,179 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 }
 
 static int
-nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
-		       struct tc_cls_flower_offload *flow,
+nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act,
+		       struct flow_cls_offload *flow,
 		       struct nfp_fl_payload *nfp_fl, int *a_len,
 		       struct net_device *netdev,
 		       enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
-		       int *out_cnt, u32 *csum_updated)
+		       int *out_cnt, u32 *csum_updated,
+		       struct nfp_flower_pedit_acts *set_act,
+		       struct netlink_ext_ack *extack, int act_idx)
 {
-	struct nfp_fl_set_ipv4_udp_tun *set_tun;
+	struct nfp_fl_set_ipv4_tun *set_tun;
 	struct nfp_fl_pre_tunnel *pre_tun;
 	struct nfp_fl_push_vlan *psh_v;
 	struct nfp_fl_pop_vlan *pop_v;
 	int err;
 
-	if (is_tcf_gact_shot(a)) {
+	switch (act->id) {
+	case FLOW_ACTION_DROP:
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_DROP);
-	} else if (is_tcf_mirred_egress_redirect(a)) {
-		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
+		break;
+	case FLOW_ACTION_REDIRECT:
+		err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev,
 					       true, tun_type, tun_out_cnt,
-					       out_cnt, csum_updated);
+					       out_cnt, csum_updated, extack);
 		if (err)
 			return err;
-
-	} else if (is_tcf_mirred_egress_mirror(a)) {
-		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
+		break;
+	case FLOW_ACTION_MIRRED:
+		err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev,
 					       false, tun_type, tun_out_cnt,
-					       out_cnt, csum_updated);
+					       out_cnt, csum_updated, extack);
 		if (err)
 			return err;
-
-	} else if (is_tcf_vlan(a) && tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
-		if (*a_len + sizeof(struct nfp_fl_pop_vlan) > NFP_FL_MAX_A_SIZ)
+		break;
+	case FLOW_ACTION_VLAN_POP:
+		if (*a_len +
+		    sizeof(struct nfp_fl_pop_vlan) > NFP_FL_MAX_A_SIZ) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at pop vlan");
 			return -EOPNOTSUPP;
+		}
 
 		pop_v = (struct nfp_fl_pop_vlan *)&nfp_fl->action_data[*a_len];
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_POPV);
 
 		nfp_fl_pop_vlan(pop_v);
 		*a_len += sizeof(struct nfp_fl_pop_vlan);
-	} else if (is_tcf_vlan(a) && tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
-		if (*a_len + sizeof(struct nfp_fl_push_vlan) > NFP_FL_MAX_A_SIZ)
+		break;
+	case FLOW_ACTION_VLAN_PUSH:
+		if (*a_len +
+		    sizeof(struct nfp_fl_push_vlan) > NFP_FL_MAX_A_SIZ) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at push vlan");
 			return -EOPNOTSUPP;
+		}
 
 		psh_v = (struct nfp_fl_push_vlan *)&nfp_fl->action_data[*a_len];
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
 
-		nfp_fl_push_vlan(psh_v, a);
+		nfp_fl_push_vlan(psh_v, act);
 		*a_len += sizeof(struct nfp_fl_push_vlan);
-	} else if (is_tcf_tunnel_set(a)) {
-		struct ip_tunnel_info *ip_tun = tcf_tunnel_info(a);
+		break;
+	case FLOW_ACTION_TUNNEL_ENCAP: {
+		const struct ip_tunnel_info *ip_tun = act->tunnel;
 
-		*tun_type = nfp_fl_get_tun_from_act_l4_port(app, a);
-		if (*tun_type == NFP_FL_TUNNEL_NONE)
+		*tun_type = nfp_fl_get_tun_from_act(app, flow, act, act_idx);
+		if (*tun_type == NFP_FL_TUNNEL_NONE) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported tunnel type in action list");
 			return -EOPNOTSUPP;
+		}
 
-		if (ip_tun->mode & ~NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS)
+		if (ip_tun->mode & ~NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported tunnel flags in action list");
 			return -EOPNOTSUPP;
+		}
 
 		/* Pre-tunnel action is required for tunnel encap.
 		 * This checks for next hop entries on NFP.
 		 * If none, the packet falls back before applying other actions.
 		 */
 		if (*a_len + sizeof(struct nfp_fl_pre_tunnel) +
-		    sizeof(struct nfp_fl_set_ipv4_udp_tun) > NFP_FL_MAX_A_SIZ)
+		    sizeof(struct nfp_fl_set_ipv4_tun) > NFP_FL_MAX_A_SIZ) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at tunnel encap");
 			return -EOPNOTSUPP;
+		}
 
 		pre_tun = nfp_fl_pre_tunnel(nfp_fl->action_data, *a_len);
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
 		*a_len += sizeof(struct nfp_fl_pre_tunnel);
 
-		err = nfp_fl_push_geneve_options(nfp_fl, a_len, a);
+		err = nfp_fl_push_geneve_options(nfp_fl, a_len, act, extack);
 		if (err)
 			return err;
 
 		set_tun = (void *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_set_ipv4_udp_tun(app, set_tun, a, pre_tun,
-					      *tun_type, netdev);
+		err = nfp_fl_set_ipv4_tun(app, set_tun, act, pre_tun,
+					  *tun_type, netdev, extack);
 		if (err)
 			return err;
-		*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
-	} else if (is_tcf_tunnel_release(a)) {
+		*a_len += sizeof(struct nfp_fl_set_ipv4_tun);
+		}
+		break;
+	case FLOW_ACTION_TUNNEL_DECAP:
 		/* Tunnel decap is handled by default so accept action. */
 		return 0;
-	} else if (is_tcf_pedit(a)) {
-		if (nfp_fl_pedit(a, flow, &nfp_fl->action_data[*a_len],
-				 a_len, csum_updated))
+	case FLOW_ACTION_MANGLE:
+		if (nfp_fl_pedit(act, flow, &nfp_fl->action_data[*a_len],
+				 a_len, csum_updated, set_act, extack))
 			return -EOPNOTSUPP;
-	} else if (is_tcf_csum(a)) {
+		break;
+	case FLOW_ACTION_CSUM:
 		/* csum action requests recalc of something we have not fixed */
-		if (tcf_csum_update_flags(a) & ~*csum_updated)
+		if (act->csum_flags & ~*csum_updated) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported csum update action in action list");
 			return -EOPNOTSUPP;
+		}
 		/* If we will correctly fix the csum we can remove it from the
 		 * csum update list. Which will later be used to check support.
 		 */
-		*csum_updated &= ~tcf_csum_update_flags(a);
-	} else {
+		*csum_updated &= ~act->csum_flags;
+		break;
+	default:
 		/* Currently we do not handle any other actions. */
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported action in action list");
 		return -EOPNOTSUPP;
 	}
 
 	return 0;
 }
 
+static bool nfp_fl_check_mangle_start(struct flow_action *flow_act,
+				      int current_act_idx)
+{
+	struct flow_action_entry current_act;
+	struct flow_action_entry prev_act;
+
+	current_act = flow_act->entries[current_act_idx];
+	if (current_act.id != FLOW_ACTION_MANGLE)
+		return false;
+
+	if (current_act_idx == 0)
+		return true;
+
+	prev_act = flow_act->entries[current_act_idx - 1];
+
+	return prev_act.id != FLOW_ACTION_MANGLE;
+}
+
+static bool nfp_fl_check_mangle_end(struct flow_action *flow_act,
+				    int current_act_idx)
+{
+	struct flow_action_entry current_act;
+	struct flow_action_entry next_act;
+
+	current_act = flow_act->entries[current_act_idx];
+	if (current_act.id != FLOW_ACTION_MANGLE)
+		return false;
+
+	if (current_act_idx == flow_act->num_entries)
+		return true;
+
+	next_act = flow_act->entries[current_act_idx + 1];
+
+	return next_act.id != FLOW_ACTION_MANGLE;
+}
+
 int nfp_flower_compile_action(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct net_device *netdev,
-			      struct nfp_fl_payload *nfp_flow)
+			      struct nfp_fl_payload *nfp_flow,
+			      struct netlink_ext_ack *extack)
 {
 	int act_len, act_cnt, err, tun_out_cnt, out_cnt, i;
+	struct nfp_flower_pedit_acts set_act;
 	enum nfp_flower_tun_type tun_type;
-	const struct tc_action *a;
+	struct flow_action_entry *act;
 	u32 csum_updated = 0;
 
 	memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
@@ -898,13 +1040,20 @@ int nfp_flower_compile_action(struct nfp_app *app,
 	tun_out_cnt = 0;
 	out_cnt = 0;
 
-	tcf_exts_for_each_action(i, a, flow->exts) {
-		err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len,
+	flow_action_for_each(i, act, &flow->rule->action) {
+		if (nfp_fl_check_mangle_start(&flow->rule->action, i))
+			memset(&set_act, 0, sizeof(set_act));
+		err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len,
 					     netdev, &tun_type, &tun_out_cnt,
-					     &out_cnt, &csum_updated);
+					     &out_cnt, &csum_updated,
+					     &set_act, extack, i);
 		if (err)
 			return err;
 		act_cnt++;
+		if (nfp_fl_check_mangle_end(&flow->rule->action, i))
+			nfp_fl_commit_mangle(flow,
+					     &nfp_flow->action_data[act_len],
+					     &act_len, &set_act, &csum_updated);
 	}
 
 	/* We optimise when the action list is small, this can unfortunately
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index 4c5eaf36d5bb..d5bbe3d6048b 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -45,11 +45,9 @@ nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports)
 {
 	struct nfp_flower_cmsg_mac_repr *msg;
 	struct sk_buff *skb;
-	unsigned int size;
 
-	size = sizeof(*msg) + num_ports * sizeof(msg->ports[0]);
-	skb = nfp_flower_cmsg_alloc(app, size, NFP_FLOWER_CMSG_TYPE_MAC_REPR,
-				    GFP_KERNEL);
+	skb = nfp_flower_cmsg_alloc(app, struct_size(msg, ports, num_ports),
+				    NFP_FLOWER_CMSG_TYPE_MAC_REPR, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
@@ -161,7 +159,7 @@ nfp_flower_cmsg_portmod_rx(struct nfp_app *app, struct sk_buff *skb)
 
 	rtnl_lock();
 	rcu_read_lock();
-	netdev = nfp_app_repr_get(app, be32_to_cpu(msg->portnum));
+	netdev = nfp_app_dev_get(app, be32_to_cpu(msg->portnum), NULL);
 	rcu_read_unlock();
 	if (!netdev) {
 		nfp_flower_cmsg_warn(app, "ctrl msg for unknown port 0x%08x\n",
@@ -194,7 +192,7 @@ nfp_flower_cmsg_portreify_rx(struct nfp_app *app, struct sk_buff *skb)
 	msg = nfp_flower_cmsg_get_data(skb);
 
 	rcu_read_lock();
-	exists = !!nfp_app_repr_get(app, be32_to_cpu(msg->portnum));
+	exists = !!nfp_app_dev_get(app, be32_to_cpu(msg->portnum), NULL);
 	rcu_read_unlock();
 	if (!exists) {
 		nfp_flower_cmsg_warn(app, "ctrl msg for unknown port 0x%08x\n",
@@ -203,7 +201,51 @@ nfp_flower_cmsg_portreify_rx(struct nfp_app *app, struct sk_buff *skb)
 	}
 
 	atomic_inc(&priv->reify_replies);
-	wake_up_interruptible(&priv->reify_wait_queue);
+	wake_up(&priv->reify_wait_queue);
+}
+
+static void
+nfp_flower_cmsg_merge_hint_rx(struct nfp_app *app, struct sk_buff *skb)
+{
+	unsigned int msg_len = nfp_flower_cmsg_get_data_len(skb);
+	struct nfp_flower_cmsg_merge_hint *msg;
+	struct nfp_fl_payload *sub_flows[2];
+	int err, i, flow_cnt;
+
+	msg = nfp_flower_cmsg_get_data(skb);
+	/* msg->count starts at 0 and always assumes at least 1 entry. */
+	flow_cnt = msg->count + 1;
+
+	if (msg_len < struct_size(msg, flow, flow_cnt)) {
+		nfp_flower_cmsg_warn(app, "Merge hint ctrl msg too short - %d bytes but expect %zd\n",
+				     msg_len, struct_size(msg, flow, flow_cnt));
+		return;
+	}
+
+	if (flow_cnt != 2) {
+		nfp_flower_cmsg_warn(app, "Merge hint contains %d flows - two are expected\n",
+				     flow_cnt);
+		return;
+	}
+
+	rtnl_lock();
+	for (i = 0; i < flow_cnt; i++) {
+		u32 ctx = be32_to_cpu(msg->flow[i].host_ctx);
+
+		sub_flows[i] = nfp_flower_get_fl_payload_from_ctx(app, ctx);
+		if (!sub_flows[i]) {
+			nfp_flower_cmsg_warn(app, "Invalid flow in merge hint\n");
+			goto err_rtnl_unlock;
+		}
+	}
+
+	err = nfp_flower_merge_offloaded_flows(app, sub_flows[0], sub_flows[1]);
+	/* Only warn on memory fail. Hint veto will not break functionality. */
+	if (err == -ENOMEM)
+		nfp_flower_cmsg_warn(app, "Flow merge memory fail.\n");
+
+err_rtnl_unlock:
+	rtnl_unlock();
 }
 
 static void
@@ -224,12 +266,21 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
 	case NFP_FLOWER_CMSG_TYPE_PORT_MOD:
 		nfp_flower_cmsg_portmod_rx(app, skb);
 		break;
+	case NFP_FLOWER_CMSG_TYPE_MERGE_HINT:
+		if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE) {
+			nfp_flower_cmsg_merge_hint_rx(app, skb);
+			break;
+		}
+		goto err_default;
 	case NFP_FLOWER_CMSG_TYPE_NO_NEIGH:
 		nfp_tunnel_request_route(app, skb);
 		break;
 	case NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS:
 		nfp_tunnel_keep_alive(app, skb);
 		break;
+	case NFP_FLOWER_CMSG_TYPE_QOS_STATS:
+		nfp_flower_stats_rlim_reply(app, skb);
+		break;
 	case NFP_FLOWER_CMSG_TYPE_LAG_CONFIG:
 		if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
 			skb_stored = nfp_flower_lag_unprocessed_msg(app, skb);
@@ -237,6 +288,7 @@ nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb)
 		}
 		/* fall through */
 	default:
+err_default:
 		nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n",
 				     type);
 		goto out;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 15f41cfef9f1..0f1706ae5bfc 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -8,6 +8,7 @@
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <net/geneve.h>
+#include <net/gre.h>
 #include <net/vxlan.h>
 
 #include "../nfp_app.h"
@@ -22,11 +23,12 @@
 #define NFP_FLOWER_LAYER_CT		BIT(6)
 #define NFP_FLOWER_LAYER_VXLAN		BIT(7)
 
+#define NFP_FLOWER_LAYER2_GRE		BIT(0)
 #define NFP_FLOWER_LAYER2_GENEVE	BIT(5)
 #define NFP_FLOWER_LAYER2_GENEVE_OP	BIT(6)
 
 #define NFP_FLOWER_MASK_VLAN_PRIO	GENMASK(15, 13)
-#define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
+#define NFP_FLOWER_MASK_VLAN_PRESENT	BIT(12)
 #define NFP_FLOWER_MASK_VLAN_VID	GENMASK(11, 0)
 
 #define NFP_FLOWER_MASK_MPLS_LB		GENMASK(31, 12)
@@ -37,6 +39,9 @@
 #define NFP_FL_IP_FRAG_FIRST		BIT(7)
 #define NFP_FL_IP_FRAGMENTED		BIT(6)
 
+/* GRE Tunnel flags */
+#define NFP_FL_GRE_FLAG_KEY		BIT(2)
+
 /* Compressed HW representation of TCP Flags */
 #define NFP_FL_TCP_FLAG_URG		BIT(4)
 #define NFP_FL_TCP_FLAG_PSH		BIT(3)
@@ -82,7 +87,6 @@
 #define NFP_FL_OUT_FLAGS_TYPE_IDX	GENMASK(2, 0)
 
 #define NFP_FL_PUSH_VLAN_PRIO		GENMASK(15, 13)
-#define NFP_FL_PUSH_VLAN_CFI		BIT(12)
 #define NFP_FL_PUSH_VLAN_VID		GENMASK(11, 0)
 
 #define IPV6_FLOW_LABEL_MASK		cpu_to_be32(0x000fffff)
@@ -97,6 +101,9 @@
 
 #define NFP_FLOWER_WORKQ_MAX_SKBS	30000
 
+/* Cmesg reply (empirical) timeout*/
+#define NFP_FL_REPLY_TIMEOUT		msecs_to_jiffies(40)
+
 #define nfp_flower_cmsg_warn(app, fmt, args...)                         \
 	do {                                                            \
 		if (net_ratelimit())                                    \
@@ -105,6 +112,7 @@
 
 enum nfp_flower_tun_type {
 	NFP_FL_TUNNEL_NONE =	0,
+	NFP_FL_TUNNEL_GRE =	1,
 	NFP_FL_TUNNEL_VXLAN =	2,
 	NFP_FL_TUNNEL_GENEVE =	4,
 };
@@ -201,7 +209,7 @@ struct nfp_fl_pre_tunnel {
 	__be32 extra[3];
 };
 
-struct nfp_fl_set_ipv4_udp_tun {
+struct nfp_fl_set_ipv4_tun {
 	struct nfp_fl_act_head head;
 	__be16 reserved;
 	__be64 tun_id __packed;
@@ -352,6 +360,16 @@ struct nfp_flower_ipv6 {
 	struct in6_addr ipv6_dst;
 };
 
+struct nfp_flower_tun_ipv4 {
+	__be32 src;
+	__be32 dst;
+};
+
+struct nfp_flower_tun_ip_ext {
+	u8 tos;
+	u8 ttl;
+};
+
 /* Flow Frame IPv4 UDP TUNNEL --> Tunnel details (4W/16B)
  * -----------------------------------------------------------------
  *    3                   2                   1
@@ -369,15 +387,42 @@ struct nfp_flower_ipv6 {
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  */
 struct nfp_flower_ipv4_udp_tun {
-	__be32 ip_src;
-	__be32 ip_dst;
+	struct nfp_flower_tun_ipv4 ipv4;
 	__be16 reserved1;
-	u8 tos;
-	u8 ttl;
+	struct nfp_flower_tun_ip_ext ip_ext;
 	__be32 reserved2;
 	__be32 tun_id;
 };
 
+/* Flow Frame GRE TUNNEL --> Tunnel details (6W/24B)
+ * -----------------------------------------------------------------
+ *    3                   2                   1
+ *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                         ipv4_addr_src                         |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                         ipv4_addr_dst                         |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |           tun_flags           |       tos     |       ttl     |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |            Reserved           |           Ethertype           |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                              Key                              |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                           Reserved                            |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+
+struct nfp_flower_ipv4_gre_tun {
+	struct nfp_flower_tun_ipv4 ipv4;
+	__be16 tun_flags;
+	struct nfp_flower_tun_ip_ext ip_ext;
+	__be16 reserved1;
+	__be16 ethertype;
+	__be32 tun_key;
+	__be32 reserved2;
+};
+
 struct nfp_flower_geneve_options {
 	u8 data[NFP_FL_MAX_GENEVE_OPT_KEY];
 };
@@ -400,11 +445,13 @@ struct nfp_flower_cmsg_hdr {
 /* Types defined for port related control messages  */
 enum nfp_flower_cmsg_type_port {
 	NFP_FLOWER_CMSG_TYPE_FLOW_ADD =		0,
+	NFP_FLOWER_CMSG_TYPE_FLOW_MOD =		1,
 	NFP_FLOWER_CMSG_TYPE_FLOW_DEL =		2,
 	NFP_FLOWER_CMSG_TYPE_LAG_CONFIG =	4,
 	NFP_FLOWER_CMSG_TYPE_PORT_REIFY =	6,
 	NFP_FLOWER_CMSG_TYPE_MAC_REPR =		7,
 	NFP_FLOWER_CMSG_TYPE_PORT_MOD =		8,
+	NFP_FLOWER_CMSG_TYPE_MERGE_HINT =	9,
 	NFP_FLOWER_CMSG_TYPE_NO_NEIGH =		10,
 	NFP_FLOWER_CMSG_TYPE_TUN_MAC =		11,
 	NFP_FLOWER_CMSG_TYPE_ACTIVE_TUNS =	12,
@@ -412,6 +459,9 @@ enum nfp_flower_cmsg_type_port {
 	NFP_FLOWER_CMSG_TYPE_TUN_IPS =		14,
 	NFP_FLOWER_CMSG_TYPE_FLOW_STATS =	15,
 	NFP_FLOWER_CMSG_TYPE_PORT_ECHO =	16,
+	NFP_FLOWER_CMSG_TYPE_QOS_MOD =		18,
+	NFP_FLOWER_CMSG_TYPE_QOS_DEL =		19,
+	NFP_FLOWER_CMSG_TYPE_QOS_STATS =	20,
 	NFP_FLOWER_CMSG_TYPE_MAX =		32,
 };
 
@@ -449,6 +499,16 @@ struct nfp_flower_cmsg_portreify {
 
 #define NFP_FLOWER_CMSG_PORTREIFY_INFO_EXIST	BIT(0)
 
+/* NFP_FLOWER_CMSG_TYPE_FLOW_MERGE_HINT */
+struct nfp_flower_cmsg_merge_hint {
+	u8 reserved[3];
+	u8 count;
+	struct {
+		__be32 host_ctx;
+		__be64 host_cookie;
+	} __packed flow[0];
+};
+
 enum nfp_flower_cmsg_port_type {
 	NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC =	0x0,
 	NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT =	0x1,
@@ -471,6 +531,13 @@ enum nfp_flower_cmsg_port_vnic_type {
 #define NFP_FLOWER_CMSG_PORT_PCIE_Q		GENMASK(5, 0)
 #define NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM	GENMASK(7, 0)
 
+static inline u32 nfp_flower_internal_port_get_port_id(u8 internal_port)
+{
+	return FIELD_PREP(NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM, internal_port) |
+		FIELD_PREP(NFP_FLOWER_CMSG_PORT_TYPE,
+			   NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT);
+}
+
 static inline u32 nfp_flower_cmsg_phys_port(u8 phys_port)
 {
 	return FIELD_PREP(NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM, phys_port) |
@@ -506,6 +573,8 @@ nfp_fl_netdev_is_tunnel_type(struct net_device *netdev,
 {
 	if (netif_is_vxlan(netdev))
 		return tun_type == NFP_FL_TUNNEL_VXLAN;
+	if (netif_is_gretap(netdev))
+		return tun_type == NFP_FL_TUNNEL_GRE;
 	if (netif_is_geneve(netdev))
 		return tun_type == NFP_FL_TUNNEL_GENEVE;
 
@@ -522,6 +591,8 @@ static inline bool nfp_fl_is_netdev_to_offload(struct net_device *netdev)
 		return true;
 	if (netif_is_geneve(netdev))
 		return true;
+	if (netif_is_gretap(netdev))
+		return true;
 
 	return false;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index 5db838f45694..63907aeb3884 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -156,7 +156,8 @@ nfp_fl_lag_find_group_for_master_with_lag(struct nfp_fl_lag *lag,
 
 int nfp_flower_lag_populate_pre_action(struct nfp_app *app,
 				       struct net_device *master,
-				       struct nfp_fl_pre_lag *pre_act)
+				       struct nfp_fl_pre_lag *pre_act,
+				       struct netlink_ext_ack *extack)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_lag_group *group = NULL;
@@ -167,6 +168,7 @@ int nfp_flower_lag_populate_pre_action(struct nfp_app *app,
 							  master);
 	if (!group) {
 		mutex_unlock(&priv->nfp_lag.lock);
+		NL_SET_ERR_MSG_MOD(extack, "invalid entry: group does not exist for LAG action");
 		return -ENOENT;
 	}
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 5059110a1768..eb846133943b 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -22,6 +22,9 @@
 
 #define NFP_FLOWER_ALLOWED_VER 0x0001000000010000UL
 
+#define NFP_MIN_INT_PORT_ID	1
+#define NFP_MAX_INT_PORT_ID	256
+
 static const char *nfp_flower_extra_cap(struct nfp_app *app, struct nfp_net *nn)
 {
 	return "FLOWER";
@@ -32,6 +35,178 @@ static enum devlink_eswitch_mode eswitch_mode_get(struct nfp_app *app)
 	return DEVLINK_ESWITCH_MODE_SWITCHDEV;
 }
 
+static int
+nfp_flower_lookup_internal_port_id(struct nfp_flower_priv *priv,
+				   struct net_device *netdev)
+{
+	struct net_device *entry;
+	int i, id = 0;
+
+	rcu_read_lock();
+	idr_for_each_entry(&priv->internal_ports.port_ids, entry, i)
+		if (entry == netdev) {
+			id = i;
+			break;
+		}
+	rcu_read_unlock();
+
+	return id;
+}
+
+static int
+nfp_flower_get_internal_port_id(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	int id;
+
+	id = nfp_flower_lookup_internal_port_id(priv, netdev);
+	if (id > 0)
+		return id;
+
+	idr_preload(GFP_ATOMIC);
+	spin_lock_bh(&priv->internal_ports.lock);
+	id = idr_alloc(&priv->internal_ports.port_ids, netdev,
+		       NFP_MIN_INT_PORT_ID, NFP_MAX_INT_PORT_ID, GFP_ATOMIC);
+	spin_unlock_bh(&priv->internal_ports.lock);
+	idr_preload_end();
+
+	return id;
+}
+
+u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app,
+				       struct net_device *netdev)
+{
+	int ext_port;
+
+	if (nfp_netdev_is_nfp_repr(netdev)) {
+		return nfp_repr_get_port_id(netdev);
+	} else if (nfp_flower_internal_port_can_offload(app, netdev)) {
+		ext_port = nfp_flower_get_internal_port_id(app, netdev);
+		if (ext_port < 0)
+			return 0;
+
+		return nfp_flower_internal_port_get_port_id(ext_port);
+	}
+
+	return 0;
+}
+
+static struct net_device *
+nfp_flower_get_netdev_from_internal_port_id(struct nfp_app *app, int port_id)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct net_device *netdev;
+
+	rcu_read_lock();
+	netdev = idr_find(&priv->internal_ports.port_ids, port_id);
+	rcu_read_unlock();
+
+	return netdev;
+}
+
+static void
+nfp_flower_free_internal_port_id(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	int id;
+
+	id = nfp_flower_lookup_internal_port_id(priv, netdev);
+	if (!id)
+		return;
+
+	spin_lock_bh(&priv->internal_ports.lock);
+	idr_remove(&priv->internal_ports.port_ids, id);
+	spin_unlock_bh(&priv->internal_ports.lock);
+}
+
+static int
+nfp_flower_internal_port_event_handler(struct nfp_app *app,
+				       struct net_device *netdev,
+				       unsigned long event)
+{
+	if (event == NETDEV_UNREGISTER &&
+	    nfp_flower_internal_port_can_offload(app, netdev))
+		nfp_flower_free_internal_port_id(app, netdev);
+
+	return NOTIFY_OK;
+}
+
+static void nfp_flower_internal_port_init(struct nfp_flower_priv *priv)
+{
+	spin_lock_init(&priv->internal_ports.lock);
+	idr_init(&priv->internal_ports.port_ids);
+}
+
+static void nfp_flower_internal_port_cleanup(struct nfp_flower_priv *priv)
+{
+	idr_destroy(&priv->internal_ports.port_ids);
+}
+
+static struct nfp_flower_non_repr_priv *
+nfp_flower_non_repr_priv_lookup(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_flower_non_repr_priv *entry;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(entry, &priv->non_repr_priv, list)
+		if (entry->netdev == netdev)
+			return entry;
+
+	return NULL;
+}
+
+void
+__nfp_flower_non_repr_priv_get(struct nfp_flower_non_repr_priv *non_repr_priv)
+{
+	non_repr_priv->ref_count++;
+}
+
+struct nfp_flower_non_repr_priv *
+nfp_flower_non_repr_priv_get(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_flower_non_repr_priv *entry;
+
+	entry = nfp_flower_non_repr_priv_lookup(app, netdev);
+	if (entry)
+		goto inc_ref;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return NULL;
+
+	entry->netdev = netdev;
+	list_add(&entry->list, &priv->non_repr_priv);
+
+inc_ref:
+	__nfp_flower_non_repr_priv_get(entry);
+	return entry;
+}
+
+void
+__nfp_flower_non_repr_priv_put(struct nfp_flower_non_repr_priv *non_repr_priv)
+{
+	if (--non_repr_priv->ref_count)
+		return;
+
+	list_del(&non_repr_priv->list);
+	kfree(non_repr_priv);
+}
+
+void
+nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_non_repr_priv *entry;
+
+	entry = nfp_flower_non_repr_priv_lookup(app, netdev);
+	if (!entry)
+		return;
+
+	__nfp_flower_non_repr_priv_put(entry);
+}
+
 static enum nfp_repr_type
 nfp_flower_repr_get_type_and_port(struct nfp_app *app, u32 port_id, u8 *port)
 {
@@ -54,12 +229,21 @@ nfp_flower_repr_get_type_and_port(struct nfp_app *app, u32 port_id, u8 *port)
 }
 
 static struct net_device *
-nfp_flower_repr_get(struct nfp_app *app, u32 port_id)
+nfp_flower_dev_get(struct nfp_app *app, u32 port_id, bool *redir_egress)
 {
 	enum nfp_repr_type repr_type;
 	struct nfp_reprs *reprs;
 	u8 port = 0;
 
+	/* Check if the port is internal. */
+	if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port_id) ==
+	    NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT) {
+		if (redir_egress)
+			*redir_egress = true;
+		port = FIELD_GET(NFP_FLOWER_CMSG_PORT_PHYS_PORT_NUM, port_id);
+		return nfp_flower_get_netdev_from_internal_port_id(app, port);
+	}
+
 	repr_type = nfp_flower_repr_get_type_and_port(app, port_id, &port);
 	if (repr_type > NFP_REPR_TYPE_MAX)
 		return NULL;
@@ -107,16 +291,14 @@ static int
 nfp_flower_wait_repr_reify(struct nfp_app *app, atomic_t *replies, int tot_repl)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	int err;
 
 	if (!tot_repl)
 		return 0;
 
 	lockdep_assert_held(&app->pf->lock);
-	err = wait_event_interruptible_timeout(priv->reify_wait_queue,
-					       atomic_read(replies) >= tot_repl,
-					       msecs_to_jiffies(10));
-	if (err <= 0) {
+	if (!wait_event_timeout(priv->reify_wait_queue,
+				atomic_read(replies) >= tot_repl,
+				NFP_FL_REPLY_TIMEOUT)) {
 		nfp_warn(app->cpp, "Not all reprs responded to reify\n");
 		return -EIO;
 	}
@@ -223,6 +405,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 
 		nfp_repr = netdev_priv(repr);
 		nfp_repr->app_priv = repr_priv;
+		repr_priv->nfp_repr = nfp_repr;
 
 		/* For now we only support 1 PF */
 		WARN_ON(repr_type == NFP_REPR_TYPE_PF && i);
@@ -337,6 +520,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 
 		nfp_repr = netdev_priv(repr);
 		nfp_repr->app_priv = repr_priv;
+		repr_priv->nfp_repr = nfp_repr;
 
 		port = nfp_port_alloc(app, NFP_PORT_PHYS_PORT, repr);
 		if (IS_ERR(port)) {
@@ -476,8 +660,8 @@ err_clear_nn:
 
 static int nfp_flower_init(struct nfp_app *app)
 {
+	u64 version, features, ctx_count, num_mems;
 	const struct nfp_pf *pf = app->pf;
-	u64 version, features, ctx_count;
 	struct nfp_flower_priv *app_priv;
 	int err;
 
@@ -502,6 +686,23 @@ static int nfp_flower_init(struct nfp_app *app)
 		return err;
 	}
 
+	num_mems = nfp_rtsym_read_le(app->pf->rtbl, "CONFIG_FC_HOST_CTX_SPLIT",
+				     &err);
+	if (err) {
+		nfp_warn(app->cpp,
+			 "FlowerNIC: unsupported host context memory: %d\n",
+			 err);
+		err = 0;
+		num_mems = 1;
+	}
+
+	if (!FIELD_FIT(NFP_FL_STAT_ID_MU_NUM, num_mems) || !num_mems) {
+		nfp_warn(app->cpp,
+			 "FlowerNIC: invalid host context memory: %llu\n",
+			 num_mems);
+		return -EINVAL;
+	}
+
 	ctx_count = nfp_rtsym_read_le(app->pf->rtbl, "CONFIG_FC_HOST_CTX_COUNT",
 				      &err);
 	if (err) {
@@ -522,6 +723,8 @@ static int nfp_flower_init(struct nfp_app *app)
 	if (!app_priv)
 		return -ENOMEM;
 
+	app_priv->total_mem_units = num_mems;
+	app_priv->active_mem_unit = 0;
 	app_priv->stats_ring_size = roundup_pow_of_two(ctx_count);
 	app->priv = app_priv;
 	app_priv->app = app;
@@ -533,7 +736,7 @@ static int nfp_flower_init(struct nfp_app *app)
 	init_waitqueue_head(&app_priv->mtu_conf.wait_q);
 	spin_lock_init(&app_priv->mtu_conf.lock);
 
-	err = nfp_flower_metadata_init(app, ctx_count);
+	err = nfp_flower_metadata_init(app, ctx_count, num_mems);
 	if (err)
 		goto err_free_app_priv;
 
@@ -557,10 +760,33 @@ static int nfp_flower_init(struct nfp_app *app)
 		goto err_cleanup_metadata;
 	}
 
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MOD) {
+		/* Tell the firmware that the driver supports flow merging. */
+		err = nfp_rtsym_write_le(app->pf->rtbl,
+					 "_abi_flower_merge_hint_enable", 1);
+		if (!err) {
+			app_priv->flower_ext_feats |= NFP_FL_FEATS_FLOW_MERGE;
+			nfp_flower_internal_port_init(app_priv);
+		} else if (err == -ENOENT) {
+			nfp_warn(app->cpp, "Flow merge not supported by FW.\n");
+		} else {
+			goto err_lag_clean;
+		}
+	} else {
+		nfp_warn(app->cpp, "Flow mod/merge not supported by FW.\n");
+	}
+
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)
+		nfp_flower_qos_init(app);
+
 	INIT_LIST_HEAD(&app_priv->indr_block_cb_priv);
+	INIT_LIST_HEAD(&app_priv->non_repr_priv);
 
 	return 0;
 
+err_lag_clean:
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
+		nfp_flower_lag_cleanup(&app_priv->nfp_lag);
 err_cleanup_metadata:
 	nfp_flower_metadata_cleanup(app);
 err_free_app_priv:
@@ -576,9 +802,15 @@ static void nfp_flower_clean(struct nfp_app *app)
 	skb_queue_purge(&app_priv->cmsg_skbs_low);
 	flush_work(&app_priv->cmsg_work);
 
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)
+		nfp_flower_qos_cleanup(app);
+
 	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
 		nfp_flower_lag_cleanup(&app_priv->nfp_lag);
 
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE)
+		nfp_flower_internal_port_cleanup(app_priv);
+
 	nfp_flower_metadata_cleanup(app);
 	vfree(app->priv);
 	app->priv = NULL;
@@ -601,7 +833,7 @@ nfp_flower_repr_change_mtu(struct nfp_app *app, struct net_device *netdev,
 {
 	struct nfp_flower_priv *app_priv = app->priv;
 	struct nfp_repr *repr = netdev_priv(netdev);
-	int err, ack;
+	int err;
 
 	/* Only need to config FW for physical port MTU change. */
 	if (repr->port->type != NFP_PORT_PHYS_PORT)
@@ -628,11 +860,9 @@ nfp_flower_repr_change_mtu(struct nfp_app *app, struct net_device *netdev,
 	}
 
 	/* Wait for fw to ack the change. */
-	ack = wait_event_timeout(app_priv->mtu_conf.wait_q,
-				 nfp_flower_check_ack(app_priv),
-				 msecs_to_jiffies(10));
-
-	if (!ack) {
+	if (!wait_event_timeout(app_priv->mtu_conf.wait_q,
+				nfp_flower_check_ack(app_priv),
+				NFP_FL_REPLY_TIMEOUT)) {
 		spin_lock_bh(&app_priv->mtu_conf.lock);
 		app_priv->mtu_conf.requested_val = 0;
 		spin_unlock_bh(&app_priv->mtu_conf.lock);
@@ -679,6 +909,10 @@ nfp_flower_netdev_event(struct nfp_app *app, struct net_device *netdev,
 	if (ret & NOTIFY_STOP_MASK)
 		return ret;
 
+	ret = nfp_flower_internal_port_event_handler(app, netdev, event);
+	if (ret & NOTIFY_STOP_MASK)
+		return ret;
+
 	return nfp_tunnel_mac_event_handler(app, netdev, event, ptr);
 }
 
@@ -717,7 +951,7 @@ const struct nfp_app_type app_flower = {
 	.sriov_disable	= nfp_flower_sriov_disable,
 
 	.eswitch_mode_get  = eswitch_mode_get,
-	.repr_get	= nfp_flower_repr_get,
+	.dev_get	= nfp_flower_dev_get,
 
 	.setup_tc	= nfp_flower_setup_tc,
 };
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index b858bac47621..af9441d5787f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -5,6 +5,7 @@
 #define __NFP_FLOWER_H__ 1
 
 #include "cmsg.h"
+#include "../nfp_net.h"
 
 #include <linux/circ_buf.h>
 #include <linux/hashtable.h>
@@ -20,6 +21,9 @@ struct nfp_fl_pre_lag;
 struct net_device;
 struct nfp_app;
 
+#define NFP_FL_STAT_ID_MU_NUM		GENMASK(31, 22)
+#define NFP_FL_STAT_ID_STAT		GENMASK(21, 0)
+
 #define NFP_FL_STATS_ELEM_RS		FIELD_SIZEOF(struct nfp_fl_stats_id, \
 						     init_unalloc)
 #define NFP_FLOWER_MASK_ENTRY_RS	256
@@ -31,14 +35,14 @@ struct nfp_app;
 #define NFP_FL_MASK_REUSE_TIME_NS	40000
 #define NFP_FL_MASK_ID_LOCATION		1
 
-#define NFP_FL_VXLAN_PORT		4789
-#define NFP_FL_GENEVE_PORT		6081
-
 /* Extra features bitmap. */
 #define NFP_FL_FEATS_GENEVE		BIT(0)
 #define NFP_FL_NBI_MTU_SETTING		BIT(1)
 #define NFP_FL_FEATS_GENEVE_OPT		BIT(2)
 #define NFP_FL_FEATS_VLAN_PCP		BIT(3)
+#define NFP_FL_FEATS_VF_RLIM		BIT(4)
+#define NFP_FL_FEATS_FLOW_MOD		BIT(5)
+#define NFP_FL_FEATS_FLOW_MERGE		BIT(30)
 #define NFP_FL_FEATS_LAG		BIT(31)
 
 struct nfp_fl_mask_id {
@@ -54,6 +58,26 @@ struct nfp_fl_stats_id {
 };
 
 /**
+ * struct nfp_fl_tunnel_offloads - priv data for tunnel offloads
+ * @offloaded_macs:	Hashtable of the offloaded MAC addresses
+ * @ipv4_off_list:	List of IPv4 addresses to offload
+ * @neigh_off_list:	List of neighbour offloads
+ * @ipv4_off_lock:	Lock for the IPv4 address list
+ * @neigh_off_lock:	Lock for the neighbour address list
+ * @mac_off_ids:	IDA to manage id assignment for offloaded MACs
+ * @neigh_nb:		Notifier to monitor neighbour state
+ */
+struct nfp_fl_tunnel_offloads {
+	struct rhashtable offloaded_macs;
+	struct list_head ipv4_off_list;
+	struct list_head neigh_off_list;
+	struct mutex ipv4_off_lock;
+	spinlock_t neigh_off_lock;
+	struct ida mac_off_ids;
+	struct notifier_block neigh_nb;
+};
+
+/**
  * struct nfp_mtu_conf - manage MTU setting
  * @portnum:		NFP port number of repr with requested MTU change
  * @requested_val:	MTU value requested for repr
@@ -95,6 +119,16 @@ struct nfp_fl_lag {
 };
 
 /**
+ * struct nfp_fl_internal_ports - Flower APP priv data for additional ports
+ * @port_ids:	Assignment of ids to any additional ports
+ * @lock:	Lock for extra ports list
+ */
+struct nfp_fl_internal_ports {
+	struct idr port_ids;
+	spinlock_t lock;
+};
+
+/**
  * struct nfp_flower_priv - Flower APP per-vNIC priv data
  * @app:		Back pointer to app
  * @nn:			Pointer to vNIC
@@ -108,28 +142,26 @@ struct nfp_fl_lag {
  * @flow_table:		Hash table used to store flower rules
  * @stats:		Stored stats updates for flower rules
  * @stats_lock:		Lock for flower rule stats updates
+ * @stats_ctx_table:	Hash table to map stats contexts to its flow rule
  * @cmsg_work:		Workqueue for control messages processing
  * @cmsg_skbs_high:	List of higher priority skbs for control message
  *			processing
  * @cmsg_skbs_low:	List of lower priority skbs for control message
  *			processing
- * @nfp_mac_off_list:	List of MAC addresses to offload
- * @nfp_mac_index_list:	List of unique 8-bit indexes for non NFP netdevs
- * @nfp_ipv4_off_list:	List of IPv4 addresses to offload
- * @nfp_neigh_off_list:	List of neighbour offloads
- * @nfp_mac_off_lock:	Lock for the MAC address list
- * @nfp_mac_index_lock:	Lock for the MAC index list
- * @nfp_ipv4_off_lock:	Lock for the IPv4 address list
- * @nfp_neigh_off_lock:	Lock for the neighbour address list
- * @nfp_mac_off_ids:	IDA to manage id assignment for offloaded macs
- * @nfp_mac_off_count:	Number of MACs in address list
- * @nfp_tun_neigh_nb:	Notifier to monitor neighbour state
+ * @tun:		Tunnel offload data
  * @reify_replies:	atomically stores the number of replies received
  *			from firmware for repr reify
  * @reify_wait_queue:	wait queue for repr reify response counting
  * @mtu_conf:		Configuration of repr MTU value
  * @nfp_lag:		Link aggregation data block
  * @indr_block_cb_priv:	List of priv data passed to indirect block cbs
+ * @non_repr_priv:	List of offloaded non-repr ports and their priv data
+ * @active_mem_unit:	Current active memory unit for flower rules
+ * @total_mem_units:	Total number of available memory units for flower rules
+ * @internal_ports:	Internal port ids used in offloaded rules
+ * @qos_stats_work:	Workqueue for qos stats processing
+ * @qos_rate_limiters:	Current active qos rate limiters
+ * @qos_stats_lock:	Lock on qos stats updates
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -144,33 +176,73 @@ struct nfp_flower_priv {
 	struct rhashtable flow_table;
 	struct nfp_fl_stats *stats;
 	spinlock_t stats_lock; /* lock stats */
+	struct rhashtable stats_ctx_table;
 	struct work_struct cmsg_work;
 	struct sk_buff_head cmsg_skbs_high;
 	struct sk_buff_head cmsg_skbs_low;
-	struct list_head nfp_mac_off_list;
-	struct list_head nfp_mac_index_list;
-	struct list_head nfp_ipv4_off_list;
-	struct list_head nfp_neigh_off_list;
-	struct mutex nfp_mac_off_lock;
-	struct mutex nfp_mac_index_lock;
-	struct mutex nfp_ipv4_off_lock;
-	spinlock_t nfp_neigh_off_lock;
-	struct ida nfp_mac_off_ids;
-	int nfp_mac_off_count;
-	struct notifier_block nfp_tun_neigh_nb;
+	struct nfp_fl_tunnel_offloads tun;
 	atomic_t reify_replies;
 	wait_queue_head_t reify_wait_queue;
 	struct nfp_mtu_conf mtu_conf;
 	struct nfp_fl_lag nfp_lag;
 	struct list_head indr_block_cb_priv;
+	struct list_head non_repr_priv;
+	unsigned int active_mem_unit;
+	unsigned int total_mem_units;
+	struct nfp_fl_internal_ports internal_ports;
+	struct delayed_work qos_stats_work;
+	unsigned int qos_rate_limiters;
+	spinlock_t qos_stats_lock; /* Protect the qos stats */
+};
+
+/**
+ * struct nfp_fl_qos - Flower APP priv data for quality of service
+ * @netdev_port_id:	NFP port number of repr with qos info
+ * @curr_stats:		Currently stored stats updates for qos info
+ * @prev_stats:		Previously stored updates for qos info
+ * @last_update:	Stored time when last stats were updated
+ */
+struct nfp_fl_qos {
+	u32 netdev_port_id;
+	struct nfp_stat_pair curr_stats;
+	struct nfp_stat_pair prev_stats;
+	u64 last_update;
 };
 
 /**
  * struct nfp_flower_repr_priv - Flower APP per-repr priv data
+ * @nfp_repr:		Back pointer to nfp_repr
  * @lag_port_flags:	Extended port flags to record lag state of repr
+ * @mac_offloaded:	Flag indicating a MAC address is offloaded for repr
+ * @offloaded_mac_addr:	MAC address that has been offloaded for repr
+ * @block_shared:	Flag indicating if offload applies to shared blocks
+ * @mac_list:		List entry of reprs that share the same offloaded MAC
+ * @qos_table:		Stored info on filters implementing qos
  */
 struct nfp_flower_repr_priv {
+	struct nfp_repr *nfp_repr;
 	unsigned long lag_port_flags;
+	bool mac_offloaded;
+	u8 offloaded_mac_addr[ETH_ALEN];
+	bool block_shared;
+	struct list_head mac_list;
+	struct nfp_fl_qos qos_table;
+};
+
+/**
+ * struct nfp_flower_non_repr_priv - Priv data for non-repr offloaded ports
+ * @list:		List entry of offloaded reprs
+ * @netdev:		Pointer to non-repr net_device
+ * @ref_count:		Number of references held for this priv data
+ * @mac_offloaded:	Flag indicating a MAC address is offloaded for device
+ * @offloaded_mac_addr:	MAC address that has been offloaded for dev
+ */
+struct nfp_flower_non_repr_priv {
+	struct list_head list;
+	struct net_device *netdev;
+	int ref_count;
+	bool mac_offloaded;
+	u8 offloaded_mac_addr[ETH_ALEN];
 };
 
 struct nfp_fl_key_ls {
@@ -206,6 +278,25 @@ struct nfp_fl_payload {
 	char *unmasked_data;
 	char *mask_data;
 	char *action_data;
+	struct list_head linked_flows;
+	bool in_hw;
+};
+
+struct nfp_fl_payload_link {
+	/* A link contains a pointer to a merge flow and an associated sub_flow.
+	 * Each merge flow will feature in 2 links to its underlying sub_flows.
+	 * A sub_flow will have at least 1 link to a merge flow or more if it
+	 * has been used to create multiple merge flows.
+	 *
+	 * For a merge flow, 'linked_flows' in its nfp_fl_payload struct lists
+	 * all links to sub_flows (sub_flow.flow) via merge.list.
+	 * For a sub_flow, 'linked_flows' gives all links to merge flows it has
+	 * formed (merge_flow.flow) via sub_flow.list.
+	 */
+	struct {
+		struct list_head list;
+		struct nfp_fl_payload *flow;
+	} merge_flow, sub_flow;
 };
 
 extern const struct rhashtable_params nfp_flower_table_params;
@@ -217,25 +308,59 @@ struct nfp_fl_stats_frame {
 	__be64 stats_cookie;
 };
 
-int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count);
+static inline bool
+nfp_flower_internal_port_can_offload(struct nfp_app *app,
+				     struct net_device *netdev)
+{
+	struct nfp_flower_priv *app_priv = app->priv;
+
+	if (!(app_priv->flower_ext_feats & NFP_FL_FEATS_FLOW_MERGE))
+		return false;
+	if (!netdev->rtnl_link_ops)
+		return false;
+	if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
+		return true;
+
+	return false;
+}
+
+/* The address of the merged flow acts as its cookie.
+ * Cookies supplied to us by TC flower are also addresses to allocated
+ * memory and thus this scheme should not generate any collisions.
+ */
+static inline bool nfp_flower_is_merge_flow(struct nfp_fl_payload *flow_pay)
+{
+	return flow_pay->tc_flower_cookie == (unsigned long)flow_pay;
+}
+
+int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
+			     unsigned int host_ctx_split);
 void nfp_flower_metadata_cleanup(struct nfp_app *app);
 
 int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
 			enum tc_setup_type type, void *type_data);
+int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
+				     struct nfp_fl_payload *sub_flow1,
+				     struct nfp_fl_payload *sub_flow2);
 int nfp_flower_compile_flow_match(struct nfp_app *app,
-				  struct tc_cls_flower_offload *flow,
+				  struct flow_cls_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
-				  enum nfp_flower_tun_type tun_type);
+				  enum nfp_flower_tun_type tun_type,
+				  struct netlink_ext_ack *extack);
 int nfp_flower_compile_action(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct net_device *netdev,
-			      struct nfp_fl_payload *nfp_flow);
+			      struct nfp_fl_payload *nfp_flow,
+			      struct netlink_ext_ack *extack);
 int nfp_compile_flow_metadata(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct nfp_fl_payload *nfp_flow,
-			      struct net_device *netdev);
+			      struct net_device *netdev,
+			      struct netlink_ext_ack *extack);
+void __nfp_modify_flow_metadata(struct nfp_flower_priv *priv,
+				struct nfp_fl_payload *nfp_flow);
 int nfp_modify_flow_metadata(struct nfp_app *app,
 			     struct nfp_fl_payload *nfp_flow);
 
@@ -243,6 +368,8 @@ struct nfp_fl_payload *
 nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
 			   struct net_device *netdev);
 struct nfp_fl_payload *
+nfp_flower_get_fl_payload_from_ctx(struct nfp_app *app, u32 ctx_id);
+struct nfp_fl_payload *
 nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
 
 void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb);
@@ -252,7 +379,6 @@ void nfp_tunnel_config_stop(struct nfp_app *app);
 int nfp_tunnel_mac_event_handler(struct nfp_app *app,
 				 struct net_device *netdev,
 				 unsigned long event, void *ptr);
-void nfp_tunnel_write_macs(struct nfp_app *app);
 void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4);
 void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4);
 void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb);
@@ -266,11 +392,27 @@ int nfp_flower_lag_netdev_event(struct nfp_flower_priv *priv,
 bool nfp_flower_lag_unprocessed_msg(struct nfp_app *app, struct sk_buff *skb);
 int nfp_flower_lag_populate_pre_action(struct nfp_app *app,
 				       struct net_device *master,
-				       struct nfp_fl_pre_lag *pre_act);
+				       struct nfp_fl_pre_lag *pre_act,
+				       struct netlink_ext_ack *extack);
 int nfp_flower_lag_get_output_id(struct nfp_app *app,
 				 struct net_device *master);
+void nfp_flower_qos_init(struct nfp_app *app);
+void nfp_flower_qos_cleanup(struct nfp_app *app);
+int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev,
+				 struct tc_cls_matchall_offload *flow);
+void nfp_flower_stats_rlim_reply(struct nfp_app *app, struct sk_buff *skb);
 int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
 				       struct net_device *netdev,
 				       unsigned long event);
 
+void
+__nfp_flower_non_repr_priv_get(struct nfp_flower_non_repr_priv *non_repr_priv);
+struct nfp_flower_non_repr_priv *
+nfp_flower_non_repr_priv_get(struct nfp_app *app, struct net_device *netdev);
+void
+__nfp_flower_non_repr_priv_put(struct nfp_flower_non_repr_priv *non_repr_priv);
+void
+nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev);
+u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app,
+				       struct net_device *netdev);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index cdf75595f627..9cc3ba17ff69 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -8,32 +8,41 @@
 #include "main.h"
 
 static void
-nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame,
-			    struct tc_cls_flower_offload *flow, u8 key_type,
-			    bool mask_version)
+nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext,
+			    struct nfp_flower_meta_tci *msk,
+			    struct flow_cls_offload *flow, u8 key_type)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_vlan *flow_vlan;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	u16 tmp_tci;
 
-	memset(frame, 0, sizeof(struct nfp_flower_meta_tci));
+	memset(ext, 0, sizeof(struct nfp_flower_meta_tci));
+	memset(msk, 0, sizeof(struct nfp_flower_meta_tci));
+
 	/* Populate the metadata frame. */
-	frame->nfp_flow_key_layer = key_type;
-	frame->mask_id = ~0;
+	ext->nfp_flow_key_layer = key_type;
+	ext->mask_id = ~0;
+
+	msk->nfp_flow_key_layer = key_type;
+	msk->mask_id = ~0;
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		flow_vlan = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_VLAN,
-						      target);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(rule, &match);
 		/* Populate the tci field. */
-		if (flow_vlan->vlan_id || flow_vlan->vlan_priority) {
-			tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
-					     flow_vlan->vlan_priority) |
-				  FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
-					     flow_vlan->vlan_id) |
-				  NFP_FLOWER_MASK_VLAN_CFI;
-			frame->tci = cpu_to_be16(tmp_tci);
-		}
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      match.key->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      match.key->vlan_id);
+		ext->tci = cpu_to_be16(tmp_tci);
+
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      match.mask->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      match.mask->vlan_id);
+		msk->tci = cpu_to_be16(tmp_tci);
 	}
 }
 
@@ -45,7 +54,8 @@ nfp_flower_compile_ext_meta(struct nfp_flower_ext_meta *frame, u32 key_ext)
 
 static int
 nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
-			bool mask_version, enum nfp_flower_tun_type tun_type)
+			bool mask_version, enum nfp_flower_tun_type tun_type,
+			struct netlink_ext_ack *extack)
 {
 	if (mask_version) {
 		frame->in_port = cpu_to_be32(~0);
@@ -55,8 +65,10 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 	if (tun_type) {
 		frame->in_port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
 	} else {
-		if (!cmsg_port)
+		if (!cmsg_port) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid ingress interface for match offload");
 			return -EOPNOTSUPP;
+		}
 		frame->in_port = cpu_to_be32(cmsg_port);
 	}
 
@@ -64,248 +76,314 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 }
 
 static void
-nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame,
-		       struct tc_cls_flower_offload *flow,
-		       bool mask_version)
+nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
+		       struct nfp_flower_mac_mpls *msk,
+		       struct flow_cls_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_eth_addrs *addr;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_mac_mpls));
+	memset(msk, 0, sizeof(struct nfp_flower_mac_mpls));
 
-	memset(frame, 0, sizeof(struct nfp_flower_mac_mpls));
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		addr = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						 target);
+		flow_rule_match_eth_addrs(rule, &match);
 		/* Populate mac frame. */
-		ether_addr_copy(frame->mac_dst, &addr->dst[0]);
-		ether_addr_copy(frame->mac_src, &addr->src[0]);
+		ether_addr_copy(ext->mac_dst, &match.key->dst[0]);
+		ether_addr_copy(ext->mac_src, &match.key->src[0]);
+		ether_addr_copy(msk->mac_dst, &match.mask->dst[0]);
+		ether_addr_copy(msk->mac_src, &match.mask->src[0]);
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) {
-		struct flow_dissector_key_mpls *mpls;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) {
+		struct flow_match_mpls match;
 		u32 t_mpls;
 
-		mpls = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_MPLS,
-						 target);
-
-		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, mpls->mpls_label) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, mpls->mpls_tc) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, mpls->mpls_bos) |
+		flow_rule_match_mpls(rule, &match);
+		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.key->mpls_label) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.key->mpls_tc) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.key->mpls_bos) |
 			 NFP_FLOWER_MASK_MPLS_Q;
-
-		frame->mpls_lse = cpu_to_be32(t_mpls);
-	} else if (dissector_uses_key(flow->dissector,
-				      FLOW_DISSECTOR_KEY_BASIC)) {
+		ext->mpls_lse = cpu_to_be32(t_mpls);
+		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.mask->mpls_label) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.mask->mpls_tc) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.mask->mpls_bos) |
+			 NFP_FLOWER_MASK_MPLS_Q;
+		msk->mpls_lse = cpu_to_be32(t_mpls);
+	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		/* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
 		 * bit, which indicates an mpls ether type but without any
 		 * mpls fields.
 		 */
-		struct flow_dissector_key_basic *key_basic;
-
-		key_basic = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_BASIC,
-						      flow->key);
-		if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
-		    key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
-			frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		if (match.key->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+		    match.key->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) {
+			ext->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+			msk->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+		}
 	}
 }
 
 static void
-nfp_flower_compile_tport(struct nfp_flower_tp_ports *frame,
-			 struct tc_cls_flower_offload *flow,
-			 bool mask_version)
+nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext,
+			 struct nfp_flower_tp_ports *msk,
+			 struct flow_cls_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ports *tp;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_tp_ports));
+	memset(msk, 0, sizeof(struct nfp_flower_tp_ports));
 
-	memset(frame, 0, sizeof(struct nfp_flower_tp_ports));
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		tp = skb_flow_dissector_target(flow->dissector,
-					       FLOW_DISSECTOR_KEY_PORTS,
-					       target);
-		frame->port_src = tp->src;
-		frame->port_dst = tp->dst;
+		flow_rule_match_ports(rule, &match);
+		ext->port_src = match.key->src;
+		ext->port_dst = match.key->dst;
+		msk->port_src = match.mask->src;
+		msk->port_dst = match.mask->dst;
 	}
 }
 
 static void
-nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *frame,
-			  struct tc_cls_flower_offload *flow,
-			  bool mask_version)
+nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext,
+			  struct nfp_flower_ip_ext *msk,
+			  struct flow_cls_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *basic;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		basic = skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  target);
-		frame->proto = basic->ip_proto;
+		flow_rule_match_basic(rule, &match);
+		ext->proto = match.key->ip_proto;
+		msk->proto = match.mask->ip_proto;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) {
-		struct flow_dissector_key_ip *flow_ip;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_match_ip match;
 
-		flow_ip = skb_flow_dissector_target(flow->dissector,
-						    FLOW_DISSECTOR_KEY_IP,
-						    target);
-		frame->tos = flow_ip->tos;
-		frame->ttl = flow_ip->ttl;
+		flow_rule_match_ip(rule, &match);
+		ext->tos = match.key->tos;
+		ext->ttl = match.key->ttl;
+		msk->tos = match.mask->tos;
+		msk->ttl = match.mask->ttl;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) {
-		struct flow_dissector_key_tcp *tcp;
-		u32 tcp_flags;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
+		u16 tcp_flags, tcp_flags_mask;
+		struct flow_match_tcp match;
 
-		tcp = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_TCP, target);
-		tcp_flags = be16_to_cpu(tcp->flags);
+		flow_rule_match_tcp(rule, &match);
+		tcp_flags = be16_to_cpu(match.key->flags);
+		tcp_flags_mask = be16_to_cpu(match.mask->flags);
 
 		if (tcp_flags & TCPHDR_FIN)
-			frame->flags |= NFP_FL_TCP_FLAG_FIN;
+			ext->flags |= NFP_FL_TCP_FLAG_FIN;
+		if (tcp_flags_mask & TCPHDR_FIN)
+			msk->flags |= NFP_FL_TCP_FLAG_FIN;
+
 		if (tcp_flags & TCPHDR_SYN)
-			frame->flags |= NFP_FL_TCP_FLAG_SYN;
+			ext->flags |= NFP_FL_TCP_FLAG_SYN;
+		if (tcp_flags_mask & TCPHDR_SYN)
+			msk->flags |= NFP_FL_TCP_FLAG_SYN;
+
 		if (tcp_flags & TCPHDR_RST)
-			frame->flags |= NFP_FL_TCP_FLAG_RST;
+			ext->flags |= NFP_FL_TCP_FLAG_RST;
+		if (tcp_flags_mask & TCPHDR_RST)
+			msk->flags |= NFP_FL_TCP_FLAG_RST;
+
 		if (tcp_flags & TCPHDR_PSH)
-			frame->flags |= NFP_FL_TCP_FLAG_PSH;
+			ext->flags |= NFP_FL_TCP_FLAG_PSH;
+		if (tcp_flags_mask & TCPHDR_PSH)
+			msk->flags |= NFP_FL_TCP_FLAG_PSH;
+
 		if (tcp_flags & TCPHDR_URG)
-			frame->flags |= NFP_FL_TCP_FLAG_URG;
+			ext->flags |= NFP_FL_TCP_FLAG_URG;
+		if (tcp_flags_mask & TCPHDR_URG)
+			msk->flags |= NFP_FL_TCP_FLAG_URG;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key;
-
-		key = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_CONTROL,
-						target);
-		if (key->flags & FLOW_DIS_IS_FRAGMENT)
-			frame->flags |= NFP_FL_IP_FRAGMENTED;
-		if (key->flags & FLOW_DIS_FIRST_FRAG)
-			frame->flags |= NFP_FL_IP_FRAG_FIRST;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		if (match.key->flags & FLOW_DIS_IS_FRAGMENT)
+			ext->flags |= NFP_FL_IP_FRAGMENTED;
+		if (match.mask->flags & FLOW_DIS_IS_FRAGMENT)
+			msk->flags |= NFP_FL_IP_FRAGMENTED;
+		if (match.key->flags & FLOW_DIS_FIRST_FRAG)
+			ext->flags |= NFP_FL_IP_FRAG_FIRST;
+		if (match.mask->flags & FLOW_DIS_FIRST_FRAG)
+			msk->flags |= NFP_FL_IP_FRAG_FIRST;
 	}
 }
 
 static void
-nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame,
-			struct tc_cls_flower_offload *flow,
-			bool mask_version)
+nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext,
+			struct nfp_flower_ipv4 *msk,
+			struct flow_cls_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ipv4_addrs *addr;
-
-	memset(frame, 0, sizeof(struct nfp_flower_ipv4));
-
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-		addr = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						 target);
-		frame->ipv4_src = addr->src;
-		frame->ipv4_dst = addr->dst;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct flow_match_ipv4_addrs match;
+
+	memset(ext, 0, sizeof(struct nfp_flower_ipv4));
+	memset(msk, 0, sizeof(struct nfp_flower_ipv4));
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		flow_rule_match_ipv4_addrs(rule, &match);
+		ext->ipv4_src = match.key->src;
+		ext->ipv4_dst = match.key->dst;
+		msk->ipv4_src = match.mask->src;
+		msk->ipv4_dst = match.mask->dst;
 	}
 
-	nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version);
+	nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow);
 }
 
 static void
-nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame,
-			struct tc_cls_flower_offload *flow,
-			bool mask_version)
+nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext,
+			struct nfp_flower_ipv6 *msk,
+			struct flow_cls_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ipv6_addrs *addr;
-
-	memset(frame, 0, sizeof(struct nfp_flower_ipv6));
-
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
-		addr = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						 target);
-		frame->ipv6_src = addr->src;
-		frame->ipv6_dst = addr->dst;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_ipv6));
+	memset(msk, 0, sizeof(struct nfp_flower_ipv6));
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
+		ext->ipv6_src = match.key->src;
+		ext->ipv6_dst = match.key->dst;
+		msk->ipv6_src = match.mask->src;
+		msk->ipv6_dst = match.mask->dst;
 	}
 
-	nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version);
+	nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow);
 }
 
 static int
-nfp_flower_compile_geneve_opt(void *key_buf, struct tc_cls_flower_offload *flow,
-			      bool mask_version)
+nfp_flower_compile_geneve_opt(void *ext, void *msk,
+			      struct flow_cls_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_enc_opts *opts;
+	struct flow_match_enc_opts match;
 
-	opts = skb_flow_dissector_target(flow->dissector,
-					 FLOW_DISSECTOR_KEY_ENC_OPTS,
-					 target);
-	memcpy(key_buf, opts->data, opts->len);
+	flow_rule_match_enc_opts(flow->rule, &match);
+	memcpy(ext, match.key->data, match.key->len);
+	memcpy(msk, match.mask->data, match.mask->len);
 
 	return 0;
 }
 
 static void
-nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
-				struct tc_cls_flower_offload *flow,
-				bool mask_version)
+nfp_flower_compile_tun_ipv4_addrs(struct nfp_flower_tun_ipv4 *ext,
+				  struct nfp_flower_tun_ipv4 *msk,
+				  struct flow_cls_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ipv4_addrs *tun_ips;
-	struct flow_dissector_key_keyid *vni;
-	struct flow_dissector_key_ip *ip;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
-	memset(frame, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
 
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		u32 temp_vni;
+		flow_rule_match_enc_ipv4_addrs(rule, &match);
+		ext->src = match.key->src;
+		ext->dst = match.key->dst;
+		msk->src = match.mask->src;
+		msk->dst = match.mask->dst;
+	}
+}
+
+static void
+nfp_flower_compile_tun_ip_ext(struct nfp_flower_tun_ip_ext *ext,
+			      struct nfp_flower_tun_ip_ext *msk,
+			      struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
-		vni = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_ENC_KEYID,
-						target);
-		temp_vni = be32_to_cpu(vni->keyid) << NFP_FL_TUN_VNI_OFFSET;
-		frame->tun_id = cpu_to_be32(temp_vni);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_match_ip match;
+
+		flow_rule_match_enc_ip(rule, &match);
+		ext->tos = match.key->tos;
+		ext->ttl = match.key->ttl;
+		msk->tos = match.mask->tos;
+		msk->ttl = match.mask->ttl;
 	}
+}
+
+static void
+nfp_flower_compile_ipv4_gre_tun(struct nfp_flower_ipv4_gre_tun *ext,
+				struct nfp_flower_ipv4_gre_tun *msk,
+				struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_ipv4_gre_tun));
+	memset(msk, 0, sizeof(struct nfp_flower_ipv4_gre_tun));
+
+	/* NVGRE is the only supported GRE tunnel type */
+	ext->ethertype = cpu_to_be16(ETH_P_TEB);
+	msk->ethertype = cpu_to_be16(~0);
 
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
-		tun_ips =
-		   skb_flow_dissector_target(flow->dissector,
-					     FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-					     target);
-		frame->ip_src = tun_ips->src;
-		frame->ip_dst = tun_ips->dst;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
+
+		flow_rule_match_enc_keyid(rule, &match);
+		ext->tun_key = match.key->keyid;
+		msk->tun_key = match.mask->keyid;
+
+		ext->tun_flags = cpu_to_be16(NFP_FL_GRE_FLAG_KEY);
+		msk->tun_flags = cpu_to_be16(NFP_FL_GRE_FLAG_KEY);
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
-		ip = skb_flow_dissector_target(flow->dissector,
-					       FLOW_DISSECTOR_KEY_ENC_IP,
-					       target);
-		frame->tos = ip->tos;
-		frame->ttl = ip->ttl;
+	nfp_flower_compile_tun_ipv4_addrs(&ext->ipv4, &msk->ipv4, flow);
+	nfp_flower_compile_tun_ip_ext(&ext->ip_ext, &msk->ip_ext, flow);
+}
+
+static void
+nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext,
+				struct nfp_flower_ipv4_udp_tun *msk,
+				struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
+	memset(msk, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
+		u32 temp_vni;
+
+		flow_rule_match_enc_keyid(rule, &match);
+		temp_vni = be32_to_cpu(match.key->keyid) << NFP_FL_TUN_VNI_OFFSET;
+		ext->tun_id = cpu_to_be32(temp_vni);
+		temp_vni = be32_to_cpu(match.mask->keyid) << NFP_FL_TUN_VNI_OFFSET;
+		msk->tun_id = cpu_to_be32(temp_vni);
 	}
+
+	nfp_flower_compile_tun_ipv4_addrs(&ext->ipv4, &msk->ipv4, flow);
+	nfp_flower_compile_tun_ip_ext(&ext->ip_ext, &msk->ip_ext, flow);
 }
 
 int nfp_flower_compile_flow_match(struct nfp_app *app,
-				  struct tc_cls_flower_offload *flow,
+				  struct flow_cls_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
-				  enum nfp_flower_tun_type tun_type)
+				  enum nfp_flower_tun_type tun_type,
+				  struct netlink_ext_ack *extack)
 {
-	u32 cmsg_port = 0;
+	u32 port_id;
 	int err;
 	u8 *ext;
 	u8 *msk;
 
-	if (nfp_netdev_is_nfp_repr(netdev))
-		cmsg_port = nfp_repr_get_port_id(netdev);
+	port_id = nfp_flower_get_port_id_from_netdev(app, netdev);
 
 	memset(nfp_flow->unmasked_data, 0, key_ls->key_size);
 	memset(nfp_flow->mask_data, 0, key_ls->key_size);
@@ -313,12 +391,9 @@ int nfp_flower_compile_flow_match(struct nfp_app *app,
 	ext = nfp_flow->unmasked_data;
 	msk = nfp_flow->mask_data;
 
-	/* Populate Exact Metadata. */
 	nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)ext,
-				    flow, key_ls->key_layer, false);
-	/* Populate Mask Metadata. */
-	nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)msk,
-				    flow, key_ls->key_layer, true);
+				    (struct nfp_flower_meta_tci *)msk,
+				    flow, key_ls->key_layer);
 	ext += sizeof(struct nfp_flower_meta_tci);
 	msk += sizeof(struct nfp_flower_meta_tci);
 
@@ -334,13 +409,13 @@ int nfp_flower_compile_flow_match(struct nfp_app *app,
 
 	/* Populate Exact Port data. */
 	err = nfp_flower_compile_port((struct nfp_flower_in_port *)ext,
-				      cmsg_port, false, tun_type);
+				      port_id, false, tun_type, extack);
 	if (err)
 		return err;
 
 	/* Populate Mask Port Data. */
 	err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
-				      cmsg_port, true, tun_type);
+				      port_id, true, tun_type, extack);
 	if (err)
 		return err;
 
@@ -348,64 +423,61 @@ int nfp_flower_compile_flow_match(struct nfp_app *app,
 	msk += sizeof(struct nfp_flower_in_port);
 
 	if (NFP_FLOWER_LAYER_MAC & key_ls->key_layer) {
-		/* Populate Exact MAC Data. */
 		nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)ext,
-				       flow, false);
-		/* Populate Mask MAC Data. */
-		nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)msk,
-				       flow, true);
+				       (struct nfp_flower_mac_mpls *)msk,
+				       flow);
 		ext += sizeof(struct nfp_flower_mac_mpls);
 		msk += sizeof(struct nfp_flower_mac_mpls);
 	}
 
 	if (NFP_FLOWER_LAYER_TP & key_ls->key_layer) {
-		/* Populate Exact TP Data. */
 		nfp_flower_compile_tport((struct nfp_flower_tp_ports *)ext,
-					 flow, false);
-		/* Populate Mask TP Data. */
-		nfp_flower_compile_tport((struct nfp_flower_tp_ports *)msk,
-					 flow, true);
+					 (struct nfp_flower_tp_ports *)msk,
+					 flow);
 		ext += sizeof(struct nfp_flower_tp_ports);
 		msk += sizeof(struct nfp_flower_tp_ports);
 	}
 
 	if (NFP_FLOWER_LAYER_IPV4 & key_ls->key_layer) {
-		/* Populate Exact IPv4 Data. */
 		nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)ext,
-					flow, false);
-		/* Populate Mask IPv4 Data. */
-		nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)msk,
-					flow, true);
+					(struct nfp_flower_ipv4 *)msk,
+					flow);
 		ext += sizeof(struct nfp_flower_ipv4);
 		msk += sizeof(struct nfp_flower_ipv4);
 	}
 
 	if (NFP_FLOWER_LAYER_IPV6 & key_ls->key_layer) {
-		/* Populate Exact IPv4 Data. */
 		nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)ext,
-					flow, false);
-		/* Populate Mask IPv4 Data. */
-		nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)msk,
-					flow, true);
+					(struct nfp_flower_ipv6 *)msk,
+					flow);
 		ext += sizeof(struct nfp_flower_ipv6);
 		msk += sizeof(struct nfp_flower_ipv6);
 	}
 
+	if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GRE) {
+		__be32 tun_dst;
+
+		nfp_flower_compile_ipv4_gre_tun((void *)ext, (void *)msk, flow);
+		tun_dst = ((struct nfp_flower_ipv4_gre_tun *)ext)->ipv4.dst;
+		ext += sizeof(struct nfp_flower_ipv4_gre_tun);
+		msk += sizeof(struct nfp_flower_ipv4_gre_tun);
+
+		/* Store the tunnel destination in the rule data.
+		 * This must be present and be an exact match.
+		 */
+		nfp_flow->nfp_tun_ipv4_addr = tun_dst;
+		nfp_tunnel_add_ipv4_off(app, tun_dst);
+	}
+
 	if (key_ls->key_layer & NFP_FLOWER_LAYER_VXLAN ||
 	    key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE) {
 		__be32 tun_dst;
 
-		/* Populate Exact VXLAN Data. */
-		nfp_flower_compile_ipv4_udp_tun((void *)ext, flow, false);
-		/* Populate Mask VXLAN Data. */
-		nfp_flower_compile_ipv4_udp_tun((void *)msk, flow, true);
-		tun_dst = ((struct nfp_flower_ipv4_udp_tun *)ext)->ip_dst;
+		nfp_flower_compile_ipv4_udp_tun((void *)ext, (void *)msk, flow);
+		tun_dst = ((struct nfp_flower_ipv4_udp_tun *)ext)->ipv4.dst;
 		ext += sizeof(struct nfp_flower_ipv4_udp_tun);
 		msk += sizeof(struct nfp_flower_ipv4_udp_tun);
 
-		/* Configure tunnel end point MAC. */
-		nfp_tunnel_write_macs(app);
-
 		/* Store the tunnel destination in the rule data.
 		 * This must be present and be an exact match.
 		 */
@@ -413,11 +485,7 @@ int nfp_flower_compile_flow_match(struct nfp_app *app,
 		nfp_tunnel_add_ipv4_off(app, tun_dst);
 
 		if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
-			err = nfp_flower_compile_geneve_opt(ext, flow, false);
-			if (err)
-				return err;
-
-			err = nfp_flower_compile_geneve_opt(msk, flow, true);
+			err = nfp_flower_compile_geneve_opt(ext, msk, flow);
 			if (err)
 				return err;
 		}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 573a4400a26c..7c4a15e967df 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -4,6 +4,7 @@
 #include <linux/hash.h>
 #include <linux/hashtable.h>
 #include <linux/jhash.h>
+#include <linux/math64.h>
 #include <linux/vmalloc.h>
 #include <net/pkt_cls.h>
 
@@ -23,6 +24,18 @@ struct nfp_fl_flow_table_cmp_arg {
 	unsigned long cookie;
 };
 
+struct nfp_fl_stats_ctx_to_flow {
+	struct rhash_head ht_node;
+	u32 stats_cxt;
+	struct nfp_fl_payload *flow;
+};
+
+static const struct rhashtable_params stats_ctx_table_params = {
+	.key_offset	= offsetof(struct nfp_fl_stats_ctx_to_flow, stats_cxt),
+	.head_offset	= offsetof(struct nfp_fl_stats_ctx_to_flow, ht_node),
+	.key_len	= sizeof(u32),
+};
+
 static int nfp_release_stats_entry(struct nfp_app *app, u32 stats_context_id)
 {
 	struct nfp_flower_priv *priv = app->priv;
@@ -52,8 +65,17 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id)
 	freed_stats_id = priv->stats_ring_size;
 	/* Check for unallocated entries first. */
 	if (priv->stats_ids.init_unalloc > 0) {
-		*stats_context_id = priv->stats_ids.init_unalloc - 1;
-		priv->stats_ids.init_unalloc--;
+		if (priv->active_mem_unit == priv->total_mem_units) {
+			priv->stats_ids.init_unalloc--;
+			priv->active_mem_unit = 0;
+		}
+
+		*stats_context_id =
+			FIELD_PREP(NFP_FL_STAT_ID_STAT,
+				   priv->stats_ids.init_unalloc - 1) |
+			FIELD_PREP(NFP_FL_STAT_ID_MU_NUM,
+				   priv->active_mem_unit);
+		priv->active_mem_unit++;
 		return 0;
 	}
 
@@ -254,9 +276,6 @@ nfp_check_mask_remove(struct nfp_app *app, char *mask_data, u32 mask_len,
 	if (!mask_entry)
 		return false;
 
-	if (meta_flags)
-		*meta_flags &= ~NFP_FL_META_FLAG_MANAGE_MASK;
-
 	*mask_id = mask_entry->mask_id;
 	mask_entry->ref_cnt--;
 	if (!mask_entry->ref_cnt) {
@@ -271,29 +290,55 @@ nfp_check_mask_remove(struct nfp_app *app, char *mask_data, u32 mask_len,
 }
 
 int nfp_compile_flow_metadata(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct nfp_fl_payload *nfp_flow,
-			      struct net_device *netdev)
+			      struct net_device *netdev,
+			      struct netlink_ext_ack *extack)
 {
+	struct nfp_fl_stats_ctx_to_flow *ctx_entry;
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *check_entry;
 	u8 new_mask_id;
 	u32 stats_cxt;
+	int err;
 
-	if (nfp_get_stats_entry(app, &stats_cxt))
-		return -ENOENT;
+	err = nfp_get_stats_entry(app, &stats_cxt);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot allocate new stats context");
+		return err;
+	}
 
 	nfp_flow->meta.host_ctx_id = cpu_to_be32(stats_cxt);
 	nfp_flow->meta.host_cookie = cpu_to_be64(flow->cookie);
 	nfp_flow->ingress_dev = netdev;
 
+	ctx_entry = kzalloc(sizeof(*ctx_entry), GFP_KERNEL);
+	if (!ctx_entry) {
+		err = -ENOMEM;
+		goto err_release_stats;
+	}
+
+	ctx_entry->stats_cxt = stats_cxt;
+	ctx_entry->flow = nfp_flow;
+
+	if (rhashtable_insert_fast(&priv->stats_ctx_table, &ctx_entry->ht_node,
+				   stats_ctx_table_params)) {
+		err = -ENOMEM;
+		goto err_free_ctx_entry;
+	}
+
 	new_mask_id = 0;
 	if (!nfp_check_mask_add(app, nfp_flow->mask_data,
 				nfp_flow->meta.mask_len,
 				&nfp_flow->meta.flags, &new_mask_id)) {
-		if (nfp_release_stats_entry(app, stats_cxt))
-			return -EINVAL;
-		return -ENOENT;
+		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot allocate a new mask id");
+		if (nfp_release_stats_entry(app, stats_cxt)) {
+			NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release stats context");
+			err = -EINVAL;
+			goto err_remove_rhash;
+		}
+		err = -ENOENT;
+		goto err_remove_rhash;
 	}
 
 	nfp_flow->meta.flow_version = cpu_to_be64(priv->flower_version);
@@ -307,43 +352,97 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 
 	check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (check_entry) {
-		if (nfp_release_stats_entry(app, stats_cxt))
-			return -EINVAL;
+		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot offload duplicate flow entry");
+		if (nfp_release_stats_entry(app, stats_cxt)) {
+			NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release stats context");
+			err = -EINVAL;
+			goto err_remove_mask;
+		}
 
 		if (!nfp_check_mask_remove(app, nfp_flow->mask_data,
 					   nfp_flow->meta.mask_len,
-					   NULL, &new_mask_id))
-			return -EINVAL;
-
-		return -EEXIST;
+					   NULL, &new_mask_id)) {
+			NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release mask id");
+			err = -EINVAL;
+			goto err_remove_mask;
+		}
+
+		err = -EEXIST;
+		goto err_remove_mask;
 	}
 
 	return 0;
+
+err_remove_mask:
+	nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len,
+			      NULL, &new_mask_id);
+err_remove_rhash:
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table,
+					    &ctx_entry->ht_node,
+					    stats_ctx_table_params));
+err_free_ctx_entry:
+	kfree(ctx_entry);
+err_release_stats:
+	nfp_release_stats_entry(app, stats_cxt);
+
+	return err;
+}
+
+void __nfp_modify_flow_metadata(struct nfp_flower_priv *priv,
+				struct nfp_fl_payload *nfp_flow)
+{
+	nfp_flow->meta.flags &= ~NFP_FL_META_FLAG_MANAGE_MASK;
+	nfp_flow->meta.flow_version = cpu_to_be64(priv->flower_version);
+	priv->flower_version++;
 }
 
 int nfp_modify_flow_metadata(struct nfp_app *app,
 			     struct nfp_fl_payload *nfp_flow)
 {
+	struct nfp_fl_stats_ctx_to_flow *ctx_entry;
 	struct nfp_flower_priv *priv = app->priv;
 	u8 new_mask_id = 0;
 	u32 temp_ctx_id;
 
+	__nfp_modify_flow_metadata(priv, nfp_flow);
+
 	nfp_check_mask_remove(app, nfp_flow->mask_data,
 			      nfp_flow->meta.mask_len, &nfp_flow->meta.flags,
 			      &new_mask_id);
 
-	nfp_flow->meta.flow_version = cpu_to_be64(priv->flower_version);
-	priv->flower_version++;
-
 	/* Update flow payload with mask ids. */
 	nfp_flow->unmasked_data[NFP_FL_MASK_ID_LOCATION] = new_mask_id;
 
-	/* Release the stats ctx id. */
+	/* Release the stats ctx id and ctx to flow table entry. */
 	temp_ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
 
+	ctx_entry = rhashtable_lookup_fast(&priv->stats_ctx_table, &temp_ctx_id,
+					   stats_ctx_table_params);
+	if (!ctx_entry)
+		return -ENOENT;
+
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table,
+					    &ctx_entry->ht_node,
+					    stats_ctx_table_params));
+	kfree(ctx_entry);
+
 	return nfp_release_stats_entry(app, temp_ctx_id);
 }
 
+struct nfp_fl_payload *
+nfp_flower_get_fl_payload_from_ctx(struct nfp_app *app, u32 ctx_id)
+{
+	struct nfp_fl_stats_ctx_to_flow *ctx_entry;
+	struct nfp_flower_priv *priv = app->priv;
+
+	ctx_entry = rhashtable_lookup_fast(&priv->stats_ctx_table, &ctx_id,
+					   stats_ctx_table_params);
+	if (!ctx_entry)
+		return NULL;
+
+	return ctx_entry->flow;
+}
+
 static int nfp_fl_obj_cmpfn(struct rhashtable_compare_arg *arg,
 			    const void *obj)
 {
@@ -381,10 +480,11 @@ const struct rhashtable_params nfp_flower_table_params = {
 	.automatic_shrinking	= true,
 };
 
-int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count)
+int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
+			     unsigned int host_num_mems)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	int err;
+	int err, stats_size;
 
 	hash_init(priv->mask_table);
 
@@ -392,6 +492,10 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count)
 	if (err)
 		return err;
 
+	err = rhashtable_init(&priv->stats_ctx_table, &stats_ctx_table_params);
+	if (err)
+		goto err_free_flow_table;
+
 	get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed));
 
 	/* Init ring buffer and unallocated mask_ids. */
@@ -399,7 +503,7 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count)
 		kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS,
 			      NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL);
 	if (!priv->mask_ids.mask_id_free_list.buf)
-		goto err_free_flow_table;
+		goto err_free_stats_ctx_table;
 
 	priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1;
 
@@ -417,10 +521,12 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count)
 	if (!priv->stats_ids.free_list.buf)
 		goto err_free_last_used;
 
-	priv->stats_ids.init_unalloc = host_ctx_count;
+	priv->stats_ids.init_unalloc = div_u64(host_ctx_count, host_num_mems);
 
-	priv->stats = kvmalloc_array(priv->stats_ring_size,
-				     sizeof(struct nfp_fl_stats), GFP_KERNEL);
+	stats_size = FIELD_PREP(NFP_FL_STAT_ID_STAT, host_ctx_count) |
+		     FIELD_PREP(NFP_FL_STAT_ID_MU_NUM, host_num_mems - 1);
+	priv->stats = kvmalloc_array(stats_size, sizeof(struct nfp_fl_stats),
+				     GFP_KERNEL);
 	if (!priv->stats)
 		goto err_free_ring_buf;
 
@@ -434,6 +540,8 @@ err_free_last_used:
 	kfree(priv->mask_ids.last_used);
 err_free_mask_id:
 	kfree(priv->mask_ids.mask_id_free_list.buf);
+err_free_stats_ctx_table:
+	rhashtable_destroy(&priv->stats_ctx_table);
 err_free_flow_table:
 	rhashtable_destroy(&priv->flow_table);
 	return -ENOMEM;
@@ -448,6 +556,8 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app)
 
 	rhashtable_free_and_destroy(&priv->flow_table,
 				    nfp_check_rhashtable_empty, NULL);
+	rhashtable_free_and_destroy(&priv->stats_ctx_table,
+				    nfp_check_rhashtable_empty, NULL);
 	kvfree(priv->stats);
 	kfree(priv->mask_ids.mask_id_free_list.buf);
 	kfree(priv->mask_ids.last_used);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 2cdbf29ecbe7..faa8ba012a37 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -52,8 +52,29 @@
 
 #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \
 	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS))
+
+#define NFP_FLOWER_MERGE_FIELDS \
+	(NFP_FLOWER_LAYER_PORT | \
+	 NFP_FLOWER_LAYER_MAC | \
+	 NFP_FLOWER_LAYER_TP | \
+	 NFP_FLOWER_LAYER_IPV4 | \
+	 NFP_FLOWER_LAYER_IPV6)
+
+struct nfp_flower_merge_check {
+	union {
+		struct {
+			__be16 tci;
+			struct nfp_flower_mac_mpls l2;
+			struct nfp_flower_tp_ports l4;
+			union {
+				struct nfp_flower_ipv4 ipv4;
+				struct nfp_flower_ipv6 ipv6;
+			};
+		};
+		unsigned long vals[8];
+	};
+};
 
 static int
 nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
@@ -100,23 +121,33 @@ nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
 	return 0;
 }
 
-static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f)
+static bool nfp_flower_check_higher_than_mac(struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+
+	return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) ||
+	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) ||
+	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) ||
+	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP);
+}
+
+static bool nfp_flower_check_higher_than_l3(struct flow_cls_offload *f)
 {
-	return dissector_uses_key(f->dissector,
-				  FLOW_DISSECTOR_KEY_IPV4_ADDRS) ||
-		dissector_uses_key(f->dissector,
-				   FLOW_DISSECTOR_KEY_IPV6_ADDRS) ||
-		dissector_uses_key(f->dissector,
-				   FLOW_DISSECTOR_KEY_PORTS) ||
-		dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ICMP);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+
+	return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) ||
+	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP);
 }
 
 static int
 nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts,
-			  u32 *key_layer_two, int *key_size)
+			  u32 *key_layer_two, int *key_size,
+			  struct netlink_ext_ack *extack)
 {
-	if (enc_opts->len > NFP_FL_MAX_GENEVE_OPT_KEY)
+	if (enc_opts->len > NFP_FL_MAX_GENEVE_OPT_KEY) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: geneve options exceed maximum length");
 		return -EOPNOTSUPP;
+	}
 
 	if (enc_opts->len > 0) {
 		*key_layer_two |= NFP_FLOWER_LAYER2_GENEVE_OP;
@@ -127,146 +158,186 @@ nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts,
 }
 
 static int
+nfp_flower_calc_udp_tun_layer(struct flow_dissector_key_ports *enc_ports,
+			      struct flow_dissector_key_enc_opts *enc_op,
+			      u32 *key_layer_two, u8 *key_layer, int *key_size,
+			      struct nfp_flower_priv *priv,
+			      enum nfp_flower_tun_type *tun_type,
+			      struct netlink_ext_ack *extack)
+{
+	int err;
+
+	switch (enc_ports->dst) {
+	case htons(IANA_VXLAN_UDP_PORT):
+		*tun_type = NFP_FL_TUNNEL_VXLAN;
+		*key_layer |= NFP_FLOWER_LAYER_VXLAN;
+		*key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+
+		if (enc_op) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: encap options not supported on vxlan tunnels");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case htons(GENEVE_UDP_PORT):
+		if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE)) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support geneve offload");
+			return -EOPNOTSUPP;
+		}
+		*tun_type = NFP_FL_TUNNEL_GENEVE;
+		*key_layer |= NFP_FLOWER_LAYER_EXT_META;
+		*key_size += sizeof(struct nfp_flower_ext_meta);
+		*key_layer_two |= NFP_FLOWER_LAYER2_GENEVE;
+		*key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+
+		if (!enc_op)
+			break;
+		if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT)) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support geneve option offload");
+			return -EOPNOTSUPP;
+		}
+		err = nfp_flower_calc_opt_layer(enc_op, key_layer_two,
+						key_size, extack);
+		if (err)
+			return err;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: tunnel type unknown");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
 nfp_flower_calculate_key_layers(struct nfp_app *app,
 				struct net_device *netdev,
 				struct nfp_fl_key_ls *ret_key_ls,
-				struct tc_cls_flower_offload *flow,
-				enum nfp_flower_tun_type *tun_type)
+				struct flow_cls_offload *flow,
+				enum nfp_flower_tun_type *tun_type,
+				struct netlink_ext_ack *extack)
 {
-	struct flow_dissector_key_basic *mask_basic = NULL;
-	struct flow_dissector_key_basic *key_basic = NULL;
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct flow_dissector *dissector = rule->match.dissector;
+	struct flow_match_basic basic = { NULL, NULL};
 	struct nfp_flower_priv *priv = app->priv;
 	u32 key_layer_two;
 	u8 key_layer;
 	int key_size;
 	int err;
 
-	if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
+	if (dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: match not supported");
 		return -EOPNOTSUPP;
+	}
 
 	/* If any tun dissector is used then the required set must be used. */
-	if (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR &&
-	    (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
-	    != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
+	if (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR &&
+	    (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
+	    != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: tunnel match not supported");
 		return -EOPNOTSUPP;
+	}
 
 	key_layer_two = 0;
 	key_layer = NFP_FLOWER_LAYER_PORT;
 	key_size = sizeof(struct nfp_flower_meta_tci) +
 		   sizeof(struct nfp_flower_in_port);
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS) ||
-	    dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS) ||
+	    flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) {
 		key_layer |= NFP_FLOWER_LAYER_MAC;
 		key_size += sizeof(struct nfp_flower_mac_mpls);
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *flow_vlan;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan vlan;
 
-		flow_vlan = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_VLAN,
-						      flow->mask);
+		flow_rule_match_vlan(rule, &vlan);
 		if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_PCP) &&
-		    flow_vlan->vlan_priority)
+		    vlan.key->vlan_priority) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support VLAN PCP offload");
 			return -EOPNOTSUPP;
+		}
 	}
 
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
-		struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL;
-		struct flow_dissector_key_ports *mask_enc_ports = NULL;
-		struct flow_dissector_key_enc_opts *enc_op = NULL;
-		struct flow_dissector_key_ports *enc_ports = NULL;
-		struct flow_dissector_key_control *mask_enc_ctl =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-						  flow->mask);
-		struct flow_dissector_key_control *enc_ctl =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-						  flow->key);
-
-		if (mask_enc_ctl->addr_type != 0xffff ||
-		    enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS)
-			return -EOPNOTSUPP;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_match_enc_opts enc_op = { NULL, NULL };
+		struct flow_match_ipv4_addrs ipv4_addrs;
+		struct flow_match_control enc_ctl;
+		struct flow_match_ports enc_ports;
 
-		/* These fields are already verified as used. */
-		mask_ipv4 =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-						  flow->mask);
-		if (mask_ipv4->dst != cpu_to_be32(~0))
-			return -EOPNOTSUPP;
+		flow_rule_match_enc_control(rule, &enc_ctl);
 
-		mask_enc_ports =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  flow->mask);
-		enc_ports =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  flow->key);
-
-		if (mask_enc_ports->dst != cpu_to_be16(~0))
+		if (enc_ctl.mask->addr_type != 0xffff) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: wildcarded protocols on tunnels are not supported");
+			return -EOPNOTSUPP;
+		}
+		if (enc_ctl.key->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: only IPv4 tunnels are supported");
 			return -EOPNOTSUPP;
-
-		if (dissector_uses_key(flow->dissector,
-				       FLOW_DISSECTOR_KEY_ENC_OPTS)) {
-			enc_op = skb_flow_dissector_target(flow->dissector,
-							   FLOW_DISSECTOR_KEY_ENC_OPTS,
-							   flow->key);
 		}
 
-		switch (enc_ports->dst) {
-		case htons(NFP_FL_VXLAN_PORT):
-			*tun_type = NFP_FL_TUNNEL_VXLAN;
-			key_layer |= NFP_FLOWER_LAYER_VXLAN;
-			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+		/* These fields are already verified as used. */
+		flow_rule_match_enc_ipv4_addrs(rule, &ipv4_addrs);
+		if (ipv4_addrs.mask->dst != cpu_to_be32(~0)) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: only an exact match IPv4 destination address is supported");
+			return -EOPNOTSUPP;
+		}
 
-			if (enc_op)
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS))
+			flow_rule_match_enc_opts(rule, &enc_op);
+
+
+		if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+			/* check if GRE, which has no enc_ports */
+			if (netif_is_gretap(netdev)) {
+				*tun_type = NFP_FL_TUNNEL_GRE;
+				key_layer |= NFP_FLOWER_LAYER_EXT_META;
+				key_size += sizeof(struct nfp_flower_ext_meta);
+				key_layer_two |= NFP_FLOWER_LAYER2_GRE;
+				key_size +=
+					sizeof(struct nfp_flower_ipv4_gre_tun);
+
+				if (enc_op.key) {
+					NL_SET_ERR_MSG_MOD(extack, "unsupported offload: encap options not supported on GRE tunnels");
+					return -EOPNOTSUPP;
+				}
+			} else {
+				NL_SET_ERR_MSG_MOD(extack, "unsupported offload: an exact match on L4 destination port is required for non-GRE tunnels");
 				return -EOPNOTSUPP;
-			break;
-		case htons(NFP_FL_GENEVE_PORT):
-			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE))
+			}
+		} else {
+			flow_rule_match_enc_ports(rule, &enc_ports);
+			if (enc_ports.mask->dst != cpu_to_be16(~0)) {
+				NL_SET_ERR_MSG_MOD(extack, "unsupported offload: only an exact match L4 destination port is supported");
 				return -EOPNOTSUPP;
-			*tun_type = NFP_FL_TUNNEL_GENEVE;
-			key_layer |= NFP_FLOWER_LAYER_EXT_META;
-			key_size += sizeof(struct nfp_flower_ext_meta);
-			key_layer_two |= NFP_FLOWER_LAYER2_GENEVE;
-			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+			}
 
-			if (!enc_op)
-				break;
-			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))
-				return -EOPNOTSUPP;
-			err = nfp_flower_calc_opt_layer(enc_op, &key_layer_two,
-							&key_size);
+			err = nfp_flower_calc_udp_tun_layer(enc_ports.key,
+							    enc_op.key,
+							    &key_layer_two,
+							    &key_layer,
+							    &key_size, priv,
+							    tun_type, extack);
 			if (err)
 				return err;
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
 
-		/* Ensure the ingress netdev matches the expected tun type. */
-		if (!nfp_fl_netdev_is_tunnel_type(netdev, *tun_type))
-			return -EOPNOTSUPP;
+			/* Ensure the ingress netdev matches the expected
+			 * tun type.
+			 */
+			if (!nfp_fl_netdev_is_tunnel_type(netdev, *tun_type)) {
+				NL_SET_ERR_MSG_MOD(extack, "unsupported offload: ingress netdev does not match the expected tunnel type");
+				return -EOPNOTSUPP;
+			}
+		}
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		mask_basic = skb_flow_dissector_target(flow->dissector,
-						       FLOW_DISSECTOR_KEY_BASIC,
-						       flow->mask);
-
-		key_basic = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_BASIC,
-						      flow->key);
-	}
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC))
+		flow_rule_match_basic(rule, &basic);
 
-	if (mask_basic && mask_basic->n_proto) {
+	if (basic.mask && basic.mask->n_proto) {
 		/* Ethernet type is present in the key. */
-		switch (key_basic->n_proto) {
+		switch (basic.key->n_proto) {
 		case cpu_to_be16(ETH_P_IP):
 			key_layer |= NFP_FLOWER_LAYER_IPV4;
 			key_size += sizeof(struct nfp_flower_ipv4);
@@ -281,6 +352,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		 * because we rely on it to get to the host.
 		 */
 		case cpu_to_be16(ETH_P_ARP):
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: ARP not supported");
 			return -EOPNOTSUPP;
 
 		case cpu_to_be16(ETH_P_MPLS_UC):
@@ -296,18 +368,16 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			break;
 
 		default:
-			/* Other ethtype - we need check the masks for the
-			 * remainder of the key to ensure we can offload.
-			 */
-			if (nfp_flower_check_higher_than_mac(flow))
-				return -EOPNOTSUPP;
-			break;
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: match on given EtherType is not supported");
+			return -EOPNOTSUPP;
 		}
+	} else if (nfp_flower_check_higher_than_mac(flow)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: cannot match above L2 without specified EtherType");
+		return -EOPNOTSUPP;
 	}
 
-	if (mask_basic && mask_basic->ip_proto) {
-		/* Ethernet type is present in the key. */
-		switch (key_basic->ip_proto) {
+	if (basic.mask && basic.mask->ip_proto) {
+		switch (basic.key->ip_proto) {
 		case IPPROTO_TCP:
 		case IPPROTO_UDP:
 		case IPPROTO_SCTP:
@@ -316,68 +386,73 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			key_layer |= NFP_FLOWER_LAYER_TP;
 			key_size += sizeof(struct nfp_flower_tp_ports);
 			break;
-		default:
-			/* Other ip proto - we need check the masks for the
-			 * remainder of the key to ensure we can offload.
-			 */
-			return -EOPNOTSUPP;
 		}
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) {
-		struct flow_dissector_key_tcp *tcp;
+	if (!(key_layer & NFP_FLOWER_LAYER_TP) &&
+	    nfp_flower_check_higher_than_l3(flow)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: cannot match on L4 information without specified IP protocol type");
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
+		struct flow_match_tcp tcp;
 		u32 tcp_flags;
 
-		tcp = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_TCP,
-						flow->key);
-		tcp_flags = be16_to_cpu(tcp->flags);
+		flow_rule_match_tcp(rule, &tcp);
+		tcp_flags = be16_to_cpu(tcp.key->flags);
 
-		if (tcp_flags & ~NFP_FLOWER_SUPPORTED_TCPFLAGS)
+		if (tcp_flags & ~NFP_FLOWER_SUPPORTED_TCPFLAGS) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: no match support for selected TCP flags");
 			return -EOPNOTSUPP;
+		}
 
 		/* We only support PSH and URG flags when either
 		 * FIN, SYN or RST is present as well.
 		 */
 		if ((tcp_flags & (TCPHDR_PSH | TCPHDR_URG)) &&
-		    !(tcp_flags & (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST)))
+		    !(tcp_flags & (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST))) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: PSH and URG is only supported when used with FIN, SYN or RST");
 			return -EOPNOTSUPP;
+		}
 
 		/* We need to store TCP flags in the either the IPv4 or IPv6 key
 		 * space, thus we need to ensure we include a IPv4/IPv6 key
 		 * layer if we have not done so already.
 		 */
-		if (!key_basic)
+		if (!basic.key) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: match on TCP flags requires a match on L3 protocol");
 			return -EOPNOTSUPP;
+		}
 
 		if (!(key_layer & NFP_FLOWER_LAYER_IPV4) &&
 		    !(key_layer & NFP_FLOWER_LAYER_IPV6)) {
-			switch (key_basic->n_proto) {
+			switch (basic.key->n_proto) {
 			case cpu_to_be16(ETH_P_IP):
 				key_layer |= NFP_FLOWER_LAYER_IPV4;
 				key_size += sizeof(struct nfp_flower_ipv4);
 				break;
 
 			case cpu_to_be16(ETH_P_IPV6):
-				key_layer |= NFP_FLOWER_LAYER_IPV6;
+					key_layer |= NFP_FLOWER_LAYER_IPV6;
 				key_size += sizeof(struct nfp_flower_ipv6);
 				break;
 
 			default:
+				NL_SET_ERR_MSG_MOD(extack, "unsupported offload: match on TCP flags requires a match on IPv4/IPv6");
 				return -EOPNOTSUPP;
 			}
 		}
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key_ctl;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control ctl;
 
-		key_ctl = skb_flow_dissector_target(flow->dissector,
-						    FLOW_DISSECTOR_KEY_CONTROL,
-						    flow->key);
-
-		if (key_ctl->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS)
+		flow_rule_match_control(rule, &ctl);
+		if (ctl.key->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS) {
+			NL_SET_ERR_MSG_MOD(extack, "unsupported offload: match on unknown control flag");
 			return -EOPNOTSUPP;
+		}
 	}
 
 	ret_key_ls->key_layer = key_layer;
@@ -412,6 +487,8 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer)
 
 	flow_pay->nfp_tun_ipv4_addr = 0;
 	flow_pay->meta.flags = 0;
+	INIT_LIST_HEAD(&flow_pay->linked_flows);
+	flow_pay->in_hw = false;
 
 	return flow_pay;
 
@@ -424,6 +501,449 @@ err_free_flow:
 	return NULL;
 }
 
+static int
+nfp_flower_update_merge_with_actions(struct nfp_fl_payload *flow,
+				     struct nfp_flower_merge_check *merge,
+				     u8 *last_act_id, int *act_out)
+{
+	struct nfp_fl_set_ipv6_tc_hl_fl *ipv6_tc_hl_fl;
+	struct nfp_fl_set_ip4_ttl_tos *ipv4_ttl_tos;
+	struct nfp_fl_set_ip4_addrs *ipv4_add;
+	struct nfp_fl_set_ipv6_addr *ipv6_add;
+	struct nfp_fl_push_vlan *push_vlan;
+	struct nfp_fl_set_tport *tport;
+	struct nfp_fl_set_eth *eth;
+	struct nfp_fl_act_head *a;
+	unsigned int act_off = 0;
+	u8 act_id = 0;
+	u8 *ports;
+	int i;
+
+	while (act_off < flow->meta.act_len) {
+		a = (struct nfp_fl_act_head *)&flow->action_data[act_off];
+		act_id = a->jump_id;
+
+		switch (act_id) {
+		case NFP_FL_ACTION_OPCODE_OUTPUT:
+			if (act_out)
+				(*act_out)++;
+			break;
+		case NFP_FL_ACTION_OPCODE_PUSH_VLAN:
+			push_vlan = (struct nfp_fl_push_vlan *)a;
+			if (push_vlan->vlan_tci)
+				merge->tci = cpu_to_be16(0xffff);
+			break;
+		case NFP_FL_ACTION_OPCODE_POP_VLAN:
+			merge->tci = cpu_to_be16(0);
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL:
+			/* New tunnel header means l2 to l4 can be matched. */
+			eth_broadcast_addr(&merge->l2.mac_dst[0]);
+			eth_broadcast_addr(&merge->l2.mac_src[0]);
+			memset(&merge->l4, 0xff,
+			       sizeof(struct nfp_flower_tp_ports));
+			memset(&merge->ipv4, 0xff,
+			       sizeof(struct nfp_flower_ipv4));
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_ETHERNET:
+			eth = (struct nfp_fl_set_eth *)a;
+			for (i = 0; i < ETH_ALEN; i++)
+				merge->l2.mac_dst[i] |= eth->eth_addr_mask[i];
+			for (i = 0; i < ETH_ALEN; i++)
+				merge->l2.mac_src[i] |=
+					eth->eth_addr_mask[ETH_ALEN + i];
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS:
+			ipv4_add = (struct nfp_fl_set_ip4_addrs *)a;
+			merge->ipv4.ipv4_src |= ipv4_add->ipv4_src_mask;
+			merge->ipv4.ipv4_dst |= ipv4_add->ipv4_dst_mask;
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS:
+			ipv4_ttl_tos = (struct nfp_fl_set_ip4_ttl_tos *)a;
+			merge->ipv4.ip_ext.ttl |= ipv4_ttl_tos->ipv4_ttl_mask;
+			merge->ipv4.ip_ext.tos |= ipv4_ttl_tos->ipv4_tos_mask;
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_IPV6_SRC:
+			ipv6_add = (struct nfp_fl_set_ipv6_addr *)a;
+			for (i = 0; i < 4; i++)
+				merge->ipv6.ipv6_src.in6_u.u6_addr32[i] |=
+					ipv6_add->ipv6[i].mask;
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_IPV6_DST:
+			ipv6_add = (struct nfp_fl_set_ipv6_addr *)a;
+			for (i = 0; i < 4; i++)
+				merge->ipv6.ipv6_dst.in6_u.u6_addr32[i] |=
+					ipv6_add->ipv6[i].mask;
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_IPV6_TC_HL_FL:
+			ipv6_tc_hl_fl = (struct nfp_fl_set_ipv6_tc_hl_fl *)a;
+			merge->ipv6.ip_ext.ttl |=
+				ipv6_tc_hl_fl->ipv6_hop_limit_mask;
+			merge->ipv6.ip_ext.tos |= ipv6_tc_hl_fl->ipv6_tc_mask;
+			merge->ipv6.ipv6_flow_label_exthdr |=
+				ipv6_tc_hl_fl->ipv6_label_mask;
+			break;
+		case NFP_FL_ACTION_OPCODE_SET_UDP:
+		case NFP_FL_ACTION_OPCODE_SET_TCP:
+			tport = (struct nfp_fl_set_tport *)a;
+			ports = (u8 *)&merge->l4.port_src;
+			for (i = 0; i < 4; i++)
+				ports[i] |= tport->tp_port_mask[i];
+			break;
+		case NFP_FL_ACTION_OPCODE_PRE_TUNNEL:
+		case NFP_FL_ACTION_OPCODE_PRE_LAG:
+		case NFP_FL_ACTION_OPCODE_PUSH_GENEVE:
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		act_off += a->len_lw << NFP_FL_LW_SIZ;
+	}
+
+	if (last_act_id)
+		*last_act_id = act_id;
+
+	return 0;
+}
+
+static int
+nfp_flower_populate_merge_match(struct nfp_fl_payload *flow,
+				struct nfp_flower_merge_check *merge,
+				bool extra_fields)
+{
+	struct nfp_flower_meta_tci *meta_tci;
+	u8 *mask = flow->mask_data;
+	u8 key_layer, match_size;
+
+	memset(merge, 0, sizeof(struct nfp_flower_merge_check));
+
+	meta_tci = (struct nfp_flower_meta_tci *)mask;
+	key_layer = meta_tci->nfp_flow_key_layer;
+
+	if (key_layer & ~NFP_FLOWER_MERGE_FIELDS && !extra_fields)
+		return -EOPNOTSUPP;
+
+	merge->tci = meta_tci->tci;
+	mask += sizeof(struct nfp_flower_meta_tci);
+
+	if (key_layer & NFP_FLOWER_LAYER_EXT_META)
+		mask += sizeof(struct nfp_flower_ext_meta);
+
+	mask += sizeof(struct nfp_flower_in_port);
+
+	if (key_layer & NFP_FLOWER_LAYER_MAC) {
+		match_size = sizeof(struct nfp_flower_mac_mpls);
+		memcpy(&merge->l2, mask, match_size);
+		mask += match_size;
+	}
+
+	if (key_layer & NFP_FLOWER_LAYER_TP) {
+		match_size = sizeof(struct nfp_flower_tp_ports);
+		memcpy(&merge->l4, mask, match_size);
+		mask += match_size;
+	}
+
+	if (key_layer & NFP_FLOWER_LAYER_IPV4) {
+		match_size = sizeof(struct nfp_flower_ipv4);
+		memcpy(&merge->ipv4, mask, match_size);
+	}
+
+	if (key_layer & NFP_FLOWER_LAYER_IPV6) {
+		match_size = sizeof(struct nfp_flower_ipv6);
+		memcpy(&merge->ipv6, mask, match_size);
+	}
+
+	return 0;
+}
+
+static int
+nfp_flower_can_merge(struct nfp_fl_payload *sub_flow1,
+		     struct nfp_fl_payload *sub_flow2)
+{
+	/* Two flows can be merged if sub_flow2 only matches on bits that are
+	 * either matched by sub_flow1 or set by a sub_flow1 action. This
+	 * ensures that every packet that hits sub_flow1 and recirculates is
+	 * guaranteed to hit sub_flow2.
+	 */
+	struct nfp_flower_merge_check sub_flow1_merge, sub_flow2_merge;
+	int err, act_out = 0;
+	u8 last_act_id = 0;
+
+	err = nfp_flower_populate_merge_match(sub_flow1, &sub_flow1_merge,
+					      true);
+	if (err)
+		return err;
+
+	err = nfp_flower_populate_merge_match(sub_flow2, &sub_flow2_merge,
+					      false);
+	if (err)
+		return err;
+
+	err = nfp_flower_update_merge_with_actions(sub_flow1, &sub_flow1_merge,
+						   &last_act_id, &act_out);
+	if (err)
+		return err;
+
+	/* Must only be 1 output action and it must be the last in sequence. */
+	if (act_out != 1 || last_act_id != NFP_FL_ACTION_OPCODE_OUTPUT)
+		return -EOPNOTSUPP;
+
+	/* Reject merge if sub_flow2 matches on something that is not matched
+	 * on or set in an action by sub_flow1.
+	 */
+	err = bitmap_andnot(sub_flow2_merge.vals, sub_flow2_merge.vals,
+			    sub_flow1_merge.vals,
+			    sizeof(struct nfp_flower_merge_check) * 8);
+	if (err)
+		return -EINVAL;
+
+	return 0;
+}
+
+static unsigned int
+nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len,
+			    bool *tunnel_act)
+{
+	unsigned int act_off = 0, act_len;
+	struct nfp_fl_act_head *a;
+	u8 act_id = 0;
+
+	while (act_off < len) {
+		a = (struct nfp_fl_act_head *)&act_src[act_off];
+		act_len = a->len_lw << NFP_FL_LW_SIZ;
+		act_id = a->jump_id;
+
+		switch (act_id) {
+		case NFP_FL_ACTION_OPCODE_PRE_TUNNEL:
+			if (tunnel_act)
+				*tunnel_act = true;
+			/* fall through */
+		case NFP_FL_ACTION_OPCODE_PRE_LAG:
+			memcpy(act_dst + act_off, act_src + act_off, act_len);
+			break;
+		default:
+			return act_off;
+		}
+
+		act_off += act_len;
+	}
+
+	return act_off;
+}
+
+static int nfp_fl_verify_post_tun_acts(char *acts, int len)
+{
+	struct nfp_fl_act_head *a;
+	unsigned int act_off = 0;
+
+	while (act_off < len) {
+		a = (struct nfp_fl_act_head *)&acts[act_off];
+		if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT)
+			return -EOPNOTSUPP;
+
+		act_off += a->len_lw << NFP_FL_LW_SIZ;
+	}
+
+	return 0;
+}
+
+static int
+nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1,
+			struct nfp_fl_payload *sub_flow2,
+			struct nfp_fl_payload *merge_flow)
+{
+	unsigned int sub1_act_len, sub2_act_len, pre_off1, pre_off2;
+	bool tunnel_act = false;
+	char *merge_act;
+	int err;
+
+	/* The last action of sub_flow1 must be output - do not merge this. */
+	sub1_act_len = sub_flow1->meta.act_len - sizeof(struct nfp_fl_output);
+	sub2_act_len = sub_flow2->meta.act_len;
+
+	if (!sub2_act_len)
+		return -EINVAL;
+
+	if (sub1_act_len + sub2_act_len > NFP_FL_MAX_A_SIZ)
+		return -EINVAL;
+
+	/* A shortcut can only be applied if there is a single action. */
+	if (sub1_act_len)
+		merge_flow->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
+	else
+		merge_flow->meta.shortcut = sub_flow2->meta.shortcut;
+
+	merge_flow->meta.act_len = sub1_act_len + sub2_act_len;
+	merge_act = merge_flow->action_data;
+
+	/* Copy any pre-actions to the start of merge flow action list. */
+	pre_off1 = nfp_flower_copy_pre_actions(merge_act,
+					       sub_flow1->action_data,
+					       sub1_act_len, &tunnel_act);
+	merge_act += pre_off1;
+	sub1_act_len -= pre_off1;
+	pre_off2 = nfp_flower_copy_pre_actions(merge_act,
+					       sub_flow2->action_data,
+					       sub2_act_len, NULL);
+	merge_act += pre_off2;
+	sub2_act_len -= pre_off2;
+
+	/* FW does a tunnel push when egressing, therefore, if sub_flow 1 pushes
+	 * a tunnel, sub_flow 2 can only have output actions for a valid merge.
+	 */
+	if (tunnel_act) {
+		char *post_tun_acts = &sub_flow2->action_data[pre_off2];
+
+		err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len);
+		if (err)
+			return err;
+	}
+
+	/* Copy remaining actions from sub_flows 1 and 2. */
+	memcpy(merge_act, sub_flow1->action_data + pre_off1, sub1_act_len);
+	merge_act += sub1_act_len;
+	memcpy(merge_act, sub_flow2->action_data + pre_off2, sub2_act_len);
+
+	return 0;
+}
+
+/* Flow link code should only be accessed under RTNL. */
+static void nfp_flower_unlink_flow(struct nfp_fl_payload_link *link)
+{
+	list_del(&link->merge_flow.list);
+	list_del(&link->sub_flow.list);
+	kfree(link);
+}
+
+static void nfp_flower_unlink_flows(struct nfp_fl_payload *merge_flow,
+				    struct nfp_fl_payload *sub_flow)
+{
+	struct nfp_fl_payload_link *link;
+
+	list_for_each_entry(link, &merge_flow->linked_flows, merge_flow.list)
+		if (link->sub_flow.flow == sub_flow) {
+			nfp_flower_unlink_flow(link);
+			return;
+		}
+}
+
+static int nfp_flower_link_flows(struct nfp_fl_payload *merge_flow,
+				 struct nfp_fl_payload *sub_flow)
+{
+	struct nfp_fl_payload_link *link;
+
+	link = kmalloc(sizeof(*link), GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+
+	link->merge_flow.flow = merge_flow;
+	list_add_tail(&link->merge_flow.list, &merge_flow->linked_flows);
+	link->sub_flow.flow = sub_flow;
+	list_add_tail(&link->sub_flow.list, &sub_flow->linked_flows);
+
+	return 0;
+}
+
+/**
+ * nfp_flower_merge_offloaded_flows() - Merge 2 existing flows to single flow.
+ * @app:	Pointer to the APP handle
+ * @sub_flow1:	Initial flow matched to produce merge hint
+ * @sub_flow2:	Post recirculation flow matched in merge hint
+ *
+ * Combines 2 flows (if valid) to a single flow, removing the initial from hw
+ * and offloading the new, merged flow.
+ *
+ * Return: negative value on error, 0 in success.
+ */
+int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
+				     struct nfp_fl_payload *sub_flow1,
+				     struct nfp_fl_payload *sub_flow2)
+{
+	struct flow_cls_offload merge_tc_off;
+	struct nfp_flower_priv *priv = app->priv;
+	struct netlink_ext_ack *extack = NULL;
+	struct nfp_fl_payload *merge_flow;
+	struct nfp_fl_key_ls merge_key_ls;
+	int err;
+
+	ASSERT_RTNL();
+
+	extack = merge_tc_off.common.extack;
+	if (sub_flow1 == sub_flow2 ||
+	    nfp_flower_is_merge_flow(sub_flow1) ||
+	    nfp_flower_is_merge_flow(sub_flow2))
+		return -EINVAL;
+
+	err = nfp_flower_can_merge(sub_flow1, sub_flow2);
+	if (err)
+		return err;
+
+	merge_key_ls.key_size = sub_flow1->meta.key_len;
+
+	merge_flow = nfp_flower_allocate_new(&merge_key_ls);
+	if (!merge_flow)
+		return -ENOMEM;
+
+	merge_flow->tc_flower_cookie = (unsigned long)merge_flow;
+	merge_flow->ingress_dev = sub_flow1->ingress_dev;
+
+	memcpy(merge_flow->unmasked_data, sub_flow1->unmasked_data,
+	       sub_flow1->meta.key_len);
+	memcpy(merge_flow->mask_data, sub_flow1->mask_data,
+	       sub_flow1->meta.mask_len);
+
+	err = nfp_flower_merge_action(sub_flow1, sub_flow2, merge_flow);
+	if (err)
+		goto err_destroy_merge_flow;
+
+	err = nfp_flower_link_flows(merge_flow, sub_flow1);
+	if (err)
+		goto err_destroy_merge_flow;
+
+	err = nfp_flower_link_flows(merge_flow, sub_flow2);
+	if (err)
+		goto err_unlink_sub_flow1;
+
+	merge_tc_off.cookie = merge_flow->tc_flower_cookie;
+	err = nfp_compile_flow_metadata(app, &merge_tc_off, merge_flow,
+					merge_flow->ingress_dev, extack);
+	if (err)
+		goto err_unlink_sub_flow2;
+
+	err = rhashtable_insert_fast(&priv->flow_table, &merge_flow->fl_node,
+				     nfp_flower_table_params);
+	if (err)
+		goto err_release_metadata;
+
+	err = nfp_flower_xmit_flow(app, merge_flow,
+				   NFP_FLOWER_CMSG_TYPE_FLOW_MOD);
+	if (err)
+		goto err_remove_rhash;
+
+	merge_flow->in_hw = true;
+	sub_flow1->in_hw = false;
+
+	return 0;
+
+err_remove_rhash:
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
+					    &merge_flow->fl_node,
+					    nfp_flower_table_params));
+err_release_metadata:
+	nfp_modify_flow_metadata(app, merge_flow);
+err_unlink_sub_flow2:
+	nfp_flower_unlink_flows(merge_flow, sub_flow2);
+err_unlink_sub_flow1:
+	nfp_flower_unlink_flows(merge_flow, sub_flow1);
+err_destroy_merge_flow:
+	kfree(merge_flow->action_data);
+	kfree(merge_flow->mask_data);
+	kfree(merge_flow->unmasked_data);
+	kfree(merge_flow);
+	return err;
+}
+
 /**
  * nfp_flower_add_offload() - Adds a new flow to hardware.
  * @app:	Pointer to the APP handle
@@ -436,15 +956,17 @@ err_free_flow:
  */
 static int
 nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow)
+		       struct flow_cls_offload *flow)
 {
 	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
 	struct nfp_flower_priv *priv = app->priv;
+	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *flow_pay;
 	struct nfp_fl_key_ls *key_layer;
 	struct nfp_port *port = NULL;
 	int err;
 
+	extack = flow->common.extack;
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
@@ -453,7 +975,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 		return -ENOMEM;
 
 	err = nfp_flower_calculate_key_layers(app, netdev, key_layer, flow,
-					      &tun_type);
+					      &tun_type, extack);
 	if (err)
 		goto err_free_key_ls;
 
@@ -464,23 +986,25 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	}
 
 	err = nfp_flower_compile_flow_match(app, flow, key_layer, netdev,
-					    flow_pay, tun_type);
+					    flow_pay, tun_type, extack);
 	if (err)
 		goto err_destroy_flow;
 
-	err = nfp_flower_compile_action(app, flow, netdev, flow_pay);
+	err = nfp_flower_compile_action(app, flow, netdev, flow_pay, extack);
 	if (err)
 		goto err_destroy_flow;
 
-	err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev);
+	err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev, extack);
 	if (err)
 		goto err_destroy_flow;
 
 	flow_pay->tc_flower_cookie = flow->cookie;
 	err = rhashtable_insert_fast(&priv->flow_table, &flow_pay->fl_node,
 				     nfp_flower_table_params);
-	if (err)
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot insert flow into tables for offloads");
 		goto err_release_metadata;
+	}
 
 	err = nfp_flower_xmit_flow(app, flow_pay,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_ADD);
@@ -490,6 +1014,8 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (port)
 		port->tc_offload_cnt++;
 
+	flow_pay->in_hw = true;
+
 	/* Deallocate flow payload when flower rule has been destroyed. */
 	kfree(key_layer);
 
@@ -511,6 +1037,75 @@ err_free_key_ls:
 	return err;
 }
 
+static void
+nfp_flower_remove_merge_flow(struct nfp_app *app,
+			     struct nfp_fl_payload *del_sub_flow,
+			     struct nfp_fl_payload *merge_flow)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_fl_payload_link *link, *temp;
+	struct nfp_fl_payload *origin;
+	bool mod = false;
+	int err;
+
+	link = list_first_entry(&merge_flow->linked_flows,
+				struct nfp_fl_payload_link, merge_flow.list);
+	origin = link->sub_flow.flow;
+
+	/* Re-add rule the merge had overwritten if it has not been deleted. */
+	if (origin != del_sub_flow)
+		mod = true;
+
+	err = nfp_modify_flow_metadata(app, merge_flow);
+	if (err) {
+		nfp_flower_cmsg_warn(app, "Metadata fail for merge flow delete.\n");
+		goto err_free_links;
+	}
+
+	if (!mod) {
+		err = nfp_flower_xmit_flow(app, merge_flow,
+					   NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
+		if (err) {
+			nfp_flower_cmsg_warn(app, "Failed to delete merged flow.\n");
+			goto err_free_links;
+		}
+	} else {
+		__nfp_modify_flow_metadata(priv, origin);
+		err = nfp_flower_xmit_flow(app, origin,
+					   NFP_FLOWER_CMSG_TYPE_FLOW_MOD);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to revert merge flow.\n");
+		origin->in_hw = true;
+	}
+
+err_free_links:
+	/* Clean any links connected with the merged flow. */
+	list_for_each_entry_safe(link, temp, &merge_flow->linked_flows,
+				 merge_flow.list)
+		nfp_flower_unlink_flow(link);
+
+	kfree(merge_flow->action_data);
+	kfree(merge_flow->mask_data);
+	kfree(merge_flow->unmasked_data);
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
+					    &merge_flow->fl_node,
+					    nfp_flower_table_params));
+	kfree_rcu(merge_flow, rcu);
+}
+
+static void
+nfp_flower_del_linked_merge_flows(struct nfp_app *app,
+				  struct nfp_fl_payload *sub_flow)
+{
+	struct nfp_fl_payload_link *link, *temp;
+
+	/* Remove any merge flow formed from the deleted sub_flow. */
+	list_for_each_entry_safe(link, temp, &sub_flow->linked_flows,
+				 sub_flow.list)
+		nfp_flower_remove_merge_flow(app, sub_flow,
+					     link->merge_flow.flow);
+}
+
 /**
  * nfp_flower_del_offload() - Removes a flow from hardware.
  * @app:	Pointer to the APP handle
@@ -518,39 +1113,48 @@ err_free_key_ls:
  * @flow:	TC flower classifier offload structure
  *
  * Removes a flow from the repeated hash structure and clears the
- * action payload.
+ * action payload. Any flows merged from this are also deleted.
  *
  * Return: negative value on error, 0 if removed successfully.
  */
 static int
 nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow)
+		       struct flow_cls_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
+	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *nfp_flow;
 	struct nfp_port *port = NULL;
 	int err;
 
+	extack = flow->common.extack;
 	if (nfp_netdev_is_nfp_repr(netdev))
 		port = nfp_port_from_netdev(netdev);
 
 	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
-	if (!nfp_flow)
+	if (!nfp_flow) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot remove flow that does not exist");
 		return -ENOENT;
+	}
 
 	err = nfp_modify_flow_metadata(app, nfp_flow);
 	if (err)
-		goto err_free_flow;
+		goto err_free_merge_flow;
 
 	if (nfp_flow->nfp_tun_ipv4_addr)
 		nfp_tunnel_del_ipv4_off(app, nfp_flow->nfp_tun_ipv4_addr);
 
+	if (!nfp_flow->in_hw) {
+		err = 0;
+		goto err_free_merge_flow;
+	}
+
 	err = nfp_flower_xmit_flow(app, nfp_flow,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
-	if (err)
-		goto err_free_flow;
+	/* Fall through on error. */
 
-err_free_flow:
+err_free_merge_flow:
+	nfp_flower_del_linked_merge_flows(app, nfp_flow);
 	if (port)
 		port->tc_offload_cnt--;
 	kfree(nfp_flow->action_data);
@@ -563,6 +1167,52 @@ err_free_flow:
 	return err;
 }
 
+static void
+__nfp_flower_update_merge_stats(struct nfp_app *app,
+				struct nfp_fl_payload *merge_flow)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_fl_payload_link *link;
+	struct nfp_fl_payload *sub_flow;
+	u64 pkts, bytes, used;
+	u32 ctx_id;
+
+	ctx_id = be32_to_cpu(merge_flow->meta.host_ctx_id);
+	pkts = priv->stats[ctx_id].pkts;
+	/* Do not cycle subflows if no stats to distribute. */
+	if (!pkts)
+		return;
+	bytes = priv->stats[ctx_id].bytes;
+	used = priv->stats[ctx_id].used;
+
+	/* Reset stats for the merge flow. */
+	priv->stats[ctx_id].pkts = 0;
+	priv->stats[ctx_id].bytes = 0;
+
+	/* The merge flow has received stats updates from firmware.
+	 * Distribute these stats to all subflows that form the merge.
+	 * The stats will collected from TC via the subflows.
+	 */
+	list_for_each_entry(link, &merge_flow->linked_flows, merge_flow.list) {
+		sub_flow = link->sub_flow.flow;
+		ctx_id = be32_to_cpu(sub_flow->meta.host_ctx_id);
+		priv->stats[ctx_id].pkts += pkts;
+		priv->stats[ctx_id].bytes += bytes;
+		max_t(u64, priv->stats[ctx_id].used, used);
+	}
+}
+
+static void
+nfp_flower_update_merge_stats(struct nfp_app *app,
+			      struct nfp_fl_payload *sub_flow)
+{
+	struct nfp_fl_payload_link *link;
+
+	/* Get merge flows that the subflow forms to distribute their stats. */
+	list_for_each_entry(link, &sub_flow->linked_flows, sub_flow.list)
+		__nfp_flower_update_merge_stats(app, link->merge_flow.flow);
+}
+
 /**
  * nfp_flower_get_stats() - Populates flow stats obtained from hardware.
  * @app:	Pointer to the APP handle
@@ -576,22 +1226,29 @@ err_free_flow:
  */
 static int
 nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
-		     struct tc_cls_flower_offload *flow)
+		     struct flow_cls_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
+	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *nfp_flow;
 	u32 ctx_id;
 
+	extack = flow->common.extack;
 	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
-	if (!nfp_flow)
+	if (!nfp_flow) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot dump stats for flow that does not exist");
 		return -EINVAL;
+	}
 
 	ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
 
 	spin_lock_bh(&priv->stats_lock);
-	tcf_exts_stats_update(flow->exts, priv->stats[ctx_id].bytes,
-			      priv->stats[ctx_id].pkts,
-			      priv->stats[ctx_id].used);
+	/* If request is for a sub_flow, update stats from merged flows. */
+	if (!list_empty(&nfp_flow->linked_flows))
+		nfp_flower_update_merge_stats(app, nfp_flow);
+
+	flow_stats_update(&flow->stats, priv->stats[ctx_id].bytes,
+			  priv->stats[ctx_id].pkts, priv->stats[ctx_id].used);
 
 	priv->stats[ctx_id].pkts = 0;
 	priv->stats[ctx_id].bytes = 0;
@@ -602,17 +1259,17 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
 
 static int
 nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
-			struct tc_cls_flower_offload *flower)
+			struct flow_cls_offload *flower)
 {
 	if (!eth_proto_is_802_3(flower->common.protocol))
 		return -EOPNOTSUPP;
 
 	switch (flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return nfp_flower_add_offload(app, netdev, flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return nfp_flower_del_offload(app, netdev, flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return nfp_flower_get_stats(app, netdev, flower);
 	default:
 		return -EOPNOTSUPP;
@@ -631,28 +1288,53 @@ static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type,
 	case TC_SETUP_CLSFLOWER:
 		return nfp_flower_repr_offload(repr->app, repr->netdev,
 					       type_data);
+	case TC_SETUP_CLSMATCHALL:
+		return nfp_flower_setup_qos_offload(repr->app, repr->netdev,
+						    type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
+static LIST_HEAD(nfp_block_cb_list);
+
 static int nfp_flower_setup_tc_block(struct net_device *netdev,
-				     struct tc_block_offload *f)
+				     struct flow_block_offload *f)
 {
 	struct nfp_repr *repr = netdev_priv(netdev);
+	struct nfp_flower_repr_priv *repr_priv;
+	struct flow_block_cb *block_cb;
 
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	repr_priv = repr->app_priv;
+	repr_priv->block_shared = f->block_shared;
+	f->driver_block_list = &nfp_block_cb_list;
+
 	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     nfp_flower_setup_tc_block_cb,
-					     repr, repr, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block,
-					nfp_flower_setup_tc_block_cb,
-					repr);
+	case FLOW_BLOCK_BIND:
+		if (flow_block_cb_is_busy(nfp_flower_setup_tc_block_cb, repr,
+					  &nfp_block_cb_list))
+			return -EBUSY;
+
+		block_cb = flow_block_cb_alloc(f->net,
+					       nfp_flower_setup_tc_block_cb,
+					       repr, repr, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &nfp_block_cb_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
+		block_cb = flow_block_cb_lookup(f, nfp_flower_setup_tc_block_cb,
+						repr);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -697,7 +1379,7 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 					  void *type_data, void *cb_priv)
 {
 	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
-	struct tc_cls_flower_offload *flower = type_data;
+	struct flow_cls_offload *flower = type_data;
 
 	if (flower->common.chain_index)
 		return -EOPNOTSUPP;
@@ -711,19 +1393,29 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 	}
 }
 
+static void nfp_flower_setup_indr_tc_release(void *cb_priv)
+{
+	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
+
+	list_del(&priv->list);
+	kfree(priv);
+}
+
 static int
 nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
-			       struct tc_block_offload *f)
+			       struct flow_block_offload *f)
 {
 	struct nfp_flower_indr_block_cb_priv *cb_priv;
 	struct nfp_flower_priv *priv = app->priv;
-	int err;
+	struct flow_block_cb *block_cb;
 
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
+	    !(f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
+	      nfp_flower_internal_port_can_offload(app, netdev)))
 		return -EOPNOTSUPP;
 
 	switch (f->command) {
-	case TC_BLOCK_BIND:
+	case FLOW_BLOCK_BIND:
 		cb_priv = kmalloc(sizeof(*cb_priv), GFP_KERNEL);
 		if (!cb_priv)
 			return -ENOMEM;
@@ -732,26 +1424,32 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 		cb_priv->app = app;
 		list_add(&cb_priv->list, &priv->indr_block_cb_priv);
 
-		err = tcf_block_cb_register(f->block,
-					    nfp_flower_setup_indr_block_cb,
-					    cb_priv, cb_priv, f->extack);
-		if (err) {
+		block_cb = flow_block_cb_alloc(f->net,
+					       nfp_flower_setup_indr_block_cb,
+					       cb_priv, cb_priv,
+					       nfp_flower_setup_indr_tc_release);
+		if (IS_ERR(block_cb)) {
 			list_del(&cb_priv->list);
 			kfree(cb_priv);
+			return PTR_ERR(block_cb);
 		}
 
-		return err;
-	case TC_BLOCK_UNBIND:
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &nfp_block_cb_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
 		cb_priv = nfp_flower_indr_block_cb_priv_lookup(app, netdev);
 		if (!cb_priv)
 			return -ENOENT;
 
-		tcf_block_cb_unregister(f->block,
-					nfp_flower_setup_indr_block_cb,
-					cb_priv);
-		list_del(&cb_priv->list);
-		kfree(cb_priv);
+		block_cb = flow_block_cb_lookup(f,
+						nfp_flower_setup_indr_block_cb,
+						cb_priv);
+		if (!block_cb)
+			return -ENOENT;
 
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
new file mode 100644
index 000000000000..86e968cd5ffd
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <linux/math64.h>
+#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
+
+#include "cmsg.h"
+#include "main.h"
+#include "../nfp_port.h"
+
+#define NFP_FL_QOS_UPDATE		msecs_to_jiffies(1000)
+
+struct nfp_police_cfg_head {
+	__be32 flags_opts;
+	__be32 port;
+};
+
+/* Police cmsg for configuring a trTCM traffic conditioner (8W/32B)
+ * See RFC 2698 for more details.
+ * ----------------------------------------------------------------
+ *    3                   2                   1
+ *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                          Flag options                         |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                          Port Ingress                         |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                        Token Bucket Peak                      |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                     Token Bucket Committed                    |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                         Peak Burst Size                       |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                      Committed Burst Size                     |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                      Peak Information Rate                    |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                    Committed Information Rate                 |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+struct nfp_police_config {
+	struct nfp_police_cfg_head head;
+	__be32 bkt_tkn_p;
+	__be32 bkt_tkn_c;
+	__be32 pbs;
+	__be32 cbs;
+	__be32 pir;
+	__be32 cir;
+};
+
+struct nfp_police_stats_reply {
+	struct nfp_police_cfg_head head;
+	__be64 pass_bytes;
+	__be64 pass_pkts;
+	__be64 drop_bytes;
+	__be64 drop_pkts;
+};
+
+static int
+nfp_flower_install_rate_limiter(struct nfp_app *app, struct net_device *netdev,
+				struct tc_cls_matchall_offload *flow,
+				struct netlink_ext_ack *extack)
+{
+	struct flow_action_entry *action = &flow->rule->action.entries[0];
+	struct nfp_flower_priv *fl_priv = app->priv;
+	struct nfp_flower_repr_priv *repr_priv;
+	struct nfp_police_config *config;
+	struct nfp_repr *repr;
+	struct sk_buff *skb;
+	u32 netdev_port_id;
+	u64 burst, rate;
+
+	if (!nfp_netdev_is_nfp_repr(netdev)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload not supported on higher level port");
+		return -EOPNOTSUPP;
+	}
+	repr = netdev_priv(netdev);
+	repr_priv = repr->app_priv;
+
+	if (repr_priv->block_shared) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload not supported on shared blocks");
+		return -EOPNOTSUPP;
+	}
+
+	if (repr->port->type != NFP_PORT_VF_PORT) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload not supported on non-VF ports");
+		return -EOPNOTSUPP;
+	}
+
+	if (!flow_offload_has_one_action(&flow->rule->action)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload requires a single action");
+		return -EOPNOTSUPP;
+	}
+
+	if (flow->common.prio != (1 << 16)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload requires highest priority");
+		return -EOPNOTSUPP;
+	}
+
+	if (action->id != FLOW_ACTION_POLICE) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload requires police action");
+		return -EOPNOTSUPP;
+	}
+
+	rate = action->police.rate_bytes_ps;
+	burst = div_u64(rate * PSCHED_NS2TICKS(action->police.burst),
+			PSCHED_TICKS_PER_SEC);
+	netdev_port_id = nfp_repr_get_port_id(netdev);
+
+	skb = nfp_flower_cmsg_alloc(repr->app, sizeof(struct nfp_police_config),
+				    NFP_FLOWER_CMSG_TYPE_QOS_MOD, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	config = nfp_flower_cmsg_get_data(skb);
+	memset(config, 0, sizeof(struct nfp_police_config));
+	config->head.port = cpu_to_be32(netdev_port_id);
+	config->bkt_tkn_p = cpu_to_be32(burst);
+	config->bkt_tkn_c = cpu_to_be32(burst);
+	config->pbs = cpu_to_be32(burst);
+	config->cbs = cpu_to_be32(burst);
+	config->pir = cpu_to_be32(rate);
+	config->cir = cpu_to_be32(rate);
+	nfp_ctrl_tx(repr->app->ctrl, skb);
+
+	repr_priv->qos_table.netdev_port_id = netdev_port_id;
+	fl_priv->qos_rate_limiters++;
+	if (fl_priv->qos_rate_limiters == 1)
+		schedule_delayed_work(&fl_priv->qos_stats_work,
+				      NFP_FL_QOS_UPDATE);
+
+	return 0;
+}
+
+static int
+nfp_flower_remove_rate_limiter(struct nfp_app *app, struct net_device *netdev,
+			       struct tc_cls_matchall_offload *flow,
+			       struct netlink_ext_ack *extack)
+{
+	struct nfp_flower_priv *fl_priv = app->priv;
+	struct nfp_flower_repr_priv *repr_priv;
+	struct nfp_police_config *config;
+	struct nfp_repr *repr;
+	struct sk_buff *skb;
+	u32 netdev_port_id;
+
+	if (!nfp_netdev_is_nfp_repr(netdev)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload not supported on higher level port");
+		return -EOPNOTSUPP;
+	}
+	repr = netdev_priv(netdev);
+
+	netdev_port_id = nfp_repr_get_port_id(netdev);
+	repr_priv = repr->app_priv;
+
+	if (!repr_priv->qos_table.netdev_port_id) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: cannot remove qos entry that does not exist");
+		return -EOPNOTSUPP;
+	}
+
+	skb = nfp_flower_cmsg_alloc(repr->app, sizeof(struct nfp_police_config),
+				    NFP_FLOWER_CMSG_TYPE_QOS_DEL, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	/* Clear all qos associate data for this interface */
+	memset(&repr_priv->qos_table, 0, sizeof(struct nfp_fl_qos));
+	fl_priv->qos_rate_limiters--;
+	if (!fl_priv->qos_rate_limiters)
+		cancel_delayed_work_sync(&fl_priv->qos_stats_work);
+
+	config = nfp_flower_cmsg_get_data(skb);
+	memset(config, 0, sizeof(struct nfp_police_config));
+	config->head.port = cpu_to_be32(netdev_port_id);
+	nfp_ctrl_tx(repr->app->ctrl, skb);
+
+	return 0;
+}
+
+void nfp_flower_stats_rlim_reply(struct nfp_app *app, struct sk_buff *skb)
+{
+	struct nfp_flower_priv *fl_priv = app->priv;
+	struct nfp_flower_repr_priv *repr_priv;
+	struct nfp_police_stats_reply *msg;
+	struct nfp_stat_pair *curr_stats;
+	struct nfp_stat_pair *prev_stats;
+	struct net_device *netdev;
+	struct nfp_repr *repr;
+	u32 netdev_port_id;
+
+	msg = nfp_flower_cmsg_get_data(skb);
+	netdev_port_id = be32_to_cpu(msg->head.port);
+	rcu_read_lock();
+	netdev = nfp_app_dev_get(app, netdev_port_id, NULL);
+	if (!netdev)
+		goto exit_unlock_rcu;
+
+	repr = netdev_priv(netdev);
+	repr_priv = repr->app_priv;
+	curr_stats = &repr_priv->qos_table.curr_stats;
+	prev_stats = &repr_priv->qos_table.prev_stats;
+
+	spin_lock_bh(&fl_priv->qos_stats_lock);
+	curr_stats->pkts = be64_to_cpu(msg->pass_pkts) +
+			   be64_to_cpu(msg->drop_pkts);
+	curr_stats->bytes = be64_to_cpu(msg->pass_bytes) +
+			    be64_to_cpu(msg->drop_bytes);
+
+	if (!repr_priv->qos_table.last_update) {
+		prev_stats->pkts = curr_stats->pkts;
+		prev_stats->bytes = curr_stats->bytes;
+	}
+
+	repr_priv->qos_table.last_update = jiffies;
+	spin_unlock_bh(&fl_priv->qos_stats_lock);
+
+exit_unlock_rcu:
+	rcu_read_unlock();
+}
+
+static void
+nfp_flower_stats_rlim_request(struct nfp_flower_priv *fl_priv,
+			      u32 netdev_port_id)
+{
+	struct nfp_police_cfg_head *head;
+	struct sk_buff *skb;
+
+	skb = nfp_flower_cmsg_alloc(fl_priv->app,
+				    sizeof(struct nfp_police_cfg_head),
+				    NFP_FLOWER_CMSG_TYPE_QOS_STATS,
+				    GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	head = nfp_flower_cmsg_get_data(skb);
+	memset(head, 0, sizeof(struct nfp_police_cfg_head));
+	head->port = cpu_to_be32(netdev_port_id);
+
+	nfp_ctrl_tx(fl_priv->app->ctrl, skb);
+}
+
+static void
+nfp_flower_stats_rlim_request_all(struct nfp_flower_priv *fl_priv)
+{
+	struct nfp_reprs *repr_set;
+	int i;
+
+	rcu_read_lock();
+	repr_set = rcu_dereference(fl_priv->app->reprs[NFP_REPR_TYPE_VF]);
+	if (!repr_set)
+		goto exit_unlock_rcu;
+
+	for (i = 0; i < repr_set->num_reprs; i++) {
+		struct net_device *netdev;
+
+		netdev = rcu_dereference(repr_set->reprs[i]);
+		if (netdev) {
+			struct nfp_repr *priv = netdev_priv(netdev);
+			struct nfp_flower_repr_priv *repr_priv;
+			u32 netdev_port_id;
+
+			repr_priv = priv->app_priv;
+			netdev_port_id = repr_priv->qos_table.netdev_port_id;
+			if (!netdev_port_id)
+				continue;
+
+			nfp_flower_stats_rlim_request(fl_priv, netdev_port_id);
+		}
+	}
+
+exit_unlock_rcu:
+	rcu_read_unlock();
+}
+
+static void update_stats_cache(struct work_struct *work)
+{
+	struct delayed_work *delayed_work;
+	struct nfp_flower_priv *fl_priv;
+
+	delayed_work = to_delayed_work(work);
+	fl_priv = container_of(delayed_work, struct nfp_flower_priv,
+			       qos_stats_work);
+
+	nfp_flower_stats_rlim_request_all(fl_priv);
+	schedule_delayed_work(&fl_priv->qos_stats_work, NFP_FL_QOS_UPDATE);
+}
+
+static int
+nfp_flower_stats_rate_limiter(struct nfp_app *app, struct net_device *netdev,
+			      struct tc_cls_matchall_offload *flow,
+			      struct netlink_ext_ack *extack)
+{
+	struct nfp_flower_priv *fl_priv = app->priv;
+	struct nfp_flower_repr_priv *repr_priv;
+	struct nfp_stat_pair *curr_stats;
+	struct nfp_stat_pair *prev_stats;
+	u64 diff_bytes, diff_pkts;
+	struct nfp_repr *repr;
+
+	if (!nfp_netdev_is_nfp_repr(netdev)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload not supported on higher level port");
+		return -EOPNOTSUPP;
+	}
+	repr = netdev_priv(netdev);
+
+	repr_priv = repr->app_priv;
+	if (!repr_priv->qos_table.netdev_port_id) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: cannot find qos entry for stats update");
+		return -EOPNOTSUPP;
+	}
+
+	spin_lock_bh(&fl_priv->qos_stats_lock);
+	curr_stats = &repr_priv->qos_table.curr_stats;
+	prev_stats = &repr_priv->qos_table.prev_stats;
+	diff_pkts = curr_stats->pkts - prev_stats->pkts;
+	diff_bytes = curr_stats->bytes - prev_stats->bytes;
+	prev_stats->pkts = curr_stats->pkts;
+	prev_stats->bytes = curr_stats->bytes;
+	spin_unlock_bh(&fl_priv->qos_stats_lock);
+
+	flow_stats_update(&flow->stats, diff_bytes, diff_pkts,
+			  repr_priv->qos_table.last_update);
+	return 0;
+}
+
+void nfp_flower_qos_init(struct nfp_app *app)
+{
+	struct nfp_flower_priv *fl_priv = app->priv;
+
+	spin_lock_init(&fl_priv->qos_stats_lock);
+	INIT_DELAYED_WORK(&fl_priv->qos_stats_work, &update_stats_cache);
+}
+
+void nfp_flower_qos_cleanup(struct nfp_app *app)
+{
+	struct nfp_flower_priv *fl_priv = app->priv;
+
+	cancel_delayed_work_sync(&fl_priv->qos_stats_work);
+}
+
+int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev,
+				 struct tc_cls_matchall_offload *flow)
+{
+	struct netlink_ext_ack *extack = flow->common.extack;
+	struct nfp_flower_priv *fl_priv = app->priv;
+
+	if (!(fl_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM)) {
+		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: loaded firmware does not support qos rate limit offload");
+		return -EOPNOTSUPP;
+	}
+
+	switch (flow->command) {
+	case TC_CLSMATCHALL_REPLACE:
+		return nfp_flower_install_rate_limiter(app, netdev, flow,
+						       extack);
+	case TC_CLSMATCHALL_DESTROY:
+		return nfp_flower_remove_rate_limiter(app, netdev, flow,
+						      extack);
+	case TC_CLSMATCHALL_STATS:
+		return nfp_flower_stats_rate_limiter(app, netdev, flow,
+						     extack);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 2d9f26a725c2..a7a80f4b722a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -98,47 +98,51 @@ struct nfp_ipv4_addr_entry {
 	struct list_head list;
 };
 
-/**
- * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP
- * @reserved:	reserved for future use
- * @count:	number of MAC addresses in the message
- * @addresses.index:	index of MAC address in the lookup table
- * @addresses.addr:	interface MAC address
- * @addresses:	series of MACs to offload
- */
-struct nfp_tun_mac_addr {
-	__be16 reserved;
-	__be16 count;
-	struct index_mac_addr {
-		__be16 index;
-		u8 addr[ETH_ALEN];
-	} addresses[];
-};
+#define NFP_TUN_MAC_OFFLOAD_DEL_FLAG	0x2
 
 /**
- * struct nfp_tun_mac_offload_entry - list of MACs to offload
- * @index:	index of MAC address for offloading
+ * struct nfp_tun_mac_addr_offload - configure MAC address of tunnel EP on NFP
+ * @flags:	MAC address offload options
+ * @count:	number of MAC addresses in the message (should be 1)
+ * @index:	index of MAC address in the lookup table
  * @addr:	interface MAC address
- * @list:	list pointer
  */
-struct nfp_tun_mac_offload_entry {
+struct nfp_tun_mac_addr_offload {
+	__be16 flags;
+	__be16 count;
 	__be16 index;
 	u8 addr[ETH_ALEN];
-	struct list_head list;
+};
+
+enum nfp_flower_mac_offload_cmd {
+	NFP_TUNNEL_MAC_OFFLOAD_ADD =		0,
+	NFP_TUNNEL_MAC_OFFLOAD_DEL =		1,
+	NFP_TUNNEL_MAC_OFFLOAD_MOD =		2,
 };
 
 #define NFP_MAX_MAC_INDEX       0xff
 
 /**
- * struct nfp_tun_mac_non_nfp_idx - converts non NFP netdev ifindex to 8-bit id
- * @ifindex:	netdev ifindex of the device
- * @index:	index of netdevs mac on NFP
- * @list:	list pointer
+ * struct nfp_tun_offloaded_mac - hashtable entry for an offloaded MAC
+ * @ht_node:	Hashtable entry
+ * @addr:	Offloaded MAC address
+ * @index:	Offloaded index for given MAC address
+ * @ref_count:	Number of devs using this MAC address
+ * @repr_list:	List of reprs sharing this MAC address
  */
-struct nfp_tun_mac_non_nfp_idx {
-	int ifindex;
-	u8 index;
-	struct list_head list;
+struct nfp_tun_offloaded_mac {
+	struct rhash_head ht_node;
+	u8 addr[ETH_ALEN];
+	u16 index;
+	int ref_count;
+	struct list_head repr_list;
+};
+
+static const struct rhashtable_params offloaded_macs_params = {
+	.key_offset	= offsetof(struct nfp_tun_offloaded_mac, addr),
+	.head_offset	= offsetof(struct nfp_tun_offloaded_mac, ht_node),
+	.key_len	= ETH_ALEN,
+	.automatic_shrinking	= true,
 };
 
 void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
@@ -158,16 +162,16 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 	}
 
 	pay_len = nfp_flower_cmsg_get_data_len(skb);
-	if (pay_len != sizeof(struct nfp_tun_active_tuns) +
-	    sizeof(struct route_ip_info) * count) {
+	if (pay_len != struct_size(payload, tun_info, count)) {
 		nfp_flower_cmsg_warn(app, "Corruption in tunnel keep-alive message.\n");
 		return;
 	}
 
+	rcu_read_lock();
 	for (i = 0; i < count; i++) {
 		ipv4_addr = payload->tun_info[i].ipv4;
 		port = be32_to_cpu(payload->tun_info[i].egress_port);
-		netdev = nfp_app_repr_get(app, port);
+		netdev = nfp_app_dev_get(app, port, NULL);
 		if (!netdev)
 			continue;
 
@@ -179,6 +183,7 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 		neigh_event_send(n, NULL);
 		neigh_release(n);
 	}
+	rcu_read_unlock();
 }
 
 static int
@@ -205,15 +210,15 @@ static bool nfp_tun_has_route(struct nfp_app *app, __be32 ipv4_addr)
 	struct nfp_ipv4_route_entry *entry;
 	struct list_head *ptr, *storage;
 
-	spin_lock_bh(&priv->nfp_neigh_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	spin_lock_bh(&priv->tun.neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
 		if (entry->ipv4_addr == ipv4_addr) {
-			spin_unlock_bh(&priv->nfp_neigh_off_lock);
+			spin_unlock_bh(&priv->tun.neigh_off_lock);
 			return true;
 		}
 	}
-	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+	spin_unlock_bh(&priv->tun.neigh_off_lock);
 	return false;
 }
 
@@ -223,24 +228,24 @@ static void nfp_tun_add_route_to_cache(struct nfp_app *app, __be32 ipv4_addr)
 	struct nfp_ipv4_route_entry *entry;
 	struct list_head *ptr, *storage;
 
-	spin_lock_bh(&priv->nfp_neigh_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	spin_lock_bh(&priv->tun.neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
 		if (entry->ipv4_addr == ipv4_addr) {
-			spin_unlock_bh(&priv->nfp_neigh_off_lock);
+			spin_unlock_bh(&priv->tun.neigh_off_lock);
 			return;
 		}
 	}
 	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry) {
-		spin_unlock_bh(&priv->nfp_neigh_off_lock);
+		spin_unlock_bh(&priv->tun.neigh_off_lock);
 		nfp_flower_cmsg_warn(app, "Mem error when storing new route.\n");
 		return;
 	}
 
 	entry->ipv4_addr = ipv4_addr;
-	list_add_tail(&entry->list, &priv->nfp_neigh_off_list);
-	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+	list_add_tail(&entry->list, &priv->tun.neigh_off_list);
+	spin_unlock_bh(&priv->tun.neigh_off_lock);
 }
 
 static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
@@ -249,8 +254,8 @@ static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
 	struct nfp_ipv4_route_entry *entry;
 	struct list_head *ptr, *storage;
 
-	spin_lock_bh(&priv->nfp_neigh_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	spin_lock_bh(&priv->tun.neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
 		if (entry->ipv4_addr == ipv4_addr) {
 			list_del(&entry->list);
@@ -258,7 +263,7 @@ static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
 			break;
 		}
 	}
-	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+	spin_unlock_bh(&priv->tun.neigh_off_lock);
 }
 
 static void
@@ -266,9 +271,10 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
 		    struct flowi4 *flow, struct neighbour *neigh, gfp_t flag)
 {
 	struct nfp_tun_neigh payload;
+	u32 port_id;
 
-	/* Only offload representor IPv4s for now. */
-	if (!nfp_netdev_is_nfp_repr(netdev))
+	port_id = nfp_flower_get_port_id_from_netdev(app, netdev);
+	if (!port_id)
 		return;
 
 	memset(&payload, 0, sizeof(struct nfp_tun_neigh));
@@ -286,7 +292,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
 	payload.src_ipv4 = flow->saddr;
 	ether_addr_copy(payload.src_addr, netdev->dev_addr);
 	neigh_ha_snapshot(payload.dst_addr, neigh, netdev);
-	payload.port_id = cpu_to_be32(nfp_repr_get_port_id(netdev));
+	payload.port_id = cpu_to_be32(port_id);
 	/* Add destination of new route to NFP cache. */
 	nfp_tun_add_route_to_cache(app, payload.dst_ipv4);
 
@@ -326,7 +332,7 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
 	if (!nfp_netdev_is_nfp_repr(n->dev))
 		return NOTIFY_DONE;
 
-	app_priv = container_of(nb, struct nfp_flower_priv, nfp_tun_neigh_nb);
+	app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
 	app = app_priv->app;
 
 	/* Only concerned with changes to routes already added to NFP. */
@@ -362,9 +368,10 @@ void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
 
 	payload = nfp_flower_cmsg_get_data(skb);
 
-	netdev = nfp_app_repr_get(app, be32_to_cpu(payload->ingress_port));
+	rcu_read_lock();
+	netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL);
 	if (!netdev)
-		goto route_fail_warning;
+		goto fail_rcu_unlock;
 
 	flow.daddr = payload->ipv4_addr;
 	flow.flowi4_proto = IPPROTO_UDP;
@@ -374,21 +381,23 @@ void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb)
 	rt = ip_route_output_key(dev_net(netdev), &flow);
 	err = PTR_ERR_OR_ZERO(rt);
 	if (err)
-		goto route_fail_warning;
+		goto fail_rcu_unlock;
 #else
-	goto route_fail_warning;
+	goto fail_rcu_unlock;
 #endif
 
 	/* Get the neighbour entry for the lookup */
 	n = dst_neigh_lookup(&rt->dst, &flow.daddr);
 	ip_rt_put(rt);
 	if (!n)
-		goto route_fail_warning;
-	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_KERNEL);
+		goto fail_rcu_unlock;
+	nfp_tun_write_neigh(n->dev, app, &flow, n, GFP_ATOMIC);
 	neigh_release(n);
+	rcu_read_unlock();
 	return;
 
-route_fail_warning:
+fail_rcu_unlock:
+	rcu_read_unlock();
 	nfp_flower_cmsg_warn(app, "Requested route not found.\n");
 }
 
@@ -401,11 +410,11 @@ static void nfp_tun_write_ipv4_list(struct nfp_app *app)
 	int count;
 
 	memset(&payload, 0, sizeof(struct nfp_tun_ipv4_addr));
-	mutex_lock(&priv->nfp_ipv4_off_lock);
+	mutex_lock(&priv->tun.ipv4_off_lock);
 	count = 0;
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		if (count >= NFP_FL_IPV4_ADDRS_MAX) {
-			mutex_unlock(&priv->nfp_ipv4_off_lock);
+			mutex_unlock(&priv->tun.ipv4_off_lock);
 			nfp_flower_cmsg_warn(app, "IPv4 offload exceeds limit.\n");
 			return;
 		}
@@ -413,7 +422,7 @@ static void nfp_tun_write_ipv4_list(struct nfp_app *app)
 		payload.ipv4_addr[count++] = entry->ipv4_addr;
 	}
 	payload.count = cpu_to_be32(count);
-	mutex_unlock(&priv->nfp_ipv4_off_lock);
+	mutex_unlock(&priv->tun.ipv4_off_lock);
 
 	nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_IPS,
 				 sizeof(struct nfp_tun_ipv4_addr),
@@ -426,26 +435,26 @@ void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4)
 	struct nfp_ipv4_addr_entry *entry;
 	struct list_head *ptr, *storage;
 
-	mutex_lock(&priv->nfp_ipv4_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	mutex_lock(&priv->tun.ipv4_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
 		if (entry->ipv4_addr == ipv4) {
 			entry->ref_count++;
-			mutex_unlock(&priv->nfp_ipv4_off_lock);
+			mutex_unlock(&priv->tun.ipv4_off_lock);
 			return;
 		}
 	}
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry) {
-		mutex_unlock(&priv->nfp_ipv4_off_lock);
+		mutex_unlock(&priv->tun.ipv4_off_lock);
 		nfp_flower_cmsg_warn(app, "Mem error when offloading IP address.\n");
 		return;
 	}
 	entry->ipv4_addr = ipv4;
 	entry->ref_count = 1;
-	list_add_tail(&entry->list, &priv->nfp_ipv4_off_list);
-	mutex_unlock(&priv->nfp_ipv4_off_lock);
+	list_add_tail(&entry->list, &priv->tun.ipv4_off_list);
+	mutex_unlock(&priv->tun.ipv4_off_lock);
 
 	nfp_tun_write_ipv4_list(app);
 }
@@ -456,8 +465,8 @@ void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4)
 	struct nfp_ipv4_addr_entry *entry;
 	struct list_head *ptr, *storage;
 
-	mutex_lock(&priv->nfp_ipv4_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	mutex_lock(&priv->tun.ipv4_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
 		if (entry->ipv4_addr == ipv4) {
 			entry->ref_count--;
@@ -468,191 +477,357 @@ void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4)
 			break;
 		}
 	}
-	mutex_unlock(&priv->nfp_ipv4_off_lock);
+	mutex_unlock(&priv->tun.ipv4_off_lock);
 
 	nfp_tun_write_ipv4_list(app);
 }
 
-void nfp_tunnel_write_macs(struct nfp_app *app)
+static int
+__nfp_tunnel_offload_mac(struct nfp_app *app, u8 *mac, u16 idx, bool del)
 {
-	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_offload_entry *entry;
-	struct nfp_tun_mac_addr *payload;
-	struct list_head *ptr, *storage;
-	int mac_count, err, pay_size;
+	struct nfp_tun_mac_addr_offload payload;
 
-	mutex_lock(&priv->nfp_mac_off_lock);
-	if (!priv->nfp_mac_off_count) {
-		mutex_unlock(&priv->nfp_mac_off_lock);
-		return;
-	}
+	memset(&payload, 0, sizeof(payload));
 
-	pay_size = sizeof(struct nfp_tun_mac_addr) +
-		   sizeof(struct index_mac_addr) * priv->nfp_mac_off_count;
+	if (del)
+		payload.flags = cpu_to_be16(NFP_TUN_MAC_OFFLOAD_DEL_FLAG);
 
-	payload = kzalloc(pay_size, GFP_KERNEL);
-	if (!payload) {
-		mutex_unlock(&priv->nfp_mac_off_lock);
-		return;
-	}
+	/* FW supports multiple MACs per cmsg but restrict to single. */
+	payload.count = cpu_to_be16(1);
+	payload.index = cpu_to_be16(idx);
+	ether_addr_copy(payload.addr, mac);
 
-	payload->count = cpu_to_be16(priv->nfp_mac_off_count);
+	return nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_MAC,
+					sizeof(struct nfp_tun_mac_addr_offload),
+					&payload, GFP_KERNEL);
+}
 
-	mac_count = 0;
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
-				   list);
-		payload->addresses[mac_count].index = entry->index;
-		ether_addr_copy(payload->addresses[mac_count].addr,
-				entry->addr);
-		mac_count++;
-	}
+static bool nfp_tunnel_port_is_phy_repr(int port)
+{
+	if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
+	    NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT)
+		return true;
 
-	err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_MAC,
-				       pay_size, payload, GFP_KERNEL);
+	return false;
+}
 
-	kfree(payload);
+static u16 nfp_tunnel_get_mac_idx_from_phy_port_id(int port)
+{
+	return port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT;
+}
 
-	if (err) {
-		mutex_unlock(&priv->nfp_mac_off_lock);
-		/* Write failed so retain list for future retry. */
-		return;
-	}
+static u16 nfp_tunnel_get_global_mac_idx_from_ida(int id)
+{
+	return id << 8 | NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+}
+
+static int nfp_tunnel_get_ida_from_global_mac_idx(u16 nfp_mac_idx)
+{
+	return nfp_mac_idx >> 8;
+}
+
+static bool nfp_tunnel_is_mac_idx_global(u16 nfp_mac_idx)
+{
+	return (nfp_mac_idx & 0xff) == NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+}
+
+static struct nfp_tun_offloaded_mac *
+nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, u8 *mac)
+{
+	struct nfp_flower_priv *priv = app->priv;
+
+	return rhashtable_lookup_fast(&priv->tun.offloaded_macs, mac,
+				      offloaded_macs_params);
+}
+
+static void
+nfp_tunnel_offloaded_macs_inc_ref_and_link(struct nfp_tun_offloaded_mac *entry,
+					   struct net_device *netdev, bool mod)
+{
+	if (nfp_netdev_is_nfp_repr(netdev)) {
+		struct nfp_flower_repr_priv *repr_priv;
+		struct nfp_repr *repr;
+
+		repr = netdev_priv(netdev);
+		repr_priv = repr->app_priv;
 
-	/* If list was successfully offloaded, flush it. */
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
-				   list);
-		list_del(&entry->list);
-		kfree(entry);
+		/* If modifing MAC, remove repr from old list first. */
+		if (mod)
+			list_del(&repr_priv->mac_list);
+
+		list_add_tail(&repr_priv->mac_list, &entry->repr_list);
 	}
 
-	priv->nfp_mac_off_count = 0;
-	mutex_unlock(&priv->nfp_mac_off_lock);
+	entry->ref_count++;
 }
 
-static int nfp_tun_get_mac_idx(struct nfp_app *app, int ifindex)
+static int
+nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev,
+			  int port, bool mod)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_non_nfp_idx *entry;
-	struct list_head *ptr, *storage;
-	int idx;
-
-	mutex_lock(&priv->nfp_mac_index_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
-		if (entry->ifindex == ifindex) {
-			idx = entry->index;
-			mutex_unlock(&priv->nfp_mac_index_lock);
-			return idx;
-		}
+	int ida_idx = NFP_MAX_MAC_INDEX, err;
+	struct nfp_tun_offloaded_mac *entry;
+	u16 nfp_mac_idx = 0;
+
+	entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr);
+	if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) {
+		nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod);
+		return 0;
 	}
 
-	idx = ida_simple_get(&priv->nfp_mac_off_ids, 0,
-			     NFP_MAX_MAC_INDEX, GFP_KERNEL);
-	if (idx < 0) {
-		mutex_unlock(&priv->nfp_mac_index_lock);
-		return idx;
+	/* Assign a global index if non-repr or MAC address is now shared. */
+	if (entry || !port) {
+		ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0,
+					 NFP_MAX_MAC_INDEX, GFP_KERNEL);
+		if (ida_idx < 0)
+			return ida_idx;
+
+		nfp_mac_idx = nfp_tunnel_get_global_mac_idx_from_ida(ida_idx);
+	} else {
+		nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port);
 	}
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry) {
-		mutex_unlock(&priv->nfp_mac_index_lock);
-		return -ENOMEM;
+		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+		if (!entry) {
+			err = -ENOMEM;
+			goto err_free_ida;
+		}
+
+		ether_addr_copy(entry->addr, netdev->dev_addr);
+		INIT_LIST_HEAD(&entry->repr_list);
+
+		if (rhashtable_insert_fast(&priv->tun.offloaded_macs,
+					   &entry->ht_node,
+					   offloaded_macs_params)) {
+			err = -ENOMEM;
+			goto err_free_entry;
+		}
+	}
+
+	err = __nfp_tunnel_offload_mac(app, netdev->dev_addr,
+				       nfp_mac_idx, false);
+	if (err) {
+		/* If not shared then free. */
+		if (!entry->ref_count)
+			goto err_remove_hash;
+		goto err_free_ida;
 	}
-	entry->ifindex = ifindex;
-	entry->index = idx;
-	list_add_tail(&entry->list, &priv->nfp_mac_index_list);
-	mutex_unlock(&priv->nfp_mac_index_lock);
 
-	return idx;
+	entry->index = nfp_mac_idx;
+	nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod);
+
+	return 0;
+
+err_remove_hash:
+	rhashtable_remove_fast(&priv->tun.offloaded_macs, &entry->ht_node,
+			       offloaded_macs_params);
+err_free_entry:
+	kfree(entry);
+err_free_ida:
+	if (ida_idx != NFP_MAX_MAC_INDEX)
+		ida_simple_remove(&priv->tun.mac_off_ids, ida_idx);
+
+	return err;
 }
 
-static void nfp_tun_del_mac_idx(struct nfp_app *app, int ifindex)
+static int
+nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev,
+			  u8 *mac, bool mod)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_non_nfp_idx *entry;
-	struct list_head *ptr, *storage;
+	struct nfp_flower_repr_priv *repr_priv;
+	struct nfp_tun_offloaded_mac *entry;
+	struct nfp_repr *repr;
+	int ida_idx;
+
+	entry = nfp_tunnel_lookup_offloaded_macs(app, mac);
+	if (!entry)
+		return 0;
+
+	entry->ref_count--;
+	/* If del is part of a mod then mac_list is still in use elsewheree. */
+	if (nfp_netdev_is_nfp_repr(netdev) && !mod) {
+		repr = netdev_priv(netdev);
+		repr_priv = repr->app_priv;
+		list_del(&repr_priv->mac_list);
+	}
 
-	mutex_lock(&priv->nfp_mac_index_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
-		if (entry->ifindex == ifindex) {
-			ida_simple_remove(&priv->nfp_mac_off_ids,
-					  entry->index);
-			list_del(&entry->list);
-			kfree(entry);
-			break;
+	/* If MAC is now used by 1 repr set the offloaded MAC index to port. */
+	if (entry->ref_count == 1 && list_is_singular(&entry->repr_list)) {
+		u16 nfp_mac_idx;
+		int port, err;
+
+		repr_priv = list_first_entry(&entry->repr_list,
+					     struct nfp_flower_repr_priv,
+					     mac_list);
+		repr = repr_priv->nfp_repr;
+		port = nfp_repr_get_port_id(repr->netdev);
+		nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port);
+		err = __nfp_tunnel_offload_mac(app, mac, nfp_mac_idx, false);
+		if (err) {
+			nfp_flower_cmsg_warn(app, "MAC offload index revert failed on %s.\n",
+					     netdev_name(netdev));
+			return 0;
 		}
+
+		ida_idx = nfp_tunnel_get_ida_from_global_mac_idx(entry->index);
+		ida_simple_remove(&priv->tun.mac_off_ids, ida_idx);
+		entry->index = nfp_mac_idx;
+		return 0;
 	}
-	mutex_unlock(&priv->nfp_mac_index_lock);
-}
 
-static void nfp_tun_add_to_mac_offload_list(struct net_device *netdev,
-					    struct nfp_app *app)
-{
-	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_offload_entry *entry;
-	u16 nfp_mac_idx;
-	int port = 0;
+	if (entry->ref_count)
+		return 0;
 
-	/* Check if MAC should be offloaded. */
-	if (!is_valid_ether_addr(netdev->dev_addr))
-		return;
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->tun.offloaded_macs,
+					    &entry->ht_node,
+					    offloaded_macs_params));
+	/* If MAC has global ID then extract and free the ida entry. */
+	if (nfp_tunnel_is_mac_idx_global(entry->index)) {
+		ida_idx = nfp_tunnel_get_ida_from_global_mac_idx(entry->index);
+		ida_simple_remove(&priv->tun.mac_off_ids, ida_idx);
+	}
 
-	if (nfp_netdev_is_nfp_repr(netdev))
+	kfree(entry);
+
+	return __nfp_tunnel_offload_mac(app, mac, 0, true);
+}
+
+static int
+nfp_tunnel_offload_mac(struct nfp_app *app, struct net_device *netdev,
+		       enum nfp_flower_mac_offload_cmd cmd)
+{
+	struct nfp_flower_non_repr_priv *nr_priv = NULL;
+	bool non_repr = false, *mac_offloaded;
+	u8 *off_mac = NULL;
+	int err, port = 0;
+
+	if (nfp_netdev_is_nfp_repr(netdev)) {
+		struct nfp_flower_repr_priv *repr_priv;
+		struct nfp_repr *repr;
+
+		repr = netdev_priv(netdev);
+		if (repr->app != app)
+			return 0;
+
+		repr_priv = repr->app_priv;
+		mac_offloaded = &repr_priv->mac_offloaded;
+		off_mac = &repr_priv->offloaded_mac_addr[0];
 		port = nfp_repr_get_port_id(netdev);
-	else if (!nfp_fl_is_netdev_to_offload(netdev))
-		return;
+		if (!nfp_tunnel_port_is_phy_repr(port))
+			return 0;
+	} else if (nfp_fl_is_netdev_to_offload(netdev)) {
+		nr_priv = nfp_flower_non_repr_priv_get(app, netdev);
+		if (!nr_priv)
+			return -ENOMEM;
+
+		mac_offloaded = &nr_priv->mac_offloaded;
+		off_mac = &nr_priv->offloaded_mac_addr[0];
+		non_repr = true;
+	} else {
+		return 0;
+	}
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry) {
-		nfp_flower_cmsg_warn(app, "Mem fail when offloading MAC.\n");
-		return;
+	if (!is_valid_ether_addr(netdev->dev_addr)) {
+		err = -EINVAL;
+		goto err_put_non_repr_priv;
 	}
 
-	if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
-	    NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT) {
-		nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT;
-	} else if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
-		   NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT) {
-		port = FIELD_GET(NFP_FLOWER_CMSG_PORT_VNIC, port);
-		nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT;
-	} else {
-		/* Must assign our own unique 8-bit index. */
-		int idx = nfp_tun_get_mac_idx(app, netdev->ifindex);
+	if (cmd == NFP_TUNNEL_MAC_OFFLOAD_MOD && !*mac_offloaded)
+		cmd = NFP_TUNNEL_MAC_OFFLOAD_ADD;
 
-		if (idx < 0) {
-			nfp_flower_cmsg_warn(app, "Can't assign non-repr MAC index.\n");
-			kfree(entry);
-			return;
-		}
-		nfp_mac_idx = idx << 8 | NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+	switch (cmd) {
+	case NFP_TUNNEL_MAC_OFFLOAD_ADD:
+		err = nfp_tunnel_add_shared_mac(app, netdev, port, false);
+		if (err)
+			goto err_put_non_repr_priv;
+
+		if (non_repr)
+			__nfp_flower_non_repr_priv_get(nr_priv);
+
+		*mac_offloaded = true;
+		ether_addr_copy(off_mac, netdev->dev_addr);
+		break;
+	case NFP_TUNNEL_MAC_OFFLOAD_DEL:
+		/* Only attempt delete if add was successful. */
+		if (!*mac_offloaded)
+			break;
+
+		if (non_repr)
+			__nfp_flower_non_repr_priv_put(nr_priv);
+
+		*mac_offloaded = false;
+
+		err = nfp_tunnel_del_shared_mac(app, netdev, netdev->dev_addr,
+						false);
+		if (err)
+			goto err_put_non_repr_priv;
+
+		break;
+	case NFP_TUNNEL_MAC_OFFLOAD_MOD:
+		/* Ignore if changing to the same address. */
+		if (ether_addr_equal(netdev->dev_addr, off_mac))
+			break;
+
+		err = nfp_tunnel_add_shared_mac(app, netdev, port, true);
+		if (err)
+			goto err_put_non_repr_priv;
+
+		/* Delete the previous MAC address. */
+		err = nfp_tunnel_del_shared_mac(app, netdev, off_mac, true);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to remove offload of replaced MAC addr on %s.\n",
+					     netdev_name(netdev));
+
+		ether_addr_copy(off_mac, netdev->dev_addr);
+		break;
+	default:
+		err = -EINVAL;
+		goto err_put_non_repr_priv;
 	}
 
-	entry->index = cpu_to_be16(nfp_mac_idx);
-	ether_addr_copy(entry->addr, netdev->dev_addr);
+	if (non_repr)
+		__nfp_flower_non_repr_priv_put(nr_priv);
+
+	return 0;
+
+err_put_non_repr_priv:
+	if (non_repr)
+		__nfp_flower_non_repr_priv_put(nr_priv);
 
-	mutex_lock(&priv->nfp_mac_off_lock);
-	priv->nfp_mac_off_count++;
-	list_add_tail(&entry->list, &priv->nfp_mac_off_list);
-	mutex_unlock(&priv->nfp_mac_off_lock);
+	return err;
 }
 
 int nfp_tunnel_mac_event_handler(struct nfp_app *app,
 				 struct net_device *netdev,
 				 unsigned long event, void *ptr)
 {
-	if (event == NETDEV_DOWN || event == NETDEV_UNREGISTER) {
-		/* If non-nfp netdev then free its offload index. */
-		if (nfp_fl_is_netdev_to_offload(netdev))
-			nfp_tun_del_mac_idx(app, netdev->ifindex);
-	} else if (event == NETDEV_UP || event == NETDEV_CHANGEADDR ||
-		   event == NETDEV_REGISTER) {
-		nfp_tun_add_to_mac_offload_list(netdev, app);
-
-		/* Force a list write to keep NFP up to date. */
-		nfp_tunnel_write_macs(app);
+	int err;
+
+	if (event == NETDEV_DOWN) {
+		err = nfp_tunnel_offload_mac(app, netdev,
+					     NFP_TUNNEL_MAC_OFFLOAD_DEL);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to delete offload MAC on %s.\n",
+					     netdev_name(netdev));
+	} else if (event == NETDEV_UP) {
+		err = nfp_tunnel_offload_mac(app, netdev,
+					     NFP_TUNNEL_MAC_OFFLOAD_ADD);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to offload MAC on %s.\n",
+					     netdev_name(netdev));
+	} else if (event == NETDEV_CHANGEADDR) {
+		/* Only offload addr change if netdev is already up. */
+		if (!(netdev->flags & IFF_UP))
+			return NOTIFY_OK;
+
+		err = nfp_tunnel_offload_mac(app, netdev,
+					     NFP_TUNNEL_MAC_OFFLOAD_MOD);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to offload MAC change on %s.\n",
+					     netdev_name(netdev));
 	}
 	return NOTIFY_OK;
 }
@@ -660,68 +835,62 @@ int nfp_tunnel_mac_event_handler(struct nfp_app *app,
 int nfp_tunnel_config_start(struct nfp_app *app)
 {
 	struct nfp_flower_priv *priv = app->priv;
+	int err;
+
+	/* Initialise rhash for MAC offload tracking. */
+	err = rhashtable_init(&priv->tun.offloaded_macs,
+			      &offloaded_macs_params);
+	if (err)
+		return err;
 
-	/* Initialise priv data for MAC offloading. */
-	priv->nfp_mac_off_count = 0;
-	mutex_init(&priv->nfp_mac_off_lock);
-	INIT_LIST_HEAD(&priv->nfp_mac_off_list);
-	mutex_init(&priv->nfp_mac_index_lock);
-	INIT_LIST_HEAD(&priv->nfp_mac_index_list);
-	ida_init(&priv->nfp_mac_off_ids);
+	ida_init(&priv->tun.mac_off_ids);
 
 	/* Initialise priv data for IPv4 offloading. */
-	mutex_init(&priv->nfp_ipv4_off_lock);
-	INIT_LIST_HEAD(&priv->nfp_ipv4_off_list);
+	mutex_init(&priv->tun.ipv4_off_lock);
+	INIT_LIST_HEAD(&priv->tun.ipv4_off_list);
 
 	/* Initialise priv data for neighbour offloading. */
-	spin_lock_init(&priv->nfp_neigh_off_lock);
-	INIT_LIST_HEAD(&priv->nfp_neigh_off_list);
-	priv->nfp_tun_neigh_nb.notifier_call = nfp_tun_neigh_event_handler;
+	spin_lock_init(&priv->tun.neigh_off_lock);
+	INIT_LIST_HEAD(&priv->tun.neigh_off_list);
+	priv->tun.neigh_nb.notifier_call = nfp_tun_neigh_event_handler;
+
+	err = register_netevent_notifier(&priv->tun.neigh_nb);
+	if (err) {
+		rhashtable_free_and_destroy(&priv->tun.offloaded_macs,
+					    nfp_check_rhashtable_empty, NULL);
+		return err;
+	}
 
-	return register_netevent_notifier(&priv->nfp_tun_neigh_nb);
+	return 0;
 }
 
 void nfp_tunnel_config_stop(struct nfp_app *app)
 {
-	struct nfp_tun_mac_offload_entry *mac_entry;
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_ipv4_route_entry *route_entry;
-	struct nfp_tun_mac_non_nfp_idx *mac_idx;
 	struct nfp_ipv4_addr_entry *ip_entry;
 	struct list_head *ptr, *storage;
 
-	unregister_netevent_notifier(&priv->nfp_tun_neigh_nb);
-
-	/* Free any memory that may be occupied by MAC list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
-		mac_entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
-				       list);
-		list_del(&mac_entry->list);
-		kfree(mac_entry);
-	}
-
-	/* Free any memory that may be occupied by MAC index list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
-		mac_idx = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx,
-				     list);
-		list_del(&mac_idx->list);
-		kfree(mac_idx);
-	}
+	unregister_netevent_notifier(&priv->tun.neigh_nb);
 
-	ida_destroy(&priv->nfp_mac_off_ids);
+	ida_destroy(&priv->tun.mac_off_ids);
 
 	/* Free any memory that may be occupied by ipv4 list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		ip_entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
 		list_del(&ip_entry->list);
 		kfree(ip_entry);
 	}
 
 	/* Free any memory that may be occupied by the route list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		route_entry = list_entry(ptr, struct nfp_ipv4_route_entry,
 					 list);
 		list_del(&route_entry->list);
 		kfree(route_entry);
 	}
+
+	/* Destroy rhash. Entries should be cleaned on netdev notifier unreg. */
+	rhashtable_free_and_destroy(&priv->tun.offloaded_macs,
+				    nfp_check_rhashtable_empty, NULL);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index d578d856a009..76d13af46a7a 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -79,7 +79,7 @@ extern const struct nfp_app_type app_abm;
  * @eswitch_mode_set:    set SR-IOV eswitch mode (under pf->lock)
  * @sriov_enable: app-specific sriov initialisation
  * @sriov_disable: app-specific sriov clean-up
- * @repr_get:	get representor netdev
+ * @dev_get:	get representor or internal port representing netdev
  */
 struct nfp_app_type {
 	enum nfp_app_id id;
@@ -143,7 +143,8 @@ struct nfp_app_type {
 
 	enum devlink_eswitch_mode (*eswitch_mode_get)(struct nfp_app *app);
 	int (*eswitch_mode_set)(struct nfp_app *app, u16 mode);
-	struct net_device *(*repr_get)(struct nfp_app *app, u32 id);
+	struct net_device *(*dev_get)(struct nfp_app *app, u32 id,
+				      bool *redir_egress);
 };
 
 /**
@@ -397,12 +398,14 @@ static inline void nfp_app_sriov_disable(struct nfp_app *app)
 		app->type->sriov_disable(app);
 }
 
-static inline struct net_device *nfp_app_repr_get(struct nfp_app *app, u32 id)
+static inline
+struct net_device *nfp_app_dev_get(struct nfp_app *app, u32 id,
+				   bool *redir_egress)
 {
-	if (unlikely(!app || !app->type->repr_get))
+	if (unlikely(!app || !app->type->dev_get))
 		return NULL;
 
-	return app->type->repr_get(app, id);
+	return app->type->dev_get(app, id, redir_egress);
 }
 
 struct nfp_app *nfp_app_from_netdev(struct net_device *netdev);
@@ -433,4 +436,6 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
 int nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app,
 				   struct nfp_net *nn, unsigned int id);
 
+struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev);
+
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 808647ec3573..c50fce42f473 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -4,6 +4,7 @@
 #include <linux/rtnetlink.h>
 #include <net/devlink.h>
 
+#include "nfpcore/nfp.h"
 #include "nfpcore/nfp_nsp.h"
 #include "nfp_app.h"
 #include "nfp_main.h"
@@ -143,7 +144,8 @@ nfp_devlink_sb_pool_get(struct devlink *devlink, unsigned int sb_index,
 static int
 nfp_devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
 			u16 pool_index,
-			u32 size, enum devlink_sb_threshold_type threshold_type)
+			u32 size, enum devlink_sb_threshold_type threshold_type,
+			struct netlink_ext_ack *extack)
 {
 	struct nfp_pf *pf = devlink_priv(devlink);
 
@@ -171,6 +173,173 @@ static int nfp_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	return ret;
 }
 
+static const struct nfp_devlink_versions_simple {
+	const char *key;
+	const char *hwinfo;
+} nfp_devlink_versions_hwinfo[] = {
+	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,	"assembly.partno", },
+	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_REV,	"assembly.revision", },
+	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE, "assembly.vendor", },
+	{ "board.model", /* code name */		"assembly.model", },
+};
+
+static int
+nfp_devlink_versions_get_hwinfo(struct nfp_pf *pf, struct devlink_info_req *req)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < ARRAY_SIZE(nfp_devlink_versions_hwinfo); i++) {
+		const struct nfp_devlink_versions_simple *info;
+		const char *val;
+
+		info = &nfp_devlink_versions_hwinfo[i];
+
+		val = nfp_hwinfo_lookup(pf->hwinfo, info->hwinfo);
+		if (!val)
+			continue;
+
+		err = devlink_info_version_fixed_put(req, info->key, val);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static const struct nfp_devlink_versions {
+	enum nfp_nsp_versions id;
+	const char *key;
+} nfp_devlink_versions_nsp[] = {
+	{ NFP_VERSIONS_BUNDLE,	"fw.bundle_id", },
+	{ NFP_VERSIONS_BSP,	DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, },
+	{ NFP_VERSIONS_CPLD,	"fw.cpld", },
+	{ NFP_VERSIONS_APP,	DEVLINK_INFO_VERSION_GENERIC_FW_APP, },
+	{ NFP_VERSIONS_UNDI,	DEVLINK_INFO_VERSION_GENERIC_FW_UNDI, },
+	{ NFP_VERSIONS_NCSI,	DEVLINK_INFO_VERSION_GENERIC_FW_NCSI, },
+	{ NFP_VERSIONS_CFGR,	"chip.init", },
+};
+
+static int
+nfp_devlink_versions_get_nsp(struct devlink_info_req *req, bool flash,
+			     const u8 *buf, unsigned int size)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < ARRAY_SIZE(nfp_devlink_versions_nsp); i++) {
+		const struct nfp_devlink_versions *info;
+		const char *version;
+
+		info = &nfp_devlink_versions_nsp[i];
+
+		version = nfp_nsp_versions_get(info->id, flash, buf, size);
+		if (IS_ERR(version)) {
+			if (PTR_ERR(version) == -ENOENT)
+				continue;
+			else
+				return PTR_ERR(version);
+		}
+
+		if (flash)
+			err = devlink_info_version_stored_put(req, info->key,
+							      version);
+		else
+			err = devlink_info_version_running_put(req, info->key,
+							       version);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int
+nfp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
+		     struct netlink_ext_ack *extack)
+{
+	struct nfp_pf *pf = devlink_priv(devlink);
+	const char *sn, *vendor, *part;
+	struct nfp_nsp *nsp;
+	char *buf = NULL;
+	int err;
+
+	err = devlink_info_driver_name_put(req, "nfp");
+	if (err)
+		return err;
+
+	vendor = nfp_hwinfo_lookup(pf->hwinfo, "assembly.vendor");
+	part = nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno");
+	sn = nfp_hwinfo_lookup(pf->hwinfo, "assembly.serial");
+	if (vendor && part && sn) {
+		char *buf;
+
+		buf = kmalloc(strlen(vendor) + strlen(part) + strlen(sn) + 1,
+			      GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		buf[0] = '\0';
+		strcat(buf, vendor);
+		strcat(buf, part);
+		strcat(buf, sn);
+
+		err = devlink_info_serial_number_put(req, buf);
+		kfree(buf);
+		if (err)
+			return err;
+	}
+
+	nsp = nfp_nsp_open(pf->cpp);
+	if (IS_ERR(nsp)) {
+		NL_SET_ERR_MSG_MOD(extack, "can't access NSP");
+		return PTR_ERR(nsp);
+	}
+
+	if (nfp_nsp_has_versions(nsp)) {
+		buf = kzalloc(NFP_NSP_VERSION_BUFSZ, GFP_KERNEL);
+		if (!buf) {
+			err = -ENOMEM;
+			goto err_close_nsp;
+		}
+
+		err = nfp_nsp_versions(nsp, buf, NFP_NSP_VERSION_BUFSZ);
+		if (err)
+			goto err_free_buf;
+
+		err = nfp_devlink_versions_get_nsp(req, false,
+						   buf, NFP_NSP_VERSION_BUFSZ);
+		if (err)
+			goto err_free_buf;
+
+		err = nfp_devlink_versions_get_nsp(req, true,
+						   buf, NFP_NSP_VERSION_BUFSZ);
+		if (err)
+			goto err_free_buf;
+
+		kfree(buf);
+	}
+
+	nfp_nsp_close(nsp);
+
+	return nfp_devlink_versions_get_hwinfo(pf, req);
+
+err_free_buf:
+	kfree(buf);
+err_close_nsp:
+	nfp_nsp_close(nsp);
+	return err;
+}
+
+static int
+nfp_devlink_flash_update(struct devlink *devlink, const char *path,
+			 const char *component, struct netlink_ext_ack *extack)
+{
+	if (component)
+		return -EOPNOTSUPP;
+	return nfp_flash_update_common(devlink_priv(devlink), path, extack);
+}
+
 const struct devlink_ops nfp_devlink_ops = {
 	.port_split		= nfp_devlink_port_split,
 	.port_unsplit		= nfp_devlink_port_unsplit,
@@ -178,12 +347,16 @@ const struct devlink_ops nfp_devlink_ops = {
 	.sb_pool_set		= nfp_devlink_sb_pool_set,
 	.eswitch_mode_get	= nfp_devlink_eswitch_mode_get,
 	.eswitch_mode_set	= nfp_devlink_eswitch_mode_set,
+	.info_get		= nfp_devlink_info_get,
+	.flash_update		= nfp_devlink_flash_update,
 };
 
 int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
 {
 	struct nfp_eth_table_port eth_port;
 	struct devlink *devlink;
+	const u8 *serial;
+	int serial_len;
 	int ret;
 
 	rtnl_lock();
@@ -192,10 +365,10 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
 	if (ret)
 		return ret;
 
-	devlink_port_type_eth_set(&port->dl_port, port->netdev);
+	serial_len = nfp_cpp_serial(port->app->cpp, &serial);
 	devlink_port_attrs_set(&port->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
 			       eth_port.label_port, eth_port.is_split,
-			       eth_port.label_subport);
+			       eth_port.label_subport, serial, serial_len);
 
 	devlink = priv_to_devlink(app->pf);
 
@@ -206,3 +379,24 @@ void nfp_devlink_port_unregister(struct nfp_port *port)
 {
 	devlink_port_unregister(&port->dl_port);
 }
+
+void nfp_devlink_port_type_eth_set(struct nfp_port *port)
+{
+	devlink_port_type_eth_set(&port->dl_port, port->netdev);
+}
+
+void nfp_devlink_port_type_clear(struct nfp_port *port)
+{
+	devlink_port_type_clear(&port->dl_port);
+}
+
+struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev)
+{
+	struct nfp_port *port;
+
+	port = nfp_port_from_netdev(netdev);
+	if (!port)
+		return NULL;
+
+	return &port->dl_port;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 6c10e8d119e4..60e57f08de80 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -294,12 +294,56 @@ static int nfp_pcie_sriov_disable(struct pci_dev *pdev)
 
 static int nfp_pcie_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
+	if (!pci_get_drvdata(pdev))
+		return -ENOENT;
+
 	if (num_vfs == 0)
 		return nfp_pcie_sriov_disable(pdev);
 	else
 		return nfp_pcie_sriov_enable(pdev, num_vfs);
 }
 
+int nfp_flash_update_common(struct nfp_pf *pf, const char *path,
+			    struct netlink_ext_ack *extack)
+{
+	struct device *dev = &pf->pdev->dev;
+	const struct firmware *fw;
+	struct nfp_nsp *nsp;
+	int err;
+
+	nsp = nfp_nsp_open(pf->cpp);
+	if (IS_ERR(nsp)) {
+		err = PTR_ERR(nsp);
+		if (extack)
+			NL_SET_ERR_MSG_MOD(extack, "can't access NSP");
+		else
+			dev_err(dev, "Failed to access the NSP: %d\n", err);
+		return err;
+	}
+
+	err = request_firmware_direct(&fw, path, dev);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "unable to read flash file from disk");
+		goto exit_close_nsp;
+	}
+
+	dev_info(dev, "Please be patient while writing flash image: %s\n",
+		 path);
+
+	err = nfp_nsp_write_flash(nsp, fw);
+	if (err < 0)
+		goto exit_release_fw;
+	dev_info(dev, "Finished writing flash image\n");
+	err = 0;
+
+exit_release_fw:
+	release_firmware(fw);
+exit_close_nsp:
+	nfp_nsp_close(nsp);
+	return err;
+}
+
 static const struct firmware *
 nfp_net_fw_request(struct pci_dev *pdev, struct nfp_pf *pf, const char *name)
 {
@@ -552,6 +596,10 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 	struct nfp_pf *pf;
 	int err;
 
+	if (pdev->vendor == PCI_VENDOR_ID_NETRONOME &&
+	    pdev->device == PCI_DEVICE_ID_NETRONOME_NFP6000_VF)
+		dev_warn(&pdev->dev, "Binding NFP VF device to the NFP PF driver, the VF driver is called 'nfp_netvf'\n");
+
 	err = pci_enable_device(pdev);
 	if (err < 0)
 		return err;
@@ -679,9 +727,13 @@ err_pci_disable:
 	return err;
 }
 
-static void nfp_pci_remove(struct pci_dev *pdev)
+static void __nfp_pci_shutdown(struct pci_dev *pdev, bool unload_fw)
 {
-	struct nfp_pf *pf = pci_get_drvdata(pdev);
+	struct nfp_pf *pf;
+
+	pf = pci_get_drvdata(pdev);
+	if (!pf)
+		return;
 
 	nfp_hwmon_unregister(pf);
 
@@ -692,7 +744,7 @@ static void nfp_pci_remove(struct pci_dev *pdev)
 	vfree(pf->dumpspec);
 	kfree(pf->rtbl);
 	nfp_mip_close(pf->mip);
-	if (pf->fw_loaded)
+	if (unload_fw && pf->fw_loaded)
 		nfp_fw_unload(pf);
 
 	destroy_workqueue(pf->wq);
@@ -708,11 +760,22 @@ static void nfp_pci_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+static void nfp_pci_remove(struct pci_dev *pdev)
+{
+	__nfp_pci_shutdown(pdev, true);
+}
+
+static void nfp_pci_shutdown(struct pci_dev *pdev)
+{
+	__nfp_pci_shutdown(pdev, false);
+}
+
 static struct pci_driver nfp_pci_driver = {
 	.name			= nfp_driver_name,
 	.id_table		= nfp_pci_device_ids,
 	.probe			= nfp_pci_probe,
 	.remove			= nfp_pci_remove,
+	.shutdown		= nfp_pci_shutdown,
 	.sriov_configure	= nfp_pcie_sriov_configure,
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h
index a3613a2e0aa5..b7211f200d22 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h
@@ -164,6 +164,8 @@ nfp_pf_map_rtsym(struct nfp_pf *pf, const char *name, const char *sym_fmt,
 		 unsigned int min_size, struct nfp_cpp_area **area);
 int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length,
 		 void *out_data, u64 out_length);
+int nfp_flash_update_common(struct nfp_pf *pf, const char *path,
+			    struct netlink_ext_ack *extack);
 
 enum nfp_dump_diag {
 	NFP_DUMP_NSP_DIAG = 0,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index be37c2d6151c..5d6c3738b494 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -12,11 +12,14 @@
 #ifndef _NFP_NET_H_
 #define _NFP_NET_H_
 
+#include <linux/atomic.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/io-64-nonatomic-hi-lo.h>
+#include <linux/semaphore.h>
+#include <linux/workqueue.h>
 #include <net/xdp.h>
 
 #include "nfp_net_ctrl.h"
@@ -238,7 +241,7 @@ struct nfp_net_tx_ring {
 #define PCIE_DESC_RX_I_TCP_CSUM_OK	cpu_to_le16(BIT(11))
 #define PCIE_DESC_RX_I_UDP_CSUM		cpu_to_le16(BIT(10))
 #define PCIE_DESC_RX_I_UDP_CSUM_OK	cpu_to_le16(BIT(9))
-#define PCIE_DESC_RX_BPF		cpu_to_le16(BIT(8))
+#define PCIE_DESC_RX_DECRYPTED		cpu_to_le16(BIT(8))
 #define PCIE_DESC_RX_EOP		cpu_to_le16(BIT(7))
 #define PCIE_DESC_RX_IP4_CSUM		cpu_to_le16(BIT(6))
 #define PCIE_DESC_RX_IP4_CSUM_OK	cpu_to_le16(BIT(5))
@@ -365,6 +368,7 @@ struct nfp_net_rx_ring {
  * @hw_csum_rx_inner_ok: Counter of packets where the inner HW checksum was OK
  * @hw_csum_rx_complete: Counter of packets with CHECKSUM_COMPLETE reported
  * @hw_csum_rx_error:	 Counter of packets with bad checksums
+ * @hw_tls_rx:	    Number of packets with TLS decrypted by hardware
  * @tx_sync:	    Seqlock for atomic updates of TX stats
  * @tx_pkts:	    Number of Transmitted packets
  * @tx_bytes:	    Number of Transmitted bytes
@@ -372,6 +376,11 @@ struct nfp_net_rx_ring {
  * @hw_csum_tx_inner:	 Counter of inner TX checksum offload requests
  * @tx_gather:	    Counter of packets with Gather DMA
  * @tx_lso:	    Counter of LSO packets sent
+ * @hw_tls_tx:	    Counter of TLS packets sent with crypto offloaded to HW
+ * @tls_tx_fallback:	Counter of TLS packets sent which had to be encrypted
+ *			by the fallback path because packets came out of order
+ * @tls_tx_no_fallback:	Counter of TLS packets not sent because the fallback
+ *			path could not encrypt them
  * @tx_errors:	    How many TX errors were encountered
  * @tx_busy:        How often was TX busy (no space)?
  * @rx_replace_buf_alloc_fail:	Counter of RX buffer allocation failures
@@ -392,7 +401,7 @@ struct nfp_net_r_vector {
 		struct {
 			struct tasklet_struct tasklet;
 			struct sk_buff_head queue;
-			struct spinlock lock;
+			spinlock_t lock;
 		};
 	};
 
@@ -408,22 +417,30 @@ struct nfp_net_r_vector {
 	u64 hw_csum_rx_ok;
 	u64 hw_csum_rx_inner_ok;
 	u64 hw_csum_rx_complete;
+	u64 hw_tls_rx;
+
+	u64 hw_csum_rx_error;
+	u64 rx_replace_buf_alloc_fail;
 
 	struct nfp_net_tx_ring *xdp_ring;
 
 	struct u64_stats_sync tx_sync;
 	u64 tx_pkts;
 	u64 tx_bytes;
-	u64 hw_csum_tx;
+
+	u64 ____cacheline_aligned_in_smp hw_csum_tx;
 	u64 hw_csum_tx_inner;
 	u64 tx_gather;
 	u64 tx_lso;
+	u64 hw_tls_tx;
 
-	u64 hw_csum_rx_error;
-	u64 rx_replace_buf_alloc_fail;
+	u64 tls_tx_fallback;
+	u64 tls_tx_no_fallback;
 	u64 tx_errors;
 	u64 tx_busy;
 
+	/* Cold data follows */
+
 	u32 irq_vector;
 	irq_handler_t handler;
 	char name[IFNAMSIZ + 8];
@@ -458,6 +475,7 @@ struct nfp_stat_pair {
  * @netdev:		Backpointer to net_device structure
  * @is_vf:		Is the driver attached to a VF?
  * @chained_metadata_format:  Firemware will use new metadata format
+ * @ktls_tx:		Is kTLS TX enabled?
  * @rx_dma_dir:		Mapping direction for RX buffers
  * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
  * @rx_offset:		Offset in the RX buffers where packet data starts
@@ -482,6 +500,7 @@ struct nfp_net_dp {
 
 	u8 is_vf:1;
 	u8 chained_metadata_format:1;
+	u8 ktls_tx:1;
 
 	u8 rx_dma_dir;
 	u8 rx_offset;
@@ -539,12 +558,17 @@ struct nfp_net_dp {
  * @shared_handler:     Handler for shared interrupts
  * @shared_name:        Name for shared interrupt
  * @me_freq_mhz:        ME clock_freq (MHz)
- * @reconfig_lock:	Protects HW reconfiguration request regs/machinery
+ * @reconfig_lock:	Protects @reconfig_posted, @reconfig_timer_active,
+ *			@reconfig_sync_present and HW reconfiguration request
+ *			regs/machinery from async requests (sync must take
+ *			@bar_lock)
  * @reconfig_posted:	Pending reconfig bits coming from async sources
  * @reconfig_timer_active:  Timer for reading reconfiguration results is pending
  * @reconfig_sync_present:  Some thread is performing synchronous reconfig
  * @reconfig_timer:	Timer for async reading of reconfig results
  * @reconfig_in_progress_update:	Update FW is processing now (debug only)
+ * @bar_lock:		vNIC config BAR access lock, protects: update,
+ *			mailbox area, crypto TLV
  * @link_up:            Is the link up?
  * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
  * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
@@ -557,6 +581,18 @@ struct nfp_net_dp {
  * @tx_bar:             Pointer to mapped TX queues
  * @rx_bar:             Pointer to mapped FL/RX queues
  * @tlv_caps:		Parsed TLV capabilities
+ * @ktls_tx_conn_cnt:	Number of offloaded kTLS TX connections
+ * @ktls_rx_conn_cnt:	Number of offloaded kTLS RX connections
+ * @ktls_conn_id_gen:	Trivial generator for kTLS connection ids (for TX)
+ * @ktls_no_space:	Counter of firmware rejecting kTLS connection due to
+ *			lack of space
+ * @mbox_cmsg:		Common Control Message via vNIC mailbox state
+ * @mbox_cmsg.queue:	CCM mbox queue of pending messages
+ * @mbox_cmsg.wq:	CCM mbox wait queue of waiting processes
+ * @mbox_cmsg.workq:	CCM mbox work queue for @wait_work and @runq_work
+ * @mbox_cmsg.wait_work:    CCM mbox posted msg reconfig wait work
+ * @mbox_cmsg.runq_work:    CCM mbox posted msg queue runner work
+ * @mbox_cmsg.tag:	CCM mbox message tag allocator
  * @debugfs_dir:	Device directory in debugfs
  * @vnic_list:		Entry on device vNIC list
  * @pdev:		Backpointer to PCI device
@@ -615,6 +651,8 @@ struct nfp_net {
 	struct timer_list reconfig_timer;
 	u32 reconfig_in_progress_update;
 
+	struct semaphore bar_lock;
+
 	u32 rx_coalesce_usecs;
 	u32 rx_coalesce_max_frames;
 	u32 tx_coalesce_usecs;
@@ -630,6 +668,22 @@ struct nfp_net {
 
 	struct nfp_net_tlv_caps tlv_caps;
 
+	unsigned int ktls_tx_conn_cnt;
+	unsigned int ktls_rx_conn_cnt;
+
+	atomic64_t ktls_conn_id_gen;
+
+	atomic_t ktls_no_space;
+
+	struct {
+		struct sk_buff_head queue;
+		wait_queue_head_t wq;
+		struct workqueue_struct *workq;
+		struct work_struct wait_work;
+		struct work_struct runq_work;
+		u16 tag;
+	} mbox_cmsg;
+
 	struct dentry *debugfs_dir;
 
 	struct list_head vnic_list;
@@ -839,6 +893,21 @@ static inline void nfp_ctrl_unlock(struct nfp_net *nn)
 	spin_unlock_bh(&nn->r_vecs[0].lock);
 }
 
+static inline void nn_ctrl_bar_lock(struct nfp_net *nn)
+{
+	down(&nn->bar_lock);
+}
+
+static inline bool nn_ctrl_bar_trylock(struct nfp_net *nn)
+{
+	return !down_trylock(&nn->bar_lock);
+}
+
+static inline void nn_ctrl_bar_unlock(struct nfp_net *nn)
+{
+	up(&nn->bar_lock);
+}
+
 /* Globals */
 extern const char nfp_driver_version[];
 
@@ -866,12 +935,17 @@ void nfp_ctrl_close(struct nfp_net *nn);
 
 void nfp_net_set_ethtool_ops(struct net_device *netdev);
 void nfp_net_info(struct nfp_net *nn);
+int __nfp_net_reconfig(struct nfp_net *nn, u32 update);
 int nfp_net_reconfig(struct nfp_net *nn, u32 update);
 unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
 void nfp_net_rss_write_itbl(struct nfp_net *nn);
 void nfp_net_rss_write_key(struct nfp_net *nn);
 void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
-int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd);
+int nfp_net_mbox_lock(struct nfp_net *nn, unsigned int data_size);
+int nfp_net_mbox_reconfig(struct nfp_net *nn, u32 mbox_cmd);
+int nfp_net_mbox_reconfig_and_unlock(struct nfp_net *nn, u32 mbox_cmd);
+void nfp_net_mbox_reconfig_post(struct nfp_net *nn, u32 update);
+int nfp_net_mbox_reconfig_wait_posted(struct nfp_net *nn);
 
 unsigned int
 nfp_net_irqs_alloc(struct pci_dev *pdev, struct msix_entry *irq_entries,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 7d2d4241498f..9903805717da 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -36,15 +36,17 @@
 #include <linux/vmalloc.h>
 #include <linux/ktime.h>
 
-#include <net/switchdev.h>
+#include <net/tls.h>
 #include <net/vxlan.h>
 
 #include "nfpcore/nfp_nsp.h"
+#include "ccm.h"
 #include "nfp_app.h"
 #include "nfp_net_ctrl.h"
 #include "nfp_net.h"
 #include "nfp_net_sriov.h"
 #include "nfp_port.h"
+#include "crypto/crypto.h"
 
 /**
  * nfp_net_get_fw_version() - Read and parse the FW version
@@ -138,20 +140,37 @@ static bool nfp_net_reconfig_check_done(struct nfp_net *nn, bool last_check)
 	return false;
 }
 
-static int nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
+static bool __nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
 {
 	bool timed_out = false;
+	int i;
+
+	/* Poll update field, waiting for NFP to ack the config.
+	 * Do an opportunistic wait-busy loop, afterward sleep.
+	 */
+	for (i = 0; i < 50; i++) {
+		if (nfp_net_reconfig_check_done(nn, false))
+			return false;
+		udelay(4);
+	}
 
-	/* Poll update field, waiting for NFP to ack the config */
 	while (!nfp_net_reconfig_check_done(nn, timed_out)) {
-		msleep(1);
+		usleep_range(250, 500);
 		timed_out = time_is_before_eq_jiffies(deadline);
 	}
 
+	return timed_out;
+}
+
+static int nfp_net_reconfig_wait(struct nfp_net *nn, unsigned long deadline)
+{
+	if (__nfp_net_reconfig_wait(nn, deadline))
+		return -EIO;
+
 	if (nn_readl(nn, NFP_NET_CFG_UPDATE) & NFP_NET_CFG_UPDATE_ERR)
 		return -EIO;
 
-	return timed_out ? -EIO : 0;
+	return 0;
 }
 
 static void nfp_net_reconfig_timer(struct timer_list *t)
@@ -211,6 +230,7 @@ static void nfp_net_reconfig_sync_enter(struct nfp_net *nn)
 
 	spin_lock_bh(&nn->reconfig_lock);
 
+	WARN_ON(nn->reconfig_sync_present);
 	nn->reconfig_sync_present = true;
 
 	if (nn->reconfig_timer_active) {
@@ -244,7 +264,7 @@ static void nfp_net_reconfig_wait_posted(struct nfp_net *nn)
 }
 
 /**
- * nfp_net_reconfig() - Reconfigure the firmware
+ * __nfp_net_reconfig() - Reconfigure the firmware
  * @nn:      NFP Net device to reconfigure
  * @update:  The value for the update field in the BAR config
  *
@@ -254,7 +274,7 @@ static void nfp_net_reconfig_wait_posted(struct nfp_net *nn)
  *
  * Return: Negative errno on error, 0 on success
  */
-int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+int __nfp_net_reconfig(struct nfp_net *nn, u32 update)
 {
 	int ret;
 
@@ -275,8 +295,31 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update)
 	return ret;
 }
 
+int nfp_net_reconfig(struct nfp_net *nn, u32 update)
+{
+	int ret;
+
+	nn_ctrl_bar_lock(nn);
+	ret = __nfp_net_reconfig(nn, update);
+	nn_ctrl_bar_unlock(nn);
+
+	return ret;
+}
+
+int nfp_net_mbox_lock(struct nfp_net *nn, unsigned int data_size)
+{
+	if (nn->tlv_caps.mbox_len < NFP_NET_CFG_MBOX_SIMPLE_VAL + data_size) {
+		nn_err(nn, "mailbox too small for %u of data (%u)\n",
+		       data_size, nn->tlv_caps.mbox_len);
+		return -EIO;
+	}
+
+	nn_ctrl_bar_lock(nn);
+	return 0;
+}
+
 /**
- * nfp_net_reconfig_mbox() - Reconfigure the firmware via the mailbox
+ * nfp_net_mbox_reconfig() - Reconfigure the firmware via the mailbox
  * @nn:        NFP Net device to reconfigure
  * @mbox_cmd:  The value for the mailbox command
  *
@@ -284,19 +327,14 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update)
  *
  * Return: Negative errno on error, 0 on success
  */
-int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd)
+int nfp_net_mbox_reconfig(struct nfp_net *nn, u32 mbox_cmd)
 {
 	u32 mbox = nn->tlv_caps.mbox_off;
 	int ret;
 
-	if (!nfp_net_has_mbox(&nn->tlv_caps)) {
-		nn_err(nn, "no mailbox present, command: %u\n", mbox_cmd);
-		return -EIO;
-	}
-
 	nn_writeq(nn, mbox + NFP_NET_CFG_MBOX_SIMPLE_CMD, mbox_cmd);
 
-	ret = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_MBOX);
+	ret = __nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_MBOX);
 	if (ret) {
 		nn_err(nn, "Mailbox update error\n");
 		return ret;
@@ -305,6 +343,33 @@ int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd)
 	return -nn_readl(nn, mbox + NFP_NET_CFG_MBOX_SIMPLE_RET);
 }
 
+void nfp_net_mbox_reconfig_post(struct nfp_net *nn, u32 mbox_cmd)
+{
+	u32 mbox = nn->tlv_caps.mbox_off;
+
+	nn_writeq(nn, mbox + NFP_NET_CFG_MBOX_SIMPLE_CMD, mbox_cmd);
+
+	nfp_net_reconfig_post(nn, NFP_NET_CFG_UPDATE_MBOX);
+}
+
+int nfp_net_mbox_reconfig_wait_posted(struct nfp_net *nn)
+{
+	u32 mbox = nn->tlv_caps.mbox_off;
+
+	nfp_net_reconfig_wait_posted(nn);
+
+	return -nn_readl(nn, mbox + NFP_NET_CFG_MBOX_SIMPLE_RET);
+}
+
+int nfp_net_mbox_reconfig_and_unlock(struct nfp_net *nn, u32 mbox_cmd)
+{
+	int ret;
+
+	ret = nfp_net_mbox_reconfig(nn, mbox_cmd);
+	nn_ctrl_bar_unlock(nn);
+	return ret;
+}
+
 /* Interrupt configuration and handling
  */
 
@@ -757,6 +822,99 @@ static void nfp_net_tx_csum(struct nfp_net_dp *dp,
 	u64_stats_update_end(&r_vec->tx_sync);
 }
 
+static struct sk_buff *
+nfp_net_tls_tx(struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec,
+	       struct sk_buff *skb, u64 *tls_handle, int *nr_frags)
+{
+#ifdef CONFIG_TLS_DEVICE
+	struct nfp_net_tls_offload_ctx *ntls;
+	struct sk_buff *nskb;
+	bool resync_pending;
+	u32 datalen, seq;
+
+	if (likely(!dp->ktls_tx))
+		return skb;
+	if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
+		return skb;
+
+	datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
+	seq = ntohl(tcp_hdr(skb)->seq);
+	ntls = tls_driver_ctx(skb->sk, TLS_OFFLOAD_CTX_DIR_TX);
+	resync_pending = tls_offload_tx_resync_pending(skb->sk);
+	if (unlikely(resync_pending || ntls->next_seq != seq)) {
+		/* Pure ACK out of order already */
+		if (!datalen)
+			return skb;
+
+		u64_stats_update_begin(&r_vec->tx_sync);
+		r_vec->tls_tx_fallback++;
+		u64_stats_update_end(&r_vec->tx_sync);
+
+		nskb = tls_encrypt_skb(skb);
+		if (!nskb) {
+			u64_stats_update_begin(&r_vec->tx_sync);
+			r_vec->tls_tx_no_fallback++;
+			u64_stats_update_end(&r_vec->tx_sync);
+			return NULL;
+		}
+		/* encryption wasn't necessary */
+		if (nskb == skb)
+			return skb;
+		/* we don't re-check ring space */
+		if (unlikely(skb_is_nonlinear(nskb))) {
+			nn_dp_warn(dp, "tls_encrypt_skb() produced fragmented frame\n");
+			u64_stats_update_begin(&r_vec->tx_sync);
+			r_vec->tx_errors++;
+			u64_stats_update_end(&r_vec->tx_sync);
+			dev_kfree_skb_any(nskb);
+			return NULL;
+		}
+
+		/* jump forward, a TX may have gotten lost, need to sync TX */
+		if (!resync_pending && seq - ntls->next_seq < U32_MAX / 4)
+			tls_offload_tx_resync_request(nskb->sk);
+
+		*nr_frags = 0;
+		return nskb;
+	}
+
+	if (datalen) {
+		u64_stats_update_begin(&r_vec->tx_sync);
+		if (!skb_is_gso(skb))
+			r_vec->hw_tls_tx++;
+		else
+			r_vec->hw_tls_tx += skb_shinfo(skb)->gso_segs;
+		u64_stats_update_end(&r_vec->tx_sync);
+	}
+
+	memcpy(tls_handle, ntls->fw_handle, sizeof(ntls->fw_handle));
+	ntls->next_seq += datalen;
+#endif
+	return skb;
+}
+
+static void nfp_net_tls_tx_undo(struct sk_buff *skb, u64 tls_handle)
+{
+#ifdef CONFIG_TLS_DEVICE
+	struct nfp_net_tls_offload_ctx *ntls;
+	u32 datalen, seq;
+
+	if (!tls_handle)
+		return;
+	if (WARN_ON_ONCE(!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk)))
+		return;
+
+	datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb));
+	seq = ntohl(tcp_hdr(skb)->seq);
+
+	ntls = tls_driver_ctx(skb->sk, TLS_OFFLOAD_CTX_DIR_TX);
+	if (ntls->next_seq == seq + datalen)
+		ntls->next_seq = seq;
+	else
+		WARN_ON_ONCE(1);
+#endif
+}
+
 static void nfp_net_tx_xmit_more_flush(struct nfp_net_tx_ring *tx_ring)
 {
 	wmb();
@@ -764,24 +922,47 @@ static void nfp_net_tx_xmit_more_flush(struct nfp_net_tx_ring *tx_ring)
 	tx_ring->wr_ptr_add = 0;
 }
 
-static int nfp_net_prep_port_id(struct sk_buff *skb)
+static int nfp_net_prep_tx_meta(struct sk_buff *skb, u64 tls_handle)
 {
 	struct metadata_dst *md_dst = skb_metadata_dst(skb);
 	unsigned char *data;
+	u32 meta_id = 0;
+	int md_bytes;
 
-	if (likely(!md_dst))
-		return 0;
-	if (unlikely(md_dst->type != METADATA_HW_PORT_MUX))
+	if (likely(!md_dst && !tls_handle))
 		return 0;
+	if (unlikely(md_dst && md_dst->type != METADATA_HW_PORT_MUX)) {
+		if (!tls_handle)
+			return 0;
+		md_dst = NULL;
+	}
 
-	if (unlikely(skb_cow_head(skb, 8)))
+	md_bytes = 4 + !!md_dst * 4 + !!tls_handle * 8;
+
+	if (unlikely(skb_cow_head(skb, md_bytes)))
 		return -ENOMEM;
 
-	data = skb_push(skb, 8);
-	put_unaligned_be32(NFP_NET_META_PORTID, data);
-	put_unaligned_be32(md_dst->u.port_info.port_id, data + 4);
+	meta_id = 0;
+	data = skb_push(skb, md_bytes) + md_bytes;
+	if (md_dst) {
+		data -= 4;
+		put_unaligned_be32(md_dst->u.port_info.port_id, data);
+		meta_id = NFP_NET_META_PORTID;
+	}
+	if (tls_handle) {
+		/* conn handle is opaque, we just use u64 to be able to quickly
+		 * compare it to zero
+		 */
+		data -= 8;
+		memcpy(data, &tls_handle, sizeof(tls_handle));
+		meta_id <<= NFP_NET_META_FIELD_SIZE;
+		meta_id |= NFP_NET_META_CONN_HANDLE;
+	}
+
+	data -= 4;
+	put_unaligned_be32(meta_id, data);
 
-	return 8;
+	return md_bytes;
 }
 
 /**
@@ -804,6 +985,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	struct nfp_net_dp *dp;
 	dma_addr_t dma_addr;
 	unsigned int fsize;
+	u64 tls_handle = 0;
 	u16 qidx;
 
 	dp = &nn->dp;
@@ -825,18 +1007,21 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 		return NETDEV_TX_BUSY;
 	}
 
-	md_bytes = nfp_net_prep_port_id(skb);
-	if (unlikely(md_bytes < 0)) {
+	skb = nfp_net_tls_tx(dp, r_vec, skb, &tls_handle, &nr_frags);
+	if (unlikely(!skb)) {
 		nfp_net_tx_xmit_more_flush(tx_ring);
-		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
+	md_bytes = nfp_net_prep_tx_meta(skb, tls_handle);
+	if (unlikely(md_bytes < 0))
+		goto err_flush;
+
 	/* Start with the head skbuf */
 	dma_addr = dma_map_single(dp->dev, skb->data, skb_headlen(skb),
 				  DMA_TO_DEVICE);
 	if (dma_mapping_error(dp->dev, dma_addr))
-		goto err_free;
+		goto err_dma_err;
 
 	wr_idx = D_IDX(tx_ring, tx_ring->wr_p);
 
@@ -910,7 +1095,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 		nfp_net_tx_ring_stop(nd_q, tx_ring);
 
 	tx_ring->wr_ptr_add += nr_frags + 1;
-	if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, skb->xmit_more))
+	if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, netdev_xmit_more()))
 		nfp_net_tx_xmit_more_flush(tx_ring);
 
 	return NETDEV_TX_OK;
@@ -932,12 +1117,14 @@ err_unmap:
 	tx_ring->txbufs[wr_idx].skb = NULL;
 	tx_ring->txbufs[wr_idx].dma_addr = 0;
 	tx_ring->txbufs[wr_idx].fidx = -2;
-err_free:
+err_dma_err:
 	nn_dp_warn(dp, "Failed to map DMA TX buffer\n");
+err_flush:
 	nfp_net_tx_xmit_more_flush(tx_ring);
 	u64_stats_update_begin(&r_vec->tx_sync);
 	r_vec->tx_errors++;
 	u64_stats_update_end(&r_vec->tx_sync);
+	nfp_net_tls_tx_undo(skb, tls_handle);
 	dev_kfree_skb_any(skb);
 	return NETDEV_TX_OK;
 }
@@ -1636,6 +1823,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 		struct nfp_net_rx_buf *rxbuf;
 		struct nfp_net_rx_desc *rxd;
 		struct nfp_meta_parsed meta;
+		bool redir_egress = false;
 		struct net_device *netdev;
 		dma_addr_t new_dma_addr;
 		u32 meta_len_xdp = 0;
@@ -1771,13 +1959,16 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			struct nfp_net *nn;
 
 			nn = netdev_priv(dp->netdev);
-			netdev = nfp_app_repr_get(nn->app, meta.portid);
+			netdev = nfp_app_dev_get(nn->app, meta.portid,
+						 &redir_egress);
 			if (unlikely(!netdev)) {
 				nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf,
 						NULL);
 				continue;
 			}
-			nfp_repr_inc_rx_stats(netdev, pkt_len);
+
+			if (nfp_netdev_is_nfp_repr(netdev))
+				nfp_repr_inc_rx_stats(netdev, pkt_len);
 		}
 
 		skb = build_skb(rxbuf->frag, true_bufsz);
@@ -1806,13 +1997,29 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		nfp_net_rx_csum(dp, r_vec, rxd, &meta, skb);
 
+#ifdef CONFIG_TLS_DEVICE
+		if (rxd->rxd.flags & PCIE_DESC_RX_DECRYPTED) {
+			skb->decrypted = true;
+			u64_stats_update_begin(&r_vec->rx_sync);
+			r_vec->hw_tls_rx++;
+			u64_stats_update_end(&r_vec->rx_sync);
+		}
+#endif
+
 		if (rxd->rxd.flags & PCIE_DESC_RX_VLAN)
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 					       le16_to_cpu(rxd->rxd.vlan));
 		if (meta_len_xdp)
 			skb_metadata_set(skb, meta_len_xdp);
 
-		napi_gro_receive(&rx_ring->r_vec->napi, skb);
+		if (likely(!redir_egress)) {
+			napi_gro_receive(&rx_ring->r_vec->napi, skb);
+		} else {
+			skb->dev = netdev;
+			skb_reset_network_header(skb);
+			__skb_push(skb, ETH_HLEN);
+			dev_queue_xmit(skb);
+		}
 	}
 
 	if (xdp_prog) {
@@ -3112,7 +3319,9 @@ static int nfp_net_change_mtu(struct net_device *netdev, int new_mtu)
 static int
 nfp_net_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 {
+	const u32 cmd = NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD;
 	struct nfp_net *nn = netdev_priv(netdev);
+	int err;
 
 	/* Priority tagged packets with vlan id 0 are processed by the
 	 * NFP as untagged packets
@@ -3120,17 +3329,23 @@ nfp_net_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	if (!vid)
 		return 0;
 
+	err = nfp_net_mbox_lock(nn, NFP_NET_CFG_VLAN_FILTER_SZ);
+	if (err)
+		return err;
+
 	nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_VID, vid);
 	nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_PROTO,
 		  ETH_P_8021Q);
 
-	return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD);
+	return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
 }
 
 static int
 nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 {
+	const u32 cmd = NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL;
 	struct nfp_net *nn = netdev_priv(netdev);
+	int err;
 
 	/* Priority tagged packets with vlan id 0 are processed by the
 	 * NFP as untagged packets
@@ -3138,11 +3353,15 @@ nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	if (!vid)
 		return 0;
 
+	err = nfp_net_mbox_lock(nn, NFP_NET_CFG_VLAN_FILTER_SZ);
+	if (err)
+		return err;
+
 	nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_VID, vid);
 	nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_VLAN_FILTER_PROTO,
 		  ETH_P_8021Q);
 
-	return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL);
+	return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
 }
 
 static void nfp_net_stat64(struct net_device *netdev,
@@ -3325,8 +3544,11 @@ nfp_net_get_phys_port_name(struct net_device *netdev, char *name, size_t len)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int n;
 
+	/* If port is defined, devlink_port is registered and devlink core
+	 * is taking care of name formatting.
+	 */
 	if (nn->port)
-		return nfp_port_get_phys_port_name(netdev, name, len);
+		return -EOPNOTSUPP;
 
 	if (nn->dp.is_vf || nn->vnic_no_name)
 		return -EOPNOTSUPP;
@@ -3518,6 +3740,7 @@ const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_set_vf_mac         = nfp_app_set_vf_mac,
 	.ndo_set_vf_vlan        = nfp_app_set_vf_vlan,
 	.ndo_set_vf_spoofchk    = nfp_app_set_vf_spoofchk,
+	.ndo_set_vf_trust	= nfp_app_set_vf_trust,
 	.ndo_get_vf_config	= nfp_app_get_vf_config,
 	.ndo_set_vf_link_state  = nfp_app_set_vf_link_state,
 	.ndo_setup_tc		= nfp_port_setup_tc,
@@ -3531,6 +3754,7 @@ const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_udp_tunnel_add	= nfp_net_add_vxlan_port,
 	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
 	.ndo_bpf		= nfp_net_xdp,
+	.ndo_get_devlink_port	= nfp_devlink_get_devlink_port,
 };
 
 /**
@@ -3547,7 +3771,7 @@ void nfp_net_info(struct nfp_net *nn)
 		nn->fw_ver.resv, nn->fw_ver.class,
 		nn->fw_ver.major, nn->fw_ver.minor,
 		nn->max_mtu);
-	nn_info(nn, "CAP: %#x %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
+	nn_info(nn, "CAP: %#x %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
 		nn->cap,
 		nn->cap & NFP_NET_CFG_CTRL_PROMISC  ? "PROMISC "  : "",
 		nn->cap & NFP_NET_CFG_CTRL_L2BC     ? "L2BCFILT " : "",
@@ -3563,7 +3787,6 @@ void nfp_net_info(struct nfp_net *nn)
 		nn->cap & NFP_NET_CFG_CTRL_RSS      ? "RSS1 "     : "",
 		nn->cap & NFP_NET_CFG_CTRL_RSS2     ? "RSS2 "     : "",
 		nn->cap & NFP_NET_CFG_CTRL_CTAG_FILTER ? "CTAG_FILTER " : "",
-		nn->cap & NFP_NET_CFG_CTRL_L2SWITCH ? "L2SWITCH " : "",
 		nn->cap & NFP_NET_CFG_CTRL_MSIXAUTO ? "AUTOMASK " : "",
 		nn->cap & NFP_NET_CFG_CTRL_IRQMOD   ? "IRQMOD "   : "",
 		nn->cap & NFP_NET_CFG_CTRL_VXLAN    ? "VXLAN "    : "",
@@ -3631,6 +3854,8 @@ nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
 	nn->dp.txd_cnt = NFP_NET_TX_DESCS_DEFAULT;
 	nn->dp.rxd_cnt = NFP_NET_RX_DESCS_DEFAULT;
 
+	sema_init(&nn->bar_lock, 1);
+
 	spin_lock_init(&nn->reconfig_lock);
 	spin_lock_init(&nn->link_status_lock);
 
@@ -3641,6 +3866,10 @@ nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
 	if (err)
 		goto err_free_nn;
 
+	err = nfp_ccm_mbox_alloc(nn);
+	if (err)
+		goto err_free_nn;
+
 	return nn;
 
 err_free_nn:
@@ -3658,6 +3887,8 @@ err_free_nn:
 void nfp_net_free(struct nfp_net *nn)
 {
 	WARN_ON(timer_pending(&nn->reconfig_timer) || nn->reconfig_posted);
+	nfp_ccm_mbox_free(nn);
+
 	if (nn->dp.netdev)
 		free_netdev(nn->dp.netdev);
 	else
@@ -3815,8 +4046,6 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	netdev->netdev_ops = &nfp_net_netdev_ops;
 	netdev->watchdog_timeo = msecs_to_jiffies(5 * 1000);
 
-	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
-
 	/* MTU range: 68 - hw-specific max */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = nn->max_mtu;
@@ -3921,9 +4150,6 @@ int nfp_net_init(struct nfp_net *nn)
 		nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
 	}
 
-	if (nn->dp.netdev)
-		nfp_net_netdev_init(nn);
-
 	/* Stash the re-configuration queue away.  First odd queue in TX Bar */
 	nn->qcp_cfg = nn->tx_bar + NFP_QCP_QUEUE_ADDR_SZ;
 
@@ -3936,11 +4162,27 @@ int nfp_net_init(struct nfp_net *nn)
 	if (err)
 		return err;
 
+	if (nn->dp.netdev) {
+		nfp_net_netdev_init(nn);
+
+		err = nfp_ccm_mbox_init(nn);
+		if (err)
+			return err;
+
+		err = nfp_net_tls_init(nn);
+		if (err)
+			goto err_clean_mbox;
+	}
+
 	nfp_net_vecs_init(nn);
 
 	if (!nn->dp.netdev)
 		return 0;
 	return register_netdev(nn->dp.netdev);
+
+err_clean_mbox:
+	nfp_ccm_mbox_clean(nn);
+	return err;
 }
 
 /**
@@ -3953,5 +4195,6 @@ void nfp_net_clean(struct nfp_net *nn)
 		return;
 
 	unregister_netdev(nn->dp.netdev);
+	nfp_ccm_mbox_clean(nn);
 	nfp_net_reconfig_wait_posted(nn);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
index 6d5213b5bcb0..d835c14b7257 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
@@ -99,6 +99,21 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 
 			caps->repr_cap = readl(data);
 			break;
+		case NFP_NET_CFG_TLV_TYPE_MBOX_CMSG_TYPES:
+			if (length >= 4)
+				caps->mbox_cmsg_types = readl(data);
+			break;
+		case NFP_NET_CFG_TLV_TYPE_CRYPTO_OPS:
+			if (length < 32) {
+				dev_err(dev,
+					"CRYPTO OPS TLV should be at least 32B, is %dB offset:%u\n",
+					length, offset);
+				return -EINVAL;
+			}
+
+			caps->crypto_ops = readl(data);
+			caps->crypto_enable_off = data - ctrl_mem + 16;
+			break;
 		default:
 			if (!FIELD_GET(NFP_NET_CFG_TLV_HEADER_REQUIRED, hdr))
 				break;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index 166d7f71442e..ee6b24e4eacd 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -44,6 +44,7 @@
 #define NFP_NET_META_MARK		2
 #define NFP_NET_META_PORTID		5
 #define NFP_NET_META_CSUM		6 /* checksum complete type */
+#define NFP_NET_META_CONN_HANDLE	7
 
 #define NFP_META_PORT_ID_CTRL		~0U
 
@@ -104,8 +105,6 @@
 #define   NFP_NET_CFG_CTRL_RINGPRIO	  (0x1 << 19) /* Ring priorities */
 #define   NFP_NET_CFG_CTRL_MSIXAUTO	  (0x1 << 20) /* MSI-X auto-masking */
 #define   NFP_NET_CFG_CTRL_TXRWB	  (0x1 << 21) /* Write-back of TX ring*/
-#define   NFP_NET_CFG_CTRL_L2SWITCH	  (0x1 << 22) /* L2 Switch */
-#define   NFP_NET_CFG_CTRL_L2SWITCH_LOCAL (0x1 << 23) /* Switch to local */
 #define   NFP_NET_CFG_CTRL_VXLAN	  (0x1 << 24) /* VXLAN tunnel support */
 #define   NFP_NET_CFG_CTRL_NVGRE	  (0x1 << 25) /* NVGRE tunnel support */
 #define   NFP_NET_CFG_CTRL_BPF		  (0x1 << 27) /* BPF offload capable */
@@ -130,7 +129,6 @@
 #define   NFP_NET_CFG_UPDATE_TXRPRIO	  (0x1 <<  3) /* TX Ring prio change */
 #define   NFP_NET_CFG_UPDATE_RXRPRIO	  (0x1 <<  4) /* RX Ring prio change */
 #define   NFP_NET_CFG_UPDATE_MSIX	  (0x1 <<  5) /* MSI-X change */
-#define   NFP_NET_CFG_UPDATE_L2SWITCH	  (0x1 <<  6) /* Switch changes */
 #define   NFP_NET_CFG_UPDATE_RESET	  (0x1 <<  7) /* Update due to FLR */
 #define   NFP_NET_CFG_UPDATE_IRQMOD	  (0x1 <<  8) /* IRQ mod change */
 #define   NFP_NET_CFG_UPDATE_VXLAN	  (0x1 <<  9) /* VXLAN port change */
@@ -138,6 +136,7 @@
 #define   NFP_NET_CFG_UPDATE_MACADDR	  (0x1 << 11) /* MAC address change */
 #define   NFP_NET_CFG_UPDATE_MBOX	  (0x1 << 12) /* Mailbox update */
 #define   NFP_NET_CFG_UPDATE_VF		  (0x1 << 13) /* VF settings change */
+#define   NFP_NET_CFG_UPDATE_CRYPTO	  (0x1 << 14) /* Crypto on/off */
 #define   NFP_NET_CFG_UPDATE_ERR	  (0x1 << 31) /* A error occurred */
 #define NFP_NET_CFG_TXRS_ENABLE		0x0008
 #define NFP_NET_CFG_RXRS_ENABLE		0x0010
@@ -392,12 +391,12 @@
 #define NFP_NET_CFG_MBOX_SIMPLE_CMD	0x0
 #define NFP_NET_CFG_MBOX_SIMPLE_RET	0x4
 #define NFP_NET_CFG_MBOX_SIMPLE_VAL	0x8
-#define NFP_NET_CFG_MBOX_SIMPLE_LEN	0x12
 
 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD 1
 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL 2
 
 #define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET	5
+#define NFP_NET_CFG_MBOX_CMD_TLV_CMSG			6
 
 /**
  * VLAN filtering using general use mailbox
@@ -470,6 +469,16 @@
  * %NFP_NET_CFG_TLV_TYPE_REPR_CAP:
  * Single word, equivalent of %NFP_NET_CFG_CAP for representors, features which
  * can be used on representors.
+ *
+ * %NFP_NET_CFG_TLV_TYPE_MBOX_CMSG_TYPES:
+ * Variable, bitmap of control message types supported by the mailbox handler.
+ * Bit 0 corresponds to message type 0, bit 1 to 1, etc.  Control messages are
+ * encapsulated into simple TLVs, with an end TLV and written to the Mailbox.
+ *
+ * %NFP_NET_CFG_TLV_TYPE_CRYPTO_OPS:
+ * 8 words, bitmaps of supported and enabled crypto operations.
+ * First 16B (4 words) contains a bitmap of supported crypto operations,
+ * and next 16B contain the enabled operations.
  */
 #define NFP_NET_CFG_TLV_TYPE_UNKNOWN		0
 #define NFP_NET_CFG_TLV_TYPE_RESERVED		1
@@ -479,6 +488,8 @@
 #define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL0	5
 #define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL1	6
 #define NFP_NET_CFG_TLV_TYPE_REPR_CAP		7
+#define NFP_NET_CFG_TLV_TYPE_MBOX_CMSG_TYPES	10
+#define NFP_NET_CFG_TLV_TYPE_CRYPTO_OPS		11 /* see crypto/fw.h */
 
 struct device;
 
@@ -488,20 +499,20 @@ struct device;
  * @mbox_off:		vNIC mailbox area offset
  * @mbox_len:		vNIC mailbox area length
  * @repr_cap:		capabilities for representors
+ * @mbox_cmsg_types:	cmsgs which can be passed through the mailbox
+ * @crypto_ops:		supported crypto operations
+ * @crypto_enable_off:	offset of crypto ops enable region
  */
 struct nfp_net_tlv_caps {
 	u32 me_freq_mhz;
 	unsigned int mbox_off;
 	unsigned int mbox_len;
 	u32 repr_cap;
+	u32 mbox_cmsg_types;
+	u32 crypto_ops;
+	unsigned int crypto_enable_off;
 };
 
 int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 			   struct nfp_net_tlv_caps *caps);
-
-static inline bool nfp_net_has_mbox(struct nfp_net_tlv_caps *caps)
-{
-	return caps->mbox_len >= NFP_NET_CFG_MBOX_SIMPLE_LEN;
-}
-
 #endif /* _NFP_NET_CTRL_H_ */
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index cb9c512abc76..d9cbe84ac6ad 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/ethtool.h>
 #include <linux/firmware.h>
+#include <linux/sfp.h>
 
 #include "nfpcore/nfp.h"
 #include "nfpcore/nfp_nsp.h"
@@ -149,8 +150,11 @@ static const struct nfp_et_stat nfp_mac_et_stats[] = {
 
 #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats)
 #define NN_ET_SWITCH_STATS_LEN 9
-#define NN_RVEC_GATHER_STATS	9
+#define NN_RVEC_GATHER_STATS	13
 #define NN_RVEC_PER_Q_STATS	3
+#define NN_CTRL_PATH_STATS	1
+
+#define SFP_SFF_REV_COMPLIANCE	1
 
 static void nfp_net_get_nspinfo(struct nfp_app *app, char *version)
 {
@@ -420,7 +424,8 @@ static unsigned int nfp_vnic_get_sw_stats_count(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	return NN_RVEC_GATHER_STATS + nn->max_r_vecs * NN_RVEC_PER_Q_STATS;
+	return NN_RVEC_GATHER_STATS + nn->max_r_vecs * NN_RVEC_PER_Q_STATS +
+		NN_CTRL_PATH_STATS;
 }
 
 static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
@@ -439,10 +444,16 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
 	data = nfp_pr_et(data, "hw_rx_csum_complete");
 	data = nfp_pr_et(data, "hw_rx_csum_err");
 	data = nfp_pr_et(data, "rx_replace_buf_alloc_fail");
+	data = nfp_pr_et(data, "rx_tls_decrypted");
 	data = nfp_pr_et(data, "hw_tx_csum");
 	data = nfp_pr_et(data, "hw_tx_inner_csum");
 	data = nfp_pr_et(data, "tx_gather");
 	data = nfp_pr_et(data, "tx_lso");
+	data = nfp_pr_et(data, "tx_tls_encrypted");
+	data = nfp_pr_et(data, "tx_tls_ooo");
+	data = nfp_pr_et(data, "tx_tls_drop_no_sync_data");
+
+	data = nfp_pr_et(data, "hw_tls_no_space");
 
 	return data;
 }
@@ -465,16 +476,20 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 			tmp[2] = nn->r_vecs[i].hw_csum_rx_complete;
 			tmp[3] = nn->r_vecs[i].hw_csum_rx_error;
 			tmp[4] = nn->r_vecs[i].rx_replace_buf_alloc_fail;
+			tmp[5] = nn->r_vecs[i].hw_tls_rx;
 		} while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start));
 
 		do {
 			start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync);
 			data[1] = nn->r_vecs[i].tx_pkts;
 			data[2] = nn->r_vecs[i].tx_busy;
-			tmp[5] = nn->r_vecs[i].hw_csum_tx;
-			tmp[6] = nn->r_vecs[i].hw_csum_tx_inner;
-			tmp[7] = nn->r_vecs[i].tx_gather;
-			tmp[8] = nn->r_vecs[i].tx_lso;
+			tmp[6] = nn->r_vecs[i].hw_csum_tx;
+			tmp[7] = nn->r_vecs[i].hw_csum_tx_inner;
+			tmp[8] = nn->r_vecs[i].tx_gather;
+			tmp[9] = nn->r_vecs[i].tx_lso;
+			tmp[10] = nn->r_vecs[i].hw_tls_tx;
+			tmp[11] = nn->r_vecs[i].tls_tx_fallback;
+			tmp[12] = nn->r_vecs[i].tls_tx_no_fallback;
 		} while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start));
 
 		data += NN_RVEC_PER_Q_STATS;
@@ -486,6 +501,8 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 	for (j = 0; j < NN_RVEC_GATHER_STATS; j++)
 		*data++ = gathered_stats[j];
 
+	*data++ = atomic_read(&nn->ktls_no_space);
+
 	return data;
 }
 
@@ -1096,6 +1113,130 @@ nfp_app_get_dump_data(struct net_device *netdev, struct ethtool_dump *dump,
 					    buffer);
 }
 
+static int
+nfp_port_get_module_info(struct net_device *netdev,
+			 struct ethtool_modinfo *modinfo)
+{
+	struct nfp_eth_table_port *eth_port;
+	struct nfp_port *port;
+	unsigned int read_len;
+	struct nfp_nsp *nsp;
+	int err = 0;
+	u8 data;
+
+	port = nfp_port_from_netdev(netdev);
+	eth_port = nfp_port_get_eth_port(port);
+	if (!eth_port)
+		return -EOPNOTSUPP;
+
+	nsp = nfp_nsp_open(port->app->cpp);
+	if (IS_ERR(nsp)) {
+		err = PTR_ERR(nsp);
+		netdev_err(netdev, "Failed to access the NSP: %d\n", err);
+		return err;
+	}
+
+	if (!nfp_nsp_has_read_module_eeprom(nsp)) {
+		netdev_info(netdev, "reading module EEPROM not supported. Please update flash\n");
+		err = -EOPNOTSUPP;
+		goto exit_close_nsp;
+	}
+
+	switch (eth_port->interface) {
+	case NFP_INTERFACE_SFP:
+	case NFP_INTERFACE_SFP28:
+		err = nfp_nsp_read_module_eeprom(nsp, eth_port->eth_index,
+						 SFP_SFF8472_COMPLIANCE, &data,
+						 1, &read_len);
+		if (err < 0)
+			goto exit_close_nsp;
+
+		if (!data) {
+			modinfo->type = ETH_MODULE_SFF_8079;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+		} else {
+			modinfo->type = ETH_MODULE_SFF_8472;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		}
+		break;
+	case NFP_INTERFACE_QSFP:
+		err = nfp_nsp_read_module_eeprom(nsp, eth_port->eth_index,
+						 SFP_SFF_REV_COMPLIANCE, &data,
+						 1, &read_len);
+		if (err < 0)
+			goto exit_close_nsp;
+
+		if (data < 0x3) {
+			modinfo->type = ETH_MODULE_SFF_8436;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		} else {
+			modinfo->type = ETH_MODULE_SFF_8636;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		}
+		break;
+	case NFP_INTERFACE_QSFP28:
+		modinfo->type = ETH_MODULE_SFF_8636;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		break;
+	default:
+		netdev_err(netdev, "Unsupported module 0x%x detected\n",
+			   eth_port->interface);
+		err = -EINVAL;
+	}
+
+exit_close_nsp:
+	nfp_nsp_close(nsp);
+	return err;
+}
+
+static int
+nfp_port_get_module_eeprom(struct net_device *netdev,
+			   struct ethtool_eeprom *eeprom, u8 *data)
+{
+	struct nfp_eth_table_port *eth_port;
+	struct nfp_port *port;
+	struct nfp_nsp *nsp;
+	int err;
+
+	port = nfp_port_from_netdev(netdev);
+	eth_port = __nfp_port_get_eth_port(port);
+	if (!eth_port)
+		return -EOPNOTSUPP;
+
+	nsp = nfp_nsp_open(port->app->cpp);
+	if (IS_ERR(nsp)) {
+		err = PTR_ERR(nsp);
+		netdev_err(netdev, "Failed to access the NSP: %d\n", err);
+		return err;
+	}
+
+	if (!nfp_nsp_has_read_module_eeprom(nsp)) {
+		netdev_info(netdev, "reading module EEPROM not supported. Please update flash\n");
+		err = -EOPNOTSUPP;
+		goto exit_close_nsp;
+	}
+
+	err = nfp_nsp_read_module_eeprom(nsp, eth_port->eth_index,
+					 eeprom->offset, data, eeprom->len,
+					 &eeprom->len);
+	if (err < 0) {
+		if (eeprom->len) {
+			netdev_warn(netdev,
+				    "Incomplete read from module EEPROM: %d\n",
+				     err);
+			err = 0;
+		} else {
+			netdev_err(netdev,
+				   "Reading from module EEPROM failed: %d\n",
+				   err);
+		}
+	}
+
+exit_close_nsp:
+	nfp_nsp_close(nsp);
+	return err;
+}
+
 static int nfp_net_set_coalesce(struct net_device *netdev,
 				struct ethtool_coalesce *ec)
 {
@@ -1234,57 +1375,6 @@ static int nfp_net_set_channels(struct net_device *netdev,
 	return nfp_net_set_num_rings(nn, total_rx, total_tx);
 }
 
-static int
-nfp_net_flash_device(struct net_device *netdev, struct ethtool_flash *flash)
-{
-	const struct firmware *fw;
-	struct nfp_app *app;
-	struct nfp_nsp *nsp;
-	struct device *dev;
-	int err;
-
-	if (flash->region != ETHTOOL_FLASH_ALL_REGIONS)
-		return -EOPNOTSUPP;
-
-	app = nfp_app_from_netdev(netdev);
-	if (!app)
-		return -EOPNOTSUPP;
-
-	dev = &app->pdev->dev;
-
-	nsp = nfp_nsp_open(app->cpp);
-	if (IS_ERR(nsp)) {
-		err = PTR_ERR(nsp);
-		dev_err(dev, "Failed to access the NSP: %d\n", err);
-		return err;
-	}
-
-	err = request_firmware_direct(&fw, flash->data, dev);
-	if (err)
-		goto exit_close_nsp;
-
-	dev_info(dev, "Please be patient while writing flash image: %s\n",
-		 flash->data);
-	dev_hold(netdev);
-	rtnl_unlock();
-
-	err = nfp_nsp_write_flash(nsp, fw);
-	if (err < 0) {
-		dev_err(dev, "Flash write failed: %d\n", err);
-		goto exit_rtnl_lock;
-	}
-	dev_info(dev, "Finished writing flash image\n");
-
-exit_rtnl_lock:
-	rtnl_lock();
-	dev_put(netdev);
-	release_firmware(fw);
-
-exit_close_nsp:
-	nfp_nsp_close(nsp);
-	return err;
-}
-
 static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.get_drvinfo		= nfp_net_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -1295,7 +1385,6 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.get_sset_count		= nfp_net_get_sset_count,
 	.get_rxnfc		= nfp_net_get_rxnfc,
 	.set_rxnfc		= nfp_net_set_rxnfc,
-	.flash_device		= nfp_net_flash_device,
 	.get_rxfh_indir_size	= nfp_net_get_rxfh_indir_size,
 	.get_rxfh_key_size	= nfp_net_get_rxfh_key_size,
 	.get_rxfh		= nfp_net_get_rxfh,
@@ -1305,6 +1394,8 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.set_dump		= nfp_app_set_dump,
 	.get_dump_flag		= nfp_app_get_dump_flag,
 	.get_dump_data		= nfp_app_get_dump_data,
+	.get_module_info	= nfp_port_get_module_info,
+	.get_module_eeprom	= nfp_port_get_module_eeprom,
 	.get_coalesce           = nfp_net_get_coalesce,
 	.set_coalesce           = nfp_net_set_coalesce,
 	.get_channels		= nfp_net_get_channels,
@@ -1321,10 +1412,11 @@ const struct ethtool_ops nfp_port_ethtool_ops = {
 	.get_strings		= nfp_port_get_strings,
 	.get_ethtool_stats	= nfp_port_get_stats,
 	.get_sset_count		= nfp_port_get_sset_count,
-	.flash_device		= nfp_net_flash_device,
 	.set_dump		= nfp_app_set_dump,
 	.get_dump_flag		= nfp_app_get_dump_flag,
 	.get_dump_data		= nfp_app_get_dump_data,
+	.get_module_info	= nfp_port_get_module_info,
+	.get_module_eeprom	= nfp_port_get_module_eeprom,
 	.get_link_ksettings	= nfp_net_get_link_ksettings,
 	.set_link_ksettings	= nfp_net_set_link_ksettings,
 	.get_fecparam		= nfp_port_get_fecparam,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 08f5fdbd8e41..986464d4a206 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -150,34 +150,39 @@ nfp_net_pf_init_vnic(struct nfp_pf *pf, struct nfp_net *nn, unsigned int id)
 
 	nn->id = id;
 
+	if (nn->port) {
+		err = nfp_devlink_port_register(pf->app, nn->port);
+		if (err)
+			return err;
+	}
+
 	err = nfp_net_init(nn);
 	if (err)
-		return err;
+		goto err_devlink_port_clean;
 
 	nfp_net_debugfs_vnic_add(nn, pf->ddir);
 
-	if (nn->port) {
-		err = nfp_devlink_port_register(pf->app, nn->port);
-		if (err)
-			goto err_dfs_clean;
-	}
+	if (nn->port)
+		nfp_devlink_port_type_eth_set(nn->port);
 
 	nfp_net_info(nn);
 
 	if (nfp_net_is_data_vnic(nn)) {
 		err = nfp_app_vnic_init(pf->app, nn);
 		if (err)
-			goto err_devlink_port_clean;
+			goto err_devlink_port_type_clean;
 	}
 
 	return 0;
 
-err_devlink_port_clean:
+err_devlink_port_type_clean:
 	if (nn->port)
-		nfp_devlink_port_unregister(nn->port);
-err_dfs_clean:
+		nfp_devlink_port_type_clear(nn->port);
 	nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
 	nfp_net_clean(nn);
+err_devlink_port_clean:
+	if (nn->port)
+		nfp_devlink_port_unregister(nn->port);
 	return err;
 }
 
@@ -221,9 +226,11 @@ static void nfp_net_pf_clean_vnic(struct nfp_pf *pf, struct nfp_net *nn)
 	if (nfp_net_is_data_vnic(nn))
 		nfp_app_vnic_clean(pf->app, nn);
 	if (nn->port)
-		nfp_devlink_port_unregister(nn->port);
+		nfp_devlink_port_type_clear(nn->port);
 	nfp_net_debugfs_dir_clean(&nn->debugfs_dir);
 	nfp_net_clean(nn);
+	if (nn->port)
+		nfp_devlink_port_unregister(nn->port);
 }
 
 static int nfp_net_pf_alloc_irqs(struct nfp_pf *pf)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 69d7aebda09b..1eef446036d6 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -5,7 +5,6 @@
 #include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/lockdep.h>
 #include <net/dst_metadata.h>
-#include <net/switchdev.h>
 
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nsp.h"
@@ -196,7 +195,7 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = dev_queue_xmit(skb);
 	nfp_repr_inc_tx_stats(netdev, len, ret);
 
-	return ret;
+	return NETDEV_TX_OK;
 }
 
 static int nfp_repr_stop(struct net_device *netdev)
@@ -268,11 +267,14 @@ const struct net_device_ops nfp_repr_netdev_ops = {
 	.ndo_set_vf_mac		= nfp_app_set_vf_mac,
 	.ndo_set_vf_vlan	= nfp_app_set_vf_vlan,
 	.ndo_set_vf_spoofchk	= nfp_app_set_vf_spoofchk,
+	.ndo_set_vf_trust	= nfp_app_set_vf_trust,
 	.ndo_get_vf_config	= nfp_app_get_vf_config,
 	.ndo_set_vf_link_state	= nfp_app_set_vf_link_state,
 	.ndo_fix_features	= nfp_repr_fix_features,
 	.ndo_set_features	= nfp_port_set_features,
 	.ndo_set_mac_address    = eth_mac_addr,
+	.ndo_get_port_parent_id	= nfp_port_get_port_parent_id,
+	.ndo_get_devlink_port	= nfp_devlink_get_devlink_port,
 };
 
 void
@@ -336,8 +338,6 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 
 	netdev->max_mtu = pf_netdev->max_mtu;
 
-	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
-
 	/* Set features the lower device can support with representors */
 	if (repr_cap & NFP_NET_CFG_CTRL_LIVE_ADDR)
 		netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
@@ -384,7 +384,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 	netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
 	netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;
 
-	netdev->priv_flags |= IFF_NO_QUEUE;
+	netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
 	netdev->features |= NETIF_F_LLTX;
 
 	if (nfp_app_has_tc(app)) {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c
index b6ec46ed0540..3fdaaf8ed2ba 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-/* Copyright (C) 2017 Netronome Systems, Inc. */
+/* Copyright (C) 2017-2019 Netronome Systems, Inc. */
 
 #include <linux/bitfield.h>
 #include <linux/errno.h>
@@ -146,6 +146,30 @@ int nfp_app_set_vf_spoofchk(struct net_device *netdev, int vf, bool enable)
 				    "spoofchk");
 }
 
+int nfp_app_set_vf_trust(struct net_device *netdev, int vf, bool enable)
+{
+	struct nfp_app *app = nfp_app_from_netdev(netdev);
+	unsigned int vf_offset;
+	u8 vf_ctrl;
+	int err;
+
+	err = nfp_net_sriov_check(app, vf, NFP_NET_VF_CFG_MB_CAP_TRUST,
+				  "trust");
+	if (err)
+		return err;
+
+	/* Write trust control bit to VF entry in VF config symbol */
+	vf_offset = NFP_NET_VF_CFG_MB_SZ + vf * NFP_NET_VF_CFG_SZ +
+		NFP_NET_VF_CFG_CTRL;
+	vf_ctrl = readb(app->pf->vfcfg_tbl2 + vf_offset);
+	vf_ctrl &= ~NFP_NET_VF_CFG_CTRL_TRUST;
+	vf_ctrl |= FIELD_PREP(NFP_NET_VF_CFG_CTRL_TRUST, enable);
+	writeb(vf_ctrl, app->pf->vfcfg_tbl2 + vf_offset);
+
+	return nfp_net_sriov_update(app, vf, NFP_NET_VF_CFG_MB_UPD_TRUST,
+				    "trust");
+}
+
 int nfp_app_set_vf_link_state(struct net_device *netdev, int vf,
 			      int link_state)
 {
@@ -213,6 +237,7 @@ int nfp_app_get_vf_config(struct net_device *netdev, int vf,
 	ivi->qos = FIELD_GET(NFP_NET_VF_CFG_VLAN_QOS, vlan_tci);
 
 	ivi->spoofchk = FIELD_GET(NFP_NET_VF_CFG_CTRL_SPOOF, flags);
+	ivi->trusted = FIELD_GET(NFP_NET_VF_CFG_CTRL_TRUST, flags);
 	ivi->linkstate = FIELD_GET(NFP_NET_VF_CFG_CTRL_LINK_STATE, flags);
 
 	return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h
index c9f09c5bb5ee..a3db0cbf6425 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
-/* Copyright (C) 2017 Netronome Systems, Inc. */
+/* Copyright (C) 2017-2019 Netronome Systems, Inc. */
 
 #ifndef _NFP_NET_SRIOV_H_
 #define _NFP_NET_SRIOV_H_
@@ -19,12 +19,14 @@
 #define   NFP_NET_VF_CFG_MB_CAP_VLAN			  (0x1 << 1)
 #define   NFP_NET_VF_CFG_MB_CAP_SPOOF			  (0x1 << 2)
 #define   NFP_NET_VF_CFG_MB_CAP_LINK_STATE		  (0x1 << 3)
+#define   NFP_NET_VF_CFG_MB_CAP_TRUST			  (0x1 << 4)
 #define NFP_NET_VF_CFG_MB_RET				0x2
 #define NFP_NET_VF_CFG_MB_UPD				0x4
 #define   NFP_NET_VF_CFG_MB_UPD_MAC			  (0x1 << 0)
 #define   NFP_NET_VF_CFG_MB_UPD_VLAN			  (0x1 << 1)
 #define   NFP_NET_VF_CFG_MB_UPD_SPOOF			  (0x1 << 2)
 #define   NFP_NET_VF_CFG_MB_UPD_LINK_STATE		  (0x1 << 3)
+#define   NFP_NET_VF_CFG_MB_UPD_TRUST			  (0x1 << 4)
 #define NFP_NET_VF_CFG_MB_VF_NUM			0x7
 
 /* VF config entry
@@ -35,6 +37,7 @@
 #define   NFP_NET_VF_CFG_MAC_HI				  0x0
 #define   NFP_NET_VF_CFG_MAC_LO				  0x6
 #define NFP_NET_VF_CFG_CTRL				0x4
+#define   NFP_NET_VF_CFG_CTRL_TRUST			  0x8
 #define   NFP_NET_VF_CFG_CTRL_SPOOF			  0x4
 #define   NFP_NET_VF_CFG_CTRL_LINK_STATE		  0x3
 #define     NFP_NET_VF_CFG_LS_MODE_AUTO			    0
@@ -48,6 +51,7 @@ int nfp_app_set_vf_mac(struct net_device *netdev, int vf, u8 *mac);
 int nfp_app_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
 			__be16 vlan_proto);
 int nfp_app_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting);
+int nfp_app_set_vf_trust(struct net_device *netdev, int vf, bool setting);
 int nfp_app_set_vf_link_state(struct net_device *netdev, int vf,
 			      int link_state);
 int nfp_app_get_vf_config(struct net_device *netdev, int vf,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index 1145849ca7ba..e4977cdf7678 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -282,8 +282,14 @@ err_free_vf:
 
 static void nfp_netvf_pci_remove(struct pci_dev *pdev)
 {
-	struct nfp_net_vf *vf = pci_get_drvdata(pdev);
-	struct nfp_net *nn = vf->nn;
+	struct nfp_net_vf *vf;
+	struct nfp_net *nn;
+
+	vf = pci_get_drvdata(pdev);
+	if (!vf)
+		return;
+
+	nn = vf->nn;
 
 	/* Note, the order is slightly different from above as we need
 	 * to keep the nn pointer around till we have freed everything.
@@ -317,4 +323,5 @@ struct pci_driver nfp_netvf_pci_driver = {
 	.id_table    = nfp_netvf_pci_device_ids,
 	.probe       = nfp_netvf_pci_probe,
 	.remove      = nfp_netvf_pci_remove,
+	.shutdown    = nfp_netvf_pci_remove,
 };
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.c b/drivers/net/ethernet/netronome/nfp/nfp_port.c
index 86bc149ca231..93c5bfc0510b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.c
@@ -3,7 +3,6 @@
 
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
-#include <net/switchdev.h>
 
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nsp.h"
@@ -31,34 +30,22 @@ struct nfp_port *nfp_port_from_netdev(struct net_device *netdev)
 	return NULL;
 }
 
-static int
-nfp_port_attr_get(struct net_device *netdev, struct switchdev_attr *attr)
+int nfp_port_get_port_parent_id(struct net_device *netdev,
+				struct netdev_phys_item_id *ppid)
 {
 	struct nfp_port *port;
+	const u8 *serial;
 
 	port = nfp_port_from_netdev(netdev);
 	if (!port)
 		return -EOPNOTSUPP;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: {
-		const u8 *serial;
-		/* N.B: attr->u.ppid.id is binary data */
-		attr->u.ppid.id_len = nfp_cpp_serial(port->app->cpp, &serial);
-		memcpy(&attr->u.ppid.id, serial, attr->u.ppid.id_len);
-		break;
-	}
-	default:
-		return -EOPNOTSUPP;
-	}
+	ppid->id_len = nfp_cpp_serial(port->app->cpp, &serial);
+	memcpy(&ppid->id, serial, ppid->id_len);
 
 	return 0;
 }
 
-const struct switchdev_ops nfp_port_switchdev_ops = {
-	.switchdev_port_attr_get	= nfp_port_attr_get,
-};
-
 int nfp_port_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 		      void *type_data)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h
index b2479a2a49e5..d7fd203bb180 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h
@@ -7,6 +7,7 @@
 #include <net/devlink.h>
 
 struct net_device;
+struct netdev_phys_item_id;
 struct nfp_app;
 struct nfp_pf;
 struct nfp_port;
@@ -90,7 +91,6 @@ struct nfp_port {
 };
 
 extern const struct ethtool_ops nfp_port_ethtool_ops;
-extern const struct switchdev_ops nfp_port_switchdev_ops;
 
 __printf(2, 3) u8 *nfp_pr_et(u8 *data, const char *fmt, ...);
 
@@ -106,6 +106,8 @@ int
 nfp_port_set_features(struct net_device *netdev, netdev_features_t features);
 
 struct nfp_port *nfp_port_from_netdev(struct net_device *netdev);
+int nfp_port_get_port_parent_id(struct net_device *netdev,
+				struct netdev_phys_item_id *ppid);
 struct nfp_port *
 nfp_port_from_id(struct nfp_pf *pf, enum nfp_port_type type, unsigned int id);
 struct nfp_eth_table_port *__nfp_port_get_eth_port(struct nfp_port *port);
@@ -129,6 +131,8 @@ int nfp_net_refresh_port_table_sync(struct nfp_pf *pf);
 
 int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port);
 void nfp_devlink_port_unregister(struct nfp_port *port);
+void nfp_devlink_port_type_eth_set(struct nfp_port *port);
+void nfp_devlink_port_type_clear(struct nfp_port *port);
 
 /**
  * Mac stats (0x0000 - 0x0200)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c
index 814360ed3a20..ea2e3f829aba 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c
@@ -48,6 +48,7 @@ int nfp_shared_buf_pool_get(struct nfp_pf *pf, unsigned int sb, u16 pool_index,
 	pool_info->pool_type = le32_to_cpu(get_data.pool_type);
 	pool_info->threshold_type = le32_to_cpu(get_data.threshold_type);
 	pool_info->size = le32_to_cpu(get_data.size) * unit_size;
+	pool_info->cell_size = unit_size;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index ce1577bbbd2a..9a08623c325d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -7,11 +7,13 @@
  *         Jason McMullan <jason.mcmullan@netronome.com>
  */
 
+#include <asm/unaligned.h>
 #include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
+#include <linux/overflow.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
 
@@ -36,6 +38,7 @@
 #define NSP_COMMAND		0x08
 #define   NSP_COMMAND_OPTION	GENMASK_ULL(63, 32)
 #define   NSP_COMMAND_CODE	GENMASK_ULL(31, 16)
+#define   NSP_COMMAND_DMA_BUF	BIT_ULL(1)
 #define   NSP_COMMAND_START	BIT_ULL(0)
 
 /* CPP address to retrieve the data from */
@@ -48,8 +51,12 @@
 #define   NSP_DFLT_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER_CONFIG	0x20
+#define   NSP_DFLT_BUFFER_DMA_CHUNK_ORDER	GENMASK_ULL(63, 58)
+#define   NSP_DFLT_BUFFER_SIZE_4KB	GENMASK_ULL(15, 8)
 #define   NSP_DFLT_BUFFER_SIZE_MB	GENMASK_ULL(7, 0)
 
+#define NFP_CAP_CMD_DMA_SG	0x28
+
 #define NSP_MAGIC		0xab10
 #define NSP_MAJOR		0
 #define NSP_MINOR		8
@@ -62,6 +69,18 @@
 
 #define NFP_HWINFO_LOOKUP_SIZE	GENMASK(11, 0)
 
+#define NFP_VERSIONS_SIZE	GENMASK(11, 0)
+#define NFP_VERSIONS_CNT_OFF	0
+#define NFP_VERSIONS_BSP_OFF	2
+#define NFP_VERSIONS_CPLD_OFF	6
+#define NFP_VERSIONS_APP_OFF	10
+#define NFP_VERSIONS_BUNDLE_OFF	14
+#define NFP_VERSIONS_UNDI_OFF	18
+#define NFP_VERSIONS_NCSI_OFF	22
+#define NFP_VERSIONS_CFGR_OFF	26
+
+#define NSP_SFF_EEPROM_BLOCK_LEN	8
+
 enum nfp_nsp_cmd {
 	SPCODE_NOOP		= 0, /* No operation */
 	SPCODE_SOFT_RESET	= 1, /* Soft reset the NFP */
@@ -77,6 +96,18 @@ enum nfp_nsp_cmd {
 	SPCODE_NSP_IDENTIFY	= 13, /* Read NSP version */
 	SPCODE_FW_STORED	= 16, /* If no FW loaded, load flash app FW */
 	SPCODE_HWINFO_LOOKUP	= 17, /* Lookup HWinfo with overwrites etc. */
+	SPCODE_VERSIONS		= 21, /* Report FW versions */
+	SPCODE_READ_SFF_EEPROM	= 22, /* Read module EEPROM */
+};
+
+struct nfp_nsp_dma_buf {
+	__le32 chunk_cnt;
+	__le32 reserved[3];
+	struct {
+		__le32 size;
+		__le32 reserved;
+		__le64 addr;
+	} descs[];
 };
 
 static const struct {
@@ -107,18 +138,18 @@ struct nfp_nsp {
 /**
  * struct nfp_nsp_command_arg - NFP command argument structure
  * @code:	NFP SP Command Code
+ * @dma:	@buf points to a host buffer, not NSP buffer
  * @timeout_sec:Timeout value to wait for completion in seconds
  * @option:	NFP SP Command Argument
- * @buff_cpp:	NFP SP Buffer CPP Address info
- * @buff_addr:	NFP SP Buffer Host address
+ * @buf:	NFP SP Buffer Address
  * @error_cb:	Callback for interpreting option if error occurred
  */
 struct nfp_nsp_command_arg {
 	u16 code;
+	bool dma;
 	unsigned int timeout_sec;
 	u32 option;
-	u32 buff_cpp;
-	u64 buff_addr;
+	u64 buf;
 	void (*error_cb)(struct nfp_nsp *state, u32 ret_val);
 };
 
@@ -210,11 +241,16 @@ static int nfp_nsp_check(struct nfp_nsp *state)
 	state->ver.major = FIELD_GET(NSP_STATUS_MAJOR, reg);
 	state->ver.minor = FIELD_GET(NSP_STATUS_MINOR, reg);
 
-	if (state->ver.major != NSP_MAJOR || state->ver.minor < NSP_MINOR) {
+	if (state->ver.major != NSP_MAJOR) {
 		nfp_err(cpp, "Unsupported ABI %hu.%hu\n",
 			state->ver.major, state->ver.minor);
 		return -EINVAL;
 	}
+	if (state->ver.minor < NSP_MINOR) {
+		nfp_err(cpp, "ABI too old to support NIC operation (%u.%hu < %u.%u), please update the management FW on the flash\n",
+			NSP_MAJOR, state->ver.minor, NSP_MAJOR, NSP_MINOR);
+		return -EINVAL;
+	}
 
 	if (reg & NSP_STATUS_BUSY) {
 		nfp_err(cpp, "Service processor busy!\n");
@@ -332,22 +368,14 @@ __nfp_nsp_command(struct nfp_nsp *state, const struct nfp_nsp_command_arg *arg)
 	if (err)
 		return err;
 
-	if (!FIELD_FIT(NSP_BUFFER_CPP, arg->buff_cpp >> 8) ||
-	    !FIELD_FIT(NSP_BUFFER_ADDRESS, arg->buff_addr)) {
-		nfp_err(cpp, "Host buffer out of reach %08x %016llx\n",
-			arg->buff_cpp, arg->buff_addr);
-		return -EINVAL;
-	}
-
-	err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_buffer,
-			     FIELD_PREP(NSP_BUFFER_CPP, arg->buff_cpp >> 8) |
-			     FIELD_PREP(NSP_BUFFER_ADDRESS, arg->buff_addr));
+	err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_buffer, arg->buf);
 	if (err < 0)
 		return err;
 
 	err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_command,
 			     FIELD_PREP(NSP_COMMAND_OPTION, arg->option) |
 			     FIELD_PREP(NSP_COMMAND_CODE, arg->code) |
+			     FIELD_PREP(NSP_COMMAND_DMA_BUF, arg->dma) |
 			     FIELD_PREP(NSP_COMMAND_START, 1));
 	if (err < 0)
 		return err;
@@ -399,36 +427,14 @@ static int nfp_nsp_command(struct nfp_nsp *state, u16 code)
 }
 
 static int
-nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
+nfp_nsp_command_buf_def(struct nfp_nsp *nsp,
+			struct nfp_nsp_command_buf_arg *arg)
 {
 	struct nfp_cpp *cpp = nsp->cpp;
-	unsigned int max_size;
 	u64 reg, cpp_buf;
-	int ret, err;
+	int err, ret;
 	u32 cpp_id;
 
-	if (nsp->ver.minor < 13) {
-		nfp_err(cpp, "NSP: Code 0x%04x with buffer not supported (ABI %hu.%hu)\n",
-			arg->arg.code, nsp->ver.major, nsp->ver.minor);
-		return -EOPNOTSUPP;
-	}
-
-	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
-			    nfp_resource_address(nsp->res) +
-			    NSP_DFLT_BUFFER_CONFIG,
-			    &reg);
-	if (err < 0)
-		return err;
-
-	max_size = max(arg->in_size, arg->out_size);
-	if (FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M < max_size) {
-		nfp_err(cpp, "NSP: default buffer too small for command 0x%04x (%llu < %u)\n",
-			arg->arg.code,
-			FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M,
-			max_size);
-		return -EINVAL;
-	}
-
 	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
 			    nfp_resource_address(nsp->res) +
 			    NSP_DFLT_BUFFER,
@@ -447,15 +453,21 @@ nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
 	}
 	/* Zero out remaining part of the buffer */
 	if (arg->out_buf && arg->out_size && arg->out_size > arg->in_size) {
-		memset(arg->out_buf, 0, arg->out_size - arg->in_size);
 		err = nfp_cpp_write(cpp, cpp_id, cpp_buf + arg->in_size,
 				    arg->out_buf, arg->out_size - arg->in_size);
 		if (err < 0)
 			return err;
 	}
 
-	arg->arg.buff_cpp = cpp_id;
-	arg->arg.buff_addr = cpp_buf;
+	if (!FIELD_FIT(NSP_BUFFER_CPP, cpp_id >> 8) ||
+	    !FIELD_FIT(NSP_BUFFER_ADDRESS, cpp_buf)) {
+		nfp_err(cpp, "Buffer out of reach %08x %016llx\n",
+			cpp_id, cpp_buf);
+		return -EINVAL;
+	}
+
+	arg->arg.buf = FIELD_PREP(NSP_BUFFER_CPP, cpp_id >> 8) |
+		       FIELD_PREP(NSP_BUFFER_ADDRESS, cpp_buf);
 	ret = __nfp_nsp_command(nsp, &arg->arg);
 	if (ret < 0)
 		return ret;
@@ -470,6 +482,210 @@ nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
 	return ret;
 }
 
+static int
+nfp_nsp_command_buf_dma_sg(struct nfp_nsp *nsp,
+			   struct nfp_nsp_command_buf_arg *arg,
+			   unsigned int max_size, unsigned int chunk_order,
+			   unsigned int dma_order)
+{
+	struct nfp_cpp *cpp = nsp->cpp;
+	struct nfp_nsp_dma_buf *desc;
+	struct {
+		dma_addr_t dma_addr;
+		unsigned long len;
+		void *chunk;
+	} *chunks;
+	size_t chunk_size, dma_size;
+	dma_addr_t dma_desc;
+	struct device *dev;
+	unsigned long off;
+	int i, ret, nseg;
+	size_t desc_sz;
+
+	chunk_size = BIT_ULL(chunk_order);
+	dma_size = BIT_ULL(dma_order);
+	nseg = DIV_ROUND_UP(max_size, chunk_size);
+
+	chunks = kzalloc(array_size(sizeof(*chunks), nseg), GFP_KERNEL);
+	if (!chunks)
+		return -ENOMEM;
+
+	off = 0;
+	ret = -ENOMEM;
+	for (i = 0; i < nseg; i++) {
+		unsigned long coff;
+
+		chunks[i].chunk = kmalloc(chunk_size,
+					  GFP_KERNEL | __GFP_NOWARN);
+		if (!chunks[i].chunk)
+			goto exit_free_prev;
+
+		chunks[i].len = min_t(u64, chunk_size, max_size - off);
+
+		coff = 0;
+		if (arg->in_size > off) {
+			coff = min_t(u64, arg->in_size - off, chunk_size);
+			memcpy(chunks[i].chunk, arg->in_buf + off, coff);
+		}
+		memset(chunks[i].chunk + coff, 0, chunk_size - coff);
+
+		off += chunks[i].len;
+	}
+
+	dev = nfp_cpp_device(cpp)->parent;
+
+	for (i = 0; i < nseg; i++) {
+		dma_addr_t addr;
+
+		addr = dma_map_single(dev, chunks[i].chunk, chunks[i].len,
+				      DMA_BIDIRECTIONAL);
+		chunks[i].dma_addr = addr;
+
+		ret = dma_mapping_error(dev, addr);
+		if (ret)
+			goto exit_unmap_prev;
+
+		if (WARN_ONCE(round_down(addr, dma_size) !=
+			      round_down(addr + chunks[i].len - 1, dma_size),
+			      "unaligned DMA address: %pad %lu %zd\n",
+			      &addr, chunks[i].len, dma_size)) {
+			ret = -EFAULT;
+			i++;
+			goto exit_unmap_prev;
+		}
+	}
+
+	desc_sz = struct_size(desc, descs, nseg);
+	desc = kmalloc(desc_sz, GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto exit_unmap_all;
+	}
+
+	desc->chunk_cnt = cpu_to_le32(nseg);
+	for (i = 0; i < nseg; i++) {
+		desc->descs[i].size = cpu_to_le32(chunks[i].len);
+		desc->descs[i].addr = cpu_to_le64(chunks[i].dma_addr);
+	}
+
+	dma_desc = dma_map_single(dev, desc, desc_sz, DMA_TO_DEVICE);
+	ret = dma_mapping_error(dev, dma_desc);
+	if (ret)
+		goto exit_free_desc;
+
+	arg->arg.dma = true;
+	arg->arg.buf = dma_desc;
+	ret = __nfp_nsp_command(nsp, &arg->arg);
+	if (ret < 0)
+		goto exit_unmap_desc;
+
+	i = 0;
+	off = 0;
+	while (off < arg->out_size) {
+		unsigned int len;
+
+		len = min_t(u64, chunks[i].len, arg->out_size - off);
+		memcpy(arg->out_buf + off, chunks[i].chunk, len);
+		off += len;
+		i++;
+	}
+
+exit_unmap_desc:
+	dma_unmap_single(dev, dma_desc, desc_sz, DMA_TO_DEVICE);
+exit_free_desc:
+	kfree(desc);
+exit_unmap_all:
+	i = nseg;
+exit_unmap_prev:
+	while (--i >= 0)
+		dma_unmap_single(dev, chunks[i].dma_addr, chunks[i].len,
+				 DMA_BIDIRECTIONAL);
+	i = nseg;
+exit_free_prev:
+	while (--i >= 0)
+		kfree(chunks[i].chunk);
+	kfree(chunks);
+	if (ret < 0)
+		nfp_err(cpp, "NSP: SG DMA failed for command 0x%04x: %d (sz:%d cord:%d)\n",
+			arg->arg.code, ret, max_size, chunk_order);
+	return ret;
+}
+
+static int
+nfp_nsp_command_buf_dma(struct nfp_nsp *nsp,
+			struct nfp_nsp_command_buf_arg *arg,
+			unsigned int max_size, unsigned int dma_order)
+{
+	unsigned int chunk_order, buf_order;
+	struct nfp_cpp *cpp = nsp->cpp;
+	bool sg_ok;
+	u64 reg;
+	int err;
+
+	buf_order = order_base_2(roundup_pow_of_two(max_size));
+
+	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
+			    nfp_resource_address(nsp->res) + NFP_CAP_CMD_DMA_SG,
+			    &reg);
+	if (err < 0)
+		return err;
+	sg_ok = reg & BIT_ULL(arg->arg.code - 1);
+
+	if (!sg_ok) {
+		if (buf_order > dma_order) {
+			nfp_err(cpp, "NSP: can't service non-SG DMA for command 0x%04x\n",
+				arg->arg.code);
+			return -ENOMEM;
+		}
+		chunk_order = buf_order;
+	} else {
+		chunk_order = min_t(unsigned int, dma_order, PAGE_SHIFT);
+	}
+
+	return nfp_nsp_command_buf_dma_sg(nsp, arg, max_size, chunk_order,
+					  dma_order);
+}
+
+static int
+nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
+{
+	unsigned int dma_order, def_size, max_size;
+	struct nfp_cpp *cpp = nsp->cpp;
+	u64 reg;
+	int err;
+
+	if (nsp->ver.minor < 13) {
+		nfp_err(cpp, "NSP: Code 0x%04x with buffer not supported (ABI %hu.%hu)\n",
+			arg->arg.code, nsp->ver.major, nsp->ver.minor);
+		return -EOPNOTSUPP;
+	}
+
+	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
+			    nfp_resource_address(nsp->res) +
+			    NSP_DFLT_BUFFER_CONFIG,
+			    &reg);
+	if (err < 0)
+		return err;
+
+	/* Zero out undefined part of the out buffer */
+	if (arg->out_buf && arg->out_size && arg->out_size > arg->in_size)
+		memset(arg->out_buf, 0, arg->out_size - arg->in_size);
+
+	max_size = max(arg->in_size, arg->out_size);
+	def_size = FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M +
+		   FIELD_GET(NSP_DFLT_BUFFER_SIZE_4KB, reg) * SZ_4K;
+	dma_order = FIELD_GET(NSP_DFLT_BUFFER_DMA_CHUNK_ORDER, reg);
+	if (def_size >= max_size) {
+		return nfp_nsp_command_buf_def(nsp, arg);
+	} else if (!dma_order) {
+		nfp_err(cpp, "NSP: default buffer too small for command 0x%04x (%u < %u)\n",
+			arg->arg.code, def_size, max_size);
+		return -EINVAL;
+	}
+
+	return nfp_nsp_command_buf_dma(nsp, arg, max_size, dma_order);
+}
+
 int nfp_nsp_wait(struct nfp_nsp *state)
 {
 	const unsigned long wait_until = jiffies + NFP_NSP_TIMEOUT_BOOT * HZ;
@@ -591,10 +807,7 @@ int nfp_nsp_write_flash(struct nfp_nsp *state, const struct firmware *fw)
 		{
 			.code		= SPCODE_NSP_WRITE_FLASH,
 			.option		= fw->size,
-			/* The flash time is specified to take a maximum of 70s
-			 * so we add an additional factor to this spec time.
-			 */
-			.timeout_sec	= 2.5 * 70,
+			.timeout_sec	= 900,
 		},
 		.in_buf		= fw->data,
 		.in_size	= fw->size,
@@ -711,3 +924,111 @@ int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size)
 
 	return 0;
 }
+
+int nfp_nsp_versions(struct nfp_nsp *state, void *buf, unsigned int size)
+{
+	struct nfp_nsp_command_buf_arg versions = {
+		{
+			.code		= SPCODE_VERSIONS,
+			.option		= min_t(u32, size, NFP_VERSIONS_SIZE),
+		},
+		.out_buf	= buf,
+		.out_size	= min_t(u32, size, NFP_VERSIONS_SIZE),
+	};
+
+	return nfp_nsp_command_buf(state, &versions);
+}
+
+const char *nfp_nsp_versions_get(enum nfp_nsp_versions id, bool flash,
+				 const u8 *buf, unsigned int size)
+{
+	static const u32 id2off[] = {
+		[NFP_VERSIONS_BSP] =	NFP_VERSIONS_BSP_OFF,
+		[NFP_VERSIONS_CPLD] =	NFP_VERSIONS_CPLD_OFF,
+		[NFP_VERSIONS_APP] =	NFP_VERSIONS_APP_OFF,
+		[NFP_VERSIONS_BUNDLE] =	NFP_VERSIONS_BUNDLE_OFF,
+		[NFP_VERSIONS_UNDI] =	NFP_VERSIONS_UNDI_OFF,
+		[NFP_VERSIONS_NCSI] =	NFP_VERSIONS_NCSI_OFF,
+		[NFP_VERSIONS_CFGR] =	NFP_VERSIONS_CFGR_OFF,
+	};
+	unsigned int field, buf_field_cnt, buf_off;
+
+	if (id >= ARRAY_SIZE(id2off) || !id2off[id])
+		return ERR_PTR(-EINVAL);
+
+	field = id * 2 + flash;
+
+	buf_field_cnt = get_unaligned_le16(buf);
+	if (buf_field_cnt <= field)
+		return ERR_PTR(-ENOENT);
+
+	buf_off = get_unaligned_le16(buf + id2off[id] + flash * 2);
+	if (!buf_off)
+		return ERR_PTR(-ENOENT);
+
+	if (buf_off >= size)
+		return ERR_PTR(-EINVAL);
+	if (strnlen(&buf[buf_off], size - buf_off) == size - buf_off)
+		return ERR_PTR(-EINVAL);
+
+	return (const char *)&buf[buf_off];
+}
+
+static int
+__nfp_nsp_module_eeprom(struct nfp_nsp *state, void *buf, unsigned int size)
+{
+	struct nfp_nsp_command_buf_arg module_eeprom = {
+		{
+			.code		= SPCODE_READ_SFF_EEPROM,
+			.option		= size,
+		},
+		.in_buf		= buf,
+		.in_size	= size,
+		.out_buf	= buf,
+		.out_size	= size,
+	};
+
+	return nfp_nsp_command_buf(state, &module_eeprom);
+}
+
+int nfp_nsp_read_module_eeprom(struct nfp_nsp *state, int eth_index,
+			       unsigned int offset, void *data,
+			       unsigned int len, unsigned int *read_len)
+{
+	struct eeprom_buf {
+		u8 metalen;
+		__le16 length;
+		__le16 offset;
+		__le16 readlen;
+		u8 eth_index;
+		u8 data[0];
+	} __packed *buf;
+	int bufsz, ret;
+
+	BUILD_BUG_ON(offsetof(struct eeprom_buf, data) % 8);
+
+	/* Buffer must be large enough and rounded to the next block size. */
+	bufsz = struct_size(buf, data, round_up(len, NSP_SFF_EEPROM_BLOCK_LEN));
+	buf = kzalloc(bufsz, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf->metalen =
+		offsetof(struct eeprom_buf, data) / NSP_SFF_EEPROM_BLOCK_LEN;
+	buf->length = cpu_to_le16(len);
+	buf->offset = cpu_to_le16(offset);
+	buf->eth_index = eth_index;
+
+	ret = __nfp_nsp_module_eeprom(state, buf, bufsz);
+
+	*read_len = min_t(unsigned int, len, le16_to_cpu(buf->readlen));
+	if (*read_len)
+		memcpy(data, buf->data, *read_len);
+
+	if (!ret && *read_len < len)
+		ret = -EIO;
+
+	kfree(buf);
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
index ff33ac54097a..22ee6985ee1c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
@@ -22,6 +22,9 @@ int nfp_nsp_write_flash(struct nfp_nsp *state, const struct firmware *fw);
 int nfp_nsp_mac_reinit(struct nfp_nsp *state);
 int nfp_nsp_load_stored_fw(struct nfp_nsp *state);
 int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size);
+int nfp_nsp_read_module_eeprom(struct nfp_nsp *state, int eth_index,
+			       unsigned int offset, void *data,
+			       unsigned int len, unsigned int *read_len);
 
 static inline bool nfp_nsp_has_mac_reinit(struct nfp_nsp *state)
 {
@@ -38,12 +41,23 @@ static inline bool nfp_nsp_has_hwinfo_lookup(struct nfp_nsp *state)
 	return nfp_nsp_get_abi_ver_minor(state) > 24;
 }
 
+static inline bool nfp_nsp_has_versions(struct nfp_nsp *state)
+{
+	return nfp_nsp_get_abi_ver_minor(state) > 27;
+}
+
+static inline bool nfp_nsp_has_read_module_eeprom(struct nfp_nsp *state)
+{
+	return nfp_nsp_get_abi_ver_minor(state) > 28;
+}
+
 enum nfp_eth_interface {
 	NFP_INTERFACE_NONE	= 0,
 	NFP_INTERFACE_SFP	= 1,
 	NFP_INTERFACE_SFPP	= 10,
 	NFP_INTERFACE_SFP28	= 28,
 	NFP_INTERFACE_QSFP	= 40,
+	NFP_INTERFACE_RJ45	= 45,
 	NFP_INTERFACE_CXP	= 100,
 	NFP_INTERFACE_QSFP28	= 112,
 };
@@ -208,4 +222,19 @@ enum nfp_nsp_sensor_id {
 int nfp_hwmon_read_sensor(struct nfp_cpp *cpp, enum nfp_nsp_sensor_id id,
 			  long *val);
 
+#define NFP_NSP_VERSION_BUFSZ	1024 /* reasonable size, not in the ABI */
+
+enum nfp_nsp_versions {
+	NFP_VERSIONS_BSP,
+	NFP_VERSIONS_CPLD,
+	NFP_VERSIONS_APP,
+	NFP_VERSIONS_BUNDLE,
+	NFP_VERSIONS_UNDI,
+	NFP_VERSIONS_NCSI,
+	NFP_VERSIONS_CFGR,
+};
+
+int nfp_nsp_versions(struct nfp_nsp *state, void *buf, unsigned int size);
+const char *nfp_nsp_versions_get(enum nfp_nsp_versions id, bool flash,
+				 const u8 *buf, unsigned int size);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
index 802c9224bb32..311a5be25acb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
@@ -206,6 +206,9 @@ nfp_eth_calc_port_type(struct nfp_cpp *cpp, struct nfp_eth_table_port *entry)
 	if (entry->interface == NFP_INTERFACE_NONE) {
 		entry->port_type = PORT_NONE;
 		return;
+	} else if (entry->interface == NFP_INTERFACE_RJ45) {
+		entry->port_type = PORT_TP;
+		return;
 	}
 
 	if (entry->media == NFP_MEDIA_FIBRE)
@@ -269,8 +272,7 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
 		goto err;
 	}
 
-	table = kzalloc(sizeof(*table) +
-			sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL);
+	table = kzalloc(struct_size(table, ports, cnt), GFP_KERNEL);
 	if (!table)
 		goto err;
 
diff --git a/drivers/net/ethernet/netx-eth.c b/drivers/net/ethernet/netx-eth.c
index df4188cb43e0..cf6e7eb1b1e1 100644
--- a/drivers/net/ethernet/netx-eth.c
+++ b/drivers/net/ethernet/netx-eth.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * drivers/net/ethernet/netx-eth.c
  *
  * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/init.h>
diff --git a/drivers/net/ethernet/ni/Kconfig b/drivers/net/ethernet/ni/Kconfig
index c73978474c4b..70b1a03c0953 100644
--- a/drivers/net/ethernet/ni/Kconfig
+++ b/drivers/net/ethernet/ni/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # National Instuments network device configuration
 #
diff --git a/drivers/net/ethernet/ni/Makefile b/drivers/net/ethernet/ni/Makefile
index 99c664651c51..b31bbea3c24c 100644
--- a/drivers/net/ethernet/ni/Makefile
+++ b/drivers/net/ethernet/ni/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_NI_XGE_MANAGEMENT_ENET) += nixge.o
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 1e408d1a9b5f..0b384f97d2fd 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -105,6 +105,12 @@
 #define NIXGE_MAX_JUMBO_FRAME_SIZE \
 	(NIXGE_JUMBO_MTU + NIXGE_HDR_SIZE + NIXGE_TRL_SIZE)
 
+enum nixge_version {
+	NIXGE_V2,
+	NIXGE_V3,
+	NIXGE_VERSION_COUNT
+};
+
 struct nixge_hw_dma_bd {
 	u32 next_lo;
 	u32 next_hi;
@@ -984,7 +990,7 @@ static void nixge_ethtools_get_drvinfo(struct net_device *ndev,
 				       struct ethtool_drvinfo *ed)
 {
 	strlcpy(ed->driver, "nixge", sizeof(ed->driver));
-	strlcpy(ed->bus_info, "platform", sizeof(ed->driver));
+	strlcpy(ed->bus_info, "platform", sizeof(ed->bus_info));
 }
 
 static int nixge_ethtools_get_coalesce(struct net_device *ndev,
@@ -1225,11 +1231,60 @@ static void *nixge_get_nvmem_address(struct device *dev)
 	return mac;
 }
 
+/* Match table for of_platform binding */
+static const struct of_device_id nixge_dt_ids[] = {
+	{ .compatible = "ni,xge-enet-2.00", .data = (void *)NIXGE_V2 },
+	{ .compatible = "ni,xge-enet-3.00", .data = (void *)NIXGE_V3 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, nixge_dt_ids);
+
+static int nixge_of_get_resources(struct platform_device *pdev)
+{
+	const struct of_device_id *of_id;
+	enum nixge_version version;
+	struct resource *ctrlres;
+	struct resource *dmares;
+	struct net_device *ndev;
+	struct nixge_priv *priv;
+
+	ndev = platform_get_drvdata(pdev);
+	priv = netdev_priv(ndev);
+	of_id = of_match_node(nixge_dt_ids, pdev->dev.of_node);
+	if (!of_id)
+		return -ENODEV;
+
+	version = (enum nixge_version)of_id->data;
+	if (version <= NIXGE_V2)
+		dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	else
+		dmares = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						      "dma");
+
+	priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares);
+	if (IS_ERR(priv->dma_regs)) {
+		netdev_err(ndev, "failed to map dma regs\n");
+		return PTR_ERR(priv->dma_regs);
+	}
+	if (version <= NIXGE_V2) {
+		priv->ctrl_regs = priv->dma_regs + NIXGE_REG_CTRL_OFFSET;
+	} else {
+		ctrlres = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						       "ctrl");
+		priv->ctrl_regs = devm_ioremap_resource(&pdev->dev, ctrlres);
+	}
+	if (IS_ERR(priv->ctrl_regs)) {
+		netdev_err(ndev, "failed to map ctrl regs\n");
+		return PTR_ERR(priv->ctrl_regs);
+	}
+	return 0;
+}
+
 static int nixge_probe(struct platform_device *pdev)
 {
+	struct device_node *mn, *phy_node;
 	struct nixge_priv *priv;
 	struct net_device *ndev;
-	struct resource *dmares;
 	const u8 *mac_addr;
 	int err;
 
@@ -1261,14 +1316,9 @@ static int nixge_probe(struct platform_device *pdev)
 	priv->dev = &pdev->dev;
 
 	netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT);
-
-	dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares);
-	if (IS_ERR(priv->dma_regs)) {
-		netdev_err(ndev, "failed to map dma regs\n");
-		return PTR_ERR(priv->dma_regs);
-	}
-	priv->ctrl_regs = priv->dma_regs + NIXGE_REG_CTRL_OFFSET;
+	err = nixge_of_get_resources(pdev);
+	if (err)
+		return err;
 	__nixge_hw_set_mac_address(ndev);
 
 	priv->tx_irq = platform_get_irq_byname(pdev, "tx");
@@ -1286,10 +1336,14 @@ static int nixge_probe(struct platform_device *pdev)
 	priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
 	priv->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
 
-	err = nixge_mdio_setup(priv, pdev->dev.of_node);
-	if (err) {
-		netdev_err(ndev, "error registering mdio bus");
-		goto free_netdev;
+	mn = of_get_child_by_name(pdev->dev.of_node, "mdio");
+	if (mn) {
+		err = nixge_mdio_setup(priv, mn);
+		of_node_put(mn);
+		if (err) {
+			netdev_err(ndev, "error registering mdio bus");
+			goto free_netdev;
+		}
 	}
 
 	priv->phy_mode = of_get_phy_mode(pdev->dev.of_node);
@@ -1299,23 +1353,33 @@ static int nixge_probe(struct platform_device *pdev)
 		goto unregister_mdio;
 	}
 
-	priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
-	if (!priv->phy_node) {
-		netdev_err(ndev, "not find \"phy-handle\" property\n");
-		err = -EINVAL;
-		goto unregister_mdio;
+	phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+	if (!phy_node && of_phy_is_fixed_link(pdev->dev.of_node)) {
+		err = of_phy_register_fixed_link(pdev->dev.of_node);
+		if (err < 0) {
+			netdev_err(ndev, "broken fixed-link specification\n");
+			goto unregister_mdio;
+		}
+		phy_node = of_node_get(pdev->dev.of_node);
 	}
+	priv->phy_node = phy_node;
 
 	err = register_netdev(priv->ndev);
 	if (err) {
 		netdev_err(ndev, "register_netdev() error (%i)\n", err);
-		goto unregister_mdio;
+		goto free_phy;
 	}
 
 	return 0;
 
+free_phy:
+	if (of_phy_is_fixed_link(pdev->dev.of_node))
+		of_phy_deregister_fixed_link(pdev->dev.of_node);
+	of_node_put(phy_node);
+
 unregister_mdio:
-	mdiobus_unregister(priv->mii_bus);
+	if (priv->mii_bus)
+		mdiobus_unregister(priv->mii_bus);
 
 free_netdev:
 	free_netdev(ndev);
@@ -1330,20 +1394,18 @@ static int nixge_remove(struct platform_device *pdev)
 
 	unregister_netdev(ndev);
 
-	mdiobus_unregister(priv->mii_bus);
+	if (of_phy_is_fixed_link(pdev->dev.of_node))
+		of_phy_deregister_fixed_link(pdev->dev.of_node);
+	of_node_put(priv->phy_node);
+
+	if (priv->mii_bus)
+		mdiobus_unregister(priv->mii_bus);
 
 	free_netdev(ndev);
 
 	return 0;
 }
 
-/* Match table for of_platform binding */
-static const struct of_device_id nixge_dt_ids[] = {
-	{ .compatible = "ni,xge-enet-2.00", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, nixge_dt_ids);
-
 static struct platform_driver nixge_driver = {
 	.probe		= nixge_probe,
 	.remove		= nixge_remove,
diff --git a/drivers/net/ethernet/nuvoton/Kconfig b/drivers/net/ethernet/nuvoton/Kconfig
index 71c973f8e50f..325e26c549f8 100644
--- a/drivers/net/ethernet/nuvoton/Kconfig
+++ b/drivers/net/ethernet/nuvoton/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Nuvoton network device configuration
 #
diff --git a/drivers/net/ethernet/nuvoton/Makefile b/drivers/net/ethernet/nuvoton/Makefile
index 171aa044bd3b..66f6e728d54b 100644
--- a/drivers/net/ethernet/nuvoton/Makefile
+++ b/drivers/net/ethernet/nuvoton/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Nuvoton network device drivers.
 #
diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
index c662c6f5bee3..3d73970b3a2e 100644
--- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
+++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2008-2009 Nuvoton technology corporation.
  *
  * Wan ZongShun <mcuos.com@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation;version 2 of the License.
- *
  */
 
 #include <linux/module.h>
@@ -630,7 +626,7 @@ static int w90p910_ether_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (!(w90p910_send_frame(dev, skb->data, skb->len))) {
 		ether->skb = skb;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		return 0;
 	}
 	return -EAGAIN;
diff --git a/drivers/net/ethernet/nvidia/Kconfig b/drivers/net/ethernet/nvidia/Kconfig
index 4efc9fe84785..faacbd129c44 100644
--- a/drivers/net/ethernet/nvidia/Kconfig
+++ b/drivers/net/ethernet/nvidia/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # NVIDIA network device configuration
 #
diff --git a/drivers/net/ethernet/nvidia/Makefile b/drivers/net/ethernet/nvidia/Makefile
index e079ae5771d5..89356992c3ed 100644
--- a/drivers/net/ethernet/nvidia/Makefile
+++ b/drivers/net/ethernet/nvidia/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the NVIDIA network device drivers.
 #
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 1d9b0d44ddb6..b327b29f5d57 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * forcedeth: Ethernet driver for NVIDIA nForce media access controllers.
  *
@@ -15,19 +16,6 @@
  *		IRQ rate fixes, bigendian fixes, cleanups, verification)
  * Copyright (c) 2004,2005,2006,2007,2008,2009 NVIDIA Corporation
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * Known bugs:
  * We suspect that on some hardware no TX done interrupts are generated.
  * This means recovery from netif_stop_queue only happens if the hw timer
diff --git a/drivers/net/ethernet/nxp/Kconfig b/drivers/net/ethernet/nxp/Kconfig
index 0d9baf98a3b9..261f107e2be0 100644
--- a/drivers/net/ethernet/nxp/Kconfig
+++ b/drivers/net/ethernet/nxp/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config LPC_ENET
         tristate "NXP ethernet MAC on LPC devices"
         depends on ARCH_LPC32XX
diff --git a/drivers/net/ethernet/nxp/Makefile b/drivers/net/ethernet/nxp/Makefile
index a128114e6895..cba6ddcc3934 100644
--- a/drivers/net/ethernet/nxp/Makefile
+++ b/drivers/net/ethernet/nxp/Makefile
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_LPC_ENET) += lpc_eth.o
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 89d17399fb5a..f7e11f1b0426 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/nxp/lpc_eth.c
  *
@@ -5,16 +6,6 @@
  *
  * Copyright (C) 2010 NXP Semiconductors
  * Copyright (C) 2012 Roland Stigge <stigge@antcom.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -1368,8 +1359,8 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
 
 	if (!is_valid_ether_addr(ndev->dev_addr)) {
 		const char *macaddr = of_get_mac_address(np);
-		if (macaddr)
-			memcpy(ndev->dev_addr, macaddr, ETH_ALEN);
+		if (!IS_ERR(macaddr))
+			ether_addr_copy(ndev->dev_addr, macaddr);
 	}
 	if (!is_valid_ether_addr(ndev->dev_addr))
 		eth_hw_addr_random(ndev);
diff --git a/drivers/net/ethernet/oki-semi/Kconfig b/drivers/net/ethernet/oki-semi/Kconfig
index 5a975af4824b..1c455c645bce 100644
--- a/drivers/net/ethernet/oki-semi/Kconfig
+++ b/drivers/net/ethernet/oki-semi/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # OKI Semiconductor device configuration
 #
diff --git a/drivers/net/ethernet/oki-semi/Makefile b/drivers/net/ethernet/oki-semi/Makefile
index b6780c877c19..b97baf9efb92 100644
--- a/drivers/net/ethernet/oki-semi/Makefile
+++ b/drivers/net/ethernet/oki-semi/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the OKI Semiconductor device drivers.
 #
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
index 5f7a35212796..69e11d19bdc6 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # OKI Semiconductor device configuration
 #
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
index 862de0f3bc41..c4762b3d124a 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_PCH_GBE) += pch_gbe.o
 
 pch_gbe-y := pch_gbe_phy.o pch_gbe_ethtool.o pch_gbe_param.o
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 44c2f291e766..32b9d7705404 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 1999 - 2010 Intel Corporation.
  * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
  *
  * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _PCH_GBE_H_
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index adaa0024adfe..1a3008e33182 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 1999 - 2010 Intel Corporation.
  * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
  *
  * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "pch_gbe.h"
 #include "pch_gbe_phy.h"
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 552d930e3940..18e6d87c607b 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 1999 - 2010 Intel Corporation.
  * Copyright (C) 2010 - 2012 LAPIS SEMICONDUCTOR CO., LTD.
  *
  * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "pch_gbe.h"
@@ -27,7 +16,6 @@
 #define DRV_VERSION     "1.01"
 const char pch_driver_version[] = DRV_VERSION;
 
-#define PCI_DEVICE_ID_INTEL_IOH1_GBE	0x8802		/* Pci device ID */
 #define PCH_GBE_MAR_ENTRIES		16
 #define PCH_GBE_SHORT_PKT		64
 #define DSC_INIT16			0xC000
@@ -37,11 +25,9 @@ const char pch_driver_version[] = DRV_VERSION;
 #define PCH_GBE_PCI_BAR			1
 #define PCH_GBE_RESERVE_MEMORY		0x200000	/* 2MB */
 
-/* Macros for ML7223 */
-#define PCI_VENDOR_ID_ROHM			0x10db
-#define PCI_DEVICE_ID_ROHM_ML7223_GBE		0x8013
+#define PCI_DEVICE_ID_INTEL_IOH1_GBE		0x8802
 
-/* Macros for ML7831 */
+#define PCI_DEVICE_ID_ROHM_ML7223_GBE		0x8013
 #define PCI_DEVICE_ID_ROHM_ML7831_GBE		0x8802
 
 #define PCH_GBE_TX_WEIGHT         64
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
index e097e6baaac4..a26966fa40b9 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 1999 - 2010 Intel Corporation.
  * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
  *
  * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "pch_gbe.h"
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
index 6b35b573beef..ed832046216a 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
@@ -1,20 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 1999 - 2010 Intel Corporation.
  * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
  *
  * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "pch_gbe.h"
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
index 23ac38711619..7f7531da1eee 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 1999 - 2010 Intel Corporation.
  * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
  *
  * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #ifndef _PCH_GBE_PHY_H_
 #define _PCH_GBE_PHY_H_
diff --git a/drivers/net/ethernet/packetengines/Kconfig b/drivers/net/ethernet/packetengines/Kconfig
index 1df28f2edd1f..8161e308e64b 100644
--- a/drivers/net/ethernet/packetengines/Kconfig
+++ b/drivers/net/ethernet/packetengines/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Packet engine device configuration
 #
diff --git a/drivers/net/ethernet/packetengines/Makefile b/drivers/net/ethernet/packetengines/Makefile
index 995ccd077d0c..1553c9cfc254 100644
--- a/drivers/net/ethernet/packetengines/Makefile
+++ b/drivers/net/ethernet/packetengines/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Packet Engine network device drivers.
 #
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index c9529c29a0a7..eee883a2aa8d 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -1337,7 +1337,7 @@ static irqreturn_t hamachi_interrupt(int irq, void *dev_instance)
 							leXX_to_cpu(hmp->tx_ring[entry].addr),
 							skb->len,
 							PCI_DMA_TODEVICE);
-						dev_kfree_skb_irq(skb);
+						dev_consume_skb_irq(skb);
 						hmp->tx_skbuff[entry] = NULL;
 					}
 					hmp->tx_ring[entry].status_n_length = 0;
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index 54224d1822e3..6f8d6584f809 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -925,7 +925,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance)
 			/* Free the original skb. */
 			pci_unmap_single(yp->pci_dev, le32_to_cpu(yp->tx_ring[entry].addr),
 				skb->len, PCI_DMA_TODEVICE);
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 			yp->tx_skbuff[entry] = NULL;
 		}
 		if (yp->tx_full &&
@@ -983,7 +983,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance)
 				pci_unmap_single(yp->pci_dev,
 					yp->tx_ring[entry<<1].addr, skb->len,
 					PCI_DMA_TODEVICE);
-				dev_kfree_skb_irq(skb);
+				dev_consume_skb_irq(skb);
 				yp->tx_skbuff[entry] = 0;
 				/* Mark status as empty. */
 				yp->tx_status[entry].tx_errs = 0;
diff --git a/drivers/net/ethernet/pasemi/Kconfig b/drivers/net/ethernet/pasemi/Kconfig
index 7c92e8306c19..f4562243d4a0 100644
--- a/drivers/net/ethernet/pasemi/Kconfig
+++ b/drivers/net/ethernet/pasemi/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # PA Semi network device configuration
 #
diff --git a/drivers/net/ethernet/pasemi/Makefile b/drivers/net/ethernet/pasemi/Makefile
index 90497ffb1ac3..f51e614a2539 100644
--- a/drivers/net/ethernet/pasemi/Makefile
+++ b/drivers/net/ethernet/pasemi/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the A Semi network device drivers.
 #
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c
index d21041554507..be6660128b55 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006-2007 PA Semi, Inc
  *
  * Driver for the PA Semi PWRficient onchip 1G/10G Ethernet MACs
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/module.h>
@@ -1053,7 +1042,6 @@ static int pasemi_mac_phy_init(struct net_device *dev)
 
 	dn = pci_device_to_OF_node(mac->pdev);
 	phy_dn = of_parse_phandle(dn, "phy-handle", 0);
-	of_node_put(phy_dn);
 
 	mac->link = 0;
 	mac->speed = 0;
@@ -1062,6 +1050,7 @@ static int pasemi_mac_phy_init(struct net_device *dev)
 	phydev = of_phy_connect(dev, phy_dn, &pasemi_adjust_link, 0,
 				PHY_INTERFACE_MODE_SGMII);
 
+	of_node_put(phy_dn);
 	if (!phydev) {
 		printk(KERN_ERR "%s: Could not attach to phy\n", dev->name);
 		return -ENODEV;
@@ -1355,7 +1344,7 @@ static void pasemi_mac_queue_csdesc(const struct sk_buff *skb,
 	const int nh_off = skb_network_offset(skb);
 	const int nh_len = skb_network_header_len(skb);
 	const int nfrags = skb_shinfo(skb)->nr_frags;
-	int cs_size, i, fill, hdr, cpyhdr, evt;
+	int cs_size, i, fill, hdr, evt;
 	dma_addr_t csdma;
 
 	fund = XCT_FUN_ST | XCT_FUN_RR_8BRES |
@@ -1396,7 +1385,6 @@ static void pasemi_mac_queue_csdesc(const struct sk_buff *skb,
 		fill++;
 
 	/* Copy the result into the TCP packet */
-	cpyhdr = fill;
 	CS_DESC(csring, fill++) = XCT_FUN_O | XCT_FUN_FUN(csring->fun) |
 				  XCT_FUN_LLEN(2) | XCT_FUN_SE;
 	CS_DESC(csring, fill++) = XCT_PTR_LEN(2) | XCT_PTR_ADDR(cs_dest) | XCT_PTR_T;
@@ -1716,6 +1704,7 @@ pasemi_mac_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		err = -ENODEV;
 		goto out;
 	}
+	dma_set_mask(&mac->dma_pdev->dev, DMA_BIT_MASK(64));
 
 	mac->iob_pdev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa001, NULL);
 	if (!mac->iob_pdev) {
@@ -1838,7 +1827,7 @@ static void __exit pasemi_mac_cleanup_module(void)
 	pci_unregister_driver(&pasemi_mac_driver);
 }
 
-int pasemi_mac_init_module(void)
+static int pasemi_mac_init_module(void)
 {
 	int err;
 
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.h b/drivers/net/ethernet/pasemi/pasemi_mac.h
index 7c47e263b8c1..d7d2068b6f1b 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.h
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.h
@@ -1,20 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2006 PA Semi, Inc
  *
  * Driver for the PA6T-1682M onchip 1G/10G Ethernet MACs, soft state and
  * hardware register layouts.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef PASEMI_MAC_H
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c b/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c
index d0afc2b8f8e3..e1a304886a3c 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c
@@ -1,19 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2006-2008 PA Semi, Inc
  *
  * Ethtool hooks for the PA Semi PWRficient onchip 1G/10G Ethernet MACs
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index 0ee2490db729..a391cf6ee4b2 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # QLogic network device configuration
 #
@@ -86,6 +87,7 @@ config QED
 	depends on PCI
 	select ZLIB_INFLATE
 	select CRC8
+	select NET_DEVLINK
 	---help---
 	  This enables the support for ...
 
diff --git a/drivers/net/ethernet/qlogic/netxen/Makefile b/drivers/net/ethernet/qlogic/netxen/Makefile
index e14e60c88381..d6e80b3ebbc9 100644
--- a/drivers/net/ethernet/qlogic/netxen/Makefile
+++ b/drivers/net/ethernet/qlogic/netxen/Makefile
@@ -1,23 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-or-later
 # Copyright (C) 2003 - 2009 NetXen, Inc.
 # Copyright (C) 2009 - QLogic Corporation.
 # All rights reserved.
-# 
-# This program is free software; you can redistribute it and/or
-# modify it under the terms of the GNU General Public License
-# as published by the Free Software Foundation; either version 2
-# of the License, or (at your option) any later version.
-#                            
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#                                   
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, see <http://www.gnu.org/licenses/>.
-# 
-# The full GNU General Public License is included in this distribution
-# in the file called "COPYING".
-# 
 #
 
 
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
index 0a5e204a0179..3dce769d83a1 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h
@@ -1,24 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #ifndef _NETXEN_NIC_H_
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c
index 7503aa222392..433052f734ed 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c
@@ -1,24 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #include "netxen_nic_hw.h"
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index 3c1be87cdfa5..6a2d91d58968 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -1,24 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hdr.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hdr.h
index a310c2f6502a..09b33e1822a1 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hdr.h
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hdr.h
@@ -1,24 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #ifndef __NETXEN_NIC_HDR_H_
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
index 52ad80621335..6e12cd21ac90 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
@@ -1,24 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #include <linux/io-64-nonatomic-lo-hi.h>
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.h
index 7433c4d21601..de73766e1132 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.h
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.h
@@ -1,24 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #ifndef __NETXEN_NIC_HW_H_
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index 6547a9dd5935..94546ed5f867 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -1,24 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 7d9819d80e44..58e2eaf77014 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -1,24 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2003 - 2009 NetXen, Inc.
  * Copyright (C) 2009 - QLogic Corporation.
  * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called "COPYING".
- *
  */
 
 #include <linux/slab.h>
@@ -3264,6 +3248,7 @@ netxen_config_indev_addr(struct netxen_adapter *adapter,
 		struct net_device *dev, unsigned long event)
 {
 	struct in_device *indev;
+	struct in_ifaddr *ifa;
 
 	if (!netxen_destip_supported(adapter))
 		return;
@@ -3272,7 +3257,8 @@ netxen_config_indev_addr(struct netxen_adapter *adapter,
 	if (!indev)
 		return;
 
-	for_ifa(indev) {
+	rcu_read_lock();
+	in_dev_for_each_ifa_rcu(ifa, indev) {
 		switch (event) {
 		case NETDEV_UP:
 			netxen_list_config_ip(adapter, ifa, NX_IP_UP);
@@ -3283,8 +3269,8 @@ netxen_config_indev_addr(struct netxen_adapter *adapter,
 		default:
 			break;
 		}
-	} endfor_ifa(indev);
-
+	}
+	rcu_read_unlock();
 	in_dev_put(indev);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 2d8a77cc156b..89fe091c958d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -140,6 +140,7 @@ struct qed_cxt_mngr;
 struct qed_sb_sp_info;
 struct qed_ll2_info;
 struct qed_mcp_info;
+struct qed_llh_info;
 
 struct qed_rt_data {
 	u32	*init_val;
@@ -431,12 +432,16 @@ struct qed_qm_info {
 	u8 num_pf_rls;
 };
 
+#define QED_OVERFLOW_BIT	1
+
 struct qed_db_recovery_info {
 	struct list_head list;
 
 	/* Lock to protect the doorbell recovery mechanism list */
 	spinlock_t lock;
+	bool dorq_attn;
 	u32 db_recovery_counter;
+	unsigned long overflow;
 };
 
 struct storm_stats {
@@ -492,6 +497,9 @@ enum qed_mf_mode_bit {
 
 	/* Allow DSCP to TC mapping */
 	QED_MF_DSCP_TO_TC_MAP,
+
+	/* Do not insert a vlan tag with id 0 */
+	QED_MF_DONT_ADD_VLAN0_TAG,
 };
 
 enum qed_ufp_mode {
@@ -554,7 +562,6 @@ struct qed_hwfn {
 	u8				dp_level;
 	char				name[NAME_SIZE];
 
-	bool				first_on_engine;
 	bool				hw_init_done;
 
 	u8				num_funcs_on_engine;
@@ -735,6 +742,7 @@ struct qed_dev {
 #define QED_DEV_ID_MASK		0xff00
 #define QED_DEV_ID_MASK_BB	0x1600
 #define QED_DEV_ID_MASK_AH	0x8000
+#define QED_IS_E4(dev)  (QED_IS_BB(dev) || QED_IS_AH(dev))
 
 	u16	chip_num;
 #define CHIP_NUM_MASK                   0xffff
@@ -754,6 +762,7 @@ struct qed_dev {
 #define CHIP_BOND_ID_SHIFT              0
 
 	u8				num_engines;
+	u8				num_ports;
 	u8				num_ports_in_engine;
 	u8				num_funcs_in_port;
 
@@ -794,6 +803,11 @@ struct qed_dev {
 	u8				num_hwfns;
 	struct qed_hwfn			hwfns[MAX_HWFNS_PER_DEVICE];
 
+	/* Engine affinity */
+	u8				l2_affin_hint;
+	u8				fir_affin;
+	u8				iwarp_affin;
+
 	/* SRIOV */
 	struct qed_hw_sriov_info *p_iov_info;
 #define IS_QED_SRIOV(cdev)              (!!(cdev)->p_iov_info)
@@ -805,6 +819,13 @@ struct qed_dev {
 
 	u32				mcp_nvm_resp;
 
+	/* Recovery */
+	bool recov_in_prog;
+
+	/* LLH info */
+	u8 ppfid_bitmap;
+	struct qed_llh_info *p_llh_info;
+
 	/* Linux specific here */
 	struct  qede_dev		*edev;
 	struct  pci_dev			*pdev;
@@ -842,6 +863,9 @@ struct qed_dev {
 	u32 rdma_max_inline;
 	u32 rdma_max_srq_sge;
 	u16 tunn_feature_mask;
+
+	struct devlink			*dl;
+	bool				iwarp_cmt;
 };
 
 #define NUM_OF_VFS(dev)         (QED_IS_BB(dev) ? MAX_NUM_VFS_BB \
@@ -890,11 +914,18 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev,
 
 void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 int qed_device_num_engines(struct qed_dev *cdev);
-int qed_device_get_port_id(struct qed_dev *cdev);
 void qed_set_fw_mac_addr(__le16 *fw_msb,
 			 __le16 *fw_mid, __le16 *fw_lsb, u8 *mac);
 
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
+#define QED_IS_CMT(dev)		((dev)->num_hwfns > 1)
+/* Macros for getting the engine-affinitized hwfn (FIR: fcoe,iscsi,roce) */
+#define QED_FIR_AFFIN_HWFN(dev)		(&(dev)->hwfns[dev->fir_affin])
+#define QED_IWARP_AFFIN_HWFN(dev)       (&(dev)->hwfns[dev->iwarp_affin])
+#define QED_AFFIN_HWFN(dev)				   \
+	(QED_IS_IWARP_PERSONALITY(QED_LEADING_HWFN(dev)) ? \
+	 QED_IWARP_AFFIN_HWFN(dev) : QED_FIR_AFFIN_HWFN(dev))
+#define QED_AFFIN_HWFN_IDX(dev) (IS_LEAD_HWFN(QED_AFFIN_HWFN(dev)) ? 0 : 1)
 
 /* Flags for indication of required queues */
 #define PQ_FLAGS_RLS    (BIT(0))
@@ -914,12 +945,9 @@ u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
 u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
-#define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
-
 /* doorbell recovery mechanism */
 void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
-			     enum qed_db_rec_exec db_exec);
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn);
 bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
 
 /* Other Linux specific common definitions */
@@ -937,6 +965,10 @@ bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
 	writel((u32)val, (void __iomem *)((u8 __iomem *)\
 					  (cdev->doorbells) + (db_addr)))
 
+#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %			  \
+				  qed_device_num_ports((_p_hwfn)->cdev))
+int qed_device_num_ports(struct qed_dev *cdev);
+
 /* Prototypes */
 int qed_fill_dev_info(struct qed_dev *cdev,
 		      struct qed_dev_info *dev_info);
@@ -944,6 +976,7 @@ void qed_link_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt);
 u32 qed_unzip_data(struct qed_hwfn *p_hwfn,
 		   u32 input_len, u8 *input_buf,
 		   u32 max_size, u8 *unzip_buf);
+void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn);
 void qed_get_protocol_stats(struct qed_dev *cdev,
 			    enum qed_mcp_protocol_type type,
 			    union qed_mcp_protocol_stats *stats);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index c2ad405b2f50..8e1bdf58b9e7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -2129,17 +2129,18 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 					       rdma_tasks);
 		/* no need for break since RoCE coexist with Ethernet */
 	}
+	/* fall through */
 	case QED_PCI_ETH:
 	{
 		struct qed_eth_pf_params *p_params =
 		    &p_hwfn->pf_params.eth_pf_params;
 
-			if (!p_params->num_vf_cons)
-				p_params->num_vf_cons =
-				    ETH_PF_PARAMS_VF_CONS_DEFAULT;
-			qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH,
-						    p_params->num_cons,
-						    p_params->num_vf_cons);
+		if (!p_params->num_vf_cons)
+			p_params->num_vf_cons =
+			    ETH_PF_PARAMS_VF_CONS_DEFAULT;
+		qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH,
+					    p_params->num_cons,
+					    p_params->num_vf_cons);
 		p_hwfn->p_cxt_mngr->arfs_count = p_params->num_arfs_filters;
 		break;
 	}
@@ -2350,7 +2351,8 @@ qed_cxt_dynamic_ilt_alloc(struct qed_hwfn *p_hwfn,
 
 	/* Write via DMAE since the PSWRQ2_REG_ILT_MEMORY line is a wide-bus */
 	qed_dmae_host2grc(p_hwfn, p_ptt, (u64) (uintptr_t)&ilt_hw_entry,
-			  reg_offset, sizeof(ilt_hw_entry) / sizeof(u32), 0);
+			  reg_offset, sizeof(ilt_hw_entry) / sizeof(u32),
+			  NULL);
 
 	if (elem_type == QED_ELEM_CXT) {
 		u32 last_cid_allocated = (1 + (iid / elems_per_p)) *
@@ -2456,7 +2458,7 @@ qed_cxt_free_ilt_range(struct qed_hwfn *p_hwfn,
 				  (u64) (uintptr_t) &ilt_hw_entry,
 				  reg_offset,
 				  sizeof(ilt_hw_entry) / sizeof(u32),
-				  0);
+				  NULL);
 	}
 
 	qed_ptt_release(p_hwfn, p_ptt);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 69966dfc6e3d..5c6a276f69ac 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -204,9 +204,7 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
 	else
 		p_data->arr[type].update = DONT_UPDATE_DCB_DSCP;
 
-	/* Do not add vlan tag 0 when DCB is enabled and port in UFP/OV mode */
-	if ((test_bit(QED_MF_8021Q_TAGGING, &p_hwfn->cdev->mf_bits) ||
-	     test_bit(QED_MF_8021AD_TAGGING, &p_hwfn->cdev->mf_bits)))
+	if (test_bit(QED_MF_DONT_ADD_VLAN0_TAG, &p_hwfn->cdev->mf_bits))
 		p_data->arr[type].dont_add_vlan0 = true;
 
 	/* QM reconf data */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 979f1e4bc18b..5ea6c4fc6050 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
- *
- * This software is available under the terms of the GNU General Public License
- * (GPL) Version 2, available from the file COPYING in the main directory of
- * this source tree.
  */
 
 #include <linux/module.h>
@@ -2537,7 +2534,7 @@ static u32 qed_grc_dump_addr_range(struct qed_hwfn *p_hwfn,
 	    (len >= s_platform_defs[dev_data->platform_id].dmae_thresh ||
 	     wide_bus)) {
 		if (!qed_dmae_grc2host(p_hwfn, p_ptt, DWORDS_TO_BYTES(addr),
-				       (u64)(uintptr_t)(dump_buf), len, 0))
+				       (u64)(uintptr_t)(dump_buf), len, NULL))
 			return len;
 		dev_data->use_dmae = 0;
 		DP_VERBOSE(p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.h b/drivers/net/ethernet/qlogic/qed/qed_debug.h
index ea1cc8eaa125..e47e0e8d75b0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* QLogic qed NIC Driver
  * Copyright (c) 2015 QLogic Corporation
- *
- * This software is available under the terms of the GNU General Public License
- * (GPL) Version 2, available from the file COPYING in the main directory of
- * this source tree.
  */
 
 #ifndef _QED_DEBUGFS_H
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 2ecaaaa4469a..a1ebc2b1ca0b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -102,11 +102,15 @@ static void qed_db_recovery_dp_entry(struct qed_hwfn *p_hwfn,
 
 /* Doorbell address sanity (address within doorbell bar range) */
 static bool qed_db_rec_sanity(struct qed_dev *cdev,
-			      void __iomem *db_addr, void *db_data)
+			      void __iomem *db_addr,
+			      enum qed_db_rec_width db_width,
+			      void *db_data)
 {
+	u32 width = (db_width == DB_REC_WIDTH_32B) ? 32 : 64;
+
 	/* Make sure doorbell address is within the doorbell bar */
 	if (db_addr < cdev->doorbells ||
-	    (u8 __iomem *)db_addr >
+	    (u8 __iomem *)db_addr + width >
 	    (u8 __iomem *)cdev->doorbells + cdev->db_size) {
 		WARN(true,
 		     "Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n",
@@ -159,7 +163,7 @@ int qed_db_recovery_add(struct qed_dev *cdev,
 	}
 
 	/* Sanitize doorbell address */
-	if (!qed_db_rec_sanity(cdev, db_addr, db_data))
+	if (!qed_db_rec_sanity(cdev, db_addr, db_width, db_data))
 		return -EINVAL;
 
 	/* Obtain hwfn from doorbell address */
@@ -205,10 +209,6 @@ int qed_db_recovery_del(struct qed_dev *cdev,
 		return 0;
 	}
 
-	/* Sanitize doorbell address */
-	if (!qed_db_rec_sanity(cdev, db_addr, db_data))
-		return -EINVAL;
-
 	/* Obtain hwfn from doorbell address */
 	p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
 
@@ -300,31 +300,24 @@ void qed_db_recovery_dp(struct qed_hwfn *p_hwfn)
 
 /* Ring the doorbell of a single doorbell recovery entry */
 static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
-				 struct qed_db_recovery_entry *db_entry,
-				 enum qed_db_rec_exec db_exec)
-{
-	if (db_exec != DB_REC_ONCE) {
-		/* Print according to width */
-		if (db_entry->db_width == DB_REC_WIDTH_32B) {
-			DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
-				   "%s doorbell address %p data %x\n",
-				   db_exec == DB_REC_DRY_RUN ?
-				   "would have rung" : "ringing",
-				   db_entry->db_addr,
-				   *(u32 *)db_entry->db_data);
-		} else {
-			DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
-				   "%s doorbell address %p data %llx\n",
-				   db_exec == DB_REC_DRY_RUN ?
-				   "would have rung" : "ringing",
-				   db_entry->db_addr,
-				   *(u64 *)(db_entry->db_data));
-		}
+				 struct qed_db_recovery_entry *db_entry)
+{
+	/* Print according to width */
+	if (db_entry->db_width == DB_REC_WIDTH_32B) {
+		DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+			   "ringing doorbell address %p data %x\n",
+			   db_entry->db_addr,
+			   *(u32 *)db_entry->db_data);
+	} else {
+		DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+			   "ringing doorbell address %p data %llx\n",
+			   db_entry->db_addr,
+			   *(u64 *)(db_entry->db_data));
 	}
 
 	/* Sanity */
 	if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr,
-			       db_entry->db_data))
+			       db_entry->db_width, db_entry->db_data))
 		return;
 
 	/* Flush the write combined buffer. Since there are multiple doorbelling
@@ -334,14 +327,12 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
 	wmb();
 
 	/* Ring the doorbell */
-	if (db_exec == DB_REC_REAL_DEAL || db_exec == DB_REC_ONCE) {
-		if (db_entry->db_width == DB_REC_WIDTH_32B)
-			DIRECT_REG_WR(db_entry->db_addr,
-				      *(u32 *)(db_entry->db_data));
-		else
-			DIRECT_REG_WR64(db_entry->db_addr,
-					*(u64 *)(db_entry->db_data));
-	}
+	if (db_entry->db_width == DB_REC_WIDTH_32B)
+		DIRECT_REG_WR(db_entry->db_addr,
+			      *(u32 *)(db_entry->db_data));
+	else
+		DIRECT_REG_WR64(db_entry->db_addr,
+				*(u64 *)(db_entry->db_data));
 
 	/* Flush the write combined buffer. Next doorbell may come from a
 	 * different entity to the same address...
@@ -350,33 +341,946 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
 }
 
 /* Traverse the doorbell recovery entry list and ring all the doorbells */
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
-			     enum qed_db_rec_exec db_exec)
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn)
 {
 	struct qed_db_recovery_entry *db_entry = NULL;
 
-	if (db_exec != DB_REC_ONCE) {
-		DP_NOTICE(p_hwfn,
-			  "Executing doorbell recovery. Counter was %d\n",
-			  p_hwfn->db_recovery_info.db_recovery_counter);
+	DP_NOTICE(p_hwfn, "Executing doorbell recovery. Counter was %d\n",
+		  p_hwfn->db_recovery_info.db_recovery_counter);
 
-		/* Track amount of times recovery was executed */
-		p_hwfn->db_recovery_info.db_recovery_counter++;
-	}
+	/* Track amount of times recovery was executed */
+	p_hwfn->db_recovery_info.db_recovery_counter++;
 
 	/* Protect the list */
 	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
 	list_for_each_entry(db_entry,
-			    &p_hwfn->db_recovery_info.list, list_entry) {
-		qed_db_recovery_ring(p_hwfn, db_entry, db_exec);
-		if (db_exec == DB_REC_ONCE)
+			    &p_hwfn->db_recovery_info.list, list_entry)
+		qed_db_recovery_ring(p_hwfn, db_entry);
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+}
+
+/******************** Doorbell Recovery end ****************/
+
+/********************************** NIG LLH ***********************************/
+
+enum qed_llh_filter_type {
+	QED_LLH_FILTER_TYPE_MAC,
+	QED_LLH_FILTER_TYPE_PROTOCOL,
+};
+
+struct qed_llh_mac_filter {
+	u8 addr[ETH_ALEN];
+};
+
+struct qed_llh_protocol_filter {
+	enum qed_llh_prot_filter_type_t type;
+	u16 source_port_or_eth_type;
+	u16 dest_port;
+};
+
+union qed_llh_filter {
+	struct qed_llh_mac_filter mac;
+	struct qed_llh_protocol_filter protocol;
+};
+
+struct qed_llh_filter_info {
+	bool b_enabled;
+	u32 ref_cnt;
+	enum qed_llh_filter_type type;
+	union qed_llh_filter filter;
+};
+
+struct qed_llh_info {
+	/* Number of LLH filters banks */
+	u8 num_ppfid;
+
+#define MAX_NUM_PPFID   8
+	u8 ppfid_array[MAX_NUM_PPFID];
+
+	/* Array of filters arrays:
+	 * "num_ppfid" elements of filters banks, where each is an array of
+	 * "NIG_REG_LLH_FUNC_FILTER_EN_SIZE" filters.
+	 */
+	struct qed_llh_filter_info **pp_filters;
+};
+
+static void qed_llh_free(struct qed_dev *cdev)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+	u32 i;
+
+	if (p_llh_info) {
+		if (p_llh_info->pp_filters)
+			for (i = 0; i < p_llh_info->num_ppfid; i++)
+				kfree(p_llh_info->pp_filters[i]);
+
+		kfree(p_llh_info->pp_filters);
+	}
+
+	kfree(p_llh_info);
+	cdev->p_llh_info = NULL;
+}
+
+static int qed_llh_alloc(struct qed_dev *cdev)
+{
+	struct qed_llh_info *p_llh_info;
+	u32 size, i;
+
+	p_llh_info = kzalloc(sizeof(*p_llh_info), GFP_KERNEL);
+	if (!p_llh_info)
+		return -ENOMEM;
+	cdev->p_llh_info = p_llh_info;
+
+	for (i = 0; i < MAX_NUM_PPFID; i++) {
+		if (!(cdev->ppfid_bitmap & (0x1 << i)))
+			continue;
+
+		p_llh_info->ppfid_array[p_llh_info->num_ppfid] = i;
+		DP_VERBOSE(cdev, QED_MSG_SP, "ppfid_array[%d] = %hhd\n",
+			   p_llh_info->num_ppfid, i);
+		p_llh_info->num_ppfid++;
+	}
+
+	size = p_llh_info->num_ppfid * sizeof(*p_llh_info->pp_filters);
+	p_llh_info->pp_filters = kzalloc(size, GFP_KERNEL);
+	if (!p_llh_info->pp_filters)
+		return -ENOMEM;
+
+	size = NIG_REG_LLH_FUNC_FILTER_EN_SIZE *
+	    sizeof(**p_llh_info->pp_filters);
+	for (i = 0; i < p_llh_info->num_ppfid; i++) {
+		p_llh_info->pp_filters[i] = kzalloc(size, GFP_KERNEL);
+		if (!p_llh_info->pp_filters[i])
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int qed_llh_shadow_sanity(struct qed_dev *cdev,
+				 u8 ppfid, u8 filter_idx, const char *action)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+
+	if (ppfid >= p_llh_info->num_ppfid) {
+		DP_NOTICE(cdev,
+			  "LLH shadow [%s]: using ppfid %d while only %d ppfids are available\n",
+			  action, ppfid, p_llh_info->num_ppfid);
+		return -EINVAL;
+	}
+
+	if (filter_idx >= NIG_REG_LLH_FUNC_FILTER_EN_SIZE) {
+		DP_NOTICE(cdev,
+			  "LLH shadow [%s]: using filter_idx %d while only %d filters are available\n",
+			  action, filter_idx, NIG_REG_LLH_FUNC_FILTER_EN_SIZE);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#define QED_LLH_INVALID_FILTER_IDX      0xff
+
+static int
+qed_llh_shadow_search_filter(struct qed_dev *cdev,
+			     u8 ppfid,
+			     union qed_llh_filter *p_filter, u8 *p_filter_idx)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+	struct qed_llh_filter_info *p_filters;
+	int rc;
+	u8 i;
+
+	rc = qed_llh_shadow_sanity(cdev, ppfid, 0, "search");
+	if (rc)
+		return rc;
+
+	*p_filter_idx = QED_LLH_INVALID_FILTER_IDX;
+
+	p_filters = p_llh_info->pp_filters[ppfid];
+	for (i = 0; i < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; i++) {
+		if (!memcmp(p_filter, &p_filters[i].filter,
+			    sizeof(*p_filter))) {
+			*p_filter_idx = i;
 			break;
+		}
 	}
 
-	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+	return 0;
 }
 
-/******************** Doorbell Recovery end ****************/
+static int
+qed_llh_shadow_get_free_idx(struct qed_dev *cdev, u8 ppfid, u8 *p_filter_idx)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+	struct qed_llh_filter_info *p_filters;
+	int rc;
+	u8 i;
+
+	rc = qed_llh_shadow_sanity(cdev, ppfid, 0, "get_free_idx");
+	if (rc)
+		return rc;
+
+	*p_filter_idx = QED_LLH_INVALID_FILTER_IDX;
+
+	p_filters = p_llh_info->pp_filters[ppfid];
+	for (i = 0; i < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; i++) {
+		if (!p_filters[i].b_enabled) {
+			*p_filter_idx = i;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int
+__qed_llh_shadow_add_filter(struct qed_dev *cdev,
+			    u8 ppfid,
+			    u8 filter_idx,
+			    enum qed_llh_filter_type type,
+			    union qed_llh_filter *p_filter, u32 *p_ref_cnt)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+	struct qed_llh_filter_info *p_filters;
+	int rc;
+
+	rc = qed_llh_shadow_sanity(cdev, ppfid, filter_idx, "add");
+	if (rc)
+		return rc;
+
+	p_filters = p_llh_info->pp_filters[ppfid];
+	if (!p_filters[filter_idx].ref_cnt) {
+		p_filters[filter_idx].b_enabled = true;
+		p_filters[filter_idx].type = type;
+		memcpy(&p_filters[filter_idx].filter, p_filter,
+		       sizeof(p_filters[filter_idx].filter));
+	}
+
+	*p_ref_cnt = ++p_filters[filter_idx].ref_cnt;
+
+	return 0;
+}
+
+static int
+qed_llh_shadow_add_filter(struct qed_dev *cdev,
+			  u8 ppfid,
+			  enum qed_llh_filter_type type,
+			  union qed_llh_filter *p_filter,
+			  u8 *p_filter_idx, u32 *p_ref_cnt)
+{
+	int rc;
+
+	/* Check if the same filter already exist */
+	rc = qed_llh_shadow_search_filter(cdev, ppfid, p_filter, p_filter_idx);
+	if (rc)
+		return rc;
+
+	/* Find a new entry in case of a new filter */
+	if (*p_filter_idx == QED_LLH_INVALID_FILTER_IDX) {
+		rc = qed_llh_shadow_get_free_idx(cdev, ppfid, p_filter_idx);
+		if (rc)
+			return rc;
+	}
+
+	/* No free entry was found */
+	if (*p_filter_idx == QED_LLH_INVALID_FILTER_IDX) {
+		DP_NOTICE(cdev,
+			  "Failed to find an empty LLH filter to utilize [ppfid %d]\n",
+			  ppfid);
+		return -EINVAL;
+	}
+
+	return __qed_llh_shadow_add_filter(cdev, ppfid, *p_filter_idx, type,
+					   p_filter, p_ref_cnt);
+}
+
+static int
+__qed_llh_shadow_remove_filter(struct qed_dev *cdev,
+			       u8 ppfid, u8 filter_idx, u32 *p_ref_cnt)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+	struct qed_llh_filter_info *p_filters;
+	int rc;
+
+	rc = qed_llh_shadow_sanity(cdev, ppfid, filter_idx, "remove");
+	if (rc)
+		return rc;
+
+	p_filters = p_llh_info->pp_filters[ppfid];
+	if (!p_filters[filter_idx].ref_cnt) {
+		DP_NOTICE(cdev,
+			  "LLH shadow: trying to remove a filter with ref_cnt=0\n");
+		return -EINVAL;
+	}
+
+	*p_ref_cnt = --p_filters[filter_idx].ref_cnt;
+	if (!p_filters[filter_idx].ref_cnt)
+		memset(&p_filters[filter_idx],
+		       0, sizeof(p_filters[filter_idx]));
+
+	return 0;
+}
+
+static int
+qed_llh_shadow_remove_filter(struct qed_dev *cdev,
+			     u8 ppfid,
+			     union qed_llh_filter *p_filter,
+			     u8 *p_filter_idx, u32 *p_ref_cnt)
+{
+	int rc;
+
+	rc = qed_llh_shadow_search_filter(cdev, ppfid, p_filter, p_filter_idx);
+	if (rc)
+		return rc;
+
+	/* No matching filter was found */
+	if (*p_filter_idx == QED_LLH_INVALID_FILTER_IDX) {
+		DP_NOTICE(cdev, "Failed to find a filter in the LLH shadow\n");
+		return -EINVAL;
+	}
+
+	return __qed_llh_shadow_remove_filter(cdev, ppfid, *p_filter_idx,
+					      p_ref_cnt);
+}
+
+static int qed_llh_abs_ppfid(struct qed_dev *cdev, u8 ppfid, u8 *p_abs_ppfid)
+{
+	struct qed_llh_info *p_llh_info = cdev->p_llh_info;
+
+	if (ppfid >= p_llh_info->num_ppfid) {
+		DP_NOTICE(cdev,
+			  "ppfid %d is not valid, available indices are 0..%hhd\n",
+			  ppfid, p_llh_info->num_ppfid - 1);
+		*p_abs_ppfid = 0;
+		return -EINVAL;
+	}
+
+	*p_abs_ppfid = p_llh_info->ppfid_array[ppfid];
+
+	return 0;
+}
+
+static int
+qed_llh_set_engine_affin(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	enum qed_eng eng;
+	u8 ppfid;
+	int rc;
+
+	rc = qed_mcp_get_engine_config(p_hwfn, p_ptt);
+	if (rc != 0 && rc != -EOPNOTSUPP) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to get the engine affinity configuration\n");
+		return rc;
+	}
+
+	/* RoCE PF is bound to a single engine */
+	if (QED_IS_ROCE_PERSONALITY(p_hwfn)) {
+		eng = cdev->fir_affin ? QED_ENG1 : QED_ENG0;
+		rc = qed_llh_set_roce_affinity(cdev, eng);
+		if (rc) {
+			DP_NOTICE(cdev,
+				  "Failed to set the RoCE engine affinity\n");
+			return rc;
+		}
+
+		DP_VERBOSE(cdev,
+			   QED_MSG_SP,
+			   "LLH: Set the engine affinity of RoCE packets as %d\n",
+			   eng);
+	}
+
+	/* Storage PF is bound to a single engine while L2 PF uses both */
+	if (QED_IS_FCOE_PERSONALITY(p_hwfn) || QED_IS_ISCSI_PERSONALITY(p_hwfn))
+		eng = cdev->fir_affin ? QED_ENG1 : QED_ENG0;
+	else			/* L2_PERSONALITY */
+		eng = QED_BOTH_ENG;
+
+	for (ppfid = 0; ppfid < cdev->p_llh_info->num_ppfid; ppfid++) {
+		rc = qed_llh_set_ppfid_affinity(cdev, ppfid, eng);
+		if (rc) {
+			DP_NOTICE(cdev,
+				  "Failed to set the engine affinity of ppfid %d\n",
+				  ppfid);
+			return rc;
+		}
+	}
+
+	DP_VERBOSE(cdev, QED_MSG_SP,
+		   "LLH: Set the engine affinity of non-RoCE packets as %d\n",
+		   eng);
+
+	return 0;
+}
+
+static int qed_llh_hw_init_pf(struct qed_hwfn *p_hwfn,
+			      struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u8 ppfid, abs_ppfid;
+	int rc;
+
+	for (ppfid = 0; ppfid < cdev->p_llh_info->num_ppfid; ppfid++) {
+		u32 addr;
+
+		rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+		if (rc)
+			return rc;
+
+		addr = NIG_REG_LLH_PPFID2PFID_TBL_0 + abs_ppfid * 0x4;
+		qed_wr(p_hwfn, p_ptt, addr, p_hwfn->rel_pf_id);
+	}
+
+	if (test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits) &&
+	    !QED_IS_FCOE_PERSONALITY(p_hwfn)) {
+		rc = qed_llh_add_mac_filter(cdev, 0,
+					    p_hwfn->hw_info.hw_mac_addr);
+		if (rc)
+			DP_NOTICE(cdev,
+				  "Failed to add an LLH filter with the primary MAC\n");
+	}
+
+	if (QED_IS_CMT(cdev)) {
+		rc = qed_llh_set_engine_affin(p_hwfn, p_ptt);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+u8 qed_llh_get_num_ppfid(struct qed_dev *cdev)
+{
+	return cdev->p_llh_info->num_ppfid;
+}
+
+#define NIG_REG_PPF_TO_ENGINE_SEL_ROCE_MASK             0x3
+#define NIG_REG_PPF_TO_ENGINE_SEL_ROCE_SHIFT            0
+#define NIG_REG_PPF_TO_ENGINE_SEL_NON_ROCE_MASK         0x3
+#define NIG_REG_PPF_TO_ENGINE_SEL_NON_ROCE_SHIFT        2
+
+int qed_llh_set_ppfid_affinity(struct qed_dev *cdev, u8 ppfid, enum qed_eng eng)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+	u32 addr, val, eng_sel;
+	u8 abs_ppfid;
+	int rc = 0;
+
+	if (!p_ptt)
+		return -EAGAIN;
+
+	if (!QED_IS_CMT(cdev))
+		goto out;
+
+	rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+	if (rc)
+		goto out;
+
+	switch (eng) {
+	case QED_ENG0:
+		eng_sel = 0;
+		break;
+	case QED_ENG1:
+		eng_sel = 1;
+		break;
+	case QED_BOTH_ENG:
+		eng_sel = 2;
+		break;
+	default:
+		DP_NOTICE(cdev, "Invalid affinity value for ppfid [%d]\n", eng);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	addr = NIG_REG_PPF_TO_ENGINE_SEL + abs_ppfid * 0x4;
+	val = qed_rd(p_hwfn, p_ptt, addr);
+	SET_FIELD(val, NIG_REG_PPF_TO_ENGINE_SEL_NON_ROCE, eng_sel);
+	qed_wr(p_hwfn, p_ptt, addr, val);
+
+	/* The iWARP affinity is set as the affinity of ppfid 0 */
+	if (!ppfid && QED_IS_IWARP_PERSONALITY(p_hwfn))
+		cdev->iwarp_affin = (eng == QED_ENG1) ? 1 : 0;
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+
+	return rc;
+}
+
+int qed_llh_set_roce_affinity(struct qed_dev *cdev, enum qed_eng eng)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+	u32 addr, val, eng_sel;
+	u8 ppfid, abs_ppfid;
+	int rc = 0;
+
+	if (!p_ptt)
+		return -EAGAIN;
+
+	if (!QED_IS_CMT(cdev))
+		goto out;
+
+	switch (eng) {
+	case QED_ENG0:
+		eng_sel = 0;
+		break;
+	case QED_ENG1:
+		eng_sel = 1;
+		break;
+	case QED_BOTH_ENG:
+		eng_sel = 2;
+		qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_ENG_CLS_ROCE_QP_SEL,
+		       0xf);  /* QP bit 15 */
+		break;
+	default:
+		DP_NOTICE(cdev, "Invalid affinity value for RoCE [%d]\n", eng);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	for (ppfid = 0; ppfid < cdev->p_llh_info->num_ppfid; ppfid++) {
+		rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+		if (rc)
+			goto out;
+
+		addr = NIG_REG_PPF_TO_ENGINE_SEL + abs_ppfid * 0x4;
+		val = qed_rd(p_hwfn, p_ptt, addr);
+		SET_FIELD(val, NIG_REG_PPF_TO_ENGINE_SEL_ROCE, eng_sel);
+		qed_wr(p_hwfn, p_ptt, addr, val);
+	}
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+
+	return rc;
+}
+
+struct qed_llh_filter_details {
+	u64 value;
+	u32 mode;
+	u32 protocol_type;
+	u32 hdr_sel;
+	u32 enable;
+};
+
+static int
+qed_llh_access_filter(struct qed_hwfn *p_hwfn,
+		      struct qed_ptt *p_ptt,
+		      u8 abs_ppfid,
+		      u8 filter_idx,
+		      struct qed_llh_filter_details *p_details)
+{
+	struct qed_dmae_params params = {0};
+	u32 addr;
+	u8 pfid;
+	int rc;
+
+	/* The NIG/LLH registers that are accessed in this function have only 16
+	 * rows which are exposed to a PF. I.e. only the 16 filters of its
+	 * default ppfid. Accessing filters of other ppfids requires pretending
+	 * to another PFs.
+	 * The calculation of PPFID->PFID in AH is based on the relative index
+	 * of a PF on its port.
+	 * For BB the pfid is actually the abs_ppfid.
+	 */
+	if (QED_IS_BB(p_hwfn->cdev))
+		pfid = abs_ppfid;
+	else
+		pfid = abs_ppfid * p_hwfn->cdev->num_ports_in_engine +
+		    MFW_PORT(p_hwfn);
+
+	/* Filter enable - should be done first when removing a filter */
+	if (!p_details->enable) {
+		qed_fid_pretend(p_hwfn, p_ptt,
+				pfid << PXP_PRETEND_CONCRETE_FID_PFID_SHIFT);
+
+		addr = NIG_REG_LLH_FUNC_FILTER_EN + filter_idx * 0x4;
+		qed_wr(p_hwfn, p_ptt, addr, p_details->enable);
+
+		qed_fid_pretend(p_hwfn, p_ptt,
+				p_hwfn->rel_pf_id <<
+				PXP_PRETEND_CONCRETE_FID_PFID_SHIFT);
+	}
+
+	/* Filter value */
+	addr = NIG_REG_LLH_FUNC_FILTER_VALUE + 2 * filter_idx * 0x4;
+
+	params.flags = QED_DMAE_FLAG_PF_DST;
+	params.dst_pfid = pfid;
+	rc = qed_dmae_host2grc(p_hwfn,
+			       p_ptt,
+			       (u64)(uintptr_t)&p_details->value,
+			       addr, 2 /* size_in_dwords */,
+			       &params);
+	if (rc)
+		return rc;
+
+	qed_fid_pretend(p_hwfn, p_ptt,
+			pfid << PXP_PRETEND_CONCRETE_FID_PFID_SHIFT);
+
+	/* Filter mode */
+	addr = NIG_REG_LLH_FUNC_FILTER_MODE + filter_idx * 0x4;
+	qed_wr(p_hwfn, p_ptt, addr, p_details->mode);
+
+	/* Filter protocol type */
+	addr = NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE + filter_idx * 0x4;
+	qed_wr(p_hwfn, p_ptt, addr, p_details->protocol_type);
+
+	/* Filter header select */
+	addr = NIG_REG_LLH_FUNC_FILTER_HDR_SEL + filter_idx * 0x4;
+	qed_wr(p_hwfn, p_ptt, addr, p_details->hdr_sel);
+
+	/* Filter enable - should be done last when adding a filter */
+	if (p_details->enable) {
+		addr = NIG_REG_LLH_FUNC_FILTER_EN + filter_idx * 0x4;
+		qed_wr(p_hwfn, p_ptt, addr, p_details->enable);
+	}
+
+	qed_fid_pretend(p_hwfn, p_ptt,
+			p_hwfn->rel_pf_id <<
+			PXP_PRETEND_CONCRETE_FID_PFID_SHIFT);
+
+	return 0;
+}
+
+static int
+qed_llh_add_filter(struct qed_hwfn *p_hwfn,
+		   struct qed_ptt *p_ptt,
+		   u8 abs_ppfid,
+		   u8 filter_idx, u8 filter_prot_type, u32 high, u32 low)
+{
+	struct qed_llh_filter_details filter_details;
+
+	filter_details.enable = 1;
+	filter_details.value = ((u64)high << 32) | low;
+	filter_details.hdr_sel = 0;
+	filter_details.protocol_type = filter_prot_type;
+	/* Mode: 0: MAC-address classification 1: protocol classification */
+	filter_details.mode = filter_prot_type ? 1 : 0;
+
+	return qed_llh_access_filter(p_hwfn, p_ptt, abs_ppfid, filter_idx,
+				     &filter_details);
+}
+
+static int
+qed_llh_remove_filter(struct qed_hwfn *p_hwfn,
+		      struct qed_ptt *p_ptt, u8 abs_ppfid, u8 filter_idx)
+{
+	struct qed_llh_filter_details filter_details = {0};
+
+	return qed_llh_access_filter(p_hwfn, p_ptt, abs_ppfid, filter_idx,
+				     &filter_details);
+}
+
+int qed_llh_add_mac_filter(struct qed_dev *cdev,
+			   u8 ppfid, u8 mac_addr[ETH_ALEN])
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+	union qed_llh_filter filter = {};
+	u8 filter_idx, abs_ppfid;
+	u32 high, low, ref_cnt;
+	int rc = 0;
+
+	if (!p_ptt)
+		return -EAGAIN;
+
+	if (!test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits))
+		goto out;
+
+	memcpy(filter.mac.addr, mac_addr, ETH_ALEN);
+	rc = qed_llh_shadow_add_filter(cdev, ppfid,
+				       QED_LLH_FILTER_TYPE_MAC,
+				       &filter, &filter_idx, &ref_cnt);
+	if (rc)
+		goto err;
+
+	/* Configure the LLH only in case of a new the filter */
+	if (ref_cnt == 1) {
+		rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+		if (rc)
+			goto err;
+
+		high = mac_addr[1] | (mac_addr[0] << 8);
+		low = mac_addr[5] | (mac_addr[4] << 8) | (mac_addr[3] << 16) |
+		      (mac_addr[2] << 24);
+		rc = qed_llh_add_filter(p_hwfn, p_ptt, abs_ppfid, filter_idx,
+					0, high, low);
+		if (rc)
+			goto err;
+	}
+
+	DP_VERBOSE(cdev,
+		   QED_MSG_SP,
+		   "LLH: Added MAC filter [%pM] to ppfid %hhd [abs %hhd] at idx %hhd [ref_cnt %d]\n",
+		   mac_addr, ppfid, abs_ppfid, filter_idx, ref_cnt);
+
+	goto out;
+
+err:	DP_NOTICE(cdev,
+		  "LLH: Failed to add MAC filter [%pM] to ppfid %hhd\n",
+		  mac_addr, ppfid);
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+
+	return rc;
+}
+
+static int
+qed_llh_protocol_filter_stringify(struct qed_dev *cdev,
+				  enum qed_llh_prot_filter_type_t type,
+				  u16 source_port_or_eth_type,
+				  u16 dest_port, u8 *str, size_t str_len)
+{
+	switch (type) {
+	case QED_LLH_FILTER_ETHERTYPE:
+		snprintf(str, str_len, "Ethertype 0x%04x",
+			 source_port_or_eth_type);
+		break;
+	case QED_LLH_FILTER_TCP_SRC_PORT:
+		snprintf(str, str_len, "TCP src port 0x%04x",
+			 source_port_or_eth_type);
+		break;
+	case QED_LLH_FILTER_UDP_SRC_PORT:
+		snprintf(str, str_len, "UDP src port 0x%04x",
+			 source_port_or_eth_type);
+		break;
+	case QED_LLH_FILTER_TCP_DEST_PORT:
+		snprintf(str, str_len, "TCP dst port 0x%04x", dest_port);
+		break;
+	case QED_LLH_FILTER_UDP_DEST_PORT:
+		snprintf(str, str_len, "UDP dst port 0x%04x", dest_port);
+		break;
+	case QED_LLH_FILTER_TCP_SRC_AND_DEST_PORT:
+		snprintf(str, str_len, "TCP src/dst ports 0x%04x/0x%04x",
+			 source_port_or_eth_type, dest_port);
+		break;
+	case QED_LLH_FILTER_UDP_SRC_AND_DEST_PORT:
+		snprintf(str, str_len, "UDP src/dst ports 0x%04x/0x%04x",
+			 source_port_or_eth_type, dest_port);
+		break;
+	default:
+		DP_NOTICE(cdev,
+			  "Non valid LLH protocol filter type %d\n", type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+qed_llh_protocol_filter_to_hilo(struct qed_dev *cdev,
+				enum qed_llh_prot_filter_type_t type,
+				u16 source_port_or_eth_type,
+				u16 dest_port, u32 *p_high, u32 *p_low)
+{
+	*p_high = 0;
+	*p_low = 0;
+
+	switch (type) {
+	case QED_LLH_FILTER_ETHERTYPE:
+		*p_high = source_port_or_eth_type;
+		break;
+	case QED_LLH_FILTER_TCP_SRC_PORT:
+	case QED_LLH_FILTER_UDP_SRC_PORT:
+		*p_low = source_port_or_eth_type << 16;
+		break;
+	case QED_LLH_FILTER_TCP_DEST_PORT:
+	case QED_LLH_FILTER_UDP_DEST_PORT:
+		*p_low = dest_port;
+		break;
+	case QED_LLH_FILTER_TCP_SRC_AND_DEST_PORT:
+	case QED_LLH_FILTER_UDP_SRC_AND_DEST_PORT:
+		*p_low = (source_port_or_eth_type << 16) | dest_port;
+		break;
+	default:
+		DP_NOTICE(cdev,
+			  "Non valid LLH protocol filter type %d\n", type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int
+qed_llh_add_protocol_filter(struct qed_dev *cdev,
+			    u8 ppfid,
+			    enum qed_llh_prot_filter_type_t type,
+			    u16 source_port_or_eth_type, u16 dest_port)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+	u8 filter_idx, abs_ppfid, str[32], type_bitmap;
+	union qed_llh_filter filter = {};
+	u32 high, low, ref_cnt;
+	int rc = 0;
+
+	if (!p_ptt)
+		return -EAGAIN;
+
+	if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits))
+		goto out;
+
+	rc = qed_llh_protocol_filter_stringify(cdev, type,
+					       source_port_or_eth_type,
+					       dest_port, str, sizeof(str));
+	if (rc)
+		goto err;
+
+	filter.protocol.type = type;
+	filter.protocol.source_port_or_eth_type = source_port_or_eth_type;
+	filter.protocol.dest_port = dest_port;
+	rc = qed_llh_shadow_add_filter(cdev,
+				       ppfid,
+				       QED_LLH_FILTER_TYPE_PROTOCOL,
+				       &filter, &filter_idx, &ref_cnt);
+	if (rc)
+		goto err;
+
+	rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+	if (rc)
+		goto err;
+
+	/* Configure the LLH only in case of a new the filter */
+	if (ref_cnt == 1) {
+		rc = qed_llh_protocol_filter_to_hilo(cdev, type,
+						     source_port_or_eth_type,
+						     dest_port, &high, &low);
+		if (rc)
+			goto err;
+
+		type_bitmap = 0x1 << type;
+		rc = qed_llh_add_filter(p_hwfn, p_ptt, abs_ppfid,
+					filter_idx, type_bitmap, high, low);
+		if (rc)
+			goto err;
+	}
+
+	DP_VERBOSE(cdev,
+		   QED_MSG_SP,
+		   "LLH: Added protocol filter [%s] to ppfid %hhd [abs %hhd] at idx %hhd [ref_cnt %d]\n",
+		   str, ppfid, abs_ppfid, filter_idx, ref_cnt);
+
+	goto out;
+
+err:	DP_NOTICE(p_hwfn,
+		  "LLH: Failed to add protocol filter [%s] to ppfid %hhd\n",
+		  str, ppfid);
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+
+	return rc;
+}
+
+void qed_llh_remove_mac_filter(struct qed_dev *cdev,
+			       u8 ppfid, u8 mac_addr[ETH_ALEN])
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+	union qed_llh_filter filter = {};
+	u8 filter_idx, abs_ppfid;
+	int rc = 0;
+	u32 ref_cnt;
+
+	if (!p_ptt)
+		return;
+
+	if (!test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits))
+		goto out;
+
+	ether_addr_copy(filter.mac.addr, mac_addr);
+	rc = qed_llh_shadow_remove_filter(cdev, ppfid, &filter, &filter_idx,
+					  &ref_cnt);
+	if (rc)
+		goto err;
+
+	rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+	if (rc)
+		goto err;
+
+	/* Remove from the LLH in case the filter is not in use */
+	if (!ref_cnt) {
+		rc = qed_llh_remove_filter(p_hwfn, p_ptt, abs_ppfid,
+					   filter_idx);
+		if (rc)
+			goto err;
+	}
+
+	DP_VERBOSE(cdev,
+		   QED_MSG_SP,
+		   "LLH: Removed MAC filter [%pM] from ppfid %hhd [abs %hhd] at idx %hhd [ref_cnt %d]\n",
+		   mac_addr, ppfid, abs_ppfid, filter_idx, ref_cnt);
+
+	goto out;
+
+err:	DP_NOTICE(cdev,
+		  "LLH: Failed to remove MAC filter [%pM] from ppfid %hhd\n",
+		  mac_addr, ppfid);
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+}
+
+void qed_llh_remove_protocol_filter(struct qed_dev *cdev,
+				    u8 ppfid,
+				    enum qed_llh_prot_filter_type_t type,
+				    u16 source_port_or_eth_type, u16 dest_port)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn);
+	u8 filter_idx, abs_ppfid, str[32];
+	union qed_llh_filter filter = {};
+	int rc = 0;
+	u32 ref_cnt;
+
+	if (!p_ptt)
+		return;
+
+	if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits))
+		goto out;
+
+	rc = qed_llh_protocol_filter_stringify(cdev, type,
+					       source_port_or_eth_type,
+					       dest_port, str, sizeof(str));
+	if (rc)
+		goto err;
+
+	filter.protocol.type = type;
+	filter.protocol.source_port_or_eth_type = source_port_or_eth_type;
+	filter.protocol.dest_port = dest_port;
+	rc = qed_llh_shadow_remove_filter(cdev, ppfid, &filter, &filter_idx,
+					  &ref_cnt);
+	if (rc)
+		goto err;
+
+	rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid);
+	if (rc)
+		goto err;
+
+	/* Remove from the LLH in case the filter is not in use */
+	if (!ref_cnt) {
+		rc = qed_llh_remove_filter(p_hwfn, p_ptt, abs_ppfid,
+					   filter_idx);
+		if (rc)
+			goto err;
+	}
+
+	DP_VERBOSE(cdev,
+		   QED_MSG_SP,
+		   "LLH: Removed protocol filter [%s] from ppfid %hhd [abs %hhd] at idx %hhd [ref_cnt %d]\n",
+		   str, ppfid, abs_ppfid, filter_idx, ref_cnt);
+
+	goto out;
+
+err:	DP_NOTICE(cdev,
+		  "LLH: Failed to remove protocol filter [%s] from ppfid %hhd\n",
+		  str, ppfid);
+out:
+	qed_ptt_release(p_hwfn, p_ptt);
+}
+
+/******************************* NIG LLH - End ********************************/
 
 #define QED_MIN_DPIS            (4)
 #define QED_MIN_PWM_REGION      (QED_WID_SIZE * QED_MIN_DPIS)
@@ -478,6 +1382,8 @@ void qed_resc_free(struct qed_dev *cdev)
 	kfree(cdev->reset_stats);
 	cdev->reset_stats = NULL;
 
+	qed_llh_free(cdev);
+
 	for_each_hwfn(cdev, i) {
 		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
 
@@ -1445,6 +2351,13 @@ int qed_resc_alloc(struct qed_dev *cdev)
 			goto alloc_err;
 	}
 
+	rc = qed_llh_alloc(cdev);
+	if (rc) {
+		DP_NOTICE(cdev,
+			  "Failed to allocate memory for the llh_info structure\n");
+		goto alloc_err;
+	}
+
 	cdev->reset_stats = kzalloc(sizeof(*cdev->reset_stats), GFP_KERNEL);
 	if (!cdev->reset_stats)
 		goto alloc_no_mem;
@@ -1896,6 +2809,10 @@ static int qed_hw_init_port(struct qed_hwfn *p_hwfn,
 {
 	int rc = 0;
 
+	/* In CMT the gate should be cleared by the 2nd hwfn */
+	if (!QED_IS_CMT(p_hwfn->cdev) || !IS_LEAD_HWFN(p_hwfn))
+		STORE_RT_REG(p_hwfn, NIG_REG_BRB_GATE_DNTFWD_PORT_RT_OFFSET, 0);
+
 	rc = qed_init_run(p_hwfn, p_ptt, PHASE_PORT, p_hwfn->port_id, hw_mode);
 	if (rc)
 		return rc;
@@ -1959,11 +2876,6 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 		     (p_hwfn->hw_info.personality == QED_PCI_FCOE) ? 1 : 0);
 	STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_ROCE_RT_OFFSET, 0);
 
-	/* Cleanup chip from previous driver if such remains exist */
-	rc = qed_final_cleanup(p_hwfn, p_ptt, rel_pf_id, false);
-	if (rc)
-		return rc;
-
 	/* Sanity check before the PF init sequence that uses DMAE */
 	rc = qed_dmae_sanity(p_hwfn, p_ptt, "pf_phase");
 	if (rc)
@@ -1986,6 +2898,13 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 	if (rc)
 		return rc;
 
+	/* Use the leading hwfn since in CMT only NIG #0 is operational */
+	if (IS_LEAD_HWFN(p_hwfn)) {
+		rc = qed_llh_hw_init_pf(p_hwfn, p_ptt);
+		if (rc)
+			return rc;
+	}
+
 	if (b_hw_start) {
 		/* enable interrupts */
 		qed_int_igu_enable(p_hwfn, p_ptt, int_mode);
@@ -2007,17 +2926,15 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-static int qed_change_pci_hwfn(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt,
-			       u8 enable)
+int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt, bool b_enable)
 {
-	u32 delay_idx = 0, val, set_val = enable ? 1 : 0;
+	u32 delay_idx = 0, val, set_val = b_enable ? 1 : 0;
 
-	/* Change PF in PXP */
-	qed_wr(p_hwfn, p_ptt,
-	       PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
+	/* Configure the PF's internal FID_enable for master transactions */
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
 
-	/* wait until value is set - try for 1 second every 50us */
+	/* Wait until value is set - try for 1 second every 50us */
 	for (delay_idx = 0; delay_idx < 20000; delay_idx++) {
 		val = qed_rd(p_hwfn, p_ptt,
 			     PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER);
@@ -2071,13 +2988,19 @@ static int qed_vf_start(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+static void qed_pglueb_clear_err(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR,
+	       BIT(p_hwfn->abs_pf_id));
+}
+
 int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 {
 	struct qed_load_req_params load_req_params;
 	u32 load_code, resp, param, drv_mb_param;
 	bool b_default_mtu = true;
 	struct qed_hwfn *p_hwfn;
-	int rc = 0, mfw_rc, i;
+	int rc = 0, i;
 	u16 ether_type;
 
 	if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
@@ -2092,7 +3015,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 	}
 
 	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+		p_hwfn = &cdev->hwfns[i];
 
 		/* If management didn't provide a default, set one of our own */
 		if (!p_hwfn->hw_info.mtu) {
@@ -2105,9 +3028,6 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			continue;
 		}
 
-		/* Enable DMAE in PXP */
-		rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true);
-
 		rc = qed_calc_hw_mode(p_hwfn);
 		if (rc)
 			return rc;
@@ -2144,12 +3064,43 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			   "Load request was sent. Load code: 0x%x\n",
 			   load_code);
 
+		/* Only relevant for recovery:
+		 * Clear the indication after LOAD_REQ is responded by the MFW.
+		 */
+		cdev->recov_in_prog = false;
+
 		qed_mcp_set_capabilities(p_hwfn, p_hwfn->p_main_ptt);
 
 		qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
 
-		p_hwfn->first_on_engine = (load_code ==
-					   FW_MSG_CODE_DRV_LOAD_ENGINE);
+		/* Clean up chip from previous driver if such remains exist.
+		 * This is not needed when the PF is the first one on the
+		 * engine, since afterwards we are going to init the FW.
+		 */
+		if (load_code != FW_MSG_CODE_DRV_LOAD_ENGINE) {
+			rc = qed_final_cleanup(p_hwfn, p_hwfn->p_main_ptt,
+					       p_hwfn->rel_pf_id, false);
+			if (rc) {
+				DP_NOTICE(p_hwfn, "Final cleanup failed\n");
+				goto load_err;
+			}
+		}
+
+		/* Log and clear previous pglue_b errors if such exist */
+		qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt);
+
+		/* Enable the PF's internal FID_enable in the PXP */
+		rc = qed_pglueb_set_pfid_enable(p_hwfn, p_hwfn->p_main_ptt,
+						true);
+		if (rc)
+			goto load_err;
+
+		/* Clear the pglue_b was_error indication.
+		 * In E4 it must be done after the BME and the internal
+		 * FID_enable for the PF are set, since VDMs may cause the
+		 * indication to be set again.
+		 */
+		qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
 
 		switch (load_code) {
 		case FW_MSG_CODE_DRV_LOAD_ENGINE:
@@ -2180,39 +3131,29 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			break;
 		}
 
-		if (rc)
+		if (rc) {
 			DP_NOTICE(p_hwfn,
 				  "init phase failed for loadcode 0x%x (rc %d)\n",
-				   load_code, rc);
+				  load_code, rc);
+			goto load_err;
+		}
 
-		/* ACK mfw regardless of success or failure of initialization */
-		mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				     DRV_MSG_CODE_LOAD_DONE,
-				     0, &load_code, &param);
+		rc = qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
 		if (rc)
 			return rc;
-		if (mfw_rc) {
-			DP_NOTICE(p_hwfn, "Failed sending LOAD_DONE command\n");
-			return mfw_rc;
-		}
-
-		/* Check if there is a DID mismatch between nvm-cfg/efuse */
-		if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
-			DP_NOTICE(p_hwfn,
-				  "warning: device configuration is not supported on this board type. The device may not function as expected.\n");
 
 		/* send DCBX attention request command */
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_DCB,
 			   "sending phony dcbx set command to trigger DCBx attention handling\n");
-		mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				     DRV_MSG_CODE_SET_DCBX,
-				     1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
-				     &load_code, &param);
-		if (mfw_rc) {
+		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
+				 DRV_MSG_CODE_SET_DCBX,
+				 1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
+				 &resp, &param);
+		if (rc) {
 			DP_NOTICE(p_hwfn,
 				  "Failed to send DCBX attention request\n");
-			return mfw_rc;
+			return rc;
 		}
 
 		p_hwfn->hw_init_done = true;
@@ -2261,6 +3202,12 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 	}
 
 	return 0;
+
+load_err:
+	/* The MFW load lock should be released also when initialization fails.
+	 */
+	qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
+	return rc;
 }
 
 #define QED_HW_STOP_RETRY_LIMIT (10)
@@ -2273,6 +3220,9 @@ static void qed_hw_timers_stop(struct qed_dev *cdev,
 	qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_CONN, 0x0);
 	qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_TASK, 0x0);
 
+	if (cdev->recov_in_prog)
+		return;
+
 	for (i = 0; i < QED_HW_STOP_RETRY_LIMIT; i++) {
 		if ((!qed_rd(p_hwfn, p_ptt,
 			     TM_REG_PF_SCAN_ACTIVE_CONN)) &&
@@ -2335,12 +3285,14 @@ int qed_hw_stop(struct qed_dev *cdev)
 		p_hwfn->hw_init_done = false;
 
 		/* Send unload command to MCP */
-		rc = qed_mcp_unload_req(p_hwfn, p_ptt);
-		if (rc) {
-			DP_NOTICE(p_hwfn,
-				  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
-				  rc);
-			rc2 = -EINVAL;
+		if (!cdev->recov_in_prog) {
+			rc = qed_mcp_unload_req(p_hwfn, p_ptt);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 		}
 
 		qed_slowpath_irq_sync(p_hwfn);
@@ -2382,27 +3334,37 @@ int qed_hw_stop(struct qed_dev *cdev)
 		qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_DB_ENABLE, 0);
 		qed_wr(p_hwfn, p_ptt, QM_REG_PF_EN, 0);
 
-		qed_mcp_unload_done(p_hwfn, p_ptt);
-		if (rc) {
-			DP_NOTICE(p_hwfn,
-				  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
-				  rc);
-			rc2 = -EINVAL;
+		if (IS_LEAD_HWFN(p_hwfn) &&
+		    test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits) &&
+		    !QED_IS_FCOE_PERSONALITY(p_hwfn))
+			qed_llh_remove_mac_filter(cdev, 0,
+						  p_hwfn->hw_info.hw_mac_addr);
+
+		if (!cdev->recov_in_prog) {
+			rc = qed_mcp_unload_done(p_hwfn, p_ptt);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 		}
 	}
 
-	if (IS_PF(cdev)) {
+	if (IS_PF(cdev) && !cdev->recov_in_prog) {
 		p_hwfn = QED_LEADING_HWFN(cdev);
 		p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt;
 
-		/* Disable DMAE in PXP - in CMT, this should only be done for
-		 * first hw-function, and only after all transactions have
-		 * stopped for all active hw-functions.
+		/* Clear the PF's internal FID_enable in the PXP.
+		 * In CMT this should only be done for first hw-function, and
+		 * only after all transactions have stopped for all active
+		 * hw-functions.
 		 */
-		rc = qed_change_pci_hwfn(p_hwfn, p_ptt, false);
+		rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false);
 		if (rc) {
 			DP_NOTICE(p_hwfn,
-				  "qed_change_pci_hwfn failed. rc = %d.\n", rc);
+				  "qed_pglueb_set_pfid_enable() failed. rc = %d.\n",
+				  rc);
 			rc2 = -EINVAL;
 		}
 	}
@@ -2502,9 +3464,8 @@ static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn)
 		       PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0);
 	}
 
-	/* Clean Previous errors if such exist */
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-	       PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR, 1 << p_hwfn->abs_pf_id);
+	/* Clean previous pglue_b errors if such exist */
+	qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
 
 	/* enable internal target-read */
 	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
@@ -2854,6 +3815,36 @@ static int qed_hw_set_resc_info(struct qed_hwfn *p_hwfn)
 	return 0;
 }
 
+static int qed_hw_get_ppfid_bitmap(struct qed_hwfn *p_hwfn,
+				   struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u8 native_ppfid_idx;
+	int rc;
+
+	/* Calculation of BB/AH is different for native_ppfid_idx */
+	if (QED_IS_BB(cdev))
+		native_ppfid_idx = p_hwfn->rel_pf_id;
+	else
+		native_ppfid_idx = p_hwfn->rel_pf_id /
+		    cdev->num_ports_in_engine;
+
+	rc = qed_mcp_get_ppfid_bitmap(p_hwfn, p_ptt);
+	if (rc != 0 && rc != -EOPNOTSUPP)
+		return rc;
+	else if (rc == -EOPNOTSUPP)
+		cdev->ppfid_bitmap = 0x1 << native_ppfid_idx;
+
+	if (!(cdev->ppfid_bitmap & (0x1 << native_ppfid_idx))) {
+		DP_INFO(p_hwfn,
+			"Fix the PPFID bitmap to include the native PPFID [native_ppfid_idx %hhd, orig_bitmap 0x%hhx]\n",
+			native_ppfid_idx, cdev->ppfid_bitmap);
+		cdev->ppfid_bitmap = 0x1 << native_ppfid_idx;
+	}
+
+	return 0;
+}
+
 static int qed_hw_get_resc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_resc_unlock_params resc_unlock_params;
@@ -2911,6 +3902,13 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 				"Failed to release the resource lock for the resource allocation commands\n");
 	}
 
+	/* PPFID bitmap */
+	if (IS_LEAD_HWFN(p_hwfn)) {
+		rc = qed_hw_get_ppfid_bitmap(p_hwfn, p_ptt);
+		if (rc)
+			return rc;
+	}
+
 	/* Sanity for ILT */
 	if ((b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_K2)) ||
 	    (!b_ah && (RESC_END(p_hwfn, QED_ILT) > PXP_NUM_ILT_RECORDS_BB))) {
@@ -3126,12 +4124,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 			cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS) |
 					BIT(QED_MF_LLH_PROTO_CLSS) |
 					BIT(QED_MF_UFP_SPECIFIC) |
-					BIT(QED_MF_8021Q_TAGGING);
+					BIT(QED_MF_8021Q_TAGGING) |
+					BIT(QED_MF_DONT_ADD_VLAN0_TAG);
 			break;
 		case NVM_CFG1_GLOB_MF_MODE_BD:
 			cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS) |
 					BIT(QED_MF_LLH_PROTO_CLSS) |
-					BIT(QED_MF_8021AD_TAGGING);
+					BIT(QED_MF_8021AD_TAGGING) |
+					BIT(QED_MF_DONT_ADD_VLAN0_TAG);
 			break;
 		case NVM_CFG1_GLOB_MF_MODE_NPAR1_0:
 			cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) |
@@ -3238,55 +4238,43 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		   p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine);
 }
 
-static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn,
-				    struct qed_ptt *p_ptt)
-{
-	u32 port_mode;
-
-	port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB);
-
-	if (port_mode < 3) {
-		p_hwfn->cdev->num_ports_in_engine = 1;
-	} else if (port_mode <= 5) {
-		p_hwfn->cdev->num_ports_in_engine = 2;
-	} else {
-		DP_NOTICE(p_hwfn, "PORT MODE: %d not supported\n",
-			  p_hwfn->cdev->num_ports_in_engine);
-
-		/* Default num_ports_in_engine to something */
-		p_hwfn->cdev->num_ports_in_engine = 1;
-	}
-}
-
-static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn,
-				    struct qed_ptt *p_ptt)
+static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 port;
-	int i;
-
-	p_hwfn->cdev->num_ports_in_engine = 0;
+	u32 addr, global_offsize, global_addr, port_mode;
+	struct qed_dev *cdev = p_hwfn->cdev;
 
-	for (i = 0; i < MAX_NUM_PORTS_K2; i++) {
-		port = qed_rd(p_hwfn, p_ptt,
-			      CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4));
-		if (port & 1)
-			p_hwfn->cdev->num_ports_in_engine++;
+	/* In CMT there is always only one port */
+	if (cdev->num_hwfns > 1) {
+		cdev->num_ports_in_engine = 1;
+		cdev->num_ports = 1;
+		return;
 	}
 
-	if (!p_hwfn->cdev->num_ports_in_engine) {
-		DP_NOTICE(p_hwfn, "All NIG ports are inactive\n");
-
-		/* Default num_ports_in_engine to something */
-		p_hwfn->cdev->num_ports_in_engine = 1;
+	/* Determine the number of ports per engine */
+	port_mode = qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE);
+	switch (port_mode) {
+	case 0x0:
+		cdev->num_ports_in_engine = 1;
+		break;
+	case 0x1:
+		cdev->num_ports_in_engine = 2;
+		break;
+	case 0x2:
+		cdev->num_ports_in_engine = 4;
+		break;
+	default:
+		DP_NOTICE(p_hwfn, "Unknown port mode 0x%08x\n", port_mode);
+		cdev->num_ports_in_engine = 1;	/* Default to something */
+		break;
 	}
-}
 
-static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
-{
-	if (QED_IS_BB(p_hwfn->cdev))
-		qed_hw_info_port_num_bb(p_hwfn, p_ptt);
-	else
-		qed_hw_info_port_num_ah(p_hwfn, p_ptt);
+	/* Get the total number of ports of the device */
+	addr = SECTION_OFFSIZE_ADDR(p_hwfn->mcp_info->public_base,
+				    PUBLIC_GLOBAL);
+	global_offsize = qed_rd(p_hwfn, p_ptt, addr);
+	global_addr = SECTION_ADDR(global_offsize, 0);
+	addr = global_addr + offsetof(struct public_global, max_ports);
+	cdev->num_ports = (u8)qed_rd(p_hwfn, p_ptt, addr);
 }
 
 static void qed_get_eee_caps(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
@@ -3324,7 +4312,8 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 			return rc;
 	}
 
-	qed_hw_info_port_num(p_hwfn, p_ptt);
+	if (IS_LEAD_HWFN(p_hwfn))
+		qed_hw_info_port_num(p_hwfn, p_ptt);
 
 	qed_mcp_get_capabilities(p_hwfn, p_ptt);
 
@@ -3438,13 +4427,16 @@ static void qed_nvm_info_free(struct qed_hwfn *p_hwfn)
 static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 				 void __iomem *p_regview,
 				 void __iomem *p_doorbells,
+				 u64 db_phys_addr,
 				 enum qed_pci_personality personality)
 {
+	struct qed_dev *cdev = p_hwfn->cdev;
 	int rc = 0;
 
 	/* Split PCI bars evenly between hwfns */
 	p_hwfn->regview = p_regview;
 	p_hwfn->doorbells = p_doorbells;
+	p_hwfn->db_phys_addr = db_phys_addr;
 
 	if (IS_VF(p_hwfn->cdev))
 		return qed_vf_hw_prepare(p_hwfn);
@@ -3492,7 +4484,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 	/* Sending a mailbox to the MFW should be done after qed_get_hw_info()
 	 * is called as it sets the ports number in an engine.
 	 */
-	if (IS_LEAD_HWFN(p_hwfn)) {
+	if (IS_LEAD_HWFN(p_hwfn) && !cdev->recov_in_prog) {
 		rc = qed_mcp_initiate_pf_flr(p_hwfn, p_hwfn->p_main_ptt);
 		if (rc)
 			DP_NOTICE(p_hwfn, "Failed to initiate PF FLR\n");
@@ -3540,7 +4532,9 @@ int qed_hw_prepare(struct qed_dev *cdev,
 	/* Initialize the first hwfn - will learn number of hwfns */
 	rc = qed_hw_prepare_single(p_hwfn,
 				   cdev->regview,
-				   cdev->doorbells, personality);
+				   cdev->doorbells,
+				   cdev->db_phys_addr,
+				   personality);
 	if (rc)
 		return rc;
 
@@ -3549,22 +4543,25 @@ int qed_hw_prepare(struct qed_dev *cdev,
 	/* Initialize the rest of the hwfns */
 	if (cdev->num_hwfns > 1) {
 		void __iomem *p_regview, *p_doorbell;
-		u8 __iomem *addr;
+		u64 db_phys_addr;
+		u32 offset;
 
 		/* adjust bar offset for second engine */
-		addr = cdev->regview +
-		       qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
-				       BAR_ID_0) / 2;
-		p_regview = addr;
+		offset = qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+					 BAR_ID_0) / 2;
+		p_regview = cdev->regview + offset;
 
-		addr = cdev->doorbells +
-		       qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
-				       BAR_ID_1) / 2;
-		p_doorbell = addr;
+		offset = qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+					 BAR_ID_1) / 2;
+
+		p_doorbell = cdev->doorbells + offset;
+
+		db_phys_addr = cdev->db_phys_addr + offset;
 
 		/* prepare second hw function */
 		rc = qed_hw_prepare_single(&cdev->hwfns[1], p_regview,
-					   p_doorbell, personality);
+					   p_doorbell, db_phys_addr,
+					   personality);
 
 		/* in case of error, need to free the previously
 		 * initiliazed hwfn 0.
@@ -3945,269 +4942,6 @@ int qed_fw_rss_eng(struct qed_hwfn *p_hwfn, u8 src_id, u8 *dst_id)
 	return 0;
 }
 
-static void qed_llh_mac_to_filter(u32 *p_high, u32 *p_low,
-				  u8 *p_filter)
-{
-	*p_high = p_filter[1] | (p_filter[0] << 8);
-	*p_low = p_filter[5] | (p_filter[4] << 8) |
-		 (p_filter[3] << 16) | (p_filter[2] << 24);
-}
-
-int qed_llh_add_mac_filter(struct qed_hwfn *p_hwfn,
-			   struct qed_ptt *p_ptt, u8 *p_filter)
-{
-	u32 high = 0, low = 0, en;
-	int i;
-
-	if (!test_bit(QED_MF_LLH_MAC_CLSS, &p_hwfn->cdev->mf_bits))
-		return 0;
-
-	qed_llh_mac_to_filter(&high, &low, p_filter);
-
-	/* Find a free entry and utilize it */
-	for (i = 0; i < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; i++) {
-		en = qed_rd(p_hwfn, p_ptt,
-			    NIG_REG_LLH_FUNC_FILTER_EN + i * sizeof(u32));
-		if (en)
-			continue;
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE +
-		       2 * i * sizeof(u32), low);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE +
-		       (2 * i + 1) * sizeof(u32), high);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_MODE + i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE +
-		       i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_EN + i * sizeof(u32), 1);
-		break;
-	}
-	if (i >= NIG_REG_LLH_FUNC_FILTER_EN_SIZE) {
-		DP_NOTICE(p_hwfn,
-			  "Failed to find an empty LLH filter to utilize\n");
-		return -EINVAL;
-	}
-
-	DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-		   "mac: %pM is added at %d\n",
-		   p_filter, i);
-
-	return 0;
-}
-
-void qed_llh_remove_mac_filter(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt, u8 *p_filter)
-{
-	u32 high = 0, low = 0;
-	int i;
-
-	if (!test_bit(QED_MF_LLH_MAC_CLSS, &p_hwfn->cdev->mf_bits))
-		return;
-
-	qed_llh_mac_to_filter(&high, &low, p_filter);
-
-	/* Find the entry and clean it */
-	for (i = 0; i < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; i++) {
-		if (qed_rd(p_hwfn, p_ptt,
-			   NIG_REG_LLH_FUNC_FILTER_VALUE +
-			   2 * i * sizeof(u32)) != low)
-			continue;
-		if (qed_rd(p_hwfn, p_ptt,
-			   NIG_REG_LLH_FUNC_FILTER_VALUE +
-			   (2 * i + 1) * sizeof(u32)) != high)
-			continue;
-
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_EN + i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE + 2 * i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE +
-		       (2 * i + 1) * sizeof(u32), 0);
-
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "mac: %pM is removed from %d\n",
-			   p_filter, i);
-		break;
-	}
-	if (i >= NIG_REG_LLH_FUNC_FILTER_EN_SIZE)
-		DP_NOTICE(p_hwfn, "Tried to remove a non-configured filter\n");
-}
-
-int
-qed_llh_add_protocol_filter(struct qed_hwfn *p_hwfn,
-			    struct qed_ptt *p_ptt,
-			    u16 source_port_or_eth_type,
-			    u16 dest_port, enum qed_llh_port_filter_type_t type)
-{
-	u32 high = 0, low = 0, en;
-	int i;
-
-	if (!test_bit(QED_MF_LLH_PROTO_CLSS, &p_hwfn->cdev->mf_bits))
-		return 0;
-
-	switch (type) {
-	case QED_LLH_FILTER_ETHERTYPE:
-		high = source_port_or_eth_type;
-		break;
-	case QED_LLH_FILTER_TCP_SRC_PORT:
-	case QED_LLH_FILTER_UDP_SRC_PORT:
-		low = source_port_or_eth_type << 16;
-		break;
-	case QED_LLH_FILTER_TCP_DEST_PORT:
-	case QED_LLH_FILTER_UDP_DEST_PORT:
-		low = dest_port;
-		break;
-	case QED_LLH_FILTER_TCP_SRC_AND_DEST_PORT:
-	case QED_LLH_FILTER_UDP_SRC_AND_DEST_PORT:
-		low = (source_port_or_eth_type << 16) | dest_port;
-		break;
-	default:
-		DP_NOTICE(p_hwfn,
-			  "Non valid LLH protocol filter type %d\n", type);
-		return -EINVAL;
-	}
-	/* Find a free entry and utilize it */
-	for (i = 0; i < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; i++) {
-		en = qed_rd(p_hwfn, p_ptt,
-			    NIG_REG_LLH_FUNC_FILTER_EN + i * sizeof(u32));
-		if (en)
-			continue;
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE +
-		       2 * i * sizeof(u32), low);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE +
-		       (2 * i + 1) * sizeof(u32), high);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_MODE + i * sizeof(u32), 1);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE +
-		       i * sizeof(u32), 1 << type);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_EN + i * sizeof(u32), 1);
-		break;
-	}
-	if (i >= NIG_REG_LLH_FUNC_FILTER_EN_SIZE) {
-		DP_NOTICE(p_hwfn,
-			  "Failed to find an empty LLH filter to utilize\n");
-		return -EINVAL;
-	}
-	switch (type) {
-	case QED_LLH_FILTER_ETHERTYPE:
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "ETH type %x is added at %d\n",
-			   source_port_or_eth_type, i);
-		break;
-	case QED_LLH_FILTER_TCP_SRC_PORT:
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "TCP src port %x is added at %d\n",
-			   source_port_or_eth_type, i);
-		break;
-	case QED_LLH_FILTER_UDP_SRC_PORT:
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "UDP src port %x is added at %d\n",
-			   source_port_or_eth_type, i);
-		break;
-	case QED_LLH_FILTER_TCP_DEST_PORT:
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "TCP dst port %x is added at %d\n", dest_port, i);
-		break;
-	case QED_LLH_FILTER_UDP_DEST_PORT:
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "UDP dst port %x is added at %d\n", dest_port, i);
-		break;
-	case QED_LLH_FILTER_TCP_SRC_AND_DEST_PORT:
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "TCP src/dst ports %x/%x are added at %d\n",
-			   source_port_or_eth_type, dest_port, i);
-		break;
-	case QED_LLH_FILTER_UDP_SRC_AND_DEST_PORT:
-		DP_VERBOSE(p_hwfn, NETIF_MSG_HW,
-			   "UDP src/dst ports %x/%x are added at %d\n",
-			   source_port_or_eth_type, dest_port, i);
-		break;
-	}
-	return 0;
-}
-
-void
-qed_llh_remove_protocol_filter(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt,
-			       u16 source_port_or_eth_type,
-			       u16 dest_port,
-			       enum qed_llh_port_filter_type_t type)
-{
-	u32 high = 0, low = 0;
-	int i;
-
-	if (!test_bit(QED_MF_LLH_PROTO_CLSS, &p_hwfn->cdev->mf_bits))
-		return;
-
-	switch (type) {
-	case QED_LLH_FILTER_ETHERTYPE:
-		high = source_port_or_eth_type;
-		break;
-	case QED_LLH_FILTER_TCP_SRC_PORT:
-	case QED_LLH_FILTER_UDP_SRC_PORT:
-		low = source_port_or_eth_type << 16;
-		break;
-	case QED_LLH_FILTER_TCP_DEST_PORT:
-	case QED_LLH_FILTER_UDP_DEST_PORT:
-		low = dest_port;
-		break;
-	case QED_LLH_FILTER_TCP_SRC_AND_DEST_PORT:
-	case QED_LLH_FILTER_UDP_SRC_AND_DEST_PORT:
-		low = (source_port_or_eth_type << 16) | dest_port;
-		break;
-	default:
-		DP_NOTICE(p_hwfn,
-			  "Non valid LLH protocol filter type %d\n", type);
-		return;
-	}
-
-	for (i = 0; i < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; i++) {
-		if (!qed_rd(p_hwfn, p_ptt,
-			    NIG_REG_LLH_FUNC_FILTER_EN + i * sizeof(u32)))
-			continue;
-		if (!qed_rd(p_hwfn, p_ptt,
-			    NIG_REG_LLH_FUNC_FILTER_MODE + i * sizeof(u32)))
-			continue;
-		if (!(qed_rd(p_hwfn, p_ptt,
-			     NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE +
-			     i * sizeof(u32)) & BIT(type)))
-			continue;
-		if (qed_rd(p_hwfn, p_ptt,
-			   NIG_REG_LLH_FUNC_FILTER_VALUE +
-			   2 * i * sizeof(u32)) != low)
-			continue;
-		if (qed_rd(p_hwfn, p_ptt,
-			   NIG_REG_LLH_FUNC_FILTER_VALUE +
-			   (2 * i + 1) * sizeof(u32)) != high)
-			continue;
-
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_EN + i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_MODE + i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE +
-		       i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE + 2 * i * sizeof(u32), 0);
-		qed_wr(p_hwfn, p_ptt,
-		       NIG_REG_LLH_FUNC_FILTER_VALUE +
-		       (2 * i + 1) * sizeof(u32), 0);
-		break;
-	}
-
-	if (i >= NIG_REG_LLH_FUNC_FILTER_EN_SIZE)
-		DP_NOTICE(p_hwfn, "Tried to remove a non-configured filter\n");
-}
-
 static int qed_set_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 			    u32 hw_addr, void *p_eth_qzone,
 			    size_t eth_qzone_size, u8 timeset)
@@ -4728,23 +5462,9 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	       sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports);
 }
 
-int qed_device_num_engines(struct qed_dev *cdev)
-{
-	return QED_IS_BB(cdev) ? 2 : 1;
-}
-
-static int qed_device_num_ports(struct qed_dev *cdev)
-{
-	/* in CMT always only one port */
-	if (cdev->num_hwfns > 1)
-		return 1;
-
-	return cdev->num_ports_in_engine * qed_device_num_engines(cdev);
-}
-
-int qed_device_get_port_id(struct qed_dev *cdev)
+int qed_device_num_ports(struct qed_dev *cdev)
 {
-	return (QED_LEADING_HWFN(cdev)->abs_pf_id) % qed_device_num_ports(cdev);
+	return cdev->num_ports;
 }
 
 void qed_set_fw_mac_addr(__le16 *fw_msb,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index acccd85170aa..47376d4d071f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -241,11 +241,17 @@ enum qed_dmae_address_type_t {
 #define QED_DMAE_FLAG_VF_SRC		0x00000002
 #define QED_DMAE_FLAG_VF_DST		0x00000004
 #define QED_DMAE_FLAG_COMPLETION_DST	0x00000008
+#define QED_DMAE_FLAG_PORT		0x00000010
+#define QED_DMAE_FLAG_PF_SRC		0x00000020
+#define QED_DMAE_FLAG_PF_DST		0x00000040
 
 struct qed_dmae_params {
 	u32 flags; /* consists of QED_DMAE_FLAG_* values */
 	u8 src_vfid;
 	u8 dst_vfid;
+	u8 port_id;
+	u8 src_pfid;
+	u8 dst_pfid;
 };
 
 /**
@@ -257,7 +263,7 @@ struct qed_dmae_params {
  * @param source_addr
  * @param grc_addr (dmae_data_offset)
  * @param size_in_dwords
- * @param flags (one of the flags defined above)
+ * @param p_params (default parameters will be used in case of NULL)
  */
 int
 qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
@@ -265,7 +271,7 @@ qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
 		  u64 source_addr,
 		  u32 grc_addr,
 		  u32 size_in_dwords,
-		  u32 flags);
+		  struct qed_dmae_params *p_params);
 
  /**
  * @brief qed_dmae_grc2host - Read data from dmae data offset
@@ -275,11 +281,11 @@ qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
  * @param grc_addr (dmae_data_offset)
  * @param dest_addr
  * @param size_in_dwords
- * @param flags - one of the flags defined above
+ * @param p_params (default parameters will be used in case of NULL)
  */
 int qed_dmae_grc2host(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 		      u32 grc_addr, dma_addr_t dest_addr, u32 size_in_dwords,
-		      u32 flags);
+		      struct qed_dmae_params *p_params);
 
 /**
  * @brief qed_dmae_host2host - copy data from to source address
@@ -290,7 +296,7 @@ int qed_dmae_grc2host(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
  * @param source_addr
  * @param dest_addr
  * @param size_in_dwords
- * @param params
+ * @param p_params (default parameters will be used in case of NULL)
  */
 int qed_dmae_host2host(struct qed_hwfn *p_hwfn,
 		       struct qed_ptt *p_ptt,
@@ -368,26 +374,66 @@ int qed_fw_rss_eng(struct qed_hwfn *p_hwfn,
 		   u8 *dst_id);
 
 /**
- * @brief qed_llh_add_mac_filter - configures a MAC filter in llh
+ * @brief qed_llh_get_num_ppfid - Return the allocated number of LLH filter
+ *	banks that are allocated to the PF.
  *
- * @param p_hwfn
- * @param p_ptt
- * @param p_filter - MAC to add
+ * @param cdev
+ *
+ * @return u8 - Number of LLH filter banks
  */
-int qed_llh_add_mac_filter(struct qed_hwfn *p_hwfn,
-			   struct qed_ptt *p_ptt, u8 *p_filter);
+u8 qed_llh_get_num_ppfid(struct qed_dev *cdev);
+
+enum qed_eng {
+	QED_ENG0,
+	QED_ENG1,
+	QED_BOTH_ENG,
+};
 
 /**
- * @brief qed_llh_remove_mac_filter - removes a MAC filter from llh
+ * @brief qed_llh_set_ppfid_affinity - Set the engine affinity for the given
+ *	LLH filter bank.
+ *
+ * @param cdev
+ * @param ppfid - relative within the allocated ppfids ('0' is the default one).
+ * @param eng
+ *
+ * @return int
+ */
+int qed_llh_set_ppfid_affinity(struct qed_dev *cdev,
+			       u8 ppfid, enum qed_eng eng);
+
+/**
+ * @brief qed_llh_set_roce_affinity - Set the RoCE engine affinity
+ *
+ * @param cdev
+ * @param eng
+ *
+ * @return int
+ */
+int qed_llh_set_roce_affinity(struct qed_dev *cdev, enum qed_eng eng);
+
+/**
+ * @brief qed_llh_add_mac_filter - Add a LLH MAC filter into the given filter
+ *	bank.
+ *
+ * @param cdev
+ * @param ppfid - relative within the allocated ppfids ('0' is the default one).
+ * @param mac_addr - MAC to add
+ */
+int qed_llh_add_mac_filter(struct qed_dev *cdev,
+			   u8 ppfid, u8 mac_addr[ETH_ALEN]);
+
+/**
+ * @brief qed_llh_remove_mac_filter - Remove a LLH MAC filter from the given
+ *	filter bank.
  *
- * @param p_hwfn
  * @param p_ptt
  * @param p_filter - MAC to remove
  */
-void qed_llh_remove_mac_filter(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt, u8 *p_filter);
+void qed_llh_remove_mac_filter(struct qed_dev *cdev,
+			       u8 ppfid, u8 mac_addr[ETH_ALEN]);
 
-enum qed_llh_port_filter_type_t {
+enum qed_llh_prot_filter_type_t {
 	QED_LLH_FILTER_ETHERTYPE,
 	QED_LLH_FILTER_TCP_SRC_PORT,
 	QED_LLH_FILTER_TCP_DEST_PORT,
@@ -398,36 +444,37 @@ enum qed_llh_port_filter_type_t {
 };
 
 /**
- * @brief qed_llh_add_protocol_filter - configures a protocol filter in llh
+ * @brief qed_llh_add_protocol_filter - Add a LLH protocol filter into the
+ *	given filter bank.
  *
- * @param p_hwfn
- * @param p_ptt
+ * @param cdev
+ * @param ppfid - relative within the allocated ppfids ('0' is the default one).
+ * @param type - type of filters and comparing
  * @param source_port_or_eth_type - source port or ethertype to add
  * @param dest_port - destination port to add
  * @param type - type of filters and comparing
  */
 int
-qed_llh_add_protocol_filter(struct qed_hwfn *p_hwfn,
-			    struct qed_ptt *p_ptt,
-			    u16 source_port_or_eth_type,
-			    u16 dest_port,
-			    enum qed_llh_port_filter_type_t type);
+qed_llh_add_protocol_filter(struct qed_dev *cdev,
+			    u8 ppfid,
+			    enum qed_llh_prot_filter_type_t type,
+			    u16 source_port_or_eth_type, u16 dest_port);
 
 /**
- * @brief qed_llh_remove_protocol_filter - remove a protocol filter in llh
+ * @brief qed_llh_remove_protocol_filter - Remove a LLH protocol filter from
+ *	the given filter bank.
  *
- * @param p_hwfn
- * @param p_ptt
+ * @param cdev
+ * @param ppfid - relative within the allocated ppfids ('0' is the default one).
+ * @param type - type of filters and comparing
  * @param source_port_or_eth_type - source port or ethertype to add
  * @param dest_port - destination port to add
- * @param type - type of filters and comparing
  */
 void
-qed_llh_remove_protocol_filter(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt,
-			       u16 source_port_or_eth_type,
-			       u16 dest_port,
-			       enum qed_llh_port_filter_type_t type);
+qed_llh_remove_protocol_filter(struct qed_dev *cdev,
+			       u8 ppfid,
+			       enum qed_llh_prot_filter_type_t type,
+			       u16 source_port_or_eth_type, u16 dest_port);
 
 /**
  * *@brief Cleanup of previous driver remains prior to load
@@ -473,6 +520,18 @@ int
 qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle);
 
 /**
+ * @brief qed_pglueb_set_pfid_enable - Enable or disable PCI BUS MASTER
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param b_enable - true/false
+ *
+ * @return int
+ */
+int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt, bool b_enable);
+
+/**
  * @brief db_recovery_add - add doorbell information to the doorbell
  * recovery mechanism.
  *
diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
index 46dc93d3b9b5..de31a382f58e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c
@@ -745,7 +745,7 @@ struct qed_hash_fcoe_con {
 static int qed_fill_fcoe_dev_info(struct qed_dev *cdev,
 				  struct qed_dev_fcoe_info *info)
 {
-	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_hwfn *hwfn = QED_AFFIN_HWFN(cdev);
 	int rc;
 
 	memset(info, 0, sizeof(*info));
@@ -806,15 +806,15 @@ static int qed_fcoe_stop(struct qed_dev *cdev)
 		return -EINVAL;
 	}
 
-	p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev));
+	p_ptt = qed_ptt_acquire(QED_AFFIN_HWFN(cdev));
 	if (!p_ptt)
 		return -EAGAIN;
 
 	/* Stop the fcoe */
-	rc = qed_sp_fcoe_func_stop(QED_LEADING_HWFN(cdev), p_ptt,
+	rc = qed_sp_fcoe_func_stop(QED_AFFIN_HWFN(cdev), p_ptt,
 				   QED_SPQ_MODE_EBLOCK, NULL);
 	cdev->flags &= ~QED_FLAG_STORAGE_STARTED;
-	qed_ptt_release(QED_LEADING_HWFN(cdev), p_ptt);
+	qed_ptt_release(QED_AFFIN_HWFN(cdev), p_ptt);
 
 	return rc;
 }
@@ -828,8 +828,8 @@ static int qed_fcoe_start(struct qed_dev *cdev, struct qed_fcoe_tid *tasks)
 		return 0;
 	}
 
-	rc = qed_sp_fcoe_func_start(QED_LEADING_HWFN(cdev),
-				    QED_SPQ_MODE_EBLOCK, NULL);
+	rc = qed_sp_fcoe_func_start(QED_AFFIN_HWFN(cdev), QED_SPQ_MODE_EBLOCK,
+				    NULL);
 	if (rc) {
 		DP_NOTICE(cdev, "Failed to start fcoe\n");
 		return rc;
@@ -849,7 +849,7 @@ static int qed_fcoe_start(struct qed_dev *cdev, struct qed_fcoe_tid *tasks)
 			return -ENOMEM;
 		}
 
-		rc = qed_cxt_get_tid_mem_info(QED_LEADING_HWFN(cdev), tid_info);
+		rc = qed_cxt_get_tid_mem_info(QED_AFFIN_HWFN(cdev), tid_info);
 		if (rc) {
 			DP_NOTICE(cdev, "Failed to gather task information\n");
 			qed_fcoe_stop(cdev);
@@ -884,7 +884,7 @@ static int qed_fcoe_acquire_conn(struct qed_dev *cdev,
 	}
 
 	/* Acquire the connection */
-	rc = qed_fcoe_acquire_connection(QED_LEADING_HWFN(cdev), NULL,
+	rc = qed_fcoe_acquire_connection(QED_AFFIN_HWFN(cdev), NULL,
 					 &hash_con->con);
 	if (rc) {
 		DP_NOTICE(cdev, "Failed to acquire Connection\n");
@@ -898,7 +898,7 @@ static int qed_fcoe_acquire_conn(struct qed_dev *cdev,
 	hash_add(cdev->connections, &hash_con->node, *handle);
 
 	if (p_doorbell)
-		*p_doorbell = qed_fcoe_get_db_addr(QED_LEADING_HWFN(cdev),
+		*p_doorbell = qed_fcoe_get_db_addr(QED_AFFIN_HWFN(cdev),
 						   *handle);
 
 	return 0;
@@ -916,7 +916,7 @@ static int qed_fcoe_release_conn(struct qed_dev *cdev, u32 handle)
 	}
 
 	hlist_del(&hash_con->node);
-	qed_fcoe_release_connection(QED_LEADING_HWFN(cdev), hash_con->con);
+	qed_fcoe_release_connection(QED_AFFIN_HWFN(cdev), hash_con->con);
 	kfree(hash_con);
 
 	return 0;
@@ -971,7 +971,7 @@ static int qed_fcoe_offload_conn(struct qed_dev *cdev,
 	con->d_id.addr_mid = conn_info->d_id.addr_mid;
 	con->d_id.addr_lo = conn_info->d_id.addr_lo;
 
-	return qed_sp_fcoe_conn_offload(QED_LEADING_HWFN(cdev), con,
+	return qed_sp_fcoe_conn_offload(QED_AFFIN_HWFN(cdev), con,
 					QED_SPQ_MODE_EBLOCK, NULL);
 }
 
@@ -992,13 +992,13 @@ static int qed_fcoe_destroy_conn(struct qed_dev *cdev,
 	con = hash_con->con;
 	con->terminate_params = terminate_params;
 
-	return qed_sp_fcoe_conn_destroy(QED_LEADING_HWFN(cdev), con,
+	return qed_sp_fcoe_conn_destroy(QED_AFFIN_HWFN(cdev), con,
 					QED_SPQ_MODE_EBLOCK, NULL);
 }
 
 static int qed_fcoe_stats(struct qed_dev *cdev, struct qed_fcoe_stats *stats)
 {
-	return qed_fcoe_get_stats(QED_LEADING_HWFN(cdev), stats);
+	return qed_fcoe_get_stats(QED_AFFIN_HWFN(cdev), stats);
 }
 
 void qed_get_protocol_stats_fcoe(struct qed_dev *cdev,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index b13cfb449d8f..e054f6c69e3a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12612,8 +12612,10 @@ struct public_drv_mb {
 
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
 #define DRV_MSG_CODE_SET_LED_MODE		0x00200000
-#define DRV_MSG_CODE_RESOURCE_CMD	0x00230000
+#define DRV_MSG_CODE_RESOURCE_CMD		0x00230000
 #define DRV_MSG_CODE_GET_TLV_DONE		0x002f0000
+#define DRV_MSG_CODE_GET_ENGINE_CONFIG		0x00370000
+#define DRV_MSG_CODE_GET_PPFID_BITMAP		0x43000000
 
 #define RESOURCE_CMD_REQ_RESC_MASK		0x0000001F
 #define RESOURCE_CMD_REQ_RESC_SHIFT		0
@@ -12796,11 +12798,24 @@ struct public_drv_mb {
 #define FW_MB_PARAM_GET_PF_RDMA_BOTH		0x3
 
 /* get MFW feature support response */
+#define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ	0x00000001
 #define FW_MB_PARAM_FEATURE_SUPPORT_EEE		0x00000002
 #define FW_MB_PARAM_FEATURE_SUPPORT_VLINK	0x00010000
 
 #define FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR	(1 << 0)
 
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALID_MASK   0x00000001
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALID_SHIFT 0
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALUE_MASK   0x00000002
+#define FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALUE_SHIFT 1
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALID_MASK    0x00000004
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALID_SHIFT  2
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALUE_MASK    0x00000008
+#define FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALUE_SHIFT  3
+
+#define FW_MB_PARAM_PPFID_BITMAP_MASK	0xFF
+#define FW_MB_PARAM_PPFID_BITMAP_SHIFT	0
+
 	u32 drv_pulse_mb;
 #define DRV_PULSE_SEQ_MASK			0x00007fff
 #define DRV_PULSE_SYSTEM_TIME_MASK		0xffff0000
@@ -12827,7 +12842,7 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_LLDP_DATA_UPDATED,
 	MFW_DRV_MSG_DCBX_REMOTE_MIB_UPDATED,
 	MFW_DRV_MSG_DCBX_OPERATIONAL_MIB_UPDATED,
-	MFW_DRV_MSG_RESERVED4,
+	MFW_DRV_MSG_ERROR_RECOVERY,
 	MFW_DRV_MSG_BW_UPDATE,
 	MFW_DRV_MSG_S_TAG_UPDATE,
 	MFW_DRV_MSG_GET_LAN_STATS,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 70504dcf4087..a4de9e3ef72c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -392,11 +392,15 @@ u32 qed_vfid_to_concrete(struct qed_hwfn *p_hwfn, u8 vfid)
 }
 
 /* DMAE */
+#define QED_DMAE_FLAGS_IS_SET(params, flag) \
+	((params) != NULL && ((params)->flags & QED_DMAE_FLAG_##flag))
+
 static void qed_dmae_opcode(struct qed_hwfn *p_hwfn,
 			    const u8 is_src_type_grc,
 			    const u8 is_dst_type_grc,
 			    struct qed_dmae_params *p_params)
 {
+	u8 src_pfid, dst_pfid, port_id;
 	u16 opcode_b = 0;
 	u32 opcode = 0;
 
@@ -407,14 +411,18 @@ static void qed_dmae_opcode(struct qed_hwfn *p_hwfn,
 	opcode |= (is_src_type_grc ? DMAE_CMD_SRC_MASK_GRC
 				   : DMAE_CMD_SRC_MASK_PCIE) <<
 		   DMAE_CMD_SRC_SHIFT;
-	opcode |= ((p_hwfn->rel_pf_id & DMAE_CMD_SRC_PF_ID_MASK) <<
+	src_pfid = QED_DMAE_FLAGS_IS_SET(p_params, PF_SRC) ?
+		   p_params->src_pfid : p_hwfn->rel_pf_id;
+	opcode |= ((src_pfid & DMAE_CMD_SRC_PF_ID_MASK) <<
 		   DMAE_CMD_SRC_PF_ID_SHIFT);
 
 	/* The destination of the DMA can be: 0-None 1-PCIe 2-GRC 3-None */
 	opcode |= (is_dst_type_grc ? DMAE_CMD_DST_MASK_GRC
 				   : DMAE_CMD_DST_MASK_PCIE) <<
 		   DMAE_CMD_DST_SHIFT;
-	opcode |= ((p_hwfn->rel_pf_id & DMAE_CMD_DST_PF_ID_MASK) <<
+	dst_pfid = QED_DMAE_FLAGS_IS_SET(p_params, PF_DST) ?
+		   p_params->dst_pfid : p_hwfn->rel_pf_id;
+	opcode |= ((dst_pfid & DMAE_CMD_DST_PF_ID_MASK) <<
 		   DMAE_CMD_DST_PF_ID_SHIFT);
 
 	/* Whether to write a completion word to the completion destination:
@@ -425,12 +433,14 @@ static void qed_dmae_opcode(struct qed_hwfn *p_hwfn,
 	opcode |= (DMAE_CMD_SRC_ADDR_RESET_MASK <<
 		   DMAE_CMD_SRC_ADDR_RESET_SHIFT);
 
-	if (p_params->flags & QED_DMAE_FLAG_COMPLETION_DST)
+	if (QED_DMAE_FLAGS_IS_SET(p_params, COMPLETION_DST))
 		opcode |= (1 << DMAE_CMD_COMP_FUNC_SHIFT);
 
 	opcode |= (DMAE_CMD_ENDIANITY << DMAE_CMD_ENDIANITY_MODE_SHIFT);
 
-	opcode |= ((p_hwfn->port_id) << DMAE_CMD_PORT_ID_SHIFT);
+	port_id = (QED_DMAE_FLAGS_IS_SET(p_params, PORT)) ?
+		   p_params->port_id : p_hwfn->port_id;
+	opcode |= (port_id << DMAE_CMD_PORT_ID_SHIFT);
 
 	/* reset source address in next go */
 	opcode |= (DMAE_CMD_SRC_ADDR_RESET_MASK <<
@@ -441,7 +451,7 @@ static void qed_dmae_opcode(struct qed_hwfn *p_hwfn,
 		   DMAE_CMD_DST_ADDR_RESET_SHIFT);
 
 	/* SRC/DST VFID: all 1's - pf, otherwise VF id */
-	if (p_params->flags & QED_DMAE_FLAG_VF_SRC) {
+	if (QED_DMAE_FLAGS_IS_SET(p_params, VF_SRC)) {
 		opcode |= 1 << DMAE_CMD_SRC_VF_ID_VALID_SHIFT;
 		opcode_b |= p_params->src_vfid << DMAE_CMD_SRC_VF_ID_SHIFT;
 	} else {
@@ -449,7 +459,7 @@ static void qed_dmae_opcode(struct qed_hwfn *p_hwfn,
 			    DMAE_CMD_SRC_VF_ID_SHIFT;
 	}
 
-	if (p_params->flags & QED_DMAE_FLAG_VF_DST) {
+	if (QED_DMAE_FLAGS_IS_SET(p_params, VF_DST)) {
 		opcode |= 1 << DMAE_CMD_DST_VF_ID_VALID_SHIFT;
 		opcode_b |= p_params->dst_vfid << DMAE_CMD_DST_VF_ID_SHIFT;
 	} else {
@@ -703,6 +713,17 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn,
 	int qed_status = 0;
 	u32 offset = 0;
 
+	if (p_hwfn->cdev->recov_in_prog) {
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "Recovery is in progress. Avoid DMAE transaction [{src: addr 0x%llx, type %d}, {dst: addr 0x%llx, type %d}, size %d].\n",
+			   src_addr, src_type, dst_addr, dst_type,
+			   size_in_dwords);
+
+		/* Let the flow complete w/o any error handling */
+		return 0;
+	}
+
 	qed_dmae_opcode(p_hwfn,
 			(src_type == QED_DMAE_ADDRESS_GRC),
 			(dst_type == QED_DMAE_ADDRESS_GRC),
@@ -722,7 +743,7 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn,
 	for (i = 0; i <= cnt_split; i++) {
 		offset = length_limit * i;
 
-		if (!(p_params->flags & QED_DMAE_FLAG_RW_REPL_SRC)) {
+		if (!QED_DMAE_FLAGS_IS_SET(p_params, RW_REPL_SRC)) {
 			if (src_type == QED_DMAE_ADDRESS_GRC)
 				src_addr_split = src_addr + offset;
 			else
@@ -760,14 +781,12 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn,
 
 int qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
 		      struct qed_ptt *p_ptt,
-		  u64 source_addr, u32 grc_addr, u32 size_in_dwords, u32 flags)
+		      u64 source_addr, u32 grc_addr, u32 size_in_dwords,
+		      struct qed_dmae_params *p_params)
 {
 	u32 grc_addr_in_dw = grc_addr / sizeof(u32);
-	struct qed_dmae_params params;
 	int rc;
 
-	memset(&params, 0, sizeof(struct qed_dmae_params));
-	params.flags = flags;
 
 	mutex_lock(&p_hwfn->dmae_info.mutex);
 
@@ -775,7 +794,7 @@ int qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
 				      grc_addr_in_dw,
 				      QED_DMAE_ADDRESS_HOST_VIRT,
 				      QED_DMAE_ADDRESS_GRC,
-				      size_in_dwords, &params);
+				      size_in_dwords, p_params);
 
 	mutex_unlock(&p_hwfn->dmae_info.mutex);
 
@@ -785,21 +804,19 @@ int qed_dmae_host2grc(struct qed_hwfn *p_hwfn,
 int qed_dmae_grc2host(struct qed_hwfn *p_hwfn,
 		      struct qed_ptt *p_ptt,
 		      u32 grc_addr,
-		      dma_addr_t dest_addr, u32 size_in_dwords, u32 flags)
+		      dma_addr_t dest_addr, u32 size_in_dwords,
+		      struct qed_dmae_params *p_params)
 {
 	u32 grc_addr_in_dw = grc_addr / sizeof(u32);
-	struct qed_dmae_params params;
 	int rc;
 
-	memset(&params, 0, sizeof(struct qed_dmae_params));
-	params.flags = flags;
 
 	mutex_lock(&p_hwfn->dmae_info.mutex);
 
 	rc = qed_dmae_execute_command(p_hwfn, p_ptt, grc_addr_in_dw,
 				      dest_addr, QED_DMAE_ADDRESS_GRC,
 				      QED_DMAE_ADDRESS_HOST_VIRT,
-				      size_in_dwords, &params);
+				      size_in_dwords, p_params);
 
 	mutex_unlock(&p_hwfn->dmae_info.mutex);
 
@@ -831,7 +848,6 @@ int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt, const char *phase)
 {
 	u32 size = PAGE_SIZE / 2, val;
-	struct qed_dmae_params params;
 	int rc = 0;
 	dma_addr_t p_phys;
 	void *p_virt;
@@ -864,9 +880,8 @@ int qed_dmae_sanity(struct qed_hwfn *p_hwfn,
 		   (u64)p_phys,
 		   p_virt, (u64)(p_phys + size), (u8 *)p_virt + size, size);
 
-	memset(&params, 0, sizeof(params));
 	rc = qed_dmae_host2host(p_hwfn, p_ptt, p_phys, p_phys + size,
-				size / 4 /* size_in_dwords */, &params);
+				size / 4, NULL);
 	if (rc) {
 		DP_NOTICE(p_hwfn,
 			  "DMAE sanity [%s]: qed_dmae_host2host() failed. rc = %d.\n",
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
index 34193c2f1699..a868d7f88601 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c
@@ -131,7 +131,7 @@ static int qed_init_rt(struct qed_hwfn	*p_hwfn,
 
 		rc = qed_dmae_host2grc(p_hwfn, p_ptt,
 				       (uintptr_t)(p_init_val + i),
-				       addr + (i << 2), segment, 0);
+				       addr + (i << 2), segment, NULL);
 		if (rc)
 			return rc;
 
@@ -194,7 +194,7 @@ static int qed_init_array_dmae(struct qed_hwfn *p_hwfn,
 	} else {
 		rc = qed_dmae_host2grc(p_hwfn, p_ptt,
 				       (uintptr_t)(buf + dmae_data_offset),
-				       addr, size, 0);
+				       addr, size, NULL);
 	}
 
 	return rc;
@@ -205,6 +205,7 @@ static int qed_init_fill_dmae(struct qed_hwfn *p_hwfn,
 			      u32 addr, u32 fill, u32 fill_count)
 {
 	static u32 zero_buffer[DMAE_MAX_RW_SIZE];
+	struct qed_dmae_params params = {};
 
 	memset(zero_buffer, 0, sizeof(u32) * DMAE_MAX_RW_SIZE);
 
@@ -214,10 +215,10 @@ static int qed_init_fill_dmae(struct qed_hwfn *p_hwfn,
 	 * 3. p_hwfb->temp_data,
 	 * 4. fill_count
 	 */
-
+	params.flags = QED_DMAE_FLAG_RW_REPL_SRC;
 	return qed_dmae_host2grc(p_hwfn, p_ptt,
 				 (uintptr_t)(&zero_buffer[0]),
-				 addr, fill_count, QED_DMAE_FLAG_RW_REPL_SRC);
+				 addr, fill_count, &params);
 }
 
 static void qed_init_fill(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 92340919d852..4e8118a08654 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -255,112 +255,114 @@ out:
 #define PGLUE_ATTENTION_ICPL_VALID		(1 << 23)
 #define PGLUE_ATTENTION_ZLR_VALID		(1 << 25)
 #define PGLUE_ATTENTION_ILT_VALID		(1 << 23)
-static int qed_pglub_rbc_attn_cb(struct qed_hwfn *p_hwfn)
+
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt)
 {
 	u32 tmp;
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_WR_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_VALID) {
 		u32 addr_lo, addr_hi, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"Illegal write by chip to [%08x:%08x] blocked.\n"
-			"Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
-			"Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
-			addr_hi, addr_lo, details,
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
-			GET_FIELD(details,
-				  PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
-			tmp,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
+		DP_NOTICE(p_hwfn,
+			  "Illegal write by chip to [%08x:%08x] blocked.\n"
+			  "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
+			  "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
+			  addr_hi, addr_lo, details,
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
+			  GET_FIELD(details,
+				    PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
+			  tmp,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_RD_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_RD_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_RD_VALID) {
 		u32 addr_lo, addr_hi, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"Illegal read by chip from [%08x:%08x] blocked.\n"
-			" Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
-			" Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
-			addr_hi, addr_lo, details,
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
-			GET_FIELD(details,
-				  PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
-			tmp,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1
-									 : 0,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1
-									: 0);
+		DP_NOTICE(p_hwfn,
+			  "Illegal read by chip from [%08x:%08x] blocked.\n"
+			  "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
+			  "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
+			  addr_hi, addr_lo, details,
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
+			  GET_FIELD(details,
+				    PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
+			  tmp,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
 	if (tmp & PGLUE_ATTENTION_ICPL_VALID)
-		DP_INFO(p_hwfn, "ICPL error - %08x\n", tmp);
+		DP_NOTICE(p_hwfn, "ICPL error - %08x\n", tmp);
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
 	if (tmp & PGLUE_ATTENTION_ZLR_VALID) {
 		u32 addr_hi, addr_lo;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_MASTER_ZLR_ERR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_MASTER_ZLR_ERR_ADD_63_32);
 
-		DP_INFO(p_hwfn, "ZLR eror - %08x [Address %08x:%08x]\n",
-			tmp, addr_hi, addr_lo);
+		DP_NOTICE(p_hwfn, "ZLR error - %08x [Address %08x:%08x]\n",
+			  tmp, addr_hi, addr_lo);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_ILT_VALID) {
 		u32 addr_hi, addr_lo, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
-			details, tmp, addr_hi, addr_lo);
+		DP_NOTICE(p_hwfn,
+			  "ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
+			  details, tmp, addr_hi, addr_lo);
 	}
 
 	/* Clear the indications */
-	qed_wr(p_hwfn, p_hwfn->p_dpc_ptt,
-	       PGLUE_B_REG_LATCHED_ERRORS_CLR, (1 << 2));
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_LATCHED_ERRORS_CLR, BIT(2));
 
 	return 0;
 }
 
+static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn)
+{
+	return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt);
+}
+
 #define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
 #define QED_DORQ_ATTENTION_OPAQUE_MASK  (0xffff)
 #define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
@@ -376,6 +378,9 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
 	u32 count = QED_DB_REC_COUNT;
 	u32 usage = 1;
 
+	/* Flush any pending (e)dpms as they may never arrive */
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
+
 	/* wait for usage to zero or count to run out. This is necessary since
 	 * EDPM doorbell transactions can take multiple 64b cycles, and as such
 	 * can "split" over the pci. Possibly, the doorbell drop can happen with
@@ -404,51 +409,74 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
 
 int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 overflow;
+	u32 attn_ovfl, cur_ovfl;
 	int rc;
 
-	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
-	DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow);
-	if (!overflow) {
-		qed_db_recovery_execute(p_hwfn, DB_REC_ONCE);
+	attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT,
+				       &p_hwfn->db_recovery_info.overflow);
+	cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!cur_ovfl && !attn_ovfl)
 		return 0;
-	}
 
-	if (qed_edpm_enabled(p_hwfn)) {
+	DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n",
+		  attn_ovfl, cur_ovfl);
+
+	if (cur_ovfl && !p_hwfn->db_bar_no_edpm) {
 		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
 		if (rc)
 			return rc;
 	}
 
-	/* Flush any pending (e)dpm as they may never arrive */
-	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
-
 	/* Release overflow sticky indication (stop silently dropping everything) */
 	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
 
 	/* Repeat all last doorbells (doorbell drop recovery) */
-	qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL);
+	qed_db_recovery_execute(p_hwfn);
 
 	return 0;
 }
 
-static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn)
 {
-	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
 	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+	u32 overflow;
 	int rc;
 
-	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
-	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!overflow)
+		goto out;
+
+	/* Run PF doorbell recovery in next periodic handler */
+	set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow);
+
+	if (!p_hwfn->db_bar_no_edpm) {
+		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+		if (rc)
+			goto out;
+	}
+
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+out:
+	/* Schedule the handler even if overflow was not detected */
+	qed_periodic_db_rec_start(p_hwfn);
+}
+
+static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
+{
+	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
+	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
 
 	/* int_sts may be zero since all PFs were interrupted for doorbell
 	 * overflow but another one already handled it. Can abort here. If
 	 * This PF also requires overflow recovery we will be interrupted again.
 	 * The masked almost full indication may also be set. Ignoring.
 	 */
+	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
 	if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
 		return 0;
 
+	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+
 	/* check if db_drop or overflow happened */
 	if (int_sts & (DORQ_REG_INT_STS_DB_DROP |
 		       DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) {
@@ -475,11 +503,6 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 			  GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
 			  first_drop_reason, all_drops_reason);
 
-		rc = qed_db_rec_handler(p_hwfn, p_ptt);
-		qed_periodic_db_rec_start(p_hwfn);
-		if (rc)
-			return rc;
-
 		/* Clear the doorbell drop details and prepare for next drop */
 		qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0);
 
@@ -505,6 +528,25 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 	return -EINVAL;
 }
 
+static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+{
+	p_hwfn->db_recovery_info.dorq_attn = true;
+	qed_dorq_attn_overflow(p_hwfn);
+
+	return qed_dorq_attn_int_sts(p_hwfn);
+}
+
+static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn)
+{
+	if (p_hwfn->db_recovery_info.dorq_attn)
+		goto out;
+
+	/* Call DORQ callback if the attention was missed */
+	qed_dorq_attn_cb(p_hwfn);
+out:
+	p_hwfn->db_recovery_info.dorq_attn = false;
+}
+
 /* Instead of major changes to the data-structure, we have a some 'special'
  * identifiers for sources that changed meaning between adapters.
  */
@@ -540,7 +582,7 @@ static struct aeu_invert_reg aeu_descs[NUM_ATTN_REGS] = {
 			{"PGLUE misc_flr", ATTENTION_SINGLE,
 			 NULL, MAX_BLOCK_ID},
 			{"PGLUE B RBC", ATTENTION_PAR_INT,
-			 qed_pglub_rbc_attn_cb, BLOCK_PGLUE_B},
+			 qed_pglueb_rbc_attn_cb, BLOCK_PGLUE_B},
 			{"PGLUE misc_mctp", ATTENTION_SINGLE,
 			 NULL, MAX_BLOCK_ID},
 			{"Flash event", ATTENTION_SINGLE, NULL, MAX_BLOCK_ID},
@@ -772,18 +814,12 @@ static inline u16 qed_attn_update_idx(struct qed_hwfn *p_hwfn,
 {
 	u16 rc = 0, index;
 
-	/* Make certain HW write took affect */
-	mmiowb();
-
 	index = le16_to_cpu(p_sb_desc->sb_attn->sb_index);
 	if (p_sb_desc->index != index) {
 		p_sb_desc->index	= index;
 		rc		      = QED_SB_ATT_IDX;
 	}
 
-	/* Make certain we got a consistent view with HW */
-	mmiowb();
-
 	return rc;
 }
 
@@ -1078,6 +1114,9 @@ static int qed_int_deassertion(struct qed_hwfn  *p_hwfn,
 		}
 	}
 
+	/* Handle missed DORQ attention */
+	qed_dorq_attn_handler(p_hwfn);
+
 	/* Clear IGU indication for the deasserted bits */
 	DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview +
 				    GTT_BAR0_MAP_REG_IGU_CMD +
@@ -1168,7 +1207,6 @@ static void qed_sb_ack_attn(struct qed_hwfn *p_hwfn,
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
 	 */
-	mmiowb();
 	barrier();
 }
 
@@ -1470,10 +1508,10 @@ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn,
 
 		qed_dmae_host2grc(p_hwfn, p_ptt, (u64)(uintptr_t)&phys_addr,
 				  CAU_REG_SB_ADDR_MEMORY +
-				  igu_sb_id * sizeof(u64), 2, 0);
+				  igu_sb_id * sizeof(u64), 2, NULL);
 		qed_dmae_host2grc(p_hwfn, p_ptt, (u64)(uintptr_t)&sb_entry,
 				  CAU_REG_SB_VAR_MEMORY +
-				  igu_sb_id * sizeof(u64), 2, 0);
+				  igu_sb_id * sizeof(u64), 2, NULL);
 	} else {
 		/* Initialize Status Block Address */
 		STORE_RT_REG_AGG(p_hwfn,
@@ -1803,9 +1841,6 @@ static void qed_int_igu_enable_attn(struct qed_hwfn *p_hwfn,
 	qed_wr(p_hwfn, p_ptt, IGU_REG_TRAILING_EDGE_LATCH, 0xfff);
 	qed_wr(p_hwfn, p_ptt, IGU_REG_ATTENTION_ENABLE, 0xfff);
 
-	/* Flush the writes to IGU */
-	mmiowb();
-
 	/* Unmask AEU signals toward IGU */
 	qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_MASK_ATTN_IGU, 0xff);
 }
@@ -1869,9 +1904,6 @@ static void qed_int_igu_cleanup_sb(struct qed_hwfn *p_hwfn,
 
 	qed_wr(p_hwfn, p_ptt, IGU_REG_COMMAND_REG_CTRL, cmd_ctrl);
 
-	/* Flush the write to IGU */
-	mmiowb();
-
 	/* calculate where to read the status bit from */
 	sb_bit = 1 << (igu_sb_id % 32);
 	sb_bit_addr = igu_sb_id / 32 * sizeof(u32);
@@ -2330,7 +2362,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 
 	rc = qed_dmae_grc2host(p_hwfn, p_ptt, CAU_REG_SB_VAR_MEMORY +
 			       sb_id * sizeof(u64),
-			       (u64)(uintptr_t)&sb_entry, 2, 0);
+			       (u64)(uintptr_t)&sb_entry, 2, NULL);
 	if (rc) {
 		DP_ERR(p_hwfn, "dmae_grc2host failed %d\n", rc);
 		return rc;
@@ -2344,7 +2376,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 	rc = qed_dmae_host2grc(p_hwfn, p_ptt,
 			       (u64)(uintptr_t)&sb_entry,
 			       CAU_REG_SB_VAR_MEMORY +
-			       sb_id * sizeof(u64), 2, 0);
+			       sb_id * sizeof(u64), 2, NULL);
 	if (rc) {
 		DP_ERR(p_hwfn, "dmae_host2grc failed %d\n", rc);
 		return rc;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index d81a62ebd524..d473b522afc5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -192,8 +192,8 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev);
 
 /**
  * @brief - Doorbell Recovery handler.
- *          Run DB_REAL_DEAL doorbell recovery in case of PF overflow
- *          (and flush DORQ if needed), otherwise run DB_REC_ONCE.
+ *          Run doorbell recovery in case of PF overflow (and flush DORQ if
+ *          needed).
  *
  * @param p_hwfn
  * @param p_ptt
@@ -431,4 +431,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 
 #define QED_MAPPING_MEMORY_SIZE(dev)	(NUM_OF_SBS(dev))
 
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt);
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index 4f8a685d1a55..5585c18053ec 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -1082,7 +1082,7 @@ struct qed_hash_iscsi_con {
 static int qed_fill_iscsi_dev_info(struct qed_dev *cdev,
 				   struct qed_dev_iscsi_info *info)
 {
-	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_hwfn *hwfn = QED_AFFIN_HWFN(cdev);
 
 	int rc;
 
@@ -1141,8 +1141,8 @@ static int qed_iscsi_stop(struct qed_dev *cdev)
 	}
 
 	/* Stop the iscsi */
-	rc = qed_sp_iscsi_func_stop(QED_LEADING_HWFN(cdev),
-				    QED_SPQ_MODE_EBLOCK, NULL);
+	rc = qed_sp_iscsi_func_stop(QED_AFFIN_HWFN(cdev), QED_SPQ_MODE_EBLOCK,
+				    NULL);
 	cdev->flags &= ~QED_FLAG_STORAGE_STARTED;
 
 	return rc;
@@ -1161,9 +1161,8 @@ static int qed_iscsi_start(struct qed_dev *cdev,
 		return 0;
 	}
 
-	rc = qed_sp_iscsi_func_start(QED_LEADING_HWFN(cdev),
-				     QED_SPQ_MODE_EBLOCK, NULL, event_context,
-				     async_event_cb);
+	rc = qed_sp_iscsi_func_start(QED_AFFIN_HWFN(cdev), QED_SPQ_MODE_EBLOCK,
+				     NULL, event_context, async_event_cb);
 	if (rc) {
 		DP_NOTICE(cdev, "Failed to start iscsi\n");
 		return rc;
@@ -1182,8 +1181,7 @@ static int qed_iscsi_start(struct qed_dev *cdev,
 		return -ENOMEM;
 	}
 
-	rc = qed_cxt_get_tid_mem_info(QED_LEADING_HWFN(cdev),
-				      tid_info);
+	rc = qed_cxt_get_tid_mem_info(QED_AFFIN_HWFN(cdev), tid_info);
 	if (rc) {
 		DP_NOTICE(cdev, "Failed to gather task information\n");
 		qed_iscsi_stop(cdev);
@@ -1215,7 +1213,7 @@ static int qed_iscsi_acquire_conn(struct qed_dev *cdev,
 		return -ENOMEM;
 
 	/* Acquire the connection */
-	rc = qed_iscsi_acquire_connection(QED_LEADING_HWFN(cdev), NULL,
+	rc = qed_iscsi_acquire_connection(QED_AFFIN_HWFN(cdev), NULL,
 					  &hash_con->con);
 	if (rc) {
 		DP_NOTICE(cdev, "Failed to acquire Connection\n");
@@ -1229,7 +1227,7 @@ static int qed_iscsi_acquire_conn(struct qed_dev *cdev,
 	hash_add(cdev->connections, &hash_con->node, *handle);
 
 	if (p_doorbell)
-		*p_doorbell = qed_iscsi_get_db_addr(QED_LEADING_HWFN(cdev),
+		*p_doorbell = qed_iscsi_get_db_addr(QED_AFFIN_HWFN(cdev),
 						    *handle);
 
 	return 0;
@@ -1247,7 +1245,7 @@ static int qed_iscsi_release_conn(struct qed_dev *cdev, u32 handle)
 	}
 
 	hlist_del(&hash_con->node);
-	qed_iscsi_release_connection(QED_LEADING_HWFN(cdev), hash_con->con);
+	qed_iscsi_release_connection(QED_AFFIN_HWFN(cdev), hash_con->con);
 	kfree(hash_con);
 
 	return 0;
@@ -1324,7 +1322,7 @@ static int qed_iscsi_offload_conn(struct qed_dev *cdev,
 	/* Set default values on other connection fields */
 	con->offl_flags = 0x1;
 
-	return qed_sp_iscsi_conn_offload(QED_LEADING_HWFN(cdev), con,
+	return qed_sp_iscsi_conn_offload(QED_AFFIN_HWFN(cdev), con,
 					 QED_SPQ_MODE_EBLOCK, NULL);
 }
 
@@ -1351,7 +1349,7 @@ static int qed_iscsi_update_conn(struct qed_dev *cdev,
 	con->first_seq_length = conn_info->first_seq_length;
 	con->exp_stat_sn = conn_info->exp_stat_sn;
 
-	return qed_sp_iscsi_conn_update(QED_LEADING_HWFN(cdev), con,
+	return qed_sp_iscsi_conn_update(QED_AFFIN_HWFN(cdev), con,
 					QED_SPQ_MODE_EBLOCK, NULL);
 }
 
@@ -1366,8 +1364,7 @@ static int qed_iscsi_clear_conn_sq(struct qed_dev *cdev, u32 handle)
 		return -EINVAL;
 	}
 
-	return qed_sp_iscsi_conn_clear_sq(QED_LEADING_HWFN(cdev),
-					  hash_con->con,
+	return qed_sp_iscsi_conn_clear_sq(QED_AFFIN_HWFN(cdev), hash_con->con,
 					  QED_SPQ_MODE_EBLOCK, NULL);
 }
 
@@ -1385,14 +1382,13 @@ static int qed_iscsi_destroy_conn(struct qed_dev *cdev,
 
 	hash_con->con->abortive_dsconnect = abrt_conn;
 
-	return qed_sp_iscsi_conn_terminate(QED_LEADING_HWFN(cdev),
-					   hash_con->con,
+	return qed_sp_iscsi_conn_terminate(QED_AFFIN_HWFN(cdev), hash_con->con,
 					   QED_SPQ_MODE_EBLOCK, NULL);
 }
 
 static int qed_iscsi_stats(struct qed_dev *cdev, struct qed_iscsi_stats *stats)
 {
-	return qed_iscsi_get_stats(QED_LEADING_HWFN(cdev), stats);
+	return qed_iscsi_get_stats(QED_AFFIN_HWFN(cdev), stats);
 }
 
 static int qed_iscsi_change_mac(struct qed_dev *cdev,
@@ -1407,8 +1403,7 @@ static int qed_iscsi_change_mac(struct qed_dev *cdev,
 		return -EINVAL;
 	}
 
-	return qed_sp_iscsi_mac_update(QED_LEADING_HWFN(cdev),
-				       hash_con->con,
+	return qed_sp_iscsi_mac_update(QED_AFFIN_HWFN(cdev), hash_con->con,
 				       QED_SPQ_MODE_EBLOCK, NULL);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index beb8e5d6401a..f380fae8799d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -63,7 +63,12 @@ struct mpa_v2_hdr {
 #define MPA_REV2(_mpa_rev) ((_mpa_rev) == MPA_NEGOTIATION_TYPE_ENHANCED)
 
 #define QED_IWARP_INVALID_TCP_CID	0xffffffff
-#define QED_IWARP_RCV_WND_SIZE_DEF	(256 * 1024)
+
+#define QED_IWARP_RCV_WND_SIZE_DEF_BB_2P (200 * 1024)
+#define QED_IWARP_RCV_WND_SIZE_DEF_BB_4P (100 * 1024)
+#define QED_IWARP_RCV_WND_SIZE_DEF_AH_2P (150 * 1024)
+#define QED_IWARP_RCV_WND_SIZE_DEF_AH_4P (90 * 1024)
+
 #define QED_IWARP_RCV_WND_SIZE_MIN	(0xffff)
 #define TIMESTAMP_HEADER_SIZE		(12)
 #define QED_IWARP_MAX_FIN_RT_DEFAULT	(2)
@@ -532,7 +537,8 @@ int qed_iwarp_destroy_qp(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
 
 	/* Make sure ep is closed before returning and freeing memory. */
 	if (ep) {
-		while (ep->state != QED_IWARP_EP_CLOSED && wait_count++ < 200)
+		while (READ_ONCE(ep->state) != QED_IWARP_EP_CLOSED &&
+		       wait_count++ < 200)
 			msleep(100);
 
 		if (ep->state != QED_IWARP_EP_CLOSED)
@@ -1022,8 +1028,6 @@ qed_iwarp_mpa_complete(struct qed_hwfn *p_hwfn,
 
 	params.ep_context = ep;
 
-	ep->state = QED_IWARP_EP_CLOSED;
-
 	switch (fw_return_code) {
 	case RDMA_RETURN_OK:
 		ep->qp->max_rd_atomic_req = ep->cm_info.ord;
@@ -1083,6 +1087,10 @@ qed_iwarp_mpa_complete(struct qed_hwfn *p_hwfn,
 		break;
 	}
 
+	if (fw_return_code != RDMA_RETURN_OK)
+		/* paired with READ_ONCE in destroy_qp */
+		smp_store_release(&ep->state, QED_IWARP_EP_CLOSED);
+
 	ep->event_cb(ep->cb_context, &params);
 
 	/* on passive side, if there is no associated QP (REJECT) we need to
@@ -1688,6 +1696,15 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
 
 	eth_hlen = ETH_HLEN + (vlan_valid ? sizeof(u32) : 0);
 
+	if (!ether_addr_equal(ethh->h_dest,
+			      p_hwfn->p_rdma_info->iwarp.mac_addr)) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_RDMA,
+			   "Got unexpected mac %pM instead of %pM\n",
+			   ethh->h_dest, p_hwfn->p_rdma_info->iwarp.mac_addr);
+		return -EINVAL;
+	}
+
 	ether_addr_copy(remote_mac_addr, ethh->h_source);
 	ether_addr_copy(local_mac_addr, ethh->h_dest);
 
@@ -2519,7 +2536,7 @@ qed_iwarp_ll2_slowpath(void *cxt,
 		memset(fpdu, 0, sizeof(*fpdu));
 }
 
-static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn)
 {
 	struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp;
 	int rc = 0;
@@ -2554,8 +2571,9 @@ static int qed_iwarp_ll2_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		iwarp_info->ll2_mpa_handle = QED_IWARP_HANDLE_INVAL;
 	}
 
-	qed_llh_remove_mac_filter(p_hwfn,
-				  p_ptt, p_hwfn->p_rdma_info->iwarp.mac_addr);
+	qed_llh_remove_mac_filter(p_hwfn->cdev, 0,
+				  p_hwfn->p_rdma_info->iwarp.mac_addr);
+
 	return rc;
 }
 
@@ -2600,12 +2618,12 @@ qed_iwarp_ll2_alloc_buffers(struct qed_hwfn *p_hwfn,
 static int
 qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 		    struct qed_rdma_start_in_params *params,
-		    struct qed_ptt *p_ptt)
+		    u32 rcv_wnd_size)
 {
 	struct qed_iwarp_info *iwarp_info;
 	struct qed_ll2_acquire_data data;
 	struct qed_ll2_cbs cbs;
-	u32 mpa_buff_size;
+	u32 buff_size;
 	u16 n_ooo_bufs;
 	int rc = 0;
 	int i;
@@ -2619,7 +2637,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 
 	ether_addr_copy(p_hwfn->p_rdma_info->iwarp.mac_addr, params->mac_addr);
 
-	rc = qed_llh_add_mac_filter(p_hwfn, p_ptt, params->mac_addr);
+	rc = qed_llh_add_mac_filter(p_hwfn->cdev, 0, params->mac_addr);
 	if (rc)
 		return rc;
 
@@ -2628,11 +2646,12 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	cbs.rx_release_cb = qed_iwarp_ll2_rel_rx_pkt;
 	cbs.tx_comp_cb = qed_iwarp_ll2_comp_tx_pkt;
 	cbs.tx_release_cb = qed_iwarp_ll2_rel_tx_pkt;
+	cbs.slowpath_cb = NULL;
 	cbs.cookie = p_hwfn;
 
 	memset(&data, 0, sizeof(data));
 	data.input.conn_type = QED_LL2_TYPE_IWARP;
-	data.input.mtu = QED_IWARP_MAX_SYN_PKT_SIZE;
+	data.input.mtu = params->max_mtu;
 	data.input.rx_num_desc = QED_IWARP_LL2_SYN_RX_SIZE;
 	data.input.tx_num_desc = QED_IWARP_LL2_SYN_TX_SIZE;
 	data.input.tx_max_bds_per_packet = 1;	/* will never be fragmented */
@@ -2644,7 +2663,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	rc = qed_ll2_acquire_connection(p_hwfn, &data);
 	if (rc) {
 		DP_NOTICE(p_hwfn, "Failed to acquire LL2 connection\n");
-		qed_llh_remove_mac_filter(p_hwfn, p_ptt, params->mac_addr);
+		qed_llh_remove_mac_filter(p_hwfn->cdev, 0, params->mac_addr);
 		return rc;
 	}
 
@@ -2654,9 +2673,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 		goto err;
 	}
 
+	buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu);
 	rc = qed_iwarp_ll2_alloc_buffers(p_hwfn,
 					 QED_IWARP_LL2_SYN_RX_SIZE,
-					 QED_IWARP_MAX_SYN_PKT_SIZE,
+					 buff_size,
 					 iwarp_info->ll2_syn_handle);
 	if (rc)
 		goto err;
@@ -2665,7 +2685,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	data.input.conn_type = QED_LL2_TYPE_OOO;
 	data.input.mtu = params->max_mtu;
 
-	n_ooo_bufs = (QED_IWARP_MAX_OOO * QED_IWARP_RCV_WND_SIZE_DEF) /
+	n_ooo_bufs = (QED_IWARP_MAX_OOO * rcv_wnd_size) /
 		     iwarp_info->max_mtu;
 	n_ooo_bufs = min_t(u32, n_ooo_bufs, QED_IWARP_LL2_OOO_MAX_RX_SIZE);
 
@@ -2698,6 +2718,8 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	data.input.rx_num_desc = n_ooo_bufs * 2;
 	data.input.tx_num_desc = data.input.rx_num_desc;
 	data.input.tx_max_bds_per_packet = QED_IWARP_MAX_BDS_PER_FPDU;
+	data.input.tx_tc = PKT_LB_TC;
+	data.input.tx_dest = QED_LL2_TX_DEST_LB;
 	data.p_connection_handle = &iwarp_info->ll2_mpa_handle;
 	data.input.secondary_queue = true;
 	data.cbs = &cbs;
@@ -2710,10 +2732,9 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	if (rc)
 		goto err;
 
-	mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu);
 	rc = qed_iwarp_ll2_alloc_buffers(p_hwfn,
 					 data.input.rx_num_desc,
-					 mpa_buff_size,
+					 buff_size,
 					 iwarp_info->ll2_mpa_handle);
 	if (rc)
 		goto err;
@@ -2726,7 +2747,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 
 	iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps;
 
-	iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL);
+	iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL);
 	if (!iwarp_info->mpa_intermediate_buf)
 		goto err;
 
@@ -2748,21 +2769,35 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 			      &iwarp_info->mpa_buf_list);
 	return rc;
 err:
-	qed_iwarp_ll2_stop(p_hwfn, p_ptt);
+	qed_iwarp_ll2_stop(p_hwfn);
 
 	return rc;
 }
 
-int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+static struct {
+	u32 two_ports;
+	u32 four_ports;
+} qed_iwarp_rcv_wnd_size[MAX_CHIP_IDS] = {
+	{QED_IWARP_RCV_WND_SIZE_DEF_BB_2P, QED_IWARP_RCV_WND_SIZE_DEF_BB_4P},
+	{QED_IWARP_RCV_WND_SIZE_DEF_AH_2P, QED_IWARP_RCV_WND_SIZE_DEF_AH_4P}
+};
+
+int qed_iwarp_setup(struct qed_hwfn *p_hwfn,
 		    struct qed_rdma_start_in_params *params)
 {
+	struct qed_dev *cdev = p_hwfn->cdev;
 	struct qed_iwarp_info *iwarp_info;
+	enum chip_ids chip_id;
 	u32 rcv_wnd_size;
 
 	iwarp_info = &p_hwfn->p_rdma_info->iwarp;
 
 	iwarp_info->tcp_flags = QED_IWARP_TS_EN;
-	rcv_wnd_size = QED_IWARP_RCV_WND_SIZE_DEF;
+
+	chip_id = QED_IS_BB(cdev) ? CHIP_BB : CHIP_K2;
+	rcv_wnd_size = (qed_device_num_ports(cdev) == 4) ?
+		qed_iwarp_rcv_wnd_size[chip_id].four_ports :
+		qed_iwarp_rcv_wnd_size[chip_id].two_ports;
 
 	/* value 0 is used for ilog2(QED_IWARP_RCV_WND_SIZE_MIN) */
 	iwarp_info->rcv_wnd_scale = ilog2(rcv_wnd_size) -
@@ -2785,10 +2820,10 @@ int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 				  qed_iwarp_async_event);
 	qed_ooo_setup(p_hwfn);
 
-	return qed_iwarp_ll2_start(p_hwfn, params, p_ptt);
+	return qed_iwarp_ll2_start(p_hwfn, params, rcv_wnd_size);
 }
 
-int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+int qed_iwarp_stop(struct qed_hwfn *p_hwfn)
 {
 	int rc;
 
@@ -2799,7 +2834,7 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 
 	qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_IWARP);
 
-	return qed_iwarp_ll2_stop(p_hwfn, p_ptt);
+	return qed_iwarp_ll2_stop(p_hwfn);
 }
 
 static void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
@@ -2816,7 +2851,9 @@ static void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
 	params.status = (fw_return_code == IWARP_QP_IN_ERROR_GOOD_CLOSE) ?
 			 0 : -ECONNRESET;
 
-	ep->state = QED_IWARP_EP_CLOSED;
+	/* paired with READ_ONCE in destroy_qp */
+	smp_store_release(&ep->state, QED_IWARP_EP_CLOSED);
+
 	spin_lock_bh(&p_hwfn->p_rdma_info->iwarp.iw_lock);
 	list_del(&ep->list_entry);
 	spin_unlock_bh(&p_hwfn->p_rdma_info->iwarp.iw_lock);
@@ -2905,7 +2942,8 @@ qed_iwarp_tcp_connect_unsuccessful(struct qed_hwfn *p_hwfn,
 	params.event = QED_IWARP_EVENT_ACTIVE_COMPLETE;
 	params.ep_context = ep;
 	params.cm_info = &ep->cm_info;
-	ep->state = QED_IWARP_EP_CLOSED;
+	/* paired with READ_ONCE in destroy_qp */
+	smp_store_release(&ep->state, QED_IWARP_EP_CLOSED);
 
 	switch (fw_return_code) {
 	case IWARP_CONN_ERROR_TCP_CONNECT_INVALID_PACKET:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
index b8f612d00241..c1b2057d23b8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
@@ -46,7 +46,6 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state);
 
 #define QED_IWARP_LL2_SYN_TX_SIZE       (128)
 #define QED_IWARP_LL2_SYN_RX_SIZE       (256)
-#define QED_IWARP_MAX_SYN_PKT_SIZE      (128)
 
 #define QED_IWARP_LL2_OOO_DEF_TX_SIZE   (256)
 #define QED_IWARP_MAX_OOO		(16)
@@ -184,13 +183,13 @@ struct qed_iwarp_listener {
 
 int qed_iwarp_alloc(struct qed_hwfn *p_hwfn);
 
-int qed_iwarp_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+int qed_iwarp_setup(struct qed_hwfn *p_hwfn,
 		    struct qed_rdma_start_in_params *params);
 
 void qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn,
 			      struct iwarp_init_func_ramrod_data *p_ramrod);
 
-int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+int qed_iwarp_stop(struct qed_hwfn *p_hwfn);
 
 void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 58be1c4c6668..9f36e7948222 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -1898,6 +1898,7 @@ static void _qed_get_vport_stats(struct qed_dev *cdev,
 		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
 		struct qed_ptt *p_ptt = IS_PF(cdev) ? qed_ptt_acquire(p_hwfn)
 						    :  NULL;
+		bool b_get_port_stats;
 
 		if (IS_PF(cdev)) {
 			/* The main vport index is relative first */
@@ -1912,8 +1913,9 @@ static void _qed_get_vport_stats(struct qed_dev *cdev,
 			continue;
 		}
 
+		b_get_port_stats = IS_PF(cdev) && IS_LEAD_HWFN(p_hwfn);
 		__qed_get_vport_stats(p_hwfn, p_ptt, stats, fw_vport,
-				      IS_PF(cdev) ? true : false);
+				      b_get_port_stats);
 
 out:
 		if (IS_PF(cdev) && p_ptt)
@@ -2109,7 +2111,7 @@ int qed_get_rxq_coalesce(struct qed_hwfn *p_hwfn,
 
 	rc = qed_dmae_grc2host(p_hwfn, p_ptt, CAU_REG_SB_VAR_MEMORY +
 			       p_cid->sb_igu_id * sizeof(u64),
-			       (u64)(uintptr_t)&sb_entry, 2, 0);
+			       (u64)(uintptr_t)&sb_entry, 2, NULL);
 	if (rc) {
 		DP_ERR(p_hwfn, "dmae_grc2host failed %d\n", rc);
 		return rc;
@@ -2142,7 +2144,7 @@ int qed_get_txq_coalesce(struct qed_hwfn *p_hwfn,
 
 	rc = qed_dmae_grc2host(p_hwfn, p_ptt, CAU_REG_SB_VAR_MEMORY +
 			       p_cid->sb_igu_id * sizeof(u64),
-			       (u64)(uintptr_t)&sb_entry, 2, 0);
+			       (u64)(uintptr_t)&sb_entry, 2, NULL);
 	if (rc) {
 		DP_ERR(p_hwfn, "dmae_grc2host failed %d\n", rc);
 		return rc;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index b5f419b71287..19a1a58d60f8 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -239,9 +239,8 @@ out_post1:
 	buffer->phys_addr = new_phys_addr;
 
 out_post:
-	rc = qed_ll2_post_rx_buffer(QED_LEADING_HWFN(cdev), cdev->ll2->handle,
-				    buffer->phys_addr, 0,  buffer, 1);
-
+	rc = qed_ll2_post_rx_buffer(p_hwfn, cdev->ll2->handle,
+				    buffer->phys_addr, 0, buffer, 1);
 	if (rc)
 		qed_ll2_dealloc_buffer(cdev, buffer);
 }
@@ -926,16 +925,15 @@ static int qed_ll2_lb_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
 	return 0;
 }
 
-static void qed_ll2_stop_ooo(struct qed_dev *cdev)
+static void qed_ll2_stop_ooo(struct qed_hwfn *p_hwfn)
 {
-	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
-	u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
+	u8 *handle = &p_hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
 
-	DP_VERBOSE(cdev, QED_MSG_STORAGE, "Stopping LL2 OOO queue [%02x]\n",
-		   *handle);
+	DP_VERBOSE(p_hwfn, (QED_MSG_STORAGE | QED_MSG_LL2),
+		   "Stopping LL2 OOO queue [%02x]\n", *handle);
 
-	qed_ll2_terminate_connection(hwfn, *handle);
-	qed_ll2_release_connection(hwfn, *handle);
+	qed_ll2_terminate_connection(p_hwfn, *handle);
+	qed_ll2_release_connection(p_hwfn, *handle);
 	*handle = QED_LL2_UNUSED_HANDLE;
 }
 
@@ -1574,12 +1572,12 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 
 	if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE) {
 		if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
-			qed_llh_add_protocol_filter(p_hwfn, p_ptt,
-						    ETH_P_FCOE, 0,
-						    QED_LLH_FILTER_ETHERTYPE);
-		qed_llh_add_protocol_filter(p_hwfn, p_ptt,
-					    ETH_P_FIP, 0,
-					    QED_LLH_FILTER_ETHERTYPE);
+			qed_llh_add_protocol_filter(p_hwfn->cdev, 0,
+						    QED_LLH_FILTER_ETHERTYPE,
+						    ETH_P_FCOE, 0);
+		qed_llh_add_protocol_filter(p_hwfn->cdev, 0,
+					    QED_LLH_FILTER_ETHERTYPE,
+					    ETH_P_FIP, 0);
 	}
 
 out:
@@ -1980,12 +1978,12 @@ int qed_ll2_terminate_connection(void *cxt, u8 connection_handle)
 
 	if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE) {
 		if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
-			qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
-						       ETH_P_FCOE, 0,
-						      QED_LLH_FILTER_ETHERTYPE);
-		qed_llh_remove_protocol_filter(p_hwfn, p_ptt,
-					       ETH_P_FIP, 0,
-					       QED_LLH_FILTER_ETHERTYPE);
+			qed_llh_remove_protocol_filter(p_hwfn->cdev, 0,
+						       QED_LLH_FILTER_ETHERTYPE,
+						       ETH_P_FCOE, 0);
+		qed_llh_remove_protocol_filter(p_hwfn->cdev, 0,
+					       QED_LLH_FILTER_ETHERTYPE,
+					       ETH_P_FIP, 0);
 	}
 
 out:
@@ -2086,12 +2084,12 @@ static void _qed_ll2_get_port_stats(struct qed_hwfn *p_hwfn,
 			TSTORM_LL2_PORT_STAT_OFFSET(MFW_PORT(p_hwfn)),
 			sizeof(port_stats));
 
-	p_stats->gsi_invalid_hdr = HILO_64_REGPAIR(port_stats.gsi_invalid_hdr);
-	p_stats->gsi_invalid_pkt_length =
+	p_stats->gsi_invalid_hdr += HILO_64_REGPAIR(port_stats.gsi_invalid_hdr);
+	p_stats->gsi_invalid_pkt_length +=
 	    HILO_64_REGPAIR(port_stats.gsi_invalid_pkt_length);
-	p_stats->gsi_unsupported_pkt_typ =
+	p_stats->gsi_unsupported_pkt_typ +=
 	    HILO_64_REGPAIR(port_stats.gsi_unsupported_pkt_typ);
-	p_stats->gsi_crcchksm_error =
+	p_stats->gsi_crcchksm_error +=
 	    HILO_64_REGPAIR(port_stats.gsi_crcchksm_error);
 }
 
@@ -2109,9 +2107,9 @@ static void _qed_ll2_get_tstats(struct qed_hwfn *p_hwfn,
 		      CORE_LL2_TSTORM_PER_QUEUE_STAT_OFFSET(qid);
 	qed_memcpy_from(p_hwfn, p_ptt, &tstats, tstats_addr, sizeof(tstats));
 
-	p_stats->packet_too_big_discard =
+	p_stats->packet_too_big_discard +=
 			HILO_64_REGPAIR(tstats.packet_too_big_discard);
-	p_stats->no_buff_discard = HILO_64_REGPAIR(tstats.no_buff_discard);
+	p_stats->no_buff_discard += HILO_64_REGPAIR(tstats.no_buff_discard);
 }
 
 static void _qed_ll2_get_ustats(struct qed_hwfn *p_hwfn,
@@ -2128,12 +2126,12 @@ static void _qed_ll2_get_ustats(struct qed_hwfn *p_hwfn,
 		      CORE_LL2_USTORM_PER_QUEUE_STAT_OFFSET(qid);
 	qed_memcpy_from(p_hwfn, p_ptt, &ustats, ustats_addr, sizeof(ustats));
 
-	p_stats->rcv_ucast_bytes = HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
-	p_stats->rcv_mcast_bytes = HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
-	p_stats->rcv_bcast_bytes = HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
-	p_stats->rcv_ucast_pkts = HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
-	p_stats->rcv_mcast_pkts = HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
-	p_stats->rcv_bcast_pkts = HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
+	p_stats->rcv_ucast_bytes += HILO_64_REGPAIR(ustats.rcv_ucast_bytes);
+	p_stats->rcv_mcast_bytes += HILO_64_REGPAIR(ustats.rcv_mcast_bytes);
+	p_stats->rcv_bcast_bytes += HILO_64_REGPAIR(ustats.rcv_bcast_bytes);
+	p_stats->rcv_ucast_pkts += HILO_64_REGPAIR(ustats.rcv_ucast_pkts);
+	p_stats->rcv_mcast_pkts += HILO_64_REGPAIR(ustats.rcv_mcast_pkts);
+	p_stats->rcv_bcast_pkts += HILO_64_REGPAIR(ustats.rcv_bcast_pkts);
 }
 
 static void _qed_ll2_get_pstats(struct qed_hwfn *p_hwfn,
@@ -2150,23 +2148,21 @@ static void _qed_ll2_get_pstats(struct qed_hwfn *p_hwfn,
 		      CORE_LL2_PSTORM_PER_QUEUE_STAT_OFFSET(stats_id);
 	qed_memcpy_from(p_hwfn, p_ptt, &pstats, pstats_addr, sizeof(pstats));
 
-	p_stats->sent_ucast_bytes = HILO_64_REGPAIR(pstats.sent_ucast_bytes);
-	p_stats->sent_mcast_bytes = HILO_64_REGPAIR(pstats.sent_mcast_bytes);
-	p_stats->sent_bcast_bytes = HILO_64_REGPAIR(pstats.sent_bcast_bytes);
-	p_stats->sent_ucast_pkts = HILO_64_REGPAIR(pstats.sent_ucast_pkts);
-	p_stats->sent_mcast_pkts = HILO_64_REGPAIR(pstats.sent_mcast_pkts);
-	p_stats->sent_bcast_pkts = HILO_64_REGPAIR(pstats.sent_bcast_pkts);
+	p_stats->sent_ucast_bytes += HILO_64_REGPAIR(pstats.sent_ucast_bytes);
+	p_stats->sent_mcast_bytes += HILO_64_REGPAIR(pstats.sent_mcast_bytes);
+	p_stats->sent_bcast_bytes += HILO_64_REGPAIR(pstats.sent_bcast_bytes);
+	p_stats->sent_ucast_pkts += HILO_64_REGPAIR(pstats.sent_ucast_pkts);
+	p_stats->sent_mcast_pkts += HILO_64_REGPAIR(pstats.sent_mcast_pkts);
+	p_stats->sent_bcast_pkts += HILO_64_REGPAIR(pstats.sent_bcast_pkts);
 }
 
-int qed_ll2_get_stats(void *cxt,
-		      u8 connection_handle, struct qed_ll2_stats *p_stats)
+static int __qed_ll2_get_stats(void *cxt, u8 connection_handle,
+			       struct qed_ll2_stats *p_stats)
 {
 	struct qed_hwfn *p_hwfn = cxt;
 	struct qed_ll2_info *p_ll2_conn = NULL;
 	struct qed_ptt *p_ptt;
 
-	memset(p_stats, 0, sizeof(*p_stats));
-
 	if ((connection_handle >= QED_MAX_NUM_OF_LL2_CONNECTIONS) ||
 	    !p_hwfn->p_ll2_info)
 		return -EINVAL;
@@ -2181,15 +2177,26 @@ int qed_ll2_get_stats(void *cxt,
 
 	if (p_ll2_conn->input.gsi_enable)
 		_qed_ll2_get_port_stats(p_hwfn, p_ptt, p_stats);
+
 	_qed_ll2_get_tstats(p_hwfn, p_ptt, p_ll2_conn, p_stats);
+
 	_qed_ll2_get_ustats(p_hwfn, p_ptt, p_ll2_conn, p_stats);
+
 	if (p_ll2_conn->tx_stats_en)
 		_qed_ll2_get_pstats(p_hwfn, p_ptt, p_ll2_conn, p_stats);
 
 	qed_ptt_release(p_hwfn, p_ptt);
+
 	return 0;
 }
 
+int qed_ll2_get_stats(void *cxt,
+		      u8 connection_handle, struct qed_ll2_stats *p_stats)
+{
+	memset(p_stats, 0, sizeof(*p_stats));
+	return __qed_ll2_get_stats(cxt, connection_handle, p_stats);
+}
+
 static void qed_ll2b_release_rx_packet(void *cxt,
 				       u8 connection_handle,
 				       void *cookie,
@@ -2216,7 +2223,7 @@ struct qed_ll2_cbs ll2_cbs = {
 	.tx_release_cb = &qed_ll2b_complete_tx_packet,
 };
 
-static void qed_ll2_set_conn_data(struct qed_dev *cdev,
+static void qed_ll2_set_conn_data(struct qed_hwfn *p_hwfn,
 				  struct qed_ll2_acquire_data *data,
 				  struct qed_ll2_params *params,
 				  enum qed_ll2_conn_type conn_type,
@@ -2232,7 +2239,7 @@ static void qed_ll2_set_conn_data(struct qed_dev *cdev,
 	data->input.tx_num_desc = QED_LL2_TX_SIZE;
 	data->p_connection_handle = handle;
 	data->cbs = &ll2_cbs;
-	ll2_cbs.cookie = QED_LEADING_HWFN(cdev);
+	ll2_cbs.cookie = p_hwfn;
 
 	if (lb) {
 		data->input.tx_tc = PKT_LB_TC;
@@ -2243,74 +2250,102 @@ static void qed_ll2_set_conn_data(struct qed_dev *cdev,
 	}
 }
 
-static int qed_ll2_start_ooo(struct qed_dev *cdev,
+static int qed_ll2_start_ooo(struct qed_hwfn *p_hwfn,
 			     struct qed_ll2_params *params)
 {
-	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
-	u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
+	u8 *handle = &p_hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
 	struct qed_ll2_acquire_data data;
 	int rc;
 
-	qed_ll2_set_conn_data(cdev, &data, params,
+	qed_ll2_set_conn_data(p_hwfn, &data, params,
 			      QED_LL2_TYPE_OOO, handle, true);
 
-	rc = qed_ll2_acquire_connection(hwfn, &data);
+	rc = qed_ll2_acquire_connection(p_hwfn, &data);
 	if (rc) {
-		DP_INFO(cdev, "Failed to acquire LL2 OOO connection\n");
+		DP_INFO(p_hwfn, "Failed to acquire LL2 OOO connection\n");
 		goto out;
 	}
 
-	rc = qed_ll2_establish_connection(hwfn, *handle);
+	rc = qed_ll2_establish_connection(p_hwfn, *handle);
 	if (rc) {
-		DP_INFO(cdev, "Failed to establist LL2 OOO connection\n");
+		DP_INFO(p_hwfn, "Failed to establish LL2 OOO connection\n");
 		goto fail;
 	}
 
 	return 0;
 
 fail:
-	qed_ll2_release_connection(hwfn, *handle);
+	qed_ll2_release_connection(p_hwfn, *handle);
 out:
 	*handle = QED_LL2_UNUSED_HANDLE;
 	return rc;
 }
 
-static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
+static bool qed_ll2_is_storage_eng1(struct qed_dev *cdev)
 {
-	struct qed_ll2_buffer *buffer, *tmp_buffer;
-	enum qed_ll2_conn_type conn_type;
-	struct qed_ll2_acquire_data data;
-	struct qed_ptt *p_ptt;
-	int rc, i;
+	return (QED_IS_FCOE_PERSONALITY(QED_LEADING_HWFN(cdev)) ||
+		QED_IS_ISCSI_PERSONALITY(QED_LEADING_HWFN(cdev))) &&
+		(QED_AFFIN_HWFN(cdev) != QED_LEADING_HWFN(cdev));
+}
 
+static int __qed_ll2_stop(struct qed_hwfn *p_hwfn)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	int rc;
 
-	/* Initialize LL2 locks & lists */
-	INIT_LIST_HEAD(&cdev->ll2->list);
-	spin_lock_init(&cdev->ll2->lock);
-	cdev->ll2->rx_size = NET_SKB_PAD + ETH_HLEN +
-			     L1_CACHE_BYTES + params->mtu;
+	rc = qed_ll2_terminate_connection(p_hwfn, cdev->ll2->handle);
+	if (rc)
+		DP_INFO(cdev, "Failed to terminate LL2 connection\n");
 
-	/*Allocate memory for LL2 */
-	DP_INFO(cdev, "Allocating LL2 buffers of size %08x bytes\n",
-		cdev->ll2->rx_size);
-	for (i = 0; i < QED_LL2_RX_SIZE; i++) {
-		buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
-		if (!buffer) {
-			DP_INFO(cdev, "Failed to allocate LL2 buffers\n");
-			goto fail;
-		}
+	qed_ll2_release_connection(p_hwfn, cdev->ll2->handle);
 
-		rc = qed_ll2_alloc_buffer(cdev, (u8 **)&buffer->data,
-					  &buffer->phys_addr);
-		if (rc) {
-			kfree(buffer);
-			goto fail;
-		}
+	return rc;
+}
 
-		list_add_tail(&buffer->list, &cdev->ll2->list);
+static int qed_ll2_stop(struct qed_dev *cdev)
+{
+	bool b_is_storage_eng1 = qed_ll2_is_storage_eng1(cdev);
+	struct qed_hwfn *p_hwfn = QED_AFFIN_HWFN(cdev);
+	int rc = 0, rc2 = 0;
+
+	if (cdev->ll2->handle == QED_LL2_UNUSED_HANDLE)
+		return 0;
+
+	qed_llh_remove_mac_filter(cdev, 0, cdev->ll2_mac_address);
+	eth_zero_addr(cdev->ll2_mac_address);
+
+	if (QED_IS_ISCSI_PERSONALITY(p_hwfn))
+		qed_ll2_stop_ooo(p_hwfn);
+
+	/* In CMT mode, LL2 is always started on engine 0 for a storage PF */
+	if (b_is_storage_eng1) {
+		rc2 = __qed_ll2_stop(QED_LEADING_HWFN(cdev));
+		if (rc2)
+			DP_NOTICE(QED_LEADING_HWFN(cdev),
+				  "Failed to stop LL2 on engine 0\n");
 	}
 
-	switch (QED_LEADING_HWFN(cdev)->hw_info.personality) {
+	rc = __qed_ll2_stop(p_hwfn);
+	if (rc)
+		DP_NOTICE(p_hwfn, "Failed to stop LL2\n");
+
+	qed_ll2_kill_buffers(cdev);
+
+	cdev->ll2->handle = QED_LL2_UNUSED_HANDLE;
+
+	return rc | rc2;
+}
+
+static int __qed_ll2_start(struct qed_hwfn *p_hwfn,
+			   struct qed_ll2_params *params)
+{
+	struct qed_ll2_buffer *buffer, *tmp_buffer;
+	struct qed_dev *cdev = p_hwfn->cdev;
+	enum qed_ll2_conn_type conn_type;
+	struct qed_ll2_acquire_data data;
+	int rc, rx_cnt;
+
+	switch (p_hwfn->hw_info.personality) {
 	case QED_PCI_FCOE:
 		conn_type = QED_LL2_TYPE_FCOE;
 		break;
@@ -2321,33 +2356,34 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 		conn_type = QED_LL2_TYPE_ROCE;
 		break;
 	default:
+
 		conn_type = QED_LL2_TYPE_TEST;
 	}
 
-	qed_ll2_set_conn_data(cdev, &data, params, conn_type,
+	qed_ll2_set_conn_data(p_hwfn, &data, params, conn_type,
 			      &cdev->ll2->handle, false);
 
-	rc = qed_ll2_acquire_connection(QED_LEADING_HWFN(cdev), &data);
+	rc = qed_ll2_acquire_connection(p_hwfn, &data);
 	if (rc) {
-		DP_INFO(cdev, "Failed to acquire LL2 connection\n");
-		goto fail;
+		DP_INFO(p_hwfn, "Failed to acquire LL2 connection\n");
+		return rc;
 	}
 
-	rc = qed_ll2_establish_connection(QED_LEADING_HWFN(cdev),
-					  cdev->ll2->handle);
+	rc = qed_ll2_establish_connection(p_hwfn, cdev->ll2->handle);
 	if (rc) {
-		DP_INFO(cdev, "Failed to establish LL2 connection\n");
-		goto release_fail;
+		DP_INFO(p_hwfn, "Failed to establish LL2 connection\n");
+		goto release_conn;
 	}
 
 	/* Post all Rx buffers to FW */
 	spin_lock_bh(&cdev->ll2->lock);
+	rx_cnt = cdev->ll2->rx_cnt;
 	list_for_each_entry_safe(buffer, tmp_buffer, &cdev->ll2->list, list) {
-		rc = qed_ll2_post_rx_buffer(QED_LEADING_HWFN(cdev),
+		rc = qed_ll2_post_rx_buffer(p_hwfn,
 					    cdev->ll2->handle,
 					    buffer->phys_addr, 0, buffer, 1);
 		if (rc) {
-			DP_INFO(cdev,
+			DP_INFO(p_hwfn,
 				"Failed to post an Rx buffer; Deleting it\n");
 			dma_unmap_single(&cdev->pdev->dev, buffer->phys_addr,
 					 cdev->ll2->rx_size, DMA_FROM_DEVICE);
@@ -2355,100 +2391,127 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 			list_del(&buffer->list);
 			kfree(buffer);
 		} else {
-			cdev->ll2->rx_cnt++;
+			rx_cnt++;
 		}
 	}
 	spin_unlock_bh(&cdev->ll2->lock);
 
-	if (!cdev->ll2->rx_cnt) {
-		DP_INFO(cdev, "Failed passing even a single Rx buffer\n");
-		goto release_terminate;
+	if (rx_cnt == cdev->ll2->rx_cnt) {
+		DP_NOTICE(p_hwfn, "Failed passing even a single Rx buffer\n");
+		goto terminate_conn;
 	}
+	cdev->ll2->rx_cnt = rx_cnt;
+
+	return 0;
+
+terminate_conn:
+	qed_ll2_terminate_connection(p_hwfn, cdev->ll2->handle);
+release_conn:
+	qed_ll2_release_connection(p_hwfn, cdev->ll2->handle);
+	return rc;
+}
+
+static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
+{
+	bool b_is_storage_eng1 = qed_ll2_is_storage_eng1(cdev);
+	struct qed_hwfn *p_hwfn = QED_AFFIN_HWFN(cdev);
+	struct qed_ll2_buffer *buffer;
+	int rx_num_desc, i, rc;
 
 	if (!is_valid_ether_addr(params->ll2_mac_address)) {
-		DP_INFO(cdev, "Invalid Ethernet address\n");
-		goto release_terminate;
+		DP_NOTICE(cdev, "Invalid Ethernet address\n");
+		return -EINVAL;
 	}
 
-	if (QED_LEADING_HWFN(cdev)->hw_info.personality == QED_PCI_ISCSI) {
-		DP_VERBOSE(cdev, QED_MSG_STORAGE, "Starting OOO LL2 queue\n");
-		rc = qed_ll2_start_ooo(cdev, params);
+	WARN_ON(!cdev->ll2->cbs);
+
+	/* Initialize LL2 locks & lists */
+	INIT_LIST_HEAD(&cdev->ll2->list);
+	spin_lock_init(&cdev->ll2->lock);
+
+	cdev->ll2->rx_size = NET_SKB_PAD + ETH_HLEN +
+			     L1_CACHE_BYTES + params->mtu;
+
+	/* Allocate memory for LL2.
+	 * In CMT mode, in case of a storage PF which is affintized to engine 1,
+	 * LL2 is started also on engine 0 and thus we need twofold buffers.
+	 */
+	rx_num_desc = QED_LL2_RX_SIZE * (b_is_storage_eng1 ? 2 : 1);
+	DP_INFO(cdev, "Allocating %d LL2 buffers of size %08x bytes\n",
+		rx_num_desc, cdev->ll2->rx_size);
+	for (i = 0; i < rx_num_desc; i++) {
+		buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+		if (!buffer) {
+			DP_INFO(cdev, "Failed to allocate LL2 buffers\n");
+			rc = -ENOMEM;
+			goto err0;
+		}
+
+		rc = qed_ll2_alloc_buffer(cdev, (u8 **)&buffer->data,
+					  &buffer->phys_addr);
 		if (rc) {
-			DP_INFO(cdev,
-				"Failed to initialize the OOO LL2 queue\n");
-			goto release_terminate;
+			kfree(buffer);
+			goto err0;
 		}
-	}
 
-	p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev));
-	if (!p_ptt) {
-		DP_INFO(cdev, "Failed to acquire PTT\n");
-		goto release_terminate;
+		list_add_tail(&buffer->list, &cdev->ll2->list);
 	}
 
-	rc = qed_llh_add_mac_filter(QED_LEADING_HWFN(cdev), p_ptt,
-				    params->ll2_mac_address);
-	qed_ptt_release(QED_LEADING_HWFN(cdev), p_ptt);
+	rc = __qed_ll2_start(p_hwfn, params);
 	if (rc) {
-		DP_ERR(cdev, "Failed to allocate LLH filter\n");
-		goto release_terminate_all;
+		DP_NOTICE(cdev, "Failed to start LL2\n");
+		goto err0;
 	}
 
-	ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address);
-	return 0;
-
-release_terminate_all:
-
-release_terminate:
-	qed_ll2_terminate_connection(QED_LEADING_HWFN(cdev), cdev->ll2->handle);
-release_fail:
-	qed_ll2_release_connection(QED_LEADING_HWFN(cdev), cdev->ll2->handle);
-fail:
-	qed_ll2_kill_buffers(cdev);
-	cdev->ll2->handle = QED_LL2_UNUSED_HANDLE;
-	return -EINVAL;
-}
-
-static int qed_ll2_stop(struct qed_dev *cdev)
-{
-	struct qed_ptt *p_ptt;
-	int rc;
-
-	if (cdev->ll2->handle == QED_LL2_UNUSED_HANDLE)
-		return 0;
+	/* In CMT mode, always need to start LL2 on engine 0 for a storage PF,
+	 * since broadcast/mutlicast packets are routed to engine 0.
+	 */
+	if (b_is_storage_eng1) {
+		rc = __qed_ll2_start(QED_LEADING_HWFN(cdev), params);
+		if (rc) {
+			DP_NOTICE(QED_LEADING_HWFN(cdev),
+				  "Failed to start LL2 on engine 0\n");
+			goto err1;
+		}
+	}
 
-	p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev));
-	if (!p_ptt) {
-		DP_INFO(cdev, "Failed to acquire PTT\n");
-		goto fail;
+	if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) {
+		DP_VERBOSE(cdev, QED_MSG_STORAGE, "Starting OOO LL2 queue\n");
+		rc = qed_ll2_start_ooo(p_hwfn, params);
+		if (rc) {
+			DP_NOTICE(cdev, "Failed to start OOO LL2\n");
+			goto err2;
+		}
 	}
 
-	qed_llh_remove_mac_filter(QED_LEADING_HWFN(cdev), p_ptt,
-				  cdev->ll2_mac_address);
-	qed_ptt_release(QED_LEADING_HWFN(cdev), p_ptt);
-	eth_zero_addr(cdev->ll2_mac_address);
+	rc = qed_llh_add_mac_filter(cdev, 0, params->ll2_mac_address);
+	if (rc) {
+		DP_NOTICE(cdev, "Failed to add an LLH filter\n");
+		goto err3;
+	}
 
-	if (QED_LEADING_HWFN(cdev)->hw_info.personality == QED_PCI_ISCSI)
-		qed_ll2_stop_ooo(cdev);
+	ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address);
 
-	rc = qed_ll2_terminate_connection(QED_LEADING_HWFN(cdev),
-					  cdev->ll2->handle);
-	if (rc)
-		DP_INFO(cdev, "Failed to terminate LL2 connection\n");
+	return 0;
 
+err3:
+	if (QED_IS_ISCSI_PERSONALITY(p_hwfn))
+		qed_ll2_stop_ooo(p_hwfn);
+err2:
+	if (b_is_storage_eng1)
+		__qed_ll2_stop(QED_LEADING_HWFN(cdev));
+err1:
+	__qed_ll2_stop(p_hwfn);
+err0:
 	qed_ll2_kill_buffers(cdev);
-
-	qed_ll2_release_connection(QED_LEADING_HWFN(cdev), cdev->ll2->handle);
 	cdev->ll2->handle = QED_LL2_UNUSED_HANDLE;
-
 	return rc;
-fail:
-	return -EINVAL;
 }
 
 static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
 			      unsigned long xmit_flags)
 {
+	struct qed_hwfn *p_hwfn = QED_AFFIN_HWFN(cdev);
 	struct qed_ll2_tx_pkt_info pkt;
 	const skb_frag_t *frag;
 	u8 flags = 0, nr_frags;
@@ -2506,7 +2569,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
 	 * routine may run and free the SKB, so no dereferencing the SKB
 	 * beyond this point unless skb has any fragments.
 	 */
-	rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle,
+	rc = qed_ll2_prepare_tx_packet(p_hwfn, cdev->ll2->handle,
 				       &pkt, 1);
 	if (rc)
 		goto err;
@@ -2524,13 +2587,13 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
 			goto err;
 		}
 
-		rc = qed_ll2_set_fragment_of_tx_packet(QED_LEADING_HWFN(cdev),
+		rc = qed_ll2_set_fragment_of_tx_packet(p_hwfn,
 						       cdev->ll2->handle,
 						       mapping,
 						       skb_frag_size(frag));
 
 		/* if failed not much to do here, partial packet has been posted
-		 * we can't free memory, will need to wait for completion.
+		 * we can't free memory, will need to wait for completion
 		 */
 		if (rc)
 			goto err2;
@@ -2540,18 +2603,37 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
 
 err:
 	dma_unmap_single(&cdev->pdev->dev, mapping, skb->len, DMA_TO_DEVICE);
-
 err2:
 	return rc;
 }
 
 static int qed_ll2_stats(struct qed_dev *cdev, struct qed_ll2_stats *stats)
 {
+	bool b_is_storage_eng1 = qed_ll2_is_storage_eng1(cdev);
+	struct qed_hwfn *p_hwfn = QED_AFFIN_HWFN(cdev);
+	int rc;
+
 	if (!cdev->ll2)
 		return -EINVAL;
 
-	return qed_ll2_get_stats(QED_LEADING_HWFN(cdev),
-				 cdev->ll2->handle, stats);
+	rc = qed_ll2_get_stats(p_hwfn, cdev->ll2->handle, stats);
+	if (rc) {
+		DP_NOTICE(p_hwfn, "Failed to get LL2 stats\n");
+		return rc;
+	}
+
+	/* In CMT mode, LL2 is always started on engine 0 for a storage PF */
+	if (b_is_storage_eng1) {
+		rc = __qed_ll2_get_stats(QED_LEADING_HWFN(cdev),
+					 cdev->ll2->handle, stats);
+		if (rc) {
+			DP_NOTICE(QED_LEADING_HWFN(cdev),
+				  "Failed to get LL2 stats on engine 0\n");
+			return rc;
+		}
+	}
+
+	return 0;
 }
 
 const struct qed_ll2_ops qed_ll2_ops_pass = {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 6adf5bda9811..829dd60ab937 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -48,6 +48,7 @@
 #include <linux/crc32.h>
 #include <linux/qed/qed_if.h>
 #include <linux/qed/qed_ll2_if.h>
+#include <net/devlink.h>
 
 #include "qed.h"
 #include "qed_sriov.h"
@@ -281,6 +282,8 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 		if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME)
 			dev_info->wol_support = true;
 
+		dev_info->smart_an = qed_mcp_is_smart_an_supported(p_hwfn);
+
 		dev_info->abs_pf_id = QED_LEADING_HWFN(cdev)->abs_pf_id;
 	} else {
 		qed_vf_get_fw_version(&cdev->hwfns[0], &dev_info->fw_major,
@@ -340,6 +343,107 @@ static int qed_set_power_state(struct qed_dev *cdev, pci_power_t state)
 	return 0;
 }
 
+struct qed_devlink {
+	struct qed_dev *cdev;
+};
+
+enum qed_devlink_param_id {
+	QED_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	QED_DEVLINK_PARAM_ID_IWARP_CMT,
+};
+
+static int qed_dl_param_get(struct devlink *dl, u32 id,
+			    struct devlink_param_gset_ctx *ctx)
+{
+	struct qed_devlink *qed_dl;
+	struct qed_dev *cdev;
+
+	qed_dl = devlink_priv(dl);
+	cdev = qed_dl->cdev;
+	ctx->val.vbool = cdev->iwarp_cmt;
+
+	return 0;
+}
+
+static int qed_dl_param_set(struct devlink *dl, u32 id,
+			    struct devlink_param_gset_ctx *ctx)
+{
+	struct qed_devlink *qed_dl;
+	struct qed_dev *cdev;
+
+	qed_dl = devlink_priv(dl);
+	cdev = qed_dl->cdev;
+	cdev->iwarp_cmt = ctx->val.vbool;
+
+	return 0;
+}
+
+static const struct devlink_param qed_devlink_params[] = {
+	DEVLINK_PARAM_DRIVER(QED_DEVLINK_PARAM_ID_IWARP_CMT,
+			     "iwarp_cmt", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     qed_dl_param_get, qed_dl_param_set, NULL),
+};
+
+static const struct devlink_ops qed_dl_ops;
+
+static int qed_devlink_register(struct qed_dev *cdev)
+{
+	union devlink_param_value value;
+	struct qed_devlink *qed_dl;
+	struct devlink *dl;
+	int rc;
+
+	dl = devlink_alloc(&qed_dl_ops, sizeof(*qed_dl));
+	if (!dl)
+		return -ENOMEM;
+
+	qed_dl = devlink_priv(dl);
+
+	cdev->dl = dl;
+	qed_dl->cdev = cdev;
+
+	rc = devlink_register(dl, &cdev->pdev->dev);
+	if (rc)
+		goto err_free;
+
+	rc = devlink_params_register(dl, qed_devlink_params,
+				     ARRAY_SIZE(qed_devlink_params));
+	if (rc)
+		goto err_unregister;
+
+	value.vbool = false;
+	devlink_param_driverinit_value_set(dl,
+					   QED_DEVLINK_PARAM_ID_IWARP_CMT,
+					   value);
+
+	devlink_params_publish(dl);
+	cdev->iwarp_cmt = false;
+
+	return 0;
+
+err_unregister:
+	devlink_unregister(dl);
+
+err_free:
+	cdev->dl = NULL;
+	devlink_free(dl);
+
+	return rc;
+}
+
+static void qed_devlink_unregister(struct qed_dev *cdev)
+{
+	if (!cdev->dl)
+		return;
+
+	devlink_params_unregister(cdev->dl, qed_devlink_params,
+				  ARRAY_SIZE(qed_devlink_params));
+
+	devlink_unregister(cdev->dl);
+	devlink_free(cdev->dl);
+}
+
 /* probing */
 static struct qed_dev *qed_probe(struct pci_dev *pdev,
 				 struct qed_probe_params *params)
@@ -359,6 +463,8 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 
 	qed_init_dp(cdev, params->dp_module, params->dp_level);
 
+	cdev->recov_in_prog = params->recov_in_prog;
+
 	rc = qed_init_pci(cdev, pdev);
 	if (rc) {
 		DP_ERR(cdev, "init pci failed\n");
@@ -366,6 +472,12 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 	}
 	DP_INFO(cdev, "PCI init completed successfully\n");
 
+	rc = qed_devlink_register(cdev);
+	if (rc) {
+		DP_INFO(cdev, "Failed to register devlink.\n");
+		goto err2;
+	}
+
 	rc = qed_hw_prepare(cdev, QED_PCI_DEFAULT);
 	if (rc) {
 		DP_ERR(cdev, "hw prepare failed\n");
@@ -395,6 +507,8 @@ static void qed_remove(struct qed_dev *cdev)
 
 	qed_set_power_state(cdev, PCI_D3hot);
 
+	qed_devlink_unregister(cdev);
+
 	qed_free_cdev(cdev);
 }
 
@@ -966,7 +1080,7 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 	}
 }
 
-#define QED_PERIODIC_DB_REC_COUNT		100
+#define QED_PERIODIC_DB_REC_COUNT		10
 #define QED_PERIODIC_DB_REC_INTERVAL_MS		100
 #define QED_PERIODIC_DB_REC_INTERVAL \
 	msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)
@@ -1297,26 +1411,21 @@ static u32 qed_sb_init(struct qed_dev *cdev,
 {
 	struct qed_hwfn *p_hwfn;
 	struct qed_ptt *p_ptt;
-	int hwfn_index;
 	u16 rel_sb_id;
-	u8 n_hwfns;
 	u32 rc;
 
-	/* RoCE uses single engine and CMT uses two engines. When using both
-	 * we force only a single engine. Storage uses only engine 0 too.
-	 */
-	if (type == QED_SB_TYPE_L2_QUEUE)
-		n_hwfns = cdev->num_hwfns;
-	else
-		n_hwfns = 1;
-
-	hwfn_index = sb_id % n_hwfns;
-	p_hwfn = &cdev->hwfns[hwfn_index];
-	rel_sb_id = sb_id / n_hwfns;
+	/* RoCE/Storage use a single engine in CMT mode while L2 uses both */
+	if (type == QED_SB_TYPE_L2_QUEUE) {
+		p_hwfn = &cdev->hwfns[sb_id % cdev->num_hwfns];
+		rel_sb_id = sb_id / cdev->num_hwfns;
+	} else {
+		p_hwfn = QED_AFFIN_HWFN(cdev);
+		rel_sb_id = sb_id;
+	}
 
 	DP_VERBOSE(cdev, NETIF_MSG_INTR,
 		   "hwfn [%d] <--[init]-- SB %04x [0x%04x upper]\n",
-		   hwfn_index, rel_sb_id, sb_id);
+		   IS_LEAD_HWFN(p_hwfn) ? 0 : 1, rel_sb_id, sb_id);
 
 	if (IS_PF(p_hwfn->cdev)) {
 		p_ptt = qed_ptt_acquire(p_hwfn);
@@ -1335,20 +1444,26 @@ static u32 qed_sb_init(struct qed_dev *cdev,
 }
 
 static u32 qed_sb_release(struct qed_dev *cdev,
-			  struct qed_sb_info *sb_info, u16 sb_id)
+			  struct qed_sb_info *sb_info,
+			  u16 sb_id,
+			  enum qed_sb_type type)
 {
 	struct qed_hwfn *p_hwfn;
-	int hwfn_index;
 	u16 rel_sb_id;
 	u32 rc;
 
-	hwfn_index = sb_id % cdev->num_hwfns;
-	p_hwfn = &cdev->hwfns[hwfn_index];
-	rel_sb_id = sb_id / cdev->num_hwfns;
+	/* RoCE/Storage use a single engine in CMT mode while L2 uses both */
+	if (type == QED_SB_TYPE_L2_QUEUE) {
+		p_hwfn = &cdev->hwfns[sb_id % cdev->num_hwfns];
+		rel_sb_id = sb_id / cdev->num_hwfns;
+	} else {
+		p_hwfn = QED_AFFIN_HWFN(cdev);
+		rel_sb_id = sb_id;
+	}
 
 	DP_VERBOSE(cdev, NETIF_MSG_INTR,
 		   "hwfn [%d] <--[init]-- SB %04x [0x%04x upper]\n",
-		   hwfn_index, rel_sb_id, sb_id);
+		   IS_LEAD_HWFN(p_hwfn) ? 0 : 1, rel_sb_id, sb_id);
 
 	rc = qed_int_sb_release(p_hwfn, sb_info, rel_sb_id);
 
@@ -2203,6 +2318,15 @@ static int qed_nvm_get_image(struct qed_dev *cdev, enum qed_nvm_images type,
 	return qed_mcp_get_nvm_image(hwfn, type, buf, len);
 }
 
+void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn)
+{
+	struct qed_common_cb_ops *ops = p_hwfn->cdev->protocol_ops.common;
+	void *cookie = p_hwfn->cdev->ops_cookie;
+
+	if (ops && ops->schedule_recovery_handler)
+		ops->schedule_recovery_handler(cookie);
+}
+
 static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
 			    void *handle)
 {
@@ -2226,6 +2350,23 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode)
 	return status;
 }
 
+static int qed_recovery_process(struct qed_dev *cdev)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt;
+	int rc = 0;
+
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EAGAIN;
+
+	rc = qed_start_recovery_process(p_hwfn, p_ptt);
+
+	qed_ptt_release(p_hwfn, p_ptt);
+
+	return rc;
+}
+
 static int qed_update_wol(struct qed_dev *cdev, bool enabled)
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
@@ -2342,6 +2483,11 @@ static int qed_read_module_eeprom(struct qed_dev *cdev, char *buf,
 	return rc;
 }
 
+static u8 qed_get_affin_hwfn_idx(struct qed_dev *cdev)
+{
+	return QED_AFFIN_HWFN_IDX(cdev);
+}
+
 static struct qed_selftest_ops qed_selftest_ops_pass = {
 	.selftest_memory = &qed_selftest_memory,
 	.selftest_interrupt = &qed_selftest_interrupt,
@@ -2380,6 +2526,8 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.nvm_get_image = &qed_nvm_get_image,
 	.set_coalesce = &qed_set_coalesce,
 	.set_led = &qed_set_led,
+	.recovery_process = &qed_recovery_process,
+	.recovery_prolog = &qed_recovery_prolog,
 	.update_drv_state = &qed_update_drv_state,
 	.update_mac = &qed_update_mac,
 	.update_mtu = &qed_update_mtu,
@@ -2387,6 +2535,7 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.db_recovery_add = &qed_db_recovery_add,
 	.db_recovery_del = &qed_db_recovery_del,
 	.read_module_eeprom = &qed_read_module_eeprom,
+	.get_affin_hwfn_idx = &qed_get_affin_hwfn_idx,
 };
 
 void qed_get_protocol_stats(struct qed_dev *cdev,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index e7f18e34ff0d..758702c1ce9c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1070,6 +1070,27 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 resp = 0, param = 0;
+	int rc;
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_LOAD_DONE, 0, &resp,
+			 &param);
+	if (rc) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to send a LOAD_DONE command, rc = %d\n", rc);
+		return rc;
+	}
+
+	/* Check if there is a DID mismatch between nvm-cfg/efuse */
+	if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
+		DP_NOTICE(p_hwfn,
+			  "warning: device configuration is not supported on this board type. The device may not function as expected.\n");
+
+	return 0;
+}
+
 int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_mcp_mb_params mb_params;
@@ -1528,6 +1549,60 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	return 0;
 }
 
+u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn,
+				 struct qed_ptt *p_ptt)
+{
+	u32 path_offsize_addr, path_offsize, path_addr, proc_kill_cnt;
+
+	if (IS_VF(p_hwfn->cdev))
+		return -EINVAL;
+
+	path_offsize_addr = SECTION_OFFSIZE_ADDR(p_hwfn->mcp_info->public_base,
+						 PUBLIC_PATH);
+	path_offsize = qed_rd(p_hwfn, p_ptt, path_offsize_addr);
+	path_addr = SECTION_ADDR(path_offsize, QED_PATH_ID(p_hwfn));
+
+	proc_kill_cnt = qed_rd(p_hwfn, p_ptt,
+			       path_addr +
+			       offsetof(struct public_path, process_kill)) &
+			PROCESS_KILL_COUNTER_MASK;
+
+	return proc_kill_cnt;
+}
+
+static void qed_mcp_handle_process_kill(struct qed_hwfn *p_hwfn,
+					struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u32 proc_kill_cnt;
+
+	/* Prevent possible attentions/interrupts during the recovery handling
+	 * and till its load phase, during which they will be re-enabled.
+	 */
+	qed_int_igu_disable_int(p_hwfn, p_ptt);
+
+	DP_NOTICE(p_hwfn, "Received a process kill indication\n");
+
+	/* The following operations should be done once, and thus in CMT mode
+	 * are carried out by only the first HW function.
+	 */
+	if (p_hwfn != QED_LEADING_HWFN(cdev))
+		return;
+
+	if (cdev->recov_in_prog) {
+		DP_NOTICE(p_hwfn,
+			  "Ignoring the indication since a recovery process is already in progress\n");
+		return;
+	}
+
+	cdev->recov_in_prog = true;
+
+	proc_kill_cnt = qed_get_process_kill_counter(p_hwfn, p_ptt);
+	DP_NOTICE(p_hwfn, "Process kill counter: %d\n", proc_kill_cnt);
+
+	qed_schedule_recovery_handler(p_hwfn);
+}
+
 static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
 					struct qed_ptt *p_ptt,
 					enum MFW_DRV_MSG_TYPE type)
@@ -1758,6 +1833,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 		case MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE:
 			qed_mcp_handle_transceiver_change(p_hwfn, p_ptt);
 			break;
+		case MFW_DRV_MSG_ERROR_RECOVERY:
+			qed_mcp_handle_process_kill(p_hwfn, p_ptt);
+			break;
 		case MFW_DRV_MSG_GET_LAN_STATS:
 		case MFW_DRV_MSG_GET_FCOE_STATS:
 		case MFW_DRV_MSG_GET_ISCSI_STATS:
@@ -2303,6 +2381,43 @@ int qed_mcp_get_flash_size(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+
+	if (cdev->recov_in_prog) {
+		DP_NOTICE(p_hwfn,
+			  "Avoid triggering a recovery since such a process is already in progress\n");
+		return -EAGAIN;
+	}
+
+	DP_NOTICE(p_hwfn, "Triggering a recovery process\n");
+	qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_GENERAL_ATTN_35, 0x1);
+
+	return 0;
+}
+
+#define QED_RECOVERY_PROLOG_SLEEP_MS    100
+
+int qed_recovery_prolog(struct qed_dev *cdev)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+	int rc;
+
+	/* Allow ongoing PCIe transactions to complete */
+	msleep(QED_RECOVERY_PROLOG_SLEEP_MS);
+
+	/* Clear the PF's internal FID_enable in the PXP */
+	rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false);
+	if (rc)
+		DP_NOTICE(p_hwfn,
+			  "qed_pglueb_set_pfid_enable() failed. rc = %d.\n",
+			  rc);
+
+	return rc;
+}
+
 static int
 qed_mcp_config_vf_msix_bb(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u8 vf_id, u8 num)
@@ -3539,6 +3654,12 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock,
 	}
 }
 
+bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn)
+{
+	return !!(p_hwfn->mcp_info->capabilities &
+		  FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ);
+}
+
 int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	u32 mcp_resp;
@@ -3564,3 +3685,68 @@ int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_FEATURE_SUPPORT,
 			   features, &mcp_resp, &mcp_param);
 }
+
+int qed_mcp_get_engine_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mcp_mb_params mb_params = {0};
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u8 fir_valid, l2_valid;
+	int rc;
+
+	mb_params.cmd = DRV_MSG_CODE_GET_ENGINE_CONFIG;
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	if (rc)
+		return rc;
+
+	if (mb_params.mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The get_engine_config command is unsupported by the MFW\n");
+		return -EOPNOTSUPP;
+	}
+
+	fir_valid = QED_MFW_GET_FIELD(mb_params.mcp_param,
+				      FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALID);
+	if (fir_valid)
+		cdev->fir_affin =
+		    QED_MFW_GET_FIELD(mb_params.mcp_param,
+				      FW_MB_PARAM_ENG_CFG_FIR_AFFIN_VALUE);
+
+	l2_valid = QED_MFW_GET_FIELD(mb_params.mcp_param,
+				     FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALID);
+	if (l2_valid)
+		cdev->l2_affin_hint =
+		    QED_MFW_GET_FIELD(mb_params.mcp_param,
+				      FW_MB_PARAM_ENG_CFG_L2_AFFIN_VALUE);
+
+	DP_INFO(p_hwfn,
+		"Engine affinity config: FIR={valid %hhd, value %hhd}, L2_hint={valid %hhd, value %hhd}\n",
+		fir_valid, cdev->fir_affin, l2_valid, cdev->l2_affin_hint);
+
+	return 0;
+}
+
+int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_mcp_mb_params mb_params = {0};
+	struct qed_dev *cdev = p_hwfn->cdev;
+	int rc;
+
+	mb_params.cmd = DRV_MSG_CODE_GET_PPFID_BITMAP;
+	rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
+	if (rc)
+		return rc;
+
+	if (mb_params.mcp_resp == FW_MSG_CODE_UNSUPPORTED) {
+		DP_INFO(p_hwfn,
+			"The get_ppfid_bitmap command is unsupported by the MFW\n");
+		return -EOPNOTSUPP;
+	}
+
+	cdev->ppfid_bitmap = QED_MFW_GET_FIELD(mb_params.mcp_param,
+					       FW_MB_PARAM_PPFID_BITMAP);
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP, "PPFID bitmap 0x%hhx\n",
+		   cdev->ppfid_bitmap);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index eddf67798d6f..e4f8fe4bd062 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -441,6 +441,38 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn,
 			 struct qed_mcp_drv_version *p_ver);
 
 /**
+ * @brief Read the MFW process kill counter
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return u32
+ */
+u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn,
+				 struct qed_ptt *p_ptt);
+
+/**
+ * @brief Trigger a recovery process
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *
+ * @return int
+ */
+int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
+ * @brief A recovery handler must call this function as its first step.
+ *        It is assumed that the handler is not run from an interrupt context.
+ *
+ *  @param cdev
+ *  @param p_ptt
+ *
+ * @return int
+ */
+int qed_recovery_prolog(struct qed_dev *cdev);
+
+/**
  * @brief Notify MFW about the change in base device properties
  *
  *  @param p_hwfn
@@ -659,10 +691,6 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 					    rel_pfid)
 #define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id)
 
-#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %			  \
-				 ((_p_hwfn)->cdev->num_ports_in_engine * \
-				  qed_device_num_engines((_p_hwfn)->cdev)))
-
 struct qed_mcp_info {
 	/* List for mailbox commands which were sent and wait for a response */
 	struct list_head			cmd_list;
@@ -801,6 +829,16 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 		     struct qed_load_req_params *p_params);
 
 /**
+ * @brief Sends a LOAD_DONE message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
  * @brief Sends a UNLOAD_REQ message to the MFW
  *
  * @param p_hwfn
@@ -1106,6 +1144,16 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock,
 				    struct qed_resc_unlock_params *p_unlock,
 				    enum qed_resc_lock
 				    resource, bool b_is_permanent);
+
+/**
+ * @brief - Return whether management firmware support smart AN
+ *
+ * @param p_hwfn
+ *
+ * @return bool - true if feature is supported.
+ */
+bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn);
+
 /**
  * @brief Learn of supported MFW features; To be done during early init
  *
@@ -1138,4 +1186,20 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
  */
 int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn);
 
+/**
+ * @brief Get the engine affinity configuration.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ */
+int qed_mcp_get_engine_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
+ * @brief Get the PPFID bitmap.
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ */
+int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index 5a90d69dc2f8..0dacf2c18c09 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -44,10 +44,12 @@
 /* Add/subtract the Adjustment_Value when making a Drift adjustment */
 #define QED_DRIFT_CNTR_DIRECTION_SHIFT		31
 #define QED_TIMESTAMP_MASK			BIT(16)
+/* Param mask for Hardware to detect/timestamp the unicast PTP packets */
+#define QED_PTP_UCAST_PARAM_MASK		0xF
 
 static enum qed_resc_lock qed_ptcdev_to_resc(struct qed_hwfn *p_hwfn)
 {
-	switch (qed_device_get_port_id(p_hwfn->cdev)) {
+	switch (MFW_PORT(p_hwfn)) {
 	case 0:
 		return QED_RESC_LOCK_PTP_PORT0;
 	case 1:
@@ -157,7 +159,8 @@ static int qed_ptp_hw_read_tx_ts(struct qed_dev *cdev, u64 *timestamp)
 	*timestamp = 0;
 	val = qed_rd(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_BUF_SEQID);
 	if (!(val & QED_TIMESTAMP_MASK)) {
-		DP_INFO(p_hwfn, "Invalid Tx timestamp, buf_seqid = %d\n", val);
+		DP_VERBOSE(p_hwfn, QED_MSG_DEBUG,
+			   "Invalid Tx timestamp, buf_seqid = %08x\n", val);
 		return -EINVAL;
 	}
 
@@ -242,7 +245,8 @@ static int qed_ptp_hw_cfg_filters(struct qed_dev *cdev,
 		return -EINVAL;
 	}
 
-	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_PARAM_MASK, 0);
+	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_PARAM_MASK,
+	       QED_PTP_UCAST_PARAM_MASK);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_LLH_PTP_RULE_MASK, rule_mask);
 	qed_wr(p_hwfn, p_ptt, NIG_REG_RX_PTP_EN, enable_cfg);
 
@@ -252,7 +256,8 @@ static int qed_ptp_hw_cfg_filters(struct qed_dev *cdev,
 		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_RULE_MASK, 0x3FFF);
 	} else {
 		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_PTP_EN, enable_cfg);
-		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_PARAM_MASK, 0);
+		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_PARAM_MASK,
+		       QED_PTP_UCAST_PARAM_MASK);
 		qed_wr(p_hwfn, p_ptt, NIG_REG_TX_LLH_PTP_RULE_MASK, rule_mask);
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 7873d6dfd91f..f900fde448db 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -700,7 +700,7 @@ static int qed_rdma_setup(struct qed_hwfn *p_hwfn,
 		return rc;
 
 	if (QED_IS_IWARP_PERSONALITY(p_hwfn)) {
-		rc = qed_iwarp_setup(p_hwfn, p_ptt, params);
+		rc = qed_iwarp_setup(p_hwfn, params);
 		if (rc)
 			return rc;
 	} else {
@@ -742,7 +742,7 @@ static int qed_rdma_stop(void *rdma_cxt)
 	       (ll2_ethertype_en & 0xFFFE));
 
 	if (QED_IS_IWARP_PERSONALITY(p_hwfn)) {
-		rc = qed_iwarp_stop(p_hwfn, p_ptt);
+		rc = qed_iwarp_stop(p_hwfn);
 		if (rc) {
 			qed_ptt_release(p_hwfn, p_ptt);
 			return rc;
@@ -803,7 +803,7 @@ static int qed_rdma_add_user(void *rdma_cxt,
 				     dpi_start_offset +
 				     ((out_params->dpi) * p_hwfn->dpi_size));
 
-	out_params->dpi_phys_addr = p_hwfn->cdev->db_phys_addr +
+	out_params->dpi_phys_addr = p_hwfn->db_phys_addr +
 				    dpi_start_offset +
 				    ((out_params->dpi) * p_hwfn->dpi_size);
 
@@ -818,14 +818,17 @@ static struct qed_rdma_port *qed_rdma_query_port(void *rdma_cxt)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct qed_rdma_port *p_port = p_hwfn->p_rdma_info->port;
+	struct qed_mcp_link_state *p_link_output;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "RDMA Query port\n");
 
-	/* Link may have changed */
-	p_port->port_state = p_hwfn->mcp_info->link_output.link_up ?
-			     QED_RDMA_PORT_UP : QED_RDMA_PORT_DOWN;
+	/* The link state is saved only for the leading hwfn */
+	p_link_output = &QED_LEADING_HWFN(p_hwfn->cdev)->mcp_info->link_output;
 
-	p_port->link_speed = p_hwfn->mcp_info->link_output.speed;
+	p_port->port_state = p_link_output->link_up ? QED_RDMA_PORT_UP
+	    : QED_RDMA_PORT_DOWN;
+
+	p_port->link_speed = p_link_output->speed;
 
 	p_port->max_msg_size = RDMA_MAX_DATA_SIZE_IN_WQE;
 
@@ -870,7 +873,7 @@ static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod)
 static int qed_fill_rdma_dev_info(struct qed_dev *cdev,
 				  struct qed_dev_rdma_info *info)
 {
-	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_hwfn *p_hwfn = QED_AFFIN_HWFN(cdev);
 
 	memset(info, 0, sizeof(*info));
 
@@ -889,9 +892,9 @@ static int qed_rdma_get_sb_start(struct qed_dev *cdev)
 	int feat_num;
 
 	if (cdev->num_hwfns > 1)
-		feat_num = FEAT_NUM(QED_LEADING_HWFN(cdev), QED_PF_L2_QUE);
+		feat_num = FEAT_NUM(QED_AFFIN_HWFN(cdev), QED_PF_L2_QUE);
 	else
-		feat_num = FEAT_NUM(QED_LEADING_HWFN(cdev), QED_PF_L2_QUE) *
+		feat_num = FEAT_NUM(QED_AFFIN_HWFN(cdev), QED_PF_L2_QUE) *
 			   cdev->num_hwfns;
 
 	return feat_num;
@@ -899,7 +902,7 @@ static int qed_rdma_get_sb_start(struct qed_dev *cdev)
 
 static int qed_rdma_get_min_cnq_msix(struct qed_dev *cdev)
 {
-	int n_cnq = FEAT_NUM(QED_LEADING_HWFN(cdev), QED_RDMA_CNQ);
+	int n_cnq = FEAT_NUM(QED_AFFIN_HWFN(cdev), QED_RDMA_CNQ);
 	int n_msix = cdev->int_params.rdma_msix_cnt;
 
 	return min_t(int, n_cnq, n_msix);
@@ -1653,7 +1656,7 @@ static int qed_rdma_deregister_tid(void *rdma_cxt, u32 itid)
 
 static void *qed_rdma_get_rdma_ctx(struct qed_dev *cdev)
 {
-	return QED_LEADING_HWFN(cdev);
+	return QED_AFFIN_HWFN(cdev);
 }
 
 static int qed_rdma_modify_srq(void *rdma_cxt,
@@ -1881,7 +1884,7 @@ err:
 static int qed_rdma_init(struct qed_dev *cdev,
 			 struct qed_rdma_start_in_params *params)
 {
-	return qed_rdma_start(QED_LEADING_HWFN(cdev), params);
+	return qed_rdma_start(QED_AFFIN_HWFN(cdev), params);
 }
 
 static void qed_rdma_remove_user(void *rdma_cxt, u16 dpi)
@@ -1899,23 +1902,12 @@ static int qed_roce_ll2_set_mac_filter(struct qed_dev *cdev,
 				       u8 *old_mac_address,
 				       u8 *new_mac_address)
 {
-	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
-	struct qed_ptt *p_ptt;
 	int rc = 0;
 
-	p_ptt = qed_ptt_acquire(p_hwfn);
-	if (!p_ptt) {
-		DP_ERR(cdev,
-		       "qed roce ll2 mac filter set: failed to acquire PTT\n");
-		return -EINVAL;
-	}
-
 	if (old_mac_address)
-		qed_llh_remove_mac_filter(p_hwfn, p_ptt, old_mac_address);
+		qed_llh_remove_mac_filter(cdev, 0, old_mac_address);
 	if (new_mac_address)
-		rc = qed_llh_add_mac_filter(p_hwfn, p_ptt, new_mac_address);
-
-	qed_ptt_release(p_hwfn, p_ptt);
+		rc = qed_llh_add_mac_filter(cdev, 0, new_mac_address);
 
 	if (rc)
 		DP_ERR(cdev,
@@ -1924,6 +1916,36 @@ static int qed_roce_ll2_set_mac_filter(struct qed_dev *cdev,
 	return rc;
 }
 
+static int qed_iwarp_set_engine_affin(struct qed_dev *cdev, bool b_reset)
+{
+	enum qed_eng eng;
+	u8 ppfid = 0;
+	int rc;
+
+	/* Make sure iwarp cmt mode is enabled before setting affinity */
+	if (!cdev->iwarp_cmt)
+		return -EINVAL;
+
+	if (b_reset)
+		eng = QED_BOTH_ENG;
+	else
+		eng = cdev->l2_affin_hint ? QED_ENG1 : QED_ENG0;
+
+	rc = qed_llh_set_ppfid_affinity(cdev, ppfid, eng);
+	if (rc) {
+		DP_NOTICE(cdev,
+			  "Failed to set the engine affinity of ppfid %d\n",
+			  ppfid);
+		return rc;
+	}
+
+	DP_VERBOSE(cdev, (QED_MSG_RDMA | QED_MSG_SP),
+		   "LLH: Set the engine affinity of non-RoCE packets as %d\n",
+		   eng);
+
+	return 0;
+}
+
 static const struct qed_rdma_ops qed_rdma_ops_pass = {
 	.common = &qed_common_ops_pass,
 	.fill_dev_info = &qed_fill_rdma_dev_info,
@@ -1963,6 +1985,7 @@ static const struct qed_rdma_ops qed_rdma_ops_pass = {
 	.ll2_set_fragment_of_tx_packet = &qed_ll2_set_fragment_of_tx_packet,
 	.ll2_set_mac_filter = &qed_roce_ll2_set_mac_filter,
 	.ll2_get_stats = &qed_ll2_get_stats,
+	.iwarp_set_engine_affin = &qed_iwarp_set_engine_affin,
 	.iwarp_connect = &qed_iwarp_connect,
 	.iwarp_create_listen = &qed_iwarp_create_listen,
 	.iwarp_destroy_listen = &qed_iwarp_destroy_listen,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index 8939ed6e08b7..60f850c3bdd6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -254,6 +254,10 @@
 	0x500840UL
 #define NIG_REG_LLH_TAGMAC_DEF_PF_VECTOR \
 	0x50196cUL
+#define NIG_REG_LLH_PPFID2PFID_TBL_0 \
+	0x501970UL
+#define NIG_REG_LLH_ENG_CLS_ROCE_QP_SEL	\
+	0x50
 #define NIG_REG_LLH_CLS_TYPE_DUALMODE \
 	0x501964UL
 #define NIG_REG_LLH_FUNC_TAG_EN 0x5019b0UL
@@ -518,6 +522,8 @@
 	0x180824UL
 #define  MISC_REG_AEU_GENERAL_ATTN_0 \
 	0x008400UL
+#define MISC_REG_AEU_GENERAL_ATTN_35 \
+	0x00848cUL
 #define  CAU_REG_SB_ADDR_MEMORY \
 	0x1c8000UL
 #define  CAU_REG_SB_VAR_MEMORY \
@@ -1624,6 +1630,8 @@
 #define PHY_PCIE_REG_PHY1_K2_E5 \
 	0x624000UL
 #define NIG_REG_ROCE_DUPLICATE_TO_HOST 0x5088f0UL
+#define NIG_REG_PPF_TO_ENGINE_SEL 0x508900UL
+#define NIG_REG_PPF_TO_ENGINE_SEL_SIZE 8
 #define PRS_REG_LIGHT_L2_ETHERTYPE_EN 0x1f0968UL
 #define NIG_REG_LLH_ENG_CLS_ENG_ID_TBL 0x501b90UL
 #define DORQ_REG_PF_DPM_ENABLE 0x100510UL
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 5a495fda9e9d..7e0b795230b2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -588,7 +588,7 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn)
 {
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
-	int rc = -EINVAL;
+	int rc;
 
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index ba64ff9bedbd..f5f3c03b9dd2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -341,9 +341,6 @@ void qed_eq_prod_update(struct qed_hwfn *p_hwfn, u16 prod)
 		   USTORM_EQE_CONS_OFFSET(p_hwfn->rel_pf_id);
 
 	REG_WR16(p_hwfn, addr, prod);
-
-	/* keep prod updates ordered */
-	mmiowb();
 }
 
 int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)
@@ -795,6 +792,17 @@ int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
 				 SPQ_HIGH_PRI_RESERVE_DEFAULT);
 }
 
+static void qed_spq_recov_set_ret_code(struct qed_spq_entry *p_ent,
+				       u8 *fw_return_code)
+{
+	if (!fw_return_code)
+		return;
+
+	if (p_ent->elem.hdr.protocol_id == PROTOCOLID_ROCE ||
+	    p_ent->elem.hdr.protocol_id == PROTOCOLID_IWARP)
+		*fw_return_code = RDMA_RETURN_OK;
+}
+
 /* Avoid overriding of SPQ entries when getting out-of-order completions, by
  * marking the completions in a bitmap and increasing the chain consumer only
  * for the first successive completed entries.
@@ -830,6 +838,17 @@ int qed_spq_post(struct qed_hwfn *p_hwfn,
 		return -EINVAL;
 	}
 
+	if (p_hwfn->cdev->recov_in_prog) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SPQ,
+			   "Recovery is in progress. Skip spq post [cmd %02x protocol %02x]\n",
+			   p_ent->elem.hdr.cmd_id, p_ent->elem.hdr.protocol_id);
+
+		/* Let the flow complete w/o any error handling */
+		qed_spq_recov_set_ret_code(p_ent, fw_return_code);
+		return 0;
+	}
+
 	/* Complete the entry */
 	rc = qed_spq_fill_entry(p_hwfn, p_ent);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 71a7af134dd8..78f77b712b10 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -917,10 +917,11 @@ static u8 qed_iov_alloc_vf_igu_sbs(struct qed_hwfn *p_hwfn,
 		/* Configure igu sb in CAU which were marked valid */
 		qed_init_cau_sb_entry(p_hwfn, &sb_entry,
 				      p_hwfn->rel_pf_id, vf->abs_vf_id, 1);
+
 		qed_dmae_host2grc(p_hwfn, p_ptt,
 				  (u64)(uintptr_t)&sb_entry,
 				  CAU_REG_SB_VAR_MEMORY +
-				  p_block->igu_sb_id * sizeof(u64), 2, 0);
+				  p_block->igu_sb_id * sizeof(u64), 2, NULL);
 	}
 
 	vf->num_sbs = (u8) num_rx_queues;
@@ -1591,7 +1592,7 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 			p_vfdev->eth_fp_hsi_minor = ETH_HSI_VER_NO_PKT_LEN_TUNN;
 		} else {
 			DP_INFO(p_hwfn,
-				"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n",
+				"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's fastpath HSI %02x.%02x\n",
 				vf->abs_vf_id,
 				req->vfdev_info.eth_fp_hsi_major,
 				req->vfdev_info.eth_fp_hsi_minor,
@@ -4449,6 +4450,13 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 	if (cdev->p_iov_info && cdev->p_iov_info->num_vfs && pci_enabled)
 		pci_disable_sriov(cdev->pdev);
 
+	if (cdev->recov_in_prog) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV,
+			   "Skip SRIOV disable operations in the device since a recovery is in progress\n");
+		goto out;
+	}
+
 	for_each_hwfn(cdev, i) {
 		struct qed_hwfn *hwfn = &cdev->hwfns[i];
 		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
@@ -4488,7 +4496,7 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 
 		qed_ptt_release(hwfn, ptt);
 	}
-
+out:
 	qed_iov_set_vfs_to_disable(cdev, false);
 
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qede/Makefile b/drivers/net/ethernet/qlogic/qede/Makefile
index 75408fbb7680..3fc91d12413f 100644
--- a/drivers/net/ethernet/qlogic/qede/Makefile
+++ b/drivers/net/ethernet/qlogic/qede/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_QEDE) := qede.o
 
 qede-y := qede_main.o qede_fp.o qede_filter.o qede_ethtool.o qede_ptp.o
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 730997b13747..0e931c04fecf 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -92,6 +92,7 @@ struct qede_stats_common {
 	u64 non_coalesced_pkts;
 	u64 coalesced_bytes;
 	u64 link_change_count;
+	u64 ptp_skip_txts;
 
 	/* port */
 	u64 rx_64_byte_packets;
@@ -162,6 +163,7 @@ struct qede_rdma_dev {
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	bool exp_recovery;
 };
 
 struct qede_ptp;
@@ -188,6 +190,7 @@ struct qede_dev {
 
 	const struct qed_eth_ops	*ops;
 	struct qede_ptp			*ptp;
+	u64				ptp_skip_txts;
 
 	struct qed_dev_eth_info dev_info;
 #define QEDE_MAX_RSS_CNT(edev)	((edev)->dev_info.num_queues)
@@ -264,6 +267,7 @@ struct qede_dev {
 enum QEDE_STATE {
 	QEDE_STATE_CLOSED,
 	QEDE_STATE_OPEN,
+	QEDE_STATE_RECOVERY,
 };
 
 #define HILO_U64(hi, lo)		((((u64)(hi)) << 32) + (lo))
@@ -462,6 +466,7 @@ struct qede_fastpath {
 #define QEDE_CSUM_UNNECESSARY		BIT(1)
 #define QEDE_TUNN_CSUM_UNNECESSARY	BIT(2)
 
+#define QEDE_SP_RECOVERY		0
 #define QEDE_SP_RX_MODE			1
 
 #ifdef CONFIG_RFS_ACCEL
@@ -495,8 +500,7 @@ struct qede_reload_args {
 /* Datapath functions definition */
 netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      struct net_device *sb_dev,
-		      select_queue_fallback_t fallback);
+		      struct net_device *sb_dev);
 netdev_features_t qede_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
@@ -547,7 +551,7 @@ int qede_txq_has_work(struct qede_tx_queue *txq);
 void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, u8 count);
 void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
 int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
-			    struct tc_cls_flower_offload *f);
+			    struct flow_cls_offload *f);
 
 #define RX_RING_SIZE_POW	13
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
index 6e7747b9b95e..e6e844a8cbc7 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_dcbnl.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* QLogic qede NIC Driver
 * Copyright (c) 2015 QLogic Corporation
-*
-* This software is available under the terms of the GNU General Public License
-* (GPL) Version 2, available from the file COPYING in the main directory of
-* this source tree.
 */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 16331c6c6fa7..e85f9fef930c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -174,6 +174,7 @@ static const struct {
 	QEDE_STAT(coalesced_bytes),
 
 	QEDE_STAT(link_change_count),
+	QEDE_STAT(ptp_skip_txts),
 };
 
 #define QEDE_NUM_STATS	ARRAY_SIZE(qede_stats_arr)
@@ -186,11 +187,13 @@ static const struct {
 
 enum {
 	QEDE_PRI_FLAG_CMT,
+	QEDE_PRI_FLAG_SMART_AN_SUPPORT, /* MFW supports SmartAN */
 	QEDE_PRI_FLAG_LEN,
 };
 
 static const char qede_private_arr[QEDE_PRI_FLAG_LEN][ETH_GSTRING_LEN] = {
 	"Coupled-Function",
+	"SmartAN capable",
 };
 
 enum qede_ethtool_tests {
@@ -404,8 +407,15 @@ static int qede_get_sset_count(struct net_device *dev, int stringset)
 static u32 qede_get_priv_flags(struct net_device *dev)
 {
 	struct qede_dev *edev = netdev_priv(dev);
+	u32 flags = 0;
 
-	return (!!(edev->dev_info.common.num_hwfns > 1)) << QEDE_PRI_FLAG_CMT;
+	if (edev->dev_info.common.num_hwfns > 1)
+		flags |= BIT(QEDE_PRI_FLAG_CMT);
+
+	if (edev->dev_info.common.smart_an)
+		flags |= BIT(QEDE_PRI_FLAG_SMART_AN_SUPPORT);
+
+	return flags;
 }
 
 struct qede_link_mode_mapping {
@@ -643,9 +653,9 @@ static void qede_get_drvinfo(struct net_device *ndev,
 {
 	char mfw[ETHTOOL_FWVERS_LEN], storm[ETHTOOL_FWVERS_LEN];
 	struct qede_dev *edev = netdev_priv(ndev);
+	char mbi[ETHTOOL_FWVERS_LEN];
 
 	strlcpy(info->driver, "qede", sizeof(info->driver));
-	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 
 	snprintf(storm, ETHTOOL_FWVERS_LEN, "%d.%d.%d.%d",
 		 edev->dev_info.common.fw_major,
@@ -659,13 +669,27 @@ static void qede_get_drvinfo(struct net_device *ndev,
 		 (edev->dev_info.common.mfw_rev >> 8) & 0xFF,
 		 edev->dev_info.common.mfw_rev & 0xFF);
 
-	if ((strlen(storm) + strlen(mfw) + strlen("mfw storm  ")) <
-	    sizeof(info->fw_version)) {
+	if ((strlen(storm) + strlen(DRV_MODULE_VERSION) + strlen("[storm]  ")) <
+	    sizeof(info->version))
+		snprintf(info->version, sizeof(info->version),
+			 "%s [storm %s]", DRV_MODULE_VERSION, storm);
+	else
+		snprintf(info->version, sizeof(info->version),
+			 "%s %s", DRV_MODULE_VERSION, storm);
+
+	if (edev->dev_info.common.mbi_version) {
+		snprintf(mbi, ETHTOOL_FWVERS_LEN, "%d.%d.%d",
+			 (edev->dev_info.common.mbi_version &
+			  QED_MBI_VERSION_2_MASK) >> QED_MBI_VERSION_2_OFFSET,
+			 (edev->dev_info.common.mbi_version &
+			  QED_MBI_VERSION_1_MASK) >> QED_MBI_VERSION_1_OFFSET,
+			 (edev->dev_info.common.mbi_version &
+			  QED_MBI_VERSION_0_MASK) >> QED_MBI_VERSION_0_OFFSET);
 		snprintf(info->fw_version, sizeof(info->fw_version),
-			 "mfw %s storm %s", mfw, storm);
+			 "mbi %s [mfw %s]", mbi, mfw);
 	} else {
 		snprintf(info->fw_version, sizeof(info->fw_version),
-			 "%s %s", mfw, storm);
+			 "mfw %s", mfw);
 	}
 
 	strlcpy(info->bus_info, pci_name(edev->pdev), sizeof(info->bus_info));
@@ -1517,14 +1541,6 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	barrier();
 	writel(txq->tx_db.raw, txq->doorbell_addr);
 
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the queue lock is released and another start_xmit is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
-
 	for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) {
 		if (qede_txq_has_work(txq))
 			break;
@@ -1654,8 +1670,11 @@ static int qede_selftest_run_loopback(struct qede_dev *edev, u32 loopback_mode)
 	/* Wait for loopback configuration to apply */
 	msleep_interruptible(500);
 
-	/* prepare the loopback packet */
-	pkt_size = edev->ndev->mtu + ETH_HLEN;
+	/* Setting max packet size to 1.5K to avoid data being split over
+	 * multiple BDs in cases where MTU > PAGE_SIZE.
+	 */
+	pkt_size = (((edev->ndev->mtu < ETH_DATA_LEN) ?
+		     edev->ndev->mtu : ETH_DATA_LEN) + ETH_HLEN);
 
 	skb = netdev_alloc_skb(edev->ndev, pkt_size);
 	if (!skb) {
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b16ce7d93caf..9a6a9a008714 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1665,198 +1665,6 @@ static int qede_set_v6_tuple_to_profile(struct qede_dev *edev,
 	return 0;
 }
 
-static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev,
-					       struct qede_arfs_tuple *t,
-					       struct ethtool_rx_flow_spec *fs)
-{
-	if ((fs->h_u.tcp_ip4_spec.ip4src &
-	     fs->m_u.tcp_ip4_spec.ip4src) != fs->h_u.tcp_ip4_spec.ip4src) {
-		DP_INFO(edev, "Don't support IP-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip4_spec.ip4dst &
-	     fs->m_u.tcp_ip4_spec.ip4dst) != fs->h_u.tcp_ip4_spec.ip4dst) {
-		DP_INFO(edev, "Don't support IP-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip4_spec.psrc &
-	     fs->m_u.tcp_ip4_spec.psrc) != fs->h_u.tcp_ip4_spec.psrc) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip4_spec.pdst &
-	     fs->m_u.tcp_ip4_spec.pdst) != fs->h_u.tcp_ip4_spec.pdst) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (fs->h_u.tcp_ip4_spec.tos) {
-		DP_INFO(edev, "Don't support tos\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->eth_proto = htons(ETH_P_IP);
-	t->src_ipv4 = fs->h_u.tcp_ip4_spec.ip4src;
-	t->dst_ipv4 = fs->h_u.tcp_ip4_spec.ip4dst;
-	t->src_port = fs->h_u.tcp_ip4_spec.psrc;
-	t->dst_port = fs->h_u.tcp_ip4_spec.pdst;
-
-	return qede_set_v4_tuple_to_profile(edev, t);
-}
-
-static int qede_flow_spec_to_tuple_tcpv4(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_TCP;
-
-	if (qede_flow_spec_to_tuple_ipv4_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple_udpv4(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_UDP;
-
-	if (qede_flow_spec_to_tuple_ipv4_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev,
-					       struct qede_arfs_tuple *t,
-					       struct ethtool_rx_flow_spec *fs)
-{
-	struct in6_addr zero_addr;
-
-	memset(&zero_addr, 0, sizeof(zero_addr));
-
-	if ((fs->h_u.tcp_ip6_spec.psrc &
-	     fs->m_u.tcp_ip6_spec.psrc) != fs->h_u.tcp_ip6_spec.psrc) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip6_spec.pdst &
-	     fs->m_u.tcp_ip6_spec.pdst) != fs->h_u.tcp_ip6_spec.pdst) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (fs->h_u.tcp_ip6_spec.tclass) {
-		DP_INFO(edev, "Don't support tclass\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->eth_proto = htons(ETH_P_IPV6);
-	memcpy(&t->src_ipv6, &fs->h_u.tcp_ip6_spec.ip6src,
-	       sizeof(struct in6_addr));
-	memcpy(&t->dst_ipv6, &fs->h_u.tcp_ip6_spec.ip6dst,
-	       sizeof(struct in6_addr));
-	t->src_port = fs->h_u.tcp_ip6_spec.psrc;
-	t->dst_port = fs->h_u.tcp_ip6_spec.pdst;
-
-	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
-}
-
-static int qede_flow_spec_to_tuple_tcpv6(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_TCP;
-
-	if (qede_flow_spec_to_tuple_ipv6_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple_udpv6(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_UDP;
-
-	if (qede_flow_spec_to_tuple_ipv6_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple(struct qede_dev *edev,
-				   struct qede_arfs_tuple *t,
-				   struct ethtool_rx_flow_spec *fs)
-{
-	memset(t, 0, sizeof(*t));
-
-	if (qede_flow_spec_validate_unused(edev, fs))
-		return -EOPNOTSUPP;
-
-	switch ((fs->flow_type & ~FLOW_EXT)) {
-	case TCP_V4_FLOW:
-		return qede_flow_spec_to_tuple_tcpv4(edev, t, fs);
-	case UDP_V4_FLOW:
-		return qede_flow_spec_to_tuple_udpv4(edev, t, fs);
-	case TCP_V6_FLOW:
-		return qede_flow_spec_to_tuple_tcpv6(edev, t, fs);
-	case UDP_V6_FLOW:
-		return qede_flow_spec_to_tuple_udpv6(edev, t, fs);
-	default:
-		DP_VERBOSE(edev, NETIF_MSG_IFUP,
-			   "Can't support flow of type %08x\n", fs->flow_type);
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static int qede_flow_spec_validate(struct qede_dev *edev,
-				   struct ethtool_rx_flow_spec *fs,
-				   struct qede_arfs_tuple *t)
-{
-	if (fs->location >= QEDE_RFS_MAX_FLTR) {
-		DP_INFO(edev, "Location out-of-bounds\n");
-		return -EINVAL;
-	}
-
-	/* Check location isn't already in use */
-	if (test_bit(fs->location, edev->arfs->arfs_fltr_bmap)) {
-		DP_INFO(edev, "Location already in use\n");
-		return -EINVAL;
-	}
-
-	/* Check if the filtering-mode could support the filter */
-	if (edev->arfs->filter_count &&
-	    edev->arfs->mode != t->mode) {
-		DP_INFO(edev,
-			"flow_spec would require filtering mode %08x, but %08x is configured\n",
-			t->mode, edev->arfs->filter_count);
-		return -EINVAL;
-	}
-
-	/* If drop requested then no need to validate other data */
-	if (fs->ring_cookie == RX_CLS_FLOW_DISC)
-		return 0;
-
-	if (ethtool_get_flow_spec_ring_vf(fs->ring_cookie))
-		return 0;
-
-	if (fs->ring_cookie >= QEDE_RSS_COUNT(edev)) {
-		DP_INFO(edev, "Queue out-of-bounds\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 /* Must be called while qede lock is held */
 static struct qede_arfs_fltr_node *
 qede_flow_find_fltr(struct qede_dev *edev, struct qede_arfs_tuple *t)
@@ -1896,72 +1704,6 @@ static void qede_flow_set_destination(struct qede_dev *edev,
 			   "Configuring N-tuple for VF 0x%02x\n", n->vfid - 1);
 }
 
-int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
-{
-	struct ethtool_rx_flow_spec *fsp = &info->fs;
-	struct qede_arfs_fltr_node *n;
-	struct qede_arfs_tuple t;
-	int min_hlen, rc;
-
-	__qede_lock(edev);
-
-	if (!edev->arfs) {
-		rc = -EPERM;
-		goto unlock;
-	}
-
-	/* Translate the flow specification into something fittign our DB */
-	rc = qede_flow_spec_to_tuple(edev, &t, fsp);
-	if (rc)
-		goto unlock;
-
-	/* Make sure location is valid and filter isn't already set */
-	rc = qede_flow_spec_validate(edev, fsp, &t);
-	if (rc)
-		goto unlock;
-
-	if (qede_flow_find_fltr(edev, &t)) {
-		rc = -EINVAL;
-		goto unlock;
-	}
-
-	n = kzalloc(sizeof(*n), GFP_KERNEL);
-	if (!n) {
-		rc = -ENOMEM;
-		goto unlock;
-	}
-
-	min_hlen = qede_flow_get_min_header_size(&t);
-	n->data = kzalloc(min_hlen, GFP_KERNEL);
-	if (!n->data) {
-		kfree(n);
-		rc = -ENOMEM;
-		goto unlock;
-	}
-
-	n->sw_id = fsp->location;
-	set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap);
-	n->buf_len = min_hlen;
-
-	memcpy(&n->tuple, &t, sizeof(n->tuple));
-
-	qede_flow_set_destination(edev, n, fsp);
-
-	/* Build a minimal header according to the flow */
-	n->tuple.build_hdr(&n->tuple, n->data);
-
-	rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0);
-	if (rc)
-		goto unlock;
-
-	qede_configure_arfs_fltr(edev, n, n->rxq_id, true);
-	rc = qede_poll_arfs_filter_config(edev, n);
-unlock:
-	__qede_unlock(edev);
-
-	return rc;
-}
-
 int qede_delete_flow_filter(struct qede_dev *edev, u64 cookie)
 {
 	struct qede_arfs_fltr_node *fltr = NULL;
@@ -2004,190 +1746,172 @@ unlock:
 }
 
 static int qede_parse_actions(struct qede_dev *edev,
-			      struct tcf_exts *exts)
+			      struct flow_action *flow_action)
 {
-	int rc = -EINVAL, num_act = 0, i;
-	const struct tc_action *a;
-	bool is_drop = false;
+	const struct flow_action_entry *act;
+	int i;
 
-	if (!tcf_exts_has_actions(exts)) {
-		DP_NOTICE(edev, "No tc actions received\n");
-		return rc;
+	if (!flow_action_has_entries(flow_action)) {
+		DP_NOTICE(edev, "No actions received\n");
+		return -EINVAL;
 	}
 
-	tcf_exts_for_each_action(i, a, exts) {
-		num_act++;
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
+			break;
+		case FLOW_ACTION_QUEUE:
+			if (act->queue.vf)
+				break;
 
-		if (is_tcf_gact_shot(a))
-			is_drop = true;
+			if (act->queue.index >= QEDE_RSS_COUNT(edev)) {
+				DP_INFO(edev, "Queue out-of-bounds\n");
+				return -EINVAL;
+			}
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
 
-	if (num_act == 1 && is_drop)
-		return 0;
-
-	return rc;
+	return 0;
 }
 
 static int
-qede_tc_parse_ports(struct qede_dev *edev,
-		    struct tc_cls_flower_offload *f,
-		    struct qede_arfs_tuple *t)
-{
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_PORTS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_PORTS,
-						 f->mask);
-
-		if ((key->src && mask->src != U16_MAX) ||
-		    (key->dst && mask->dst != U16_MAX)) {
+qede_flow_parse_ports(struct qede_dev *edev, struct flow_rule *rule,
+		      struct qede_arfs_tuple *t)
+{
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(rule, &match);
+		if ((match.key->src && match.mask->src != U16_MAX) ||
+		    (match.key->dst && match.mask->dst != U16_MAX)) {
 			DP_NOTICE(edev, "Do not support ports masks\n");
 			return -EINVAL;
 		}
 
-		t->src_port = key->src;
-		t->dst_port = key->dst;
+		t->src_port = match.key->src;
+		t->dst_port = match.key->dst;
 	}
 
 	return 0;
 }
 
 static int
-qede_tc_parse_v6_common(struct qede_dev *edev,
-			struct tc_cls_flower_offload *f,
-			struct qede_arfs_tuple *t)
+qede_flow_parse_v6_common(struct qede_dev *edev, struct flow_rule *rule,
+			  struct qede_arfs_tuple *t)
 {
 	struct in6_addr zero_addr, addr;
 
 	memset(&zero_addr, 0, sizeof(addr));
 	memset(&addr, 0xff, sizeof(addr));
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
-		struct flow_dissector_key_ipv6_addrs *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match;
 
-		if ((memcmp(&key->src, &zero_addr, sizeof(addr)) &&
-		     memcmp(&mask->src, &addr, sizeof(addr))) ||
-		    (memcmp(&key->dst, &zero_addr, sizeof(addr)) &&
-		     memcmp(&mask->dst, &addr, sizeof(addr)))) {
+		flow_rule_match_ipv6_addrs(rule, &match);
+		if ((memcmp(&match.key->src, &zero_addr, sizeof(addr)) &&
+		     memcmp(&match.mask->src, &addr, sizeof(addr))) ||
+		    (memcmp(&match.key->dst, &zero_addr, sizeof(addr)) &&
+		     memcmp(&match.mask->dst, &addr, sizeof(addr)))) {
 			DP_NOTICE(edev,
 				  "Do not support IPv6 address prefix/mask\n");
 			return -EINVAL;
 		}
 
-		memcpy(&t->src_ipv6, &key->src, sizeof(addr));
-		memcpy(&t->dst_ipv6, &key->dst, sizeof(addr));
+		memcpy(&t->src_ipv6, &match.key->src, sizeof(addr));
+		memcpy(&t->dst_ipv6, &match.key->dst, sizeof(addr));
 	}
 
-	if (qede_tc_parse_ports(edev, f, t))
+	if (qede_flow_parse_ports(edev, rule, t))
 		return -EINVAL;
 
 	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
 }
 
 static int
-qede_tc_parse_v4_common(struct qede_dev *edev,
-			struct tc_cls_flower_offload *f,
+qede_flow_parse_v4_common(struct qede_dev *edev, struct flow_rule *rule,
 			struct qede_arfs_tuple *t)
 {
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-		struct flow_dissector_key_ipv4_addrs *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
 
-		if ((key->src && mask->src != U32_MAX) ||
-		    (key->dst && mask->dst != U32_MAX)) {
+		flow_rule_match_ipv4_addrs(rule, &match);
+		if ((match.key->src && match.mask->src != U32_MAX) ||
+		    (match.key->dst && match.mask->dst != U32_MAX)) {
 			DP_NOTICE(edev, "Do not support ipv4 prefix/masks\n");
 			return -EINVAL;
 		}
 
-		t->src_ipv4 = key->src;
-		t->dst_ipv4 = key->dst;
+		t->src_ipv4 = match.key->src;
+		t->dst_ipv4 = match.key->dst;
 	}
 
-	if (qede_tc_parse_ports(edev, f, t))
+	if (qede_flow_parse_ports(edev, rule, t))
 		return -EINVAL;
 
 	return qede_set_v4_tuple_to_profile(edev, t);
 }
 
 static int
-qede_tc_parse_tcp_v6(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_tcp_v6(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_TCP;
 	tuple->eth_proto = htons(ETH_P_IPV6);
 
-	return qede_tc_parse_v6_common(edev, f, tuple);
+	return qede_flow_parse_v6_common(edev, rule, tuple);
 }
 
 static int
-qede_tc_parse_tcp_v4(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_tcp_v4(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_TCP;
 	tuple->eth_proto = htons(ETH_P_IP);
 
-	return qede_tc_parse_v4_common(edev, f, tuple);
+	return qede_flow_parse_v4_common(edev, rule, tuple);
 }
 
 static int
-qede_tc_parse_udp_v6(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_udp_v6(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_UDP;
 	tuple->eth_proto = htons(ETH_P_IPV6);
 
-	return qede_tc_parse_v6_common(edev, f, tuple);
+	return qede_flow_parse_v6_common(edev, rule, tuple);
 }
 
 static int
-qede_tc_parse_udp_v4(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_udp_v4(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_UDP;
 	tuple->eth_proto = htons(ETH_P_IP);
 
-	return qede_tc_parse_v4_common(edev, f, tuple);
+	return qede_flow_parse_v4_common(edev, rule, tuple);
 }
 
 static int
-qede_parse_flower_attr(struct qede_dev *edev, __be16 proto,
-		       struct tc_cls_flower_offload *f,
-		       struct qede_arfs_tuple *tuple)
+qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
+		     struct flow_rule *rule, struct qede_arfs_tuple *tuple)
 {
+	struct flow_dissector *dissector = rule->match.dissector;
 	int rc = -EINVAL;
 	u8 ip_proto = 0;
 
 	memset(tuple, 0, sizeof(*tuple));
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
 		DP_NOTICE(edev, "Unsupported key set:0x%x\n",
-			  f->dissector->used_keys);
+			  dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
@@ -2197,31 +1921,29 @@ qede_parse_flower_attr(struct qede_dev *edev, __be16 proto,
 		return -EPROTONOSUPPORT;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_BASIC,
-						f->key);
-		ip_proto = key->ip_proto;
+		flow_rule_match_basic(rule, &match);
+		ip_proto = match.key->ip_proto;
 	}
 
 	if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IP))
-		rc = qede_tc_parse_tcp_v4(edev, f, tuple);
+		rc = qede_flow_parse_tcp_v4(edev, rule, tuple);
 	else if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IPV6))
-		rc = qede_tc_parse_tcp_v6(edev, f, tuple);
+		rc = qede_flow_parse_tcp_v6(edev, rule, tuple);
 	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IP))
-		rc = qede_tc_parse_udp_v4(edev, f, tuple);
+		rc = qede_flow_parse_udp_v4(edev, rule, tuple);
 	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IPV6))
-		rc = qede_tc_parse_udp_v6(edev, f, tuple);
+		rc = qede_flow_parse_udp_v6(edev, rule, tuple);
 	else
-		DP_NOTICE(edev, "Invalid tc protocol request\n");
+		DP_NOTICE(edev, "Invalid protocol request\n");
 
 	return rc;
 }
 
 int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
-			    struct tc_cls_flower_offload *f)
+			    struct flow_cls_offload *f)
 {
 	struct qede_arfs_fltr_node *n;
 	int min_hlen, rc = -EINVAL;
@@ -2235,7 +1957,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 	}
 
 	/* parse flower attribute and prepare filter */
-	if (qede_parse_flower_attr(edev, proto, f, &t))
+	if (qede_parse_flow_attr(edev, proto, f->rule, &t))
 		goto unlock;
 
 	/* Validate profile mode and number of filters */
@@ -2248,7 +1970,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 	}
 
 	/* parse tc actions and get the vf_id */
-	if (qede_parse_actions(edev, f->exts))
+	if (qede_parse_actions(edev, &f->rule->action))
 		goto unlock;
 
 	if (qede_flow_find_fltr(edev, &t)) {
@@ -2290,3 +2012,141 @@ unlock:
 	__qede_unlock(edev);
 	return rc;
 }
+
+static int qede_flow_spec_validate(struct qede_dev *edev,
+				   struct flow_action *flow_action,
+				   struct qede_arfs_tuple *t,
+				   __u32 location)
+{
+	if (location >= QEDE_RFS_MAX_FLTR) {
+		DP_INFO(edev, "Location out-of-bounds\n");
+		return -EINVAL;
+	}
+
+	/* Check location isn't already in use */
+	if (test_bit(location, edev->arfs->arfs_fltr_bmap)) {
+		DP_INFO(edev, "Location already in use\n");
+		return -EINVAL;
+	}
+
+	/* Check if the filtering-mode could support the filter */
+	if (edev->arfs->filter_count &&
+	    edev->arfs->mode != t->mode) {
+		DP_INFO(edev,
+			"flow_spec would require filtering mode %08x, but %08x is configured\n",
+			t->mode, edev->arfs->filter_count);
+		return -EINVAL;
+	}
+
+	if (qede_parse_actions(edev, flow_action))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int qede_flow_spec_to_rule(struct qede_dev *edev,
+				  struct qede_arfs_tuple *t,
+				  struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_rx_flow_spec_input input = {};
+	struct ethtool_rx_flow_rule *flow;
+	__be16 proto;
+	int err = 0;
+
+	if (qede_flow_spec_validate_unused(edev, fs))
+		return -EOPNOTSUPP;
+
+	switch ((fs->flow_type & ~FLOW_EXT)) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		proto = htons(ETH_P_IP);
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		proto = htons(ETH_P_IPV6);
+		break;
+	default:
+		DP_VERBOSE(edev, NETIF_MSG_IFUP,
+			   "Can't support flow of type %08x\n", fs->flow_type);
+		return -EOPNOTSUPP;
+	}
+
+	input.fs = fs;
+	flow = ethtool_rx_flow_rule_create(&input);
+	if (IS_ERR(flow))
+		return PTR_ERR(flow);
+
+	if (qede_parse_flow_attr(edev, proto, flow->rule, t)) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	/* Make sure location is valid and filter isn't already set */
+	err = qede_flow_spec_validate(edev, &flow->rule->action, t,
+				      fs->location);
+err_out:
+	ethtool_rx_flow_rule_destroy(flow);
+	return err;
+
+}
+
+int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
+{
+	struct ethtool_rx_flow_spec *fsp = &info->fs;
+	struct qede_arfs_fltr_node *n;
+	struct qede_arfs_tuple t;
+	int min_hlen, rc;
+
+	__qede_lock(edev);
+
+	if (!edev->arfs) {
+		rc = -EPERM;
+		goto unlock;
+	}
+
+	/* Translate the flow specification into something fittign our DB */
+	rc = qede_flow_spec_to_rule(edev, &t, fsp);
+	if (rc)
+		goto unlock;
+
+	if (qede_flow_find_fltr(edev, &t)) {
+		rc = -EINVAL;
+		goto unlock;
+	}
+
+	n = kzalloc(sizeof(*n), GFP_KERNEL);
+	if (!n) {
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	min_hlen = qede_flow_get_min_header_size(&t);
+	n->data = kzalloc(min_hlen, GFP_KERNEL);
+	if (!n->data) {
+		kfree(n);
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	n->sw_id = fsp->location;
+	set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap);
+	n->buf_len = min_hlen;
+
+	memcpy(&n->tuple, &t, sizeof(n->tuple));
+
+	qede_flow_set_destination(edev, n, fsp);
+
+	/* Build a minimal header according to the flow */
+	n->tuple.build_hdr(&n->tuple, n->data);
+
+	rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0);
+	if (rc)
+		goto unlock;
+
+	qede_configure_arfs_fltr(edev, n, n->rxq_id, true);
+	rc = qede_poll_arfs_filter_config(edev, n);
+unlock:
+	__qede_unlock(edev);
+
+	return rc;
+}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 31b046e24565..0ae28f0d2523 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -580,14 +580,6 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq)
 
 	internal_ram_wr(rxq->hw_rxq_prod_addr, sizeof(rx_prods),
 			(u32 *)&rx_prods);
-
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the napi lock is released and another qede_poll is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
 }
 
 static void qede_get_rxhash(struct sk_buff *skb, u8 bitfields, __le32 rss_hash)
@@ -1665,12 +1657,12 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	txq->tx_db.data.bd_prod =
 		cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl));
 
-	if (!skb->xmit_more || netif_xmit_stopped(netdev_txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(netdev_txq))
 		qede_update_tx_producer(txq);
 
 	if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl)
 		      < (MAX_SKB_FRAGS + 1))) {
-		if (skb->xmit_more)
+		if (netdev_xmit_more())
 			qede_update_tx_producer(txq);
 
 		netif_tx_stop_queue(netdev_txq);
@@ -1696,8 +1688,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 }
 
 u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      struct net_device *sb_dev,
-		      select_queue_fallback_t fallback)
+		      struct net_device *sb_dev)
 {
 	struct qede_dev *edev = netdev_priv(dev);
 	int total_txq;
@@ -1705,7 +1696,7 @@ u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
 	total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc;
 
 	return QEDE_TSS_COUNT(edev) ?
-		fallback(dev, skb, NULL) % total_txq :  0;
+		netdev_pick_tx(dev, skb, NULL) % total_txq :  0;
 }
 
 /* 8B udp header + 8B base tunnel header + 32B option length */
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 9790f26d17c4..8d1c208f778f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -133,23 +133,12 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id);
 static void qede_remove(struct pci_dev *pdev);
 static void qede_shutdown(struct pci_dev *pdev);
 static void qede_link_update(void *dev, struct qed_link_output *link);
+static void qede_schedule_recovery_handler(void *dev);
+static void qede_recovery_handler(struct qede_dev *edev);
 static void qede_get_eth_tlv_data(void *edev, void *data);
 static void qede_get_generic_tlv_data(void *edev,
 				      struct qed_generic_tlvs *data);
 
-/* The qede lock is used to protect driver state change and driver flows that
- * are not reentrant.
- */
-void __qede_lock(struct qede_dev *edev)
-{
-	mutex_lock(&edev->qede_lock);
-}
-
-void __qede_unlock(struct qede_dev *edev)
-{
-	mutex_unlock(&edev->qede_lock);
-}
-
 #ifdef CONFIG_QED_SRIOV
 static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos,
 			    __be16 vlan_proto)
@@ -231,6 +220,7 @@ static struct qed_eth_cb_ops qede_ll_ops = {
 		.arfs_filter_op = qede_arfs_filter_op,
 #endif
 		.link_update = qede_link_update,
+		.schedule_recovery_handler = qede_schedule_recovery_handler,
 		.get_generic_tlv_data = qede_get_generic_tlv_data,
 		.get_protocol_tlv_data = qede_get_eth_tlv_data,
 	},
@@ -400,6 +390,7 @@ void qede_fill_by_demand_stats(struct qede_dev *edev)
 	p_common->brb_discards = stats.common.brb_discards;
 	p_common->tx_mac_ctrl_frames = stats.common.tx_mac_ctrl_frames;
 	p_common->link_change_count = stats.common.link_change_count;
+	p_common->ptp_skip_txts = edev->ptp_skip_txts;
 
 	if (QEDE_IS_BB(edev)) {
 		struct qede_stats_bb *p_bb = &edev->stats.bb;
@@ -557,13 +548,13 @@ static int qede_setup_tc(struct net_device *ndev, u8 num_tc)
 }
 
 static int
-qede_set_flower(struct qede_dev *edev, struct tc_cls_flower_offload *f,
+qede_set_flower(struct qede_dev *edev, struct flow_cls_offload *f,
 		__be16 proto)
 {
 	switch (f->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return qede_add_tc_flower_fltr(edev, proto, f);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return qede_delete_flow_filter(edev, f->cookie);
 	default:
 		return -EOPNOTSUPP;
@@ -573,7 +564,7 @@ qede_set_flower(struct qede_dev *edev, struct tc_cls_flower_offload *f,
 static int qede_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 				  void *cb_priv)
 {
-	struct tc_cls_flower_offload *f;
+	struct flow_cls_offload *f;
 	struct qede_dev *edev = cb_priv;
 
 	if (!tc_cls_can_offload_and_chain0(edev->ndev, type_data))
@@ -588,24 +579,7 @@ static int qede_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int qede_setup_tc_block(struct qede_dev *edev,
-			       struct tc_block_offload *f)
-{
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     qede_setup_tc_block_cb,
-					     edev, edev, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, qede_setup_tc_block_cb, edev);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(qede_block_cb_list);
 
 static int
 qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
@@ -616,7 +590,10 @@ qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return qede_setup_tc_block(edev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &qede_block_cb_list,
+						  qede_setup_tc_block_cb,
+						  edev, edev, true);
 	case TC_SETUP_QDISC_MQPRIO:
 		mqprio = type_data;
 
@@ -953,11 +930,57 @@ err:
 	return -ENOMEM;
 }
 
+/* The qede lock is used to protect driver state change and driver flows that
+ * are not reentrant.
+ */
+void __qede_lock(struct qede_dev *edev)
+{
+	mutex_lock(&edev->qede_lock);
+}
+
+void __qede_unlock(struct qede_dev *edev)
+{
+	mutex_unlock(&edev->qede_lock);
+}
+
+/* This version of the lock should be used when acquiring the RTNL lock is also
+ * needed in addition to the internal qede lock.
+ */
+static void qede_lock(struct qede_dev *edev)
+{
+	rtnl_lock();
+	__qede_lock(edev);
+}
+
+static void qede_unlock(struct qede_dev *edev)
+{
+	__qede_unlock(edev);
+	rtnl_unlock();
+}
+
 static void qede_sp_task(struct work_struct *work)
 {
 	struct qede_dev *edev = container_of(work, struct qede_dev,
 					     sp_task.work);
 
+	/* The locking scheme depends on the specific flag:
+	 * In case of QEDE_SP_RECOVERY, acquiring the RTNL lock is required to
+	 * ensure that ongoing flows are ended and new ones are not started.
+	 * In other cases - only the internal qede lock should be acquired.
+	 */
+
+	if (test_and_clear_bit(QEDE_SP_RECOVERY, &edev->sp_flags)) {
+#ifdef CONFIG_QED_SRIOV
+		/* SRIOV must be disabled outside the lock to avoid a deadlock.
+		 * The recovery of the active VFs is currently not supported.
+		 */
+		qede_sriov_configure(edev->pdev, 0);
+#endif
+		qede_lock(edev);
+		qede_recovery_handler(edev);
+		qede_unlock(edev);
+	}
+
 	__qede_lock(edev);
 
 	if (test_and_clear_bit(QEDE_SP_RX_MODE, &edev->sp_flags))
@@ -1034,6 +1057,7 @@ static void qede_log_probe(struct qede_dev *edev)
 
 enum qede_probe_mode {
 	QEDE_PROBE_NORMAL,
+	QEDE_PROBE_RECOVERY,
 };
 
 static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
@@ -1054,6 +1078,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	probe_params.dp_module = dp_module;
 	probe_params.dp_level = dp_level;
 	probe_params.is_vf = is_vf;
+	probe_params.recov_in_prog = (mode == QEDE_PROBE_RECOVERY);
 	cdev = qed_ops->common->probe(pdev, &probe_params);
 	if (!cdev) {
 		rc = -ENODEV;
@@ -1081,11 +1106,20 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	if (rc)
 		goto err2;
 
-	edev = qede_alloc_etherdev(cdev, pdev, &dev_info, dp_module,
-				   dp_level);
-	if (!edev) {
-		rc = -ENOMEM;
-		goto err2;
+	if (mode != QEDE_PROBE_RECOVERY) {
+		edev = qede_alloc_etherdev(cdev, pdev, &dev_info, dp_module,
+					   dp_level);
+		if (!edev) {
+			rc = -ENOMEM;
+			goto err2;
+		}
+	} else {
+		struct net_device *ndev = pci_get_drvdata(pdev);
+
+		edev = netdev_priv(ndev);
+		edev->cdev = cdev;
+		memset(&edev->stats, 0, sizeof(edev->stats));
+		memcpy(&edev->dev_info, &dev_info, sizeof(dev_info));
 	}
 
 	if (is_vf)
@@ -1093,28 +1127,31 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 
 	qede_init_ndev(edev);
 
-	rc = qede_rdma_dev_add(edev);
+	rc = qede_rdma_dev_add(edev, (mode == QEDE_PROBE_RECOVERY));
 	if (rc)
 		goto err3;
 
-	/* Prepare the lock prior to the registration of the netdev,
-	 * as once it's registered we might reach flows requiring it
-	 * [it's even possible to reach a flow needing it directly
-	 * from there, although it's unlikely].
-	 */
-	INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
-	mutex_init(&edev->qede_lock);
-	rc = register_netdev(edev->ndev);
-	if (rc) {
-		DP_NOTICE(edev, "Cannot register net-device\n");
-		goto err4;
+	if (mode != QEDE_PROBE_RECOVERY) {
+		/* Prepare the lock prior to the registration of the netdev,
+		 * as once it's registered we might reach flows requiring it
+		 * [it's even possible to reach a flow needing it directly
+		 * from there, although it's unlikely].
+		 */
+		INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
+		mutex_init(&edev->qede_lock);
+
+		rc = register_netdev(edev->ndev);
+		if (rc) {
+			DP_NOTICE(edev, "Cannot register net-device\n");
+			goto err4;
+		}
 	}
 
 	edev->ops->common->set_name(cdev, edev->ndev->name);
 
 	/* PTP not supported on VFs */
 	if (!is_vf)
-		qede_ptp_enable(edev, true);
+		qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL));
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
@@ -1129,7 +1166,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	return 0;
 
 err4:
-	qede_rdma_dev_remove(edev);
+	qede_rdma_dev_remove(edev, (mode == QEDE_PROBE_RECOVERY));
 err3:
 	free_netdev(edev->ndev);
 err2:
@@ -1165,6 +1202,7 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 enum qede_remove_mode {
 	QEDE_REMOVE_NORMAL,
+	QEDE_REMOVE_RECOVERY,
 };
 
 static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
@@ -1175,15 +1213,19 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
-	qede_rdma_dev_remove(edev);
-	unregister_netdev(ndev);
-	cancel_delayed_work_sync(&edev->sp_task);
+	qede_rdma_dev_remove(edev, (mode == QEDE_REMOVE_RECOVERY));
 
-	qede_ptp_disable(edev);
+	if (mode != QEDE_REMOVE_RECOVERY) {
+		unregister_netdev(ndev);
+
+		cancel_delayed_work_sync(&edev->sp_task);
+
+		edev->ops->common->set_power_state(cdev, PCI_D0);
 
-	edev->ops->common->set_power_state(cdev, PCI_D0);
+		pci_set_drvdata(pdev, NULL);
+	}
 
-	pci_set_drvdata(pdev, NULL);
+	qede_ptp_disable(edev);
 
 	/* Use global ops since we've freed edev */
 	qed_ops->common->slowpath_stop(cdev);
@@ -1197,7 +1239,8 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 	 * [e.g., QED register callbacks] won't break anything when
 	 * accessing the netdevice.
 	 */
-	 free_netdev(ndev);
+	if (mode != QEDE_REMOVE_RECOVERY)
+		free_netdev(ndev);
 
 	dev_info(&pdev->dev, "Ending qede_remove successfully\n");
 }
@@ -1250,7 +1293,8 @@ static void qede_free_mem_sb(struct qede_dev *edev, struct qed_sb_info *sb_info,
 			     u16 sb_id)
 {
 	if (sb_info->sb_virt) {
-		edev->ops->common->sb_release(edev->cdev, sb_info, sb_id);
+		edev->ops->common->sb_release(edev->cdev, sb_info, sb_id,
+					      QED_SB_TYPE_L2_QUEUE);
 		dma_free_coherent(&edev->pdev->dev, sizeof(*sb_info->sb_virt),
 				  (void *)sb_info->sb_virt, sb_info->sb_phys);
 		memset(sb_info, 0, sizeof(*sb_info));
@@ -1542,6 +1586,58 @@ static int qede_alloc_mem_load(struct qede_dev *edev)
 	return 0;
 }
 
+static void qede_empty_tx_queue(struct qede_dev *edev,
+				struct qede_tx_queue *txq)
+{
+	unsigned int pkts_compl = 0, bytes_compl = 0;
+	struct netdev_queue *netdev_txq;
+	int rc, len = 0;
+
+	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id);
+
+	while (qed_chain_get_cons_idx(&txq->tx_pbl) !=
+	       qed_chain_get_prod_idx(&txq->tx_pbl)) {
+		DP_VERBOSE(edev, NETIF_MSG_IFDOWN,
+			   "Freeing a packet on tx queue[%d]: chain_cons 0x%x, chain_prod 0x%x\n",
+			   txq->index, qed_chain_get_cons_idx(&txq->tx_pbl),
+			   qed_chain_get_prod_idx(&txq->tx_pbl));
+
+		rc = qede_free_tx_pkt(edev, txq, &len);
+		if (rc) {
+			DP_NOTICE(edev,
+				  "Failed to free a packet on tx queue[%d]: chain_cons 0x%x, chain_prod 0x%x\n",
+				  txq->index,
+				  qed_chain_get_cons_idx(&txq->tx_pbl),
+				  qed_chain_get_prod_idx(&txq->tx_pbl));
+			break;
+		}
+
+		bytes_compl += len;
+		pkts_compl++;
+		txq->sw_tx_cons++;
+	}
+
+	netdev_tx_completed_queue(netdev_txq, pkts_compl, bytes_compl);
+}
+
+static void qede_empty_tx_queues(struct qede_dev *edev)
+{
+	int i;
+
+	for_each_queue(i)
+		if (edev->fp_array[i].type & QEDE_FASTPATH_TX) {
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				struct qede_fastpath *fp;
+
+				fp = &edev->fp_array[i];
+				qede_empty_tx_queue(edev,
+						    &fp->txq[cos]);
+			}
+		}
+}
+
 /* This function inits fp content and resets the SB, RXQ and TXQ structures */
 static void qede_init_fp(struct qede_dev *edev)
 {
@@ -2056,6 +2152,7 @@ out:
 
 enum qede_unload_mode {
 	QEDE_UNLOAD_NORMAL,
+	QEDE_UNLOAD_RECOVERY,
 };
 
 static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
@@ -2071,7 +2168,8 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 
 	clear_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags);
 
-	edev->state = QEDE_STATE_CLOSED;
+	if (mode != QEDE_UNLOAD_RECOVERY)
+		edev->state = QEDE_STATE_CLOSED;
 
 	qede_rdma_dev_event_close(edev);
 
@@ -2079,17 +2177,20 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 	netif_tx_disable(edev->ndev);
 	netif_carrier_off(edev->ndev);
 
-	/* Reset the link */
-	memset(&link_params, 0, sizeof(link_params));
-	link_params.link_up = false;
-	edev->ops->common->set_link(edev->cdev, &link_params);
-	rc = qede_stop_queues(edev);
-	if (rc) {
-		qede_sync_free_irqs(edev);
-		goto out;
-	}
+	if (mode != QEDE_UNLOAD_RECOVERY) {
+		/* Reset the link */
+		memset(&link_params, 0, sizeof(link_params));
+		link_params.link_up = false;
+		edev->ops->common->set_link(edev->cdev, &link_params);
+
+		rc = qede_stop_queues(edev);
+		if (rc) {
+			qede_sync_free_irqs(edev);
+			goto out;
+		}
 
-	DP_INFO(edev, "Stopped Queues\n");
+		DP_INFO(edev, "Stopped Queues\n");
+	}
 
 	qede_vlan_mark_nonconfigured(edev);
 	edev->ops->fastpath_stop(edev->cdev);
@@ -2105,18 +2206,28 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 
 	qede_napi_disable_remove(edev);
 
+	if (mode == QEDE_UNLOAD_RECOVERY)
+		qede_empty_tx_queues(edev);
+
 	qede_free_mem_load(edev);
 	qede_free_fp_array(edev);
 
 out:
 	if (!is_locked)
 		__qede_unlock(edev);
+
+	if (mode != QEDE_UNLOAD_RECOVERY)
+		DP_NOTICE(edev, "Link is down\n");
+
+	edev->ptp_skip_txts = 0;
+
 	DP_INFO(edev, "Ending qede unload\n");
 }
 
 enum qede_load_mode {
 	QEDE_LOAD_NORMAL,
 	QEDE_LOAD_RELOAD,
+	QEDE_LOAD_RECOVERY,
 };
 
 static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
@@ -2296,6 +2407,77 @@ static void qede_link_update(void *dev, struct qed_link_output *link)
 	}
 }
 
+static void qede_schedule_recovery_handler(void *dev)
+{
+	struct qede_dev *edev = dev;
+
+	if (edev->state == QEDE_STATE_RECOVERY) {
+		DP_NOTICE(edev,
+			  "Avoid scheduling a recovery handling since already in recovery state\n");
+		return;
+	}
+
+	set_bit(QEDE_SP_RECOVERY, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+
+	DP_INFO(edev, "Scheduled a recovery handler\n");
+}
+
+static void qede_recovery_failed(struct qede_dev *edev)
+{
+	netdev_err(edev->ndev, "Recovery handling has failed. Power cycle is needed.\n");
+
+	netif_device_detach(edev->ndev);
+
+	if (edev->cdev)
+		edev->ops->common->set_power_state(edev->cdev, PCI_D3hot);
+}
+
+static void qede_recovery_handler(struct qede_dev *edev)
+{
+	u32 curr_state = edev->state;
+	int rc;
+
+	DP_NOTICE(edev, "Starting a recovery process\n");
+
+	/* No need to acquire first the qede_lock since is done by qede_sp_task
+	 * before calling this function.
+	 */
+	edev->state = QEDE_STATE_RECOVERY;
+
+	edev->ops->common->recovery_prolog(edev->cdev);
+
+	if (curr_state == QEDE_STATE_OPEN)
+		qede_unload(edev, QEDE_UNLOAD_RECOVERY, true);
+
+	__qede_remove(edev->pdev, QEDE_REMOVE_RECOVERY);
+
+	rc = __qede_probe(edev->pdev, edev->dp_module, edev->dp_level,
+			  IS_VF(edev), QEDE_PROBE_RECOVERY);
+	if (rc) {
+		edev->cdev = NULL;
+		goto err;
+	}
+
+	if (curr_state == QEDE_STATE_OPEN) {
+		rc = qede_load(edev, QEDE_LOAD_RECOVERY, true);
+		if (rc)
+			goto err;
+
+		qede_config_rx_mode(edev->ndev);
+		udp_tunnel_get_rx_info(edev->ndev);
+	}
+
+	edev->state = curr_state;
+
+	DP_NOTICE(edev, "Recovery handling is done\n");
+
+	return;
+
+err:
+	qede_recovery_failed(edev);
+}
+
 static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
 	struct netdev_queue *netdev_txq;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 5f3f42a25361..f815435cf106 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 #include "qede_ptp.h"
+#define QEDE_PTP_TX_TIMEOUT (2 * HZ)
 
 struct qede_ptp {
 	const struct qed_eth_ptp_ops	*ops;
@@ -38,6 +39,7 @@ struct qede_ptp {
 	struct timecounter		tc;
 	struct ptp_clock		*clock;
 	struct work_struct		work;
+	unsigned long			ptp_tx_start;
 	struct qede_dev			*edev;
 	struct sk_buff			*tx_skb;
 
@@ -160,18 +162,30 @@ static void qede_ptp_task(struct work_struct *work)
 	struct qede_dev *edev;
 	struct qede_ptp *ptp;
 	u64 timestamp, ns;
+	bool timedout;
 	int rc;
 
 	ptp = container_of(work, struct qede_ptp, work);
 	edev = ptp->edev;
+	timedout = time_is_before_jiffies(ptp->ptp_tx_start +
+					  QEDE_PTP_TX_TIMEOUT);
 
 	/* Read Tx timestamp registers */
 	spin_lock_bh(&ptp->lock);
 	rc = ptp->ops->read_tx_ts(edev->cdev, &timestamp);
 	spin_unlock_bh(&ptp->lock);
 	if (rc) {
-		/* Reschedule to keep checking for a valid timestamp value */
-		schedule_work(&ptp->work);
+		if (unlikely(timedout)) {
+			DP_INFO(edev, "Tx timestamp is not recorded\n");
+			dev_kfree_skb_any(ptp->tx_skb);
+			ptp->tx_skb = NULL;
+			clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS,
+					 &edev->flags);
+			edev->ptp_skip_txts++;
+		} else {
+			/* Reschedule to keep checking for a valid TS value */
+			schedule_work(&ptp->work);
+		}
 		return;
 	}
 
@@ -490,18 +504,17 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
 
 	ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
-		rc = -EINVAL;
 		DP_ERR(edev, "PTP clock registration failed\n");
+		qede_ptp_disable(edev);
+		rc = -EINVAL;
 		goto err2;
 	}
 
 	return 0;
 
-err2:
-	qede_ptp_disable(edev);
-	ptp->clock = NULL;
 err1:
 	kfree(ptp);
+err2:
 	edev->ptp = NULL;
 
 	return rc;
@@ -515,19 +528,28 @@ void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb)
 	if (!ptp)
 		return;
 
-	if (test_and_set_bit_lock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags))
+	if (test_and_set_bit_lock(QEDE_FLAGS_PTP_TX_IN_PRORGESS,
+				  &edev->flags)) {
+		DP_ERR(edev, "Timestamping in progress\n");
+		edev->ptp_skip_txts++;
 		return;
+	}
 
 	if (unlikely(!test_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags))) {
-		DP_NOTICE(edev,
-			  "Tx timestamping was not enabled, this packet will not be timestamped\n");
+		DP_ERR(edev,
+		       "Tx timestamping was not enabled, this packet will not be timestamped\n");
+		clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags);
+		edev->ptp_skip_txts++;
 	} else if (unlikely(ptp->tx_skb)) {
-		DP_NOTICE(edev,
-			  "The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n");
+		DP_ERR(edev,
+		       "The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n");
+		clear_bit_unlock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags);
+		edev->ptp_skip_txts++;
 	} else {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		/* schedule check for Tx timestamp */
 		ptp->tx_skb = skb_get(skb);
+		ptp->ptp_tx_start = jiffies;
 		schedule_work(&ptp->work);
 	}
 }
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 1900bf7e67d1..ffabc2d2f082 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -50,6 +50,8 @@ static void _qede_rdma_dev_add(struct qede_dev *edev)
 	if (!qedr_drv)
 		return;
 
+	/* Leftovers from previous error recovery */
+	edev->rdma_info.exp_recovery = false;
 	edev->rdma_info.qedr_dev = qedr_drv->add(edev->cdev, edev->pdev,
 						 edev->ndev);
 }
@@ -87,21 +89,26 @@ static void qede_rdma_destroy_wq(struct qede_dev *edev)
 	destroy_workqueue(edev->rdma_info.rdma_wq);
 }
 
-int qede_rdma_dev_add(struct qede_dev *edev)
+int qede_rdma_dev_add(struct qede_dev *edev, bool recovery)
 {
-	int rc = 0;
+	int rc;
 
-	if (qede_rdma_supported(edev)) {
-		rc = qede_rdma_create_wq(edev);
-		if (rc)
-			return rc;
+	if (!qede_rdma_supported(edev))
+		return 0;
 
-		INIT_LIST_HEAD(&edev->rdma_info.entry);
-		mutex_lock(&qedr_dev_list_lock);
-		list_add_tail(&edev->rdma_info.entry, &qedr_dev_list);
-		_qede_rdma_dev_add(edev);
-		mutex_unlock(&qedr_dev_list_lock);
-	}
+	/* Cannot start qedr while recovering since it wasn't fully stopped */
+	if (recovery)
+		return 0;
+
+	rc = qede_rdma_create_wq(edev);
+	if (rc)
+		return rc;
+
+	INIT_LIST_HEAD(&edev->rdma_info.entry);
+	mutex_lock(&qedr_dev_list_lock);
+	list_add_tail(&edev->rdma_info.entry, &qedr_dev_list);
+	_qede_rdma_dev_add(edev);
+	mutex_unlock(&qedr_dev_list_lock);
 
 	return rc;
 }
@@ -110,19 +117,30 @@ static void _qede_rdma_dev_remove(struct qede_dev *edev)
 {
 	if (qedr_drv && qedr_drv->remove && edev->rdma_info.qedr_dev)
 		qedr_drv->remove(edev->rdma_info.qedr_dev);
-	edev->rdma_info.qedr_dev = NULL;
 }
 
-void qede_rdma_dev_remove(struct qede_dev *edev)
+void qede_rdma_dev_remove(struct qede_dev *edev, bool recovery)
 {
 	if (!qede_rdma_supported(edev))
 		return;
 
-	qede_rdma_destroy_wq(edev);
-	mutex_lock(&qedr_dev_list_lock);
-	_qede_rdma_dev_remove(edev);
-	list_del(&edev->rdma_info.entry);
-	mutex_unlock(&qedr_dev_list_lock);
+	/* Cannot remove qedr while recovering since it wasn't fully stopped */
+	if (!recovery) {
+		qede_rdma_destroy_wq(edev);
+		mutex_lock(&qedr_dev_list_lock);
+		if (!edev->rdma_info.exp_recovery)
+			_qede_rdma_dev_remove(edev);
+		edev->rdma_info.qedr_dev = NULL;
+		list_del(&edev->rdma_info.entry);
+		mutex_unlock(&qedr_dev_list_lock);
+	} else {
+		if (!edev->rdma_info.exp_recovery) {
+			mutex_lock(&qedr_dev_list_lock);
+			_qede_rdma_dev_remove(edev);
+			mutex_unlock(&qedr_dev_list_lock);
+		}
+		edev->rdma_info.exp_recovery = true;
+	}
 }
 
 static void _qede_rdma_dev_open(struct qede_dev *edev)
@@ -204,7 +222,8 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv)
 
 	mutex_lock(&qedr_dev_list_lock);
 	list_for_each_entry(edev, &qedr_dev_list, rdma_info.entry) {
-		if (edev->rdma_info.qedr_dev)
+		/* If device has experienced recovery it was already removed */
+		if (edev->rdma_info.qedr_dev && !edev->rdma_info.exp_recovery)
 			_qede_rdma_dev_remove(edev);
 	}
 	qedr_drv = NULL;
@@ -284,6 +303,10 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 {
 	struct qede_rdma_event_work *event_node;
 
+	/* If a recovery was experienced avoid adding the event */
+	if (edev->rdma_info.exp_recovery)
+		return;
+
 	if (!edev->rdma_info.qedr_dev)
 		return;
 
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 10b075bc5959..457444894d80 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -1858,7 +1858,6 @@ static void ql_update_small_bufq_prod_index(struct ql3_adapter *qdev)
 		wmb();
 		writel_relaxed(qdev->small_buf_q_producer_index,
 			       &port_regs->CommonRegs.rxSmallQProducerIndex);
-		mmiowb();
 	}
 }
 
@@ -3886,6 +3885,12 @@ static int ql3xxx_probe(struct pci_dev *pdev,
 	netif_stop_queue(ndev);
 
 	qdev->workqueue = create_singlethread_workqueue(ndev->name);
+	if (!qdev->workqueue) {
+		unregister_netdev(ndev);
+		err = -ENOMEM;
+		goto err_out_iounmap;
+	}
+
 	INIT_DELAYED_WORK(&qdev->reset_work, ql_reset_work);
 	INIT_DELAYED_WORK(&qdev->tx_timeout_work, ql_tx_timeout_work);
 	INIT_DELAYED_WORK(&qdev->link_state_work, ql_link_state_machine_work);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 0c443ea98479..374a4d4371f9 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -497,7 +497,7 @@ struct qlcnic_hardware_context {
 	u16 board_type;
 	u16 supported_type;
 
-	u16 link_speed;
+	u32 link_speed;
 	u16 link_duplex;
 	u16 link_autoneg;
 	u16 module_type;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 3b0adda7cc9c..a4cd6f2cfb86 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -1048,6 +1048,8 @@ int qlcnic_do_lb_test(struct qlcnic_adapter *adapter, u8 mode)
 
 	for (i = 0; i < QLCNIC_NUM_ILB_PKT; i++) {
 		skb = netdev_alloc_skb(adapter->netdev, QLCNIC_ILB_PKT_SIZE);
+		if (!skb)
+			break;
 		qlcnic_create_loopback_buff(skb->data, adapter->mac_addr);
 		skb_put(skb, QLCNIC_ILB_PKT_SIZE);
 		adapter->ahw->diag_cnt = 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 16d0479f6891..c07438db30ba 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -396,7 +396,8 @@ static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 
 static int qlcnic_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			struct net_device *netdev,
-			const unsigned char *addr, u16 vid, u16 flags)
+			const unsigned char *addr, u16 vid, u16 flags,
+			struct netlink_ext_ack *extack)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int err = 0;
@@ -4118,13 +4119,14 @@ static void
 qlcnic_config_indev_addr(struct qlcnic_adapter *adapter,
 			struct net_device *dev, unsigned long event)
 {
+	const struct in_ifaddr *ifa;
 	struct in_device *indev;
 
 	indev = in_dev_get(dev);
 	if (!indev)
 		return;
 
-	for_ifa(indev) {
+	in_dev_for_each_ifa_rtnl(ifa, indev) {
 		switch (event) {
 		case NETDEV_UP:
 			qlcnic_config_ipaddr(adapter,
@@ -4137,7 +4139,7 @@ qlcnic_config_indev_addr(struct qlcnic_adapter *adapter,
 		default:
 			break;
 		}
-	} endfor_ifa(indev);
+	}
 
 	in_dev_put(indev);
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index af3b037fa442..5632da05145a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -1066,7 +1066,7 @@ static int qlcnic_sriov_pf_cfg_ip_cmd(struct qlcnic_bc_trans *trans,
 {
 	struct qlcnic_vf_info *vf = trans->vf;
 	struct qlcnic_adapter *adapter = vf->adapter;
-	int err = -EIO;
+	int err;
 
 	cmd->req.arg[1] |= vf->vp->handle << 16;
 	cmd->req.arg[1] |= BIT_31;
diff --git a/drivers/net/ethernet/qlogic/qlge/Makefile b/drivers/net/ethernet/qlogic/qlge/Makefile
index 8a197658d76f..1dc2568e820c 100644
--- a/drivers/net/ethernet/qlogic/qlge/Makefile
+++ b/drivers/net/ethernet/qlogic/qlge/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Qlogic 10GbE PCI Express ethernet driver
 #
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 3e71b65a9546..ad7c5eb8a3b6 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -2181,7 +2181,6 @@ static inline void ql_write32(const struct ql_adapter *qdev, int reg, u32 val)
 static inline void ql_write_db_reg(u32 val, void __iomem *addr)
 {
 	writel(val, addr);
-	mmiowb();
 }
 
 /*
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
index 5edbd532127d..a6886cc5654c 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
@@ -249,8 +249,8 @@ static void ql_update_stats(struct ql_adapter *qdev)
 
 	spin_lock(&qdev->stats_lock);
 	if (ql_sem_spinlock(qdev, qdev->xg_sem_mask)) {
-			netif_err(qdev, drv, qdev->ndev,
-				  "Couldn't get xgmac sem.\n");
+		netif_err(qdev, drv, qdev->ndev,
+			  "Couldn't get xgmac sem.\n");
 		goto quit;
 	}
 	/*
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 059ba9429e51..6cae33072496 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1159,10 +1159,10 @@ static void ql_update_lbq(struct ql_adapter *qdev, struct rx_ring *rx_ring)
 
 			map = lbq_desc->p.pg_chunk.map +
 				lbq_desc->p.pg_chunk.offset;
-				dma_unmap_addr_set(lbq_desc, mapaddr, map);
+			dma_unmap_addr_set(lbq_desc, mapaddr, map);
 			dma_unmap_len_set(lbq_desc, maplen,
 					rx_ring->lbq_buf_size);
-				*lbq_desc->addr = cpu_to_le64(map);
+			*lbq_desc->addr = cpu_to_le64(map);
 
 			pci_dma_sync_single_for_device(qdev->pdev, map,
 						rx_ring->lbq_buf_size,
@@ -2695,7 +2695,6 @@ static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev)
 	wmb();
 
 	ql_write_db_reg_relaxed(tx_ring->prod_idx, tx_ring->prod_idx_db_reg);
-	mmiowb();
 	netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev,
 		     "tx queued, slot %d, len %d\n",
 		     tx_ring->prod_idx, skb->len);
@@ -4681,6 +4680,11 @@ static int ql_init_device(struct pci_dev *pdev, struct net_device *ndev,
 	 */
 	qdev->workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
 						  ndev->name);
+	if (!qdev->workqueue) {
+		err = -ENOMEM;
+		goto err_out2;
+	}
+
 	INIT_DELAYED_WORK(&qdev->asic_reset_work, ql_asic_reset_work);
 	INIT_DELAYED_WORK(&qdev->mpi_reset_work, ql_mpi_reset_work);
 	INIT_DELAYED_WORK(&qdev->mpi_work, ql_mpi_work);
diff --git a/drivers/net/ethernet/qualcomm/Kconfig b/drivers/net/ethernet/qualcomm/Kconfig
index f5200712718d..09a678a94634 100644
--- a/drivers/net/ethernet/qualcomm/Kconfig
+++ b/drivers/net/ethernet/qualcomm/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Qualcomm network device configuration
 #
diff --git a/drivers/net/ethernet/qualcomm/emac/Makefile b/drivers/net/ethernet/qualcomm/emac/Makefile
index fc57cedf4c0c..61d15e091be2 100644
--- a/drivers/net/ethernet/qualcomm/emac/Makefile
+++ b/drivers/net/ethernet/qualcomm/emac/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Qualcomm Technologies, Inc. EMAC Gigabit Ethernet driver
 #
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
index c8c6231b87f3..79e50079ed03 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/ethtool.h>
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index 8d790313ee3d..707665b62eb7 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* Qualcomm Technologies, Inc. EMAC Ethernet Controller MAC layer support
@@ -1204,7 +1196,7 @@ void emac_mac_tx_process(struct emac_adapter *adpt, struct emac_tx_queue *tx_q)
 		if (tpbuf->skb) {
 			pkts_compl++;
 			bytes_compl += tpbuf->skb->len;
-			dev_kfree_skb_irq(tpbuf->skb);
+			dev_consume_skb_irq(tpbuf->skb);
 			tpbuf->skb = NULL;
 		}
 
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.h b/drivers/net/ethernet/qualcomm/emac/emac-mac.h
index 4beedb8faa1e..ae08bdd9046c 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.h
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.h
@@ -1,13 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* EMAC DMA HW engine uses three rings:
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.c b/drivers/net/ethernet/qualcomm/emac/emac-phy.c
index 53dbf1e163a8..5c94af7bb6b6 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-phy.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* Qualcomm Technologies, Inc. EMAC PHY Controller driver.
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.h b/drivers/net/ethernet/qualcomm/emac/emac-phy.h
index c0c301c72129..7d703e5d84dd 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-phy.h
+++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.h
@@ -1,13 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
-*
-* This program is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License version 2 and
-* only version 2 as published by the Free Software Foundation.
-*
-* This program is distributed in the hope that it will be useful,
-* but WITHOUT ANY WARRANTY; without even the implied warranty of
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-* GNU General Public License for more details.
 */
 
 #ifndef _EMAC_PHY_H_
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-fsm9900.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-fsm9900.c
index 10de8d0d9a56..bd9ad3297153 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-fsm9900.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-fsm9900.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* Qualcomm Technologies, Inc. FSM9900 EMAC SGMII Controller driver.
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
index 7116be485e61..b29148ce7e05 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2400.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* Qualcomm Technologies, Inc. QDF2400 EMAC SGMII Controller driver.
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2432.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2432.c
index b9c0df7bdd15..65519eeebecd 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2432.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii-qdf2432.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* Qualcomm Technologies, Inc. QDF2432 EMAC SGMII Controller driver.
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
index c694e3428dfc..802ef81493e0 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* Qualcomm Technologies, Inc. EMAC SGMII Controller driver.
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.h b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.h
index 31ba21eb61d2..6daeddacbcfa 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-sgmii.h
+++ b/drivers/net/ethernet/qualcomm/emac/emac-sgmii.h
@@ -1,13 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _EMAC_SGMII_H_
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c
index 2a0cbc535a2e..59c2349b59df 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /* Qualcomm Technologies, Inc. EMAC Gigabit Ethernet Driver */
diff --git a/drivers/net/ethernet/qualcomm/emac/emac.h b/drivers/net/ethernet/qualcomm/emac/emac.h
index d7c9f44209d4..7e9e151f6879 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac.h
+++ b/drivers/net/ethernet/qualcomm/emac/emac.h
@@ -1,13 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _EMAC_H_
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 97f92953bdb9..b28360bc2255 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -966,7 +966,7 @@ qca_spi_probe(struct spi_device *spi)
 
 	mac = of_get_mac_address(spi->dev.of_node);
 
-	if (mac)
+	if (!IS_ERR(mac))
 		ether_addr_copy(qca->net_dev->dev_addr, mac);
 
 	if (!is_valid_ether_addr(qca->net_dev->dev_addr)) {
diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c
index db6068cd7a1f..590616846cd1 100644
--- a/drivers/net/ethernet/qualcomm/qca_uart.c
+++ b/drivers/net/ethernet/qualcomm/qca_uart.c
@@ -351,7 +351,7 @@ static int qca_uart_probe(struct serdev_device *serdev)
 
 	mac = of_get_mac_address(serdev->dev.of_node);
 
-	if (mac)
+	if (!IS_ERR(mac))
 		ether_addr_copy(qca->net_dev->dev_addr, mac);
 
 	if (!is_valid_ether_addr(qca->net_dev->dev_addr)) {
diff --git a/drivers/net/ethernet/qualcomm/rmnet/Kconfig b/drivers/net/ethernet/qualcomm/rmnet/Kconfig
index 9bb06d284644..9f9279575e2e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/Kconfig
+++ b/drivers/net/ethernet/qualcomm/rmnet/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # RMNET MAP driver
 #
diff --git a/drivers/net/ethernet/qualcomm/rmnet/Makefile b/drivers/net/ethernet/qualcomm/rmnet/Makefile
index 01bddf207cac..8252e40bf570 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/Makefile
+++ b/drivers/net/ethernet/qualcomm/rmnet/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the RMNET module
 #
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index b8bbee645f51..9c54b715228e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * RMNET configuration engine
- *
  */
 
 #include <net/sock.h>
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
index 34ac45a774e7..cd0a6bcbe74a 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2013-2014, 2016-2018 The Linux Foundation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * RMNET Data configuration engine
- *
  */
 
 #include <linux/skbuff.h>
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
index 11167abe5934..1b74bc160402 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * RMNET Data ingress/egress handler
- *
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h
index 3537e4ceedb3..c4571dc3239d 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2013, 2016-2017 The Linux Foundation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * RMNET Data ingress/egress handler
- *
  */
 
 #ifndef _RMNET_HANDLERS_H_
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
index 884f1f52dcc2..576501db2a0b 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h
@@ -1,17 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _RMNET_MAP_H_
 #define _RMNET_MAP_H_
+#include <linux/if_rmnet.h>
 
 struct rmnet_map_control_command {
 	u8  command_name;
@@ -39,30 +32,6 @@ enum rmnet_map_commands {
 	RMNET_MAP_COMMAND_ENUM_LENGTH
 };
 
-struct rmnet_map_header {
-	u8  pad_len:6;
-	u8  reserved_bit:1;
-	u8  cd_bit:1;
-	u8  mux_id;
-	__be16 pkt_len;
-}  __aligned(1);
-
-struct rmnet_map_dl_csum_trailer {
-	u8  reserved1;
-	u8  valid:1;
-	u8  reserved2:7;
-	u16 csum_start_offset;
-	u16 csum_length;
-	__be16 csum_value;
-} __aligned(1);
-
-struct rmnet_map_ul_csum_header {
-	__be16 csum_start_offset;
-	u16 csum_insert_offset:14;
-	u16 udp_ip4_ind:1;
-	u16 csum_enabled:1;
-} __aligned(1);
-
 #define RMNET_MAP_GET_MUX_ID(Y) (((struct rmnet_map_header *) \
 				 (Y)->data)->mux_id)
 #define RMNET_MAP_GET_CD_BIT(Y) (((struct rmnet_map_header *) \
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
index f6cf59aee212..beaee4962128 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
@@ -1,13 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
index 57a9c314a665..60189923737a 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * RMNET Data MAP protocol
- *
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h
index b9cc4f85f229..e1337f164faa 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h
@@ -1,13 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2013-2014, 2016-2018 The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef _RMNET_PRIVATE_H_
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index d11c16aeb19a..509dfc895a33 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -1,17 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- *
  * RMNET Data virtual network driver
- *
  */
 
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
index 71e4c3286951..54cbaf3c3bc4 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  * RMNET Data Virtual Network Device APIs
- *
  */
 
 #ifndef _RMNET_VND_H_
diff --git a/drivers/net/ethernet/rdc/Kconfig b/drivers/net/ethernet/rdc/Kconfig
index a9c4e990d29b..76df60c2f4ac 100644
--- a/drivers/net/ethernet/rdc/Kconfig
+++ b/drivers/net/ethernet/rdc/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # RDC network device configuration
 #
diff --git a/drivers/net/ethernet/rdc/Makefile b/drivers/net/ethernet/rdc/Makefile
index 8d51fd2d07fc..807465483f1c 100644
--- a/drivers/net/ethernet/rdc/Makefile
+++ b/drivers/net/ethernet/rdc/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the RDC network device drivers.
 #
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 04aa592f35c3..274e5b4bc4ac 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * RDC R6040 Fast Ethernet MAC support
  *
@@ -5,21 +6,6 @@
  * Copyright (C) 2007
  *	Daniel Gimpelevich <daniel@gimpelevich.san-francisco.ca.us>
  * Copyright (C) 2007-2012 Florian Fainelli <f.fainelli@gmail.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
- * Boston, MA  02110-1301, USA.
 */
 
 #include <linux/kernel.h>
@@ -840,7 +826,7 @@ static netdev_tx_t r6040_start_xmit(struct sk_buff *skb,
 	skb_tx_timestamp(skb);
 
 	/* Trigger the MAC to check the TX descriptor */
-	if (!skb->xmit_more || netif_queue_stopped(dev))
+	if (!netdev_xmit_more() || netif_queue_stopped(dev))
 		iowrite16(TM2TX, ioaddr + MTPR);
 	lp->tx_insert_ptr = descptr->vndescp;
 
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 69d752f0b621..55d01266e615 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -258,6 +258,7 @@ static const struct pci_device_id rtl8139_pci_tbl[] = {
 	{0x126c, 0x1211, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
 	{0x1743, 0x8139, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
 	{0x021b, 0x8139, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
+	{0x16ec, 0xab06, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
 
 #ifdef CONFIG_SH_SECUREEDGE5410
 	/* Bogus 8139 silicon reports 8129 without external PROM :-( */
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 96d1b9c08f1a..b18e7a91d5cd 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Realtek device configuration
 #
diff --git a/drivers/net/ethernet/realtek/Makefile b/drivers/net/ethernet/realtek/Makefile
index 71b1da30ecb5..d5304bad2372 100644
--- a/drivers/net/ethernet/realtek/Makefile
+++ b/drivers/net/ethernet/realtek/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Realtek network device drivers.
 #
@@ -5,4 +6,5 @@
 obj-$(CONFIG_8139CP) += 8139cp.o
 obj-$(CONFIG_8139TOO) += 8139too.o
 obj-$(CONFIG_ATP) += atp.o
+r8169-objs += r8169_main.o r8169_firmware.o
 obj-$(CONFIG_R8169) += r8169.o
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index 7e011c1c1e6e..58e0ca9093d3 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -454,14 +454,14 @@ static void hardware_init(struct net_device *dev)
 {
 	struct net_local *lp = netdev_priv(dev);
 	long ioaddr = dev->base_addr;
-    int i;
+	int i;
 
 	/* Turn off the printer multiplexer on the 8012. */
 	for (i = 0; i < 8; i++)
 		outb(mux_8012[i], ioaddr + PAR_DATA);
 	write_reg_high(ioaddr, CMR1, CMR1h_RESET);
 
-    for (i = 0; i < 6; i++)
+	for (i = 0; i < 6; i++)
 		write_reg_byte(ioaddr, PAR0 + i, dev->dev_addr[i]);
 
 	write_reg_high(ioaddr, CMR2, lp->addr_mode);
@@ -471,18 +471,18 @@ static void hardware_init(struct net_device *dev)
 			   (read_nibble(ioaddr, CMR2_h) >> 3) & 0x0f);
 	}
 
-    write_reg(ioaddr, CMR2, CMR2_IRQOUT);
-    write_reg_high(ioaddr, CMR1, CMR1h_RxENABLE | CMR1h_TxENABLE);
+	write_reg(ioaddr, CMR2, CMR2_IRQOUT);
+	write_reg_high(ioaddr, CMR1, CMR1h_RxENABLE | CMR1h_TxENABLE);
 
 	/* Enable the interrupt line from the serial port. */
 	outb(Ctrl_SelData + Ctrl_IRQEN, ioaddr + PAR_CONTROL);
 
 	/* Unmask the interesting interrupts. */
-    write_reg(ioaddr, IMR, ISR_RxOK | ISR_TxErr | ISR_TxOK);
-    write_reg_high(ioaddr, IMR, ISRh_RxErr);
+	write_reg(ioaddr, IMR, ISR_RxOK | ISR_TxErr | ISR_TxOK);
+	write_reg_high(ioaddr, IMR, ISRh_RxErr);
 
 	lp->tx_unit_busy = 0;
-    lp->pac_cnt_in_tx_buf = 0;
+	lp->pac_cnt_in_tx_buf = 0;
 	lp->saved_tx_size = 0;
 }
 
@@ -610,10 +610,12 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 	write_reg(ioaddr, CMR2, CMR2_NULL);
 	write_reg(ioaddr, IMR, 0);
 
-	if (net_debug > 5) printk(KERN_DEBUG "%s: In interrupt ", dev->name);
-    while (--boguscount > 0) {
+	if (net_debug > 5)
+		printk(KERN_DEBUG "%s: In interrupt ", dev->name);
+	while (--boguscount > 0) {
 		int status = read_nibble(ioaddr, ISR);
-		if (net_debug > 5) printk("loop status %02x..", status);
+		if (net_debug > 5)
+			printk("loop status %02x..", status);
 
 		if (status & (ISR_RxOK<<3)) {
 			handled = 1;
@@ -640,7 +642,8 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 			} while (--boguscount > 0);
 		} else if (status & ((ISR_TxErr + ISR_TxOK)<<3)) {
 			handled = 1;
-			if (net_debug > 6)  printk("handling Tx done..");
+			if (net_debug > 6)
+				printk("handling Tx done..");
 			/* Clear the Tx interrupt.  We should check for too many failures
 			   and reinitialize the adapter. */
 			write_reg(ioaddr, ISR, ISR_TxErr + ISR_TxOK);
@@ -680,7 +683,7 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 			break;
 		} else
 			break;
-    }
+	}
 
 	/* This following code fixes a rare (and very difficult to track down)
 	   problem where the adapter forgets its ethernet address. */
@@ -694,7 +697,7 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 	}
 
 	/* Tell the adapter that it can go back to using the output line as IRQ. */
-    write_reg(ioaddr, CMR2, CMR2_IRQOUT);
+	write_reg(ioaddr, CMR2, CMR2_IRQOUT);
 	/* Enable the physical interrupt line, which is sure to be low until.. */
 	outb(Ctrl_SelData + Ctrl_IRQEN, ioaddr + PAR_CONTROL);
 	/* .. we enable the interrupt sources. */
diff --git a/drivers/net/ethernet/realtek/r8169_firmware.c b/drivers/net/ethernet/realtek/r8169_firmware.c
new file mode 100644
index 000000000000..8f54a2c832eb
--- /dev/null
+++ b/drivers/net/ethernet/realtek/r8169_firmware.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* r8169_firmware.c: RealTek 8169/8168/8101 ethernet driver.
+ *
+ * Copyright (c) 2002 ShuChen <shuchen@realtek.com.tw>
+ * Copyright (c) 2003 - 2007 Francois Romieu <romieu@fr.zoreil.com>
+ * Copyright (c) a lot of people too. Please respect their work.
+ *
+ * See MAINTAINERS file for support contact information.
+ */
+
+#include <linux/delay.h>
+#include <linux/firmware.h>
+
+#include "r8169_firmware.h"
+
+enum rtl_fw_opcode {
+	PHY_READ		= 0x0,
+	PHY_DATA_OR		= 0x1,
+	PHY_DATA_AND		= 0x2,
+	PHY_BJMPN		= 0x3,
+	PHY_MDIO_CHG		= 0x4,
+	PHY_CLEAR_READCOUNT	= 0x7,
+	PHY_WRITE		= 0x8,
+	PHY_READCOUNT_EQ_SKIP	= 0x9,
+	PHY_COMP_EQ_SKIPN	= 0xa,
+	PHY_COMP_NEQ_SKIPN	= 0xb,
+	PHY_WRITE_PREVIOUS	= 0xc,
+	PHY_SKIPN		= 0xd,
+	PHY_DELAY_MS		= 0xe,
+};
+
+struct fw_info {
+	u32	magic;
+	char	version[RTL_VER_SIZE];
+	__le32	fw_start;
+	__le32	fw_len;
+	u8	chksum;
+} __packed;
+
+#define FW_OPCODE_SIZE	sizeof(typeof(*((struct rtl_fw_phy_action *)0)->code))
+
+static bool rtl_fw_format_ok(struct rtl_fw *rtl_fw)
+{
+	const struct firmware *fw = rtl_fw->fw;
+	struct fw_info *fw_info = (struct fw_info *)fw->data;
+	struct rtl_fw_phy_action *pa = &rtl_fw->phy_action;
+
+	if (fw->size < FW_OPCODE_SIZE)
+		return false;
+
+	if (!fw_info->magic) {
+		size_t i, size, start;
+		u8 checksum = 0;
+
+		if (fw->size < sizeof(*fw_info))
+			return false;
+
+		for (i = 0; i < fw->size; i++)
+			checksum += fw->data[i];
+		if (checksum != 0)
+			return false;
+
+		start = le32_to_cpu(fw_info->fw_start);
+		if (start > fw->size)
+			return false;
+
+		size = le32_to_cpu(fw_info->fw_len);
+		if (size > (fw->size - start) / FW_OPCODE_SIZE)
+			return false;
+
+		strscpy(rtl_fw->version, fw_info->version, RTL_VER_SIZE);
+
+		pa->code = (__le32 *)(fw->data + start);
+		pa->size = size;
+	} else {
+		if (fw->size % FW_OPCODE_SIZE)
+			return false;
+
+		strscpy(rtl_fw->version, rtl_fw->fw_name, RTL_VER_SIZE);
+
+		pa->code = (__le32 *)fw->data;
+		pa->size = fw->size / FW_OPCODE_SIZE;
+	}
+
+	return true;
+}
+
+static bool rtl_fw_data_ok(struct rtl_fw *rtl_fw)
+{
+	struct rtl_fw_phy_action *pa = &rtl_fw->phy_action;
+	size_t index;
+
+	for (index = 0; index < pa->size; index++) {
+		u32 action = le32_to_cpu(pa->code[index]);
+		u32 regno = (action & 0x0fff0000) >> 16;
+
+		switch (action >> 28) {
+		case PHY_READ:
+		case PHY_DATA_OR:
+		case PHY_DATA_AND:
+		case PHY_MDIO_CHG:
+		case PHY_CLEAR_READCOUNT:
+		case PHY_WRITE:
+		case PHY_WRITE_PREVIOUS:
+		case PHY_DELAY_MS:
+			break;
+
+		case PHY_BJMPN:
+			if (regno > index)
+				goto out;
+			break;
+		case PHY_READCOUNT_EQ_SKIP:
+			if (index + 2 >= pa->size)
+				goto out;
+			break;
+		case PHY_COMP_EQ_SKIPN:
+		case PHY_COMP_NEQ_SKIPN:
+		case PHY_SKIPN:
+			if (index + 1 + regno >= pa->size)
+				goto out;
+			break;
+
+		default:
+			dev_err(rtl_fw->dev, "Invalid action 0x%08x\n", action);
+			return false;
+		}
+	}
+
+	return true;
+out:
+	dev_err(rtl_fw->dev, "Out of range of firmware\n");
+	return false;
+}
+
+void rtl_fw_write_firmware(struct rtl8169_private *tp, struct rtl_fw *rtl_fw)
+{
+	struct rtl_fw_phy_action *pa = &rtl_fw->phy_action;
+	rtl_fw_write_t fw_write = rtl_fw->phy_write;
+	rtl_fw_read_t fw_read = rtl_fw->phy_read;
+	int predata = 0, count = 0;
+	size_t index;
+
+	for (index = 0; index < pa->size; index++) {
+		u32 action = le32_to_cpu(pa->code[index]);
+		u32 data = action & 0x0000ffff;
+		u32 regno = (action & 0x0fff0000) >> 16;
+		enum rtl_fw_opcode opcode = action >> 28;
+
+		if (!action)
+			break;
+
+		switch (opcode) {
+		case PHY_READ:
+			predata = fw_read(tp, regno);
+			count++;
+			break;
+		case PHY_DATA_OR:
+			predata |= data;
+			break;
+		case PHY_DATA_AND:
+			predata &= data;
+			break;
+		case PHY_BJMPN:
+			index -= (regno + 1);
+			break;
+		case PHY_MDIO_CHG:
+			if (data == 0) {
+				fw_write = rtl_fw->phy_write;
+				fw_read = rtl_fw->phy_read;
+			} else if (data == 1) {
+				fw_write = rtl_fw->mac_mcu_write;
+				fw_read = rtl_fw->mac_mcu_read;
+			}
+
+			break;
+		case PHY_CLEAR_READCOUNT:
+			count = 0;
+			break;
+		case PHY_WRITE:
+			fw_write(tp, regno, data);
+			break;
+		case PHY_READCOUNT_EQ_SKIP:
+			if (count == data)
+				index++;
+			break;
+		case PHY_COMP_EQ_SKIPN:
+			if (predata == data)
+				index += regno;
+			break;
+		case PHY_COMP_NEQ_SKIPN:
+			if (predata != data)
+				index += regno;
+			break;
+		case PHY_WRITE_PREVIOUS:
+			fw_write(tp, regno, predata);
+			break;
+		case PHY_SKIPN:
+			index += regno;
+			break;
+		case PHY_DELAY_MS:
+			mdelay(data);
+			break;
+		}
+	}
+}
+
+void rtl_fw_release_firmware(struct rtl_fw *rtl_fw)
+{
+	release_firmware(rtl_fw->fw);
+}
+
+int rtl_fw_request_firmware(struct rtl_fw *rtl_fw)
+{
+	int rc;
+
+	rc = request_firmware(&rtl_fw->fw, rtl_fw->fw_name, rtl_fw->dev);
+	if (rc < 0)
+		goto out;
+
+	if (!rtl_fw_format_ok(rtl_fw) || !rtl_fw_data_ok(rtl_fw)) {
+		release_firmware(rtl_fw->fw);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	return 0;
+out:
+	dev_err(rtl_fw->dev, "Unable to load firmware %s (%d)\n",
+		rtl_fw->fw_name, rc);
+	return rc;
+}
diff --git a/drivers/net/ethernet/realtek/r8169_firmware.h b/drivers/net/ethernet/realtek/r8169_firmware.h
new file mode 100644
index 000000000000..7dc348ed8345
--- /dev/null
+++ b/drivers/net/ethernet/realtek/r8169_firmware.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* r8169_firmware.h: RealTek 8169/8168/8101 ethernet driver.
+ *
+ * Copyright (c) 2002 ShuChen <shuchen@realtek.com.tw>
+ * Copyright (c) 2003 - 2007 Francois Romieu <romieu@fr.zoreil.com>
+ * Copyright (c) a lot of people too. Please respect their work.
+ *
+ * See MAINTAINERS file for support contact information.
+ */
+
+#include <linux/device.h>
+#include <linux/firmware.h>
+
+struct rtl8169_private;
+typedef void (*rtl_fw_write_t)(struct rtl8169_private *tp, int reg, int val);
+typedef int (*rtl_fw_read_t)(struct rtl8169_private *tp, int reg);
+
+#define RTL_VER_SIZE		32
+
+struct rtl_fw {
+	rtl_fw_write_t phy_write;
+	rtl_fw_read_t phy_read;
+	rtl_fw_write_t mac_mcu_write;
+	rtl_fw_read_t mac_mcu_read;
+	const struct firmware *fw;
+	const char *fw_name;
+	struct device *dev;
+
+	char version[RTL_VER_SIZE];
+
+	struct rtl_fw_phy_action {
+		__le32 *code;
+		size_t size;
+	} phy_action;
+};
+
+int rtl_fw_request_firmware(struct rtl_fw *rtl_fw);
+void rtl_fw_release_firmware(struct rtl_fw *rtl_fw);
+void rtl_fw_write_firmware(struct rtl8169_private *tp, struct rtl_fw *rtl_fw);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169_main.c
index abb94c543aa2..efef5453b94f 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * r8169.c: RealTek 8169/8168/8101 ethernet driver.
  *
@@ -26,11 +27,13 @@
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
-#include <linux/firmware.h>
 #include <linux/prefetch.h>
+#include <linux/pci-aspm.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
 
+#include "r8169_firmware.h"
+
 #define MODULENAME "r8169"
 
 #define FIRMWARE_8168D_1	"rtl_nic/rtl8168d-1.fw"
@@ -70,6 +73,8 @@ static const int multicast_filter_limit = 32;
 #define R8169_TX_RING_BYTES	(NUM_TX_DESC * sizeof(struct TxDesc))
 #define R8169_RX_RING_BYTES	(NUM_RX_DESC * sizeof(struct RxDesc))
 
+#define RTL_CFG_NO_GBIT	1
+
 /* write/read MMIO register */
 #define RTL_W8(tp, reg, val8)	writeb((val8), tp->mmio_addr + (reg))
 #define RTL_W16(tp, reg, val16)	writew((val16), tp->mmio_addr + (reg))
@@ -79,7 +84,7 @@ static const int multicast_filter_limit = 32;
 #define RTL_R32(tp, reg)		readl(tp->mmio_addr + (reg))
 
 enum mac_version {
-	RTL_GIGA_MAC_VER_01 = 0,
+	/* support for ancient RTL_GIGA_MAC_VER_01 has been removed */
 	RTL_GIGA_MAC_VER_02,
 	RTL_GIGA_MAC_VER_03,
 	RTL_GIGA_MAC_VER_04,
@@ -130,7 +135,7 @@ enum mac_version {
 	RTL_GIGA_MAC_VER_49,
 	RTL_GIGA_MAC_VER_50,
 	RTL_GIGA_MAC_VER_51,
-	RTL_GIGA_MAC_NONE   = 0xff,
+	RTL_GIGA_MAC_NONE
 };
 
 #define JUMBO_1K	ETH_DATA_LEN
@@ -144,7 +149,6 @@ static const struct {
 	const char *fw_name;
 } rtl_chip_infos[] = {
 	/* PCI devices. */
-	[RTL_GIGA_MAC_VER_01] = {"RTL8169"				},
 	[RTL_GIGA_MAC_VER_02] = {"RTL8169s"				},
 	[RTL_GIGA_MAC_VER_03] = {"RTL8110s"				},
 	[RTL_GIGA_MAC_VER_04] = {"RTL8169sb/8110sb"			},
@@ -153,7 +157,7 @@ static const struct {
 	/* PCI-E devices. */
 	[RTL_GIGA_MAC_VER_07] = {"RTL8102e"				},
 	[RTL_GIGA_MAC_VER_08] = {"RTL8102e"				},
-	[RTL_GIGA_MAC_VER_09] = {"RTL8102e"				},
+	[RTL_GIGA_MAC_VER_09] = {"RTL8102e/RTL8103e"			},
 	[RTL_GIGA_MAC_VER_10] = {"RTL8101e"				},
 	[RTL_GIGA_MAC_VER_11] = {"RTL8168b/8111b"			},
 	[RTL_GIGA_MAC_VER_12] = {"RTL8168b/8111b"			},
@@ -186,9 +190,9 @@ static const struct {
 	[RTL_GIGA_MAC_VER_39] = {"RTL8106e",		FIRMWARE_8106E_1},
 	[RTL_GIGA_MAC_VER_40] = {"RTL8168g/8111g",	FIRMWARE_8168G_2},
 	[RTL_GIGA_MAC_VER_41] = {"RTL8168g/8111g"			},
-	[RTL_GIGA_MAC_VER_42] = {"RTL8168g/8111g",	FIRMWARE_8168G_3},
-	[RTL_GIGA_MAC_VER_43] = {"RTL8106e",		FIRMWARE_8106E_2},
-	[RTL_GIGA_MAC_VER_44] = {"RTL8411",		FIRMWARE_8411_2 },
+	[RTL_GIGA_MAC_VER_42] = {"RTL8168gu/8111gu",	FIRMWARE_8168G_3},
+	[RTL_GIGA_MAC_VER_43] = {"RTL8106eus",		FIRMWARE_8106E_2},
+	[RTL_GIGA_MAC_VER_44] = {"RTL8411b",		FIRMWARE_8411_2 },
 	[RTL_GIGA_MAC_VER_45] = {"RTL8168h/8111h",	FIRMWARE_8168H_1},
 	[RTL_GIGA_MAC_VER_46] = {"RTL8168h/8111h",	FIRMWARE_8168H_2},
 	[RTL_GIGA_MAC_VER_47] = {"RTL8107e",		FIRMWARE_8107E_1},
@@ -198,38 +202,29 @@ static const struct {
 	[RTL_GIGA_MAC_VER_51] = {"RTL8168ep/8111ep"			},
 };
 
-enum cfg_version {
-	RTL_CFG_0 = 0x00,
-	RTL_CFG_1,
-	RTL_CFG_2
-};
-
 static const struct pci_device_id rtl8169_pci_tbl[] = {
-	{ PCI_VDEVICE(REALTEK,	0x2502), RTL_CFG_1 },
-	{ PCI_VDEVICE(REALTEK,	0x2600), RTL_CFG_1 },
-	{ PCI_VDEVICE(REALTEK,	0x8129), RTL_CFG_0 },
-	{ PCI_VDEVICE(REALTEK,	0x8136), RTL_CFG_2 },
-	{ PCI_VDEVICE(REALTEK,	0x8161), RTL_CFG_1 },
-	{ PCI_VDEVICE(REALTEK,	0x8167), RTL_CFG_0 },
-	{ PCI_VDEVICE(REALTEK,	0x8168), RTL_CFG_1 },
-	{ PCI_VDEVICE(NCUBE,	0x8168), RTL_CFG_1 },
-	{ PCI_VDEVICE(REALTEK,	0x8169), RTL_CFG_0 },
+	{ PCI_VDEVICE(REALTEK,	0x2502) },
+	{ PCI_VDEVICE(REALTEK,	0x2600) },
+	{ PCI_VDEVICE(REALTEK,	0x8129) },
+	{ PCI_VDEVICE(REALTEK,	0x8136), RTL_CFG_NO_GBIT },
+	{ PCI_VDEVICE(REALTEK,	0x8161) },
+	{ PCI_VDEVICE(REALTEK,	0x8167) },
+	{ PCI_VDEVICE(REALTEK,	0x8168) },
+	{ PCI_VDEVICE(NCUBE,	0x8168) },
+	{ PCI_VDEVICE(REALTEK,	0x8169) },
 	{ PCI_VENDOR_ID_DLINK,	0x4300,
-		PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0, RTL_CFG_1 },
-	{ PCI_VDEVICE(DLINK,	0x4300), RTL_CFG_0 },
-	{ PCI_VDEVICE(DLINK,	0x4302), RTL_CFG_0 },
-	{ PCI_VDEVICE(AT,	0xc107), RTL_CFG_0 },
-	{ PCI_VDEVICE(USR,	0x0116), RTL_CFG_0 },
-	{ PCI_VENDOR_ID_LINKSYS,		0x1032,
-		PCI_ANY_ID, 0x0024, 0, 0, RTL_CFG_0 },
-	{ 0x0001,				0x8168,
-		PCI_ANY_ID, 0x2410, 0, 0, RTL_CFG_2 },
+		PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0 },
+	{ PCI_VDEVICE(DLINK,	0x4300) },
+	{ PCI_VDEVICE(DLINK,	0x4302) },
+	{ PCI_VDEVICE(AT,	0xc107) },
+	{ PCI_VDEVICE(USR,	0x0116) },
+	{ PCI_VENDOR_ID_LINKSYS, 0x1032, PCI_ANY_ID, 0x0024 },
+	{ 0x0001, 0x8168, PCI_ANY_ID, 0x2410 },
 	{}
 };
 
 MODULE_DEVICE_TABLE(pci, rtl8169_pci_tbl);
 
-static int use_dac = -1;
 static struct {
 	u32 msg_enable;
 } debug = { -1 };
@@ -405,8 +400,6 @@ enum rtl_register_content {
 	RxOK		= 0x0001,
 
 	/* RxStatusDesc */
-	RxBOVF	= (1 << 24),
-	RxFOVF	= (1 << 23),
 	RxRWT	= (1 << 22),
 	RxRES	= (1 << 21),
 	RxRUNT	= (1 << 20),
@@ -491,10 +484,7 @@ enum rtl_register_content {
 	PCIDAC		= (1 << 4),
 	PCIMulRW	= (1 << 3),
 #define INTT_MASK	GENMASK(1, 0)
-	INTT_0		= 0x0000,	// 8168
-	INTT_1		= 0x0001,	// 8168
-	INTT_2		= 0x0002,	// 8168
-	INTT_3		= 0x0003,	// 8168
+#define CPCMD_MASK	(Normal_mode | RxVlan | RxChkSum | INTT_MASK)
 
 	/* rtl8169_PHYstatus */
 	TBI_Enable	= 0x80,
@@ -506,9 +496,6 @@ enum rtl_register_content {
 	LinkStatus	= 0x02,
 	FullDup		= 0x01,
 
-	/* _TBICSRBit */
-	TBILinkOK	= 0x02000000,
-
 	/* ResetCounterCommand */
 	CounterReset	= 0x1,
 
@@ -581,7 +568,6 @@ enum rtl_rx_desc_bit {
 };
 
 #define RsvdMask	0x3fffc000
-#define CPCMD_QUIRK_MASK	(Normal_mode | RxVlan | RxChkSum | INTT_MASK)
 
 struct TxDesc {
 	__le32 opts1;
@@ -639,9 +625,10 @@ struct rtl8169_private {
 	void __iomem *mmio_addr;	/* memory map physical address */
 	struct pci_dev *pci_dev;
 	struct net_device *dev;
+	struct phy_device *phydev;
 	struct napi_struct napi;
 	u32 msg_enable;
-	u16 mac_version;
+	enum mac_version mac_version;
 	u32 cur_rx; /* Index into the Rx descriptor buffer of next Rx pkt. */
 	u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */
 	u32 dirty_tx;
@@ -654,58 +641,33 @@ struct rtl8169_private {
 	void *Rx_databuff[NUM_RX_DESC];	/* Rx data buffers */
 	struct ring_info tx_skb[NUM_TX_DESC];	/* Tx data buffers */
 	u16 cp_cmd;
-
 	u16 irq_mask;
-	const struct rtl_coalesce_info *coalesce_info;
 	struct clk *clk;
 
-	struct mdio_ops {
-		void (*write)(struct rtl8169_private *, int, int);
-		int (*read)(struct rtl8169_private *, int);
-	} mdio_ops;
-
-	struct jumbo_ops {
-		void (*enable)(struct rtl8169_private *);
-		void (*disable)(struct rtl8169_private *);
-	} jumbo_ops;
-
-	void (*hw_start)(struct rtl8169_private *tp);
-	bool (*tso_csum)(struct rtl8169_private *, struct sk_buff *, u32 *);
-
 	struct {
 		DECLARE_BITMAP(flags, RTL_FLAG_MAX);
 		struct mutex mutex;
 		struct work_struct work;
 	} wk;
 
+	unsigned irq_enabled:1;
 	unsigned supports_gmii:1;
-	struct mii_bus *mii_bus;
+	unsigned aspm_manageable:1;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
 	u32 saved_wolopts;
 
-	struct rtl_fw {
-		const struct firmware *fw;
-
-#define RTL_VER_SIZE		32
-
-		char version[RTL_VER_SIZE];
-
-		struct rtl_fw_phy_action {
-			__le32 *code;
-			size_t size;
-		} phy_action;
-	} *rtl_fw;
-#define RTL_FIRMWARE_UNKNOWN	ERR_PTR(-EAGAIN)
+	const char *fw_name;
+	struct rtl_fw *rtl_fw;
 
 	u32 ocp_base;
 };
 
+typedef void (*rtl_generic_fct)(struct rtl8169_private *tp);
+
 MODULE_AUTHOR("Realtek and the Linux r8169 crew <netdev@vger.kernel.org>");
 MODULE_DESCRIPTION("RealTek RTL-8169 Gigabit Ethernet driver");
-module_param(use_dac, int, 0);
-MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot.");
 module_param_named(debug, debug.msg_enable, int, 0);
 MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
 MODULE_SOFTDEP("pre: realtek");
@@ -745,12 +707,28 @@ static void rtl_unlock_work(struct rtl8169_private *tp)
 	mutex_unlock(&tp->wk.mutex);
 }
 
+static void rtl_lock_config_regs(struct rtl8169_private *tp)
+{
+	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+}
+
+static void rtl_unlock_config_regs(struct rtl8169_private *tp)
+{
+	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+}
+
 static void rtl_tx_performance_tweak(struct rtl8169_private *tp, u16 force)
 {
 	pcie_capability_clear_and_set_word(tp->pci_dev, PCI_EXP_DEVCTL,
 					   PCI_EXP_DEVCTL_READRQ, force);
 }
 
+static bool rtl_is_8168evl_up(struct rtl8169_private *tp)
+{
+	return tp->mac_version >= RTL_GIGA_MAC_VER_34 &&
+	       tp->mac_version != RTL_GIGA_MAC_VER_39;
+}
+
 struct rtl_cond {
 	bool (*check)(struct rtl8169_private *);
 	const char *msg;
@@ -768,9 +746,9 @@ static bool rtl_loop_wait(struct rtl8169_private *tp, const struct rtl_cond *c,
 	int i;
 
 	for (i = 0; i < n; i++) {
-		delay(d);
 		if (c->check(tp) == high)
 			return true;
+		delay(d);
 	}
 	netif_err(tp, drv, tp->dev, "%s == %d (loop: %d, delay: %d).\n",
 		  c->msg, !high, n, d);
@@ -839,7 +817,7 @@ static void r8168_phy_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data)
 	rtl_udelay_loop_wait_low(tp, &rtl_ocp_gphy_cond, 25, 10);
 }
 
-static u16 r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
+static int r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
 {
 	if (rtl_ocp_reg_failure(tp, reg))
 		return 0;
@@ -847,7 +825,7 @@ static u16 r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
 	RTL_W32(tp, GPHY_OCP, reg << 15);
 
 	return rtl_udelay_loop_wait_high(tp, &rtl_ocp_gphy_cond, 25, 10) ?
-		(RTL_R32(tp, GPHY_OCP) & 0xffff) : ~0;
+		(RTL_R32(tp, GPHY_OCP) & 0xffff) : -ETIMEDOUT;
 }
 
 static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data)
@@ -930,7 +908,7 @@ static int r8169_mdio_read(struct rtl8169_private *tp, int reg)
 	RTL_W32(tp, PHYAR, 0x0 | (reg & 0x1f) << 16);
 
 	value = rtl_udelay_loop_wait_high(tp, &rtl_phyar_cond, 25, 20) ?
-		RTL_R32(tp, PHYAR) & 0xffff : ~0;
+		RTL_R32(tp, PHYAR) & 0xffff : -ETIMEDOUT;
 
 	/*
 	 * According to hardware specs a 20us delay is required after read
@@ -970,7 +948,7 @@ static int r8168dp_1_mdio_read(struct rtl8169_private *tp, int reg)
 	RTL_W32(tp, EPHY_RXER_NUM, 0);
 
 	return rtl_udelay_loop_wait_high(tp, &rtl_ocpar_cond, 1000, 100) ?
-		RTL_R32(tp, OCPDR) & OCPDR_DATA_MASK : ~0;
+		RTL_R32(tp, OCPDR) & OCPDR_DATA_MASK : -ETIMEDOUT;
 }
 
 #define R8168DP_1_MDIO_ACCESS_BIT	0x00020000
@@ -1007,14 +985,38 @@ static int r8168dp_2_mdio_read(struct rtl8169_private *tp, int reg)
 	return value;
 }
 
-static void rtl_writephy(struct rtl8169_private *tp, int location, u32 val)
+static void rtl_writephy(struct rtl8169_private *tp, int location, int val)
 {
-	tp->mdio_ops.write(tp, location, val);
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_27:
+		r8168dp_1_mdio_write(tp, location, val);
+		break;
+	case RTL_GIGA_MAC_VER_28:
+	case RTL_GIGA_MAC_VER_31:
+		r8168dp_2_mdio_write(tp, location, val);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		r8168g_mdio_write(tp, location, val);
+		break;
+	default:
+		r8169_mdio_write(tp, location, val);
+		break;
+	}
 }
 
 static int rtl_readphy(struct rtl8169_private *tp, int location)
 {
-	return tp->mdio_ops.read(tp, location);
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_27:
+		return r8168dp_1_mdio_read(tp, location);
+	case RTL_GIGA_MAC_VER_28:
+	case RTL_GIGA_MAC_VER_31:
+		return r8168dp_2_mdio_read(tp, location);
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		return r8168g_mdio_read(tp, location);
+	default:
+		return r8169_mdio_read(tp, location);
+	}
 }
 
 static void rtl_patchphy(struct rtl8169_private *tp, int reg_addr, int value)
@@ -1058,8 +1060,8 @@ DECLARE_RTL_COND(rtl_eriar_cond)
 	return RTL_R32(tp, ERIAR) & ERIAR_FLAG;
 }
 
-static void rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
-			  u32 val, int type)
+static void _rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
+			   u32 val, int type)
 {
 	BUG_ON((addr & 3) || (mask == 0));
 	RTL_W32(tp, ERIDR, val);
@@ -1068,7 +1070,13 @@ static void rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
 	rtl_udelay_loop_wait_low(tp, &rtl_eriar_cond, 100, 100);
 }
 
-static u32 rtl_eri_read(struct rtl8169_private *tp, int addr, int type)
+static void rtl_eri_write(struct rtl8169_private *tp, int addr, u32 mask,
+			  u32 val)
+{
+	_rtl_eri_write(tp, addr, mask, val, ERIAR_EXGMAC);
+}
+
+static u32 _rtl_eri_read(struct rtl8169_private *tp, int addr, int type)
 {
 	RTL_W32(tp, ERIAR, ERIAR_READ_CMD | type | ERIAR_MASK_1111 | addr);
 
@@ -1076,13 +1084,30 @@ static u32 rtl_eri_read(struct rtl8169_private *tp, int addr, int type)
 		RTL_R32(tp, ERIDR) : ~0;
 }
 
+static u32 rtl_eri_read(struct rtl8169_private *tp, int addr)
+{
+	return _rtl_eri_read(tp, addr, ERIAR_EXGMAC);
+}
+
 static void rtl_w0w1_eri(struct rtl8169_private *tp, int addr, u32 mask, u32 p,
-			 u32 m, int type)
+			 u32 m)
 {
 	u32 val;
 
-	val = rtl_eri_read(tp, addr, type);
-	rtl_eri_write(tp, addr, mask, (val & ~m) | p, type);
+	val = rtl_eri_read(tp, addr);
+	rtl_eri_write(tp, addr, mask, (val & ~m) | p);
+}
+
+static void rtl_eri_set_bits(struct rtl8169_private *tp, int addr, u32 mask,
+			     u32 p)
+{
+	rtl_w0w1_eri(tp, addr, mask, p, 0);
+}
+
+static void rtl_eri_clear_bits(struct rtl8169_private *tp, int addr, u32 mask,
+			       u32 m)
+{
+	rtl_w0w1_eri(tp, addr, mask, 0, m);
 }
 
 static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
@@ -1094,7 +1119,7 @@ static u32 r8168dp_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
 
 static u32 r8168ep_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
 {
-	return rtl_eri_read(tp, reg, ERIAR_OOB);
+	return _rtl_eri_read(tp, reg, ERIAR_OOB);
 }
 
 static void r8168dp_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
@@ -1108,13 +1133,13 @@ static void r8168dp_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
 static void r8168ep_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
 			      u32 data)
 {
-	rtl_eri_write(tp, reg, ((u32)mask & 0x0f) << ERIAR_MASK_SHIFT,
-		      data, ERIAR_OOB);
+	_rtl_eri_write(tp, reg, ((u32)mask & 0x0f) << ERIAR_MASK_SHIFT,
+		       data, ERIAR_OOB);
 }
 
 static void r8168dp_oob_notify(struct rtl8169_private *tp, u8 cmd)
 {
-	rtl_eri_write(tp, 0xe8, ERIAR_MASK_0001, cmd, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0xe8, ERIAR_MASK_0001, cmd);
 
 	r8168dp_ocp_write(tp, 0x1, 0x30, 0x00000001);
 }
@@ -1250,19 +1275,10 @@ static bool r8168_check_dash(struct rtl8169_private *tp)
 	}
 }
 
-struct exgmac_reg {
-	u16 addr;
-	u16 mask;
-	u32 val;
-};
-
-static void rtl_write_exgmac_batch(struct rtl8169_private *tp,
-				   const struct exgmac_reg *r, int len)
+static void rtl_reset_packet_filter(struct rtl8169_private *tp)
 {
-	while (len-- > 0) {
-		rtl_eri_write(tp, r->addr, r->mask, r->val, ERIAR_EXGMAC);
-		r++;
-	}
+	rtl_eri_clear_bits(tp, 0xdc, ERIAR_MASK_0001, BIT(0));
+	rtl_eri_set_bits(tp, 0xdc, ERIAR_MASK_0001, BIT(0));
 }
 
 DECLARE_RTL_COND(rtl_efusear_cond)
@@ -1278,11 +1294,6 @@ static u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr)
 		RTL_R32(tp, EFUSEAR) & EFUSEAR_DATA_MASK : ~0;
 }
 
-static u16 rtl_get_events(struct rtl8169_private *tp)
-{
-	return RTL_R16(tp, IntrStatus);
-}
-
 static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
 {
 	RTL_W16(tp, IntrStatus, bits);
@@ -1291,6 +1302,7 @@ static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
 static void rtl_irq_disable(struct rtl8169_private *tp)
 {
 	RTL_W16(tp, IntrMask, 0);
+	tp->irq_enabled = 0;
 }
 
 #define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
@@ -1299,6 +1311,7 @@ static void rtl_irq_disable(struct rtl8169_private *tp)
 
 static void rtl_irq_enable(struct rtl8169_private *tp)
 {
+	tp->irq_enabled = 1;
 	RTL_W16(tp, IntrMask, tp->irq_mask);
 }
 
@@ -1313,7 +1326,7 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 static void rtl_link_chg_patch(struct rtl8169_private *tp)
 {
 	struct net_device *dev = tp->dev;
-	struct phy_device *phydev = dev->phydev;
+	struct phy_device *phydev = tp->phydev;
 
 	if (!netif_running(dev))
 		return;
@@ -1321,89 +1334,37 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 	if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_38) {
 		if (phydev->speed == SPEED_1000) {
-			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
-				      ERIAR_EXGMAC);
-			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
-				      ERIAR_EXGMAC);
+			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011);
+			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005);
 		} else if (phydev->speed == SPEED_100) {
-			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f,
-				      ERIAR_EXGMAC);
-			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
-				      ERIAR_EXGMAC);
+			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f);
+			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005);
 		} else {
-			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f,
-				      ERIAR_EXGMAC);
-			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x0000003f,
-				      ERIAR_EXGMAC);
+			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f);
+			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x0000003f);
 		}
-		/* Reset packet filter */
-		rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01,
-			     ERIAR_EXGMAC);
-		rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00,
-			     ERIAR_EXGMAC);
+		rtl_reset_packet_filter(tp);
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_35 ||
 		   tp->mac_version == RTL_GIGA_MAC_VER_36) {
 		if (phydev->speed == SPEED_1000) {
-			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
-				      ERIAR_EXGMAC);
-			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
-				      ERIAR_EXGMAC);
+			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011);
+			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005);
 		} else {
-			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f,
-				      ERIAR_EXGMAC);
-			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x0000003f,
-				      ERIAR_EXGMAC);
+			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f);
+			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x0000003f);
 		}
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_37) {
 		if (phydev->speed == SPEED_10) {
-			rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x4d02,
-				      ERIAR_EXGMAC);
-			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_0011, 0x0060,
-				      ERIAR_EXGMAC);
+			rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x4d02);
+			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_0011, 0x0060a);
 		} else {
-			rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000,
-				      ERIAR_EXGMAC);
+			rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000);
 		}
 	}
 }
 
 #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
 
-static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
-{
-	u8 options;
-	u32 wolopts = 0;
-
-	options = RTL_R8(tp, Config1);
-	if (!(options & PMEnable))
-		return 0;
-
-	options = RTL_R8(tp, Config3);
-	if (options & LinkUp)
-		wolopts |= WAKE_PHY;
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
-		if (rtl_eri_read(tp, 0xdc, ERIAR_EXGMAC) & MagicPacket_v2)
-			wolopts |= WAKE_MAGIC;
-		break;
-	default:
-		if (options & MagicPacket)
-			wolopts |= WAKE_MAGIC;
-		break;
-	}
-
-	options = RTL_R8(tp, Config5);
-	if (options & UWF)
-		wolopts |= WAKE_UCAST;
-	if (options & BWF)
-		wolopts |= WAKE_BCAST;
-	if (options & MWF)
-		wolopts |= WAKE_MCAST;
-
-	return wolopts;
-}
-
 static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
@@ -1431,30 +1392,18 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	};
 	u8 options;
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	rtl_unlock_config_regs(tp);
 
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+	if (rtl_is_8168evl_up(tp)) {
 		tmp = ARRAY_SIZE(cfg) - 1;
 		if (wolopts & WAKE_MAGIC)
-			rtl_w0w1_eri(tp,
-				     0x0dc,
-				     ERIAR_MASK_0100,
-				     MagicPacket_v2,
-				     0x0000,
-				     ERIAR_EXGMAC);
+			rtl_eri_set_bits(tp, 0x0dc, ERIAR_MASK_0100,
+					 MagicPacket_v2);
 		else
-			rtl_w0w1_eri(tp,
-				     0x0dc,
-				     ERIAR_MASK_0100,
-				     0x0000,
-				     MagicPacket_v2,
-				     ERIAR_EXGMAC);
-		break;
-	default:
+			rtl_eri_clear_bits(tp, 0x0dc, ERIAR_MASK_0100,
+					   MagicPacket_v2);
+	} else {
 		tmp = ARRAY_SIZE(cfg);
-		break;
 	}
 
 	for (i = 0; i < tmp; i++) {
@@ -1465,7 +1414,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	}
 
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_17:
+	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_17:
 		options = RTL_R8(tp, Config1) & ~PMEnable;
 		if (wolopts)
 			options |= PMEnable;
@@ -1479,7 +1428,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		break;
 	}
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+	rtl_lock_config_regs(tp);
 
 	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
 }
@@ -1508,11 +1457,6 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
-static const char *rtl_lookup_firmware_name(struct rtl8169_private *tp)
-{
-	return rtl_chip_infos[tp->mac_version].fw_name;
-}
-
 static void rtl8169_get_drvinfo(struct net_device *dev,
 				struct ethtool_drvinfo *info)
 {
@@ -1522,7 +1466,7 @@ static void rtl8169_get_drvinfo(struct net_device *dev,
 	strlcpy(info->driver, MODULENAME, sizeof(info->driver));
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 	BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version));
-	if (!IS_ERR_OR_NULL(rtl_fw))
+	if (rtl_fw)
 		strlcpy(info->fw_version, rtl_fw->version,
 			sizeof(info->fw_version));
 }
@@ -1840,18 +1784,16 @@ static const struct rtl_coalesce_info rtl_coalesce_info_8168_8136[] = {
 static const struct rtl_coalesce_info *rtl_coalesce_info(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	struct ethtool_link_ksettings ecmd;
 	const struct rtl_coalesce_info *ci;
-	int rc;
 
-	rc = phy_ethtool_get_link_ksettings(dev, &ecmd);
-	if (rc < 0)
-		return ERR_PTR(rc);
+	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
+		ci = rtl_coalesce_info_8169;
+	else
+		ci = rtl_coalesce_info_8168_8136;
 
-	for (ci = tp->coalesce_info; ci->speed != 0; ci++) {
-		if (ecmd.base.speed == ci->speed) {
+	for (; ci->speed; ci++) {
+		if (tp->phydev->speed == ci->speed)
 			return ci;
-		}
 	}
 
 	return ERR_PTR(-ELNRNG);
@@ -1987,6 +1929,188 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
+static int rtl_get_eee_supp(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		ret = phy_read_paged(phydev, 0x0a5c, 0x12);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl_get_eee_lpadv(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		ret = phy_read_paged(phydev, 0x0a5d, 0x11);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl_get_eee_adv(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		ret = phy_read_paged(phydev, 0x0a5d, 0x10);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl_set_eee_adv(struct rtl8169_private *tp, int val)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret = 0;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, val);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		phy_write_paged(phydev, 0x0a5d, 0x10, val);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl8169_get_eee(struct net_device *dev, struct ethtool_eee *data)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct device *d = tp_to_dev(tp);
+	int ret;
+
+	pm_runtime_get_noresume(d);
+
+	if (!pm_runtime_active(d)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	/* Get Supported EEE */
+	ret = rtl_get_eee_supp(tp);
+	if (ret < 0)
+		goto out;
+	data->supported = mmd_eee_cap_to_ethtool_sup_t(ret);
+
+	/* Get advertisement EEE */
+	ret = rtl_get_eee_adv(tp);
+	if (ret < 0)
+		goto out;
+	data->advertised = mmd_eee_adv_to_ethtool_adv_t(ret);
+	data->eee_enabled = !!data->advertised;
+
+	/* Get LP advertisement EEE */
+	ret = rtl_get_eee_lpadv(tp);
+	if (ret < 0)
+		goto out;
+	data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(ret);
+	data->eee_active = !!(data->advertised & data->lp_advertised);
+out:
+	pm_runtime_put_noidle(d);
+	return ret < 0 ? ret : 0;
+}
+
+static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct device *d = tp_to_dev(tp);
+	int old_adv, adv = 0, cap, ret;
+
+	pm_runtime_get_noresume(d);
+
+	if (!dev->phydev || !pm_runtime_active(d)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (dev->phydev->autoneg == AUTONEG_DISABLE ||
+	    dev->phydev->duplex != DUPLEX_FULL) {
+		ret = -EPROTONOSUPPORT;
+		goto out;
+	}
+
+	/* Get Supported EEE */
+	ret = rtl_get_eee_supp(tp);
+	if (ret < 0)
+		goto out;
+	cap = ret;
+
+	ret = rtl_get_eee_adv(tp);
+	if (ret < 0)
+		goto out;
+	old_adv = ret;
+
+	if (data->eee_enabled) {
+		adv = !data->advertised ? cap :
+		      ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap;
+		/* Mask prohibited EEE modes */
+		adv &= ~dev->phydev->eee_broken_modes;
+	}
+
+	if (old_adv != adv) {
+		ret = rtl_set_eee_adv(tp, adv);
+		if (ret < 0)
+			goto out;
+
+		/* Restart autonegotiation so the new modes get sent to the
+		 * link partner.
+		 */
+		ret = phy_restart_aneg(dev->phydev);
+	}
+
+out:
+	pm_runtime_put_noidle(d);
+	return ret < 0 ? ret : 0;
+}
+
 static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_drvinfo		= rtl8169_get_drvinfo,
 	.get_regs_len		= rtl8169_get_regs_len,
@@ -2003,10 +2127,20 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_ethtool_stats	= rtl8169_get_ethtool_stats,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.nway_reset		= phy_ethtool_nway_reset,
+	.get_eee		= rtl8169_get_eee,
+	.set_eee		= rtl8169_set_eee,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
+static void rtl_enable_eee(struct rtl8169_private *tp)
+{
+	int supported = rtl_get_eee_supp(tp);
+
+	if (supported > 0)
+		rtl_set_eee_adv(tp, supported);
+}
+
 static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 {
 	/*
@@ -2098,7 +2232,6 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 		{ 0xfc8, 0x100,	RTL_GIGA_MAC_VER_04 },
 		{ 0xfc8, 0x040,	RTL_GIGA_MAC_VER_03 },
 		{ 0xfc8, 0x008,	RTL_GIGA_MAC_VER_02 },
-		{ 0xfc8, 0x000,	RTL_GIGA_MAC_VER_01 },
 
 		/* Catch-all */
 		{ 0x000, 0x000,	RTL_GIGA_MAC_NONE   }
@@ -2127,8 +2260,8 @@ struct phy_reg {
 	u16 val;
 };
 
-static void rtl_writephy_batch(struct rtl8169_private *tp,
-			       const struct phy_reg *regs, int len)
+static void __rtl_writephy_batch(struct rtl8169_private *tp,
+				 const struct phy_reg *regs, int len)
 {
 	while (len-- > 0) {
 		rtl_writephy(tp, regs->reg, regs->val);
@@ -2136,266 +2269,59 @@ static void rtl_writephy_batch(struct rtl8169_private *tp,
 	}
 }
 
-#define PHY_READ		0x00000000
-#define PHY_DATA_OR		0x10000000
-#define PHY_DATA_AND		0x20000000
-#define PHY_BJMPN		0x30000000
-#define PHY_MDIO_CHG		0x40000000
-#define PHY_CLEAR_READCOUNT	0x70000000
-#define PHY_WRITE		0x80000000
-#define PHY_READCOUNT_EQ_SKIP	0x90000000
-#define PHY_COMP_EQ_SKIPN	0xa0000000
-#define PHY_COMP_NEQ_SKIPN	0xb0000000
-#define PHY_WRITE_PREVIOUS	0xc0000000
-#define PHY_SKIPN		0xd0000000
-#define PHY_DELAY_MS		0xe0000000
-
-struct fw_info {
-	u32	magic;
-	char	version[RTL_VER_SIZE];
-	__le32	fw_start;
-	__le32	fw_len;
-	u8	chksum;
-} __packed;
-
-#define FW_OPCODE_SIZE	sizeof(typeof(*((struct rtl_fw_phy_action *)0)->code))
-
-static bool rtl_fw_format_ok(struct rtl8169_private *tp, struct rtl_fw *rtl_fw)
-{
-	const struct firmware *fw = rtl_fw->fw;
-	struct fw_info *fw_info = (struct fw_info *)fw->data;
-	struct rtl_fw_phy_action *pa = &rtl_fw->phy_action;
-	char *version = rtl_fw->version;
-	bool rc = false;
-
-	if (fw->size < FW_OPCODE_SIZE)
-		goto out;
-
-	if (!fw_info->magic) {
-		size_t i, size, start;
-		u8 checksum = 0;
-
-		if (fw->size < sizeof(*fw_info))
-			goto out;
-
-		for (i = 0; i < fw->size; i++)
-			checksum += fw->data[i];
-		if (checksum != 0)
-			goto out;
-
-		start = le32_to_cpu(fw_info->fw_start);
-		if (start > fw->size)
-			goto out;
-
-		size = le32_to_cpu(fw_info->fw_len);
-		if (size > (fw->size - start) / FW_OPCODE_SIZE)
-			goto out;
-
-		memcpy(version, fw_info->version, RTL_VER_SIZE);
-
-		pa->code = (__le32 *)(fw->data + start);
-		pa->size = size;
-	} else {
-		if (fw->size % FW_OPCODE_SIZE)
-			goto out;
-
-		strlcpy(version, rtl_lookup_firmware_name(tp), RTL_VER_SIZE);
+#define rtl_writephy_batch(tp, a) __rtl_writephy_batch(tp, a, ARRAY_SIZE(a))
 
-		pa->code = (__le32 *)fw->data;
-		pa->size = fw->size / FW_OPCODE_SIZE;
+static void rtl_release_firmware(struct rtl8169_private *tp)
+{
+	if (tp->rtl_fw) {
+		rtl_fw_release_firmware(tp->rtl_fw);
+		kfree(tp->rtl_fw);
+		tp->rtl_fw = NULL;
 	}
-	version[RTL_VER_SIZE - 1] = 0;
-
-	rc = true;
-out:
-	return rc;
 }
 
-static bool rtl_fw_data_ok(struct rtl8169_private *tp, struct net_device *dev,
-			   struct rtl_fw_phy_action *pa)
+static void rtl_apply_firmware(struct rtl8169_private *tp)
 {
-	bool rc = false;
-	size_t index;
-
-	for (index = 0; index < pa->size; index++) {
-		u32 action = le32_to_cpu(pa->code[index]);
-		u32 regno = (action & 0x0fff0000) >> 16;
-
-		switch(action & 0xf0000000) {
-		case PHY_READ:
-		case PHY_DATA_OR:
-		case PHY_DATA_AND:
-		case PHY_MDIO_CHG:
-		case PHY_CLEAR_READCOUNT:
-		case PHY_WRITE:
-		case PHY_WRITE_PREVIOUS:
-		case PHY_DELAY_MS:
-			break;
-
-		case PHY_BJMPN:
-			if (regno > index) {
-				netif_err(tp, ifup, tp->dev,
-					  "Out of range of firmware\n");
-				goto out;
-			}
-			break;
-		case PHY_READCOUNT_EQ_SKIP:
-			if (index + 2 >= pa->size) {
-				netif_err(tp, ifup, tp->dev,
-					  "Out of range of firmware\n");
-				goto out;
-			}
-			break;
-		case PHY_COMP_EQ_SKIPN:
-		case PHY_COMP_NEQ_SKIPN:
-		case PHY_SKIPN:
-			if (index + 1 + regno >= pa->size) {
-				netif_err(tp, ifup, tp->dev,
-					  "Out of range of firmware\n");
-				goto out;
-			}
-			break;
-
-		default:
-			netif_err(tp, ifup, tp->dev,
-				  "Invalid action 0x%08x\n", action);
-			goto out;
-		}
-	}
-	rc = true;
-out:
-	return rc;
+	/* TODO: release firmware if rtl_fw_write_firmware signals failure. */
+	if (tp->rtl_fw)
+		rtl_fw_write_firmware(tp, tp->rtl_fw);
 }
 
-static int rtl_check_firmware(struct rtl8169_private *tp, struct rtl_fw *rtl_fw)
+static void rtl_apply_firmware_cond(struct rtl8169_private *tp, u8 reg, u16 val)
 {
-	struct net_device *dev = tp->dev;
-	int rc = -EINVAL;
-
-	if (!rtl_fw_format_ok(tp, rtl_fw)) {
-		netif_err(tp, ifup, dev, "invalid firmware\n");
-		goto out;
-	}
-
-	if (rtl_fw_data_ok(tp, dev, &rtl_fw->phy_action))
-		rc = 0;
-out:
-	return rc;
+	if (rtl_readphy(tp, reg) != val)
+		netif_warn(tp, hw, tp->dev, "chipset not ready for firmware\n");
+	else
+		rtl_apply_firmware(tp);
 }
 
-static void rtl_phy_write_fw(struct rtl8169_private *tp, struct rtl_fw *rtl_fw)
+static void rtl8168_config_eee_mac(struct rtl8169_private *tp)
 {
-	struct rtl_fw_phy_action *pa = &rtl_fw->phy_action;
-	struct mdio_ops org, *ops = &tp->mdio_ops;
-	u32 predata, count;
-	size_t index;
-
-	predata = count = 0;
-	org.write = ops->write;
-	org.read = ops->read;
-
-	for (index = 0; index < pa->size; ) {
-		u32 action = le32_to_cpu(pa->code[index]);
-		u32 data = action & 0x0000ffff;
-		u32 regno = (action & 0x0fff0000) >> 16;
-
-		if (!action)
-			break;
-
-		switch(action & 0xf0000000) {
-		case PHY_READ:
-			predata = rtl_readphy(tp, regno);
-			count++;
-			index++;
-			break;
-		case PHY_DATA_OR:
-			predata |= data;
-			index++;
-			break;
-		case PHY_DATA_AND:
-			predata &= data;
-			index++;
-			break;
-		case PHY_BJMPN:
-			index -= regno;
-			break;
-		case PHY_MDIO_CHG:
-			if (data == 0) {
-				ops->write = org.write;
-				ops->read = org.read;
-			} else if (data == 1) {
-				ops->write = mac_mcu_write;
-				ops->read = mac_mcu_read;
-			}
-
-			index++;
-			break;
-		case PHY_CLEAR_READCOUNT:
-			count = 0;
-			index++;
-			break;
-		case PHY_WRITE:
-			rtl_writephy(tp, regno, data);
-			index++;
-			break;
-		case PHY_READCOUNT_EQ_SKIP:
-			index += (count == data) ? 2 : 1;
-			break;
-		case PHY_COMP_EQ_SKIPN:
-			if (predata == data)
-				index += regno;
-			index++;
-			break;
-		case PHY_COMP_NEQ_SKIPN:
-			if (predata != data)
-				index += regno;
-			index++;
-			break;
-		case PHY_WRITE_PREVIOUS:
-			rtl_writephy(tp, regno, predata);
-			index++;
-			break;
-		case PHY_SKIPN:
-			index += regno + 1;
-			break;
-		case PHY_DELAY_MS:
-			mdelay(data);
-			index++;
-			break;
-
-		default:
-			BUG();
-		}
-	}
+	/* Adjust EEE LED frequency */
+	if (tp->mac_version != RTL_GIGA_MAC_VER_38)
+		RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
 
-	ops->write = org.write;
-	ops->read = org.read;
+	rtl_eri_set_bits(tp, 0x1b0, ERIAR_MASK_1111, 0x0003);
 }
 
-static void rtl_release_firmware(struct rtl8169_private *tp)
+static void rtl8168f_config_eee_phy(struct rtl8169_private *tp)
 {
-	if (!IS_ERR_OR_NULL(tp->rtl_fw)) {
-		release_firmware(tp->rtl_fw->fw);
-		kfree(tp->rtl_fw);
-	}
-	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
-}
+	struct phy_device *phydev = tp->phydev;
 
-static void rtl_apply_firmware(struct rtl8169_private *tp)
-{
-	struct rtl_fw *rtl_fw = tp->rtl_fw;
+	phy_write(phydev, 0x1f, 0x0007);
+	phy_write(phydev, 0x1e, 0x0020);
+	phy_set_bits(phydev, 0x15, BIT(8));
 
-	/* TODO: release firmware once rtl_phy_write_fw signals failures. */
-	if (!IS_ERR_OR_NULL(rtl_fw))
-		rtl_phy_write_fw(tp, rtl_fw);
+	phy_write(phydev, 0x1f, 0x0005);
+	phy_write(phydev, 0x05, 0x8b85);
+	phy_set_bits(phydev, 0x06, BIT(13));
+
+	phy_write(phydev, 0x1f, 0x0000);
 }
 
-static void rtl_apply_firmware_cond(struct rtl8169_private *tp, u8 reg, u16 val)
+static void rtl8168g_config_eee_phy(struct rtl8169_private *tp)
 {
-	if (rtl_readphy(tp, reg) != val)
-		netif_warn(tp, hw, tp->dev, "chipset not ready for firmware\n");
-	else
-		rtl_apply_firmware(tp);
+	phy_modify_paged(tp->phydev, 0x0a43, 0x11, 0, BIT(4));
 }
 
 static void rtl8169s_hw_phy_config(struct rtl8169_private *tp)
@@ -2462,7 +2388,7 @@ static void rtl8169s_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x00, 0x9200 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8169sb_hw_phy_config(struct rtl8169_private *tp)
@@ -2473,7 +2399,7 @@ static void rtl8169sb_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8169scd_hw_phy_config_quirk(struct rtl8169_private *tp)
@@ -2531,7 +2457,7 @@ static void rtl8169scd_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	rtl8169scd_hw_phy_config_quirk(tp);
 }
@@ -2586,7 +2512,7 @@ static void rtl8169sce_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8168bb_hw_phy_config(struct rtl8169_private *tp)
@@ -2599,7 +2525,7 @@ static void rtl8168bb_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0001);
 	rtl_patchphy(tp, 0x16, 1 << 0);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8168bef_hw_phy_config(struct rtl8169_private *tp)
@@ -2610,7 +2536,7 @@ static void rtl8168bef_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8168cp_1_hw_phy_config(struct rtl8169_private *tp)
@@ -2623,7 +2549,7 @@ static void rtl8168cp_1_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8168cp_2_hw_phy_config(struct rtl8169_private *tp)
@@ -2638,7 +2564,7 @@ static void rtl8168cp_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_patchphy(tp, 0x14, 1 << 5);
 	rtl_patchphy(tp, 0x0d, 1 << 5);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8168c_1_hw_phy_config(struct rtl8169_private *tp)
@@ -2663,7 +2589,7 @@ static void rtl8168c_1_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x09, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	rtl_patchphy(tp, 0x14, 1 << 5);
 	rtl_patchphy(tp, 0x0d, 1 << 5);
@@ -2690,7 +2616,7 @@ static void rtl8168c_2_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	rtl_patchphy(tp, 0x16, 1 << 0);
 	rtl_patchphy(tp, 0x14, 1 << 5);
@@ -2712,7 +2638,7 @@ static void rtl8168c_3_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	rtl_patchphy(tp, 0x16, 1 << 0);
 	rtl_patchphy(tp, 0x14, 1 << 5);
@@ -2725,50 +2651,59 @@ static void rtl8168c_4_hw_phy_config(struct rtl8169_private *tp)
 	rtl8168c_3_hw_phy_config(tp);
 }
 
-static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp)
-{
-	static const struct phy_reg phy_reg_init_0[] = {
-		/* Channel Estimation */
-		{ 0x1f, 0x0001 },
-		{ 0x06, 0x4064 },
-		{ 0x07, 0x2863 },
-		{ 0x08, 0x059c },
-		{ 0x09, 0x26b4 },
-		{ 0x0a, 0x6a19 },
-		{ 0x0b, 0xdcc8 },
-		{ 0x10, 0xf06d },
-		{ 0x14, 0x7f68 },
-		{ 0x18, 0x7fd9 },
-		{ 0x1c, 0xf0ff },
-		{ 0x1d, 0x3d9c },
-		{ 0x1f, 0x0003 },
-		{ 0x12, 0xf49f },
-		{ 0x13, 0x070b },
-		{ 0x1a, 0x05ad },
-		{ 0x14, 0x94c0 },
+static const struct phy_reg rtl8168d_1_phy_reg_init_0[] = {
+	/* Channel Estimation */
+	{ 0x1f, 0x0001 },
+	{ 0x06, 0x4064 },
+	{ 0x07, 0x2863 },
+	{ 0x08, 0x059c },
+	{ 0x09, 0x26b4 },
+	{ 0x0a, 0x6a19 },
+	{ 0x0b, 0xdcc8 },
+	{ 0x10, 0xf06d },
+	{ 0x14, 0x7f68 },
+	{ 0x18, 0x7fd9 },
+	{ 0x1c, 0xf0ff },
+	{ 0x1d, 0x3d9c },
+	{ 0x1f, 0x0003 },
+	{ 0x12, 0xf49f },
+	{ 0x13, 0x070b },
+	{ 0x1a, 0x05ad },
+	{ 0x14, 0x94c0 },
 
-		/*
-		 * Tx Error Issue
-		 * Enhance line driver power
-		 */
-		{ 0x1f, 0x0002 },
-		{ 0x06, 0x5561 },
-		{ 0x1f, 0x0005 },
-		{ 0x05, 0x8332 },
-		{ 0x06, 0x5561 },
+	/*
+	 * Tx Error Issue
+	 * Enhance line driver power
+	 */
+	{ 0x1f, 0x0002 },
+	{ 0x06, 0x5561 },
+	{ 0x1f, 0x0005 },
+	{ 0x05, 0x8332 },
+	{ 0x06, 0x5561 },
 
-		/*
-		 * Can not link to 1Gbps with bad cable
-		 * Decrease SNR threshold form 21.07dB to 19.04dB
-		 */
-		{ 0x1f, 0x0001 },
-		{ 0x17, 0x0cc0 },
+	/*
+	 * Can not link to 1Gbps with bad cable
+	 * Decrease SNR threshold form 21.07dB to 19.04dB
+	 */
+	{ 0x1f, 0x0001 },
+	{ 0x17, 0x0cc0 },
 
-		{ 0x1f, 0x0000 },
-		{ 0x0d, 0xf880 }
-	};
+	{ 0x1f, 0x0000 },
+	{ 0x0d, 0xf880 }
+};
 
-	rtl_writephy_batch(tp, phy_reg_init_0, ARRAY_SIZE(phy_reg_init_0));
+static const struct phy_reg rtl8168d_1_phy_reg_init_1[] = {
+	{ 0x1f, 0x0002 },
+	{ 0x05, 0x669a },
+	{ 0x1f, 0x0005 },
+	{ 0x05, 0x8330 },
+	{ 0x06, 0x669a },
+	{ 0x1f, 0x0002 }
+};
+
+static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp)
+{
+	rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_0);
 
 	/*
 	 * Rx Error Issue
@@ -2779,17 +2714,9 @@ static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x0c, 0xa200, 0x5d00);
 
 	if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) {
-		static const struct phy_reg phy_reg_init[] = {
-			{ 0x1f, 0x0002 },
-			{ 0x05, 0x669a },
-			{ 0x1f, 0x0005 },
-			{ 0x05, 0x8330 },
-			{ 0x06, 0x669a },
-			{ 0x1f, 0x0002 }
-		};
 		int val;
 
-		rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+		rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_1);
 
 		val = rtl_readphy(tp, 0x0d);
 
@@ -2815,7 +2742,7 @@ static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp)
 			{ 0x06, 0x6662 }
 		};
 
-		rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+		rtl_writephy_batch(tp, phy_reg_init);
 	}
 
 	/* RSET couple improve */
@@ -2838,62 +2765,12 @@ static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp)
 
 static void rtl8168d_2_hw_phy_config(struct rtl8169_private *tp)
 {
-	static const struct phy_reg phy_reg_init_0[] = {
-		/* Channel Estimation */
-		{ 0x1f, 0x0001 },
-		{ 0x06, 0x4064 },
-		{ 0x07, 0x2863 },
-		{ 0x08, 0x059c },
-		{ 0x09, 0x26b4 },
-		{ 0x0a, 0x6a19 },
-		{ 0x0b, 0xdcc8 },
-		{ 0x10, 0xf06d },
-		{ 0x14, 0x7f68 },
-		{ 0x18, 0x7fd9 },
-		{ 0x1c, 0xf0ff },
-		{ 0x1d, 0x3d9c },
-		{ 0x1f, 0x0003 },
-		{ 0x12, 0xf49f },
-		{ 0x13, 0x070b },
-		{ 0x1a, 0x05ad },
-		{ 0x14, 0x94c0 },
-
-		/*
-		 * Tx Error Issue
-		 * Enhance line driver power
-		 */
-		{ 0x1f, 0x0002 },
-		{ 0x06, 0x5561 },
-		{ 0x1f, 0x0005 },
-		{ 0x05, 0x8332 },
-		{ 0x06, 0x5561 },
-
-		/*
-		 * Can not link to 1Gbps with bad cable
-		 * Decrease SNR threshold form 21.07dB to 19.04dB
-		 */
-		{ 0x1f, 0x0001 },
-		{ 0x17, 0x0cc0 },
-
-		{ 0x1f, 0x0000 },
-		{ 0x0d, 0xf880 }
-	};
-
-	rtl_writephy_batch(tp, phy_reg_init_0, ARRAY_SIZE(phy_reg_init_0));
+	rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_0);
 
 	if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) {
-		static const struct phy_reg phy_reg_init[] = {
-			{ 0x1f, 0x0002 },
-			{ 0x05, 0x669a },
-			{ 0x1f, 0x0005 },
-			{ 0x05, 0x8330 },
-			{ 0x06, 0x669a },
-
-			{ 0x1f, 0x0002 }
-		};
 		int val;
 
-		rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+		rtl_writephy_batch(tp, rtl8168d_1_phy_reg_init_1);
 
 		val = rtl_readphy(tp, 0x0d);
 		if ((val & 0x00ff) != 0x006c) {
@@ -2918,7 +2795,7 @@ static void rtl8168d_2_hw_phy_config(struct rtl8169_private *tp)
 			{ 0x06, 0x2642 }
 		};
 
-		rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+		rtl_writephy_batch(tp, phy_reg_init);
 	}
 
 	/* Fine tune PLL performance */
@@ -2996,7 +2873,7 @@ static void rtl8168d_3_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8168d_4_hw_phy_config(struct rtl8169_private *tp)
@@ -3011,7 +2888,7 @@ static void rtl8168d_4_hw_phy_config(struct rtl8169_private *tp)
 		{ 0x1f, 0x0000 }
 	};
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 	rtl_patchphy(tp, 0x0d, 1 << 5);
 }
 
@@ -3047,7 +2924,7 @@ static void rtl8168e_1_hw_phy_config(struct rtl8169_private *tp)
 
 	rtl_apply_firmware(tp);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	/* DCO enable for 10M IDLE Power */
 	rtl_writephy(tp, 0x1f, 0x0007);
@@ -3095,14 +2972,11 @@ static void rtl_rar_exgmac_set(struct rtl8169_private *tp, u8 *addr)
 		addr[2] | (addr[3] << 8),
 		addr[4] | (addr[5] << 8)
 	};
-	const struct exgmac_reg e[] = {
-		{ .addr = 0xe0, ERIAR_MASK_1111, .val = w[0] | (w[1] << 16) },
-		{ .addr = 0xe4, ERIAR_MASK_1111, .val = w[2] },
-		{ .addr = 0xf0, ERIAR_MASK_1111, .val = w[0] << 16 },
-		{ .addr = 0xf4, ERIAR_MASK_1111, .val = w[1] | (w[2] << 16) }
-	};
 
-	rtl_write_exgmac_batch(tp, e, ARRAY_SIZE(e));
+	rtl_eri_write(tp, 0xe0, ERIAR_MASK_1111, w[0] | (w[1] << 16));
+	rtl_eri_write(tp, 0xe4, ERIAR_MASK_1111, w[2]);
+	rtl_eri_write(tp, 0xf0, ERIAR_MASK_1111, w[0] << 16);
+	rtl_eri_write(tp, 0xf4, ERIAR_MASK_1111, w[1] | (w[2] << 16));
 }
 
 static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp)
@@ -3136,7 +3010,7 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp)
 
 	rtl_apply_firmware(tp);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	/* For 4-corner performance improve */
 	rtl_writephy(tp, 0x1f, 0x0005);
@@ -3165,22 +3039,8 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x06, 0x4000, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* EEE setting */
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_1111, 0x0003, 0x0000, ERIAR_EXGMAC);
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b85);
-	rtl_w0w1_phy(tp, 0x06, 0x2000, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0004);
-	rtl_writephy(tp, 0x1f, 0x0007);
-	rtl_writephy(tp, 0x1e, 0x0020);
-	rtl_w0w1_phy(tp, 0x15, 0x0100, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0002);
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_writephy(tp, 0x0d, 0x0007);
-	rtl_writephy(tp, 0x0e, 0x003c);
-	rtl_writephy(tp, 0x0d, 0x4007);
-	rtl_writephy(tp, 0x0e, 0x0006);
-	rtl_writephy(tp, 0x0d, 0x0000);
+	rtl8168f_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 
 	/* Green feature */
 	rtl_writephy(tp, 0x1f, 0x0003);
@@ -3215,6 +3075,9 @@ static void rtl8168f_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x05, 0x8b86);
 	rtl_w0w1_phy(tp, 0x06, 0x0001, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
+
+	rtl8168f_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp)
@@ -3256,7 +3119,7 @@ static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp)
 
 	rtl_apply_firmware(tp);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	rtl8168f_hw_phy_config(tp);
 
@@ -3322,7 +3185,7 @@ static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x06, 0x4000, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 
 	/* Modify green table for giga */
 	rtl_writephy(tp, 0x1f, 0x0005);
@@ -3348,22 +3211,6 @@ static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x06, 0x8000, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* eee setting */
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0001, 0x00, 0x03, ERIAR_EXGMAC);
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b85);
-	rtl_w0w1_phy(tp, 0x06, 0x0000, 0x2000);
-	rtl_writephy(tp, 0x1f, 0x0004);
-	rtl_writephy(tp, 0x1f, 0x0007);
-	rtl_writephy(tp, 0x1e, 0x0020);
-	rtl_w0w1_phy(tp, 0x15, 0x0000, 0x0100);
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_writephy(tp, 0x0d, 0x0007);
-	rtl_writephy(tp, 0x0e, 0x003c);
-	rtl_writephy(tp, 0x0d, 0x4007);
-	rtl_writephy(tp, 0x0e, 0x0000);
-	rtl_writephy(tp, 0x0d, 0x0000);
-
 	/* Green feature */
 	rtl_writephy(tp, 0x1f, 0x0003);
 	rtl_w0w1_phy(tp, 0x19, 0x0000, 0x0001);
@@ -3371,52 +3218,57 @@ static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 }
 
+static void rtl8168g_disable_aldps(struct rtl8169_private *tp)
+{
+	phy_modify_paged(tp->phydev, 0x0a43, 0x10, BIT(2), 0);
+}
+
+static void rtl8168g_phy_adjust_10m_aldps(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+
+	phy_modify_paged(phydev, 0x0bcc, 0x14, BIT(8), 0);
+	phy_modify_paged(phydev, 0x0a44, 0x11, 0, BIT(7) | BIT(6));
+	phy_write(phydev, 0x1f, 0x0a43);
+	phy_write(phydev, 0x13, 0x8084);
+	phy_clear_bits(phydev, 0x14, BIT(14) | BIT(13));
+	phy_set_bits(phydev, 0x10, BIT(12) | BIT(1) | BIT(0));
+
+	phy_write(phydev, 0x1f, 0x0000);
+}
+
 static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
 {
+	int ret;
+
 	rtl_apply_firmware(tp);
 
-	rtl_writephy(tp, 0x1f, 0x0a46);
-	if (rtl_readphy(tp, 0x10) & 0x0100) {
-		rtl_writephy(tp, 0x1f, 0x0bcc);
-		rtl_w0w1_phy(tp, 0x12, 0x0000, 0x8000);
-	} else {
-		rtl_writephy(tp, 0x1f, 0x0bcc);
-		rtl_w0w1_phy(tp, 0x12, 0x8000, 0x0000);
-	}
+	ret = phy_read_paged(tp->phydev, 0x0a46, 0x10);
+	if (ret & BIT(8))
+		phy_modify_paged(tp->phydev, 0x0bcc, 0x12, BIT(15), 0);
+	else
+		phy_modify_paged(tp->phydev, 0x0bcc, 0x12, 0, BIT(15));
 
-	rtl_writephy(tp, 0x1f, 0x0a46);
-	if (rtl_readphy(tp, 0x13) & 0x0100) {
-		rtl_writephy(tp, 0x1f, 0x0c41);
-		rtl_w0w1_phy(tp, 0x15, 0x0002, 0x0000);
-	} else {
-		rtl_writephy(tp, 0x1f, 0x0c41);
-		rtl_w0w1_phy(tp, 0x15, 0x0000, 0x0002);
-	}
+	ret = phy_read_paged(tp->phydev, 0x0a46, 0x13);
+	if (ret & BIT(8))
+		phy_modify_paged(tp->phydev, 0x0c41, 0x12, 0, BIT(1));
+	else
+		phy_modify_paged(tp->phydev, 0x0c41, 0x12, BIT(1), 0);
 
 	/* Enable PHY auto speed down */
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x000c, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2));
 
-	rtl_writephy(tp, 0x1f, 0x0bcc);
-	rtl_w0w1_phy(tp, 0x14, 0x0100, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x00c0, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	rtl_writephy(tp, 0x13, 0x8084);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x6000);
-	rtl_w0w1_phy(tp, 0x10, 0x1003, 0x0000);
+	rtl8168g_phy_adjust_10m_aldps(tp);
 
 	/* EEE auto-fallback function */
-	rtl_writephy(tp, 0x1f, 0x0a4b);
-	rtl_w0w1_phy(tp, 0x11, 0x0004, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a4b, 0x11, 0, BIT(2));
 
 	/* Enable UC LPF tune function */
 	rtl_writephy(tp, 0x1f, 0x0a43);
 	rtl_writephy(tp, 0x13, 0x8012);
 	rtl_w0w1_phy(tp, 0x14, 0x8000, 0x0000);
 
-	rtl_writephy(tp, 0x1f, 0x0c42);
-	rtl_w0w1_phy(tp, 0x11, 0x4000, 0x2000);
+	phy_modify_paged(tp->phydev, 0x0c42, 0x11, BIT(13), BIT(14));
 
 	/* Improve SWR Efficiency */
 	rtl_writephy(tp, 0x1f, 0x0bcd);
@@ -3428,18 +3280,18 @@ static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x14, 0x1065);
 	rtl_writephy(tp, 0x14, 0x9065);
 	rtl_writephy(tp, 0x14, 0x1065);
-
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
 	rtl_writephy(tp, 0x1f, 0x0000);
+
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168g_2_hw_phy_config(struct rtl8169_private *tp)
 {
 	rtl_apply_firmware(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp)
@@ -3513,14 +3365,10 @@ static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 
 	/* enable GPHY 10M */
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x0800, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(11));
 
 	/* SAR ADC performance */
-	rtl_writephy(tp, 0x1f, 0x0bca);
-	rtl_w0w1_phy(tp, 0x17, 0x4000, 0x3000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0bca, 0x17, BIT(12) | BIT(13), BIT(14));
 
 	rtl_writephy(tp, 0x1f, 0x0a43);
 	rtl_writephy(tp, 0x13, 0x803f);
@@ -3540,16 +3388,11 @@ static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 
 	/* disable phy pfm mode */
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x0000, 0x0080);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a44, 0x11, BIT(7), 0);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp)
@@ -3575,9 +3418,7 @@ static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 
 	/* enable GPHY 10M */
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x0800, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(11));
 
 	r8168_mac_ocp_write(tp, 0xdd02, 0x807d);
 	data = r8168_mac_ocp_read(tp, 0xdd02);
@@ -3613,40 +3454,22 @@ static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 
 	/* disable phy pfm mode */
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x0000, 0x0080);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a44, 0x11, BIT(7), 0);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168ep_1_hw_phy_config(struct rtl8169_private *tp)
 {
 	/* Enable PHY auto speed down */
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x000c, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2));
 
-	/* patch 10M & ALDPS */
-	rtl_writephy(tp, 0x1f, 0x0bcc);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x0100);
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x00c0, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	rtl_writephy(tp, 0x13, 0x8084);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x6000);
-	rtl_w0w1_phy(tp, 0x10, 0x1003, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_phy_adjust_10m_aldps(tp);
 
 	/* Enable EEE auto-fallback function */
-	rtl_writephy(tp, 0x1f, 0x0a4b);
-	rtl_w0w1_phy(tp, 0x11, 0x0004, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0a4b, 0x11, 0, BIT(2));
 
 	/* Enable UC LPF tune function */
 	rtl_writephy(tp, 0x1f, 0x0a43);
@@ -3655,30 +3478,16 @@ static void rtl8168ep_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 
 	/* set rg_sel_sdm_rate */
-	rtl_writephy(tp, 0x1f, 0x0c42);
-	rtl_w0w1_phy(tp, 0x11, 0x4000, 0x2000);
-	rtl_writephy(tp, 0x1f, 0x0000);
-
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
+	phy_modify_paged(tp->phydev, 0x0c42, 0x11, BIT(13), BIT(14));
 
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168ep_2_hw_phy_config(struct rtl8169_private *tp)
 {
-	/* patch 10M & ALDPS */
-	rtl_writephy(tp, 0x1f, 0x0bcc);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x0100);
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x00c0, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	rtl_writephy(tp, 0x13, 0x8084);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x6000);
-	rtl_w0w1_phy(tp, 0x10, 0x1003, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_phy_adjust_10m_aldps(tp);
 
 	/* Enable UC LPF tune function */
 	rtl_writephy(tp, 0x1f, 0x0a43);
@@ -3687,9 +3496,7 @@ static void rtl8168ep_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 
 	/* Set rg_sel_sdm_rate */
-	rtl_writephy(tp, 0x1f, 0x0c42);
-	rtl_w0w1_phy(tp, 0x11, 0x4000, 0x2000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	phy_modify_paged(tp->phydev, 0x0c42, 0x11, BIT(13), BIT(14));
 
 	/* Channel estimation parameters */
 	rtl_writephy(tp, 0x1f, 0x0a43);
@@ -3750,12 +3557,9 @@ static void rtl8168ep_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x14, 0x1065);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8102e_hw_phy_config(struct rtl8169_private *tp)
@@ -3772,7 +3576,7 @@ static void rtl8102e_hw_phy_config(struct rtl8169_private *tp)
 	rtl_patchphy(tp, 0x19, 1 << 13);
 	rtl_patchphy(tp, 0x10, 1 << 15);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8105e_hw_phy_config(struct rtl8169_private *tp)
@@ -3798,7 +3602,7 @@ static void rtl8105e_hw_phy_config(struct rtl8169_private *tp)
 
 	rtl_apply_firmware(tp);
 
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_writephy_batch(tp, phy_reg_init);
 }
 
 static void rtl8402_hw_phy_config(struct rtl8169_private *tp)
@@ -3811,7 +3615,7 @@ static void rtl8402_hw_phy_config(struct rtl8169_private *tp)
 	rtl_apply_firmware(tp);
 
 	/* EEE setting */
-	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0004);
 	rtl_writephy(tp, 0x10, 0x401f);
 	rtl_writephy(tp, 0x19, 0x7030);
@@ -3834,139 +3638,72 @@ static void rtl8106e_hw_phy_config(struct rtl8169_private *tp)
 
 	rtl_apply_firmware(tp);
 
-	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_writephy_batch(tp, phy_reg_init, ARRAY_SIZE(phy_reg_init));
+	rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000);
+	rtl_writephy_batch(tp, phy_reg_init);
 
-	rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000);
 }
 
 static void rtl_hw_phy_config(struct net_device *dev)
 {
+	static const rtl_generic_fct phy_configs[] = {
+		/* PCI devices. */
+		[RTL_GIGA_MAC_VER_02] = rtl8169s_hw_phy_config,
+		[RTL_GIGA_MAC_VER_03] = rtl8169s_hw_phy_config,
+		[RTL_GIGA_MAC_VER_04] = rtl8169sb_hw_phy_config,
+		[RTL_GIGA_MAC_VER_05] = rtl8169scd_hw_phy_config,
+		[RTL_GIGA_MAC_VER_06] = rtl8169sce_hw_phy_config,
+		/* PCI-E devices. */
+		[RTL_GIGA_MAC_VER_07] = rtl8102e_hw_phy_config,
+		[RTL_GIGA_MAC_VER_08] = rtl8102e_hw_phy_config,
+		[RTL_GIGA_MAC_VER_09] = rtl8102e_hw_phy_config,
+		[RTL_GIGA_MAC_VER_10] = NULL,
+		[RTL_GIGA_MAC_VER_11] = rtl8168bb_hw_phy_config,
+		[RTL_GIGA_MAC_VER_12] = rtl8168bef_hw_phy_config,
+		[RTL_GIGA_MAC_VER_13] = NULL,
+		[RTL_GIGA_MAC_VER_14] = NULL,
+		[RTL_GIGA_MAC_VER_15] = NULL,
+		[RTL_GIGA_MAC_VER_16] = NULL,
+		[RTL_GIGA_MAC_VER_17] = rtl8168bef_hw_phy_config,
+		[RTL_GIGA_MAC_VER_18] = rtl8168cp_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_19] = rtl8168c_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_20] = rtl8168c_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_21] = rtl8168c_3_hw_phy_config,
+		[RTL_GIGA_MAC_VER_22] = rtl8168c_4_hw_phy_config,
+		[RTL_GIGA_MAC_VER_23] = rtl8168cp_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_24] = rtl8168cp_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_25] = rtl8168d_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_26] = rtl8168d_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_27] = rtl8168d_3_hw_phy_config,
+		[RTL_GIGA_MAC_VER_28] = rtl8168d_4_hw_phy_config,
+		[RTL_GIGA_MAC_VER_29] = rtl8105e_hw_phy_config,
+		[RTL_GIGA_MAC_VER_30] = rtl8105e_hw_phy_config,
+		[RTL_GIGA_MAC_VER_31] = NULL,
+		[RTL_GIGA_MAC_VER_32] = rtl8168e_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_33] = rtl8168e_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_34] = rtl8168e_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_35] = rtl8168f_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_36] = rtl8168f_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_37] = rtl8402_hw_phy_config,
+		[RTL_GIGA_MAC_VER_38] = rtl8411_hw_phy_config,
+		[RTL_GIGA_MAC_VER_39] = rtl8106e_hw_phy_config,
+		[RTL_GIGA_MAC_VER_40] = rtl8168g_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_41] = NULL,
+		[RTL_GIGA_MAC_VER_42] = rtl8168g_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_43] = rtl8168g_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_44] = rtl8168g_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_45] = rtl8168h_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_46] = rtl8168h_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_47] = rtl8168h_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_48] = rtl8168h_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_49] = rtl8168ep_1_hw_phy_config,
+		[RTL_GIGA_MAC_VER_50] = rtl8168ep_2_hw_phy_config,
+		[RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config,
+	};
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_01:
-		break;
-	case RTL_GIGA_MAC_VER_02:
-	case RTL_GIGA_MAC_VER_03:
-		rtl8169s_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_04:
-		rtl8169sb_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_05:
-		rtl8169scd_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_06:
-		rtl8169sce_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_07:
-	case RTL_GIGA_MAC_VER_08:
-	case RTL_GIGA_MAC_VER_09:
-		rtl8102e_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_11:
-		rtl8168bb_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_12:
-		rtl8168bef_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_17:
-		rtl8168bef_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_18:
-		rtl8168cp_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_19:
-		rtl8168c_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_20:
-		rtl8168c_2_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_21:
-		rtl8168c_3_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_22:
-		rtl8168c_4_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_23:
-	case RTL_GIGA_MAC_VER_24:
-		rtl8168cp_2_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_25:
-		rtl8168d_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_26:
-		rtl8168d_2_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_27:
-		rtl8168d_3_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_28:
-		rtl8168d_4_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_29:
-	case RTL_GIGA_MAC_VER_30:
-		rtl8105e_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_31:
-		/* None. */
-		break;
-	case RTL_GIGA_MAC_VER_32:
-	case RTL_GIGA_MAC_VER_33:
-		rtl8168e_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_34:
-		rtl8168e_2_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_35:
-		rtl8168f_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_36:
-		rtl8168f_2_hw_phy_config(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_37:
-		rtl8402_hw_phy_config(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_38:
-		rtl8411_hw_phy_config(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_39:
-		rtl8106e_hw_phy_config(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_40:
-		rtl8168g_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_42:
-	case RTL_GIGA_MAC_VER_43:
-	case RTL_GIGA_MAC_VER_44:
-		rtl8168g_2_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_45:
-	case RTL_GIGA_MAC_VER_47:
-		rtl8168h_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_46:
-	case RTL_GIGA_MAC_VER_48:
-		rtl8168h_2_hw_phy_config(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_49:
-		rtl8168ep_1_hw_phy_config(tp);
-		break;
-	case RTL_GIGA_MAC_VER_50:
-	case RTL_GIGA_MAC_VER_51:
-		rtl8168ep_2_hw_phy_config(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_41:
-	default:
-		break;
-	}
+	if (phy_configs[tp->mac_version])
+		phy_configs[tp->mac_version](tp);
 }
 
 static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
@@ -3975,12 +3712,6 @@ static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
 		schedule_work(&tp->wk.work);
 }
 
-static bool rtl_tbi_enabled(struct rtl8169_private *tp)
-{
-	return (tp->mac_version == RTL_GIGA_MAC_VER_01) &&
-	       (RTL_R8(tp, PHYstatus) & TBI_Enable);
-}
-
 static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 {
 	rtl_hw_phy_config(dev);
@@ -3994,24 +3725,16 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 	}
 
 	/* We may have called phy_speed_down before */
-	phy_speed_up(dev->phydev);
+	phy_speed_up(tp->phydev);
 
-	genphy_soft_reset(dev->phydev);
-
-	/* It was reported that several chips end up with 10MBit/Half on a
-	 * 1GBit link after resuming from S3. For whatever reason the PHY on
-	 * these chips doesn't properly start a renegotiation when soft-reset.
-	 * Explicitly requesting a renegotiation fixes this.
-	 */
-	if (dev->phydev->autoneg == AUTONEG_ENABLE)
-		phy_restart_aneg(dev->phydev);
+	genphy_soft_reset(tp->phydev);
 }
 
 static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
 {
 	rtl_lock_work(tp);
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	rtl_unlock_config_regs(tp);
 
 	RTL_W32(tp, MAC4, addr[4] | addr[5] << 8);
 	RTL_R32(tp, MAC4);
@@ -4022,7 +3745,7 @@ static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
 	if (tp->mac_version == RTL_GIGA_MAC_VER_34)
 		rtl_rar_exgmac_set(tp, addr);
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+	rtl_lock_config_regs(tp);
 
 	rtl_unlock_work(tp);
 }
@@ -4049,35 +3772,12 @@ static int rtl_set_mac_address(struct net_device *dev, void *p)
 
 static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
+	struct rtl8169_private *tp = netdev_priv(dev);
+
 	if (!netif_running(dev))
 		return -ENODEV;
 
-	return phy_mii_ioctl(dev->phydev, ifr, cmd);
-}
-
-static void rtl_init_mdio_ops(struct rtl8169_private *tp)
-{
-	struct mdio_ops *ops = &tp->mdio_ops;
-
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_27:
-		ops->write	= r8168dp_1_mdio_write;
-		ops->read	= r8168dp_1_mdio_read;
-		break;
-	case RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		ops->write	= r8168dp_2_mdio_write;
-		ops->read	= r8168dp_2_mdio_read;
-		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
-		ops->write	= r8168g_mdio_write;
-		ops->read	= r8168g_mdio_read;
-		break;
-	default:
-		ops->write	= r8169_mdio_write;
-		ops->read	= r8169_mdio_read;
-		break;
-	}
+	return phy_mii_ioctl(tp->phydev, ifr, cmd);
 }
 
 static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
@@ -4099,23 +3799,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 	}
 }
 
-static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
-{
-	struct phy_device *phydev;
-
-	if (!__rtl8169_get_wol(tp))
-		return false;
-
-	/* phydev may not be attached to netdevice */
-	phydev = mdiobus_get_phy(tp->mii_bus, 0);
-
-	phy_speed_down(phydev, false);
-	rtl_wol_suspend_quirk(tp);
-
-	return true;
-}
-
-static void r8168_pll_power_down(struct rtl8169_private *tp)
+static void rtl_pll_power_down(struct rtl8169_private *tp)
 {
 	if (r8168_check_dash(tp))
 		return;
@@ -4124,8 +3808,11 @@ static void r8168_pll_power_down(struct rtl8169_private *tp)
 	    tp->mac_version == RTL_GIGA_MAC_VER_33)
 		rtl_ephy_write(tp, 0x19, 0xff64);
 
-	if (rtl_wol_pll_power_down(tp))
+	if (device_may_wakeup(tp_to_dev(tp))) {
+		phy_speed_down(tp->phydev, false);
+		rtl_wol_suspend_quirk(tp);
 		return;
+	}
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
@@ -4144,14 +3831,15 @@ static void r8168_pll_power_down(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_40:
 	case RTL_GIGA_MAC_VER_41:
 	case RTL_GIGA_MAC_VER_49:
-		rtl_w0w1_eri(tp, 0x1a8, ERIAR_MASK_1111, 0x00000000,
-			     0xfc000000, ERIAR_EXGMAC);
+		rtl_eri_clear_bits(tp, 0x1a8, ERIAR_MASK_1111, 0xfc000000);
 		RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80);
 		break;
+	default:
+		break;
 	}
 }
 
-static void r8168_pll_power_up(struct rtl8169_private *tp)
+static void rtl_pll_power_up(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
@@ -4173,42 +3861,21 @@ static void r8168_pll_power_up(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_41:
 	case RTL_GIGA_MAC_VER_49:
 		RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0);
-		rtl_w0w1_eri(tp, 0x1a8, ERIAR_MASK_1111, 0xfc000000,
-			     0x00000000, ERIAR_EXGMAC);
+		rtl_eri_set_bits(tp, 0x1a8, ERIAR_MASK_1111, 0xfc000000);
+		break;
+	default:
 		break;
 	}
 
-	phy_resume(tp->dev->phydev);
+	phy_resume(tp->phydev);
 	/* give MAC/PHY some time to resume */
 	msleep(20);
 }
 
-static void rtl_pll_power_down(struct rtl8169_private *tp)
-{
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
-	case RTL_GIGA_MAC_VER_13 ... RTL_GIGA_MAC_VER_15:
-		break;
-	default:
-		r8168_pll_power_down(tp);
-	}
-}
-
-static void rtl_pll_power_up(struct rtl8169_private *tp)
-{
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
-	case RTL_GIGA_MAC_VER_13 ... RTL_GIGA_MAC_VER_15:
-		break;
-	default:
-		r8168_pll_power_up(tp);
-	}
-}
-
 static void rtl_init_rxcfg(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
 	case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
 		RTL_W32(tp, RxConfig, RX_FIFO_THRESH | RX_DMA_BURST);
 		break;
@@ -4231,24 +3898,6 @@ static void rtl8169_init_ring_indexes(struct rtl8169_private *tp)
 	tp->dirty_tx = tp->cur_tx = tp->cur_rx = 0;
 }
 
-static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
-{
-	if (tp->jumbo_ops.enable) {
-		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
-		tp->jumbo_ops.enable(tp);
-		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
-	}
-}
-
-static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
-{
-	if (tp->jumbo_ops.disable) {
-		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
-		tp->jumbo_ops.disable(tp);
-		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
-	}
-}
-
 static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0);
@@ -4315,55 +3964,56 @@ static void r8168b_1_hw_jumbo_disable(struct rtl8169_private *tp)
 	RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~(1 << 0));
 }
 
-static void rtl_init_jumbo_ops(struct rtl8169_private *tp)
+static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
 {
-	struct jumbo_ops *ops = &tp->jumbo_ops;
-
+	rtl_unlock_config_regs(tp);
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_11:
-		ops->disable	= r8168b_0_hw_jumbo_disable;
-		ops->enable	= r8168b_0_hw_jumbo_enable;
+		r8168b_0_hw_jumbo_enable(tp);
 		break;
 	case RTL_GIGA_MAC_VER_12:
 	case RTL_GIGA_MAC_VER_17:
-		ops->disable	= r8168b_1_hw_jumbo_disable;
-		ops->enable	= r8168b_1_hw_jumbo_enable;
+		r8168b_1_hw_jumbo_enable(tp);
 		break;
-	case RTL_GIGA_MAC_VER_18: /* Wild guess. Needs info from Realtek. */
-	case RTL_GIGA_MAC_VER_19:
-	case RTL_GIGA_MAC_VER_20:
-	case RTL_GIGA_MAC_VER_21: /* Wild guess. Needs info from Realtek. */
-	case RTL_GIGA_MAC_VER_22:
-	case RTL_GIGA_MAC_VER_23:
-	case RTL_GIGA_MAC_VER_24:
-	case RTL_GIGA_MAC_VER_25:
-	case RTL_GIGA_MAC_VER_26:
-		ops->disable	= r8168c_hw_jumbo_disable;
-		ops->enable	= r8168c_hw_jumbo_enable;
+	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_26:
+		r8168c_hw_jumbo_enable(tp);
 		break;
-	case RTL_GIGA_MAC_VER_27:
-	case RTL_GIGA_MAC_VER_28:
-		ops->disable	= r8168dp_hw_jumbo_disable;
-		ops->enable	= r8168dp_hw_jumbo_enable;
+	case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28:
+		r8168dp_hw_jumbo_enable(tp);
 		break;
-	case RTL_GIGA_MAC_VER_31: /* Wild guess. Needs info from Realtek. */
-	case RTL_GIGA_MAC_VER_32:
-	case RTL_GIGA_MAC_VER_33:
-	case RTL_GIGA_MAC_VER_34:
-		ops->disable	= r8168e_hw_jumbo_disable;
-		ops->enable	= r8168e_hw_jumbo_enable;
+	case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_34:
+		r8168e_hw_jumbo_enable(tp);
 		break;
+	default:
+		break;
+	}
+	rtl_lock_config_regs(tp);
+}
 
-	/*
-	 * No action needed for jumbo frames with 8169.
-	 * No jumbo for 810x at all.
-	 */
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
+{
+	rtl_unlock_config_regs(tp);
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_11:
+		r8168b_0_hw_jumbo_disable(tp);
+		break;
+	case RTL_GIGA_MAC_VER_12:
+	case RTL_GIGA_MAC_VER_17:
+		r8168b_1_hw_jumbo_disable(tp);
+		break;
+	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_26:
+		r8168c_hw_jumbo_disable(tp);
+		break;
+	case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28:
+		r8168dp_hw_jumbo_disable(tp);
+		break;
+	case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_34:
+		r8168e_hw_jumbo_disable(tp);
+		break;
 	default:
-		ops->disable	= NULL;
-		ops->enable	= NULL;
 		break;
 	}
+	rtl_lock_config_regs(tp);
 }
 
 DECLARE_RTL_COND(rtl_chipcmd_cond)
@@ -4378,48 +4028,31 @@ static void rtl_hw_reset(struct rtl8169_private *tp)
 	rtl_udelay_loop_wait_low(tp, &rtl_chipcmd_cond, 100, 100);
 }
 
-static void rtl_request_uncached_firmware(struct rtl8169_private *tp)
+static void rtl_request_firmware(struct rtl8169_private *tp)
 {
 	struct rtl_fw *rtl_fw;
-	const char *name;
-	int rc = -ENOMEM;
 
-	name = rtl_lookup_firmware_name(tp);
-	if (!name)
-		goto out_no_firmware;
+	/* firmware loaded already or no firmware available */
+	if (tp->rtl_fw || !tp->fw_name)
+		return;
 
 	rtl_fw = kzalloc(sizeof(*rtl_fw), GFP_KERNEL);
-	if (!rtl_fw)
-		goto err_warn;
-
-	rc = request_firmware(&rtl_fw->fw, name, tp_to_dev(tp));
-	if (rc < 0)
-		goto err_free;
-
-	rc = rtl_check_firmware(tp, rtl_fw);
-	if (rc < 0)
-		goto err_release_firmware;
+	if (!rtl_fw) {
+		netif_warn(tp, ifup, tp->dev, "Unable to load firmware, out of memory\n");
+		return;
+	}
 
-	tp->rtl_fw = rtl_fw;
-out:
-	return;
-
-err_release_firmware:
-	release_firmware(rtl_fw->fw);
-err_free:
-	kfree(rtl_fw);
-err_warn:
-	netif_warn(tp, ifup, tp->dev, "unable to load firmware patch %s (%d)\n",
-		   name, rc);
-out_no_firmware:
-	tp->rtl_fw = NULL;
-	goto out;
-}
+	rtl_fw->phy_write = rtl_writephy;
+	rtl_fw->phy_read = rtl_readphy;
+	rtl_fw->mac_mcu_write = mac_mcu_write;
+	rtl_fw->mac_mcu_read = mac_mcu_read;
+	rtl_fw->fw_name = tp->fw_name;
+	rtl_fw->dev = tp_to_dev(tp);
 
-static void rtl_request_firmware(struct rtl8169_private *tp)
-{
-	if (IS_ERR(tp->rtl_fw))
-		rtl_request_uncached_firmware(tp);
+	if (rtl_fw_request_firmware(rtl_fw))
+		kfree(rtl_fw);
+	else
+		tp->rtl_fw = rtl_fw;
 }
 
 static void rtl_rx_close(struct rtl8169_private *tp)
@@ -4469,8 +4102,7 @@ static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
 	u32 val = TX_DMA_BURST << TxDMAShift |
 		  InterFrameGap << TxInterFrameGapShift;
 
-	if (tp->mac_version >= RTL_GIGA_MAC_VER_34 &&
-	    tp->mac_version != RTL_GIGA_MAC_VER_39)
+	if (rtl_is_8168evl_up(tp))
 		val |= TXCFG_AUTO_FIFO;
 
 	RTL_W32(tp, TxConfig, val);
@@ -4564,57 +4196,6 @@ static void rtl_set_rx_mode(struct net_device *dev)
 	RTL_W32(tp, RxConfig, tmp);
 }
 
-static void rtl_hw_start(struct  rtl8169_private *tp)
-{
-	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
-
-	tp->hw_start(tp);
-
-	rtl_set_rx_max_size(tp);
-	rtl_set_rx_tx_desc_registers(tp);
-	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
-
-	/* Initially a 10 us delay. Turned it into a PCI commit. - FR */
-	RTL_R8(tp, IntrMask);
-	RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
-	rtl_init_rxcfg(tp);
-	rtl_set_tx_config_registers(tp);
-
-	rtl_set_rx_mode(tp->dev);
-	/* no early-rx interrupts */
-	RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
-	rtl_irq_enable(tp);
-}
-
-static void rtl_hw_start_8169(struct rtl8169_private *tp)
-{
-	if (tp->mac_version == RTL_GIGA_MAC_VER_05)
-		pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
-
-	RTL_W8(tp, EarlyTxThres, NoEarlyTx);
-
-	tp->cp_cmd |= PCIMulRW;
-
-	if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_03) {
-		netif_dbg(tp, drv, tp->dev,
-			  "Set MAC Reg C+CR Offset 0xe0. Bit 3 and Bit 14 MUST be 1\n");
-		tp->cp_cmd |= (1 << 14);
-	}
-
-	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
-
-	rtl8169_set_magic_reg(tp, tp->mac_version);
-
-	/*
-	 * Undocumented corner. Supposedly:
-	 * (TxTimer << 12) | (TxPackets << 8) | (RxTimer << 4) | RxPackets
-	 */
-	RTL_W16(tp, IntrMitigate, 0x0000);
-
-	RTL_W32(tp, RxMissed, 0);
-}
-
 DECLARE_RTL_COND(rtl_csiar_cond)
 {
 	return RTL_R32(tp, CSIAR) & CSIAR_FLAG;
@@ -4672,8 +4253,8 @@ struct ephy_info {
 	u16 bits;
 };
 
-static void rtl_ephy_init(struct rtl8169_private *tp, const struct ephy_info *e,
-			  int len)
+static void __rtl_ephy_init(struct rtl8169_private *tp,
+			    const struct ephy_info *e, int len)
 {
 	u16 w;
 
@@ -4684,6 +4265,8 @@ static void rtl_ephy_init(struct rtl8169_private *tp, const struct ephy_info *e,
 	}
 }
 
+#define rtl_ephy_init(tp, a) __rtl_ephy_init(tp, a, ARRAY_SIZE(a))
+
 static void rtl_disable_clock_request(struct rtl8169_private *tp)
 {
 	pcie_capability_clear_word(tp->pci_dev, PCI_EXP_LNKCTL,
@@ -4696,23 +4279,16 @@ static void rtl_enable_clock_request(struct rtl8169_private *tp)
 				 PCI_EXP_LNKCTL_CLKREQ_EN);
 }
 
-static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable)
+static void rtl_pcie_state_l2l3_disable(struct rtl8169_private *tp)
 {
-	u8 data;
-
-	data = RTL_R8(tp, Config3);
-
-	if (enable)
-		data |= Rdy_to_L23;
-	else
-		data &= ~Rdy_to_L23;
-
-	RTL_W8(tp, Config3, data);
+	/* work around an issue when PCI reset occurs during L2/L3 state */
+	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Rdy_to_L23);
 }
 
 static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 {
-	if (enable) {
+	/* Don't enable ASPM in the chip if OS can't control ASPM */
+	if (enable && tp->aspm_manageable) {
 		RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
 	} else {
@@ -4723,13 +4299,28 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 	udelay(10);
 }
 
+static void rtl_set_fifo_size(struct rtl8169_private *tp, u16 rx_stat,
+			      u16 tx_stat, u16 rx_dyn, u16 tx_dyn)
+{
+	/* Usage of dynamic vs. static FIFO is controlled by bit
+	 * TXCFG_AUTO_FIFO. Exact meaning of FIFO values isn't known.
+	 */
+	rtl_eri_write(tp, 0xc8, ERIAR_MASK_1111, (rx_stat << 16) | rx_dyn);
+	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, (tx_stat << 16) | tx_dyn);
+}
+
+static void rtl8168g_set_pause_thresholds(struct rtl8169_private *tp,
+					  u8 low, u8 high)
+{
+	/* FIFO thresholds for pause flow control */
+	rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, low);
+	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, high);
+}
+
 static void rtl_hw_start_8168bb(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
 
-	tp->cp_cmd &= CPCMD_QUIRK_MASK;
-	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
-
 	if (tp->dev->mtu <= ETH_DATA_LEN) {
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B |
 					 PCI_EXP_DEVCTL_NOSNOOP_EN);
@@ -4740,8 +4331,6 @@ static void rtl_hw_start_8168bef(struct rtl8169_private *tp)
 {
 	rtl_hw_start_8168bb(tp);
 
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
 	RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~(1 << 0));
 }
 
@@ -4755,9 +4344,6 @@ static void __rtl_hw_start_8168cp(struct rtl8169_private *tp)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
 	rtl_disable_clock_request(tp);
-
-	tp->cp_cmd &= CPCMD_QUIRK_MASK;
-	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 }
 
 static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
@@ -4772,7 +4358,7 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
 
 	rtl_set_def_aspm_entry_latency(tp);
 
-	rtl_ephy_init(tp, e_info_8168cp, ARRAY_SIZE(e_info_8168cp));
+	rtl_ephy_init(tp, e_info_8168cp);
 
 	__rtl_hw_start_8168cp(tp);
 }
@@ -4785,9 +4371,6 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
 
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
-
-	tp->cp_cmd &= CPCMD_QUIRK_MASK;
-	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 }
 
 static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
@@ -4799,13 +4382,8 @@ static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
 	/* Magic. */
 	RTL_W8(tp, DBG_REG, 0x20);
 
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
-
-	tp->cp_cmd &= CPCMD_QUIRK_MASK;
-	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 }
 
 static void rtl_hw_start_8168c_1(struct rtl8169_private *tp)
@@ -4820,7 +4398,7 @@ static void rtl_hw_start_8168c_1(struct rtl8169_private *tp)
 
 	RTL_W8(tp, DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2);
 
-	rtl_ephy_init(tp, e_info_8168c_1, ARRAY_SIZE(e_info_8168c_1));
+	rtl_ephy_init(tp, e_info_8168c_1);
 
 	__rtl_hw_start_8168cp(tp);
 }
@@ -4834,7 +4412,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp)
 
 	rtl_set_def_aspm_entry_latency(tp);
 
-	rtl_ephy_init(tp, e_info_8168c_2, ARRAY_SIZE(e_info_8168c_2));
+	rtl_ephy_init(tp, e_info_8168c_2);
 
 	__rtl_hw_start_8168cp(tp);
 }
@@ -4857,13 +4435,8 @@ static void rtl_hw_start_8168d(struct rtl8169_private *tp)
 
 	rtl_disable_clock_request(tp);
 
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
-
-	tp->cp_cmd &= CPCMD_QUIRK_MASK;
-	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 }
 
 static void rtl_hw_start_8168dp(struct rtl8169_private *tp)
@@ -4873,8 +4446,6 @@ static void rtl_hw_start_8168dp(struct rtl8169_private *tp)
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
 	rtl_disable_clock_request(tp);
 }
 
@@ -4890,9 +4461,7 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp)
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
-	rtl_ephy_init(tp, e_info_8168d_4, ARRAY_SIZE(e_info_8168d_4));
+	rtl_ephy_init(tp, e_info_8168d_4);
 
 	rtl_enable_clock_request(tp);
 }
@@ -4917,13 +4486,11 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp)
 
 	rtl_set_def_aspm_entry_latency(tp);
 
-	rtl_ephy_init(tp, e_info_8168e_1, ARRAY_SIZE(e_info_8168e_1));
+	rtl_ephy_init(tp, e_info_8168e_1);
 
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
 	rtl_disable_clock_request(tp);
 
 	/* Reset tx FIFO pointer */
@@ -4942,28 +4509,24 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 
 	rtl_set_def_aspm_entry_latency(tp);
 
-	rtl_ephy_init(tp, e_info_8168e_2, ARRAY_SIZE(e_info_8168e_2));
+	rtl_ephy_init(tp, e_info_8168e_2);
 
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xc8, ERIAR_MASK_1111, 0x00100002, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x07ff0060, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0001, 0x10, 0x00, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00, ERIAR_EXGMAC);
-
-	RTL_W8(tp, MaxTxPacketSize, EarlySize);
+	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
+	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
+	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050);
+	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x07ff0060);
+	rtl_eri_set_bits(tp, 0x1b0, ERIAR_MASK_0001, BIT(4));
+	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00);
 
 	rtl_disable_clock_request(tp);
 
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
 
-	/* Adjust EEE LED frequency */
-	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
+	rtl8168_config_eee_mac(tp);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
@@ -4978,18 +4541,14 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xc8, ERIAR_MASK_1111, 0x00100002, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0001, 0x10, 0x00, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0x1d0, ERIAR_MASK_0001, 0x10, 0x00, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x00000060, ERIAR_EXGMAC);
-
-	RTL_W8(tp, MaxTxPacketSize, EarlySize);
+	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
+	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
+	rtl_reset_packet_filter(tp);
+	rtl_eri_set_bits(tp, 0x1b0, ERIAR_MASK_0001, BIT(4));
+	rtl_eri_set_bits(tp, 0x1d0, ERIAR_MASK_0001, BIT(4));
+	rtl_eri_write(tp, 0xcc, ERIAR_MASK_1111, 0x00000050);
+	rtl_eri_write(tp, 0xd0, ERIAR_MASK_1111, 0x00000060);
 
 	rtl_disable_clock_request(tp);
 
@@ -4997,6 +4556,8 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
 	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
+
+	rtl8168_config_eee_mac(tp);
 }
 
 static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
@@ -5010,12 +4571,9 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
 
 	rtl_hw_start_8168f(tp);
 
-	rtl_ephy_init(tp, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
-
-	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00, ERIAR_EXGMAC);
+	rtl_ephy_init(tp, e_info_8168f_1);
 
-	/* Adjust EEE LED frequency */
-	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
+	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0xff00);
 }
 
 static void rtl_hw_start_8411(struct rtl8169_private *tp)
@@ -5028,41 +4586,36 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
 	};
 
 	rtl_hw_start_8168f(tp);
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 
-	rtl_ephy_init(tp, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
+	rtl_ephy_init(tp, e_info_8168f_1);
 
-	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00, 0x0000, ERIAR_EXGMAC);
+	rtl_eri_set_bits(tp, 0x0d4, ERIAR_MASK_0011, 0x0c00);
 }
 
 static void rtl_hw_start_8168g(struct rtl8169_private *tp)
 {
-	rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x080002, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
+	rtl_set_fifo_size(tp, 0x08, 0x10, 0x02, 0x06);
+	rtl8168g_set_pause_thresholds(tp, 0x38, 0x48);
 
 	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0x2f8, ERIAR_MASK_0011, 0x1d8f, ERIAR_EXGMAC);
+	rtl_reset_packet_filter(tp);
+	rtl_eri_write(tp, 0x2f8, ERIAR_MASK_0011, 0x1d8f);
 
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN);
-	RTL_W8(tp, MaxTxPacketSize, EarlySize);
 
-	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
 
-	/* Adjust EEE LED frequency */
-	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
+	rtl8168_config_eee_mac(tp);
 
-	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC);
+	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06);
+	rtl_eri_clear_bits(tp, 0x1b0, ERIAR_MASK_0011, BIT(12));
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
@@ -5078,7 +4631,7 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
 
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
-	rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1));
+	rtl_ephy_init(tp, e_info_8168g_1);
 	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
@@ -5096,7 +4649,7 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
 	/* disable aspm and clock request before access ephy */
 	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
 	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
-	rtl_ephy_init(tp, e_info_8168g_2, ARRAY_SIZE(e_info_8168g_2));
+	rtl_ephy_init(tp, e_info_8168g_2);
 }
 
 static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
@@ -5113,7 +4666,7 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
-	rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2));
+	rtl_ephy_init(tp, e_info_8411_2);
 	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
@@ -5132,43 +4685,38 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
-	rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1));
+	rtl_ephy_init(tp, e_info_8168h_1);
 
-	rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
+	rtl_set_fifo_size(tp, 0x08, 0x10, 0x02, 0x06);
+	rtl8168g_set_pause_thresholds(tp, 0x38, 0x48);
 
 	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC);
+	rtl_reset_packet_filter(tp);
 
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_1111, 0x0010, 0x00, ERIAR_EXGMAC);
+	rtl_eri_set_bits(tp, 0xdc, ERIAR_MASK_1111, BIT(4));
 
-	rtl_w0w1_eri(tp, 0xd4, ERIAR_MASK_1111, 0x1f00, 0x00, ERIAR_EXGMAC);
+	rtl_eri_set_bits(tp, 0xd4, ERIAR_MASK_1111, 0x1f00);
 
-	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN);
-	RTL_W8(tp, MaxTxPacketSize, EarlySize);
 
-	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
 
-	/* Adjust EEE LED frequency */
-	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
+	rtl8168_config_eee_mac(tp);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
 	RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN);
 
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC);
+	rtl_eri_clear_bits(tp, 0x1b0, ERIAR_MASK_0011, BIT(12));
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 
 	rtl_writephy(tp, 0x1f, 0x0c42);
 	rg_saw_cnt = (rtl_readphy(tp, 0x13) & 0x3fff);
@@ -5216,36 +4764,31 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
 {
 	rtl8168ep_stop_cmac(tp);
 
-	rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x2f, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
+	rtl_set_fifo_size(tp, 0x08, 0x10, 0x02, 0x06);
+	rtl8168g_set_pause_thresholds(tp, 0x2f, 0x5f);
 
 	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC);
+	rtl_reset_packet_filter(tp);
 
-	rtl_w0w1_eri(tp, 0xd4, ERIAR_MASK_1111, 0x1f80, 0x00, ERIAR_EXGMAC);
+	rtl_eri_set_bits(tp, 0xd4, ERIAR_MASK_1111, 0x1f80);
 
-	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0x5f0, ERIAR_MASK_0011, 0x4f87);
 
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN);
-	RTL_W8(tp, MaxTxPacketSize, EarlySize);
 
-	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
+	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
 
-	/* Adjust EEE LED frequency */
-	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
+	rtl8168_config_eee_mac(tp);
 
-	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC);
+	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp)
@@ -5260,7 +4803,7 @@ static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp)
 
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
-	rtl_ephy_init(tp, e_info_8168ep_1, ARRAY_SIZE(e_info_8168ep_1));
+	rtl_ephy_init(tp, e_info_8168ep_1);
 
 	rtl_hw_start_8168ep(tp);
 
@@ -5277,7 +4820,7 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp)
 
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
-	rtl_ephy_init(tp, e_info_8168ep_2, ARRAY_SIZE(e_info_8168ep_2));
+	rtl_ephy_init(tp, e_info_8168ep_2);
 
 	rtl_hw_start_8168ep(tp);
 
@@ -5299,7 +4842,7 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 
 	/* disable aspm and clock request before access ephy */
 	rtl_hw_aspm_clkreq_enable(tp, false);
-	rtl_ephy_init(tp, e_info_8168ep_3, ARRAY_SIZE(e_info_8168ep_3));
+	rtl_ephy_init(tp, e_info_8168ep_3);
 
 	rtl_hw_start_8168ep(tp);
 
@@ -5322,128 +4865,6 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
-static void rtl_hw_start_8168(struct rtl8169_private *tp)
-{
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
-
-	tp->cp_cmd &= ~INTT_MASK;
-	tp->cp_cmd |= PktCntrDisable | INTT_1;
-	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
-
-	RTL_W16(tp, IntrMitigate, 0x5151);
-
-	/* Work around for RxFIFO overflow. */
-	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
-		tp->irq_mask |= RxFIFOOver;
-		tp->irq_mask &= ~RxOverflow;
-	}
-
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_11:
-		rtl_hw_start_8168bb(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_12:
-	case RTL_GIGA_MAC_VER_17:
-		rtl_hw_start_8168bef(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_18:
-		rtl_hw_start_8168cp_1(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_19:
-		rtl_hw_start_8168c_1(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_20:
-		rtl_hw_start_8168c_2(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_21:
-		rtl_hw_start_8168c_3(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_22:
-		rtl_hw_start_8168c_4(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_23:
-		rtl_hw_start_8168cp_2(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_24:
-		rtl_hw_start_8168cp_3(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_25:
-	case RTL_GIGA_MAC_VER_26:
-	case RTL_GIGA_MAC_VER_27:
-		rtl_hw_start_8168d(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_28:
-		rtl_hw_start_8168d_4(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_31:
-		rtl_hw_start_8168dp(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_32:
-	case RTL_GIGA_MAC_VER_33:
-		rtl_hw_start_8168e_1(tp);
-		break;
-	case RTL_GIGA_MAC_VER_34:
-		rtl_hw_start_8168e_2(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_35:
-	case RTL_GIGA_MAC_VER_36:
-		rtl_hw_start_8168f_1(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_38:
-		rtl_hw_start_8411(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_40:
-	case RTL_GIGA_MAC_VER_41:
-		rtl_hw_start_8168g_1(tp);
-		break;
-	case RTL_GIGA_MAC_VER_42:
-		rtl_hw_start_8168g_2(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_44:
-		rtl_hw_start_8411_2(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_45:
-	case RTL_GIGA_MAC_VER_46:
-		rtl_hw_start_8168h_1(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_49:
-		rtl_hw_start_8168ep_1(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_50:
-		rtl_hw_start_8168ep_2(tp);
-		break;
-
-	case RTL_GIGA_MAC_VER_51:
-		rtl_hw_start_8168ep_3(tp);
-		break;
-
-	default:
-		netif_err(tp, drv, tp->dev,
-			  "unknown chipset (mac_version = %d)\n",
-			  tp->mac_version);
-		break;
-	}
-}
-
 static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
 {
 	static const struct ephy_info e_info_8102e_1[] = {
@@ -5472,7 +4893,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
 	if ((cfg1 & LEDS0) && (cfg1 & LEDS1))
 		RTL_W8(tp, Config1, cfg1 & ~LEDS0);
 
-	rtl_ephy_init(tp, e_info_8102e_1, ARRAY_SIZE(e_info_8102e_1));
+	rtl_ephy_init(tp, e_info_8102e_1);
 }
 
 static void rtl_hw_start_8102e_2(struct rtl8169_private *tp)
@@ -5514,9 +4935,9 @@ static void rtl_hw_start_8105e_1(struct rtl8169_private *tp)
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 
-	rtl_ephy_init(tp, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1));
+	rtl_ephy_init(tp, e_info_8105e_1);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8105e_2(struct rtl8169_private *tp)
@@ -5539,19 +4960,17 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
 
-	rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402));
+	rtl_ephy_init(tp, e_info_8402);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
-	rtl_eri_write(tp, 0xc8, ERIAR_MASK_1111, 0x00000002, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00000006, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
-	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00, ERIAR_EXGMAC);
+	rtl_set_fifo_size(tp, 0x00, 0x00, 0x02, 0x06);
+	rtl_reset_packet_filter(tp);
+	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
+	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
+	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8106(struct rtl8169_private *tp)
@@ -5565,62 +4984,130 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
-static void rtl_hw_start_8101(struct rtl8169_private *tp)
-{
-	if (tp->mac_version >= RTL_GIGA_MAC_VER_30)
-		tp->irq_mask &= ~RxFIFOOver;
+static void rtl_hw_config(struct rtl8169_private *tp)
+{
+	static const rtl_generic_fct hw_configs[] = {
+		[RTL_GIGA_MAC_VER_07] = rtl_hw_start_8102e_1,
+		[RTL_GIGA_MAC_VER_08] = rtl_hw_start_8102e_3,
+		[RTL_GIGA_MAC_VER_09] = rtl_hw_start_8102e_2,
+		[RTL_GIGA_MAC_VER_10] = NULL,
+		[RTL_GIGA_MAC_VER_11] = rtl_hw_start_8168bb,
+		[RTL_GIGA_MAC_VER_12] = rtl_hw_start_8168bef,
+		[RTL_GIGA_MAC_VER_13] = NULL,
+		[RTL_GIGA_MAC_VER_14] = NULL,
+		[RTL_GIGA_MAC_VER_15] = NULL,
+		[RTL_GIGA_MAC_VER_16] = NULL,
+		[RTL_GIGA_MAC_VER_17] = rtl_hw_start_8168bef,
+		[RTL_GIGA_MAC_VER_18] = rtl_hw_start_8168cp_1,
+		[RTL_GIGA_MAC_VER_19] = rtl_hw_start_8168c_1,
+		[RTL_GIGA_MAC_VER_20] = rtl_hw_start_8168c_2,
+		[RTL_GIGA_MAC_VER_21] = rtl_hw_start_8168c_3,
+		[RTL_GIGA_MAC_VER_22] = rtl_hw_start_8168c_4,
+		[RTL_GIGA_MAC_VER_23] = rtl_hw_start_8168cp_2,
+		[RTL_GIGA_MAC_VER_24] = rtl_hw_start_8168cp_3,
+		[RTL_GIGA_MAC_VER_25] = rtl_hw_start_8168d,
+		[RTL_GIGA_MAC_VER_26] = rtl_hw_start_8168d,
+		[RTL_GIGA_MAC_VER_27] = rtl_hw_start_8168d,
+		[RTL_GIGA_MAC_VER_28] = rtl_hw_start_8168d_4,
+		[RTL_GIGA_MAC_VER_29] = rtl_hw_start_8105e_1,
+		[RTL_GIGA_MAC_VER_30] = rtl_hw_start_8105e_2,
+		[RTL_GIGA_MAC_VER_31] = rtl_hw_start_8168dp,
+		[RTL_GIGA_MAC_VER_32] = rtl_hw_start_8168e_1,
+		[RTL_GIGA_MAC_VER_33] = rtl_hw_start_8168e_1,
+		[RTL_GIGA_MAC_VER_34] = rtl_hw_start_8168e_2,
+		[RTL_GIGA_MAC_VER_35] = rtl_hw_start_8168f_1,
+		[RTL_GIGA_MAC_VER_36] = rtl_hw_start_8168f_1,
+		[RTL_GIGA_MAC_VER_37] = rtl_hw_start_8402,
+		[RTL_GIGA_MAC_VER_38] = rtl_hw_start_8411,
+		[RTL_GIGA_MAC_VER_39] = rtl_hw_start_8106,
+		[RTL_GIGA_MAC_VER_40] = rtl_hw_start_8168g_1,
+		[RTL_GIGA_MAC_VER_41] = rtl_hw_start_8168g_1,
+		[RTL_GIGA_MAC_VER_42] = rtl_hw_start_8168g_2,
+		[RTL_GIGA_MAC_VER_43] = rtl_hw_start_8168g_2,
+		[RTL_GIGA_MAC_VER_44] = rtl_hw_start_8411_2,
+		[RTL_GIGA_MAC_VER_45] = rtl_hw_start_8168h_1,
+		[RTL_GIGA_MAC_VER_46] = rtl_hw_start_8168h_1,
+		[RTL_GIGA_MAC_VER_47] = rtl_hw_start_8168h_1,
+		[RTL_GIGA_MAC_VER_48] = rtl_hw_start_8168h_1,
+		[RTL_GIGA_MAC_VER_49] = rtl_hw_start_8168ep_1,
+		[RTL_GIGA_MAC_VER_50] = rtl_hw_start_8168ep_2,
+		[RTL_GIGA_MAC_VER_51] = rtl_hw_start_8168ep_3,
+	};
+
+	if (hw_configs[tp->mac_version])
+		hw_configs[tp->mac_version](tp);
+}
 
+static void rtl_hw_start_8168(struct rtl8169_private *tp)
+{
 	if (tp->mac_version == RTL_GIGA_MAC_VER_13 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_16)
 		pcie_capability_set_word(tp->pci_dev, PCI_EXP_DEVCTL,
 					 PCI_EXP_DEVCTL_NOSNOOP_EN);
 
-	RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
+	if (rtl_is_8168evl_up(tp))
+		RTL_W8(tp, MaxTxPacketSize, EarlySize);
+	else
+		RTL_W8(tp, MaxTxPacketSize, TxPacketMax);
+
+	rtl_hw_config(tp);
+}
+
+static void rtl_hw_start_8169(struct rtl8169_private *tp)
+{
+	if (tp->mac_version == RTL_GIGA_MAC_VER_05)
+		pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
+
+	RTL_W8(tp, EarlyTxThres, NoEarlyTx);
+
+	tp->cp_cmd |= PCIMulRW;
+
+	if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_03) {
+		netif_dbg(tp, drv, tp->dev,
+			  "Set MAC Reg C+CR Offset 0xe0. Bit 3 and Bit 14 MUST be 1\n");
+		tp->cp_cmd |= (1 << 14);
+	}
 
-	tp->cp_cmd &= CPCMD_QUIRK_MASK;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_07:
-		rtl_hw_start_8102e_1(tp);
-		break;
+	rtl8169_set_magic_reg(tp, tp->mac_version);
 
-	case RTL_GIGA_MAC_VER_08:
-		rtl_hw_start_8102e_3(tp);
-		break;
+	RTL_W32(tp, RxMissed, 0);
+}
 
-	case RTL_GIGA_MAC_VER_09:
-		rtl_hw_start_8102e_2(tp);
-		break;
+static void rtl_hw_start(struct  rtl8169_private *tp)
+{
+	rtl_unlock_config_regs(tp);
 
-	case RTL_GIGA_MAC_VER_29:
-		rtl_hw_start_8105e_1(tp);
-		break;
-	case RTL_GIGA_MAC_VER_30:
-		rtl_hw_start_8105e_2(tp);
-		break;
+	tp->cp_cmd &= CPCMD_MASK;
+	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
-	case RTL_GIGA_MAC_VER_37:
-		rtl_hw_start_8402(tp);
-		break;
+	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
+		rtl_hw_start_8169(tp);
+	else
+		rtl_hw_start_8168(tp);
 
-	case RTL_GIGA_MAC_VER_39:
-		rtl_hw_start_8106(tp);
-		break;
-	case RTL_GIGA_MAC_VER_43:
-		rtl_hw_start_8168g_2(tp);
-		break;
-	case RTL_GIGA_MAC_VER_47:
-	case RTL_GIGA_MAC_VER_48:
-		rtl_hw_start_8168h_1(tp);
-		break;
-	}
+	rtl_set_rx_max_size(tp);
+	rtl_set_rx_tx_desc_registers(tp);
+	rtl_lock_config_regs(tp);
 
+	/* disable interrupt coalescing */
 	RTL_W16(tp, IntrMitigate, 0x0000);
+	/* Initially a 10 us delay. Turned it into a PCI commit. - FR */
+	RTL_R8(tp, IntrMask);
+	RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
+	rtl_init_rxcfg(tp);
+	rtl_set_tx_config_registers(tp);
+
+	rtl_set_rx_mode(tp->dev);
+	/* no early-rx interrupts */
+	RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
+	rtl_irq_enable(tp);
 }
 
 static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
@@ -5665,11 +5152,6 @@ static inline void rtl8169_mark_to_asic(struct RxDesc *desc)
 	desc->opts1 = cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE);
 }
 
-static inline void *rtl8169_align(void *data)
-{
-	return (void *)ALIGN((long)data, 16);
-}
-
 static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp,
 					     struct RxDesc *desc)
 {
@@ -5682,15 +5164,13 @@ static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp,
 	if (!data)
 		return NULL;
 
-	if (rtl8169_align(data) != data) {
-		kfree(data);
-		data = kmalloc_node(R8169_RX_BUF_SIZE + 15, GFP_KERNEL, node);
-		if (!data)
-			return NULL;
+	/* Memory should be properly aligned, but better check. */
+	if (!IS_ALIGNED((unsigned long)data, 8)) {
+		netdev_err_once(tp->dev, "RX buffer not 8-byte-aligned\n");
+		goto err_out;
 	}
 
-	mapping = dma_map_single(d, rtl8169_align(data), R8169_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+	mapping = dma_map_single(d, data, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(d, mapping))) {
 		if (net_ratelimit())
 			netif_err(tp, drv, tp->dev, "Failed to map RX DMA!\n");
@@ -5899,7 +5379,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 static void r8169_csum_workaround(struct rtl8169_private *tp,
 				  struct sk_buff *skb)
 {
-	if (skb_shinfo(skb)->gso_size) {
+	if (skb_is_gso(skb)) {
 		netdev_features_t features = tp->dev->features;
 		struct sk_buff *segs, *nskb;
 
@@ -5922,11 +5402,8 @@ static void r8169_csum_workaround(struct rtl8169_private *tp,
 
 		rtl8169_start_xmit(skb, tp->dev);
 	} else {
-		struct net_device_stats *stats;
-
 drop:
-		stats = &tp->dev->stats;
-		stats->tx_dropped++;
+		tp->dev->stats.tx_dropped++;
 		dev_kfree_skb_any(skb);
 	}
 }
@@ -5954,8 +5431,7 @@ static int msdn_giant_send_check(struct sk_buff *skb)
 	return ret;
 }
 
-static bool rtl8169_tso_csum_v1(struct rtl8169_private *tp,
-				struct sk_buff *skb, u32 *opts)
+static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts)
 {
 	u32 mss = skb_shinfo(skb)->gso_size;
 
@@ -5972,8 +5448,6 @@ static bool rtl8169_tso_csum_v1(struct rtl8169_private *tp,
 		else
 			WARN_ON_ONCE(1);
 	}
-
-	return true;
 }
 
 static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
@@ -6063,6 +5537,18 @@ static bool rtl_tx_slots_avail(struct rtl8169_private *tp,
 	return slots_avail > nr_frags;
 }
 
+/* Versions RTL8102e and from RTL8168c onwards support csum_v2 */
+static bool rtl_chip_supports_csum_v2(struct rtl8169_private *tp)
+{
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
+	case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
+		return false;
+	default:
+		return true;
+	}
+}
+
 static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
@@ -6072,7 +5558,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	struct device *d = tp_to_dev(tp);
 	dma_addr_t mapping;
 	u32 opts[2], len;
-	bool stop_queue;
 	int frags;
 
 	if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) {
@@ -6083,12 +5568,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	if (unlikely(le32_to_cpu(txd->opts1) & DescOwn))
 		goto err_stop_0;
 
-	opts[1] = cpu_to_le32(rtl8169_tx_vlan_tag(skb));
+	opts[1] = rtl8169_tx_vlan_tag(skb);
 	opts[0] = DescOwn;
 
-	if (!tp->tso_csum(tp, skb, opts)) {
-		r8169_csum_workaround(tp, skb);
-		return NETDEV_TX_OK;
+	if (rtl_chip_supports_csum_v2(tp)) {
+		if (!rtl8169_tso_csum_v2(tp, skb, opts)) {
+			r8169_csum_workaround(tp, skb);
+			return NETDEV_TX_OK;
+		}
+	} else {
+		rtl8169_tso_csum_v1(skb, opts);
 	}
 
 	len = skb_headlen(skb);
@@ -6114,6 +5603,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	txd->opts2 = cpu_to_le32(opts[1]);
 
+	netdev_sent_queue(dev, skb->len);
+
 	skb_tx_timestamp(skb);
 
 	/* Force memory writes to complete before releasing descriptor */
@@ -6126,14 +5617,14 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	tp->cur_tx += frags + 1;
 
-	stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS);
-	if (unlikely(stop_queue))
-		netif_stop_queue(dev);
-
-	if (__netdev_sent_queue(dev, skb->len, skb->xmit_more))
-		RTL_W8(tp, TxPoll, NPQ);
+	RTL_W8(tp, TxPoll, NPQ);
 
-	if (unlikely(stop_queue)) {
+	if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
+		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
+		 * not miss a ring update when it notices a stopped queue.
+		 */
+		smp_wmb();
+		netif_stop_queue(dev);
 		/* Sync with rtl_tx:
 		 * - publish queue status and cur_tx ring index (write barrier)
 		 * - refresh dirty_tx ring index (read barrier).
@@ -6143,7 +5634,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 		 */
 		smp_mb();
 		if (rtl_tx_slots_avail(tp, MAX_SKB_FRAGS))
-			netif_wake_queue(dev);
+			netif_start_queue(dev);
 	}
 
 	return NETDEV_TX_OK;
@@ -6193,16 +5684,6 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev)
 		PCI_STATUS_SIG_SYSTEM_ERROR | PCI_STATUS_REC_MASTER_ABORT |
 		PCI_STATUS_REC_TARGET_ABORT | PCI_STATUS_SIG_TARGET_ABORT));
 
-	/* The infamous DAC f*ckup only happens at boot time */
-	if ((tp->cp_cmd & PCIDAC) && !tp->cur_rx) {
-		netif_info(tp, intr, dev, "disabling PCI DAC\n");
-		tp->cp_cmd &= ~PCIDAC;
-		RTL_W16(tp, CPlusCmd, tp->cp_cmd);
-		dev->features &= ~NETIF_F_HIGHDMA;
-	}
-
-	rtl8169_hw_reset(tp);
-
 	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
@@ -6298,13 +5779,11 @@ static struct sk_buff *rtl8169_try_rx_copy(void *data,
 	struct sk_buff *skb;
 	struct device *d = tp_to_dev(tp);
 
-	data = rtl8169_align(data);
 	dma_sync_single_for_cpu(d, addr, pkt_size, DMA_FROM_DEVICE);
 	prefetch(data);
 	skb = napi_alloc_skb(&tp->napi, pkt_size);
 	if (skb)
 		skb_copy_to_linear_data(skb, data, pkt_size);
-	dma_sync_single_for_device(d, addr, pkt_size, DMA_FROM_DEVICE);
 
 	return skb;
 }
@@ -6339,14 +5818,8 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget
 				dev->stats.rx_length_errors++;
 			if (status & RxCRC)
 				dev->stats.rx_crc_errors++;
-			/* RxFOVF is a reserved bit on later chip versions */
-			if (tp->mac_version == RTL_GIGA_MAC_VER_01 &&
-			    status & RxFOVF) {
-				rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
-				dev->stats.rx_fifo_errors++;
-			} else if (status & (RxRUNT | RxCRC) &&
-				   !(status & RxRWT) &&
-				   dev->features & NETIF_F_RXALL) {
+			if (status & (RxRUNT | RxCRC) && !(status & RxRWT) &&
+			    dev->features & NETIF_F_RXALL) {
 				goto process_pkt;
 			}
 		} else {
@@ -6409,10 +5882,9 @@ release_descriptor:
 static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 {
 	struct rtl8169_private *tp = dev_instance;
-	u16 status = rtl_get_events(tp);
-	u16 irq_mask = RTL_R16(tp, IntrMask);
+	u16 status = RTL_R16(tp, IntrStatus);
 
-	if (status == 0xffff || !(status & irq_mask))
+	if (!tp->irq_enabled || status == 0xffff || !(status & tp->irq_mask))
 		return IRQ_NONE;
 
 	if (unlikely(status & SYSErr)) {
@@ -6420,8 +5892,8 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 		goto out;
 	}
 
-	if (status & LinkChg && tp->dev->phydev)
-		phy_mac_interrupt(tp->dev->phydev);
+	if (status & LinkChg)
+		phy_mac_interrupt(tp->phydev);
 
 	if (unlikely(status & RxFIFOOver &&
 	    tp->mac_version == RTL_GIGA_MAC_VER_11)) {
@@ -6430,10 +5902,8 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 		set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags);
 	}
 
-	if (status & RTL_EVENT_NAPI) {
-		rtl_irq_disable(tp);
-		napi_schedule_irqoff(&tp->napi);
-	}
+	rtl_irq_disable(tp);
+	napi_schedule_irqoff(&tp->napi);
 out:
 	rtl_ack_events(tp, status);
 
@@ -6512,12 +5982,12 @@ static void r8169_phylink_handler(struct net_device *ndev)
 	}
 
 	if (net_ratelimit())
-		phy_print_status(ndev->phydev);
+		phy_print_status(tp->phydev);
 }
 
 static int r8169_phy_connect(struct rtl8169_private *tp)
 {
-	struct phy_device *phydev = mdiobus_get_phy(tp->mii_bus, 0);
+	struct phy_device *phydev = tp->phydev;
 	phy_interface_t phy_mode;
 	int ret;
 
@@ -6529,11 +5999,13 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 	if (ret)
 		return ret;
 
-	if (!tp->supports_gmii)
+	if (tp->supports_gmii)
+		phy_remove_link_mode(phydev,
+				     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+	else
 		phy_set_max_speed(phydev, SPEED_100);
 
-	/* Ensure to advertise everything, incl. pause */
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_support_asym_pause(phydev);
 
 	phy_attached_info(phydev);
 
@@ -6544,7 +6016,7 @@ static void rtl8169_down(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	phy_stop(dev->phydev);
+	phy_stop(tp->phydev);
 
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
@@ -6586,7 +6058,7 @@ static int rtl8169_close(struct net_device *dev)
 
 	cancel_work_sync(&tp->wk.work);
 
-	phy_disconnect(dev->phydev);
+	phy_disconnect(tp->phydev);
 
 	pci_free_irq(pdev, 0, tp);
 
@@ -6637,10 +6109,6 @@ static int rtl_open(struct net_device *dev)
 	if (retval < 0)
 		goto err_free_rx_1;
 
-	INIT_WORK(&tp->wk.work, rtl_task);
-
-	smp_mb();
-
 	rtl_request_firmware(tp);
 
 	retval = pci_request_irq(pdev, 0, rtl8169_interrupt, NULL, tp,
@@ -6667,7 +6135,7 @@ static int rtl_open(struct net_device *dev)
 	if (!rtl8169_init_counter_offsets(tp))
 		netif_warn(tp, hw, dev, "counter reset/update failed\n");
 
-	phy_start(dev->phydev);
+	phy_start(tp->phydev);
 	netif_start_queue(dev);
 
 	rtl_unlock_work(tp);
@@ -6756,7 +6224,7 @@ static void rtl8169_net_suspend(struct net_device *dev)
 	if (!netif_running(dev))
 		return;
 
-	phy_stop(dev->phydev);
+	phy_stop(tp->phydev);
 	netif_device_detach(dev);
 
 	rtl_lock_work(tp);
@@ -6791,14 +6259,13 @@ static void __rtl8169_resume(struct net_device *dev)
 	rtl_pll_power_up(tp);
 	rtl8169_init_phy(dev, tp);
 
-	phy_start(tp->dev->phydev);
+	phy_start(tp->phydev);
 
 	rtl_lock_work(tp);
 	napi_enable(&tp->napi);
 	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
+	rtl_reset_work(tp);
 	rtl_unlock_work(tp);
-
-	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
 static int rtl8169_resume(struct device *device)
@@ -6806,6 +6273,8 @@ static int rtl8169_resume(struct device *device)
 	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
+	rtl_rar_set(tp, dev->dev_addr);
+
 	clk_prepare_enable(tp->clk);
 
 	if (netif_running(dev))
@@ -6839,6 +6308,7 @@ static int rtl8169_runtime_resume(struct device *device)
 {
 	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
+
 	rtl_rar_set(tp, dev->dev_addr);
 
 	if (!tp->TxDescArray)
@@ -6935,7 +6405,7 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	netif_napi_del(&tp->napi);
 
 	unregister_netdev(dev);
-	mdiobus_unregister(tp->mii_bus);
+	mdiobus_unregister(tp->phydev->mdio.bus);
 
 	rtl_release_firmware(tp);
 
@@ -6965,39 +6435,27 @@ static const struct net_device_ops rtl_netdev_ops = {
 
 };
 
-static const struct rtl_cfg_info {
-	void (*hw_start)(struct rtl8169_private *tp);
-	u16 irq_mask;
-	unsigned int has_gmii:1;
-	const struct rtl_coalesce_info *coalesce_info;
-} rtl_cfg_infos [] = {
-	[RTL_CFG_0] = {
-		.hw_start	= rtl_hw_start_8169,
-		.irq_mask	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
-		.has_gmii	= 1,
-		.coalesce_info	= rtl_coalesce_info_8169,
-	},
-	[RTL_CFG_1] = {
-		.hw_start	= rtl_hw_start_8168,
-		.irq_mask	= LinkChg | RxOverflow,
-		.has_gmii	= 1,
-		.coalesce_info	= rtl_coalesce_info_8168_8136,
-	},
-	[RTL_CFG_2] = {
-		.hw_start	= rtl_hw_start_8101,
-		.irq_mask	= LinkChg | RxOverflow | RxFIFOOver,
-		.coalesce_info	= rtl_coalesce_info_8168_8136,
-	}
-};
+static void rtl_set_irq_mask(struct rtl8169_private *tp)
+{
+	tp->irq_mask = RTL_EVENT_NAPI | LinkChg;
+
+	if (tp->mac_version <= RTL_GIGA_MAC_VER_06)
+		tp->irq_mask |= SYSErr | RxOverflow | RxFIFOOver;
+	else if (tp->mac_version == RTL_GIGA_MAC_VER_11)
+		/* special workaround needed */
+		tp->irq_mask |= RxFIFOOver;
+	else
+		tp->irq_mask |= RxOverflow;
+}
 
 static int rtl_alloc_irq(struct rtl8169_private *tp)
 {
 	unsigned int flags;
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
-		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+		rtl_unlock_config_regs(tp);
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
-		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+		rtl_lock_config_regs(tp);
 		flags = PCI_IRQ_LEGACY;
 	} else {
 		flags = PCI_IRQ_ALL_TYPES;
@@ -7006,6 +6464,24 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 	return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags);
 }
 
+static void rtl_read_mac_address(struct rtl8169_private *tp,
+				 u8 mac_addr[ETH_ALEN])
+{
+	/* Get MAC address */
+	if (rtl_is_8168evl_up(tp) && tp->mac_version != RTL_GIGA_MAC_VER_34) {
+		u32 value = rtl_eri_read(tp, 0xe0);
+
+		mac_addr[0] = (value >>  0) & 0xff;
+		mac_addr[1] = (value >>  8) & 0xff;
+		mac_addr[2] = (value >> 16) & 0xff;
+		mac_addr[3] = (value >> 24) & 0xff;
+
+		value = rtl_eri_read(tp, 0xe4);
+		mac_addr[4] = (value >>  0) & 0xff;
+		mac_addr[5] = (value >>  8) & 0xff;
+	}
+}
+
 DECLARE_RTL_COND(rtl_link_list_ready_cond)
 {
 	return RTL_R8(tp, MCU) & LINK_LIST_RDY;
@@ -7042,7 +6518,6 @@ static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr,
 static int r8169_mdio_register(struct rtl8169_private *tp)
 {
 	struct pci_dev *pdev = tp->pci_dev;
-	struct phy_device *phydev;
 	struct mii_bus *new_bus;
 	int ret;
 
@@ -7054,8 +6529,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->priv = tp;
 	new_bus->parent = &pdev->dev;
 	new_bus->irq[0] = PHY_IGNORE_INTERRUPT;
-	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x",
-		 PCI_DEVID(pdev->bus->number, pdev->devfn));
+	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x", pci_dev_id(pdev));
 
 	new_bus->read = r8169_mdio_read_reg;
 	new_bus->write = r8169_mdio_write_reg;
@@ -7064,16 +6538,14 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	if (ret)
 		return ret;
 
-	phydev = mdiobus_get_phy(new_bus, 0);
-	if (!phydev) {
+	tp->phydev = mdiobus_get_phy(new_bus, 0);
+	if (!tp->phydev) {
 		mdiobus_unregister(new_bus);
 		return -ENODEV;
 	}
 
 	/* PHY will be woken up in rtl_open() */
-	phy_suspend(phydev);
-
-	tp->mii_bus = new_bus;
+	phy_suspend(tp->phydev);
 
 	return 0;
 }
@@ -7107,42 +6579,23 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 	data |= (1 << 15);
 	r8168_mac_ocp_write(tp, 0xe8de, data);
 
-	if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42))
-		return;
-}
-
-static void rtl_hw_init_8168ep(struct rtl8169_private *tp)
-{
-	rtl8168ep_stop_cmac(tp);
-	rtl_hw_init_8168g(tp);
+	rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42);
 }
 
 static void rtl_hw_initialize(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_51:
+		rtl8168ep_stop_cmac(tp);
+		/* fall through */
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48:
 		rtl_hw_init_8168g(tp);
 		break;
-	case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_51:
-		rtl_hw_init_8168ep(tp);
-		break;
 	default:
 		break;
 	}
 }
 
-/* Versions RTL8102e and from RTL8168c onwards support csum_v2 */
-static bool rtl_chip_supports_csum_v2(struct rtl8169_private *tp)
-{
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
-	case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
-		return false;
-	default:
-		return true;
-	}
-}
-
 static int rtl_jumbo_max(struct rtl8169_private *tp)
 {
 	/* Non-GBit versions don't support jumbo frames */
@@ -7151,7 +6604,7 @@ static int rtl_jumbo_max(struct rtl8169_private *tp)
 
 	switch (tp->mac_version) {
 	/* RTL8169 */
-	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+	case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
 		return JUMBO_7K;
 	/* RTL8168b */
 	case RTL_GIGA_MAC_VER_11:
@@ -7171,12 +6624,62 @@ static void rtl_disable_clk(void *data)
 	clk_disable_unprepare(data);
 }
 
+static int rtl_get_ether_clk(struct rtl8169_private *tp)
+{
+	struct device *d = tp_to_dev(tp);
+	struct clk *clk;
+	int rc;
+
+	clk = devm_clk_get(d, "ether_clk");
+	if (IS_ERR(clk)) {
+		rc = PTR_ERR(clk);
+		if (rc == -ENOENT)
+			/* clk-core allows NULL (for suspend / resume) */
+			rc = 0;
+		else if (rc != -EPROBE_DEFER)
+			dev_err(d, "failed to get clk: %d\n", rc);
+	} else {
+		tp->clk = clk;
+		rc = clk_prepare_enable(clk);
+		if (rc)
+			dev_err(d, "failed to enable clk: %d\n", rc);
+		else
+			rc = devm_add_action_or_reset(d, rtl_disable_clk, clk);
+	}
+
+	return rc;
+}
+
+static void rtl_init_mac_address(struct rtl8169_private *tp)
+{
+	struct net_device *dev = tp->dev;
+	u8 *mac_addr = dev->dev_addr;
+	int rc, i;
+
+	rc = eth_platform_get_mac_address(tp_to_dev(tp), mac_addr);
+	if (!rc)
+		goto done;
+
+	rtl_read_mac_address(tp, mac_addr);
+	if (is_valid_ether_addr(mac_addr))
+		goto done;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		mac_addr[i] = RTL_R8(tp, MAC0 + i);
+	if (is_valid_ether_addr(mac_addr))
+		goto done;
+
+	eth_hw_addr_random(dev);
+	dev_warn(tp_to_dev(tp), "can't read MAC address, setting random one\n");
+done:
+	rtl_rar_set(tp, mac_addr);
+}
+
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
 	struct rtl8169_private *tp;
 	struct net_device *dev;
-	int chipset, region, i;
+	int chipset, region;
 	int jumbo_max, rc;
 
 	dev = devm_alloc_etherdev(&pdev->dev, sizeof (*tp));
@@ -7189,33 +6692,19 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->dev = dev;
 	tp->pci_dev = pdev;
 	tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
-	tp->supports_gmii = cfg->has_gmii;
+	tp->supports_gmii = ent->driver_data == RTL_CFG_NO_GBIT ? 0 : 1;
 
 	/* Get the *optional* external "ether_clk" used on some boards */
-	tp->clk = devm_clk_get(&pdev->dev, "ether_clk");
-	if (IS_ERR(tp->clk)) {
-		rc = PTR_ERR(tp->clk);
-		if (rc == -ENOENT) {
-			/* clk-core allows NULL (for suspend / resume) */
-			tp->clk = NULL;
-		} else if (rc == -EPROBE_DEFER) {
-			return rc;
-		} else {
-			dev_err(&pdev->dev, "failed to get clk: %d\n", rc);
-			return rc;
-		}
-	} else {
-		rc = clk_prepare_enable(tp->clk);
-		if (rc) {
-			dev_err(&pdev->dev, "failed to enable clk: %d\n", rc);
-			return rc;
-		}
+	rc = rtl_get_ether_clk(tp);
+	if (rc)
+		return rc;
 
-		rc = devm_add_action_or_reset(&pdev->dev, rtl_disable_clk,
-					      tp->clk);
-		if (rc)
-			return rc;
-	}
+	/* Disable ASPM completely as that cause random device stop working
+	 * problems as well as full system hangs for some PCIe devices users.
+	 */
+	rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
+					  PCIE_LINK_STATE_L1);
+	tp->aspm_manageable = !rc;
 
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
@@ -7253,28 +6742,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (tp->mac_version == RTL_GIGA_MAC_NONE)
 		return -ENODEV;
 
-	if (rtl_tbi_enabled(tp)) {
-		dev_err(&pdev->dev, "TBI fiber mode not supported\n");
-		return -ENODEV;
-	}
-
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd);
 
-	if (sizeof(dma_addr_t) > 4 && (use_dac == 1 || (use_dac == -1 &&
-	    tp->mac_version >= RTL_GIGA_MAC_VER_18)) &&
-	    !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
-
-		/* CPlusCmd Dual Access Cycle is only needed for non-PCIe */
-		if (!pci_is_pcie(pdev))
-			tp->cp_cmd |= PCIDAC;
+	if (sizeof(dma_addr_t) > 4 && tp->mac_version >= RTL_GIGA_MAC_VER_18 &&
+	    !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)))
 		dev->features |= NETIF_F_HIGHDMA;
-	} else {
-		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (rc < 0) {
-			dev_err(&pdev->dev, "DMA configuration failed\n");
-			return rc;
-		}
-	}
 
 	rtl_init_rxcfg(tp);
 
@@ -7286,9 +6758,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	rtl_init_mdio_ops(tp);
-	rtl_init_jumbo_ops(tp);
-
 	chipset = tp->mac_version;
 
 	rc = rtl_alloc_irq(tp);
@@ -7297,28 +6766,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return rc;
 	}
 
-	tp->saved_wolopts = __rtl8169_get_wol(tp);
-
 	mutex_init(&tp->wk.mutex);
+	INIT_WORK(&tp->wk.work, rtl_task);
 	u64_stats_init(&tp->rx_stats.syncp);
 	u64_stats_init(&tp->tx_stats.syncp);
 
-	/* Get MAC address */
-	switch (tp->mac_version) {
-		u8 mac_addr[ETH_ALEN] __aligned(4);
-	case RTL_GIGA_MAC_VER_35 ... RTL_GIGA_MAC_VER_38:
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
-		*(u32 *)&mac_addr[0] = rtl_eri_read(tp, 0xe0, ERIAR_EXGMAC);
-		*(u16 *)&mac_addr[4] = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC);
-
-		if (is_valid_ether_addr(mac_addr))
-			rtl_rar_set(tp, mac_addr);
-		break;
-	default:
-		break;
-	}
-	for (i = 0; i < ETH_ALEN; i++)
-		dev->dev_addr[i] = RTL_R8(tp, MAC0 + i);
+	rtl_init_mac_address(tp);
 
 	dev->ethtool_ops = &rtl8169_ethtool_ops;
 
@@ -7346,12 +6799,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		/* Disallow toggling */
 		dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 
-	if (rtl_chip_supports_csum_v2(tp)) {
-		tp->tso_csum = rtl8169_tso_csum_v2;
+	if (rtl_chip_supports_csum_v2(tp))
 		dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
-	} else {
-		tp->tso_csum = rtl8169_tso_csum_v1;
-	}
 
 	dev->hw_features |= NETIF_F_RXALL;
 	dev->hw_features |= NETIF_F_RXFCS;
@@ -7361,11 +6810,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	jumbo_max = rtl_jumbo_max(tp);
 	dev->max_mtu = jumbo_max;
 
-	tp->hw_start = cfg->hw_start;
-	tp->irq_mask = RTL_EVENT_NAPI | cfg->irq_mask;
-	tp->coalesce_info = cfg->coalesce_info;
+	rtl_set_irq_mask(tp);
 
-	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
+	tp->fw_name = rtl_chip_infos[chipset].fw_name;
 
 	tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
 					    &tp->counters_phys_addr,
@@ -7406,7 +6853,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 err_mdio_unregister:
-	mdiobus_unregister(tp->mii_bus);
+	mdiobus_unregister(tp->phydev->mdio.bus);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index d28c8f9ca55b..ef8f08931fe8 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -111,7 +111,7 @@ static void ravb_set_buffer_align(struct sk_buff *skb)
  */
 static void ravb_read_mac_address(struct net_device *ndev, const u8 *mac)
 {
-	if (mac) {
+	if (!IS_ERR(mac)) {
 		ether_addr_copy(ndev->dev_addr, mac);
 	} else {
 		u32 mahr = ravb_read(ndev, MAHR);
@@ -458,7 +458,7 @@ static int ravb_dmac_init(struct net_device *ndev)
 		   RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR);
 
 	/* Set FIFO size */
-	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC);
+	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC);
 
 	/* Timestamp enable */
 	ravb_write(ndev, TCCR_TFEN, TCCR);
@@ -728,7 +728,6 @@ static irqreturn_t ravb_emac_interrupt(int irq, void *dev_id)
 
 	spin_lock(&priv->lock);
 	ravb_emac_interrupt_unlocked(ndev);
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return IRQ_HANDLED;
 }
@@ -848,7 +847,6 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id)
 		result = IRQ_HANDLED;
 	}
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -881,7 +879,6 @@ static irqreturn_t ravb_multi_interrupt(int irq, void *dev_id)
 		result = IRQ_HANDLED;
 	}
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -898,7 +895,6 @@ static irqreturn_t ravb_dma_interrupt(int irq, void *dev_id, int q)
 	if (ravb_queue_interrupt(ndev, q))
 		result = IRQ_HANDLED;
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -943,7 +939,6 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 			ravb_write(ndev, ~(mask | TIS_RESERVED), TIS);
 			ravb_tx_free(ndev, q, true);
 			netif_wake_subqueue(ndev, q);
-			mmiowb();
 			spin_unlock_irqrestore(&priv->lock, flags);
 		}
 	}
@@ -959,7 +954,6 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 		ravb_write(ndev, mask, RIE0);
 		ravb_write(ndev, mask, TIE);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	/* Receive error message handling */
@@ -1008,7 +1002,6 @@ static void ravb_adjust_link(struct net_device *ndev)
 	if (priv->no_avb_link && phydev->link)
 		ravb_rcv_snd_enable(ndev);
 
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	if (new_state && netif_msg_link(priv))
@@ -1601,7 +1594,6 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		netif_stop_subqueue(ndev, q);
 
 exit:
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 	return NETDEV_TX_OK;
 
@@ -1615,8 +1607,7 @@ drop:
 }
 
 static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	/* If skb needs TX timestamp, it is handled in network control queue */
 	return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC :
@@ -1673,7 +1664,6 @@ static void ravb_set_rx_mode(struct net_device *ndev)
 	spin_lock_irqsave(&priv->lock, flags);
 	ravb_modify(ndev, ECMR, ECMR_PRM,
 		    ndev->flags & IFF_PROMISC ? ECMR_PRM : 0);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
@@ -1970,6 +1960,13 @@ static void ravb_set_config_mode(struct net_device *ndev)
 	}
 }
 
+static const struct soc_device_attribute ravb_delay_mode_quirk_match[] = {
+	{ .soc_id = "r8a774c0" },
+	{ .soc_id = "r8a77990" },
+	{ .soc_id = "r8a77995" },
+	{ /* sentinel */ }
+};
+
 /* Set tx and rx clock internal delay modes */
 static void ravb_set_delay_mode(struct net_device *ndev)
 {
@@ -1981,8 +1978,12 @@ static void ravb_set_delay_mode(struct net_device *ndev)
 		set |= APSR_DM_RDM;
 
 	if (priv->phy_interface == PHY_INTERFACE_MODE_RGMII_ID ||
-	    priv->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID)
-		set |= APSR_DM_TDM;
+	    priv->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID) {
+		if (!WARN(soc_device_match(ravb_delay_mode_quirk_match),
+			  "phy-mode %s requires TX clock internal delay mode which is not supported by this hardware revision. Please update device tree",
+			  phy_modes(priv->phy_interface)))
+			set |= APSR_DM_TDM;
+	}
 
 	ravb_modify(ndev, APSR, APSR_DM, set);
 }
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index dce2a40a31e3..9a42580693cb 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -196,7 +196,6 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 		ravb_write(ndev, GIE_PTCS, GIE);
 	else
 		ravb_write(ndev, GID_PTCD, GID);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
@@ -259,7 +258,6 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 		else
 			ravb_write(ndev, GID_PTMD0, GID);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return error;
@@ -331,7 +329,6 @@ void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev)
 	spin_lock_irqsave(&priv->lock, flags);
 	ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
 	ravb_modify(ndev, GCCR, GCCR_TCSS, GCCR_TCSS_ADJGPTP);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	priv->ptp.clock = ptp_clock_register(&priv->ptp.info, &pdev->dev);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index f27a0dc8c563..7ba35a0bdb29 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -555,7 +555,7 @@ static int sh_eth_soft_reset_gether(struct net_device *ndev)
 	sh_eth_write(ndev, 0, RDFFR);
 
 	/* Reset HW CRC register */
-	if (mdp->cd->hw_checksum)
+	if (mdp->cd->csmr)
 		sh_eth_write(ndev, 0, CSMR);
 
 	/* Select MII mode */
@@ -619,7 +619,8 @@ static struct sh_eth_cpu_data r7s72100_data = {
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.tsu		= 1,
 	.no_tx_cntrs	= 1,
 };
@@ -668,7 +669,8 @@ static struct sh_eth_cpu_data r8a7740_data = {
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.tsu		= 1,
 	.select_mii	= 1,
 	.magic		= 1,
@@ -793,7 +795,8 @@ static struct sh_eth_cpu_data r8a77980_data = {
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.select_mii	= 1,
 	.magic		= 1,
 	.cexcr		= 1,
@@ -1045,7 +1048,8 @@ static struct sh_eth_cpu_data sh7734_data = {
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
 	.tsu		= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.select_mii	= 1,
 	.magic		= 1,
 	.cexcr		= 1,
@@ -1088,6 +1092,7 @@ static struct sh_eth_cpu_data sh7763_data = {
 	.irq_flags	= IRQF_SHARED,
 	.magic		= 1,
 	.cexcr		= 1,
+	.rx_csum	= 1,
 	.dual_port	= 1,
 };
 
@@ -1532,8 +1537,9 @@ static int sh_eth_dev_init(struct net_device *ndev)
 	mdp->irq_enabled = true;
 	sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
 
-	/* PAUSE Prohibition */
+	/* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
 	sh_eth_write(ndev, ECMR_ZPF | (mdp->duplex ? ECMR_DM : 0) |
+		     (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) |
 		     ECMR_TE | ECMR_RE, ECMR);
 
 	if (mdp->cd->set_rate)
@@ -1588,10 +1594,27 @@ static void sh_eth_dev_exit(struct net_device *ndev)
 	sh_eth_get_stats(ndev);
 	mdp->cd->soft_reset(ndev);
 
+	/* Set the RMII mode again if required */
+	if (mdp->cd->rmiimode)
+		sh_eth_write(ndev, 0x1, RMIIMODE);
+
 	/* Set MAC address again */
 	update_mac_address(ndev);
 }
 
+static void sh_eth_rx_csum(struct sk_buff *skb)
+{
+	u8 *hw_csum;
+
+	/* The hardware checksum is 2 bytes appended to packet data */
+	if (unlikely(skb->len < sizeof(__sum16)))
+		return;
+	hw_csum = skb_tail_pointer(skb) - sizeof(__sum16);
+	skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb_trim(skb, skb->len - sizeof(__sum16));
+}
+
 /* Packet receive function */
 static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 {
@@ -1633,7 +1656,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 		 * the RFS bits are from bit 25 to bit 16. So, the
 		 * driver needs right shifting by 16.
 		 */
-		if (mdp->cd->hw_checksum)
+		if (mdp->cd->csmr)
 			desc_status >>= 16;
 
 		skb = mdp->rx_skbuff[entry];
@@ -1666,6 +1689,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 					 DMA_FROM_DEVICE);
 			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, ndev);
+			if (ndev->features & NETIF_F_RXCSUM)
+				sh_eth_rx_csum(skb);
 			netif_receive_skb(skb);
 			ndev->stats.rx_packets++;
 			ndev->stats.rx_bytes += pkt_len;
@@ -1989,7 +2014,6 @@ static void sh_eth_adjust_link(struct net_device *ndev)
 	if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link)
 		sh_eth_rcv_snd_enable(ndev);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mdp->lock, flags);
 
 	if (new_state && netif_msg_link(mdp))
@@ -2173,7 +2197,7 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf)
 	add_reg(MAFCR);
 	if (cd->rtrate)
 		add_reg(RTRATE);
-	if (cd->hw_checksum)
+	if (cd->csmr)
 		add_reg(CSMR);
 	if (cd->select_mii)
 		add_reg(RMII_MII);
@@ -2921,6 +2945,39 @@ static void sh_eth_set_rx_mode(struct net_device *ndev)
 	spin_unlock_irqrestore(&mdp->lock, flags);
 }
 
+static void sh_eth_set_rx_csum(struct net_device *ndev, bool enable)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mdp->lock, flags);
+
+	/* Disable TX and RX */
+	sh_eth_rcv_snd_disable(ndev);
+
+	/* Modify RX Checksum setting */
+	sh_eth_modify(ndev, ECMR, ECMR_RCSC, enable ? ECMR_RCSC : 0);
+
+	/* Enable TX and RX */
+	sh_eth_rcv_snd_enable(ndev);
+
+	spin_unlock_irqrestore(&mdp->lock, flags);
+}
+
+static int sh_eth_set_features(struct net_device *ndev,
+			       netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+
+	if (changed & NETIF_F_RXCSUM && mdp->cd->rx_csum)
+		sh_eth_set_rx_csum(ndev, features & NETIF_F_RXCSUM);
+
+	ndev->features = features;
+
+	return 0;
+}
+
 static int sh_eth_get_vtag_index(struct sh_eth_private *mdp)
 {
 	if (!mdp->port)
@@ -3102,6 +3159,7 @@ static const struct net_device_ops sh_eth_netdev_ops = {
 	.ndo_change_mtu		= sh_eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_set_features	= sh_eth_set_features,
 };
 
 static const struct net_device_ops sh_eth_netdev_ops_tsu = {
@@ -3117,6 +3175,7 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = {
 	.ndo_change_mtu		= sh_eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_set_features	= sh_eth_set_features,
 };
 
 #ifdef CONFIG_OF
@@ -3125,16 +3184,20 @@ static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev)
 	struct device_node *np = dev->of_node;
 	struct sh_eth_plat_data *pdata;
 	const char *mac_addr;
+	int ret;
 
 	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return NULL;
 
-	pdata->phy_interface = of_get_phy_mode(np);
+	ret = of_get_phy_mode(np);
+	if (ret < 0)
+		return NULL;
+	pdata->phy_interface = ret;
 
 	mac_addr = of_get_mac_address(np);
-	if (mac_addr)
-		memcpy(pdata->mac_addr, mac_addr, ETH_ALEN);
+	if (!IS_ERR(mac_addr))
+		ether_addr_copy(pdata->mac_addr, mac_addr);
 
 	pdata->no_ether_link =
 		of_property_read_bool(np, "renesas,no-ether-link");
@@ -3245,6 +3308,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	ndev->max_mtu = 2000 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN);
 	ndev->min_mtu = ETH_MIN_MTU;
 
+	if (mdp->cd->rx_csum) {
+		ndev->features = NETIF_F_RXCSUM;
+		ndev->hw_features = NETIF_F_RXCSUM;
+	}
+
 	/* set function */
 	if (mdp->cd->tsu)
 		ndev->netdev_ops = &sh_eth_netdev_ops_tsu;
@@ -3294,7 +3362,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 			goto out_release;
 		}
 		mdp->port = port;
-		ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER;
+		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
 		/* Need to init only the first port of the two sharing a TSU */
 		if (port == 0) {
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 0c18650bbfe6..850726301e1c 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -499,7 +499,8 @@ struct sh_eth_cpu_data {
 	unsigned no_ade:1;	/* E-DMAC DOES NOT have ADE bit in EESR */
 	unsigned no_xdfar:1;	/* E-DMAC DOES NOT have RDFAR/TDFAR */
 	unsigned xdfar_rw:1;	/* E-DMAC has writeable RDFAR/TDFAR */
-	unsigned hw_checksum:1;	/* E-DMAC has CSMR */
+	unsigned csmr:1;	/* E-DMAC has CSMR */
+	unsigned rx_csum:1;	/* EtherC has ECMR.RCSC */
 	unsigned select_mii:1;	/* EtherC has RMII_MII (MII select register) */
 	unsigned rmiimode:1;	/* EtherC has RMIIMODE register */
 	unsigned rtrate:1;	/* EtherC has RTRATE register */
diff --git a/drivers/net/ethernet/rocker/Kconfig b/drivers/net/ethernet/rocker/Kconfig
index b9952ef040e4..1083de99830d 100644
--- a/drivers/net/ethernet/rocker/Kconfig
+++ b/drivers/net/ethernet/rocker/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Rocker device configuration
 #
diff --git a/drivers/net/ethernet/rocker/Makefile b/drivers/net/ethernet/rocker/Makefile
index faa36acee223..6e0a363ac148 100644
--- a/drivers/net/ethernet/rocker/Makefile
+++ b/drivers/net/ethernet/rocker/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Rocker network device drivers.
 #
diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h
index 748fb12260a6..6fad25321dc5 100644
--- a/drivers/net/ethernet/rocker/rocker.h
+++ b/drivers/net/ethernet/rocker/rocker.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/rocker/rocker.h - Rocker switch device driver
  * Copyright (c) 2014-2016 Jiri Pirko <jiri@mellanox.com>
  * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _ROCKER_H
@@ -109,8 +105,6 @@ struct rocker_world_ops {
 	int (*port_attr_bridge_flags_set)(struct rocker_port *rocker_port,
 					  unsigned long brport_flags,
 					  struct switchdev_trans *trans);
-	int (*port_attr_bridge_flags_get)(const struct rocker_port *rocker_port,
-					  unsigned long *p_brport_flags);
 	int (*port_attr_bridge_flags_support_get)(const struct rocker_port *
 						  rocker_port,
 						  unsigned long *
diff --git a/drivers/net/ethernet/rocker/rocker_hw.h b/drivers/net/ethernet/rocker/rocker_hw.h
index 2adfe88859f2..59f1f8b690d2 100644
--- a/drivers/net/ethernet/rocker/rocker_hw.h
+++ b/drivers/net/ethernet/rocker/rocker_hw.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/rocker/rocker_hw.h - Rocker switch device driver
  * Copyright (c) 2014-2016 Jiri Pirko <jiri@mellanox.com>
  * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _ROCKER_HW_H
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 6213827e3956..079f459c73a5 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/rocker/rocker.c - Rocker switch device driver
  * Copyright (c) 2014-2016 Jiri Pirko <jiri@mellanox.com>
  * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -1566,45 +1562,57 @@ static int rocker_world_port_attr_stp_state_set(struct rocker_port *rocker_port,
 }
 
 static int
-rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
-					unsigned long brport_flags,
-					struct switchdev_trans *trans)
+rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port *
+						rocker_port,
+						unsigned long *
+						p_brport_flags_support)
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
 
-	if (!wops->port_attr_bridge_flags_set)
+	if (!wops->port_attr_bridge_flags_support_get)
 		return -EOPNOTSUPP;
-
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
-
-	return wops->port_attr_bridge_flags_set(rocker_port, brport_flags,
-						trans);
+	return wops->port_attr_bridge_flags_support_get(rocker_port,
+							p_brport_flags_support);
 }
 
 static int
-rocker_world_port_attr_bridge_flags_get(const struct rocker_port *rocker_port,
-					unsigned long *p_brport_flags)
+rocker_world_port_attr_pre_bridge_flags_set(struct rocker_port *rocker_port,
+					    unsigned long brport_flags,
+					    struct switchdev_trans *trans)
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
+	unsigned long brport_flags_s;
+	int err;
 
-	if (!wops->port_attr_bridge_flags_get)
+	if (!wops->port_attr_bridge_flags_set)
 		return -EOPNOTSUPP;
-	return wops->port_attr_bridge_flags_get(rocker_port, p_brport_flags);
+
+	err = rocker_world_port_attr_bridge_flags_support_get(rocker_port,
+							      &brport_flags_s);
+	if (err)
+		return err;
+
+	if (brport_flags & ~brport_flags_s)
+		return -EINVAL;
+
+	return 0;
 }
 
 static int
-rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port *
-						rocker_port,
-						unsigned long *
-						p_brport_flags_support)
+rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
+					unsigned long brport_flags,
+					struct switchdev_trans *trans)
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
 
-	if (!wops->port_attr_bridge_flags_support_get)
+	if (!wops->port_attr_bridge_flags_set)
 		return -EOPNOTSUPP;
-	return wops->port_attr_bridge_flags_support_get(rocker_port,
-							p_brport_flags_support);
+
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
+	return wops->port_attr_bridge_flags_set(rocker_port, brport_flags,
+						trans);
 }
 
 static int
@@ -2026,6 +2034,18 @@ static void rocker_port_neigh_destroy(struct net_device *dev,
 			    err);
 }
 
+static int rocker_port_get_port_parent_id(struct net_device *dev,
+					  struct netdev_phys_item_id *ppid)
+{
+	const struct rocker_port *rocker_port = netdev_priv(dev);
+	const struct rocker *rocker = rocker_port->rocker;
+
+	ppid->id_len = sizeof(rocker->hw.id);
+	memcpy(&ppid->id, &rocker->hw.id, ppid->id_len);
+
+	return 0;
+}
+
 static const struct net_device_ops rocker_port_netdev_ops = {
 	.ndo_open			= rocker_port_open,
 	.ndo_stop			= rocker_port_stop,
@@ -2035,39 +2055,13 @@ static const struct net_device_ops rocker_port_netdev_ops = {
 	.ndo_get_phys_port_name		= rocker_port_get_phys_port_name,
 	.ndo_change_proto_down		= rocker_port_change_proto_down,
 	.ndo_neigh_destroy		= rocker_port_neigh_destroy,
+	.ndo_get_port_parent_id		= rocker_port_get_port_parent_id,
 };
 
 /********************
  * swdev interface
  ********************/
 
-static int rocker_port_attr_get(struct net_device *dev,
-				struct switchdev_attr *attr)
-{
-	const struct rocker_port *rocker_port = netdev_priv(dev);
-	const struct rocker *rocker = rocker_port->rocker;
-	int err = 0;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(rocker->hw.id);
-		memcpy(&attr->u.ppid.id, &rocker->hw.id, attr->u.ppid.id_len);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
-		err = rocker_world_port_attr_bridge_flags_get(rocker_port,
-							      &attr->u.brport_flags);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
-		err = rocker_world_port_attr_bridge_flags_support_get(rocker_port,
-								      &attr->u.brport_flags_support);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return err;
-}
-
 static int rocker_port_attr_set(struct net_device *dev,
 				const struct switchdev_attr *attr,
 				struct switchdev_trans *trans)
@@ -2081,6 +2075,11 @@ static int rocker_port_attr_set(struct net_device *dev,
 							   attr->u.stp_state,
 							   trans);
 		break;
+	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+		err = rocker_world_port_attr_pre_bridge_flags_set(rocker_port,
+							      attr->u.brport_flags,
+							      trans);
+		break;
 	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
 		err = rocker_world_port_attr_bridge_flags_set(rocker_port,
 							      attr->u.brport_flags,
@@ -2139,11 +2138,6 @@ static int rocker_port_obj_del(struct net_device *dev,
 	return err;
 }
 
-static const struct switchdev_ops rocker_port_switchdev_ops = {
-	.switchdev_port_attr_get	= rocker_port_attr_get,
-	.switchdev_port_attr_set	= rocker_port_attr_set,
-};
-
 struct rocker_fib_event_work {
 	struct work_struct work;
 	union {
@@ -2209,6 +2203,19 @@ static int rocker_router_fib_event(struct notifier_block *nb,
 	switch (event) {
 	case FIB_EVENT_ENTRY_ADD: /* fall through */
 	case FIB_EVENT_ENTRY_DEL:
+		if (info->family == AF_INET) {
+			struct fib_entry_notifier_info *fen_info = ptr;
+
+			if (fen_info->fi->fib_nh_is_v6) {
+				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+				return notifier_from_errno(-EINVAL);
+			}
+			if (fen_info->fi->nh) {
+				NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
+				return notifier_from_errno(-EINVAL);
+			}
+		}
+
 		memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info));
 		/* Take referece on fib_info to prevent it from being
 		 * freed while work is queued. Release it afterwards.
@@ -2597,7 +2604,6 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 	rocker_port_dev_addr_init(rocker_port);
 	dev->netdev_ops = &rocker_port_netdev_ops;
 	dev->ethtool_ops = &rocker_port_ethtool_ops;
-	dev->switchdev_ops = &rocker_port_switchdev_ops;
 	netif_tx_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx,
 			  NAPI_POLL_WEIGHT);
 	netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx,
@@ -2708,6 +2714,19 @@ static bool rocker_port_dev_check(const struct net_device *dev)
 	return dev->netdev_ops == &rocker_port_netdev_ops;
 }
 
+static int
+rocker_switchdev_port_attr_set_event(struct net_device *netdev,
+		struct switchdev_notifier_port_attr_info *port_attr_info)
+{
+	int err;
+
+	err = rocker_port_attr_set(netdev, port_attr_info->attr,
+				   port_attr_info->trans);
+
+	port_attr_info->handled = true;
+	return notifier_from_errno(err);
+}
+
 struct rocker_switchdev_event_work {
 	struct work_struct work;
 	struct switchdev_notifier_fdb_info fdb_info;
@@ -2725,7 +2744,7 @@ rocker_fdb_offload_notify(struct rocker_port *rocker_port,
 	info.vid = recv_info->vid;
 	info.offloaded = true;
 	call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED,
-				 rocker_port->dev, &info.info);
+				 rocker_port->dev, &info.info, NULL);
 }
 
 static void rocker_switchdev_event_work(struct work_struct *work)
@@ -2777,6 +2796,9 @@ static int rocker_switchdev_event(struct notifier_block *unused,
 	if (!rocker_port_dev_check(dev))
 		return NOTIFY_DONE;
 
+	if (event == SWITCHDEV_PORT_ATTR_SET)
+		return rocker_switchdev_port_attr_set_event(dev, ptr);
+
 	rocker_port = netdev_priv(dev);
 	switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
 	if (WARN_ON(!switchdev_work))
@@ -2792,6 +2814,11 @@ static int rocker_switchdev_event(struct notifier_block *unused,
 		memcpy(&switchdev_work->fdb_info, ptr,
 		       sizeof(switchdev_work->fdb_info));
 		switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
+		if (unlikely(!switchdev_work->fdb_info.addr)) {
+			kfree(switchdev_work);
+			return NOTIFY_BAD;
+		}
+
 		ether_addr_copy((u8 *)switchdev_work->fdb_info.addr,
 				fdb_info->addr);
 		/* Take a reference on the rocker device */
@@ -2839,6 +2866,8 @@ static int rocker_switchdev_blocking_event(struct notifier_block *unused,
 	case SWITCHDEV_PORT_OBJ_ADD:
 	case SWITCHDEV_PORT_OBJ_DEL:
 		return rocker_switchdev_port_obj_event(event, dev, ptr);
+	case SWITCHDEV_PORT_ATTR_SET:
+		return rocker_switchdev_port_attr_set_event(dev, ptr);
 	}
 
 	return NOTIFY_DONE;
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 6473cc68c2d5..7072b249c8bd 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/rocker/rocker_ofdpa.c - Rocker switch OF-DPA-like
  *					        implementation
  * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
  * Copyright (c) 2014-2016 Jiri Pirko <jiri@mellanox.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/kernel.h>
@@ -22,6 +18,7 @@
 #include <net/neighbour.h>
 #include <net/switchdev.h>
 #include <net/ip_fib.h>
+#include <net/nexthop.h>
 #include <net/arp.h>
 
 #include "rocker.h"
@@ -1833,10 +1830,10 @@ static void ofdpa_port_fdb_learn_work(struct work_struct *work)
 	rtnl_lock();
 	if (learned && removing)
 		call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE,
-					 lw->ofdpa_port->dev, &info.info);
+					 lw->ofdpa_port->dev, &info.info, NULL);
 	else if (learned && !removing)
 		call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE,
-					 lw->ofdpa_port->dev, &info.info);
+					 lw->ofdpa_port->dev, &info.info, NULL);
 	rtnl_unlock();
 
 	kfree(work);
@@ -2286,13 +2283,13 @@ static int ofdpa_port_fib_ipv4(struct ofdpa_port *ofdpa_port,  __be32 dst,
 
 	/* XXX support ECMP */
 
-	nh = fi->fib_nh;
-	nh_on_port = (fi->fib_dev == ofdpa_port->dev);
-	has_gw = !!nh->nh_gw;
+	nh = fib_info_nh(fi, 0);
+	nh_on_port = (nh->fib_nh_dev == ofdpa_port->dev);
+	has_gw = !!nh->fib_nh_gw4;
 
 	if (has_gw && nh_on_port) {
 		err = ofdpa_port_ipv4_nh(ofdpa_port, flags,
-					 nh->nh_gw, &index);
+					 nh->fib_nh_gw4, &index);
 		if (err)
 			return err;
 
@@ -2512,16 +2509,6 @@ static int ofdpa_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
 }
 
 static int
-ofdpa_port_attr_bridge_flags_get(const struct rocker_port *rocker_port,
-				 unsigned long *p_brport_flags)
-{
-	const struct ofdpa_port *ofdpa_port = rocker_port->wpriv;
-
-	*p_brport_flags = ofdpa_port->brport_flags;
-	return 0;
-}
-
-static int
 ofdpa_port_attr_bridge_flags_support_get(const struct rocker_port *
 					 rocker_port,
 					 unsigned long *
@@ -2747,11 +2734,13 @@ static int ofdpa_fib4_add(struct rocker *rocker,
 {
 	struct ofdpa *ofdpa = rocker->wpriv;
 	struct ofdpa_port *ofdpa_port;
+	struct fib_nh *nh;
 	int err;
 
 	if (ofdpa->fib_aborted)
 		return 0;
-	ofdpa_port = ofdpa_port_dev_lower_find(fen_info->fi->fib_dev, rocker);
+	nh = fib_info_nh(fen_info->fi, 0);
+	ofdpa_port = ofdpa_port_dev_lower_find(nh->fib_nh_dev, rocker);
 	if (!ofdpa_port)
 		return 0;
 	err = ofdpa_port_fib_ipv4(ofdpa_port, htonl(fen_info->dst),
@@ -2759,7 +2748,7 @@ static int ofdpa_fib4_add(struct rocker *rocker,
 				  fen_info->tb_id, 0);
 	if (err)
 		return err;
-	fen_info->fi->fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+	nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 	return 0;
 }
 
@@ -2768,13 +2757,15 @@ static int ofdpa_fib4_del(struct rocker *rocker,
 {
 	struct ofdpa *ofdpa = rocker->wpriv;
 	struct ofdpa_port *ofdpa_port;
+	struct fib_nh *nh;
 
 	if (ofdpa->fib_aborted)
 		return 0;
-	ofdpa_port = ofdpa_port_dev_lower_find(fen_info->fi->fib_dev, rocker);
+	nh = fib_info_nh(fen_info->fi, 0);
+	ofdpa_port = ofdpa_port_dev_lower_find(nh->fib_nh_dev, rocker);
 	if (!ofdpa_port)
 		return 0;
-	fen_info->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+	nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	return ofdpa_port_fib_ipv4(ofdpa_port, htonl(fen_info->dst),
 				   fen_info->dst_len, fen_info->fi,
 				   fen_info->tb_id, OFDPA_OP_FLAG_REMOVE);
@@ -2794,14 +2785,16 @@ static void ofdpa_fib4_abort(struct rocker *rocker)
 
 	spin_lock_irqsave(&ofdpa->flow_tbl_lock, flags);
 	hash_for_each_safe(ofdpa->flow_tbl, bkt, tmp, flow_entry, entry) {
+		struct fib_nh *nh;
+
 		if (flow_entry->key.tbl_id !=
 		    ROCKER_OF_DPA_TABLE_ID_UNICAST_ROUTING)
 			continue;
-		ofdpa_port = ofdpa_port_dev_lower_find(flow_entry->fi->fib_dev,
-						       rocker);
+		nh = fib_info_nh(flow_entry->fi, 0);
+		ofdpa_port = ofdpa_port_dev_lower_find(nh->fib_nh_dev, rocker);
 		if (!ofdpa_port)
 			continue;
-		flow_entry->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+		nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 		ofdpa_flow_tbl_del(ofdpa_port, OFDPA_OP_FLAG_REMOVE,
 				   flow_entry);
 	}
@@ -2823,7 +2816,6 @@ struct rocker_world_ops rocker_ofdpa_ops = {
 	.port_stop = ofdpa_port_stop,
 	.port_attr_stp_state_set = ofdpa_port_attr_stp_state_set,
 	.port_attr_bridge_flags_set = ofdpa_port_attr_bridge_flags_set,
-	.port_attr_bridge_flags_get = ofdpa_port_attr_bridge_flags_get,
 	.port_attr_bridge_flags_support_get = ofdpa_port_attr_bridge_flags_support_get,
 	.port_attr_bridge_ageing_time_set = ofdpa_port_attr_bridge_ageing_time_set,
 	.port_obj_vlan_add = ofdpa_port_obj_vlan_add,
diff --git a/drivers/net/ethernet/rocker/rocker_tlv.c b/drivers/net/ethernet/rocker/rocker_tlv.c
index 8185118f3492..256447b7599b 100644
--- a/drivers/net/ethernet/rocker/rocker_tlv.c
+++ b/drivers/net/ethernet/rocker/rocker_tlv.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * drivers/net/ethernet/rocker/rocker_tlv.c - Rocker switch device driver
  * Copyright (c) 2014-2016 Jiri Pirko <jiri@mellanox.com>
  * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/rocker/rocker_tlv.h b/drivers/net/ethernet/rocker/rocker_tlv.h
index dfae3c9d57c6..fe876e5d5b01 100644
--- a/drivers/net/ethernet/rocker/rocker_tlv.h
+++ b/drivers/net/ethernet/rocker/rocker_tlv.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * drivers/net/ethernet/rocker/rocker_tlv.h - Rocker switch device driver
  * Copyright (c) 2014-2016 Jiri Pirko <jiri@mellanox.com>
  * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _ROCKER_TLV_H
diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig
index fbd5e06654c6..027938017579 100644
--- a/drivers/net/ethernet/samsung/Kconfig
+++ b/drivers/net/ethernet/samsung/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Samsung Ethernet device configuration
 #
diff --git a/drivers/net/ethernet/samsung/Makefile b/drivers/net/ethernet/samsung/Makefile
index 1773c29b8d76..f94faecc2a0b 100644
--- a/drivers/net/ethernet/samsung/Makefile
+++ b/drivers/net/ethernet/samsung/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Samsung Ethernet device drivers.
 #
diff --git a/drivers/net/ethernet/samsung/sxgbe/Makefile b/drivers/net/ethernet/samsung/sxgbe/Makefile
index 31e968561d5c..b7e29d08874c 100644
--- a/drivers/net/ethernet/samsung/sxgbe/Makefile
+++ b/drivers/net/ethernet/samsung/sxgbe/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_SXGBE_ETH) += samsung-sxgbe.o
 samsung-sxgbe-objs:= sxgbe_platform.o sxgbe_main.o sxgbe_desc.o \
 		sxgbe_dma.o sxgbe_core.o sxgbe_mtl.o  sxgbe_mdio.o \
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
index c61f260e18a4..049dc6cf4611 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __SXGBE_COMMON_H__
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
index 58c35692560e..e96e2bd295ef 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
index 2686bb5b6765..b33ebf2dca47 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
index 18609324db72..ede0827bf122 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef __SXGBE_DESC_H__
 #define __SXGBE_DESC_H__
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
index bb9b5b8afc5f..243db04b968c 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/delay.h>
 #include <linux/export.h>
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
index 1607b54c9bb0..e8f79a297278 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef __SXGBE_DMA_H__
 #define __SXGBE_DMA_H__
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
index c9aad0eda57f..0775b9464b4e 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 6d22dd500790..c56fcbb37066 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
index 467ff7033606..b1e7f7ab281c 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
index 324681c2bb74..298a7402e39c 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
index 7e4810c4137e..e5634520700f 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef __SXGBE_MTL_H__
 #define __SXGBE_MTL_H__
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
index fbd00cb0cb7d..d2c48116f181 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -124,7 +121,7 @@ static int sxgbe_platform_probe(struct platform_device *pdev)
 	}
 
 	/* Get MAC address if available (DT) */
-	if (mac)
+	if (!IS_ERR_OR_NULL(mac))
 		ether_addr_copy(priv->dev->dev_addr, mac);
 
 	/* Get the TX/RX IRQ numbers */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
index 81437d91df99..4def84ebf143 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* 10G controller driver for Samsung SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
  * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef __SXGBE_REGMAP_H__
 #define __SXGBE_REGMAP_H__
diff --git a/drivers/net/ethernet/seeq/Kconfig b/drivers/net/ethernet/seeq/Kconfig
index 69c62d89295e..f3ac9cba5770 100644
--- a/drivers/net/ethernet/seeq/Kconfig
+++ b/drivers/net/ethernet/seeq/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # SEEQ device configuration
 #
diff --git a/drivers/net/ethernet/seeq/Makefile b/drivers/net/ethernet/seeq/Makefile
index 0488e99b831f..02aad7869fa5 100644
--- a/drivers/net/ethernet/seeq/Makefile
+++ b/drivers/net/ethernet/seeq/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the SEEQ network device drivers
 #
diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
index d1bb73bf9914..632a7c85964d 100644
--- a/drivers/net/ethernet/seeq/ether3.c
+++ b/drivers/net/ethernet/seeq/ether3.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/drivers/acorn/net/ether3.c
  *
  *  Copyright (C) 1995-2000 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * SEEQ nq8005 ethernet driver for Acorn/ANT Ether3 card
  *  for Acorn machines
  *
diff --git a/drivers/net/ethernet/seeq/ether3.h b/drivers/net/ethernet/seeq/ether3.h
index be19e5fa5cf2..585dd51be201 100644
--- a/drivers/net/ethernet/seeq/ether3.h
+++ b/drivers/net/ethernet/seeq/ether3.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/drivers/acorn/net/ether3.h
  *
  *  Copyright (C) 1995-2000 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  network driver for Acorn/ANT Ether3 cards
  */
 
diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c
index 70cce63a6081..7a5e6c5abb57 100644
--- a/drivers/net/ethernet/seeq/sgiseeq.c
+++ b/drivers/net/ethernet/seeq/sgiseeq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * sgiseeq.c: Seeq8003 ethernet driver for SGI machines.
  *
@@ -735,6 +736,7 @@ static int sgiseeq_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
 	sp = netdev_priv(dev);
 
 	/* Make private data page aligned */
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 2c032629c369..5f36774bf4b8 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Solarflare device configuration
 #
diff --git a/drivers/net/ethernet/sfc/bitfield.h b/drivers/net/ethernet/sfc/bitfield.h
index 41ad07d45144..1b59e9fe58b4 100644
--- a/drivers/net/ethernet/sfc/bitfield.h
+++ b/drivers/net/ethernet/sfc/bitfield.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_BITFIELD_H
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 2f2bda68d861..16d6952c312a 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2012-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include "net_driver.h"
@@ -6041,10 +6038,13 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = {
 	{ NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3, 0,   3, "sfc_exp_rom_cfg" },
 	{ NVRAM_PARTITION_TYPE_LICENSE,		   0,    0, "sfc_license" },
 	{ NVRAM_PARTITION_TYPE_PHY_MIN,		   0xff, 0, "sfc_phy_fw" },
-	/* MUM and SUC firmware share the same partition type */
 	{ NVRAM_PARTITION_TYPE_MUM_FIRMWARE,	   0,    0, "sfc_mumfw" },
 	{ NVRAM_PARTITION_TYPE_EXPANSION_UEFI,	   0,    0, "sfc_uefi" },
-	{ NVRAM_PARTITION_TYPE_STATUS,		   0,    0, "sfc_status" }
+	{ NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS, 0,    0, "sfc_dynamic_cfg_dflt" },
+	{ NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS, 0,    0, "sfc_exp_rom_cfg_dflt" },
+	{ NVRAM_PARTITION_TYPE_STATUS,		   0,    0, "sfc_status" },
+	{ NVRAM_PARTITION_TYPE_BUNDLE,		   0,    0, "sfc_bundle" },
+	{ NVRAM_PARTITION_TYPE_BUNDLE_METADATA,	   0,    0, "sfc_bundle_metadata" },
 };
 #define EF10_NVRAM_PARTITION_COUNT	ARRAY_SIZE(efx_ef10_nvram_types)
 
@@ -6074,8 +6074,15 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
 	if (rc)
 		return rc;
+	if (protected &&
+	    (type != NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS &&
+	     type != NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS))
+		/* Hide protected partitions that don't provide defaults. */
+		return -ENODEV;
+
 	if (protected)
-		return -ENODEV; /* hide it */
+		/* Protected partitions are read only. */
+		erase_size = 0;
 
 	/* If we've already exposed a partition of this type, hide this
 	 * duplicate.  All operations on MTDs are keyed by the type anyway,
@@ -6115,7 +6122,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 static int efx_ef10_mtd_probe(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX);
-	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT);
+	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 };
 	struct efx_mcdi_mtd_partition *parts;
 	size_t outlen, n_parts_total, i, n_parts;
 	unsigned int type;
diff --git a/drivers/net/ethernet/sfc/ef10_regs.h b/drivers/net/ethernet/sfc/ef10_regs.h
index 6a56778cf06c..154cfad95186 100644
--- a/drivers/net/ethernet/sfc/ef10_regs.h
+++ b/drivers/net/ethernet/sfc/ef10_regs.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2012-2017 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_EF10_REGS_H
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 3d76fd1504c2..52bd43f45761 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h
index 2aa444ed42de..cfe556d17313 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.h
+++ b/drivers/net/ethernet/sfc/ef10_sriov.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF10_SRIOV_H
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 3643015a55cf..ab58b837df47 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/module.h>
@@ -915,7 +912,7 @@ rollback:
 
 void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
 {
-	mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100));
+	mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(10));
 }
 
 static bool efx_default_channel_want_txqs(struct efx_channel *channel)
@@ -3617,11 +3614,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 		netif_warn(efx, probe, efx->net_dev,
 			   "failed to create MTDs (%d)\n", rc);
 
-	rc = pci_enable_pcie_error_reporting(pci_dev);
-	if (rc && rc != -EINVAL)
-		netif_notice(efx, probe, efx->net_dev,
-			     "PCIE error reporting unavailable (%d).\n",
-			     rc);
+	(void)pci_enable_pcie_error_reporting(pci_dev);
 
 	if (efx->type->udp_tnl_push_ports)
 		efx->type->udp_tnl_push_ports(efx);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 3f759ebdcf10..04fed7c06618 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_EFX_H
diff --git a/drivers/net/ethernet/sfc/enum.h b/drivers/net/ethernet/sfc/enum.h
index 6fa824211d91..3332cdf2918a 100644
--- a/drivers/net/ethernet/sfc/enum.h
+++ b/drivers/net/ethernet/sfc/enum.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2007-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_ENUM_H
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 600d7b895cf2..86b965875540 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/sfc/falcon/Kconfig b/drivers/net/ethernet/sfc/falcon/Kconfig
index 6248e96253a2..20e361950f7d 100644
--- a/drivers/net/ethernet/sfc/falcon/Kconfig
+++ b/drivers/net/ethernet/sfc/falcon/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config SFC_FALCON
 	tristate "Solarflare SFC4000 support"
 	depends on PCI
diff --git a/drivers/net/ethernet/sfc/falcon/bitfield.h b/drivers/net/ethernet/sfc/falcon/bitfield.h
index 230fd77bd311..5eb178d0c149 100644
--- a/drivers/net/ethernet/sfc/falcon/bitfield.h
+++ b/drivers/net/ethernet/sfc/falcon/bitfield.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_BITFIELD_H
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index 8b1f94d7a6c5..9b15c39ac670 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/sfc/falcon/efx.h b/drivers/net/ethernet/sfc/falcon/efx.h
index a4e4d8ea4078..d3b4646545fa 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.h
+++ b/drivers/net/ethernet/sfc/falcon/efx.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_EFX_H
diff --git a/drivers/net/ethernet/sfc/falcon/enum.h b/drivers/net/ethernet/sfc/falcon/enum.h
index 4824fcf5c3d4..7e6277fb47ec 100644
--- a/drivers/net/ethernet/sfc/falcon/enum.h
+++ b/drivers/net/ethernet/sfc/falcon/enum.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2007-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_ENUM_H
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index 72cedec945c1..08bd6a321918 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/sfc/falcon/falcon.c b/drivers/net/ethernet/sfc/falcon/falcon.c
index 6520d7bc8d21..3324a6219a09 100644
--- a/drivers/net/ethernet/sfc/falcon/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon/falcon.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/sfc/falcon/falcon_boards.c b/drivers/net/ethernet/sfc/falcon/falcon_boards.c
index dec83a217093..839189dab98e 100644
--- a/drivers/net/ethernet/sfc/falcon/falcon_boards.c
+++ b/drivers/net/ethernet/sfc/falcon/falcon_boards.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2007-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/rtnetlink.h>
diff --git a/drivers/net/ethernet/sfc/falcon/farch.c b/drivers/net/ethernet/sfc/falcon/farch.c
index 411a2f419447..332183280a45 100644
--- a/drivers/net/ethernet/sfc/falcon/farch.c
+++ b/drivers/net/ethernet/sfc/falcon/farch.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/sfc/falcon/farch_regs.h b/drivers/net/ethernet/sfc/falcon/farch_regs.h
index 8095f273d574..5b01f3f3fde1 100644
--- a/drivers/net/ethernet/sfc/falcon/farch_regs.h
+++ b/drivers/net/ethernet/sfc/falcon/farch_regs.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_FARCH_REGS_H
diff --git a/drivers/net/ethernet/sfc/falcon/filter.h b/drivers/net/ethernet/sfc/falcon/filter.h
index 647f6b2725c5..bc6f5f563e70 100644
--- a/drivers/net/ethernet/sfc/falcon/filter.h
+++ b/drivers/net/ethernet/sfc/falcon/filter.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_FILTER_H
diff --git a/drivers/net/ethernet/sfc/falcon/io.h b/drivers/net/ethernet/sfc/falcon/io.h
index 7085ee1d5e2b..bc23c800a10f 100644
--- a/drivers/net/ethernet/sfc/falcon/io.h
+++ b/drivers/net/ethernet/sfc/falcon/io.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_IO_H
@@ -108,7 +105,6 @@ static inline void ef4_writeo(struct ef4_nic *efx, const ef4_oword_t *value,
 	_ef4_writed(efx, value->u32[2], reg + 8);
 	_ef4_writed(efx, value->u32[3], reg + 12);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
@@ -130,7 +126,6 @@ static inline void ef4_sram_writeq(struct ef4_nic *efx, void __iomem *membase,
 	__raw_writel((__force u32)value->u32[0], membase + addr);
 	__raw_writel((__force u32)value->u32[1], membase + addr + 4);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
diff --git a/drivers/net/ethernet/sfc/falcon/mdio_10g.c b/drivers/net/ethernet/sfc/falcon/mdio_10g.c
index ee0713f03d01..540278161449 100644
--- a/drivers/net/ethernet/sfc/falcon/mdio_10g.c
+++ b/drivers/net/ethernet/sfc/falcon/mdio_10g.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2006-2011 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 /*
  * Useful functions for working with MDIO clause 45 PHYs
diff --git a/drivers/net/ethernet/sfc/falcon/mdio_10g.h b/drivers/net/ethernet/sfc/falcon/mdio_10g.h
index 53cb5cc4ad37..de676bfa064d 100644
--- a/drivers/net/ethernet/sfc/falcon/mdio_10g.h
+++ b/drivers/net/ethernet/sfc/falcon/mdio_10g.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2006-2011 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_MDIO_10G_H
diff --git a/drivers/net/ethernet/sfc/falcon/mtd.c b/drivers/net/ethernet/sfc/falcon/mtd.c
index 2d67e4621a3d..15bd47bf9e8e 100644
--- a/drivers/net/ethernet/sfc/falcon/mtd.c
+++ b/drivers/net/ethernet/sfc/falcon/mtd.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/sfc/falcon/net_driver.h b/drivers/net/ethernet/sfc/falcon/net_driver.h
index 37a8bdf32206..a49ea2e719b6 100644
--- a/drivers/net/ethernet/sfc/falcon/net_driver.h
+++ b/drivers/net/ethernet/sfc/falcon/net_driver.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 /* Common definitions for all Efx net driver code */
diff --git a/drivers/net/ethernet/sfc/falcon/nic.c b/drivers/net/ethernet/sfc/falcon/nic.c
index 9c07b5175581..156da315ec89 100644
--- a/drivers/net/ethernet/sfc/falcon/nic.c
+++ b/drivers/net/ethernet/sfc/falcon/nic.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/sfc/falcon/nic.h b/drivers/net/ethernet/sfc/falcon/nic.h
index 07c62dc552cb..9f413474bd9f 100644
--- a/drivers/net/ethernet/sfc/falcon/nic.h
+++ b/drivers/net/ethernet/sfc/falcon/nic.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_NIC_H
diff --git a/drivers/net/ethernet/sfc/falcon/phy.h b/drivers/net/ethernet/sfc/falcon/phy.h
index 362141cee313..69bb548eae59 100644
--- a/drivers/net/ethernet/sfc/falcon/phy.h
+++ b/drivers/net/ethernet/sfc/falcon/phy.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2007-2010 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_PHY_H
diff --git a/drivers/net/ethernet/sfc/falcon/qt202x_phy.c b/drivers/net/ethernet/sfc/falcon/qt202x_phy.c
index f5e0f18d4ea8..21af67e42296 100644
--- a/drivers/net/ethernet/sfc/falcon/qt202x_phy.c
+++ b/drivers/net/ethernet/sfc/falcon/qt202x_phy.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2006-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 /*
  * Driver for AMCC QT202x SFP+ and XFP adapters; see www.amcc.com for details
diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 02456ed13a7d..fd850d3d8ec0 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/socket.h>
diff --git a/drivers/net/ethernet/sfc/falcon/selftest.c b/drivers/net/ethernet/sfc/falcon/selftest.c
index 55c0fbbc4fb8..147677c7c72f 100644
--- a/drivers/net/ethernet/sfc/falcon/selftest.c
+++ b/drivers/net/ethernet/sfc/falcon/selftest.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/sfc/falcon/selftest.h b/drivers/net/ethernet/sfc/falcon/selftest.h
index be52a49c006a..c0dbc6394e0f 100644
--- a/drivers/net/ethernet/sfc/falcon/selftest.h
+++ b/drivers/net/ethernet/sfc/falcon/selftest.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_SELFTEST_H
diff --git a/drivers/net/ethernet/sfc/falcon/tenxpress.c b/drivers/net/ethernet/sfc/falcon/tenxpress.c
index ff9b4e2b590c..e27824ef121f 100644
--- a/drivers/net/ethernet/sfc/falcon/tenxpress.c
+++ b/drivers/net/ethernet/sfc/falcon/tenxpress.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2007-2011 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c
index 3409bbf5b19f..f7306e93a8b8 100644
--- a/drivers/net/ethernet/sfc/falcon/tx.c
+++ b/drivers/net/ethernet/sfc/falcon/tx.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/pci.h>
@@ -321,7 +318,7 @@ netdev_tx_t ef4_enqueue_skb(struct ef4_tx_queue *tx_queue, struct sk_buff *skb)
 	netdev_tx_sent_queue(tx_queue->core_txq, skb_len);
 
 	/* Pass off to hardware */
-	if (!skb->xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+	if (!netdev_xmit_more() || netif_xmit_stopped(tx_queue->core_txq)) {
 		struct ef4_tx_queue *txq2 = ef4_tx_queue_partner(tx_queue);
 
 		/* There could be packets left on the partner queue if those
@@ -333,7 +330,7 @@ netdev_tx_t ef4_enqueue_skb(struct ef4_tx_queue *tx_queue, struct sk_buff *skb)
 
 		ef4_nic_push_buffers(tx_queue);
 	} else {
-		tx_queue->xmit_more_available = skb->xmit_more;
+		tx_queue->xmit_more_available = netdev_xmit_more();
 	}
 
 	tx_queue->tx_packets++;
diff --git a/drivers/net/ethernet/sfc/falcon/tx.h b/drivers/net/ethernet/sfc/falcon/tx.h
index a607eb0087a8..2a88c59cbbbe 100644
--- a/drivers/net/ethernet/sfc/falcon/tx.h
+++ b/drivers/net/ethernet/sfc/falcon/tx.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_TX_H
diff --git a/drivers/net/ethernet/sfc/falcon/txc43128_phy.c b/drivers/net/ethernet/sfc/falcon/txc43128_phy.c
index 3c55fd23c271..f3503965c52c 100644
--- a/drivers/net/ethernet/sfc/falcon/txc43128_phy.c
+++ b/drivers/net/ethernet/sfc/falcon/txc43128_phy.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2006-2011 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 /*
diff --git a/drivers/net/ethernet/sfc/falcon/workarounds.h b/drivers/net/ethernet/sfc/falcon/workarounds.h
index 6af800bc9633..e28c67fc92a3 100644
--- a/drivers/net/ethernet/sfc/falcon/workarounds.h
+++ b/drivers/net/ethernet/sfc/falcon/workarounds.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EF4_WORKAROUNDS_H
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index e045a5d6b938..eedd32e2bfcb 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/sfc/farch_regs.h b/drivers/net/ethernet/sfc/farch_regs.h
index 7019a712e799..d138be423e63 100644
--- a/drivers/net/ethernet/sfc/farch_regs.h
+++ b/drivers/net/ethernet/sfc/farch_regs.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_FARCH_REGS_H
diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h
index 59021ad6d98d..40b2af8bfb81 100644
--- a/drivers/net/ethernet/sfc/filter.h
+++ b/drivers/net/ethernet/sfc/filter.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_FILTER_H
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 89563170af52..c3c011bc6a68 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_IO_H
@@ -120,7 +117,6 @@ static inline void efx_writeo(struct efx_nic *efx, const efx_oword_t *value,
 	_efx_writed(efx, value->u32[2], reg + 8);
 	_efx_writed(efx, value->u32[3], reg + 12);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
@@ -142,7 +138,6 @@ static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase,
 	__raw_writel((__force u32)value->u32[0], membase + addr);
 	__raw_writel((__force u32)value->u32[1], membase + addr + 4);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index dfad93fca0a6..2713300343c7 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2008-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/delay.h>
@@ -2074,22 +2071,26 @@ fail:
 
 static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
 {
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_START_IN_LEN);
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_START_V2_IN_LEN);
 	int rc;
 
 	MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_START_IN_TYPE, type);
+	MCDI_POPULATE_DWORD_1(inbuf, NVRAM_UPDATE_START_V2_IN_FLAGS,
+			      NVRAM_UPDATE_START_V2_IN_FLAG_REPORT_VERIFY_RESULT,
+			      1);
 
 	BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_START_OUT_LEN != 0);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_START, inbuf, sizeof(inbuf),
 			  NULL, 0, NULL);
+
 	return rc;
 }
 
 static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 			       loff_t offset, u8 *buffer, size_t length)
 {
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_READ_IN_LEN);
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_READ_IN_V2_LEN);
 	MCDI_DECLARE_BUF(outbuf,
 			 MC_CMD_NVRAM_READ_OUT_LEN(EFX_MCDI_NVRAM_LEN_MAX));
 	size_t outlen;
@@ -2098,6 +2099,8 @@ static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_TYPE, type);
 	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_OFFSET, offset);
 	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_LENGTH, length);
+	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_V2_MODE,
+		       MC_CMD_NVRAM_READ_IN_V2_DEFAULT);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_READ, inbuf, sizeof(inbuf),
 			  outbuf, sizeof(outbuf), &outlen);
@@ -2147,15 +2150,51 @@ static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
 
 static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 {
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN);
-	int rc;
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN);
+	size_t outlen;
+	int rc, rc2;
 
 	MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_FINISH_IN_TYPE, type);
-
-	BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN != 0);
+	/* Always set this flag. Old firmware ignores it */
+	MCDI_POPULATE_DWORD_1(inbuf, NVRAM_UPDATE_FINISH_V2_IN_FLAGS,
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_REPORT_VERIFY_RESULT,
+			      1);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf),
-			  NULL, 0, NULL);
+			  outbuf, sizeof(outbuf), &outlen);
+	if (!rc && outlen >= MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN) {
+		rc2 = MCDI_DWORD(outbuf, NVRAM_UPDATE_FINISH_V2_OUT_RESULT_CODE);
+		if (rc2 != MC_CMD_NVRAM_VERIFY_RC_SUCCESS)
+			netif_err(efx, drv, efx->net_dev,
+				  "NVRAM update failed verification with code 0x%x\n",
+				  rc2);
+		switch (rc2) {
+		case MC_CMD_NVRAM_VERIFY_RC_SUCCESS:
+			break;
+		case MC_CMD_NVRAM_VERIFY_RC_CMS_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_MESSAGE_DIGEST_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_TRUSTED_APPROVERS_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHAIN_CHECK_FAILED:
+			rc = -EIO;
+			break;
+		case MC_CMD_NVRAM_VERIFY_RC_INVALID_CMS_FORMAT:
+		case MC_CMD_NVRAM_VERIFY_RC_BAD_MESSAGE_DIGEST:
+			rc = -EINVAL;
+			break;
+		case MC_CMD_NVRAM_VERIFY_RC_NO_VALID_SIGNATURES:
+		case MC_CMD_NVRAM_VERIFY_RC_NO_TRUSTED_APPROVERS:
+		case MC_CMD_NVRAM_VERIFY_RC_NO_SIGNATURE_MATCH:
+			rc = -EPERM;
+			break;
+		default:
+			netif_err(efx, drv, efx->net_dev,
+				  "Unknown response to NVRAM_UPDATE_FINISH\n");
+			rc = -EIO;
+		}
+	}
+
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index ebd95972ae7b..9081f84a2604 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2008-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_MCDI_H
diff --git a/drivers/net/ethernet/sfc/mcdi_mon.c b/drivers/net/ethernet/sfc/mcdi_mon.c
index f17751559ccc..5954fcfee2b1 100644
--- a/drivers/net/ethernet/sfc/mcdi_mon.c
+++ b/drivers/net/ethernet/sfc/mcdi_mon.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2011-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index 3839eec783ea..79d834a4ae49 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2009-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 
@@ -6784,6 +6781,14 @@
  * subset of the information stored in this partition.
  */
 #define          NVRAM_PARTITION_TYPE_FRU_INFORMATION 0x1d00
+/* enum: Bundle image partition */
+#define          NVRAM_PARTITION_TYPE_BUNDLE 0x1e00
+/* enum: Bundle metadata partition that holds additional information related to
+ * a bundle update in TLV format
+ */
+#define          NVRAM_PARTITION_TYPE_BUNDLE_METADATA 0x1e01
+/* enum: Bundle update non-volatile log output partition */
+#define          NVRAM_PARTITION_TYPE_BUNDLE_LOG 0x1e02
 /* enum: Start of reserved value range (firmware may use for any purpose) */
 #define          NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00
 /* enum: End of reserved value range (firmware may use for any purpose) */
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index 9382bb0b4d5a..fb7cde4980ed 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2009-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 /*
@@ -342,6 +339,7 @@ static void efx_mcdi_phy_decode_link(struct efx_nic *efx,
 		break;
 	default:
 		WARN_ON(1);
+		/* Fall through */
 	case MC_CMD_FCNTL_OFF:
 		link_state->fc = 0;
 		break;
diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c
index 4ac30b6e5dab..273c08e5455f 100644
--- a/drivers/net/ethernet/sfc/mtd.c
+++ b/drivers/net/ethernet/sfc/mtd.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/module.h>
@@ -66,6 +63,9 @@ int efx_mtd_add(struct efx_nic *efx, struct efx_mtd_partition *parts,
 
 		part->mtd.writesize = 1;
 
+		if (!(part->mtd.flags & MTD_NO_ERASE))
+			part->mtd.flags |= MTD_WRITEABLE;
+
 		part->mtd.owner = THIS_MODULE;
 		part->mtd.priv = efx;
 		part->mtd.name = part->name;
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 961b92979640..284a1b047ac2 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 /* Common definitions for all Efx net driver code */
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index c2d45a40eb48..b0baa70fbba7 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 5cca0556b47f..1f7c5717de75 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_NIC_H
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index f21661532ed3..02ed6d1b716c 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2011-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 /* Theory of operation:
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 396ff01298cd..d5db045535d3 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/socket.h>
@@ -360,8 +357,7 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic)
 		rc = efx_init_rx_buffers(rx_queue, atomic);
 		if (unlikely(rc)) {
 			/* Ensure that we don't leave the rx queue empty */
-			if (rx_queue->added_count == rx_queue->removed_count)
-				efx_schedule_slow_fill(rx_queue);
+			efx_schedule_slow_fill(rx_queue);
 			goto out;
 		}
 	} while ((space -= batch_size) >= batch_size);
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index f6936949fc85..8474cf8ea7d3 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/sfc/selftest.h b/drivers/net/ethernet/sfc/selftest.h
index 32a427253a03..a3553816d92c 100644
--- a/drivers/net/ethernet/sfc/selftest.h
+++ b/drivers/net/ethernet/sfc/selftest.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_SELFTEST_H
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 65161f68265a..81499244a4b4 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index da7b94f34604..dfbdf05dcf79 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2010-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 #include <linux/pci.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/sfc/siena_sriov.h b/drivers/net/ethernet/sfc/siena_sriov.h
index d88d4dab170a..e441c89c25ce 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.h
+++ b/drivers/net/ethernet/sfc/siena_sriov.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef SIENA_SRIOV_H
diff --git a/drivers/net/ethernet/sfc/sriov.c b/drivers/net/ethernet/sfc/sriov.c
index 0b766fdbcddb..3f241e6c881a 100644
--- a/drivers/net/ethernet/sfc/sriov.c
+++ b/drivers/net/ethernet/sfc/sriov.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2014-2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 #include <linux/module.h>
 #include "net_driver.h"
diff --git a/drivers/net/ethernet/sfc/sriov.h b/drivers/net/ethernet/sfc/sriov.h
index 84c7984edcaf..747707bee483 100644
--- a/drivers/net/ethernet/sfc/sriov.h
+++ b/drivers/net/ethernet/sfc/sriov.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2014-2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_SRIOV_H
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 22eb059086f7..31ec56091a5d 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/pci.h>
@@ -471,15 +468,13 @@ static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue,
 	if (IS_ERR(segments))
 		return PTR_ERR(segments);
 
-	dev_kfree_skb_any(skb);
+	dev_consume_skb_any(skb);
 	skb = segments;
 
 	while (skb) {
 		next = skb->next;
 		skb->next = NULL;
 
-		if (next)
-			skb->xmit_more = true;
 		efx_enqueue_skb(tx_queue, skb);
 		skb = next;
 	}
@@ -506,7 +501,7 @@ static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue,
 netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 {
 	unsigned int old_insert_count = tx_queue->insert_count;
-	bool xmit_more = skb->xmit_more;
+	bool xmit_more = netdev_xmit_more();
 	bool data_mapped = false;
 	unsigned int segments;
 	unsigned int skb_len;
@@ -533,7 +528,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 		if (rc)
 			goto err;
 #ifdef EFX_USE_PIO
-	} else if (skb_len <= efx_piobuf_size && !skb->xmit_more &&
+	} else if (skb_len <= efx_piobuf_size && !xmit_more &&
 		   efx_nic_may_tx_pio(tx_queue)) {
 		/* Use PIO for short packets with an empty queue. */
 		if (efx_enqueue_skb_pio(tx_queue, skb))
@@ -559,8 +554,8 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	if (__netdev_tx_sent_queue(tx_queue->core_txq, skb_len, xmit_more)) {
 		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
 
-		/* There could be packets left on the partner queue if those
-		 * SKBs had skb->xmit_more set. If we do not push those they
+		/* There could be packets left on the partner queue if
+		 * xmit_more was set. If we do not push those they
 		 * could be left for a long time and cause a netdev watchdog.
 		 */
 		if (txq2->xmit_more_available)
@@ -568,7 +563,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 
 		efx_nic_push_buffers(tx_queue);
 	} else {
-		tx_queue->xmit_more_available = skb->xmit_more;
+		tx_queue->xmit_more_available = xmit_more;
 	}
 
 	if (segments) {
diff --git a/drivers/net/ethernet/sfc/tx.h b/drivers/net/ethernet/sfc/tx.h
index 1cccc97ec676..e04d5ddeb32c 100644
--- a/drivers/net/ethernet/sfc/tx.h
+++ b/drivers/net/ethernet/sfc/tx.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2006-2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_TX_H
diff --git a/drivers/net/ethernet/sfc/tx_tso.c b/drivers/net/ethernet/sfc/tx_tso.c
index e0cbda9ae859..898e5c61d908 100644
--- a/drivers/net/ethernet/sfc/tx_tso.c
+++ b/drivers/net/ethernet/sfc/tx_tso.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2005-2006 Fen Systems Ltd.
  * Copyright 2005-2015 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #include <linux/pci.h>
diff --git a/drivers/net/ethernet/sfc/vfdi.h b/drivers/net/ethernet/sfc/vfdi.h
index f62901d4cae0..480b872eb4d1 100644
--- a/drivers/net/ethernet/sfc/vfdi.h
+++ b/drivers/net/ethernet/sfc/vfdi.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2010-2012 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 #ifndef _VFDI_H
 #define _VFDI_H
diff --git a/drivers/net/ethernet/sfc/workarounds.h b/drivers/net/ethernet/sfc/workarounds.h
index c67fa18b8121..815be2d20c4b 100644
--- a/drivers/net/ethernet/sfc/workarounds.h
+++ b/drivers/net/ethernet/sfc/workarounds.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /****************************************************************************
  * Driver for Solarflare network controllers and boards
  * Copyright 2006-2013 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
  */
 
 #ifndef EFX_WORKAROUNDS_H
diff --git a/drivers/net/ethernet/sgi/Kconfig b/drivers/net/ethernet/sgi/Kconfig
index fbbb21c13e95..37f048e1230c 100644
--- a/drivers/net/ethernet/sgi/Kconfig
+++ b/drivers/net/ethernet/sgi/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # SGI device configuration
 #
diff --git a/drivers/net/ethernet/sgi/Makefile b/drivers/net/ethernet/sgi/Makefile
index e5bedd271e29..68eefbcf50b8 100644
--- a/drivers/net/ethernet/sgi/Makefile
+++ b/drivers/net/ethernet/sgi/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the SGI device drivers.
 #
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 3140999642ba..358e66b81926 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -666,7 +666,7 @@ static inline void ioc3_tx(struct net_device *dev)
 		packets++;
 		skb = ip->tx_skbs[o_entry];
 		bytes += skb->len;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		ip->tx_skbs[o_entry] = NULL;
 
 		o_entry = (o_entry + 1) & 127;		/* Next */
diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c
index 0e1b7e960b98..00660dd820e2 100644
--- a/drivers/net/ethernet/sgi/meth.c
+++ b/drivers/net/ethernet/sgi/meth.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * meth.c -- O2 Builtin 10/100 Ethernet driver
  *
  * Copyright (C) 2001-2003 Ilya Volynets
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
  */
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
@@ -68,6 +64,8 @@ module_param(timeout, int, 0);
  * packets in and out, so there is place for a packet
  */
 struct meth_private {
+	struct platform_device *pdev;
+
 	/* in-memory copy of MAC Control register */
 	u64 mac_ctrl;
 
@@ -211,8 +209,8 @@ static void meth_check_link(struct net_device *dev)
 static int meth_init_tx_ring(struct meth_private *priv)
 {
 	/* Init TX ring */
-	priv->tx_ring = dma_alloc_coherent(NULL, TX_RING_BUFFER_SIZE,
-					   &priv->tx_ring_dma, GFP_ATOMIC);
+	priv->tx_ring = dma_alloc_coherent(&priv->pdev->dev,
+			TX_RING_BUFFER_SIZE, &priv->tx_ring_dma, GFP_ATOMIC);
 	if (!priv->tx_ring)
 		return -ENOMEM;
 
@@ -236,7 +234,7 @@ static int meth_init_rx_ring(struct meth_private *priv)
 		priv->rx_ring[i]=(rx_packet*)(priv->rx_skbs[i]->head);
 		/* I'll need to re-sync it after each RX */
 		priv->rx_ring_dmas[i] =
-			dma_map_single(NULL, priv->rx_ring[i],
+			dma_map_single(&priv->pdev->dev, priv->rx_ring[i],
 				       METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		mace->eth.rx_fifo = priv->rx_ring_dmas[i];
 	}
@@ -253,7 +251,7 @@ static void meth_free_tx_ring(struct meth_private *priv)
 			dev_kfree_skb(priv->tx_skbs[i]);
 		priv->tx_skbs[i] = NULL;
 	}
-	dma_free_coherent(NULL, TX_RING_BUFFER_SIZE, priv->tx_ring,
+	dma_free_coherent(&priv->pdev->dev, TX_RING_BUFFER_SIZE, priv->tx_ring,
 	                  priv->tx_ring_dma);
 }
 
@@ -263,7 +261,7 @@ static void meth_free_rx_ring(struct meth_private *priv)
 	int i;
 
 	for (i = 0; i < RX_RING_ENTRIES; i++) {
-		dma_unmap_single(NULL, priv->rx_ring_dmas[i],
+		dma_unmap_single(&priv->pdev->dev, priv->rx_ring_dmas[i],
 				 METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		priv->rx_ring[i] = 0;
 		priv->rx_ring_dmas[i] = 0;
@@ -393,7 +391,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status)
 		fifo_rptr = (fifo_rptr - 1) & 0x0f;
 	}
 	while (priv->rx_write != fifo_rptr) {
-		dma_unmap_single(NULL, priv->rx_ring_dmas[priv->rx_write],
+		dma_unmap_single(&priv->pdev->dev,
+				 priv->rx_ring_dmas[priv->rx_write],
 				 METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		status = priv->rx_ring[priv->rx_write]->status.raw;
 #if MFE_DEBUG
@@ -454,7 +453,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status)
 		priv->rx_ring[priv->rx_write] = (rx_packet*)skb->head;
 		priv->rx_ring[priv->rx_write]->status.raw = 0;
 		priv->rx_ring_dmas[priv->rx_write] =
-			dma_map_single(NULL, priv->rx_ring[priv->rx_write],
+			dma_map_single(&priv->pdev->dev,
+				       priv->rx_ring[priv->rx_write],
 				       METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		mace->eth.rx_fifo = priv->rx_ring_dmas[priv->rx_write];
 		ADVANCE_RX_PTR(priv->rx_write);
@@ -521,7 +521,7 @@ static void meth_tx_cleanup(struct net_device* dev, unsigned long int_status)
 			DPRINTK("RPTR points us here, but packet not done?\n");
 			break;
 		}
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		priv->tx_skbs[priv->tx_read] = NULL;
 		priv->tx_ring[priv->tx_read].header.raw = 0;
 		priv->tx_read = (priv->tx_read+1)&(TX_RING_ENTRIES-1);
@@ -637,7 +637,7 @@ static void meth_tx_1page_prepare(struct meth_private *priv,
 	}
 
 	/* first page */
-	catbuf = dma_map_single(NULL, buffer_data, buffer_len,
+	catbuf = dma_map_single(&priv->pdev->dev, buffer_data, buffer_len,
 				DMA_TO_DEVICE);
 	desc->data.cat_buf[0].form.start_addr = catbuf >> 3;
 	desc->data.cat_buf[0].form.len = buffer_len - 1;
@@ -663,12 +663,12 @@ static void meth_tx_2page_prepare(struct meth_private *priv,
 	}
 
 	/* first page */
-	catbuf1 = dma_map_single(NULL, buffer1_data, buffer1_len,
+	catbuf1 = dma_map_single(&priv->pdev->dev, buffer1_data, buffer1_len,
 				 DMA_TO_DEVICE);
 	desc->data.cat_buf[0].form.start_addr = catbuf1 >> 3;
 	desc->data.cat_buf[0].form.len = buffer1_len - 1;
 	/* second page */
-	catbuf2 = dma_map_single(NULL, buffer2_data, buffer2_len,
+	catbuf2 = dma_map_single(&priv->pdev->dev, buffer2_data, buffer2_len,
 				 DMA_TO_DEVICE);
 	desc->data.cat_buf[1].form.start_addr = catbuf2 >> 3;
 	desc->data.cat_buf[1].form.len = buffer2_len - 1;
@@ -840,6 +840,7 @@ static int meth_probe(struct platform_device *pdev)
 	memcpy(dev->dev_addr, o2meth_eaddr, ETH_ALEN);
 
 	priv = netdev_priv(dev);
+	priv->pdev = pdev;
 	spin_lock_init(&priv->meth_lock);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
diff --git a/drivers/net/ethernet/silan/Kconfig b/drivers/net/ethernet/silan/Kconfig
index ac982be38510..71929d148c3c 100644
--- a/drivers/net/ethernet/silan/Kconfig
+++ b/drivers/net/ethernet/silan/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Silan device configuration
 #
diff --git a/drivers/net/ethernet/silan/Makefile b/drivers/net/ethernet/silan/Makefile
index 4ad3523dcb92..86f716f0f582 100644
--- a/drivers/net/ethernet/silan/Makefile
+++ b/drivers/net/ethernet/silan/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Silan network device drivers.
 #
diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c
index c07fd594fe71..c7641a236eb8 100644
--- a/drivers/net/ethernet/silan/sc92031.c
+++ b/drivers/net/ethernet/silan/sc92031.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*  Silan SC92031 PCI Fast Ethernet Adapter driver
  *
  *  Based on vendor drivers:
@@ -251,7 +252,6 @@ enum PMConfigBits {
  * use of mdelay() at _sc92031_reset.
  * Functions prefixed with _sc92031_ must be called with the lock held;
  * functions prefixed with sc92031_ must be called without the lock held.
- * Use mmiowb() before unlocking if the hardware was written to.
  */
 
 /* Locking rules for the interrupt:
@@ -361,7 +361,6 @@ static void sc92031_disable_interrupts(struct net_device *dev)
 	/* stop interrupts */
 	iowrite32(0, port_base + IntrMask);
 	_sc92031_dummy_read(port_base);
-	mmiowb();
 
 	/* wait for any concurrent interrupt/tasklet to finish */
 	synchronize_irq(priv->pdev->irq);
@@ -379,7 +378,6 @@ static void sc92031_enable_interrupts(struct net_device *dev)
 	wmb();
 
 	iowrite32(IntrBits, port_base + IntrMask);
-	mmiowb();
 }
 
 static void _sc92031_disable_tx_rx(struct net_device *dev)
@@ -867,7 +865,6 @@ out:
 	rmb();
 
 	iowrite32(intr_mask, port_base + IntrMask);
-	mmiowb();
 
 	spin_unlock(&priv->lock);
 }
@@ -901,7 +898,6 @@ out_none:
 	rmb();
 
 	iowrite32(intr_mask, port_base + IntrMask);
-	mmiowb();
 
 	return IRQ_NONE;
 }
@@ -978,7 +974,6 @@ static netdev_tx_t sc92031_start_xmit(struct sk_buff *skb,
 	iowrite32(priv->tx_bufs_dma_addr + entry * TX_BUF_SIZE,
 			port_base + TxAddr0 + entry * 4);
 	iowrite32(tx_status, port_base + TxStatus0 + entry * 4);
-	mmiowb();
 
 	if (priv->tx_head - priv->tx_tail >= NUM_TX_DESC)
 		netif_stop_queue(dev);
@@ -1024,7 +1019,6 @@ static int sc92031_open(struct net_device *dev)
 	spin_lock_bh(&priv->lock);
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 	sc92031_enable_interrupts(dev);
@@ -1060,7 +1054,6 @@ static int sc92031_stop(struct net_device *dev)
 
 	_sc92031_disable_tx_rx(dev);
 	_sc92031_tx_clear(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1081,7 +1074,6 @@ static void sc92031_set_multicast_list(struct net_device *dev)
 
 	_sc92031_set_mar(dev);
 	_sc92031_set_rx_config(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 }
@@ -1098,7 +1090,6 @@ static void sc92031_tx_timeout(struct net_device *dev)
 	priv->tx_timeouts++;
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock(&priv->lock);
 
@@ -1140,7 +1131,6 @@ sc92031_ethtool_get_link_ksettings(struct net_device *dev,
 
 	output_status = _sc92031_mii_read(port_base, MII_OutputStatus);
 	_sc92031_mii_scan(port_base);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1311,7 +1301,6 @@ static int sc92031_ethtool_set_wol(struct net_device *dev,
 
 	priv->pm_config = pm_config;
 	iowrite32(pm_config, port_base + PMConfig);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1337,7 +1326,6 @@ static int sc92031_ethtool_nway_reset(struct net_device *dev)
 
 out:
 	_sc92031_mii_scan(port_base);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1530,7 +1518,6 @@ static int sc92031_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	_sc92031_disable_tx_rx(dev);
 	_sc92031_tx_clear(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1555,7 +1542,6 @@ static int sc92031_resume(struct pci_dev *pdev)
 	spin_lock_bh(&priv->lock);
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 	sc92031_enable_interrupts(dev);
diff --git a/drivers/net/ethernet/sis/Kconfig b/drivers/net/ethernet/sis/Kconfig
index 22ec98ec9d3e..d848ab0349a7 100644
--- a/drivers/net/ethernet/sis/Kconfig
+++ b/drivers/net/ethernet/sis/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Silicon Integrated Systems (SiS) device configuration
 #
diff --git a/drivers/net/ethernet/sis/Makefile b/drivers/net/ethernet/sis/Makefile
index 58d3ac1985df..853407bce343 100644
--- a/drivers/net/ethernet/sis/Makefile
+++ b/drivers/net/ethernet/sis/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for Silicon Integrated Systems (SiS) network device drivers.
 #
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index 808cf9816673..5b351beb78cb 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -714,7 +714,7 @@ static void sis190_tx_interrupt(struct net_device *dev,
 
 		sis190_unmap_tx_skb(tp->pci_dev, skb, txd);
 		tp->Tx_skbuff[entry] = NULL;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 	}
 
 	if (tp->dirty_tx != dirty_tx) {
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 4bb89f74742c..aba6eea72f15 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -360,7 +360,7 @@ static int sis635_get_mac_addr(struct pci_dev *pci_dev,
  *	SiS962 or SiS963 model, use EEPROM to store MAC address. And EEPROM
  *	is shared by
  *	LAN and 1394. When access EEPROM, send EEREQ signal to hardware first
- *	and wait for EEGNT. If EEGNT is ON, EEPROM is permitted to be access
+ *	and wait for EEGNT. If EEGNT is ON, EEPROM is permitted to be accessed
  *	by LAN, otherwise is not. After MAC address is read from EEPROM, send
  *	EEDONE signal to refuse EEPROM access by LAN.
  *	The EEPROM map of SiS962 or SiS963 is different to SiS900.
@@ -730,10 +730,10 @@ static u16 sis900_default_phy(struct net_device * net_dev)
 		status = mdio_read(net_dev, phy->phy_addr, MII_STATUS);
 
 		/* Link ON & Not select default PHY & not ghost PHY */
-		 if ((status & MII_STAT_LINK) && !default_phy &&
-					(phy->phy_types != UNKNOWN))
-		 	default_phy = phy;
-		 else {
+		if ((status & MII_STAT_LINK) && !default_phy &&
+		    (phy->phy_types != UNKNOWN)) {
+			default_phy = phy;
+		} else {
 			status = mdio_read(net_dev, phy->phy_addr, MII_CONTROL);
 			mdio_write(net_dev, phy->phy_addr, MII_CONTROL,
 				status | MII_CNTL_AUTO | MII_CNTL_ISOLATE);
@@ -741,7 +741,7 @@ static u16 sis900_default_phy(struct net_device * net_dev)
 				phy_home = phy;
 			else if(phy->phy_types == LAN)
 				phy_lan = phy;
-		 }
+		}
 	}
 
 	if (!default_phy && phy_home)
@@ -882,7 +882,7 @@ static void mdio_reset(struct sis900_private *sp)
  *	mdio_read - read MII PHY register
  *	@net_dev: the net device to read
  *	@phy_id: the phy address to read
- *	@location: the phy regiester id to read
+ *	@location: the phy register id to read
  *
  *	Read MII registers through MDIO and MDC
  *	using MDIO management frame structure and protocol(defined by ISO/IEC).
@@ -926,7 +926,7 @@ static int mdio_read(struct net_device *net_dev, int phy_id, int location)
  *	mdio_write - write MII PHY register
  *	@net_dev: the net device to write
  *	@phy_id: the phy address to write
- *	@location: the phy regiester id to write
+ *	@location: the phy register id to write
  *	@value: the register value to write with
  *
  *	Write MII registers with @value through MDIO and MDC
@@ -1057,7 +1057,7 @@ sis900_open(struct net_device *net_dev)
 	sis900_set_mode(sis_priv, HW_SPEED_10_MBPS, FDX_CAPABLE_HALF_SELECTED);
 
 	/* Enable all known interrupts by setting the interrupt mask. */
-	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE);
+	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxDESC);
 	sw32(cr, RxENA | sr32(cr));
 	sw32(ier, IE);
 
@@ -1101,7 +1101,7 @@ sis900_init_rxfilter (struct net_device * net_dev)
 		sw32(rfdr, w);
 
 		if (netif_msg_hw(sis_priv)) {
-			printk(KERN_DEBUG "%s: Receive Filter Addrss[%d]=%x\n",
+			printk(KERN_DEBUG "%s: Receive Filter Address[%d]=%x\n",
 			       net_dev->name, i, sr32(rfdr));
 		}
 	}
@@ -1148,7 +1148,7 @@ sis900_init_tx_ring(struct net_device *net_dev)
  *	@net_dev: the net device to initialize for
  *
  *	Initialize the Rx descriptor ring,
- *	and pre-allocate recevie buffers (socket buffer)
+ *	and pre-allocate receive buffers (socket buffer)
  */
 
 static void
@@ -1578,7 +1578,7 @@ static void sis900_tx_timeout(struct net_device *net_dev)
 	sw32(txdp, sis_priv->tx_ring_dma);
 
 	/* Enable all known interrupts by setting the interrupt mask. */
-	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE);
+	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxDESC);
 }
 
 /**
@@ -1618,7 +1618,7 @@ sis900_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 			spin_unlock_irqrestore(&sis_priv->lock, flags);
 			return NETDEV_TX_OK;
 	}
-	sis_priv->tx_ring[entry].cmdsts = (OWN | skb->len);
+	sis_priv->tx_ring[entry].cmdsts = (OWN | INTR | skb->len);
 	sw32(cr, TxENA | sr32(cr));
 
 	sis_priv->cur_tx ++;
@@ -1674,8 +1674,8 @@ static irqreturn_t sis900_interrupt(int irq, void *dev_instance)
 	do {
 		status = sr32(isr);
 
-		if ((status & (HIBERR|TxURN|TxERR|TxIDLE|RxORN|RxERR|RxOK)) == 0)
-			/* nothing intresting happened */
+		if ((status & (HIBERR|TxURN|TxERR|TxDESC|RxORN|RxERR|RxOK)) == 0)
+			/* nothing interesting happened */
 			break;
 		handled = 1;
 
@@ -1684,7 +1684,7 @@ static irqreturn_t sis900_interrupt(int irq, void *dev_instance)
 			/* Rx interrupt */
 			sis900_rx(net_dev);
 
-		if (status & (TxURN | TxERR | TxIDLE))
+		if (status & (TxURN | TxERR | TxDESC))
 			/* Tx interrupt */
 			sis900_finish_xmit(net_dev);
 
@@ -1896,8 +1896,8 @@ static void sis900_finish_xmit (struct net_device *net_dev)
 
 		if (tx_status & OWN) {
 			/* The packet is not transmitted yet (owned by hardware) !
-			 * Note: the interrupt is generated only when Tx Machine
-			 * is idle, so this is an almost impossible case */
+			 * Note: this is an almost impossible condition
+			 * on TxDESC interrupt ('descriptor interrupt') */
 			break;
 		}
 
@@ -1927,7 +1927,7 @@ static void sis900_finish_xmit (struct net_device *net_dev)
 		pci_unmap_single(sis_priv->pci_dev,
 			sis_priv->tx_ring[entry].bufptr, skb->len,
 			PCI_DMA_TODEVICE);
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		sis_priv->tx_skbuff[entry] = NULL;
 		sis_priv->tx_ring[entry].bufptr = 0;
 		sis_priv->tx_ring[entry].cmdsts = 0;
@@ -2473,7 +2473,7 @@ static int sis900_resume(struct pci_dev *pci_dev)
 	sis900_set_mode(sis_priv, HW_SPEED_10_MBPS, FDX_CAPABLE_HALF_SELECTED);
 
 	/* Enable all known interrupts by setting the interrupt mask. */
-	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE);
+	sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxDESC);
 	sw32(cr, RxENA | sr32(cr));
 	sw32(ier, IE);
 
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index 79612060d0ba..9e1c3752b200 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Western Digital/SMC network device configuration
 #
@@ -48,7 +49,7 @@ config SMC91X
 	  This driver is also available as a module ( = code which can be
 	  inserted in and removed from the running kernel whenever you want).
 	  The module will be called smc91x.  If you want to compile it as a
-	  module, say M here and read <file:Documentation/kbuild/modules.txt>.
+	  module, say M here and read <file:Documentation/kbuild/modules.rst>.
 
 config PCMCIA_SMC91C92
 	tristate "SMC 91Cxx PCMCIA support"
@@ -85,7 +86,7 @@ config SMC911X
 
 	  This driver is also available as a module. The module will be
 	  called smc911x.  If you want to compile it as a module, say M
-	  here and read <file:Documentation/kbuild/modules.txt>
+	  here and read <file:Documentation/kbuild/modules.rst>
 
 config SMSC911X
 	tristate "SMSC LAN911x/LAN921x families embedded ethernet support"
@@ -120,6 +121,6 @@ config SMSC9420
 
 	  This driver is also available as a module. The module will be
 	  called smsc9420.  If you want to compile it as a module, say M
-	  here and read <file:Documentation/kbuild/modules.txt>
+	  here and read <file:Documentation/kbuild/modules.rst>
 
 endif # NET_VENDOR_SMSC
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 8355dfbb8ec3..bd14803545de 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * smc911x.c
  * This is a driver for SMSC's LAN911{5,6,7,8} single-chip Ethernet devices.
@@ -6,19 +7,6 @@
  *	   Derived from the unified SMC91x driver by Nicolas Pitre
  *	   and the smsc911x.c reference driver by SMSC
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * Arguments:
  *	 watchdog  = TX watchdog timeout
  *	 tx_fifo_kb = Size of TX FIFO in KB
@@ -1188,7 +1176,7 @@ smc911x_tx_dma_irq(void *data)
 
 	DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "TX DMA irq handler\n");
 	BUG_ON(skb == NULL);
-	dma_unmap_single(NULL, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE);
+	dma_unmap_single(lp->dev, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE);
 	netif_trans_update(dev);
 	dev_kfree_skb_irq(skb);
 	lp->current_tx_skb = NULL;
@@ -1219,7 +1207,7 @@ smc911x_rx_dma_irq(void *data)
 
 	DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__);
 	DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, "RX DMA irq handler\n");
-	dma_unmap_single(NULL, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE);
+	dma_unmap_single(lp->dev, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE);
 	BUG_ON(skb == NULL);
 	lp->current_rx_skb = NULL;
 	PRINT_PKT(skb->data, skb->len);
diff --git a/drivers/net/ethernet/smsc/smc911x.h b/drivers/net/ethernet/smsc/smc911x.h
index fa528ea0ea51..d4edcc0da87c 100644
--- a/drivers/net/ethernet/smsc/smc911x.h
+++ b/drivers/net/ethernet/smsc/smc911x.h
@@ -1,21 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*------------------------------------------------------------------------
  . smc911x.h - macros for SMSC's LAN911{5,6,7,8} single-chip Ethernet device.
  .
  . Copyright (C) 2005 Sensoria Corp.
  . Derived from the unified SMC91x driver by Nicolas Pitre
  .
- . This program is free software; you can redistribute it and/or modify
- . it under the terms of the GNU General Public License as published by
- . the Free Software Foundation; either version 2 of the License, or
- . (at your option) any later version.
- .
- . This program is distributed in the hope that it will be useful,
- . but WITHOUT ANY WARRANTY; without even the implied warranty of
- . MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- . GNU General Public License for more details.
- .
- . You should have received a copy of the GNU General Public License
- . along with this program; if not, see <http://www.gnu.org/licenses/>.
  .
  . Information contained in this file was obtained from the LAN9118
  . manual from SMC.  To get a copy, if you really want one, you can find
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 4823b6a51134..601e76ad99a0 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * smc91x.c
  * This is a driver for SMSC's 91C9x/91C1xx single-chip Ethernet devices.
@@ -8,19 +9,6 @@
  * Copyright (C) 2003 Monta Vista Software, Inc.
  *	Unified SMC91x driver by Nicolas Pitre
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * Arguments:
  * 	io	= for the base address
  *	irq	= for the IRQ
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index a27352229fc2..387539a8094b 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*------------------------------------------------------------------------
  . smc91x.h - macros for SMSC's 91C9x/91C1xx single-chip Ethernet device.
  .
@@ -7,18 +8,6 @@
  . Copyright (C) 2003 Monta Vista Software, Inc.
  .	Unified SMC91x driver by Nicolas Pitre
  .
- . This program is free software; you can redistribute it and/or modify
- . it under the terms of the GNU General Public License as published by
- . the Free Software Foundation; either version 2 of the License, or
- . (at your option) any later version.
- .
- . This program is distributed in the hope that it will be useful,
- . but WITHOUT ANY WARRANTY; without even the implied warranty of
- . MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- . GNU General Public License for more details.
- .
- . You should have received a copy of the GNU General Public License
- . along with this program; if not, see <http://www.gnu.org/licenses/>.
  .
  . Information contained in this file was obtained from the LAN91C111
  . manual from SMC.  To get a copy, if you really want one, you can find
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 99a5a8a7c777..38068fc34141 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /***************************************************************************
  *
  * Copyright (C) 2004-2008 SMSC
  * Copyright (C) 2005-2008 ARM
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  ***************************************************************************
  * Rewritten, heavily based on smsc911x simple driver by SMSC.
  * Partly uses io macros from smc91x.c by Nicolas Pitre
@@ -26,7 +14,6 @@
  *   LAN9210, LAN9211
  *   LAN9220, LAN9221
  *   LAN89218,LAN9250
- *
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/drivers/net/ethernet/smsc/smsc911x.h b/drivers/net/ethernet/smsc/smsc911x.h
index 51b2fc1a395f..09b46382b364 100644
--- a/drivers/net/ethernet/smsc/smsc911x.h
+++ b/drivers/net/ethernet/smsc/smsc911x.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /***************************************************************************
  *
  * Copyright (C) 2004-2008 SMSC
  * Copyright (C) 2005-2008 ARM
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  ***************************************************************************/
 #ifndef __SMSC911X_H__
 #define __SMSC911X_H__
diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index 9b6366b20110..a6962a41c3d2 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
  /***************************************************************************
  *
  * Copyright (C) 2007,2008  SMSC
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  ***************************************************************************
  */
 
diff --git a/drivers/net/ethernet/smsc/smsc9420.h b/drivers/net/ethernet/smsc/smsc9420.h
index c63c76381af6..409e82b2018a 100644
--- a/drivers/net/ethernet/smsc/smsc9420.h
+++ b/drivers/net/ethernet/smsc/smsc9420.h
@@ -1,20 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
  /***************************************************************************
  *
  * Copyright (C) 2007,2008  SMSC
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  ***************************************************************************
  */
 
diff --git a/drivers/net/ethernet/socionext/Kconfig b/drivers/net/ethernet/socionext/Kconfig
index b80048ca82a0..95e99baf3f45 100644
--- a/drivers/net/ethernet/socionext/Kconfig
+++ b/drivers/net/ethernet/socionext/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config NET_VENDOR_SOCIONEXT
 	bool "Socionext ethernet drivers"
 	default y
@@ -25,6 +26,7 @@ config SNI_NETSEC
 	tristate "Socionext NETSEC ethernet support"
 	depends on (ARCH_SYNQUACER || COMPILE_TEST) && OF
 	select PHYLIB
+	select PAGE_POOL
 	select MII
 	---help---
 	  Enable to add support for the SocioNext NetSec Gigabit Ethernet
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index a18149720aa2..1502fe8b0456 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -9,8 +9,12 @@
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/netlink.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 
 #include <net/tcp.h>
+#include <net/page_pool.h>
 #include <net/ip6_checksum.h>
 
 #define NETSEC_REG_SOFT_RST			0x104
@@ -235,22 +239,41 @@
 #define DESC_NUM	256
 
 #define NETSEC_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
-#define NETSEC_RX_BUF_SZ 1536
+#define NETSEC_RXBUF_HEADROOM (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + \
+			       NET_IP_ALIGN)
+#define NETSEC_RX_BUF_NON_DATA (NETSEC_RXBUF_HEADROOM + \
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
 #define DESC_SZ	sizeof(struct netsec_de)
 
 #define NETSEC_F_NETSEC_VER_MAJOR_NUM(x)	((x) & 0xffff0000)
 
+#define NETSEC_XDP_PASS          0
+#define NETSEC_XDP_CONSUMED      BIT(0)
+#define NETSEC_XDP_TX            BIT(1)
+#define NETSEC_XDP_REDIR         BIT(2)
+#define NETSEC_XDP_RX_OK (NETSEC_XDP_PASS | NETSEC_XDP_TX | NETSEC_XDP_REDIR)
+
 enum ring_id {
 	NETSEC_RING_TX = 0,
 	NETSEC_RING_RX
 };
 
+enum buf_type {
+	TYPE_NETSEC_SKB = 0,
+	TYPE_NETSEC_XDP_TX,
+	TYPE_NETSEC_XDP_NDO,
+};
+
 struct netsec_desc {
-	struct sk_buff *skb;
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdpf;
+	};
 	dma_addr_t dma_addr;
 	void *addr;
 	u16 len;
+	u8 buf_type;
 };
 
 struct netsec_desc_ring {
@@ -258,11 +281,17 @@ struct netsec_desc_ring {
 	struct netsec_desc *desc;
 	void *vaddr;
 	u16 head, tail;
+	u16 xdp_xmit; /* netsec_xdp_xmit packets */
+	bool is_xdp;
+	struct page_pool *page_pool;
+	struct xdp_rxq_info xdp_rxq;
+	spinlock_t lock; /* XDP tx queue locking */
 };
 
 struct netsec_priv {
 	struct netsec_desc_ring desc_ring[NETSEC_RING_MAX];
 	struct ethtool_coalesce et_coalesce;
+	struct bpf_prog *xdp_prog;
 	spinlock_t reglock; /* protect reg access */
 	struct napi_struct napi;
 	phy_interface_t phy_interface;
@@ -600,12 +629,14 @@ static void netsec_set_rx_de(struct netsec_priv *priv,
 static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
-	unsigned int pkts, bytes;
 	struct netsec_de *entry;
 	int tail = dring->tail;
+	unsigned int bytes;
 	int cnt = 0;
 
-	pkts = 0;
+	if (dring->is_xdp)
+		spin_lock(&dring->lock);
+
 	bytes = 0;
 	entry = dring->vaddr + DESC_SZ * tail;
 
@@ -618,13 +649,23 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 		eop = (entry->attr >> NETSEC_TX_LAST) & 1;
 		dma_rmb();
 
-		dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
-				 DMA_TO_DEVICE);
-		if (eop) {
-			pkts++;
+		/* if buf_type is either TYPE_NETSEC_SKB or
+		 * TYPE_NETSEC_XDP_NDO we mapped it
+		 */
+		if (desc->buf_type != TYPE_NETSEC_XDP_TX)
+			dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
+					 DMA_TO_DEVICE);
+
+		if (!eop)
+			goto next;
+
+		if (desc->buf_type == TYPE_NETSEC_SKB) {
 			bytes += desc->skb->len;
 			dev_kfree_skb(desc->skb);
+		} else {
+			xdp_return_frame(desc->xdpf);
 		}
+next:
 		/* clean up so netsec_uninit_pkt_dring() won't free the skb
 		 * again
 		 */
@@ -641,6 +682,8 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 		entry = dring->vaddr + DESC_SZ * tail;
 		cnt++;
 	}
+	if (dring->is_xdp)
+		spin_unlock(&dring->lock);
 
 	if (!cnt)
 		return false;
@@ -674,31 +717,30 @@ static void netsec_process_tx(struct netsec_priv *priv)
 
 static void *netsec_alloc_rx_data(struct netsec_priv *priv,
 				  dma_addr_t *dma_handle, u16 *desc_len)
+
 {
-	size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	size_t payload_len = NETSEC_RX_BUF_SZ;
-	dma_addr_t mapping;
-	void *buf;
 
-	total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD);
+	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+	enum dma_data_direction dma_dir;
+	struct page *page;
 
-	buf = napi_alloc_frag(total_len);
-	if (!buf)
+	page = page_pool_dev_alloc_pages(dring->page_pool);
+	if (!page)
 		return NULL;
 
-	mapping = dma_map_single(priv->dev, buf + NETSEC_SKB_PAD, payload_len,
-				 DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(priv->dev, mapping)))
-		goto err_out;
-
-	*dma_handle = mapping;
-	*desc_len = payload_len;
-
-	return buf;
+	/* We allocate the same buffer length for XDP and non-XDP cases.
+	 * page_pool API will map the whole page, skip what's needed for
+	 * network payloads and/or XDP
+	 */
+	*dma_handle = page_pool_get_dma_addr(page) + NETSEC_RXBUF_HEADROOM;
+	/* Make sure the incoming payload fits in the page for XDP and non-XDP
+	 * cases and reserve enough space for headroom + skb_shared_info
+	 */
+	*desc_len = PAGE_SIZE - NETSEC_RX_BUF_NON_DATA;
+	dma_dir = page_pool_get_dma_dir(dring->page_pool);
+	dma_sync_single_for_device(priv->dev, *dma_handle, *desc_len, dma_dir);
 
-err_out:
-	skb_free_frag(buf);
-	return NULL;
+	return page_address(page);
 }
 
 static void netsec_rx_fill(struct netsec_priv *priv, u16 from, u16 num)
@@ -715,22 +757,201 @@ static void netsec_rx_fill(struct netsec_priv *priv, u16 from, u16 num)
 	}
 }
 
+static void netsec_xdp_ring_tx_db(struct netsec_priv *priv, u16 pkts)
+{
+	if (likely(pkts))
+		netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, pkts);
+}
+
+static void netsec_finalize_xdp_rx(struct netsec_priv *priv, u32 xdp_res,
+				   u16 pkts)
+{
+	if (xdp_res & NETSEC_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_res & NETSEC_XDP_TX)
+		netsec_xdp_ring_tx_db(priv, pkts);
+}
+
+static void netsec_set_tx_de(struct netsec_priv *priv,
+			     struct netsec_desc_ring *dring,
+			     const struct netsec_tx_pkt_ctrl *tx_ctrl,
+			     const struct netsec_desc *desc, void *buf)
+{
+	int idx = dring->head;
+	struct netsec_de *de;
+	u32 attr;
+
+	de = dring->vaddr + (DESC_SZ * idx);
+
+	attr = (1 << NETSEC_TX_SHIFT_OWN_FIELD) |
+	       (1 << NETSEC_TX_SHIFT_PT_FIELD) |
+	       (NETSEC_RING_GMAC << NETSEC_TX_SHIFT_TDRID_FIELD) |
+	       (1 << NETSEC_TX_SHIFT_FS_FIELD) |
+	       (1 << NETSEC_TX_LAST) |
+	       (tx_ctrl->cksum_offload_flag << NETSEC_TX_SHIFT_CO) |
+	       (tx_ctrl->tcp_seg_offload_flag << NETSEC_TX_SHIFT_SO) |
+	       (1 << NETSEC_TX_SHIFT_TRS_FIELD);
+	if (idx == DESC_NUM - 1)
+		attr |= (1 << NETSEC_TX_SHIFT_LD_FIELD);
+
+	de->data_buf_addr_up = upper_32_bits(desc->dma_addr);
+	de->data_buf_addr_lw = lower_32_bits(desc->dma_addr);
+	de->buf_len_info = (tx_ctrl->tcp_seg_len << 16) | desc->len;
+	de->attr = attr;
+	/* under spin_lock if using XDP */
+	if (!dring->is_xdp)
+		dma_wmb();
+
+	dring->desc[idx] = *desc;
+	if (desc->buf_type == TYPE_NETSEC_SKB)
+		dring->desc[idx].skb = buf;
+	else if (desc->buf_type == TYPE_NETSEC_XDP_TX ||
+		 desc->buf_type == TYPE_NETSEC_XDP_NDO)
+		dring->desc[idx].xdpf = buf;
+
+	/* move head ahead */
+	dring->head = (dring->head + 1) % DESC_NUM;
+}
+
+/* The current driver only supports 1 Txq, this should run under spin_lock() */
+static u32 netsec_xdp_queue_one(struct netsec_priv *priv,
+				struct xdp_frame *xdpf, bool is_ndo)
+
+{
+	struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
+	struct page *page = virt_to_page(xdpf->data);
+	struct netsec_tx_pkt_ctrl tx_ctrl = {};
+	struct netsec_desc tx_desc;
+	dma_addr_t dma_handle;
+	u16 filled;
+
+	if (tx_ring->head >= tx_ring->tail)
+		filled = tx_ring->head - tx_ring->tail;
+	else
+		filled = tx_ring->head + DESC_NUM - tx_ring->tail;
+
+	if (DESC_NUM - filled <= 1)
+		return NETSEC_XDP_CONSUMED;
+
+	if (is_ndo) {
+		/* this is for ndo_xdp_xmit, the buffer needs mapping before
+		 * sending
+		 */
+		dma_handle = dma_map_single(priv->dev, xdpf->data, xdpf->len,
+					    DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->dev, dma_handle))
+			return NETSEC_XDP_CONSUMED;
+		tx_desc.buf_type = TYPE_NETSEC_XDP_NDO;
+	} else {
+		/* This is the device Rx buffer from page_pool. No need to remap
+		 * just sync and send it
+		 */
+		struct netsec_desc_ring *rx_ring =
+			&priv->desc_ring[NETSEC_RING_RX];
+		enum dma_data_direction dma_dir =
+			page_pool_get_dma_dir(rx_ring->page_pool);
+
+		dma_handle = page_pool_get_dma_addr(page) +
+			NETSEC_RXBUF_HEADROOM;
+		dma_sync_single_for_device(priv->dev, dma_handle, xdpf->len,
+					   dma_dir);
+		tx_desc.buf_type = TYPE_NETSEC_XDP_TX;
+	}
+
+	tx_desc.dma_addr = dma_handle;
+	tx_desc.addr = xdpf->data;
+	tx_desc.len = xdpf->len;
+
+	netsec_set_tx_de(priv, tx_ring, &tx_ctrl, &tx_desc, xdpf);
+
+	return NETSEC_XDP_TX;
+}
+
+static u32 netsec_xdp_xmit_back(struct netsec_priv *priv, struct xdp_buff *xdp)
+{
+	struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
+	struct xdp_frame *xdpf = convert_to_xdp_frame(xdp);
+	u32 ret;
+
+	if (unlikely(!xdpf))
+		return NETSEC_XDP_CONSUMED;
+
+	spin_lock(&tx_ring->lock);
+	ret = netsec_xdp_queue_one(priv, xdpf, false);
+	spin_unlock(&tx_ring->lock);
+
+	return ret;
+}
+
+static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog,
+			  struct xdp_buff *xdp)
+{
+	u32 ret = NETSEC_XDP_PASS;
+	int err;
+	u32 act;
+
+	act = bpf_prog_run_xdp(prog, xdp);
+
+	switch (act) {
+	case XDP_PASS:
+		ret = NETSEC_XDP_PASS;
+		break;
+	case XDP_TX:
+		ret = netsec_xdp_xmit_back(priv, xdp);
+		if (ret != NETSEC_XDP_TX)
+			xdp_return_buff(xdp);
+		break;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(priv->ndev, xdp, prog);
+		if (!err) {
+			ret = NETSEC_XDP_REDIR;
+		} else {
+			ret = NETSEC_XDP_CONSUMED;
+			xdp_return_buff(xdp);
+		}
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(priv->ndev, prog, act);
+		/* fall through -- handle aborts by dropping packet */
+	case XDP_DROP:
+		ret = NETSEC_XDP_CONSUMED;
+		xdp_return_buff(xdp);
+		break;
+	}
+
+	return ret;
+}
+
 static int netsec_process_rx(struct netsec_priv *priv, int budget)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
 	struct net_device *ndev = priv->ndev;
 	struct netsec_rx_pkt_info rx_info;
-	struct sk_buff *skb;
+	enum dma_data_direction dma_dir;
+	struct bpf_prog *xdp_prog;
+	struct sk_buff *skb = NULL;
+	u16 xdp_xmit = 0;
+	u32 xdp_act = 0;
 	int done = 0;
 
+	rcu_read_lock();
+	xdp_prog = READ_ONCE(priv->xdp_prog);
+	dma_dir = page_pool_get_dma_dir(dring->page_pool);
+
 	while (done < budget) {
 		u16 idx = dring->tail;
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 		struct netsec_desc *desc = &dring->desc[idx];
+		struct page *page = virt_to_page(desc->addr);
+		u32 xdp_result = XDP_PASS;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
+		struct xdp_buff xdp;
 		void *buf_addr;
-		u32 truesize;
 
 		if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) {
 			/* reading the register clears the irq */
@@ -766,51 +987,70 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		 * This will eventually replace the old buffer in the hardware
 		 */
 		buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len);
+
 		if (unlikely(!buf_addr))
 			break;
 
 		dma_sync_single_for_cpu(priv->dev, desc->dma_addr, pkt_len,
-					DMA_FROM_DEVICE);
+					dma_dir);
 		prefetch(desc->addr);
 
-		truesize = SKB_DATA_ALIGN(desc->len + NETSEC_SKB_PAD) +
-			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-		skb = build_skb(desc->addr, truesize);
+		xdp.data_hard_start = desc->addr;
+		xdp.data = desc->addr + NETSEC_RXBUF_HEADROOM;
+		xdp_set_data_meta_invalid(&xdp);
+		xdp.data_end = xdp.data + pkt_len;
+		xdp.rxq = &dring->xdp_rxq;
+
+		if (xdp_prog) {
+			xdp_result = netsec_run_xdp(priv, xdp_prog, &xdp);
+			if (xdp_result != NETSEC_XDP_PASS) {
+				xdp_act |= xdp_result;
+				if (xdp_result == NETSEC_XDP_TX)
+					xdp_xmit++;
+				goto next;
+			}
+		}
+		skb = build_skb(desc->addr, desc->len + NETSEC_RX_BUF_NON_DATA);
+
 		if (unlikely(!skb)) {
-			/* free the newly allocated buffer, we are not going to
-			 * use it
+			/* If skb fails recycle_direct will either unmap and
+			 * free the page or refill the cache depending on the
+			 * cache state. Since we paid the allocation cost if
+			 * building an skb fails try to put the page into cache
 			 */
-			dma_unmap_single(priv->dev, dma_handle, desc_len,
-					 DMA_FROM_DEVICE);
-			skb_free_frag(buf_addr);
+			page_pool_recycle_direct(dring->page_pool, page);
 			netif_err(priv, drv, priv->ndev,
 				  "rx failed to build skb\n");
 			break;
 		}
-		dma_unmap_single_attrs(priv->dev, desc->dma_addr, desc->len,
-				       DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
-
-		/* Update the descriptor with the new buffer we allocated */
-		desc->len = desc_len;
-		desc->dma_addr = dma_handle;
-		desc->addr = buf_addr;
+		page_pool_release_page(dring->page_pool, page);
 
-		skb_reserve(skb, NETSEC_SKB_PAD);
-		skb_put(skb, pkt_len);
+		skb_reserve(skb, xdp.data - xdp.data_hard_start);
+		skb_put(skb, xdp.data_end - xdp.data);
 		skb->protocol = eth_type_trans(skb, priv->ndev);
 
 		if (priv->rx_cksum_offload_flag &&
 		    rx_info.rx_cksum_result == NETSEC_RX_CKSUM_OK)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-		if (napi_gro_receive(&priv->napi, skb) != GRO_DROP) {
+next:
+		if ((skb && napi_gro_receive(&priv->napi, skb) != GRO_DROP) ||
+		    xdp_result & NETSEC_XDP_RX_OK) {
 			ndev->stats.rx_packets++;
-			ndev->stats.rx_bytes += pkt_len;
+			ndev->stats.rx_bytes += xdp.data_end - xdp.data;
 		}
 
+		/* Update the descriptor with fresh buffers */
+		desc->len = desc_len;
+		desc->dma_addr = dma_handle;
+		desc->addr = buf_addr;
+
 		netsec_rx_fill(priv, idx, 1);
 		dring->tail = (dring->tail + 1) % DESC_NUM;
 	}
+	netsec_finalize_xdp_rx(priv, xdp_act, xdp_xmit);
+
+	rcu_read_unlock();
 
 	return done;
 }
@@ -818,19 +1058,12 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 static int netsec_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct netsec_priv *priv;
-	int rx, done, todo;
+	int done;
 
 	priv = container_of(napi, struct netsec_priv, napi);
 
 	netsec_process_tx(priv);
-
-	todo = budget;
-	do {
-		rx = netsec_process_rx(priv, todo);
-		todo -= rx;
-	} while (rx);
-
-	done = budget - todo;
+	done = netsec_process_rx(priv, budget);
 
 	if (done < budget && napi_complete_done(napi, done)) {
 		unsigned long flags;
@@ -844,41 +1077,6 @@ static int netsec_napi_poll(struct napi_struct *napi, int budget)
 	return done;
 }
 
-static void netsec_set_tx_de(struct netsec_priv *priv,
-			     struct netsec_desc_ring *dring,
-			     const struct netsec_tx_pkt_ctrl *tx_ctrl,
-			     const struct netsec_desc *desc,
-			     struct sk_buff *skb)
-{
-	int idx = dring->head;
-	struct netsec_de *de;
-	u32 attr;
-
-	de = dring->vaddr + (DESC_SZ * idx);
-
-	attr = (1 << NETSEC_TX_SHIFT_OWN_FIELD) |
-	       (1 << NETSEC_TX_SHIFT_PT_FIELD) |
-	       (NETSEC_RING_GMAC << NETSEC_TX_SHIFT_TDRID_FIELD) |
-	       (1 << NETSEC_TX_SHIFT_FS_FIELD) |
-	       (1 << NETSEC_TX_LAST) |
-	       (tx_ctrl->cksum_offload_flag << NETSEC_TX_SHIFT_CO) |
-	       (tx_ctrl->tcp_seg_offload_flag << NETSEC_TX_SHIFT_SO) |
-	       (1 << NETSEC_TX_SHIFT_TRS_FIELD);
-	if (idx == DESC_NUM - 1)
-		attr |= (1 << NETSEC_TX_SHIFT_LD_FIELD);
-
-	de->data_buf_addr_up = upper_32_bits(desc->dma_addr);
-	de->data_buf_addr_lw = lower_32_bits(desc->dma_addr);
-	de->buf_len_info = (tx_ctrl->tcp_seg_len << 16) | desc->len;
-	de->attr = attr;
-	dma_wmb();
-
-	dring->desc[idx] = *desc;
-	dring->desc[idx].skb = skb;
-
-	/* move head ahead */
-	dring->head = (dring->head + 1) % DESC_NUM;
-}
 
 static int netsec_desc_used(struct netsec_desc_ring *dring)
 {
@@ -925,8 +1123,12 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	u16 tso_seg_len = 0;
 	int filled;
 
+	if (dring->is_xdp)
+		spin_lock_bh(&dring->lock);
 	filled = netsec_desc_used(dring);
 	if (netsec_check_stop_tx(priv, filled)) {
+		if (dring->is_xdp)
+			spin_unlock_bh(&dring->lock);
 		net_warn_ratelimited("%s %s Tx queue full\n",
 				     dev_name(priv->dev), ndev->name);
 		return NETDEV_TX_BUSY;
@@ -959,6 +1161,8 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	tx_desc.dma_addr = dma_map_single(priv->dev, skb->data,
 					  skb_headlen(skb), DMA_TO_DEVICE);
 	if (dma_mapping_error(priv->dev, tx_desc.dma_addr)) {
+		if (dring->is_xdp)
+			spin_unlock_bh(&dring->lock);
 		netif_err(priv, drv, priv->ndev,
 			  "%s: DMA mapping failed\n", __func__);
 		ndev->stats.tx_dropped++;
@@ -967,11 +1171,14 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	}
 	tx_desc.addr = skb->data;
 	tx_desc.len = skb_headlen(skb);
+	tx_desc.buf_type = TYPE_NETSEC_SKB;
 
 	skb_tx_timestamp(skb);
 	netdev_sent_queue(priv->ndev, skb->len);
 
 	netsec_set_tx_de(priv, dring, &tx_ctrl, &tx_desc, skb);
+	if (dring->is_xdp)
+		spin_unlock_bh(&dring->lock);
 	netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, 1); /* submit another tx */
 
 	return NETDEV_TX_OK;
@@ -985,19 +1192,27 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
 
 	if (!dring->vaddr || !dring->desc)
 		return;
-
 	for (idx = 0; idx < DESC_NUM; idx++) {
 		desc = &dring->desc[idx];
 		if (!desc->addr)
 			continue;
 
-		dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
-				 id == NETSEC_RING_RX ? DMA_FROM_DEVICE :
-							      DMA_TO_DEVICE);
-		if (id == NETSEC_RING_RX)
-			skb_free_frag(desc->addr);
-		else if (id == NETSEC_RING_TX)
+		if (id == NETSEC_RING_RX) {
+			struct page *page = virt_to_page(desc->addr);
+
+			page_pool_put_page(dring->page_pool, page, false);
+		} else if (id == NETSEC_RING_TX) {
+			dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
+					 DMA_TO_DEVICE);
 			dev_kfree_skb(desc->skb);
+		}
+	}
+
+	/* Rx is currently using page_pool */
+	if (id == NETSEC_RING_RX) {
+		if (xdp_rxq_info_is_reg(&dring->xdp_rxq))
+			xdp_rxq_info_unreg(&dring->xdp_rxq);
+		page_pool_destroy(dring->page_pool);
 	}
 
 	memset(dring->desc, 0, sizeof(struct netsec_desc) * DESC_NUM);
@@ -1027,7 +1242,6 @@ static void netsec_free_dring(struct netsec_priv *priv, int id)
 static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[id];
-	int i;
 
 	dring->vaddr = dma_alloc_coherent(priv->dev, DESC_SZ * DESC_NUM,
 					  &dring->desc_dma, GFP_KERNEL);
@@ -1038,19 +1252,6 @@ static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 	if (!dring->desc)
 		goto err;
 
-	if (id == NETSEC_RING_TX) {
-		for (i = 0; i < DESC_NUM; i++) {
-			struct netsec_de *de;
-
-			de = dring->vaddr + (DESC_SZ * i);
-			/* de->attr is not going to be accessed by the NIC
-			 * until netsec_set_tx_de() is called.
-			 * No need for a dma_wmb() here
-			 */
-			de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
-		}
-	}
-
 	return 0;
 err:
 	netsec_free_dring(priv, id);
@@ -1058,10 +1259,60 @@ err:
 	return -ENOMEM;
 }
 
+static void netsec_setup_tx_dring(struct netsec_priv *priv)
+{
+	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
+	struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
+	int i;
+
+	for (i = 0; i < DESC_NUM; i++) {
+		struct netsec_de *de;
+
+		de = dring->vaddr + (DESC_SZ * i);
+		/* de->attr is not going to be accessed by the NIC
+		 * until netsec_set_tx_de() is called.
+		 * No need for a dma_wmb() here
+		 */
+		de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
+	}
+
+	if (xdp_prog)
+		dring->is_xdp = true;
+	else
+		dring->is_xdp = false;
+
+}
+
 static int netsec_setup_rx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	int i;
+	struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
+	struct page_pool_params pp_params = { 0 };
+	int i, err;
+
+	pp_params.order = 0;
+	/* internal DMA mapping in page_pool */
+	pp_params.flags = PP_FLAG_DMA_MAP;
+	pp_params.pool_size = DESC_NUM;
+	pp_params.nid = cpu_to_node(0);
+	pp_params.dev = priv->dev;
+	pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
+
+	dring->page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(dring->page_pool)) {
+		err = PTR_ERR(dring->page_pool);
+		dring->page_pool = NULL;
+		goto err_out;
+	}
+
+	err = xdp_rxq_info_reg(&dring->xdp_rxq, priv->ndev, 0);
+	if (err)
+		goto err_out;
+
+	err = xdp_rxq_info_reg_mem_model(&dring->xdp_rxq, MEM_TYPE_PAGE_POOL,
+					 dring->page_pool);
+	if (err)
+		goto err_out;
 
 	for (i = 0; i < DESC_NUM; i++) {
 		struct netsec_desc *desc = &dring->desc[i];
@@ -1070,8 +1321,9 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
 		u16 len;
 
 		buf = netsec_alloc_rx_data(priv, &dma_handle, &len);
+
 		if (!buf) {
-			netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
+			err = -ENOMEM;
 			goto err_out;
 		}
 		desc->dma_addr = dma_handle;
@@ -1084,7 +1336,8 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
 	return 0;
 
 err_out:
-	return -ENOMEM;
+	netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
+	return err;
 }
 
 static int netsec_netdev_load_ucode_region(struct netsec_priv *priv, u32 reg,
@@ -1358,6 +1611,7 @@ static int netsec_netdev_open(struct net_device *ndev)
 
 	pm_runtime_get_sync(priv->dev);
 
+	netsec_setup_tx_dring(priv);
 	ret = netsec_setup_rx_dring(priv);
 	if (ret) {
 		netif_err(priv, probe, priv->ndev,
@@ -1463,6 +1717,9 @@ static int netsec_netdev_init(struct net_device *ndev)
 	if (ret)
 		goto err2;
 
+	spin_lock_init(&priv->desc_ring[NETSEC_RING_TX].lock);
+	spin_lock_init(&priv->desc_ring[NETSEC_RING_RX].lock);
+
 	return 0;
 err2:
 	netsec_free_dring(priv, NETSEC_RING_RX);
@@ -1495,6 +1752,81 @@ static int netsec_netdev_ioctl(struct net_device *ndev, struct ifreq *ifr,
 	return phy_mii_ioctl(ndev->phydev, ifr, cmd);
 }
 
+static int netsec_xdp_xmit(struct net_device *ndev, int n,
+			   struct xdp_frame **frames, u32 flags)
+{
+	struct netsec_priv *priv = netdev_priv(ndev);
+	struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
+	int drops = 0;
+	int i;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	spin_lock(&tx_ring->lock);
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		int err;
+
+		err = netsec_xdp_queue_one(priv, xdpf, true);
+		if (err != NETSEC_XDP_TX) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		} else {
+			tx_ring->xdp_xmit++;
+		}
+	}
+	spin_unlock(&tx_ring->lock);
+
+	if (unlikely(flags & XDP_XMIT_FLUSH)) {
+		netsec_xdp_ring_tx_db(priv, tx_ring->xdp_xmit);
+		tx_ring->xdp_xmit = 0;
+	}
+
+	return n - drops;
+}
+
+static int netsec_xdp_setup(struct netsec_priv *priv, struct bpf_prog *prog,
+			    struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = priv->ndev;
+	struct bpf_prog *old_prog;
+
+	/* For now just support only the usual MTU sized frames */
+	if (prog && dev->mtu > 1500) {
+		NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP");
+		return -EOPNOTSUPP;
+	}
+
+	if (netif_running(dev))
+		netsec_netdev_stop(dev);
+
+	/* Detach old prog, if any */
+	old_prog = xchg(&priv->xdp_prog, prog);
+	if (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (netif_running(dev))
+		netsec_netdev_open(dev);
+
+	return 0;
+}
+
+static int netsec_xdp(struct net_device *ndev, struct netdev_bpf *xdp)
+{
+	struct netsec_priv *priv = netdev_priv(ndev);
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return netsec_xdp_setup(priv, xdp->prog, xdp->extack);
+	case XDP_QUERY_PROG:
+		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops netsec_netdev_ops = {
 	.ndo_init		= netsec_netdev_init,
 	.ndo_uninit		= netsec_netdev_uninit,
@@ -1505,6 +1837,8 @@ static const struct net_device_ops netsec_netdev_ops = {
 	.ndo_set_mac_address    = eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_do_ioctl		= netsec_netdev_ioctl,
+	.ndo_xdp_xmit		= netsec_xdp_xmit,
+	.ndo_bpf		= netsec_xdp,
 };
 
 static int netsec_of_probe(struct platform_device *pdev,
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index bb6d5fb73035..51a7b48db4bc 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1599,7 +1599,7 @@ static int ave_probe(struct platform_device *pdev)
 	ndev->max_mtu = AVE_MAX_ETHFRAME - (ETH_HLEN + ETH_FCS_LEN);
 
 	mac_addr = of_get_mac_address(np);
-	if (mac_addr)
+	if (!IS_ERR(mac_addr))
 		ether_addr_copy(ndev->dev_addr, mac_addr);
 
 	/* if the mac address is invalid, use random mac address */
diff --git a/drivers/net/ethernet/stmicro/Kconfig b/drivers/net/ethernet/stmicro/Kconfig
index ecd7a5edef5d..39ef86360417 100644
--- a/drivers/net/ethernet/stmicro/Kconfig
+++ b/drivers/net/ethernet/stmicro/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # STMicroelectronics device configuration
 #
diff --git a/drivers/net/ethernet/stmicro/Makefile b/drivers/net/ethernet/stmicro/Makefile
index 9b3bfddda7dd..72fd1f6ab9b2 100644
--- a/drivers/net/ethernet/stmicro/Makefile
+++ b/drivers/net/ethernet/stmicro/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the STMicroelectronics device drivers.
 #
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 6209cc1fb305..2325b40dff6e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -1,8 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
 config STMMAC_ETH
-	tristate "STMicroelectronics 10/100/1000/EQOS Ethernet driver"
+	tristate "STMicroelectronics Multi-Gigabit Ethernet driver"
 	depends on HAS_IOMEM && HAS_DMA
 	select MII
-	select PHYLIB
+	select PAGE_POOL
+	select PHYLINK
 	select CRC32
 	imply PTP_1588_CLOCK
 	select RESET_CONTROLLER
@@ -12,6 +14,16 @@ config STMMAC_ETH
 
 if STMMAC_ETH
 
+config STMMAC_SELFTESTS
+	bool "Support for STMMAC Selftests"
+	depends on INET
+	depends on STMMAC_ETH
+	default n
+	---help---
+	  This adds support for STMMAC Selftests using ethtool. Enable this
+	  feature if you are facing problems with your HW and submit the test
+	  results to the netdev Mailing List.
+
 config STMMAC_PLATFORM
 	tristate "STMMAC Platform bus support"
 	depends on STMMAC_ETH
@@ -30,7 +42,6 @@ if STMMAC_PLATFORM
 
 config DWMAC_DWC_QOS_ETH
 	tristate "Support for snps,dwc-qos-ethernet.txt DT binding."
-	select PHYLIB
 	select CRC32
 	select MII
 	depends on OF && HAS_DMA
@@ -105,6 +116,16 @@ config DWMAC_OXNAS
 	  This selects the Oxford Semiconductor OXNASSoC glue layer support for
 	  the stmmac device driver. This driver is used for OX820.
 
+config DWMAC_QCOM_ETHQOS
+	tristate "Qualcomm ETHQOS support"
+	default ARCH_QCOM
+	depends on OF && (ARCH_QCOM || COMPILE_TEST)
+	help
+	  Support for the Qualcomm ETHQOS core.
+
+	  This selects the Qualcomm ETHQOS glue layer support for the
+	  stmmac device driver.
+
 config DWMAC_ROCKCHIP
 	tristate "Rockchip dwmac support"
 	default ARCH_ROCKCHIP
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index bf09701d2623..c59926d96bcc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -8,6 +8,8 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \
 	      $(stmmac-y)
 
+stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o
+
 # Ordering matters. Generic driver must be last.
 obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
 obj-$(CONFIG_DWMAC_ANARION)	+= dwmac-anarion.o
@@ -16,6 +18,7 @@ obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
 obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
 obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o dwmac-meson8b.o
 obj-$(CONFIG_DWMAC_OXNAS)	+= dwmac-oxnas.o
+obj-$(CONFIG_DWMAC_QCOM_ETHQOS)	+= dwmac-qcom-ethqos.o
 obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
 obj-$(CONFIG_DWMAC_SOCFPGA)	+= dwmac-altr-socfpga.o
 obj-$(CONFIG_DWMAC_STI)		+= dwmac-sti.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
index 8b50afcdb52d..cd478d2cd871 100644
--- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
@@ -1,17 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright Altera Corporation (C) 2016. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
  * Author: Tien Hock Loh <thloh@altera.com>
  */
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h
index 2f5882450b06..442812c0a4bd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h
@@ -1,17 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright Altera Corporation (C) 2016. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
  * Author: Tien Hock Loh <thloh@altera.com>
  */
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
index b9c9003060c5..52971f5293aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   Specialised functions for managing Chained mode
 
@@ -7,17 +8,6 @@
   descriptors in case of the DMA is configured to work in chained or
   in ring mode.
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 272b9ca66314..ed872eed1cab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -1,19 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   STMMAC Common Header File
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -256,12 +246,13 @@ struct stmmac_safety_stats {
 
 /* Max/Min RI Watchdog Timer count value */
 #define MAX_DMA_RIWT		0xff
-#define MIN_DMA_RIWT		0x20
+#define MIN_DMA_RIWT		0x10
 /* Tx coalesce parameters */
 #define STMMAC_COAL_TX_TIMER	1000
 #define STMMAC_MAX_COAL_TX_TICK	100000
 #define STMMAC_TX_MAX_FRAMES	256
-#define STMMAC_TX_FRAMES	25
+#define STMMAC_TX_FRAMES	1
+#define STMMAC_RX_FRAMES	25
 
 /* Packets types */
 enum packets_types {
@@ -335,6 +326,7 @@ struct dma_features {
 	/* 802.3az - Energy-Efficient Ethernet (EEE) */
 	unsigned int eee;
 	unsigned int av;
+	unsigned int hash_tb_sz;
 	unsigned int tsoen;
 	/* TX and RX csum */
 	unsigned int tx_coe;
@@ -361,6 +353,7 @@ struct dma_features {
 	unsigned int frpsel;
 	unsigned int frpbs;
 	unsigned int frpes;
+	unsigned int addr64;
 };
 
 /* GMAC TX FIFO is 8K, Rx FIFO is 16K */
@@ -402,8 +395,12 @@ struct mac_link {
 	u32 speed100;
 	u32 speed1000;
 	u32 speed2500;
-	u32 speed10000;
 	u32 duplex;
+	struct {
+		u32 speed2500;
+		u32 speed5000;
+		u32 speed10000;
+	} xgmii;
 };
 
 struct mii_regs {
@@ -424,12 +421,13 @@ struct mac_device_info {
 	const struct stmmac_mode_ops *mode;
 	const struct stmmac_hwtimestamp *ptp;
 	const struct stmmac_tc_ops *tc;
+	const struct stmmac_mmc_ops *mmc;
 	struct mii_regs mii;	/* MII register Addresses */
 	struct mac_link link;
 	void __iomem *pcsr;     /* vpointer to device CSRs */
-	int multicast_filter_bins;
-	int unicast_filter_entries;
-	int mcast_bits_log2;
+	unsigned int multicast_filter_bins;
+	unsigned int unicast_filter_entries;
+	unsigned int mcast_bits_log2;
 	unsigned int rx_csum;
 	unsigned int pcs;
 	unsigned int pmt;
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index 0c2432b1ce67..9f0b9a9e63b3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -1,18 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   Header File to describe the DMA descriptors and related definitions.
   This is for DWMAC100 and 1000 cores.
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -133,7 +123,7 @@
 #define	ETDES1_BUFFER2_SIZE_SHIFT	16
 
 /* Extended Receive descriptor definitions */
-#define	ERDES4_IP_PAYLOAD_TYPE_MASK	GENMASK(2, 6)
+#define	ERDES4_IP_PAYLOAD_TYPE_MASK	GENMASK(6, 2)
 #define	ERDES4_IP_HDR_ERR		BIT(3)
 #define	ERDES4_IP_PAYLOAD_ERR		BIT(4)
 #define	ERDES4_IP_CSUM_BYPASSED		BIT(5)
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
index 40d6356a7e73..40f7f2da9c5e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   Header File to describe Normal/enhanced descriptor functions used for RING
   and CHAINED modes.
@@ -8,17 +9,6 @@
   descriptors in case of the DMA is configured to work in chained or
   in ring mode.
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -29,11 +19,13 @@
 /* Specific functions used for Ring mode */
 
 /* Enhanced descriptors */
-static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end,
+					   int bfsize)
 {
-	p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
-			<< ERDES1_BUFFER2_SIZE_SHIFT)
-		   & ERDES1_BUFFER2_SIZE_MASK);
+	if (bfsize == BUF_SIZE_16KiB)
+		p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
+				<< ERDES1_BUFFER2_SIZE_SHIFT)
+			   & ERDES1_BUFFER2_SIZE_MASK);
 
 	if (end)
 		p->des1 |= cpu_to_le32(ERDES1_END_RING);
@@ -59,11 +51,15 @@ static inline void enh_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
 }
 
 /* Normal descriptors */
-static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end, int bfsize)
 {
-	p->des1 |= cpu_to_le32(((BUF_SIZE_2KiB - 1)
-				<< RDES1_BUFFER2_SIZE_SHIFT)
-		    & RDES1_BUFFER2_SIZE_MASK);
+	if (bfsize >= BUF_SIZE_2KiB) {
+		int bfsize2;
+
+		bfsize2 = min(bfsize - BUF_SIZE_2KiB + 1, BUF_SIZE_2KiB - 1);
+		p->des1 |= cpu_to_le32((bfsize2 << RDES1_BUFFER2_SIZE_SHIFT)
+			    & RDES1_BUFFER2_SIZE_MASK);
+	}
 
 	if (end)
 		p->des1 |= cpu_to_le32(RDES1_END_RING);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
index 85ce80c600c7..6ce3a7fb41ab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
@@ -1,9 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Adaptrum Anarion DWMAC glue layer
  *
  * Copyright (C) 2017, Adaptrum, Inc.
  * (Written by Alexandru Gagniuc <alex.g at adaptrum.com> for Adaptrum, Inc.)
- * Licensed under the GPLv2 or (at your option) any later version.
  */
 
 #include <linux/io.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 3256e5cbad27..3a14cdd01f5f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -1,14 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Synopsys DWC Ethernet Quality-of-Service v4.10a linux driver
  *
  * Copyright (C) 2016 Joao Pinto <jpinto@synopsys.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/clk.h>
@@ -455,7 +449,11 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	priv = data->probe(pdev, plat_dat, &stmmac_res);
 	if (IS_ERR(priv)) {
 		ret = PTR_ERR(priv);
-		dev_err(&pdev->dev, "failed to probe subdriver: %d\n", ret);
+
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "failed to probe subdriver: %d\n",
+				ret);
+
 		goto remove_config;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index bf2562995fc8..79f2ee37afed 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -9,6 +9,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_net.h>
+#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/stmmac.h>
 
@@ -298,6 +299,9 @@ static int mediatek_dwmac_init(struct platform_device *pdev, void *priv)
 		return ret;
 	}
 
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+
 	return 0;
 }
 
@@ -307,6 +311,9 @@ static void mediatek_dwmac_exit(struct platform_device *pdev, void *priv)
 	const struct mediatek_dwmac_variant *variant = plat->variant;
 
 	clk_bulk_disable_unprepare(variant->num_clks, plat->clks);
+
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 }
 
 static int mediatek_dwmac_probe(struct platform_device *pdev)
@@ -346,11 +353,10 @@ static int mediatek_dwmac_probe(struct platform_device *pdev)
 		return PTR_ERR(plat_dat);
 
 	plat_dat->interface = priv_plat->phy_mode;
-	/* clk_csr_i = 250-300MHz & MDC = clk_csr_i/124 */
-	plat_dat->clk_csr = 5;
 	plat_dat->has_gmac4 = 1;
 	plat_dat->has_gmac = 0;
 	plat_dat->pmt = 0;
+	plat_dat->riwt_off = 1;
 	plat_dat->maxmtu = ETH_DATA_LEN;
 	plat_dat->bsp_priv = priv_plat;
 	plat_dat->init = mediatek_dwmac_init;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
index 7fdd1760a74c..88eb16954627 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
@@ -1,14 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Amlogic Meson6 and Meson8 DWMAC glue layer
  *
  * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/device.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index c5979569fd60..786ca4a7bf36 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -1,14 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Amlogic Meson8b, Meson8m2 and GXBB DWMAC glue layer
  *
  * Copyright (C) 2016 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/clk.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
index 3dc7d279f805..8551ea878ba5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Oxford Semiconductor OXNAS DWMAC glue layer
  *
@@ -5,13 +6,6 @@
  * Copyright (C) 2014 Daniel Golle <daniel@makrotopia.org>
  * Copyright (C) 2013 Ma Haijun <mahaijuns@gmail.com>
  * Copyright (C) 2012 John Crispin <blogic@openwrt.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
 #include <linux/device.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
new file mode 100644
index 000000000000..7ec895407d23
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018-19, Linaro Limited
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/phy.h>
+#include "stmmac.h"
+#include "stmmac_platform.h"
+
+#define RGMII_IO_MACRO_CONFIG		0x0
+#define SDCC_HC_REG_DLL_CONFIG		0x4
+#define SDCC_HC_REG_DDR_CONFIG		0xC
+#define SDCC_HC_REG_DLL_CONFIG2		0x10
+#define SDC4_STATUS			0x14
+#define SDCC_USR_CTL			0x18
+#define RGMII_IO_MACRO_CONFIG2		0x1C
+#define RGMII_IO_MACRO_DEBUG1		0x20
+#define EMAC_SYSTEM_LOW_POWER_DEBUG	0x28
+
+/* RGMII_IO_MACRO_CONFIG fields */
+#define RGMII_CONFIG_FUNC_CLK_EN		BIT(30)
+#define RGMII_CONFIG_POS_NEG_DATA_SEL		BIT(23)
+#define RGMII_CONFIG_GPIO_CFG_RX_INT		GENMASK(21, 20)
+#define RGMII_CONFIG_GPIO_CFG_TX_INT		GENMASK(19, 17)
+#define RGMII_CONFIG_MAX_SPD_PRG_9		GENMASK(16, 8)
+#define RGMII_CONFIG_MAX_SPD_PRG_2		GENMASK(7, 6)
+#define RGMII_CONFIG_INTF_SEL			GENMASK(5, 4)
+#define RGMII_CONFIG_BYPASS_TX_ID_EN		BIT(3)
+#define RGMII_CONFIG_LOOPBACK_EN		BIT(2)
+#define RGMII_CONFIG_PROG_SWAP			BIT(1)
+#define RGMII_CONFIG_DDR_MODE			BIT(0)
+
+/* SDCC_HC_REG_DLL_CONFIG fields */
+#define SDCC_DLL_CONFIG_DLL_RST			BIT(30)
+#define SDCC_DLL_CONFIG_PDN			BIT(29)
+#define SDCC_DLL_CONFIG_MCLK_FREQ		GENMASK(26, 24)
+#define SDCC_DLL_CONFIG_CDR_SELEXT		GENMASK(23, 20)
+#define SDCC_DLL_CONFIG_CDR_EXT_EN		BIT(19)
+#define SDCC_DLL_CONFIG_CK_OUT_EN		BIT(18)
+#define SDCC_DLL_CONFIG_CDR_EN			BIT(17)
+#define SDCC_DLL_CONFIG_DLL_EN			BIT(16)
+#define SDCC_DLL_MCLK_GATING_EN			BIT(5)
+#define SDCC_DLL_CDR_FINE_PHASE			GENMASK(3, 2)
+
+/* SDCC_HC_REG_DDR_CONFIG fields */
+#define SDCC_DDR_CONFIG_PRG_DLY_EN		BIT(31)
+#define SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY	GENMASK(26, 21)
+#define SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE	GENMASK(29, 27)
+#define SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN	BIT(30)
+#define SDCC_DDR_CONFIG_PRG_RCLK_DLY		GENMASK(8, 0)
+
+/* SDCC_HC_REG_DLL_CONFIG2 fields */
+#define SDCC_DLL_CONFIG2_DLL_CLOCK_DIS		BIT(21)
+#define SDCC_DLL_CONFIG2_MCLK_FREQ_CALC		GENMASK(17, 10)
+#define SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SEL	GENMASK(3, 2)
+#define SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW	BIT(1)
+#define SDCC_DLL_CONFIG2_DDR_CAL_EN		BIT(0)
+
+/* SDC4_STATUS bits */
+#define SDC4_STATUS_DLL_LOCK			BIT(7)
+
+/* RGMII_IO_MACRO_CONFIG2 fields */
+#define RGMII_CONFIG2_RSVD_CONFIG15		GENMASK(31, 17)
+#define RGMII_CONFIG2_RGMII_CLK_SEL_CFG		BIT(16)
+#define RGMII_CONFIG2_TX_TO_RX_LOOPBACK_EN	BIT(13)
+#define RGMII_CONFIG2_CLK_DIVIDE_SEL		BIT(12)
+#define RGMII_CONFIG2_RX_PROG_SWAP		BIT(7)
+#define RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL	BIT(6)
+#define RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN	BIT(5)
+
+struct ethqos_emac_por {
+	unsigned int offset;
+	unsigned int value;
+};
+
+struct qcom_ethqos {
+	struct platform_device *pdev;
+	void __iomem *rgmii_base;
+
+	unsigned int rgmii_clk_rate;
+	struct clk *rgmii_clk;
+	unsigned int speed;
+
+	const struct ethqos_emac_por *por;
+	unsigned int num_por;
+};
+
+static int rgmii_readl(struct qcom_ethqos *ethqos, unsigned int offset)
+{
+	return readl(ethqos->rgmii_base + offset);
+}
+
+static void rgmii_writel(struct qcom_ethqos *ethqos,
+			 int value, unsigned int offset)
+{
+	writel(value, ethqos->rgmii_base + offset);
+}
+
+static void rgmii_updatel(struct qcom_ethqos *ethqos,
+			  int mask, int val, unsigned int offset)
+{
+	unsigned int temp;
+
+	temp =  rgmii_readl(ethqos, offset);
+	temp = (temp & ~(mask)) | val;
+	rgmii_writel(ethqos, temp, offset);
+}
+
+static void rgmii_dump(struct qcom_ethqos *ethqos)
+{
+	dev_dbg(&ethqos->pdev->dev, "Rgmii register dump\n");
+	dev_dbg(&ethqos->pdev->dev, "RGMII_IO_MACRO_CONFIG: %x\n",
+		rgmii_readl(ethqos, RGMII_IO_MACRO_CONFIG));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_HC_REG_DLL_CONFIG: %x\n",
+		rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_HC_REG_DDR_CONFIG: %x\n",
+		rgmii_readl(ethqos, SDCC_HC_REG_DDR_CONFIG));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_HC_REG_DLL_CONFIG2: %x\n",
+		rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG2));
+	dev_dbg(&ethqos->pdev->dev, "SDC4_STATUS: %x\n",
+		rgmii_readl(ethqos, SDC4_STATUS));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_USR_CTL: %x\n",
+		rgmii_readl(ethqos, SDCC_USR_CTL));
+	dev_dbg(&ethqos->pdev->dev, "RGMII_IO_MACRO_CONFIG2: %x\n",
+		rgmii_readl(ethqos, RGMII_IO_MACRO_CONFIG2));
+	dev_dbg(&ethqos->pdev->dev, "RGMII_IO_MACRO_DEBUG1: %x\n",
+		rgmii_readl(ethqos, RGMII_IO_MACRO_DEBUG1));
+	dev_dbg(&ethqos->pdev->dev, "EMAC_SYSTEM_LOW_POWER_DEBUG: %x\n",
+		rgmii_readl(ethqos, EMAC_SYSTEM_LOW_POWER_DEBUG));
+}
+
+/* Clock rates */
+#define RGMII_1000_NOM_CLK_FREQ			(250 * 1000 * 1000UL)
+#define RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ	 (50 * 1000 * 1000UL)
+#define RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ	  (5 * 1000 * 1000UL)
+
+static void
+ethqos_update_rgmii_clk(struct qcom_ethqos *ethqos, unsigned int speed)
+{
+	switch (speed) {
+	case SPEED_1000:
+		ethqos->rgmii_clk_rate =  RGMII_1000_NOM_CLK_FREQ;
+		break;
+
+	case SPEED_100:
+		ethqos->rgmii_clk_rate =  RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ;
+		break;
+
+	case SPEED_10:
+		ethqos->rgmii_clk_rate =  RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ;
+		break;
+	}
+
+	clk_set_rate(ethqos->rgmii_clk, ethqos->rgmii_clk_rate);
+}
+
+static void ethqos_set_func_clk_en(struct qcom_ethqos *ethqos)
+{
+	rgmii_updatel(ethqos, RGMII_CONFIG_FUNC_CLK_EN,
+		      RGMII_CONFIG_FUNC_CLK_EN, RGMII_IO_MACRO_CONFIG);
+}
+
+static const struct ethqos_emac_por emac_v2_3_0_por[] = {
+	{ .offset = RGMII_IO_MACRO_CONFIG,	.value = 0x00C01343 },
+	{ .offset = SDCC_HC_REG_DLL_CONFIG,	.value = 0x2004642C },
+	{ .offset = SDCC_HC_REG_DDR_CONFIG,	.value = 0x00000000 },
+	{ .offset = SDCC_HC_REG_DLL_CONFIG2,	.value = 0x00200000 },
+	{ .offset = SDCC_USR_CTL,		.value = 0x00010800 },
+	{ .offset = RGMII_IO_MACRO_CONFIG2,	.value = 0x00002060 },
+};
+
+static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
+{
+	unsigned int val;
+	int retry = 1000;
+
+	/* Set CDR_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CDR_EN,
+		      SDCC_DLL_CONFIG_CDR_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Set CDR_EXT_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CDR_EXT_EN,
+		      SDCC_DLL_CONFIG_CDR_EXT_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Clear CK_OUT_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN,
+		      0, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Set DLL_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN,
+		      SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	rgmii_updatel(ethqos, SDCC_DLL_MCLK_GATING_EN,
+		      0, SDCC_HC_REG_DLL_CONFIG);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CDR_FINE_PHASE,
+		      0, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Wait for CK_OUT_EN clear */
+	do {
+		val = rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG);
+		val &= SDCC_DLL_CONFIG_CK_OUT_EN;
+		if (!val)
+			break;
+		mdelay(1);
+		retry--;
+	} while (retry > 0);
+	if (!retry)
+		dev_err(&ethqos->pdev->dev, "Clear CK_OUT_EN timedout\n");
+
+	/* Set CK_OUT_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN,
+		      SDCC_DLL_CONFIG_CK_OUT_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Wait for CK_OUT_EN set */
+	retry = 1000;
+	do {
+		val = rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG);
+		val &= SDCC_DLL_CONFIG_CK_OUT_EN;
+		if (val)
+			break;
+		mdelay(1);
+		retry--;
+	} while (retry > 0);
+	if (!retry)
+		dev_err(&ethqos->pdev->dev, "Set CK_OUT_EN timedout\n");
+
+	/* Set DDR_CAL_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_CAL_EN,
+		      SDCC_DLL_CONFIG2_DDR_CAL_EN, SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DLL_CLOCK_DIS,
+		      0, SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_MCLK_FREQ_CALC,
+		      0x1A << 10, SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SEL,
+		      BIT(2), SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW,
+		      SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW,
+		      SDCC_HC_REG_DLL_CONFIG2);
+
+	return 0;
+}
+
+static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
+{
+	/* Disable loopback mode */
+	rgmii_updatel(ethqos, RGMII_CONFIG2_TX_TO_RX_LOOPBACK_EN,
+		      0, RGMII_IO_MACRO_CONFIG2);
+
+	/* Select RGMII, write 0 to interface select */
+	rgmii_updatel(ethqos, RGMII_CONFIG_INTF_SEL,
+		      0, RGMII_IO_MACRO_CONFIG);
+
+	switch (ethqos->speed) {
+	case SPEED_1000:
+		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
+			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP,
+			      RGMII_CONFIG_PROG_SWAP, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP,
+			      RGMII_CONFIG2_RX_PROG_SWAP,
+			      RGMII_IO_MACRO_CONFIG2);
+
+		/* Set PRG_RCLK_DLY to 57 for 1.8 ns delay */
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_PRG_RCLK_DLY,
+			      57, SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_PRG_DLY_EN,
+			      SDCC_DDR_CONFIG_PRG_DLY_EN,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN,
+			      RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG);
+		break;
+
+	case SPEED_100:
+		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
+			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG_MAX_SPD_PRG_2,
+			      BIT(6), RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		/* Write 0x5 to PRG_RCLK_DLY_CODE */
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE,
+			      (BIT(29) | BIT(27)), SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN,
+			      RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG);
+		break;
+
+	case SPEED_10:
+		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
+			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG_MAX_SPD_PRG_9,
+			      BIT(12) | GENMASK(9, 8),
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		/* Write 0x5 to PRG_RCLK_DLY_CODE */
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE,
+			      (BIT(29) | BIT(27)), SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN,
+			      RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG);
+		break;
+	default:
+		dev_err(&ethqos->pdev->dev,
+			"Invalid speed %d\n", ethqos->speed);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ethqos_configure(struct qcom_ethqos *ethqos)
+{
+	volatile unsigned int dll_lock;
+	unsigned int i, retry = 1000;
+
+	/* Reset to POR values and enable clk */
+	for (i = 0; i < ethqos->num_por; i++)
+		rgmii_writel(ethqos, ethqos->por[i].value,
+			     ethqos->por[i].offset);
+	ethqos_set_func_clk_en(ethqos);
+
+	/* Initialize the DLL first */
+
+	/* Set DLL_RST */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_RST,
+		      SDCC_DLL_CONFIG_DLL_RST, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Set PDN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN,
+		      SDCC_DLL_CONFIG_PDN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Clear DLL_RST */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_RST, 0,
+		      SDCC_HC_REG_DLL_CONFIG);
+
+	/* Clear PDN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN, 0,
+		      SDCC_HC_REG_DLL_CONFIG);
+
+	if (ethqos->speed != SPEED_100 && ethqos->speed != SPEED_10) {
+		/* Set DLL_EN */
+		rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN,
+			      SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG);
+
+		/* Set CK_OUT_EN */
+		rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN,
+			      SDCC_DLL_CONFIG_CK_OUT_EN,
+			      SDCC_HC_REG_DLL_CONFIG);
+
+		/* Set USR_CTL bit 26 with mask of 3 bits */
+		rgmii_updatel(ethqos, GENMASK(26, 24), BIT(26), SDCC_USR_CTL);
+
+		/* wait for DLL LOCK */
+		do {
+			mdelay(1);
+			dll_lock = rgmii_readl(ethqos, SDC4_STATUS);
+			if (dll_lock & SDC4_STATUS_DLL_LOCK)
+				break;
+		} while (retry > 0);
+		if (!retry)
+			dev_err(&ethqos->pdev->dev,
+				"Timeout while waiting for DLL lock\n");
+	}
+
+	if (ethqos->speed == SPEED_1000)
+		ethqos_dll_configure(ethqos);
+
+	ethqos_rgmii_macro_init(ethqos);
+
+	return 0;
+}
+
+static void ethqos_fix_mac_speed(void *priv, unsigned int speed)
+{
+	struct qcom_ethqos *ethqos = priv;
+
+	ethqos->speed = speed;
+	ethqos_update_rgmii_clk(ethqos, speed);
+	ethqos_configure(ethqos);
+}
+
+static int qcom_ethqos_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct qcom_ethqos *ethqos;
+	struct resource *res;
+	int ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return ret;
+
+	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+	if (IS_ERR(plat_dat)) {
+		dev_err(&pdev->dev, "dt configuration failed\n");
+		return PTR_ERR(plat_dat);
+	}
+
+	ethqos = devm_kzalloc(&pdev->dev, sizeof(*ethqos), GFP_KERNEL);
+	if (!ethqos) {
+		ret = -ENOMEM;
+		goto err_mem;
+	}
+
+	ethqos->pdev = pdev;
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rgmii");
+	ethqos->rgmii_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ethqos->rgmii_base)) {
+		dev_err(&pdev->dev, "Can't get rgmii base\n");
+		ret = PTR_ERR(ethqos->rgmii_base);
+		goto err_mem;
+	}
+
+	ethqos->por = of_device_get_match_data(&pdev->dev);
+
+	ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii");
+	if (IS_ERR(ethqos->rgmii_clk)) {
+		ret = PTR_ERR(ethqos->rgmii_clk);
+		goto err_mem;
+	}
+
+	ret = clk_prepare_enable(ethqos->rgmii_clk);
+	if (ret)
+		goto err_mem;
+
+	ethqos->speed = SPEED_1000;
+	ethqos_update_rgmii_clk(ethqos, SPEED_1000);
+	ethqos_set_func_clk_en(ethqos);
+
+	plat_dat->bsp_priv = ethqos;
+	plat_dat->fix_mac_speed = ethqos_fix_mac_speed;
+	plat_dat->has_gmac4 = 1;
+	plat_dat->pmt = 1;
+	plat_dat->tso_en = of_property_read_bool(np, "snps,tso");
+
+	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	if (ret)
+		goto err_clk;
+
+	rgmii_dump(ethqos);
+
+	return ret;
+
+err_clk:
+	clk_disable_unprepare(ethqos->rgmii_clk);
+
+err_mem:
+	stmmac_remove_config_dt(pdev, plat_dat);
+
+	return ret;
+}
+
+static int qcom_ethqos_remove(struct platform_device *pdev)
+{
+	struct qcom_ethqos *ethqos;
+	int ret;
+
+	ethqos = get_stmmac_bsp_priv(&pdev->dev);
+	if (!ethqos)
+		return -ENODEV;
+
+	ret = stmmac_pltfr_remove(pdev);
+	clk_disable_unprepare(ethqos->rgmii_clk);
+
+	return ret;
+}
+
+static const struct of_device_id qcom_ethqos_match[] = {
+	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qcom_ethqos_match);
+
+static struct platform_driver qcom_ethqos_driver = {
+	.probe  = qcom_ethqos_probe,
+	.remove = qcom_ethqos_remove,
+	.driver = {
+		.name           = "qcom-ethqos",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = of_match_ptr(qcom_ethqos_match),
+	},
+};
+module_platform_driver(qcom_ethqos_driver);
+
+MODULE_DESCRIPTION("Qualcomm ETHQOS driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 3b174eae77c1..4644b2aeeba1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1,19 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /**
  * dwmac-rk.c - Rockchip RK3288 DWMAC specific glue layer
  *
  * Copyright (C) 2014 Chen-Zhi (Roger Chen)
  *
  * Chen-Zhi (Roger Chen)  <roger.chen@rock-chips.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/stmmac.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 5b3b06a0a3bf..c141fe783e87 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -1,21 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /* Copyright Altera Corporation (C) 2014. All rights reserved.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
  * Adopted from dwmac-sti.c
  */
 
-#include <linux/mfd/syscon.h>
+#include <linux/mfd/altera-sysmgr.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_net.h>
@@ -38,9 +27,12 @@
 #define SYSMGR_EMACGRP_CTRL_PHYSEL_WIDTH 2
 #define SYSMGR_EMACGRP_CTRL_PHYSEL_MASK 0x00000003
 #define SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK 0x00000010
+#define SYSMGR_GEN10_EMACGRP_CTRL_PTP_REF_CLK_MASK 0x00000100
 
 #define SYSMGR_FPGAGRP_MODULE_REG  0x00000028
 #define SYSMGR_FPGAGRP_MODULE_EMAC 0x00000004
+#define SYSMGR_FPGAINTF_EMAC_REG	0x00000070
+#define SYSMGR_FPGAINTF_EMAC_BIT	0x1
 
 #define EMAC_SPLITTER_CTRL_REG			0x0
 #define EMAC_SPLITTER_CTRL_SPEED_MASK		0x3
@@ -48,6 +40,11 @@
 #define EMAC_SPLITTER_CTRL_SPEED_100		0x3
 #define EMAC_SPLITTER_CTRL_SPEED_1000		0x0
 
+struct socfpga_dwmac;
+struct socfpga_dwmac_ops {
+	int (*set_phy_mode)(struct socfpga_dwmac *dwmac_priv);
+};
+
 struct socfpga_dwmac {
 	int	interface;
 	u32	reg_offset;
@@ -59,6 +56,7 @@ struct socfpga_dwmac {
 	void __iomem *splitter_base;
 	bool f2h_ptp_ref_clk;
 	struct tse_pcs pcs;
+	const struct socfpga_dwmac_ops *ops;
 };
 
 static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed)
@@ -114,7 +112,8 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device *
 
 	dwmac->interface = of_get_phy_mode(np);
 
-	sys_mgr_base_addr = syscon_regmap_lookup_by_phandle(np, "altr,sysmgr-syscon");
+	sys_mgr_base_addr =
+		altr_sysmgr_regmap_lookup_by_phandle(np, "altr,sysmgr-syscon");
 	if (IS_ERR(sys_mgr_base_addr)) {
 		dev_info(dev, "No sysmgr-syscon node found\n");
 		return PTR_ERR(sys_mgr_base_addr);
@@ -232,25 +231,36 @@ err_node_put:
 	return ret;
 }
 
-static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac)
+static int socfpga_set_phy_mode_common(int phymode, u32 *val)
 {
-	struct regmap *sys_mgr_base_addr = dwmac->sys_mgr_base_addr;
-	int phymode = dwmac->interface;
-	u32 reg_offset = dwmac->reg_offset;
-	u32 reg_shift = dwmac->reg_shift;
-	u32 ctrl, val, module;
-
 	switch (phymode) {
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
-		val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII;
+		*val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII;
 		break;
 	case PHY_INTERFACE_MODE_MII:
 	case PHY_INTERFACE_MODE_GMII:
 	case PHY_INTERFACE_MODE_SGMII:
-		val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
+		*val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		*val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII;
 		break;
 	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int socfpga_gen5_set_phy_mode(struct socfpga_dwmac *dwmac)
+{
+	struct regmap *sys_mgr_base_addr = dwmac->sys_mgr_base_addr;
+	int phymode = dwmac->interface;
+	u32 reg_offset = dwmac->reg_offset;
+	u32 reg_shift = dwmac->reg_shift;
+	u32 ctrl, val, module;
+
+	if (socfpga_set_phy_mode_common(phymode, &val)) {
 		dev_err(dwmac->dev, "bad phy mode %d\n", phymode);
 		return -EINVAL;
 	}
@@ -301,6 +311,62 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac)
 	return 0;
 }
 
+static int socfpga_gen10_set_phy_mode(struct socfpga_dwmac *dwmac)
+{
+	struct regmap *sys_mgr_base_addr = dwmac->sys_mgr_base_addr;
+	int phymode = dwmac->interface;
+	u32 reg_offset = dwmac->reg_offset;
+	u32 reg_shift = dwmac->reg_shift;
+	u32 ctrl, val, module;
+
+	if (socfpga_set_phy_mode_common(phymode, &val))
+		return -EINVAL;
+
+	/* Overwrite val to GMII if splitter core is enabled. The phymode here
+	 * is the actual phy mode on phy hardware, but phy interface from
+	 * EMAC core is GMII.
+	 */
+	if (dwmac->splitter_base)
+		val = SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII;
+
+	/* Assert reset to the enet controller before changing the phy mode */
+	reset_control_assert(dwmac->stmmac_ocp_rst);
+	reset_control_assert(dwmac->stmmac_rst);
+
+	regmap_read(sys_mgr_base_addr, reg_offset, &ctrl);
+	ctrl &= ~(SYSMGR_EMACGRP_CTRL_PHYSEL_MASK);
+	ctrl |= val;
+
+	if (dwmac->f2h_ptp_ref_clk ||
+	    phymode == PHY_INTERFACE_MODE_MII ||
+	    phymode == PHY_INTERFACE_MODE_GMII ||
+	    phymode == PHY_INTERFACE_MODE_SGMII) {
+		ctrl |= SYSMGR_GEN10_EMACGRP_CTRL_PTP_REF_CLK_MASK;
+		regmap_read(sys_mgr_base_addr, SYSMGR_FPGAINTF_EMAC_REG,
+			    &module);
+		module |= (SYSMGR_FPGAINTF_EMAC_BIT << reg_shift);
+		regmap_write(sys_mgr_base_addr, SYSMGR_FPGAINTF_EMAC_REG,
+			     module);
+	} else {
+		ctrl &= ~SYSMGR_GEN10_EMACGRP_CTRL_PTP_REF_CLK_MASK;
+	}
+
+	regmap_write(sys_mgr_base_addr, reg_offset, ctrl);
+
+	/* Deassert reset for the phy configuration to be sampled by
+	 * the enet controller, and operation to start in requested mode
+	 */
+	reset_control_deassert(dwmac->stmmac_ocp_rst);
+	reset_control_deassert(dwmac->stmmac_rst);
+	if (phymode == PHY_INTERFACE_MODE_SGMII) {
+		if (tse_pcs_init(dwmac->pcs.tse_pcs_base, &dwmac->pcs) != 0) {
+			dev_err(dwmac->dev, "Unable to initialize TSE PCS");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 static int socfpga_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat_dat;
@@ -310,6 +376,13 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	struct socfpga_dwmac	*dwmac;
 	struct net_device	*ndev;
 	struct stmmac_priv	*stpriv;
+	const struct socfpga_dwmac_ops *ops;
+
+	ops = device_get_match_data(&pdev->dev);
+	if (!ops) {
+		dev_err(&pdev->dev, "no of match data provided\n");
+		return -EINVAL;
+	}
 
 	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
 	if (ret)
@@ -340,6 +413,7 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 		goto err_remove_config_dt;
 	}
 
+	dwmac->ops = ops;
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed;
 
@@ -356,7 +430,7 @@ static int socfpga_dwmac_probe(struct platform_device *pdev)
 	 */
 	dwmac->stmmac_rst = stpriv->plat->stmmac_rst;
 
-	ret = socfpga_dwmac_set_phy_mode(dwmac);
+	ret = ops->set_phy_mode(dwmac);
 	if (ret)
 		goto err_dvr_remove;
 
@@ -375,8 +449,9 @@ static int socfpga_dwmac_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct socfpga_dwmac *dwmac_priv = get_stmmac_bsp_priv(dev);
 
-	socfpga_dwmac_set_phy_mode(priv->plat->bsp_priv);
+	dwmac_priv->ops->set_phy_mode(priv->plat->bsp_priv);
 
 	/* Before the enet controller is suspended, the phy is suspended.
 	 * This causes the phy clock to be gated. The enet controller is
@@ -403,8 +478,17 @@ static int socfpga_dwmac_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(socfpga_dwmac_pm_ops, stmmac_suspend,
 					       socfpga_dwmac_resume);
 
+static const struct socfpga_dwmac_ops socfpga_gen5_ops = {
+	.set_phy_mode = socfpga_gen5_set_phy_mode,
+};
+
+static const struct socfpga_dwmac_ops socfpga_gen10_ops = {
+	.set_phy_mode = socfpga_gen10_set_phy_mode,
+};
+
 static const struct of_device_id socfpga_dwmac_match[] = {
-	{ .compatible = "altr,socfpga-stmmac" },
+	{ .compatible = "altr,socfpga-stmmac", .data = &socfpga_gen5_ops },
+	{ .compatible = "altr,socfpga-stmmac-a10-s10", .data = &socfpga_gen10_ops },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, socfpga_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index 86e0e053804c..e9fd661f7995 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * dwmac-sti.c - STMicroelectronics DWMAC Specific Glue layer
  *
  * Copyright (C) 2003-2014 STMicroelectronics (R&D) Limited
  * Author: Srinivas Kandagatla <srinivas.kandagatla@st.com>
  * Contributors: Giuseppe Cavallaro <peppe.cavallaro@st.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index 7e2e79dedebf..4ef041bdf6a1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * dwmac-stm32.c - DWMAC Specific Glue layer for STM32 MCU
  *
  * Copyright (C) STMicroelectronics SA 2017
  * Author:  Alexandre Torgue <alexandre.torgue@st.com> for STMicroelectronics.
- * License terms:  GNU General Public License (GPL), version 2
- *
  */
 
 #include <linux/clk.h>
@@ -25,9 +24,24 @@
 
 #define SYSCFG_MCU_ETH_MASK		BIT(23)
 #define SYSCFG_MP1_ETH_MASK		GENMASK(23, 16)
+#define SYSCFG_PMCCLRR_OFFSET		0x40
 
 #define SYSCFG_PMCR_ETH_CLK_SEL		BIT(16)
 #define SYSCFG_PMCR_ETH_REF_CLK_SEL	BIT(17)
+
+/*  Ethernet PHY interface selection in register SYSCFG Configuration
+ *------------------------------------------
+ * src	 |BIT(23)| BIT(22)| BIT(21)|BIT(20)|
+ *------------------------------------------
+ * MII   |   0	 |   0	  |   0    |   1   |
+ *------------------------------------------
+ * GMII  |   0	 |   0	  |   0    |   0   |
+ *------------------------------------------
+ * RGMII |   0	 |   0	  |   1	   |  n/a  |
+ *------------------------------------------
+ * RMII  |   1	 |   0	  |   0	   |  n/a  |
+ *------------------------------------------
+ */
 #define SYSCFG_PMCR_ETH_SEL_MII		BIT(20)
 #define SYSCFG_PMCR_ETH_SEL_RGMII	BIT(21)
 #define SYSCFG_PMCR_ETH_SEL_RMII	BIT(23)
@@ -35,14 +49,54 @@
 #define SYSCFG_MCU_ETH_SEL_MII		0
 #define SYSCFG_MCU_ETH_SEL_RMII		1
 
+/* STM32MP1 register definitions
+ *
+ * Below table summarizes the clock requirement and clock sources for
+ * supported phy interface modes.
+ * __________________________________________________________________________
+ *|PHY_MODE | Normal | PHY wo crystal|   PHY wo crystal   |No 125Mhz from PHY|
+ *|         |        |      25MHz    |        50MHz       |                  |
+ * ---------------------------------------------------------------------------
+ *|  MII    |	 -   |     eth-ck    |	      n/a	  |	  n/a        |
+ *|         |        |		     |                    |		     |
+ * ---------------------------------------------------------------------------
+ *|  GMII   |	 -   |     eth-ck    |	      n/a	  |	  n/a        |
+ *|         |        |               |                    |		     |
+ * ---------------------------------------------------------------------------
+ *| RGMII   |	 -   |     eth-ck    |	      n/a	  |  eth-ck (no pin) |
+ *|         |        |               |                    |  st,eth-clk-sel  |
+ * ---------------------------------------------------------------------------
+ *| RMII    |	 -   |     eth-ck    |	    eth-ck        |	  n/a        |
+ *|         |        |		     | st,eth-ref-clk-sel |		     |
+ * ---------------------------------------------------------------------------
+ *
+ * BIT(17) : set this bit in RMII mode when you have PHY without crystal 50MHz
+ * BIT(16) : set this bit in GMII/RGMII PHY when you do not want use 125Mhz
+ * from PHY
+ *-----------------------------------------------------
+ * src	 |         BIT(17)       |       BIT(16)      |
+ *-----------------------------------------------------
+ * MII   |           n/a	 |         n/a        |
+ *-----------------------------------------------------
+ * GMII  |           n/a         |   st,eth-clk-sel   |
+ *-----------------------------------------------------
+ * RGMII |           n/a         |   st,eth-clk-sel   |
+ *-----------------------------------------------------
+ * RMII  |   st,eth-ref-clk-sel	 |         n/a        |
+ *-----------------------------------------------------
+ *
+ */
+
 struct stm32_dwmac {
 	struct clk *clk_tx;
 	struct clk *clk_rx;
 	struct clk *clk_eth_ck;
 	struct clk *clk_ethstp;
 	struct clk *syscfg_clk;
-	bool int_phyclk;	/* Clock from RCC to drive PHY */
-	u32 mode_reg;		/* MAC glue-logic mode register */
+	int eth_clk_sel_reg;
+	int eth_ref_clk_sel_reg;
+	int irq_pwr_wakeup;
+	u32 mode_reg;		 /* MAC glue-logic mode register */
 	struct regmap *regmap;
 	u32 speed;
 	const struct stm32_ops *ops;
@@ -102,7 +156,7 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare)
 		if (ret)
 			return ret;
 
-		if (dwmac->int_phyclk) {
+		if (dwmac->clk_eth_ck) {
 			ret = clk_prepare_enable(dwmac->clk_eth_ck);
 			if (ret) {
 				clk_disable_unprepare(dwmac->syscfg_clk);
@@ -111,7 +165,7 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare)
 		}
 	} else {
 		clk_disable_unprepare(dwmac->syscfg_clk);
-		if (dwmac->int_phyclk)
+		if (dwmac->clk_eth_ck)
 			clk_disable_unprepare(dwmac->clk_eth_ck);
 	}
 	return ret;
@@ -121,7 +175,7 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 {
 	struct stm32_dwmac *dwmac = plat_dat->bsp_priv;
 	u32 reg = dwmac->mode_reg;
-	int val;
+	int val, ret;
 
 	switch (plat_dat->interface) {
 	case PHY_INTERFACE_MODE_MII:
@@ -130,19 +184,22 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 	case PHY_INTERFACE_MODE_GMII:
 		val = SYSCFG_PMCR_ETH_SEL_GMII;
-		if (dwmac->int_phyclk)
+		if (dwmac->eth_clk_sel_reg)
 			val |= SYSCFG_PMCR_ETH_CLK_SEL;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_GMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RMII:
 		val = SYSCFG_PMCR_ETH_SEL_RMII;
-		if (dwmac->int_phyclk)
+		if (dwmac->eth_ref_clk_sel_reg)
 			val |= SYSCFG_PMCR_ETH_REF_CLK_SEL;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		val = SYSCFG_PMCR_ETH_SEL_RGMII;
-		if (dwmac->int_phyclk)
+		if (dwmac->eth_clk_sel_reg)
 			val |= SYSCFG_PMCR_ETH_CLK_SEL;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RGMII\n");
 		break;
@@ -153,6 +210,11 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 		return -EINVAL;
 	}
 
+	/* Need to update PMCCLRR (clear register) */
+	ret = regmap_write(dwmac->regmap, reg + SYSCFG_PMCCLRR_OFFSET,
+			   dwmac->ops->syscfg_eth_mask);
+
+	/* Update PMCSETR (set register) */
 	return regmap_update_bits(dwmac->regmap, reg,
 				 dwmac->ops->syscfg_eth_mask, val);
 }
@@ -180,7 +242,7 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat)
 	}
 
 	return regmap_update_bits(dwmac->regmap, reg,
-				 dwmac->ops->syscfg_eth_mask, val);
+				 dwmac->ops->syscfg_eth_mask, val << 23);
 }
 
 static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac)
@@ -232,24 +294,29 @@ static int stm32_dwmac_parse_data(struct stm32_dwmac *dwmac,
 static int stm32mp1_parse_data(struct stm32_dwmac *dwmac,
 			       struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct device_node *np = dev->of_node;
+	int err = 0;
 
-	dwmac->int_phyclk = of_property_read_bool(np, "st,int-phyclk");
+	/* Gigabit Ethernet 125MHz clock selection. */
+	dwmac->eth_clk_sel_reg = of_property_read_bool(np, "st,eth-clk-sel");
 
-	/* Check if internal clk from RCC selected */
-	if (dwmac->int_phyclk) {
-		/*  Get ETH_CLK clocks */
-		dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck");
-		if (IS_ERR(dwmac->clk_eth_ck)) {
-			dev_err(dev, "No ETH CK clock provided...\n");
-			return PTR_ERR(dwmac->clk_eth_ck);
-		}
+	/* Ethernet 50Mhz RMII clock selection */
+	dwmac->eth_ref_clk_sel_reg =
+		of_property_read_bool(np, "st,eth-ref-clk-sel");
+
+	/*  Get ETH_CLK clocks */
+	dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck");
+	if (IS_ERR(dwmac->clk_eth_ck)) {
+		dev_warn(dev, "No phy clock provided...\n");
+		dwmac->clk_eth_ck = NULL;
 	}
 
 	/*  Clock used for low power mode */
 	dwmac->clk_ethstp = devm_clk_get(dev, "ethstp");
 	if (IS_ERR(dwmac->clk_ethstp)) {
-		dev_err(dev, "No ETH peripheral clock provided for CStop mode ...\n");
+		dev_err(dev,
+			"No ETH peripheral clock provided for CStop mode ...\n");
 		return PTR_ERR(dwmac->clk_ethstp);
 	}
 
@@ -260,7 +327,29 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac,
 		return PTR_ERR(dwmac->syscfg_clk);
 	}
 
-	return 0;
+	/* Get IRQ information early to have an ability to ask for deferred
+	 * probe if needed before we went too far with resource allocation.
+	 */
+	dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev,
+							"stm32_pwr_wakeup");
+	if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
+	if (!dwmac->clk_eth_ck && dwmac->irq_pwr_wakeup >= 0) {
+		err = device_init_wakeup(&pdev->dev, true);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to init wake up irq\n");
+			return err;
+		}
+		err = dev_pm_set_dedicated_wake_irq(&pdev->dev,
+						    dwmac->irq_pwr_wakeup);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to set wake up irq\n");
+			device_init_wakeup(&pdev->dev, false);
+		}
+		device_set_wakeup_enable(&pdev->dev, false);
+	}
+	return err;
 }
 
 static int stm32_dwmac_probe(struct platform_device *pdev)
@@ -326,9 +415,15 @@ static int stm32_dwmac_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	int ret = stmmac_dvr_remove(&pdev->dev);
+	struct stm32_dwmac *dwmac = priv->plat->bsp_priv;
 
 	stm32_dwmac_clk_disable(priv->plat->bsp_priv);
 
+	if (dwmac->irq_pwr_wakeup >= 0) {
+		dev_pm_clear_wake_irq(&pdev->dev);
+		device_init_wakeup(&pdev->dev, false);
+	}
+
 	return ret;
 }
 
@@ -342,7 +437,7 @@ static int stm32mp1_suspend(struct stm32_dwmac *dwmac)
 
 	clk_disable_unprepare(dwmac->clk_tx);
 	clk_disable_unprepare(dwmac->syscfg_clk);
-	if (dwmac->int_phyclk)
+	if (dwmac->clk_eth_ck)
 		clk_disable_unprepare(dwmac->clk_eth_ck);
 
 	return ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 0f660af01a4b..4083019c547a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1,17 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * dwmac-sun8i.c - Allwinner sun8i DWMAC specific glue layer
  *
  * Copyright (C) 2017 Corentin Labbe <clabbe.montjoie@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/clk.h>
@@ -147,6 +138,20 @@ static const struct emac_variant emac_variant_a64 = {
 	.tx_delay_max = 7,
 };
 
+static const struct emac_variant emac_variant_h6 = {
+	.default_syscon_value = 0x50000,
+	.syscon_field = &sun8i_syscon_reg_field,
+	/* The "Internal PHY" of H6 is not on the die. It's on the
+	 * co-packaged AC200 chip instead.
+	 */
+	.soc_has_internal_phy = false,
+	.support_mii = true,
+	.support_rmii = true,
+	.support_rgmii = true,
+	.rx_delay_max = 31,
+	.tx_delay_max = 7,
+};
+
 #define EMAC_BASIC_CTL0 0x00
 #define EMAC_BASIC_CTL1 0x04
 #define EMAC_INT_STA    0x08
@@ -187,7 +192,7 @@ static const struct emac_variant emac_variant_a64 = {
 
 /* Used in RX_CTL1*/
 #define EMAC_RX_MD              BIT(1)
-#define EMAC_RX_TH_MASK		GENMASK(4, 5)
+#define EMAC_RX_TH_MASK		GENMASK(5, 4)
 #define EMAC_RX_TH_32		0
 #define EMAC_RX_TH_64		(0x1 << 4)
 #define EMAC_RX_TH_96		(0x2 << 4)
@@ -198,7 +203,7 @@ static const struct emac_variant emac_variant_a64 = {
 /* Used in TX_CTL1*/
 #define EMAC_TX_MD              BIT(1)
 #define EMAC_TX_NEXT_FRM        BIT(2)
-#define EMAC_TX_TH_MASK		GENMASK(8, 10)
+#define EMAC_TX_TH_MASK		GENMASK(10, 8)
 #define EMAC_TX_TH_64		0
 #define EMAC_TX_TH_128		(0x1 << 8)
 #define EMAC_TX_TH_192		(0x2 << 8)
@@ -284,18 +289,18 @@ static void sun8i_dwmac_dma_init(void __iomem *ioaddr,
 
 static void sun8i_dwmac_dma_init_rx(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_rx_phy, u32 chan)
+				    dma_addr_t dma_rx_phy, u32 chan)
 {
 	/* Write RX descriptors address */
-	writel(dma_rx_phy, ioaddr + EMAC_RX_DESC_LIST);
+	writel(lower_32_bits(dma_rx_phy), ioaddr + EMAC_RX_DESC_LIST);
 }
 
 static void sun8i_dwmac_dma_init_tx(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_tx_phy, u32 chan)
+				    dma_addr_t dma_tx_phy, u32 chan)
 {
 	/* Write TX descriptors address */
-	writel(dma_tx_phy, ioaddr + EMAC_TX_DESC_LIST);
+	writel(lower_32_bits(dma_tx_phy), ioaddr + EMAC_TX_DESC_LIST);
 }
 
 /* sun8i_dwmac_dump_regs() - Dump EMAC address space
@@ -893,6 +898,11 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
 		 * address. No need to mask it again.
 		 */
 		reg |= 1 << H3_EPHY_ADDR_SHIFT;
+	} else {
+		/* For SoCs without internal PHY the PHY selection bit should be
+		 * set to 0 (external PHY).
+		 */
+		reg &= ~H3_EPHY_SELECT;
 	}
 
 	if (!of_property_read_u32(node, "allwinner,tx-delay-ps", &val)) {
@@ -986,6 +996,18 @@ static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv)
 		regulator_disable(gmac->regulator);
 }
 
+static void sun8i_dwmac_set_mac_loopback(void __iomem *ioaddr, bool enable)
+{
+	u32 value = readl(ioaddr + EMAC_BASIC_CTL0);
+
+	if (enable)
+		value |= EMAC_LOOPBACK;
+	else
+		value &= ~EMAC_LOOPBACK;
+
+	writel(value, ioaddr + EMAC_BASIC_CTL0);
+}
+
 static const struct stmmac_ops sun8i_dwmac_ops = {
 	.core_init = sun8i_dwmac_core_init,
 	.set_mac = sun8i_dwmac_set_mac,
@@ -995,6 +1017,7 @@ static const struct stmmac_ops sun8i_dwmac_ops = {
 	.flow_ctrl = sun8i_dwmac_flow_ctrl,
 	.set_umac_addr = sun8i_dwmac_set_umac_addr,
 	.get_umac_addr = sun8i_dwmac_get_umac_addr,
+	.set_mac_loopback = sun8i_dwmac_set_mac_loopback,
 };
 
 static struct mac_device_info *sun8i_dwmac_setup(void *ppriv)
@@ -1015,6 +1038,8 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv)
 	mac->mac = &sun8i_dwmac_ops;
 	mac->dma = &sun8i_dwmac_dma_ops;
 
+	priv->dev->priv_flags |= IFF_UNICAST_FLT;
+
 	/* The loopback bit seems to be re-set when link change
 	 * Simply mask it each time
 	 * Speed 10/100/1000 are set in BIT(2)/BIT(3)
@@ -1147,7 +1172,10 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	plat_dat->interface = of_get_phy_mode(dev->of_node);
+	ret = of_get_phy_mode(dev->of_node);
+	if (ret < 0)
+		return -EINVAL;
+	plat_dat->interface = ret;
 
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
@@ -1207,6 +1235,8 @@ static const struct of_device_id sun8i_dwmac_match[] = {
 		.data = &emac_variant_r40 },
 	{ .compatible = "allwinner,sun50i-a64-emac",
 		.data = &emac_variant_a64 },
+	{ .compatible = "allwinner,sun50i-h6-emac",
+		.data = &emac_variant_h6 },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sun8i_dwmac_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 62ccbd47c1db..a299da3971b4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -1,19 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * dwmac-sunxi.c - Allwinner sunxi DWMAC specific glue layer
  *
  * Copyright (C) 2013 Chen-Yu Tsai
  *
  * Chen-Yu Tsai  <wens@csie.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/stmmac.h>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100.h b/drivers/net/ethernet/stmicro/stmmac/dwmac100.h
index e14984814041..35ab8d0bdce7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100.h
@@ -1,19 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   MAC 10/100 Header File
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 184ca13c8f79..b70d44ac0990 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -1,17 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -146,6 +136,7 @@ enum inter_frame_gap {
 #define GMAC_FRAME_FILTER_DAIF	0x00000008	/* DA Inverse Filtering */
 #define GMAC_FRAME_FILTER_PM	0x00000010	/* Pass all multicast */
 #define GMAC_FRAME_FILTER_DBF	0x00000020	/* Disable Broadcast frames */
+#define GMAC_FRAME_FILTER_PCF	0x00000080	/* Pass Control frames */
 #define GMAC_FRAME_FILTER_SAIF	0x00000100	/* Inverse Filtering */
 #define GMAC_FRAME_FILTER_SAF	0x00000200	/* Source Address Filter */
 #define GMAC_FRAME_FILTER_HPF	0x00000400	/* Hash or perfect Filter */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 0877bde6e860..3d69da112625 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This is the driver for the GMAC on-chip Ethernet controller for ST SoCs.
   DWC Ether MAC 10/100/1000 Universal version 3.41a  has been used for
@@ -7,17 +8,6 @@
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -172,7 +162,7 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 	memset(mc_filter, 0, sizeof(mc_filter));
 
 	if (dev->flags & IFF_PROMISC) {
-		value = GMAC_FRAME_FILTER_PR;
+		value = GMAC_FRAME_FILTER_PR | GMAC_FRAME_FILTER_PCF;
 	} else if (dev->flags & IFF_ALLMULTI) {
 		value = GMAC_FRAME_FILTER_PM;	/* pass all multi */
 	} else if (!netdev_mc_empty(dev)) {
@@ -198,6 +188,7 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 		}
 	}
 
+	value |= GMAC_FRAME_FILTER_HPF;
 	dwmac1000_set_mchash(ioaddr, mc_filter, mcbitslog2);
 
 	/* Handle multiple unicast addresses (perfect filtering) */
@@ -216,6 +207,12 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 					    GMAC_ADDR_LOW(reg));
 			reg++;
 		}
+
+		while (reg <= perfect_addr_number) {
+			writel(0, ioaddr + GMAC_ADDR_HIGH(reg));
+			writel(0, ioaddr + GMAC_ADDR_LOW(reg));
+			reg++;
+		}
 	}
 
 #ifdef FRAME_FILTER_DEBUG
@@ -499,6 +496,18 @@ static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
 		x->mac_gmii_rx_proto_engine++;
 }
 
+static void dwmac1000_set_mac_loopback(void __iomem *ioaddr, bool enable)
+{
+	u32 value = readl(ioaddr + GMAC_CONTROL);
+
+	if (enable)
+		value |= GMAC_CONTROL_LM;
+	else
+		value &= ~GMAC_CONTROL_LM;
+
+	writel(value, ioaddr + GMAC_CONTROL);
+}
+
 const struct stmmac_ops dwmac1000_ops = {
 	.core_init = dwmac1000_core_init,
 	.set_mac = stmmac_set_mac,
@@ -518,6 +527,7 @@ const struct stmmac_ops dwmac1000_ops = {
 	.pcs_ctrl_ane = dwmac1000_ctrl_ane,
 	.pcs_rane = dwmac1000_rane,
 	.pcs_get_adv_lp = dwmac1000_get_adv_lp,
+	.set_mac_loopback = dwmac1000_set_mac_loopback,
 };
 
 int dwmac1000_setup(struct stmmac_priv *priv)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index aacc4aa80e3c..2bac49b49f73 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This is the driver for the GMAC on-chip Ethernet controller for ST SoCs.
   DWC Ether MAC 10/100/1000 Universal version 3.41a  has been used for
@@ -7,17 +8,6 @@
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -122,18 +112,18 @@ static void dwmac1000_dma_init(void __iomem *ioaddr,
 
 static void dwmac1000_dma_init_rx(void __iomem *ioaddr,
 				  struct stmmac_dma_cfg *dma_cfg,
-				  u32 dma_rx_phy, u32 chan)
+				  dma_addr_t dma_rx_phy, u32 chan)
 {
 	/* RX descriptor base address list must be written into DMA CSR3 */
-	writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR);
 }
 
 static void dwmac1000_dma_init_tx(void __iomem *ioaddr,
 				  struct stmmac_dma_cfg *dma_cfg,
-				  u32 dma_tx_phy, u32 chan)
+				  dma_addr_t dma_tx_phy, u32 chan)
 {
 	/* TX descriptor base address list must be written into DMA CSR4 */
-	writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
+	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR);
 }
 
 static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index b735143987e1..ebcad8dd99db 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This is the driver for the MAC 10/100 on-chip Ethernet controller
   currently tested on all the ST boards based on STb7109 and stx7200 SoCs.
@@ -9,17 +10,6 @@
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -160,6 +150,18 @@ static void dwmac100_pmt(struct mac_device_info *hw, unsigned long mode)
 	return;
 }
 
+static void dwmac100_set_mac_loopback(void __iomem *ioaddr, bool enable)
+{
+	u32 value = readl(ioaddr + MAC_CONTROL);
+
+	if (enable)
+		value |= MAC_CONTROL_OM;
+	else
+		value &= ~MAC_CONTROL_OM;
+
+	writel(value, ioaddr + MAC_CONTROL);
+}
+
 const struct stmmac_ops dwmac100_ops = {
 	.core_init = dwmac100_core_init,
 	.set_mac = stmmac_set_mac,
@@ -171,6 +173,7 @@ const struct stmmac_ops dwmac100_ops = {
 	.pmt = dwmac100_pmt,
 	.set_umac_addr = dwmac100_set_umac_addr,
 	.get_umac_addr = dwmac100_get_umac_addr,
+	.set_mac_loopback = dwmac100_set_mac_loopback,
 };
 
 int dwmac100_setup(struct stmmac_priv *priv)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index 21dee25ee570..8f0d9bc7cab5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This is the driver for the MAC 10/100 on-chip Ethernet controller
   currently tested on all the ST boards based on STb7109 and stx7200 SoCs.
@@ -9,17 +10,6 @@
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -41,18 +31,18 @@ static void dwmac100_dma_init(void __iomem *ioaddr,
 
 static void dwmac100_dma_init_rx(void __iomem *ioaddr,
 				 struct stmmac_dma_cfg *dma_cfg,
-				 u32 dma_rx_phy, u32 chan)
+				 dma_addr_t dma_rx_phy, u32 chan)
 {
 	/* RX descriptor base addr lists must be written into DMA CSR3 */
-	writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR);
 }
 
 static void dwmac100_dma_init_tx(void __iomem *ioaddr,
 				 struct stmmac_dma_cfg *dma_cfg,
-				 u32 dma_tx_phy, u32 chan)
+				 dma_addr_t dma_tx_phy, u32 chan)
 {
 	/* TX descriptor base addr lists must be written into DMA CSR4 */
-	writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
+	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR);
 }
 
 /* Store and Forward capability is not used at all.
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index eb013d54025a..2ed11a581d80 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * DWMAC4 Header file.
  *
  * Copyright (C) 2015  STMicroelectronics Ltd
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
  * Author: Alexandre Torgue <alexandre.torgue@st.com>
  */
 
@@ -18,8 +15,7 @@
 /*  MAC registers */
 #define GMAC_CONFIG			0x00000000
 #define GMAC_PACKET_FILTER		0x00000008
-#define GMAC_HASH_TAB_0_31		0x00000010
-#define GMAC_HASH_TAB_32_63		0x00000014
+#define GMAC_HASH_TAB(x)		(0x10 + (x) * 4)
 #define GMAC_RX_FLOW_CTRL		0x00000090
 #define GMAC_QX_TX_FLOW_CTRL(x)		(0x70 + x * 4)
 #define GMAC_TXQ_PRTY_MAP0		0x98
@@ -64,6 +60,8 @@
 #define GMAC_PACKET_FILTER_PR		BIT(0)
 #define GMAC_PACKET_FILTER_HMC		BIT(2)
 #define GMAC_PACKET_FILTER_PM		BIT(4)
+#define GMAC_PACKET_FILTER_PCF		BIT(7)
+#define GMAC_PACKET_FILTER_HPF		BIT(10)
 
 #define GMAC_MAX_PERFECT_ADDRESSES	128
 
@@ -160,6 +158,7 @@ enum power_event {
 #define GMAC_CONFIG_PS			BIT(15)
 #define GMAC_CONFIG_FES			BIT(14)
 #define GMAC_CONFIG_DM			BIT(13)
+#define GMAC_CONFIG_LM			BIT(12)
 #define GMAC_CONFIG_DCRS		BIT(9)
 #define GMAC_CONFIG_TE			BIT(1)
 #define GMAC_CONFIG_RE			BIT(0)
@@ -181,6 +180,7 @@ enum power_event {
 #define GMAC_HW_FEAT_MIISEL		BIT(0)
 
 /* MAC HW features1 bitmap */
+#define GMAC_HW_HASH_TB_SZ		GENMASK(25, 24)
 #define GMAC_HW_FEAT_AVSEL		BIT(20)
 #define GMAC_HW_TSOEN			BIT(18)
 #define GMAC_HW_TXFIFOSIZE		GENMASK(10, 6)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 7e5d5db0d516..01c2e2d83e76 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * This is the driver for the GMAC on-chip Ethernet controller for ST SoCs.
  * DWC Ether MAC version 4.00  has been used for developing this code.
@@ -6,10 +7,6 @@
  *
  * Copyright (C) 2015  STMicroelectronics Ltd
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
  * Author: Alexandre Torgue <alexandre.torgue@st.com>
  */
 
@@ -192,6 +189,8 @@ static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw,
 	default:
 		break;
 	}
+
+	writel(value, ioaddr + MTL_OPERATION_MODE);
 }
 
 static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw,
@@ -401,57 +400,74 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 			      struct net_device *dev)
 {
 	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
-	unsigned int value = 0;
+	int numhashregs = (hw->multicast_filter_bins >> 5);
+	int mcbitslog2 = hw->mcast_bits_log2;
+	unsigned int value;
+	int i;
 
+	value = readl(ioaddr + GMAC_PACKET_FILTER);
+	value &= ~GMAC_PACKET_FILTER_HMC;
+	value &= ~GMAC_PACKET_FILTER_HPF;
+	value &= ~GMAC_PACKET_FILTER_PCF;
+	value &= ~GMAC_PACKET_FILTER_PM;
+	value &= ~GMAC_PACKET_FILTER_PR;
 	if (dev->flags & IFF_PROMISC) {
-		value = GMAC_PACKET_FILTER_PR;
+		value = GMAC_PACKET_FILTER_PR | GMAC_PACKET_FILTER_PCF;
 	} else if ((dev->flags & IFF_ALLMULTI) ||
-			(netdev_mc_count(dev) > HASH_TABLE_SIZE)) {
+		   (netdev_mc_count(dev) > hw->multicast_filter_bins)) {
 		/* Pass all multi */
-		value = GMAC_PACKET_FILTER_PM;
-		/* Set the 64 bits of the HASH tab. To be updated if taller
-		 * hash table is used
-		 */
-		writel(0xffffffff, ioaddr + GMAC_HASH_TAB_0_31);
-		writel(0xffffffff, ioaddr + GMAC_HASH_TAB_32_63);
+		value |= GMAC_PACKET_FILTER_PM;
+		/* Set all the bits of the HASH tab */
+		for (i = 0; i < numhashregs; i++)
+			writel(0xffffffff, ioaddr + GMAC_HASH_TAB(i));
 	} else if (!netdev_mc_empty(dev)) {
-		u32 mc_filter[2];
 		struct netdev_hw_addr *ha;
+		u32 mc_filter[8];
 
 		/* Hash filter for multicast */
-		value = GMAC_PACKET_FILTER_HMC;
+		value |= GMAC_PACKET_FILTER_HMC;
 
 		memset(mc_filter, 0, sizeof(mc_filter));
 		netdev_for_each_mc_addr(ha, dev) {
-			/* The upper 6 bits of the calculated CRC are used to
-			 * index the content of the Hash Table Reg 0 and 1.
+			/* The upper n bits of the calculated CRC are used to
+			 * index the contents of the hash table. The number of
+			 * bits used depends on the hardware configuration
+			 * selected at core configuration time.
 			 */
-			int bit_nr =
-				(bitrev32(~crc32_le(~0, ha->addr, 6)) >> 26);
-			/* The most significant bit determines the register
-			 * to use while the other 5 bits determines the bit
-			 * within the selected register
+			int bit_nr = bitrev32(~crc32_le(~0, ha->addr,
+					ETH_ALEN)) >> (32 - mcbitslog2);
+			/* The most significant bit determines the register to
+			 * use (H/L) while the other 5 bits determine the bit
+			 * within the register.
 			 */
-			mc_filter[bit_nr >> 5] |= (1 << (bit_nr & 0x1F));
+			mc_filter[bit_nr >> 5] |= (1 << (bit_nr & 0x1f));
 		}
-		writel(mc_filter[0], ioaddr + GMAC_HASH_TAB_0_31);
-		writel(mc_filter[1], ioaddr + GMAC_HASH_TAB_32_63);
+		for (i = 0; i < numhashregs; i++)
+			writel(mc_filter[i], ioaddr + GMAC_HASH_TAB(i));
 	}
 
+	value |= GMAC_PACKET_FILTER_HPF;
+
 	/* Handle multiple unicast addresses */
 	if (netdev_uc_count(dev) > GMAC_MAX_PERFECT_ADDRESSES) {
 		/* Switch to promiscuous mode if more than 128 addrs
 		 * are required
 		 */
 		value |= GMAC_PACKET_FILTER_PR;
-	} else if (!netdev_uc_empty(dev)) {
-		int reg = 1;
+	} else {
 		struct netdev_hw_addr *ha;
+		int reg = 1;
 
 		netdev_for_each_uc_addr(ha, dev) {
 			dwmac4_set_umac_addr(hw, ha->addr, reg);
 			reg++;
 		}
+
+		while (reg < GMAC_MAX_PERFECT_ADDRESSES) {
+			writel(0, ioaddr + GMAC_ADDR_HIGH(reg));
+			writel(0, ioaddr + GMAC_ADDR_LOW(reg));
+			reg++;
+		}
 	}
 
 	writel(value, ioaddr + GMAC_PACKET_FILTER);
@@ -469,8 +485,9 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
 	if (fc & FLOW_RX) {
 		pr_debug("\tReceive Flow-Control ON\n");
 		flow |= GMAC_RX_FLOW_CTRL_RFE;
-		writel(flow, ioaddr + GMAC_RX_FLOW_CTRL);
 	}
+	writel(flow, ioaddr + GMAC_RX_FLOW_CTRL);
+
 	if (fc & FLOW_TX) {
 		pr_debug("\tTransmit Flow-Control ON\n");
 
@@ -478,7 +495,7 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
 			pr_debug("\tduplex mode: PAUSE %d\n", pause_time);
 
 		for (queue = 0; queue < tx_cnt; queue++) {
-			flow |= GMAC_TX_FLOW_CTRL_TFE;
+			flow = GMAC_TX_FLOW_CTRL_TFE;
 
 			if (duplex)
 				flow |=
@@ -486,6 +503,9 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
 
 			writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
 		}
+	} else {
+		for (queue = 0; queue < tx_cnt; queue++)
+			writel(0, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
 	}
 }
 
@@ -701,6 +721,18 @@ static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
 		x->mac_gmii_rx_proto_engine++;
 }
 
+static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable)
+{
+	u32 value = readl(ioaddr + GMAC_CONFIG);
+
+	if (enable)
+		value |= GMAC_CONFIG_LM;
+	else
+		value &= ~GMAC_CONFIG_LM;
+
+	writel(value, ioaddr + GMAC_CONFIG);
+}
+
 const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
 	.set_mac = stmmac_set_mac,
@@ -730,6 +762,7 @@ const struct stmmac_ops dwmac4_ops = {
 	.pcs_get_adv_lp = dwmac4_get_adv_lp,
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
+	.set_mac_loopback = dwmac4_set_mac_loopback,
 };
 
 const struct stmmac_ops dwmac410_ops = {
@@ -761,6 +794,7 @@ const struct stmmac_ops dwmac410_ops = {
 	.pcs_get_adv_lp = dwmac4_get_adv_lp,
 	.debug = dwmac4_debug,
 	.set_filter = dwmac4_set_filter,
+	.set_mac_loopback = dwmac4_set_mac_loopback,
 };
 
 const struct stmmac_ops dwmac510_ops = {
@@ -797,6 +831,7 @@ const struct stmmac_ops dwmac510_ops = {
 	.safety_feat_dump = dwmac5_safety_feat_dump,
 	.rxp_config = dwmac5_rxp_config,
 	.flex_pps_config = dwmac5_flex_pps_config,
+	.set_mac_loopback = dwmac4_set_mac_loopback,
 };
 
 int dwmac4_setup(struct stmmac_priv *priv)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 20299f6f65fc..dbde23e7e169 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * This contains the functions to handle the descriptors for DesignWare databook
  * 4.xx.
  *
  * Copyright (C) 2015  STMicroelectronics Ltd
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
  * Author: Alexandre Torgue <alexandre.torgue@st.com>
  */
 
@@ -241,15 +238,18 @@ static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts)
 static int dwmac4_rx_check_timestamp(void *desc)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes0 = le32_to_cpu(p->des0);
+	unsigned int rdes1 = le32_to_cpu(p->des1);
+	unsigned int rdes3 = le32_to_cpu(p->des3);
 	u32 own, ctxt;
 	int ret = 1;
 
-	own = p->des3 & RDES3_OWN;
-	ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR)
+	own = rdes3 & RDES3_OWN;
+	ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR)
 		>> RDES3_CONTEXT_DESCRIPTOR_SHIFT);
 
 	if (likely(!own && ctxt)) {
-		if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff))
+		if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff))
 			/* Corrupted value */
 			ret = -EINVAL;
 		else
@@ -268,7 +268,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, void *next_desc,
 	int ret = -EINVAL;
 
 	/* Get the status from normal w/b descriptor */
-	if (likely(p->des3 & TDES3_RS1V)) {
+	if (likely(le32_to_cpu(p->des3) & RDES3_RDES1_VALID)) {
 		if (likely(le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)) {
 			int i = 0;
 
@@ -293,7 +293,7 @@ exit:
 }
 
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				   int mode, int end)
+				   int mode, int end, int bfsize)
 {
 	dwmac4_set_rx_owner(p, disable_rx_ic);
 }
@@ -443,6 +443,15 @@ static void dwmac4_clear(struct dma_desc *p)
 	p->des3 = 0;
 }
 
+static int set_16kib_bfsize(int mtu)
+{
+	int ret = 0;
+
+	if (unlikely(mtu >= BUF_SIZE_8KiB))
+		ret = BUF_SIZE_16KiB;
+	return ret;
+}
+
 const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.tx_status = dwmac4_wrback_get_tx_status,
 	.rx_status = dwmac4_wrback_get_rx_status,
@@ -469,4 +478,6 @@ const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.clear = dwmac4_clear,
 };
 
-const struct stmmac_mode_ops dwmac4_ring_mode_ops = { };
+const struct stmmac_mode_ops dwmac4_ring_mode_ops = {
+	.set_16kib_bfsize = set_16kib_bfsize,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
index 9736c505211a..f58191174287 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Header File to describe the DMA descriptors and related definitions specific
  * for DesignWare databook 4.xx.
  *
  * Copyright (C) 2015  STMicroelectronics Ltd
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
  * Author: Alexandre Torgue <alexandre.torgue@st.com>
  */
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index edb6053bd980..3ed5508586ef 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * This is the driver for the GMAC on-chip Ethernet controller for ST SoCs.
  * DWC Ether MAC version 4.xx  has been used for  developing this code.
@@ -6,10 +7,6 @@
  *
  * Copyright (C) 2015  STMicroelectronics Ltd
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
  * Author: Alexandre Torgue <alexandre.torgue@st.com>
  */
 
@@ -73,7 +70,7 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 
 static void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_rx_phy, u32 chan)
+				    dma_addr_t dma_rx_phy, u32 chan)
 {
 	u32 value;
 	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
@@ -82,12 +79,12 @@ static void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
 	value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
 	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
-	writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
+	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
 }
 
 static void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_tx_phy, u32 chan)
+				    dma_addr_t dma_tx_phy, u32 chan)
 {
 	u32 value;
 	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
@@ -100,7 +97,7 @@ static void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
 
 	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
-	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
+	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
 }
 
 static void dwmac4_dma_init_channel(void __iomem *ioaddr,
@@ -354,6 +351,7 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr,
 
 	/* MAC HW feature1 */
 	hw_cap = readl(ioaddr + GMAC_HW_FEATURE1);
+	dma_cap->hash_tb_sz = (hw_cap & GMAC_HW_HASH_TB_SZ) >> 24;
 	dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20;
 	dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18;
 	/* RX and TX FIFO sizes are encoded as log2(n / 128). Undo that by
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 22a4a6dbb1a4..b66da0237d2a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * DWMAC4 DMA Header file.
  *
- *
  * Copyright (C) 2007-2015  STMicroelectronics Ltd
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
  * Author: Alexandre Torgue <alexandre.torgue@st.com>
  */
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index 49f5687879df..f2a29a90e085 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2007-2015  STMicroelectronics Ltd
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
  * Author: Alexandre Torgue <alexandre.torgue@st.com>
  */
 
@@ -88,10 +85,6 @@ void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 
 	value &= ~DMA_CONTROL_SR;
 	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
-
-	value = readl(ioaddr + GMAC_CONFIG);
-	value &= ~GMAC_CONFIG_RE;
-	writel(value, ioaddr + GMAC_CONFIG);
 }
 
 void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
@@ -124,9 +117,9 @@ void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
 			 struct stmmac_extra_stats *x, u32 chan)
 {
-	int ret = 0;
-
 	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
+	u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
+	int ret = 0;
 
 	/* ABNORMAL interrupts */
 	if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
@@ -151,16 +144,11 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 	if (likely(intr_status & DMA_CHAN_STATUS_NIS)) {
 		x->normal_irq_n++;
 		if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
-			u32 value;
-
-			value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
-			/* to schedule NAPI on real RIE event. */
-			if (likely(value & DMA_CHAN_INTR_ENA_RIE)) {
-				x->rx_normal_irq_n++;
-				ret |= handle_rx;
-			}
+			x->rx_normal_irq_n++;
+			ret |= handle_rx;
 		}
-		if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
+		if (likely(intr_status & (DMA_CHAN_STATUS_TI |
+					  DMA_CHAN_STATUS_TBU))) {
 			x->tx_normal_irq_n++;
 			ret |= handle_tx;
 		}
@@ -168,12 +156,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 			x->rx_early_irq++;
 	}
 
-	/* Clear the interrupt by writing a logic 1 to the chanX interrupt
-	 * status [21-0] expect reserved bits [5-3]
-	 */
-	writel((intr_status & 0x3fffc7),
-	       ioaddr + DMA_CHAN_STATUS(chan));
-
+	writel(intr_status & intr_en, ioaddr + DMA_CHAN_STATUS(chan));
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index adc54006f884..292b880f3f9f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -1,19 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   DWMAC DMA Header file.
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 7516ca210855..1bc25aa86dbd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -1,17 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index d6bb953685fa..7f86dffb264d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -15,10 +15,14 @@
 /* MAC Registers */
 #define XGMAC_TX_CONFIG			0x00000000
 #define XGMAC_CONFIG_SS_OFF		29
-#define XGMAC_CONFIG_SS_MASK		GENMASK(30, 29)
+#define XGMAC_CONFIG_SS_MASK		GENMASK(31, 29)
 #define XGMAC_CONFIG_SS_10000		(0x0 << XGMAC_CONFIG_SS_OFF)
-#define XGMAC_CONFIG_SS_2500		(0x2 << XGMAC_CONFIG_SS_OFF)
-#define XGMAC_CONFIG_SS_1000		(0x3 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_2500_GMII	(0x2 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_1000_GMII	(0x3 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_100_MII		(0x4 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_5000		(0x5 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_2500		(0x6 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_10_MII		(0x7 << XGMAC_CONFIG_SS_OFF)
 #define XGMAC_CONFIG_SARC		GENMASK(22, 20)
 #define XGMAC_CONFIG_SARC_SHIFT		20
 #define XGMAC_CONFIG_JD			BIT(16)
@@ -29,6 +33,7 @@
 #define XGMAC_CONFIG_GPSL		GENMASK(29, 16)
 #define XGMAC_CONFIG_GPSL_SHIFT		16
 #define XGMAC_CONFIG_S2KP		BIT(11)
+#define XGMAC_CONFIG_LM			BIT(10)
 #define XGMAC_CONFIG_IPC		BIT(9)
 #define XGMAC_CONFIG_JE			BIT(8)
 #define XGMAC_CONFIG_WD			BIT(7)
@@ -39,6 +44,7 @@
 #define XGMAC_CORE_INIT_RX		0
 #define XGMAC_PACKET_FILTER		0x00000008
 #define XGMAC_FILTER_RA			BIT(31)
+#define XGMAC_FILTER_PCF		BIT(7)
 #define XGMAC_FILTER_PM			BIT(4)
 #define XGMAC_FILTER_HMC		BIT(2)
 #define XGMAC_FILTER_PR			BIT(0)
@@ -81,6 +87,7 @@
 #define XGMAC_HWFEAT_GMIISEL		BIT(1)
 #define XGMAC_HW_FEATURE1		0x00000120
 #define XGMAC_HWFEAT_TSOEN		BIT(18)
+#define XGMAC_HWFEAT_ADDR64		GENMASK(15, 14)
 #define XGMAC_HWFEAT_TXFIFOSIZE		GENMASK(10, 6)
 #define XGMAC_HWFEAT_RXFIFOSIZE		GENMASK(4, 0)
 #define XGMAC_HW_FEATURE2		0x00000124
@@ -143,6 +150,11 @@
 #define XGMAC_RSF			BIT(5)
 #define XGMAC_RTC			GENMASK(1, 0)
 #define XGMAC_RTC_SHIFT			0
+#define XGMAC_MTL_RXQ_FLOW_CONTROL(x)	(0x00001150 + (0x80 * (x)))
+#define XGMAC_RFD			GENMASK(31, 17)
+#define XGMAC_RFD_SHIFT			17
+#define XGMAC_RFA			GENMASK(15, 1)
+#define XGMAC_RFA_SHIFT			1
 #define XGMAC_MTL_QINTEN(x)		(0x00001170 + (0x80 * (x)))
 #define XGMAC_RXOIE			BIT(16)
 #define XGMAC_MTL_QINT_STATUS(x)	(0x00001174 + (0x80 * (x)))
@@ -161,6 +173,7 @@
 #define XGMAC_EN_LPI			BIT(15)
 #define XGMAC_LPI_XIT_PKT		BIT(14)
 #define XGMAC_AAL			BIT(12)
+#define XGMAC_EAME			BIT(11)
 #define XGMAC_BLEN			GENMASK(7, 1)
 #define XGMAC_BLEN256			BIT(7)
 #define XGMAC_BLEN128			BIT(6)
@@ -170,6 +183,10 @@
 #define XGMAC_BLEN8			BIT(2)
 #define XGMAC_BLEN4			BIT(1)
 #define XGMAC_UNDEF			BIT(0)
+#define XGMAC_TX_EDMA_CTRL		0x00003040
+#define XGMAC_TDPS			GENMASK(29, 0)
+#define XGMAC_RX_EDMA_CTRL		0x00003044
+#define XGMAC_RDPS			GENMASK(29, 0)
 #define XGMAC_DMA_CH_CONTROL(x)		(0x00003100 + (0x80 * (x)))
 #define XGMAC_PBLx8			BIT(16)
 #define XGMAC_DMA_CH_TX_CONTROL(x)	(0x00003104 + (0x80 * (x)))
@@ -182,7 +199,9 @@
 #define XGMAC_RxPBL			GENMASK(21, 16)
 #define XGMAC_RxPBL_SHIFT		16
 #define XGMAC_RXST			BIT(0)
+#define XGMAC_DMA_CH_TxDESC_HADDR(x)	(0x00003110 + (0x80 * (x)))
 #define XGMAC_DMA_CH_TxDESC_LADDR(x)	(0x00003114 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_HADDR(x)	(0x00003118 + (0x80 * (x)))
 #define XGMAC_DMA_CH_RxDESC_LADDR(x)	(0x0000311c + (0x80 * (x)))
 #define XGMAC_DMA_CH_TxDESC_TAIL_LPTR(x)	(0x00003124 + (0x80 * (x)))
 #define XGMAC_DMA_CH_RxDESC_TAIL_LPTR(x)	(0x0000312c + (0x80 * (x)))
@@ -193,9 +212,10 @@
 #define XGMAC_AIE			BIT(14)
 #define XGMAC_RBUE			BIT(7)
 #define XGMAC_RIE			BIT(6)
+#define XGMAC_TBUE			BIT(2)
 #define XGMAC_TIE			BIT(0)
 #define XGMAC_DMA_INT_DEFAULT_EN	(XGMAC_NIE | XGMAC_AIE | XGMAC_RBUE | \
-					XGMAC_RIE | XGMAC_TIE)
+					XGMAC_RIE | XGMAC_TBUE | XGMAC_TIE)
 #define XGMAC_DMA_CH_Rx_WATCHDOG(x)	(0x0000313c + (0x80 * (x)))
 #define XGMAC_RWT			GENMASK(7, 0)
 #define XGMAC_DMA_CH_STATUS(x)		(0x00003160 + (0x80 * (x)))
@@ -204,6 +224,7 @@
 #define XGMAC_FBE			BIT(12)
 #define XGMAC_RBU			BIT(7)
 #define XGMAC_RI			BIT(6)
+#define XGMAC_TBU			BIT(2)
 #define XGMAC_TPS			BIT(1)
 #define XGMAC_TI			BIT(0)
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 64b8cb88ea45..0a32c96a7854 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -36,7 +36,7 @@ static void dwxgmac2_core_init(struct mac_device_info *hw,
 
 		switch (hw->ps) {
 		case SPEED_10000:
-			tx |= hw->link.speed10000;
+			tx |= hw->link.xgmii.speed10000;
 			break;
 		case SPEED_2500:
 			tx |= hw->link.speed2500;
@@ -310,7 +310,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw,
 	u32 value = XGMAC_FILTER_RA;
 
 	if (dev->flags & IFF_PROMISC) {
-		value |= XGMAC_FILTER_PR;
+		value |= XGMAC_FILTER_PR | XGMAC_FILTER_PCF;
 	} else if ((dev->flags & IFF_ALLMULTI) ||
 		   (netdev_mc_count(dev) > HASH_TABLE_SIZE)) {
 		value |= XGMAC_FILTER_PM;
@@ -321,6 +321,18 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw,
 	writel(value, ioaddr + XGMAC_PACKET_FILTER);
 }
 
+static void dwxgmac2_set_mac_loopback(void __iomem *ioaddr, bool enable)
+{
+	u32 value = readl(ioaddr + XGMAC_RX_CONFIG);
+
+	if (enable)
+		value |= XGMAC_CONFIG_LM;
+	else
+		value &= ~XGMAC_CONFIG_LM;
+
+	writel(value, ioaddr + XGMAC_RX_CONFIG);
+}
+
 const struct stmmac_ops dwxgmac210_ops = {
 	.core_init = dwxgmac2_core_init,
 	.set_mac = dwxgmac2_set_mac,
@@ -350,6 +362,7 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.pcs_get_adv_lp = NULL,
 	.debug = NULL,
 	.set_filter = dwxgmac2_set_filter,
+	.set_mac_loopback = dwxgmac2_set_mac_loopback,
 };
 
 int dwxgmac2_setup(struct stmmac_priv *priv)
@@ -368,11 +381,13 @@ int dwxgmac2_setup(struct stmmac_priv *priv)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
 	mac->link.duplex = 0;
-	mac->link.speed10 = 0;
-	mac->link.speed100 = 0;
-	mac->link.speed1000 = XGMAC_CONFIG_SS_1000;
-	mac->link.speed2500 = XGMAC_CONFIG_SS_2500;
-	mac->link.speed10000 = XGMAC_CONFIG_SS_10000;
+	mac->link.speed10 = XGMAC_CONFIG_SS_10_MII;
+	mac->link.speed100 = XGMAC_CONFIG_SS_100_MII;
+	mac->link.speed1000 = XGMAC_CONFIG_SS_1000_GMII;
+	mac->link.speed2500 = XGMAC_CONFIG_SS_2500_GMII;
+	mac->link.xgmii.speed2500 = XGMAC_CONFIG_SS_2500;
+	mac->link.xgmii.speed5000 = XGMAC_CONFIG_SS_5000;
+	mac->link.xgmii.speed10000 = XGMAC_CONFIG_SS_10000;
 	mac->link.speed_mask = XGMAC_CONFIG_SS_MASK;
 
 	mac->mii.addr = XGMAC_MDIO_ADDR;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index 1d858fdec997..c4c45402b8f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -123,7 +123,7 @@ static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc,
 }
 
 static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				  int mode, int end)
+				  int mode, int end, int bfsize)
 {
 	dwxgmac2_set_rx_owner(p, disable_rx_ic);
 }
@@ -242,8 +242,8 @@ static void dwxgmac2_get_addr(struct dma_desc *p, unsigned int *addr)
 
 static void dwxgmac2_set_addr(struct dma_desc *p, dma_addr_t addr)
 {
-	p->des0 = cpu_to_le32(addr);
-	p->des1 = 0;
+	p->des0 = cpu_to_le32(lower_32_bits(addr));
+	p->des1 = cpu_to_le32(upper_32_bits(addr));
 }
 
 static void dwxgmac2_clear(struct dma_desc *p)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index c5e25580a43f..a4f236e3593e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -27,7 +27,7 @@ static void dwxgmac2_dma_init(void __iomem *ioaddr,
 	if (dma_cfg->aal)
 		value |= XGMAC_AAL;
 
-	writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE);
+	writel(value | XGMAC_EAME, ioaddr + XGMAC_DMA_SYSBUS_MODE);
 }
 
 static void dwxgmac2_dma_init_chan(void __iomem *ioaddr,
@@ -44,7 +44,7 @@ static void dwxgmac2_dma_init_chan(void __iomem *ioaddr,
 
 static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
 				      struct stmmac_dma_cfg *dma_cfg,
-				      u32 dma_rx_phy, u32 chan)
+				      dma_addr_t phy, u32 chan)
 {
 	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
 	u32 value;
@@ -54,12 +54,13 @@ static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
 	value |= (rxpbl << XGMAC_RxPBL_SHIFT) & XGMAC_RxPBL;
 	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
 
-	writel(dma_rx_phy, ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
+	writel(upper_32_bits(phy), ioaddr + XGMAC_DMA_CH_RxDESC_HADDR(chan));
+	writel(lower_32_bits(phy), ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
 }
 
 static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
 				      struct stmmac_dma_cfg *dma_cfg,
-				      u32 dma_tx_phy, u32 chan)
+				      dma_addr_t phy, u32 chan)
 {
 	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
 	u32 value;
@@ -70,7 +71,8 @@ static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
 	value |= XGMAC_OSP;
 	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
 
-	writel(dma_tx_phy, ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
+	writel(upper_32_bits(phy), ioaddr + XGMAC_DMA_CH_TxDESC_HADDR(chan));
+	writel(lower_32_bits(phy), ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
 }
 
 static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
@@ -91,11 +93,11 @@ static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 	value |= (axi->axi_rd_osr_lmt << XGMAC_RD_OSR_LMT_SHIFT) &
 		XGMAC_RD_OSR_LMT;
 
+	if (!axi->axi_fb)
+		value |= XGMAC_UNDEF;
+
 	value &= ~XGMAC_BLEN;
 	for (i = 0; i < AXI_BLEN; i++) {
-		if (axi->axi_blen[i])
-			value &= ~XGMAC_UNDEF;
-
 		switch (axi->axi_blen[i]) {
 		case 256:
 			value |= XGMAC_BLEN256;
@@ -122,6 +124,8 @@ static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 	}
 
 	writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE);
+	writel(XGMAC_TDPS, ioaddr + XGMAC_TX_EDMA_CTRL);
+	writel(XGMAC_RDPS, ioaddr + XGMAC_RX_EDMA_CTRL);
 }
 
 static void dwxgmac2_dma_rx_mode(void __iomem *ioaddr, int mode,
@@ -147,6 +151,52 @@ static void dwxgmac2_dma_rx_mode(void __iomem *ioaddr, int mode,
 	value &= ~XGMAC_RQS;
 	value |= (rqs << XGMAC_RQS_SHIFT) & XGMAC_RQS;
 
+	if ((fifosz >= 4096) && (qmode != MTL_QUEUE_AVB)) {
+		u32 flow = readl(ioaddr + XGMAC_MTL_RXQ_FLOW_CONTROL(channel));
+		unsigned int rfd, rfa;
+
+		value |= XGMAC_EHFC;
+
+		/* Set Threshold for Activating Flow Control to min 2 frames,
+		 * i.e. 1500 * 2 = 3000 bytes.
+		 *
+		 * Set Threshold for Deactivating Flow Control to min 1 frame,
+		 * i.e. 1500 bytes.
+		 */
+		switch (fifosz) {
+		case 4096:
+			/* This violates the above formula because of FIFO size
+			 * limit therefore overflow may occur in spite of this.
+			 */
+			rfd = 0x03; /* Full-2.5K */
+			rfa = 0x01; /* Full-1.5K */
+			break;
+
+		case 8192:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x0a; /* Full-6K */
+			break;
+
+		case 16384:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x12; /* Full-10K */
+			break;
+
+		default:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x1e; /* Full-16K */
+			break;
+		}
+
+		flow &= ~XGMAC_RFD;
+		flow |= rfd << XGMAC_RFD_SHIFT;
+
+		flow &= ~XGMAC_RFA;
+		flow |= rfa << XGMAC_RFA_SHIFT;
+
+		writel(flow, ioaddr + XGMAC_MTL_RXQ_FLOW_CONTROL(channel));
+	}
+
 	writel(value, ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
 
 	/* Enable MTL RX overflow */
@@ -253,10 +303,6 @@ static void dwxgmac2_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
 	value &= ~XGMAC_RXST;
 	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
-
-	value = readl(ioaddr + XGMAC_RX_CONFIG);
-	value &= ~XGMAC_CONFIG_RE;
-	writel(value, ioaddr + XGMAC_RX_CONFIG);
 }
 
 static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
@@ -283,12 +329,10 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
 		x->normal_irq_n++;
 
 		if (likely(intr_status & XGMAC_RI)) {
-			if (likely(intr_en & XGMAC_RIE)) {
-				x->rx_normal_irq_n++;
-				ret |= handle_rx;
-			}
+			x->rx_normal_irq_n++;
+			ret |= handle_rx;
 		}
-		if (likely(intr_status & XGMAC_TI)) {
+		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
 			x->tx_normal_irq_n++;
 			ret |= handle_tx;
 		}
@@ -319,6 +363,23 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 	/* MAC HW feature 1 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1);
 	dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18;
+
+	dma_cap->addr64 = (hw_cap & XGMAC_HWFEAT_ADDR64) >> 14;
+	switch (dma_cap->addr64) {
+	case 0:
+		dma_cap->addr64 = 32;
+		break;
+	case 1:
+		dma_cap->addr64 = 40;
+		break;
+	case 2:
+		dma_cap->addr64 = 48;
+		break;
+	default:
+		dma_cap->addr64 = 32;
+		break;
+	}
+
 	dma_cap->tx_fifo_size =
 		128 << ((hw_cap & XGMAC_HWFEAT_TXFIFOSIZE) >> 6);
 	dma_cap->rx_fifo_size =
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 5ef91a790f9d..d02cec296f51 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -1,19 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This contains the functions to handle the enhanced descriptors.
 
   Copyright (C) 2007-2014  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -201,6 +191,11 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 	if (unlikely(rdes0 & RDES0_OWN))
 		return dma_own;
 
+	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
+		stats->rx_length_errors++;
+		return discard_frame;
+	}
+
 	if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) {
 		if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR)) {
 			x->rx_desc++;
@@ -231,9 +226,10 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 	 * It doesn't match with the information reported into the databook.
 	 * At any rate, we need to understand if the CSUM hw computation is ok
 	 * and report this info to the upper layers. */
-	ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
-				 !!(rdes0 & RDES0_FRAME_TYPE),
-				 !!(rdes0 & ERDES0_RX_MAC_ADDR));
+	if (likely(ret == good_frame))
+		ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
+					 !!(rdes0 & RDES0_FRAME_TYPE),
+					 !!(rdes0 & ERDES0_RX_MAC_ADDR));
 
 	if (unlikely(rdes0 & RDES0_DRIBBLING))
 		x->dribbling_bit++;
@@ -259,15 +255,19 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 }
 
 static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				  int mode, int end)
+				  int mode, int end, int bfsize)
 {
+	int bfsize1;
+
 	p->des0 |= cpu_to_le32(RDES0_OWN);
-	p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK);
+
+	bfsize1 = min(bfsize, BUF_SIZE_8KiB);
+	p->des1 |= cpu_to_le32(bfsize1 & ERDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ehn_desc_rx_set_on_chain(p);
 	else
-		ehn_desc_rx_set_on_ring(p, end);
+		ehn_desc_rx_set_on_ring(p, end, bfsize);
 
 	if (disable_rx_ic)
 		p->des1 |= cpu_to_le32(ERDES1_DISABLE_IC);
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 81b966a8261b..6c61b753b55e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -81,6 +81,7 @@ static const struct stmmac_hwif_entry {
 	const void *hwtimestamp;
 	const void *mode;
 	const void *tc;
+	const void *mmc;
 	int (*setup)(struct stmmac_priv *priv);
 	int (*quirks)(struct stmmac_priv *priv);
 } stmmac_hw[] = {
@@ -100,6 +101,7 @@ static const struct stmmac_hwif_entry {
 		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
 		.tc = NULL,
+		.mmc = &dwmac_mmc_ops,
 		.setup = dwmac100_setup,
 		.quirks = stmmac_dwmac1_quirks,
 	}, {
@@ -117,6 +119,7 @@ static const struct stmmac_hwif_entry {
 		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
 		.tc = NULL,
+		.mmc = &dwmac_mmc_ops,
 		.setup = dwmac1000_setup,
 		.quirks = stmmac_dwmac1_quirks,
 	}, {
@@ -134,6 +137,7 @@ static const struct stmmac_hwif_entry {
 		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
 		.tc = &dwmac510_tc_ops,
+		.mmc = &dwmac_mmc_ops,
 		.setup = dwmac4_setup,
 		.quirks = stmmac_dwmac4_quirks,
 	}, {
@@ -151,6 +155,7 @@ static const struct stmmac_hwif_entry {
 		.hwtimestamp = &stmmac_ptp,
 		.mode = &dwmac4_ring_mode_ops,
 		.tc = &dwmac510_tc_ops,
+		.mmc = &dwmac_mmc_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
 	}, {
@@ -168,6 +173,7 @@ static const struct stmmac_hwif_entry {
 		.hwtimestamp = &stmmac_ptp,
 		.mode = &dwmac4_ring_mode_ops,
 		.tc = &dwmac510_tc_ops,
+		.mmc = &dwmac_mmc_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
 	}, {
@@ -185,6 +191,7 @@ static const struct stmmac_hwif_entry {
 		.hwtimestamp = &stmmac_ptp,
 		.mode = &dwmac4_ring_mode_ops,
 		.tc = &dwmac510_tc_ops,
+		.mmc = &dwmac_mmc_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
 	}, {
@@ -202,6 +209,7 @@ static const struct stmmac_hwif_entry {
 		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
 		.tc = &dwmac510_tc_ops,
+		.mmc = NULL,
 		.setup = dwxgmac2_setup,
 		.quirks = NULL,
 	},
@@ -267,6 +275,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 		mac->ptp = mac->ptp ? : entry->hwtimestamp;
 		mac->mode = mac->mode ? : entry->mode;
 		mac->tc = mac->tc ? : entry->tc;
+		mac->mmc = mac->mmc ? : entry->mmc;
 
 		priv->hw = mac;
 		priv->ptpaddr = priv->ioaddr + entry->regs.ptp_off;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 92b8944f26e3..278c0dbec9d9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -6,6 +6,7 @@
 #define __STMMAC_HWIF_H__
 
 #include <linux/netdevice.h>
+#include <linux/stmmac.h>
 
 #define stmmac_do_void_callback(__priv, __module, __cname,  __arg0, __args...) \
 ({ \
@@ -33,7 +34,7 @@ struct dma_extended_desc;
 struct stmmac_desc_ops {
 	/* DMA RX descriptor ring initialization */
 	void (*init_rx_desc)(struct dma_desc *p, int disable_rx_ic, int mode,
-			int end);
+			int end, int bfsize);
 	/* DMA TX descriptor ring initialization */
 	void (*init_tx_desc)(struct dma_desc *p, int mode, int end);
 	/* Invoked by the xmit function to prepare the tx descriptor */
@@ -149,10 +150,10 @@ struct stmmac_dma_ops {
 			  struct stmmac_dma_cfg *dma_cfg, u32 chan);
 	void (*init_rx_chan)(void __iomem *ioaddr,
 			     struct stmmac_dma_cfg *dma_cfg,
-			     u32 dma_rx_phy, u32 chan);
+			     dma_addr_t phy, u32 chan);
 	void (*init_tx_chan)(void __iomem *ioaddr,
 			     struct stmmac_dma_cfg *dma_cfg,
-			     u32 dma_tx_phy, u32 chan);
+			     dma_addr_t phy, u32 chan);
 	/* Configure the AXI Bus Mode Register */
 	void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
 	/* Dump DMA registers */
@@ -324,6 +325,8 @@ struct stmmac_ops {
 	int (*flex_pps_config)(void __iomem *ioaddr, int index,
 			       struct stmmac_pps_cfg *cfg, bool enable,
 			       u32 sub_second_inc, u32 systime_flags);
+	/* Loopback for selftests */
+	void (*set_mac_loopback)(void __iomem *ioaddr, bool enable);
 };
 
 #define stmmac_core_init(__priv, __args...) \
@@ -392,6 +395,8 @@ struct stmmac_ops {
 	stmmac_do_callback(__priv, mac, rxp_config, __args)
 #define stmmac_flex_pps_config(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, flex_pps_config, __args)
+#define stmmac_set_mac_loopback(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mac, set_mac_loopback, __args)
 
 /* PTP and HW Timer helpers */
 struct stmmac_hwtimestamp {
@@ -464,6 +469,21 @@ struct stmmac_tc_ops {
 #define stmmac_tc_setup_cbs(__priv, __args...) \
 	stmmac_do_callback(__priv, tc, setup_cbs, __args)
 
+struct stmmac_counters;
+
+struct stmmac_mmc_ops {
+	void (*ctrl)(void __iomem *ioaddr, unsigned int mode);
+	void (*intr_all_mask)(void __iomem *ioaddr);
+	void (*read)(void __iomem *ioaddr, struct stmmac_counters *mmc);
+};
+
+#define stmmac_mmc_ctrl(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mmc, ctrl, __args)
+#define stmmac_mmc_intr_all_mask(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mmc, intr_all_mask, __args)
+#define stmmac_mmc_read(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mmc, read, __args)
+
 struct stmmac_regs_off {
 	u32 ptp_off;
 	u32 mmc_off;
@@ -482,6 +502,7 @@ extern const struct stmmac_tc_ops dwmac510_tc_ops;
 extern const struct stmmac_ops dwxgmac210_ops;
 extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
 extern const struct stmmac_desc_ops dwxgmac210_desc_ops;
+extern const struct stmmac_mmc_ops dwmac_mmc_ops;
 
 #define GMAC_VERSION		0x00000020	/* GMAC CORE Version */
 #define GMAC4_VERSION		0x00000110	/* GMAC4+ CORE Version */
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h
index c037326331f5..3587ceb9faf5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc.h
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h
@@ -1,19 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   MMC Header file
 
   Copyright (C) 2011  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -128,8 +118,4 @@ struct stmmac_counters {
 	unsigned int mmc_rx_icmp_err_octets;
 };
 
-void dwmac_mmc_ctrl(void __iomem *ioaddr, unsigned int mode);
-void dwmac_mmc_intr_all_mask(void __iomem *ioaddr);
-void dwmac_mmc_read(void __iomem *ioaddr, struct stmmac_counters *mmc);
-
 #endif /* __MMC_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index e9b04c28980f..a471db6d7b11 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -1,25 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   DWMAC Management Counters
 
   Copyright (C) 2011  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
 #include <linux/kernel.h>
 #include <linux/io.h>
+#include "hwif.h"
 #include "mmc.h"
 
 /* MAC Management Counters register offset */
@@ -128,7 +119,7 @@
 #define MMC_RX_ICMP_GD_OCTETS		0x180
 #define MMC_RX_ICMP_ERR_OCTETS		0x184
 
-void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode)
+static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode)
 {
 	u32 value = readl(mmcaddr + MMC_CNTRL);
 
@@ -141,7 +132,7 @@ void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode)
 }
 
 /* To mask all all interrupts.*/
-void dwmac_mmc_intr_all_mask(void __iomem *mmcaddr)
+static void dwmac_mmc_intr_all_mask(void __iomem *mmcaddr)
 {
 	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_RX_INTR_MASK);
 	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_TX_INTR_MASK);
@@ -153,7 +144,7 @@ void dwmac_mmc_intr_all_mask(void __iomem *mmcaddr)
  * counter after a read. So all the field of the mmc struct
  * have to be incremented.
  */
-void dwmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
+static void dwmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
 {
 	mmc->mmc_tx_octetcount_gb += readl(mmcaddr + MMC_TX_OCTETCOUNT_GB);
 	mmc->mmc_tx_framecount_gb += readl(mmcaddr + MMC_TX_FRAMECOUNT_GB);
@@ -266,3 +257,9 @@ void dwmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
 	mmc->mmc_rx_icmp_gd_octets += readl(mmcaddr + MMC_RX_ICMP_GD_OCTETS);
 	mmc->mmc_rx_icmp_err_octets += readl(mmcaddr + MMC_RX_ICMP_ERR_OCTETS);
 }
+
+const struct stmmac_mmc_ops dwmac_mmc_ops = {
+	.ctrl = dwmac_mmc_ctrl,
+	.intr_all_mask = dwmac_mmc_intr_all_mask,
+	.read = dwmac_mmc_read,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index de65bb29feba..f083360e4ba6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -1,19 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This contains the functions to handle the normal descriptors.
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -91,8 +81,6 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 		return dma_own;
 
 	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
-		pr_warn("%s: Oversized frame spanned multiple buffers\n",
-			__func__);
 		stats->rx_length_errors++;
 		return discard_frame;
 	}
@@ -135,15 +123,19 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 }
 
 static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
-			       int end)
+			       int end, int bfsize)
 {
+	int bfsize1;
+
 	p->des0 |= cpu_to_le32(RDES0_OWN);
-	p->des1 |= cpu_to_le32((BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK);
+
+	bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1);
+	p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ndesc_rx_set_on_chain(p, end);
 	else
-		ndesc_rx_set_on_ring(p, end);
+		ndesc_rx_set_on_ring(p, end, bfsize);
 
 	if (disable_rx_ic)
 		p->des1 |= cpu_to_le32(RDES1_DISABLE_IC);
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index d8c5bc412219..14bd5e7b9875 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   Specialised functions for managing Ring mode
 
@@ -7,17 +8,6 @@
   descriptors in case of the DMA is configured to work in chained or
   in ring mode.
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -59,7 +49,7 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum,
-				STMMAC_RING_MODE, 1, false, skb->len);
+				STMMAC_RING_MODE, 0, false, skb->len);
 		tx_q->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
@@ -79,7 +69,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 0, len, csum,
-				STMMAC_RING_MODE, 1, true, skb->len);
+				STMMAC_RING_MODE, 1, !skb_is_nonlinear(skb),
+				skb->len);
 	} else {
 		des2 = dma_map_single(priv->device, skb->data,
 				      nopaged_len, DMA_TO_DEVICE);
@@ -91,7 +82,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 1, nopaged_len, csum,
-				STMMAC_RING_MODE, 1, true, skb->len);
+				STMMAC_RING_MODE, 0, !skb_is_nonlinear(skb),
+				skb->len);
 	}
 
 	tx_q->cur_tx = entry;
@@ -111,10 +103,11 @@ static unsigned int is_jumbo_frm(int len, int enh_desc)
 
 static void refill_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+	struct stmmac_rx_queue *rx_q = priv_ptr;
+	struct stmmac_priv *priv = rx_q->priv_data;
 
 	/* Fill DES3 in case of RING mode */
-	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 63e1064b27a2..5cd966c154f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -1,17 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -24,11 +14,13 @@
 
 #include <linux/clk.h>
 #include <linux/stmmac.h>
-#include <linux/phy.h>
+#include <linux/phylink.h>
 #include <linux/pci.h>
 #include "common.h"
 #include <linux/ptp_clock_kernel.h>
+#include <linux/net_tstamp.h>
 #include <linux/reset.h>
+#include <net/page_pool.h>
 
 struct stmmac_resources {
 	void __iomem *addr;
@@ -63,13 +55,19 @@ struct stmmac_tx_queue {
 	u32 mss;
 };
 
+struct stmmac_rx_buffer {
+	struct page *page;
+	dma_addr_t addr;
+};
+
 struct stmmac_rx_queue {
+	u32 rx_count_frames;
 	u32 queue_index;
+	struct page_pool *page_pool;
+	struct stmmac_rx_buffer *buf_pool;
 	struct stmmac_priv *priv_data;
 	struct dma_extended_desc *dma_erx;
 	struct dma_desc *dma_rx ____cacheline_aligned_in_smp;
-	struct sk_buff **rx_skbuff;
-	dma_addr_t *rx_skbuff_dma;
 	unsigned int cur_rx;
 	unsigned int dirty_rx;
 	u32 rx_zeroc_thresh;
@@ -78,11 +76,10 @@ struct stmmac_rx_queue {
 };
 
 struct stmmac_channel {
-	struct napi_struct napi ____cacheline_aligned_in_smp;
+	struct napi_struct rx_napi ____cacheline_aligned_in_smp;
+	struct napi_struct tx_napi ____cacheline_aligned_in_smp;
 	struct stmmac_priv *priv_data;
 	u32 index;
-	int has_rx;
-	int has_tx;
 };
 
 struct stmmac_tc_entry {
@@ -120,6 +117,7 @@ struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
+	u32 rx_coal_frames;
 
 	int tx_coalesce;
 	int hwts_tx_en;
@@ -147,14 +145,15 @@ struct stmmac_priv {
 	/* Generic channel for NAPI */
 	struct stmmac_channel channel[STMMAC_CH_MAX];
 
-	bool oldlink;
 	int speed;
-	int oldduplex;
 	unsigned int flow_ctrl;
 	unsigned int pause;
 	struct mii_bus *mii;
 	int mii_irq[PHY_MAX_ADDR];
 
+	struct phylink_config phylink_config;
+	struct phylink *phylink;
+
 	struct stmmac_extra_stats xstats ____cacheline_aligned_in_smp;
 	struct stmmac_safety_stats sstats;
 	struct plat_stmmacenet_data *plat;
@@ -174,6 +173,7 @@ struct stmmac_priv {
 	unsigned int mode;
 	unsigned int chain_mode;
 	int extend_desc;
+	struct hwtstamp_config tstamp_config;
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_clock_ops;
 	unsigned int default_addend;
@@ -228,4 +228,26 @@ int stmmac_dvr_probe(struct device *device,
 void stmmac_disable_eee_mode(struct stmmac_priv *priv);
 bool stmmac_eee_init(struct stmmac_priv *priv);
 
+#if IS_ENABLED(CONFIG_STMMAC_SELFTESTS)
+void stmmac_selftest_run(struct net_device *dev,
+			 struct ethtool_test *etest, u64 *buf);
+void stmmac_selftest_get_strings(struct stmmac_priv *priv, u8 *data);
+int stmmac_selftest_get_count(struct stmmac_priv *priv);
+#else
+static inline void stmmac_selftest_run(struct net_device *dev,
+				       struct ethtool_test *etest, u64 *buf)
+{
+	/* Not enabled */
+}
+static inline void stmmac_selftest_get_strings(struct stmmac_priv *priv,
+					       u8 *data)
+{
+	/* Not enabled */
+}
+static inline int stmmac_selftest_get_count(struct stmmac_priv *priv)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_STMMAC_SELFTESTS */
+
 #endif /* __STMMAC_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 5d85742a2be0..6efb66820d4c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -1,19 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   STMMAC Ethtool support
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -22,7 +12,7 @@
 #include <linux/ethtool.h>
 #include <linux/interrupt.h>
 #include <linux/mii.h>
-#include <linux/phy.h>
+#include <linux/phylink.h>
 #include <linux/net_tstamp.h>
 #include <asm/io.h>
 
@@ -274,7 +264,6 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev,
 					     struct ethtool_link_ksettings *cmd)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	struct phy_device *phy = dev->phydev;
 
 	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
 	    priv->hw->pcs & STMMAC_PCS_SGMII) {
@@ -353,18 +342,7 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev,
 		return 0;
 	}
 
-	if (phy == NULL) {
-		pr_err("%s: %s: PHY is not registered\n",
-		       __func__, dev->name);
-		return -ENODEV;
-	}
-	if (!netif_running(dev)) {
-		pr_err("%s: interface is disabled: we cannot track "
-		"link speed / duplex setting\n", dev->name);
-		return -EBUSY;
-	}
-	phy_ethtool_ksettings_get(phy, cmd);
-	return 0;
+	return phylink_ethtool_ksettings_get(priv->phylink, cmd);
 }
 
 static int
@@ -372,8 +350,6 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev,
 				  const struct ethtool_link_ksettings *cmd)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	struct phy_device *phy = dev->phydev;
-	int rc;
 
 	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
 	    priv->hw->pcs & STMMAC_PCS_SGMII) {
@@ -397,9 +373,7 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev,
 		return 0;
 	}
 
-	rc = phy_ethtool_ksettings_set(phy, cmd);
-
-	return rc;
+	return phylink_ethtool_ksettings_set(priv->phylink, cmd);
 }
 
 static u32 stmmac_ethtool_getmsglevel(struct net_device *dev)
@@ -443,6 +417,13 @@ static void stmmac_ethtool_gregs(struct net_device *dev,
 	       NUM_DWMAC1000_DMA_REGS * 4);
 }
 
+static int stmmac_nway_reset(struct net_device *dev)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+
+	return phylink_ethtool_nway_reset(priv->phylink);
+}
+
 static void
 stmmac_get_pauseparam(struct net_device *netdev,
 		      struct ethtool_pauseparam *pause)
@@ -450,28 +431,13 @@ stmmac_get_pauseparam(struct net_device *netdev,
 	struct stmmac_priv *priv = netdev_priv(netdev);
 	struct rgmii_adv adv_lp;
 
-	pause->rx_pause = 0;
-	pause->tx_pause = 0;
-
 	if (priv->hw->pcs && !stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv_lp)) {
 		pause->autoneg = 1;
 		if (!adv_lp.pause)
 			return;
 	} else {
-		if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-				       netdev->phydev->supported) ||
-		    linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-				      netdev->phydev->supported))
-			return;
+		phylink_ethtool_get_pauseparam(priv->phylink, pause);
 	}
-
-	pause->autoneg = netdev->phydev->autoneg;
-
-	if (priv->flow_ctrl & FLOW_RX)
-		pause->rx_pause = 1;
-	if (priv->flow_ctrl & FLOW_TX)
-		pause->tx_pause = 1;
-
 }
 
 static int
@@ -479,39 +445,16 @@ stmmac_set_pauseparam(struct net_device *netdev,
 		      struct ethtool_pauseparam *pause)
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
-	u32 tx_cnt = priv->plat->tx_queues_to_use;
-	struct phy_device *phy = netdev->phydev;
-	int new_pause = FLOW_OFF;
 	struct rgmii_adv adv_lp;
 
 	if (priv->hw->pcs && !stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv_lp)) {
 		pause->autoneg = 1;
 		if (!adv_lp.pause)
 			return -EOPNOTSUPP;
+		return 0;
 	} else {
-		if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-				       phy->supported) ||
-		    linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-				      phy->supported))
-			return -EOPNOTSUPP;
+		return phylink_ethtool_set_pauseparam(priv->phylink, pause);
 	}
-
-	if (pause->rx_pause)
-		new_pause |= FLOW_RX;
-	if (pause->tx_pause)
-		new_pause |= FLOW_TX;
-
-	priv->flow_ctrl = new_pause;
-	phy->autoneg = pause->autoneg;
-
-	if (phy->autoneg) {
-		if (netif_running(netdev))
-			return phy_start_aneg(phy);
-	}
-
-	stmmac_flow_ctrl(priv, priv->hw, phy->duplex, priv->flow_ctrl,
-			priv->pause, tx_cnt);
-	return 0;
 }
 
 static void stmmac_get_ethtool_stats(struct net_device *dev,
@@ -537,7 +480,7 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 	if (ret) {
 		/* If supported, for new GMAC chips expose the MMC counters */
 		if (priv->dma_cap.rmon) {
-			dwmac_mmc_read(priv->mmcaddr, &priv->mmc);
+			stmmac_mmc_read(priv, priv->mmcaddr, &priv->mmc);
 
 			for (i = 0; i < STMMAC_MMC_STATS_LEN; i++) {
 				char *p;
@@ -549,7 +492,7 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
 			}
 		}
 		if (priv->eee_enabled) {
-			int val = phy_get_eee_err(dev->phydev);
+			int val = phylink_get_eee_err(priv->phylink);
 			if (val)
 				priv->xstats.phy_eee_wakeup_error_n = val;
 		}
@@ -589,6 +532,8 @@ static int stmmac_get_sset_count(struct net_device *netdev, int sset)
 		}
 
 		return len;
+	case ETH_SS_TEST:
+		return stmmac_selftest_get_count(priv);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -625,6 +570,9 @@ static void stmmac_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 			p += ETH_GSTRING_LEN;
 		}
 		break;
+	case ETH_SS_TEST:
+		stmmac_selftest_get_strings(priv, p);
+		break;
 	default:
 		WARN_ON(1);
 		break;
@@ -689,32 +637,34 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev,
 	edata->eee_active = priv->eee_active;
 	edata->tx_lpi_timer = priv->tx_lpi_timer;
 
-	return phy_ethtool_get_eee(dev->phydev, edata);
+	return phylink_ethtool_get_eee(priv->phylink, edata);
 }
 
 static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 				     struct ethtool_eee *edata)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	int ret;
 
-	priv->eee_enabled = edata->eee_enabled;
-
-	if (!priv->eee_enabled)
+	if (!edata->eee_enabled) {
 		stmmac_disable_eee_mode(priv);
-	else {
+	} else {
 		/* We are asking for enabling the EEE but it is safe
 		 * to verify all by invoking the eee_init function.
 		 * In case of failure it will return an error.
 		 */
-		priv->eee_enabled = stmmac_eee_init(priv);
-		if (!priv->eee_enabled)
+		edata->eee_enabled = stmmac_eee_init(priv);
+		if (!edata->eee_enabled)
 			return -EOPNOTSUPP;
-
-		/* Do not change tx_lpi_timer in case of failure */
-		priv->tx_lpi_timer = edata->tx_lpi_timer;
 	}
 
-	return phy_ethtool_set_eee(dev->phydev, edata);
+	ret = phylink_ethtool_set_eee(priv->phylink, edata);
+	if (ret)
+		return ret;
+
+	priv->eee_enabled = edata->eee_enabled;
+	priv->tx_lpi_timer = edata->tx_lpi_timer;
+	return 0;
 }
 
 static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)
@@ -751,8 +701,10 @@ static int stmmac_get_coalesce(struct net_device *dev,
 	ec->tx_coalesce_usecs = priv->tx_coal_timer;
 	ec->tx_max_coalesced_frames = priv->tx_coal_frames;
 
-	if (priv->use_riwt)
+	if (priv->use_riwt) {
+		ec->rx_max_coalesced_frames = priv->rx_coal_frames;
 		ec->rx_coalesce_usecs = stmmac_riwt2usec(priv->rx_riwt, priv);
+	}
 
 	return 0;
 }
@@ -765,7 +717,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 	unsigned int rx_riwt;
 
 	/* Check not supported parameters  */
-	if ((ec->rx_max_coalesced_frames) || (ec->rx_coalesce_usecs_irq) ||
+	if ((ec->rx_coalesce_usecs_irq) ||
 	    (ec->rx_max_coalesced_frames_irq) || (ec->tx_coalesce_usecs_irq) ||
 	    (ec->use_adaptive_rx_coalesce) || (ec->use_adaptive_tx_coalesce) ||
 	    (ec->pkt_rate_low) || (ec->rx_coalesce_usecs_low) ||
@@ -799,6 +751,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 	/* Only copy relevant parameters, ignore all others. */
 	priv->tx_coal_frames = ec->tx_max_coalesced_frames;
 	priv->tx_coal_timer = ec->tx_coalesce_usecs;
+	priv->rx_coal_frames = ec->rx_max_coalesced_frames;
 	priv->rx_riwt = rx_riwt;
 	stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
 
@@ -885,9 +838,10 @@ static const struct ethtool_ops stmmac_ethtool_ops = {
 	.get_regs = stmmac_ethtool_gregs,
 	.get_regs_len = stmmac_ethtool_get_regs_len,
 	.get_link = ethtool_op_get_link,
-	.nway_reset = phy_ethtool_nway_reset,
+	.nway_reset = stmmac_nway_reset,
 	.get_pauseparam = stmmac_get_pauseparam,
 	.set_pauseparam = stmmac_set_pauseparam,
+	.self_test = stmmac_selftest_run,
 	.get_ethtool_stats = stmmac_get_ethtool_stats,
 	.get_strings = stmmac_get_strings,
 	.get_wol = stmmac_get_wol,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index 8d9cc2157afd..020159622559 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -1,19 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   Copyright (C) 2013  Vayavya Labs Pvt Ltd
 
   This implements all the API for managing HW timestamp & PTP.
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Rayagond Kokatanur <rayagond@vayavyalabs.com>
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
@@ -122,7 +112,7 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec,
 		 * programmed with (2^32 – <new_sec_value>)
 		 */
 		if (gmac4)
-			sec = (100000000ULL - sec);
+			sec = -sec;
 
 		value = readl(ioaddr + PTP_TCR);
 		if (value & PTP_TCR_TSCTRLSSR)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 685d20472358..c7c9e5f162e6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1,20 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This is the driver for the ST MAC 10/100/1000 on-chip Ethernet controllers.
   ST Ethernet IPs are built around a Synopsys IP Core.
 
 	Copyright(C) 2007-2011 STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 
@@ -45,6 +35,7 @@
 #include <linux/seq_file.h>
 #endif /* CONFIG_DEBUG_FS */
 #include <linux/net_tstamp.h>
+#include <linux/phylink.h>
 #include <net/pkt_cls.h>
 #include "stmmac_ptp.h"
 #include "stmmac.h"
@@ -74,7 +65,7 @@ MODULE_PARM_DESC(phyaddr, "Physical device address");
 #define STMMAC_TX_THRESH	(DMA_TX_SIZE / 4)
 #define STMMAC_RX_THRESH	(DMA_RX_SIZE / 4)
 
-static int flow_ctrl = FLOW_OFF;
+static int flow_ctrl = FLOW_AUTO;
 module_param(flow_ctrl, int, 0644);
 MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off]");
 
@@ -155,7 +146,10 @@ static void stmmac_disable_all_queues(struct stmmac_priv *priv)
 	for (queue = 0; queue < maxq; queue++) {
 		struct stmmac_channel *ch = &priv->channel[queue];
 
-		napi_disable(&ch->napi);
+		if (queue < rx_queues_cnt)
+			napi_disable(&ch->rx_napi);
+		if (queue < tx_queues_cnt)
+			napi_disable(&ch->tx_napi);
 	}
 }
 
@@ -173,7 +167,10 @@ static void stmmac_enable_all_queues(struct stmmac_priv *priv)
 	for (queue = 0; queue < maxq; queue++) {
 		struct stmmac_channel *ch = &priv->channel[queue];
 
-		napi_enable(&ch->napi);
+		if (queue < rx_queues_cnt)
+			napi_enable(&ch->rx_napi);
+		if (queue < tx_queues_cnt)
+			napi_enable(&ch->tx_napi);
 	}
 }
 
@@ -322,21 +319,6 @@ static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue)
 }
 
 /**
- * stmmac_hw_fix_mac_speed - callback for speed selection
- * @priv: driver private structure
- * Description: on some platforms (e.g. ST), some HW system configuration
- * registers have to be set according to the link speed negotiated.
- */
-static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv)
-{
-	struct net_device *ndev = priv->dev;
-	struct phy_device *phydev = ndev->phydev;
-
-	if (likely(priv->plat->fix_mac_speed))
-		priv->plat->fix_mac_speed(priv->plat->bsp_priv, phydev->speed);
-}
-
-/**
  * stmmac_enable_eee_mode - check and enter in LPI mode
  * @priv: driver private structure
  * Description: this function is to verify and enter in LPI mode in case of
@@ -399,14 +381,7 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t)
  */
 bool stmmac_eee_init(struct stmmac_priv *priv)
 {
-	struct net_device *ndev = priv->dev;
-	int interface = priv->plat->interface;
-	bool ret = false;
-
-	if ((interface != PHY_INTERFACE_MODE_MII) &&
-	    (interface != PHY_INTERFACE_MODE_GMII) &&
-	    !phy_interface_mode_is_rgmii(interface))
-		goto out;
+	int tx_lpi_timer = priv->tx_lpi_timer;
 
 	/* Using PCS we cannot dial with the phy registers at this stage
 	 * so we do not support extra feature like EEE.
@@ -414,52 +389,35 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
 	if ((priv->hw->pcs == STMMAC_PCS_RGMII) ||
 	    (priv->hw->pcs == STMMAC_PCS_TBI) ||
 	    (priv->hw->pcs == STMMAC_PCS_RTBI))
-		goto out;
-
-	/* MAC core supports the EEE feature. */
-	if (priv->dma_cap.eee) {
-		int tx_lpi_timer = priv->tx_lpi_timer;
-
-		/* Check if the PHY supports EEE */
-		if (phy_init_eee(ndev->phydev, 1)) {
-			/* To manage at run-time if the EEE cannot be supported
-			 * anymore (for example because the lp caps have been
-			 * changed).
-			 * In that case the driver disable own timers.
-			 */
-			mutex_lock(&priv->lock);
-			if (priv->eee_active) {
-				netdev_dbg(priv->dev, "disable EEE\n");
-				del_timer_sync(&priv->eee_ctrl_timer);
-				stmmac_set_eee_timer(priv, priv->hw, 0,
-						tx_lpi_timer);
-			}
-			priv->eee_active = 0;
-			mutex_unlock(&priv->lock);
-			goto out;
-		}
-		/* Activate the EEE and start timers */
-		mutex_lock(&priv->lock);
-		if (!priv->eee_active) {
-			priv->eee_active = 1;
-			timer_setup(&priv->eee_ctrl_timer,
-				    stmmac_eee_ctrl_timer, 0);
-			mod_timer(&priv->eee_ctrl_timer,
-				  STMMAC_LPI_T(eee_timer));
-
-			stmmac_set_eee_timer(priv, priv->hw,
-					STMMAC_DEFAULT_LIT_LS, tx_lpi_timer);
-		}
-		/* Set HW EEE according to the speed */
-		stmmac_set_eee_pls(priv, priv->hw, ndev->phydev->link);
+		return false;
 
-		ret = true;
+	/* Check if MAC core supports the EEE feature. */
+	if (!priv->dma_cap.eee)
+		return false;
+
+	mutex_lock(&priv->lock);
+
+	/* Check if it needs to be deactivated */
+	if (!priv->eee_active) {
+		if (priv->eee_enabled) {
+			netdev_dbg(priv->dev, "disable EEE\n");
+			del_timer_sync(&priv->eee_ctrl_timer);
+			stmmac_set_eee_timer(priv, priv->hw, 0, tx_lpi_timer);
+		}
 		mutex_unlock(&priv->lock);
+		return false;
+	}
 
-		netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
+	if (priv->eee_active && !priv->eee_enabled) {
+		timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0);
+		mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
+		stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
+				     tx_lpi_timer);
 	}
-out:
-	return ret;
+
+	mutex_unlock(&priv->lock);
+	netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
+	return true;
 }
 
 /* stmmac_get_tx_hwtstamp - get HW TX timestamps
@@ -474,7 +432,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
 				   struct dma_desc *p, struct sk_buff *skb)
 {
 	struct skb_shared_hwtstamps shhwtstamp;
-	u64 ns;
+	u64 ns = 0;
 
 	if (!priv->hwts_tx_en)
 		return;
@@ -513,7 +471,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 {
 	struct skb_shared_hwtstamps *shhwtstamp = NULL;
 	struct dma_desc *desc = p;
-	u64 ns;
+	u64 ns = 0;
 
 	if (!priv->hwts_rx_en)
 		return;
@@ -534,7 +492,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 }
 
 /**
- *  stmmac_hwtstamp_ioctl - control hardware timestamping.
+ *  stmmac_hwtstamp_set - control hardware timestamping.
  *  @dev: device pointer.
  *  @ifr: An IOCTL specific structure, that can contain a pointer to
  *  a proprietary structure used to pass information to the driver.
@@ -544,7 +502,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
  *  Return Value:
  *  0 on success and an appropriate -ve integer on failure.
  */
-static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config config;
@@ -558,8 +516,8 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	u32 snap_type_sel = 0;
 	u32 ts_master_en = 0;
 	u32 ts_event_en = 0;
+	u32 sec_inc = 0;
 	u32 value = 0;
-	u32 sec_inc;
 	bool xmac;
 
 	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
@@ -573,7 +531,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	}
 
 	if (copy_from_user(&config, ifr->ifr_data,
-			   sizeof(struct hwtstamp_config)))
+			   sizeof(config)))
 		return -EFAULT;
 
 	netdev_dbg(priv->dev, "%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n",
@@ -597,12 +555,13 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 		case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 			/* PTP v1, UDP, any kind of event packet */
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
-			/* take time stamp for all event messages */
-			if (xmac)
-				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
-			else
-				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-
+			/* 'xmac' hardware can support Sync, Pdelay_Req and
+			 * Pdelay_resp by setting bit14 and bits17/16 to 01
+			 * This leaves Delay_Req timestamps out.
+			 * Enable all events *and* general purpose message
+			 * timestamping
+			 */
+			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			break;
@@ -633,10 +592,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
-			if (xmac)
-				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
-			else
-				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
+			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
@@ -669,12 +625,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			/* PTP v2/802.AS1 any layer, any kind of event packet */
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
-			/* take time stamp for all event messages */
-			if (xmac)
-				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
-			else
-				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-
+			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
@@ -765,8 +716,31 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 				(u32)now.tv_sec, now.tv_nsec);
 	}
 
+	memcpy(&priv->tstamp_config, &config, sizeof(config));
+
 	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(struct hwtstamp_config)) ? -EFAULT : 0;
+			    sizeof(config)) ? -EFAULT : 0;
+}
+
+/**
+ *  stmmac_hwtstamp_get - read hardware timestamping.
+ *  @dev: device pointer.
+ *  @ifr: An IOCTL specific structure, that can contain a pointer to
+ *  a proprietary structure used to pass information to the driver.
+ *  Description:
+ *  This function obtain the current hardware timestamping settings
+    as requested.
+ */
+static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	struct hwtstamp_config *config = &priv->tstamp_config;
+
+	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
+		return -EOPNOTSUPP;
+
+	return copy_to_user(ifr->ifr_data, config,
+			    sizeof(*config)) ? -EFAULT : 0;
 }
 
 /**
@@ -826,97 +800,171 @@ static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
 			priv->pause, tx_cnt);
 }
 
-/**
- * stmmac_adjust_link - adjusts the link parameters
- * @dev: net device structure
- * Description: this is the helper called by the physical abstraction layer
- * drivers to communicate the phy link status. According the speed and duplex
- * this driver can invoke registered glue-logic as well.
- * It also invoke the eee initialization because it could happen when switch
- * on different networks (that are eee capable).
- */
-static void stmmac_adjust_link(struct net_device *dev)
+static void stmmac_validate(struct phylink_config *config,
+			    unsigned long *supported,
+			    struct phylink_link_state *state)
 {
-	struct stmmac_priv *priv = netdev_priv(dev);
-	struct phy_device *phydev = dev->phydev;
-	bool new_state = false;
-
-	if (!phydev)
-		return;
+	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mac_supported) = { 0, };
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+	int tx_cnt = priv->plat->tx_queues_to_use;
+	int max_speed = priv->plat->max_speed;
 
-	mutex_lock(&priv->lock);
+	phylink_set(mac_supported, 10baseT_Half);
+	phylink_set(mac_supported, 10baseT_Full);
+	phylink_set(mac_supported, 100baseT_Half);
+	phylink_set(mac_supported, 100baseT_Full);
+
+	phylink_set(mac_supported, Autoneg);
+	phylink_set(mac_supported, Pause);
+	phylink_set(mac_supported, Asym_Pause);
+	phylink_set_port_modes(mac_supported);
+
+	if (priv->plat->has_gmac ||
+	    priv->plat->has_gmac4 ||
+	    priv->plat->has_xgmac) {
+		phylink_set(mac_supported, 1000baseT_Half);
+		phylink_set(mac_supported, 1000baseT_Full);
+		phylink_set(mac_supported, 1000baseKX_Full);
+	}
+
+	/* Cut down 1G if asked to */
+	if ((max_speed > 0) && (max_speed < 1000)) {
+		phylink_set(mask, 1000baseT_Full);
+		phylink_set(mask, 1000baseX_Full);
+	} else if (priv->plat->has_xgmac) {
+		phylink_set(mac_supported, 2500baseT_Full);
+		phylink_set(mac_supported, 5000baseT_Full);
+		phylink_set(mac_supported, 10000baseSR_Full);
+		phylink_set(mac_supported, 10000baseLR_Full);
+		phylink_set(mac_supported, 10000baseER_Full);
+		phylink_set(mac_supported, 10000baseLRM_Full);
+		phylink_set(mac_supported, 10000baseT_Full);
+		phylink_set(mac_supported, 10000baseKX4_Full);
+		phylink_set(mac_supported, 10000baseKR_Full);
+	}
+
+	/* Half-Duplex can only work with single queue */
+	if (tx_cnt > 1) {
+		phylink_set(mask, 10baseT_Half);
+		phylink_set(mask, 100baseT_Half);
+		phylink_set(mask, 1000baseT_Half);
+	}
+
+	bitmap_and(supported, supported, mac_supported,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_andnot(supported, supported, mask,
+		      __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mac_supported,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_andnot(state->advertising, state->advertising, mask,
+		      __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
 
-	if (phydev->link) {
-		u32 ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
+static int stmmac_mac_link_state(struct phylink_config *config,
+				 struct phylink_link_state *state)
+{
+	return -EOPNOTSUPP;
+}
 
-		/* Now we make sure that we can be in full duplex mode.
-		 * If not, we operate in half-duplex mode. */
-		if (phydev->duplex != priv->oldduplex) {
-			new_state = true;
-			if (!phydev->duplex)
-				ctrl &= ~priv->hw->link.duplex;
-			else
-				ctrl |= priv->hw->link.duplex;
-			priv->oldduplex = phydev->duplex;
-		}
-		/* Flow Control operation */
-		if (phydev->pause)
-			stmmac_mac_flow_ctrl(priv, phydev->duplex);
-
-		if (phydev->speed != priv->speed) {
-			new_state = true;
-			ctrl &= ~priv->hw->link.speed_mask;
-			switch (phydev->speed) {
-			case SPEED_1000:
-				ctrl |= priv->hw->link.speed1000;
-				break;
-			case SPEED_100:
-				ctrl |= priv->hw->link.speed100;
-				break;
-			case SPEED_10:
-				ctrl |= priv->hw->link.speed10;
-				break;
-			default:
-				netif_warn(priv, link, priv->dev,
-					   "broken speed: %d\n", phydev->speed);
-				phydev->speed = SPEED_UNKNOWN;
-				break;
-			}
-			if (phydev->speed != SPEED_UNKNOWN)
-				stmmac_hw_fix_mac_speed(priv);
-			priv->speed = phydev->speed;
-		}
+static void stmmac_mac_config(struct phylink_config *config, unsigned int mode,
+			      const struct phylink_link_state *state)
+{
+	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+	u32 ctrl;
 
-		writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
+	ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
+	ctrl &= ~priv->hw->link.speed_mask;
 
-		if (!priv->oldlink) {
-			new_state = true;
-			priv->oldlink = true;
+	if (state->interface == PHY_INTERFACE_MODE_USXGMII) {
+		switch (state->speed) {
+		case SPEED_10000:
+			ctrl |= priv->hw->link.xgmii.speed10000;
+			break;
+		case SPEED_5000:
+			ctrl |= priv->hw->link.xgmii.speed5000;
+			break;
+		case SPEED_2500:
+			ctrl |= priv->hw->link.xgmii.speed2500;
+			break;
+		default:
+			return;
+		}
+	} else {
+		switch (state->speed) {
+		case SPEED_2500:
+			ctrl |= priv->hw->link.speed2500;
+			break;
+		case SPEED_1000:
+			ctrl |= priv->hw->link.speed1000;
+			break;
+		case SPEED_100:
+			ctrl |= priv->hw->link.speed100;
+			break;
+		case SPEED_10:
+			ctrl |= priv->hw->link.speed10;
+			break;
+		default:
+			return;
 		}
-	} else if (priv->oldlink) {
-		new_state = true;
-		priv->oldlink = false;
-		priv->speed = SPEED_UNKNOWN;
-		priv->oldduplex = DUPLEX_UNKNOWN;
 	}
 
-	if (new_state && netif_msg_link(priv))
-		phy_print_status(phydev);
+	priv->speed = state->speed;
 
-	mutex_unlock(&priv->lock);
+	if (priv->plat->fix_mac_speed)
+		priv->plat->fix_mac_speed(priv->plat->bsp_priv, state->speed);
 
-	if (phydev->is_pseudo_fixed_link)
-		/* Stop PHY layer to call the hook to adjust the link in case
-		 * of a switch is attached to the stmmac driver.
-		 */
-		phydev->irq = PHY_IGNORE_INTERRUPT;
+	if (!state->duplex)
+		ctrl &= ~priv->hw->link.duplex;
 	else
-		/* At this stage, init the EEE if supported.
-		 * Never called in case of fixed_link.
-		 */
+		ctrl |= priv->hw->link.duplex;
+
+	/* Flow Control operation */
+	if (state->pause)
+		stmmac_mac_flow_ctrl(priv, state->duplex);
+
+	writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
+}
+
+static void stmmac_mac_an_restart(struct phylink_config *config)
+{
+	/* Not Supported */
+}
+
+static void stmmac_mac_link_down(struct phylink_config *config,
+				 unsigned int mode, phy_interface_t interface)
+{
+	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+
+	stmmac_mac_set(priv, priv->ioaddr, false);
+	priv->eee_active = false;
+	stmmac_eee_init(priv);
+	stmmac_set_eee_pls(priv, priv->hw, false);
+}
+
+static void stmmac_mac_link_up(struct phylink_config *config,
+			       unsigned int mode, phy_interface_t interface,
+			       struct phy_device *phy)
+{
+	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+
+	stmmac_mac_set(priv, priv->ioaddr, true);
+	if (phy && priv->dma_cap.eee) {
+		priv->eee_active = phy_init_eee(phy, 1) >= 0;
 		priv->eee_enabled = stmmac_eee_init(priv);
+		stmmac_set_eee_pls(priv, priv->hw, true);
+	}
 }
 
+static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
+	.validate = stmmac_validate,
+	.mac_link_state = stmmac_mac_link_state,
+	.mac_config = stmmac_mac_config,
+	.mac_an_restart = stmmac_mac_an_restart,
+	.mac_link_down = stmmac_mac_link_down,
+	.mac_link_up = stmmac_mac_link_up,
+};
+
 /**
  * stmmac_check_pcs_mode - verify if RGMII/SGMII is supported
  * @priv: driver private structure
@@ -953,79 +1001,48 @@ static void stmmac_check_pcs_mode(struct stmmac_priv *priv)
 static int stmmac_init_phy(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
-	u32 tx_cnt = priv->plat->tx_queues_to_use;
-	struct phy_device *phydev;
-	char phy_id_fmt[MII_BUS_ID_SIZE + 3];
-	char bus_id[MII_BUS_ID_SIZE];
-	int interface = priv->plat->interface;
-	int max_speed = priv->plat->max_speed;
-	priv->oldlink = false;
-	priv->speed = SPEED_UNKNOWN;
-	priv->oldduplex = DUPLEX_UNKNOWN;
+	struct device_node *node;
+	int ret;
 
-	if (priv->plat->phy_node) {
-		phydev = of_phy_connect(dev, priv->plat->phy_node,
-					&stmmac_adjust_link, 0, interface);
-	} else {
-		snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
-			 priv->plat->bus_id);
+	node = priv->plat->phylink_node;
 
-		snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
-			 priv->plat->phy_addr);
-		netdev_dbg(priv->dev, "%s: trying to attach to %s\n", __func__,
-			   phy_id_fmt);
+	if (node)
+		ret = phylink_of_phy_connect(priv->phylink, node, 0);
 
-		phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link,
-				     interface);
-	}
+	/* Some DT bindings do not set-up the PHY handle. Let's try to
+	 * manually parse it
+	 */
+	if (!node || ret) {
+		int addr = priv->plat->phy_addr;
+		struct phy_device *phydev;
 
-	if (IS_ERR_OR_NULL(phydev)) {
-		netdev_err(priv->dev, "Could not attach to PHY\n");
-		if (!phydev)
+		phydev = mdiobus_get_phy(priv->mii, addr);
+		if (!phydev) {
+			netdev_err(priv->dev, "no phy at addr %d\n", addr);
 			return -ENODEV;
+		}
 
-		return PTR_ERR(phydev);
+		ret = phylink_connect_phy(priv->phylink, phydev);
 	}
 
-	/* Stop Advertising 1000BASE Capability if interface is not GMII */
-	if ((interface == PHY_INTERFACE_MODE_MII) ||
-	    (interface == PHY_INTERFACE_MODE_RMII) ||
-		(max_speed < 1000 && max_speed > 0))
-		phy_set_max_speed(phydev, SPEED_100);
+	return ret;
+}
 
-	/*
-	 * Half-duplex mode not supported with multiqueue
-	 * half-duplex can only works with single queue
-	 */
-	if (tx_cnt > 1) {
-		phy_remove_link_mode(phydev,
-				     ETHTOOL_LINK_MODE_10baseT_Half_BIT);
-		phy_remove_link_mode(phydev,
-				     ETHTOOL_LINK_MODE_100baseT_Half_BIT);
-		phy_remove_link_mode(phydev,
-				     ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-	}
+static int stmmac_phy_setup(struct stmmac_priv *priv)
+{
+	struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node);
+	int mode = priv->plat->interface;
+	struct phylink *phylink;
 
-	/*
-	 * Broken HW is sometimes missing the pull-up resistor on the
-	 * MDIO line, which results in reads to non-existent devices returning
-	 * 0 rather than 0xffff. Catch this here and treat 0 as a non-existent
-	 * device as well.
-	 * Note: phydev->phy_id is the result of reading the UID PHY registers.
-	 */
-	if (!priv->plat->phy_node && phydev->phy_id == 0) {
-		phy_disconnect(phydev);
-		return -ENODEV;
-	}
+	priv->phylink_config.dev = &priv->dev->dev;
+	priv->phylink_config.type = PHYLINK_NETDEV;
 
-	/* stmmac_adjust_link will change this to PHY_IGNORE_INTERRUPT to avoid
-	 * subsequent PHY polling, make sure we force a link transition if
-	 * we have a UP/DOWN/UP transition
-	 */
-	if (phydev->is_pseudo_fixed_link)
-		phydev->irq = PHY_POLL;
+	phylink = phylink_create(&priv->phylink_config, fwnode,
+				 mode, &stmmac_phylink_mac_ops);
+	if (IS_ERR(phylink))
+		return PTR_ERR(phylink);
 
-	phy_attached_info(phydev);
+	priv->phylink = phylink;
 	return 0;
 }
 
@@ -1114,11 +1131,13 @@ static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue)
 		if (priv->extend_desc)
 			stmmac_init_rx_desc(priv, &rx_q->dma_erx[i].basic,
 					priv->use_riwt, priv->mode,
-					(i == DMA_RX_SIZE - 1));
+					(i == DMA_RX_SIZE - 1),
+					priv->dma_buf_sz);
 		else
 			stmmac_init_rx_desc(priv, &rx_q->dma_rx[i],
 					priv->use_riwt, priv->mode,
-					(i == DMA_RX_SIZE - 1));
+					(i == DMA_RX_SIZE - 1),
+					priv->dma_buf_sz);
 }
 
 /**
@@ -1178,26 +1197,14 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 				  int i, gfp_t flags, u32 queue)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
-	struct sk_buff *skb;
+	struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
 
-	skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
-	if (!skb) {
-		netdev_err(priv->dev,
-			   "%s: Rx init fails; skb is NULL\n", __func__);
+	buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+	if (!buf->page)
 		return -ENOMEM;
-	}
-	rx_q->rx_skbuff[i] = skb;
-	rx_q->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
-						priv->dma_buf_sz,
-						DMA_FROM_DEVICE);
-	if (dma_mapping_error(priv->device, rx_q->rx_skbuff_dma[i])) {
-		netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
-		dev_kfree_skb_any(skb);
-		return -EINVAL;
-	}
-
-	stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[i]);
 
+	buf->addr = page_pool_get_dma_addr(buf->page);
+	stmmac_set_desc_addr(priv, p, buf->addr);
 	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		stmmac_init_desc3(priv, p);
 
@@ -1213,13 +1220,11 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
 
-	if (rx_q->rx_skbuff[i]) {
-		dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[i],
-				 priv->dma_buf_sz, DMA_FROM_DEVICE);
-		dev_kfree_skb_any(rx_q->rx_skbuff[i]);
-	}
-	rx_q->rx_skbuff[i] = NULL;
+	if (buf->page)
+		page_pool_put_page(rx_q->page_pool, buf->page, false);
+	buf->page = NULL;
 }
 
 /**
@@ -1302,10 +1307,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags)
 						     queue);
 			if (ret)
 				goto err_init_rx_buffers;
-
-			netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
-				  rx_q->rx_skbuff[i], rx_q->rx_skbuff[i]->data,
-				  (unsigned int)rx_q->rx_skbuff_dma[i]);
 		}
 
 		rx_q->cur_rx = 0;
@@ -1479,8 +1480,11 @@ static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
 					  sizeof(struct dma_extended_desc),
 					  rx_q->dma_erx, rx_q->dma_rx_phy);
 
-		kfree(rx_q->rx_skbuff_dma);
-		kfree(rx_q->rx_skbuff);
+		kfree(rx_q->buf_pool);
+		if (rx_q->page_pool) {
+			page_pool_request_shutdown(rx_q->page_pool);
+			page_pool_destroy(rx_q->page_pool);
+		}
 	}
 }
 
@@ -1532,20 +1536,29 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
 	/* RX queues buffers and DMA */
 	for (queue = 0; queue < rx_count; queue++) {
 		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+		struct page_pool_params pp_params = { 0 };
 
 		rx_q->queue_index = queue;
 		rx_q->priv_data = priv;
 
-		rx_q->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE,
-						    sizeof(dma_addr_t),
-						    GFP_KERNEL);
-		if (!rx_q->rx_skbuff_dma)
+		pp_params.flags = PP_FLAG_DMA_MAP;
+		pp_params.pool_size = DMA_RX_SIZE;
+		pp_params.order = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE);
+		pp_params.nid = dev_to_node(priv->device);
+		pp_params.dev = priv->device;
+		pp_params.dma_dir = DMA_FROM_DEVICE;
+
+		rx_q->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(rx_q->page_pool)) {
+			ret = PTR_ERR(rx_q->page_pool);
+			rx_q->page_pool = NULL;
 			goto err_dma;
+		}
 
-		rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE,
-						sizeof(struct sk_buff *),
-						GFP_KERNEL);
-		if (!rx_q->rx_skbuff)
+		rx_q->buf_pool = kmalloc_array(DMA_RX_SIZE,
+					       sizeof(*rx_q->buf_pool),
+					       GFP_KERNEL);
+		if (!rx_q->buf_pool)
 			goto err_dma;
 
 		if (priv->extend_desc) {
@@ -1939,6 +1952,10 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 		mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
 	}
 
+	/* We still have pending packets, let's call for a new scheduling */
+	if (tx_q->dirty_tx != tx_q->cur_tx)
+		mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(10));
+
 	__netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue));
 
 	return count;
@@ -2029,24 +2046,17 @@ static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan)
 	int status = stmmac_dma_interrupt_status(priv, priv->ioaddr,
 						 &priv->xstats, chan);
 	struct stmmac_channel *ch = &priv->channel[chan];
-	bool needs_work = false;
-
-	if ((status & handle_rx) && ch->has_rx) {
-		needs_work = true;
-	} else {
-		status &= ~handle_rx;
-	}
 
-	if ((status & handle_tx) && ch->has_tx) {
-		needs_work = true;
-	} else {
-		status &= ~handle_tx;
+	if ((status & handle_rx) && (chan < priv->plat->rx_queues_to_use)) {
+		if (napi_schedule_prep(&ch->rx_napi)) {
+			stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
+			__napi_schedule_irqoff(&ch->rx_napi);
+			status |= handle_tx;
+		}
 	}
 
-	if (needs_work && napi_schedule_prep(&ch->napi)) {
-		stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
-		__napi_schedule(&ch->napi);
-	}
+	if ((status & handle_tx) && (chan < priv->plat->tx_queues_to_use))
+		napi_schedule_irqoff(&ch->tx_napi);
 
 	return status;
 }
@@ -2108,10 +2118,10 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
 	unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET |
 			    MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET;
 
-	dwmac_mmc_intr_all_mask(priv->mmcaddr);
+	stmmac_mmc_intr_all_mask(priv, priv->mmcaddr);
 
 	if (priv->dma_cap.rmon) {
-		dwmac_mmc_ctrl(priv->mmcaddr, mode);
+		stmmac_mmc_ctrl(priv, priv->mmcaddr, mode);
 		memset(&priv->mmc, 0, sizeof(struct stmmac_counters));
 	} else
 		netdev_info(priv->dev, "No MAC Management Counters available\n");
@@ -2144,8 +2154,8 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv)
 		stmmac_get_umac_addr(priv, priv->hw, priv->dev->dev_addr, 0);
 		if (!is_valid_ether_addr(priv->dev->dev_addr))
 			eth_hw_addr_random(priv->dev);
-		netdev_info(priv->dev, "device MAC address %pM\n",
-			    priv->dev->dev_addr);
+		dev_info(priv->device, "device MAC address %pM\n",
+			 priv->dev->dev_addr);
 	}
 }
 
@@ -2188,6 +2198,10 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	if (priv->plat->axi)
 		stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
 
+	/* DMA CSR Channel configuration */
+	for (chan = 0; chan < dma_csr_ch; chan++)
+		stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan);
+
 	/* DMA RX Channel Configuration */
 	for (chan = 0; chan < rx_channels_count; chan++) {
 		rx_q = &priv->rx_queue[chan];
@@ -2213,10 +2227,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 				       tx_q->tx_tail_addr, chan);
 	}
 
-	/* DMA CSR Channel configuration */
-	for (chan = 0; chan < dma_csr_ch; chan++)
-		stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan);
-
 	return ret;
 }
 
@@ -2241,25 +2251,32 @@ static void stmmac_tx_timer(struct timer_list *t)
 
 	ch = &priv->channel[tx_q->queue_index];
 
-	if (likely(napi_schedule_prep(&ch->napi)))
-		__napi_schedule(&ch->napi);
+	/*
+	 * If NAPI is already running we can miss some events. Let's rearm
+	 * the timer and try again.
+	 */
+	if (likely(napi_schedule_prep(&ch->tx_napi)))
+		__napi_schedule(&ch->tx_napi);
+	else
+		mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(10));
 }
 
 /**
- * stmmac_init_tx_coalesce - init tx mitigation options.
+ * stmmac_init_coalesce - init mitigation options.
  * @priv: driver private structure
  * Description:
- * This inits the transmit coalesce parameters: i.e. timer rate,
+ * This inits the coalesce parameters: i.e. timer rate,
  * timer handler and default threshold used for enabling the
  * interrupt on completion bit.
  */
-static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
+static void stmmac_init_coalesce(struct stmmac_priv *priv)
 {
 	u32 tx_channel_count = priv->plat->tx_queues_to_use;
 	u32 chan;
 
 	priv->tx_coal_frames = STMMAC_TX_FRAMES;
 	priv->tx_coal_timer = STMMAC_COAL_TX_TIMER;
+	priv->rx_coal_frames = STMMAC_RX_FRAMES;
 
 	for (chan = 0; chan < tx_channel_count; chan++) {
 		struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
@@ -2545,9 +2562,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
 
 	if (priv->use_riwt) {
-		ret = stmmac_rx_watchdog(priv, priv->ioaddr, MAX_DMA_RIWT, rx_cnt);
+		ret = stmmac_rx_watchdog(priv, priv->ioaddr, MIN_DMA_RIWT, rx_cnt);
 		if (!ret)
-			priv->rx_riwt = MAX_DMA_RIWT;
+			priv->rx_riwt = MIN_DMA_RIWT;
 	}
 
 	if (priv->hw->pcs)
@@ -2590,8 +2607,6 @@ static int stmmac_open(struct net_device *dev)
 	u32 chan;
 	int ret;
 
-	stmmac_check_ether_addr(priv);
-
 	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
 	    priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI) {
@@ -2631,10 +2646,9 @@ static int stmmac_open(struct net_device *dev)
 		goto init_error;
 	}
 
-	stmmac_init_tx_coalesce(priv);
+	stmmac_init_coalesce(priv);
 
-	if (dev->phydev)
-		phy_start(dev->phydev);
+	phylink_start(priv->phylink);
 
 	/* Request the IRQ lines */
 	ret = request_irq(dev->irq, stmmac_interrupt,
@@ -2681,8 +2695,7 @@ lpiirq_error:
 wolirq_error:
 	free_irq(dev->irq, dev);
 irq_error:
-	if (dev->phydev)
-		phy_stop(dev->phydev);
+	phylink_stop(priv->phylink);
 
 	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
 		del_timer_sync(&priv->tx_queue[chan].txtimer);
@@ -2691,9 +2704,7 @@ irq_error:
 init_error:
 	free_dma_desc_resources(priv);
 dma_desc_error:
-	if (dev->phydev)
-		phy_disconnect(dev->phydev);
-
+	phylink_disconnect_phy(priv->phylink);
 	return ret;
 }
 
@@ -2712,10 +2723,8 @@ static int stmmac_release(struct net_device *dev)
 		del_timer_sync(&priv->eee_ctrl_timer);
 
 	/* Stop and disconnect the PHY */
-	if (dev->phydev) {
-		phy_stop(dev->phydev);
-		phy_disconnect(dev->phydev);
-	}
+	phylink_stop(priv->phylink);
+	phylink_disconnect_phy(priv->phylink);
 
 	stmmac_stop_all_queues(priv);
 
@@ -2758,7 +2767,7 @@ static int stmmac_release(struct net_device *dev)
  *  This function fills descriptor and request new descriptors according to
  *  buffer length to fill
  */
-static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
+static void stmmac_tso_allocator(struct stmmac_priv *priv, dma_addr_t des,
 				 int total_len, bool last_segment, u32 queue)
 {
 	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
@@ -2769,11 +2778,18 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
 	tmp_len = total_len;
 
 	while (tmp_len > 0) {
+		dma_addr_t curr_addr;
+
 		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
 		WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]);
 		desc = tx_q->dma_tx + tx_q->cur_tx;
 
-		desc->des0 = cpu_to_le32(des + (total_len - tmp_len));
+		curr_addr = des + (total_len - tmp_len);
+		if (priv->dma_cap.addr64 <= 32)
+			desc->des0 = cpu_to_le32(curr_addr);
+		else
+			stmmac_set_desc_addr(priv, desc, curr_addr);
+
 		buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
 			    TSO_MAX_BUFF_SIZE : tmp_len;
 
@@ -2819,11 +2835,12 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	u32 queue = skb_get_queue_mapping(skb);
-	unsigned int first_entry, des;
+	unsigned int first_entry;
 	struct stmmac_tx_queue *tx_q;
 	int tmp_pay_len = 0;
 	u32 pay_len, mss;
 	u8 proto_hdr_len;
+	dma_addr_t des;
 	int i;
 
 	tx_q = &priv->tx_queue[queue];
@@ -2880,14 +2897,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	tx_q->tx_skbuff_dma[first_entry].buf = des;
 	tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
 
-	first->des0 = cpu_to_le32(des);
+	if (priv->dma_cap.addr64 <= 32) {
+		first->des0 = cpu_to_le32(des);
 
-	/* Fill start of payload in buff2 of first descriptor */
-	if (pay_len)
-		first->des1 = cpu_to_le32(des + proto_hdr_len);
+		/* Fill start of payload in buff2 of first descriptor */
+		if (pay_len)
+			first->des1 = cpu_to_le32(des + proto_hdr_len);
 
-	/* If needed take extra descriptors to fill the remaining payload */
-	tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
+		/* If needed take extra descriptors to fill the remaining payload */
+		tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
+	} else {
+		stmmac_set_desc_addr(priv, first, des);
+		tmp_pay_len = pay_len;
+	}
 
 	stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
 
@@ -2933,12 +2955,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage tx mitigation */
 	tx_q->tx_count_frames += nfrags + 1;
-	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
+	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
-		tx_q->tx_count_frames = 0;
-	} else {
-		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
@@ -3014,12 +3039,12 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	int i, csum_insertion = 0, is_jumbo = 0;
 	u32 queue = skb_get_queue_mapping(skb);
 	int nfrags = skb_shinfo(skb)->nr_frags;
-	int entry;
-	unsigned int first_entry;
 	struct dma_desc *desc, *first;
 	struct stmmac_tx_queue *tx_q;
+	unsigned int first_entry;
 	unsigned int enh_desc;
-	unsigned int des;
+	dma_addr_t des;
+	int entry;
 
 	tx_q = &priv->tx_queue[queue];
 
@@ -3028,17 +3053,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
-		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			/*
-			 * There is no way to determine the number of TSO
-			 * capable Queues. Let's use always the Queue 0
-			 * because if TSO is supported then at least this
-			 * one will be capable.
-			 */
-			skb_set_queue_mapping(skb, 0);
-
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
 			return stmmac_tso_xmit(skb, dev);
-		}
 	}
 
 	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
@@ -3152,12 +3168,15 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * element in case of no SG.
 	 */
 	tx_q->tx_count_frames += nfrags + 1;
-	if (priv->tx_coal_frames <= tx_q->tx_count_frames) {
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
+	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		tx_q->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
-		tx_q->tx_count_frames = 0;
-	} else {
-		stmmac_tx_timer_arm(priv, queue);
 	}
 
 	skb_tx_timestamp(skb);
@@ -3192,14 +3211,16 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		stmmac_prepare_tx_desc(priv, first, 1, nopaged_len,
 				csum_insertion, priv->mode, 1, last_segment,
 				skb->len);
-
-		/* The own bit must be the latest setting done when prepare the
-		 * descriptor and then barrier is needed to make sure that
-		 * all is coherent before granting the DMA engine.
-		 */
-		wmb();
+	} else {
+		stmmac_set_tx_owner(priv, first);
 	}
 
+	/* The own bit must be the latest setting done when prepare the
+	 * descriptor and then barrier is needed to make sure that
+	 * all is coherent before granting the DMA engine.
+	 */
+	wmb();
+
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -3259,59 +3280,39 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 	int dirty = stmmac_rx_dirty(priv, queue);
 	unsigned int entry = rx_q->dirty_rx;
 
-	int bfsize = priv->dma_buf_sz;
-
 	while (dirty-- > 0) {
+		struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry];
 		struct dma_desc *p;
+		bool use_rx_wd;
 
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
 			p = rx_q->dma_rx + entry;
 
-		if (likely(!rx_q->rx_skbuff[entry])) {
-			struct sk_buff *skb;
-
-			skb = netdev_alloc_skb_ip_align(priv->dev, bfsize);
-			if (unlikely(!skb)) {
-				/* so for a while no zero-copy! */
-				rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH;
-				if (unlikely(net_ratelimit()))
-					dev_err(priv->device,
-						"fail to alloc skb entry %d\n",
-						entry);
-				break;
-			}
-
-			rx_q->rx_skbuff[entry] = skb;
-			rx_q->rx_skbuff_dma[entry] =
-			    dma_map_single(priv->device, skb->data, bfsize,
-					   DMA_FROM_DEVICE);
-			if (dma_mapping_error(priv->device,
-					      rx_q->rx_skbuff_dma[entry])) {
-				netdev_err(priv->dev, "Rx DMA map failed\n");
-				dev_kfree_skb(skb);
+		if (!buf->page) {
+			buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+			if (!buf->page)
 				break;
-			}
-
-			stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[entry]);
-			stmmac_refill_desc3(priv, rx_q, p);
-
-			if (rx_q->rx_zeroc_thresh > 0)
-				rx_q->rx_zeroc_thresh--;
-
-			netif_dbg(priv, rx_status, priv->dev,
-				  "refill entry #%d\n", entry);
 		}
-		dma_wmb();
 
-		stmmac_set_rx_owner(priv, p, priv->use_riwt);
+		buf->addr = page_pool_get_dma_addr(buf->page);
+		stmmac_set_desc_addr(priv, p, buf->addr);
+		stmmac_refill_desc3(priv, rx_q, p);
+
+		rx_q->rx_count_frames++;
+		rx_q->rx_count_frames %= priv->rx_coal_frames;
+		use_rx_wd = priv->use_riwt && rx_q->rx_count_frames;
 
 		dma_wmb();
+		stmmac_set_rx_owner(priv, p, use_rx_wd);
 
 		entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
 	}
 	rx_q->dirty_rx = entry;
+	rx_q->rx_tail_addr = rx_q->dma_rx_phy +
+			    (rx_q->dirty_rx * sizeof(struct dma_desc));
+	stmmac_set_rx_tail_ptr(priv, priv->ioaddr, rx_q->rx_tail_addr, queue);
 }
 
 /**
@@ -3326,13 +3327,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	struct stmmac_channel *ch = &priv->channel[queue];
-	unsigned int entry = rx_q->cur_rx;
+	unsigned int next_entry = rx_q->cur_rx;
 	int coe = priv->hw->rx_csum;
-	unsigned int next_entry;
 	unsigned int count = 0;
-	bool xmac;
-
-	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
@@ -3346,9 +3343,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 		stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true);
 	}
 	while (count < limit) {
-		int status;
-		struct dma_desc *p;
-		struct dma_desc *np;
+		struct stmmac_rx_buffer *buf;
+		struct dma_desc *np, *p;
+		int entry, status;
+
+		entry = next_entry;
+		buf = &rx_q->buf_pool[entry];
 
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(rx_q->dma_erx + entry);
@@ -3378,20 +3378,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			stmmac_rx_extended_status(priv, &priv->dev->stats,
 					&priv->xstats, rx_q->dma_erx + entry);
 		if (unlikely(status == discard_frame)) {
+			page_pool_recycle_direct(rx_q->page_pool, buf->page);
 			priv->dev->stats.rx_errors++;
-			if (priv->hwts_rx_en && !priv->extend_desc) {
-				/* DESC2 & DESC3 will be overwritten by device
-				 * with timestamp value, hence reinitialize
-				 * them in stmmac_rx_refill() function so that
-				 * device can reuse it.
-				 */
-				dev_kfree_skb_any(rx_q->rx_skbuff[entry]);
-				rx_q->rx_skbuff[entry] = NULL;
-				dma_unmap_single(priv->device,
-						 rx_q->rx_skbuff_dma[entry],
-						 priv->dma_buf_sz,
-						 DMA_FROM_DEVICE);
-			}
+			buf->page = NULL;
 		} else {
 			struct sk_buff *skb;
 			int frame_len;
@@ -3405,11 +3394,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			 *  ignored
 			 */
 			if (frame_len > priv->dma_buf_sz) {
-				netdev_err(priv->dev,
-					   "len %d larger than size (%d)\n",
-					   frame_len, priv->dma_buf_sz);
+				if (net_ratelimit())
+					netdev_err(priv->dev,
+						   "len %d larger than size (%d)\n",
+						   frame_len, priv->dma_buf_sz);
 				priv->dev->stats.rx_length_errors++;
-				break;
+				continue;
 			}
 
 			/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
@@ -3430,57 +3420,20 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 					   frame_len, status);
 			}
 
-			/* The zero-copy is always used for all the sizes
-			 * in case of GMAC4 because it needs
-			 * to refill the used descriptors, always.
-			 */
-			if (unlikely(!xmac &&
-				     ((frame_len < priv->rx_copybreak) ||
-				     stmmac_rx_threshold_count(rx_q)))) {
-				skb = netdev_alloc_skb_ip_align(priv->dev,
-								frame_len);
-				if (unlikely(!skb)) {
-					if (net_ratelimit())
-						dev_warn(priv->device,
-							 "packet dropped\n");
-					priv->dev->stats.rx_dropped++;
-					break;
-				}
-
-				dma_sync_single_for_cpu(priv->device,
-							rx_q->rx_skbuff_dma
-							[entry], frame_len,
-							DMA_FROM_DEVICE);
-				skb_copy_to_linear_data(skb,
-							rx_q->
-							rx_skbuff[entry]->data,
-							frame_len);
-
-				skb_put(skb, frame_len);
-				dma_sync_single_for_device(priv->device,
-							   rx_q->rx_skbuff_dma
-							   [entry], frame_len,
-							   DMA_FROM_DEVICE);
-			} else {
-				skb = rx_q->rx_skbuff[entry];
-				if (unlikely(!skb)) {
-					netdev_err(priv->dev,
-						   "%s: Inconsistent Rx chain\n",
-						   priv->dev->name);
-					priv->dev->stats.rx_dropped++;
-					break;
-				}
-				prefetch(skb->data - NET_IP_ALIGN);
-				rx_q->rx_skbuff[entry] = NULL;
-				rx_q->rx_zeroc_thresh++;
-
-				skb_put(skb, frame_len);
-				dma_unmap_single(priv->device,
-						 rx_q->rx_skbuff_dma[entry],
-						 priv->dma_buf_sz,
-						 DMA_FROM_DEVICE);
+			skb = netdev_alloc_skb_ip_align(priv->dev, frame_len);
+			if (unlikely(!skb)) {
+				priv->dev->stats.rx_dropped++;
+				continue;
 			}
 
+			dma_sync_single_for_cpu(priv->device, buf->addr,
+						frame_len, DMA_FROM_DEVICE);
+			skb_copy_to_linear_data(skb, page_address(buf->page),
+						frame_len);
+			skb_put(skb, frame_len);
+			dma_sync_single_for_device(priv->device, buf->addr,
+						   frame_len, DMA_FROM_DEVICE);
+
 			if (netif_msg_pktdata(priv)) {
 				netdev_dbg(priv->dev, "frame received (%dbytes)",
 					   frame_len);
@@ -3498,12 +3451,15 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			else
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-			napi_gro_receive(&ch->napi, skb);
+			napi_gro_receive(&ch->rx_napi, skb);
+
+			/* Data payload copied into SKB, page ready for recycle */
+			page_pool_recycle_direct(rx_q->page_pool, buf->page);
+			buf->page = NULL;
 
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
 		}
-		entry = next_entry;
 	}
 
 	stmmac_rx_refill(priv, queue);
@@ -3513,40 +3469,45 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	return count;
 }
 
-/**
- *  stmmac_poll - stmmac poll method (NAPI)
- *  @napi : pointer to the napi structure.
- *  @budget : maximum number of packets that the current CPU can receive from
- *	      all interfaces.
- *  Description :
- *  To look at the incoming frames and clear the tx resources.
- */
-static int stmmac_napi_poll(struct napi_struct *napi, int budget)
+static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
 {
 	struct stmmac_channel *ch =
-		container_of(napi, struct stmmac_channel, napi);
+		container_of(napi, struct stmmac_channel, rx_napi);
 	struct stmmac_priv *priv = ch->priv_data;
-	int work_done, rx_done = 0, tx_done = 0;
 	u32 chan = ch->index;
+	int work_done;
 
 	priv->xstats.napi_poll++;
 
-	if (ch->has_tx)
-		tx_done = stmmac_tx_clean(priv, budget, chan);
-	if (ch->has_rx)
-		rx_done = stmmac_rx(priv, budget, chan);
+	work_done = stmmac_rx(priv, budget, chan);
+	if (work_done < budget && napi_complete_done(napi, work_done))
+		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
+	return work_done;
+}
 
-	work_done = max(rx_done, tx_done);
+static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
+{
+	struct stmmac_channel *ch =
+		container_of(napi, struct stmmac_channel, tx_napi);
+	struct stmmac_priv *priv = ch->priv_data;
+	struct stmmac_tx_queue *tx_q;
+	u32 chan = ch->index;
+	int work_done;
+
+	priv->xstats.napi_poll++;
+
+	work_done = stmmac_tx_clean(priv, DMA_TX_SIZE, chan);
 	work_done = min(work_done, budget);
 
-	if (work_done < budget && napi_complete_done(napi, work_done)) {
-		int stat;
+	if (work_done < budget)
+		napi_complete_done(napi, work_done);
 
-		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
-		stat = stmmac_dma_interrupt_status(priv, priv->ioaddr,
-						   &priv->xstats, chan);
-		if (stat && napi_reschedule(napi))
-			stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
+	/* Force transmission restart */
+	tx_q = &priv->tx_queue[chan];
+	if (tx_q->cur_tx != tx_q->dirty_tx) {
+		stmmac_enable_dma_transmission(priv, priv->ioaddr);
+		stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr,
+				       chan);
 	}
 
 	return work_done;
@@ -3762,6 +3723,7 @@ static void stmmac_poll_controller(struct net_device *dev)
  */
 static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
+	struct stmmac_priv *priv = netdev_priv (dev);
 	int ret = -EOPNOTSUPP;
 
 	if (!netif_running(dev))
@@ -3771,12 +3733,13 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
-		if (!dev->phydev)
-			return -EINVAL;
-		ret = phy_mii_ioctl(dev->phydev, rq, cmd);
+		ret = phylink_mii_ioctl(priv->phylink, rq, cmd);
 		break;
 	case SIOCSHWTSTAMP:
-		ret = stmmac_hwtstamp_ioctl(dev, rq);
+		ret = stmmac_hwtstamp_set(dev, rq);
+		break;
+	case SIOCGHWTSTAMP:
+		ret = stmmac_hwtstamp_get(dev, rq);
 		break;
 	default:
 		break;
@@ -3806,23 +3769,7 @@ static int stmmac_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	return ret;
 }
 
-static int stmmac_setup_tc_block(struct stmmac_priv *priv,
-				 struct tc_block_offload *f)
-{
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb,
-				priv, priv, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(stmmac_block_cb_list);
 
 static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 			   void *type_data)
@@ -3831,7 +3778,10 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return stmmac_setup_tc_block(priv, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &stmmac_block_cb_list,
+						  stmmac_setup_tc_block_cb,
+						  priv, priv, true);
 	case TC_SETUP_QDISC_CBS:
 		return stmmac_tc_setup_cbs(priv, priv, type_data);
 	default:
@@ -3839,6 +3789,22 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
+static u16 stmmac_select_queue(struct net_device *dev, struct sk_buff *skb,
+			       struct net_device *sb_dev)
+{
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+		/*
+		 * There is no way to determine the number of TSO
+		 * capable Queues. Let's use always the Queue 0
+		 * because if TSO is supported then at least this
+		 * one will be capable.
+		 */
+		return 0;
+	}
+
+	return netdev_pick_tx(dev, skb, NULL) % dev->real_num_tx_queues;
+}
+
 static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -4055,6 +4021,7 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_tx_timeout = stmmac_tx_timeout,
 	.ndo_do_ioctl = stmmac_ioctl,
 	.ndo_setup_tc = stmmac_setup_tc,
+	.ndo_select_queue = stmmac_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = stmmac_poll_controller,
 #endif
@@ -4127,6 +4094,12 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 		priv->plat->enh_desc = priv->dma_cap.enh_desc;
 		priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up;
 		priv->hw->pmt = priv->plat->pmt;
+		if (priv->dma_cap.hash_tb_sz) {
+			priv->hw->multicast_filter_bins =
+					(BIT(priv->dma_cap.hash_tb_sz) << 5);
+			priv->hw->mcast_bits_log2 =
+					ilog2(priv->hw->multicast_filter_bins);
+		}
 
 		/* TXCOE doesn't work in thresh DMA mode */
 		if (priv->plat->force_thresh_dma_mode)
@@ -4204,9 +4177,8 @@ int stmmac_dvr_probe(struct device *device,
 	u32 queue, maxq;
 	int ret = 0;
 
-	ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv),
-				  MTL_MAX_TX_QUEUES,
-				  MTL_MAX_RX_QUEUES);
+	ndev = devm_alloc_etherdev_mqs(device, sizeof(struct stmmac_priv),
+				       MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES);
 	if (!ndev)
 		return -ENOMEM;
 
@@ -4226,7 +4198,7 @@ int stmmac_dvr_probe(struct device *device,
 	priv->wol_irq = res->wol_irq;
 	priv->lpi_irq = res->lpi_irq;
 
-	if (res->mac)
+	if (!IS_ERR_OR_NULL(res->mac))
 		memcpy(priv->dev->dev_addr, res->mac, ETH_ALEN);
 
 	dev_set_drvdata(device, priv->dev);
@@ -4238,8 +4210,7 @@ int stmmac_dvr_probe(struct device *device,
 	priv->wq = create_singlethread_workqueue("stmmac_wq");
 	if (!priv->wq) {
 		dev_err(priv->device, "failed to create workqueue\n");
-		ret = -ENOMEM;
-		goto error_wq;
+		return -ENOMEM;
 	}
 
 	INIT_WORK(&priv->service_task, stmmac_service_task);
@@ -4265,6 +4236,8 @@ int stmmac_dvr_probe(struct device *device,
 	if (ret)
 		goto error_hw_init;
 
+	stmmac_check_ether_addr(priv);
+
 	/* Configure real RX and TX queues */
 	netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
 	netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
@@ -4284,6 +4257,24 @@ int stmmac_dvr_probe(struct device *device,
 		priv->tso = true;
 		dev_info(priv->device, "TSO feature enabled\n");
 	}
+
+	if (priv->dma_cap.addr64) {
+		ret = dma_set_mask_and_coherent(device,
+				DMA_BIT_MASK(priv->dma_cap.addr64));
+		if (!ret) {
+			dev_info(priv->device, "Using %d bits DMA width\n",
+				 priv->dma_cap.addr64);
+		} else {
+			ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(32));
+			if (ret) {
+				dev_err(priv->device, "Failed to set DMA Mask\n");
+				goto error_hw_init;
+			}
+
+			priv->dma_cap.addr64 = 32;
+		}
+	}
+
 	ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
 	ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
 #ifdef STMMAC_VLAN_TAG_USED
@@ -4323,13 +4314,14 @@ int stmmac_dvr_probe(struct device *device,
 		ch->priv_data = priv;
 		ch->index = queue;
 
-		if (queue < priv->plat->rx_queues_to_use)
-			ch->has_rx = true;
-		if (queue < priv->plat->tx_queues_to_use)
-			ch->has_tx = true;
-
-		netif_napi_add(ndev, &ch->napi, stmmac_napi_poll,
-			       NAPI_POLL_WEIGHT);
+		if (queue < priv->plat->rx_queues_to_use) {
+			netif_napi_add(ndev, &ch->rx_napi, stmmac_napi_poll_rx,
+				       NAPI_POLL_WEIGHT);
+		}
+		if (queue < priv->plat->tx_queues_to_use) {
+			netif_napi_add(ndev, &ch->tx_napi, stmmac_napi_poll_tx,
+				       NAPI_POLL_WEIGHT);
+		}
 	}
 
 	mutex_init(&priv->lock);
@@ -4340,10 +4332,10 @@ int stmmac_dvr_probe(struct device *device,
 	 * set the MDC clock dynamically according to the csr actual
 	 * clock input.
 	 */
-	if (!priv->plat->clk_csr)
-		stmmac_clk_csr_set(priv);
-	else
+	if (priv->plat->clk_csr >= 0)
 		priv->clk_csr = priv->plat->clk_csr;
+	else
+		stmmac_clk_csr_set(priv);
 
 	stmmac_check_pcs_mode(priv);
 
@@ -4360,6 +4352,12 @@ int stmmac_dvr_probe(struct device *device,
 		}
 	}
 
+	ret = stmmac_phy_setup(priv);
+	if (ret) {
+		netdev_err(ndev, "failed to setup phy (%d)\n", ret);
+		goto error_phy_setup;
+	}
+
 	ret = register_netdev(ndev);
 	if (ret) {
 		dev_err(priv->device, "%s: ERROR %i registering the device\n",
@@ -4377,6 +4375,8 @@ int stmmac_dvr_probe(struct device *device,
 	return ret;
 
 error_netdev_register:
+	phylink_destroy(priv->phylink);
+error_phy_setup:
 	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
 	    priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI)
@@ -4385,12 +4385,13 @@ error_mdio_register:
 	for (queue = 0; queue < maxq; queue++) {
 		struct stmmac_channel *ch = &priv->channel[queue];
 
-		netif_napi_del(&ch->napi);
+		if (queue < priv->plat->rx_queues_to_use)
+			netif_napi_del(&ch->rx_napi);
+		if (queue < priv->plat->tx_queues_to_use)
+			netif_napi_del(&ch->tx_napi);
 	}
 error_hw_init:
 	destroy_workqueue(priv->wq);
-error_wq:
-	free_netdev(ndev);
 
 	return ret;
 }
@@ -4417,6 +4418,7 @@ int stmmac_dvr_remove(struct device *dev)
 	stmmac_mac_set(priv, priv->ioaddr, false);
 	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
+	phylink_destroy(priv->phylink);
 	if (priv->plat->stmmac_rst)
 		reset_control_assert(priv->plat->stmmac_rst);
 	clk_disable_unprepare(priv->plat->pclk);
@@ -4427,7 +4429,6 @@ int stmmac_dvr_remove(struct device *dev)
 		stmmac_mdio_unregister(ndev);
 	destroy_workqueue(priv->wq);
 	mutex_destroy(&priv->lock);
-	free_netdev(ndev);
 
 	return 0;
 }
@@ -4448,8 +4449,7 @@ int stmmac_suspend(struct device *dev)
 	if (!ndev || !netif_running(ndev))
 		return 0;
 
-	if (ndev->phydev)
-		phy_stop(ndev->phydev);
+	phylink_stop(priv->phylink);
 
 	mutex_lock(&priv->lock);
 
@@ -4474,9 +4474,7 @@ int stmmac_suspend(struct device *dev)
 	}
 	mutex_unlock(&priv->lock);
 
-	priv->oldlink = false;
 	priv->speed = SPEED_UNKNOWN;
-	priv->oldduplex = DUPLEX_UNKNOWN;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(stmmac_suspend);
@@ -4551,7 +4549,7 @@ int stmmac_resume(struct device *dev)
 	stmmac_clear_descriptors(priv);
 
 	stmmac_hw_setup(ndev, false);
-	stmmac_init_tx_coalesce(priv);
+	stmmac_init_coalesce(priv);
 	stmmac_set_rx_mode(ndev);
 
 	stmmac_enable_all_queues(priv);
@@ -4560,8 +4558,7 @@ int stmmac_resume(struct device *dev)
 
 	mutex_unlock(&priv->lock);
 
-	if (ndev->phydev)
-		phy_start(ndev->phydev);
+	phylink_start(priv->phylink);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index bdd351597b55..4304c1abc5d1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -1,32 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   STMMAC Ethernet Driver -- MDIO bus implementation
   Provides Bus interface for MII registers
 
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Carl Shaw <carl.shaw@st.com>
   Maintainer: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
+#include <linux/gpio/consumer.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
 #include <linux/mii.h>
-#include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_mdio.h>
 #include <linux/phy.h>
+#include <linux/property.h>
 #include <linux/slab.h>
 
 #include "dwxgmac2.h"
@@ -34,11 +24,14 @@
 
 #define MII_BUSY 0x00000001
 #define MII_WRITE 0x00000002
+#define MII_DATA_MASK GENMASK(15, 0)
 
 /* GMAC4 defines */
 #define MII_GMAC4_GOC_SHIFT		2
+#define MII_GMAC4_REG_ADDR_SHIFT	16
 #define MII_GMAC4_WRITE			(1 << MII_GMAC4_GOC_SHIFT)
 #define MII_GMAC4_READ			(3 << MII_GMAC4_GOC_SHIFT)
+#define MII_GMAC4_C45E			BIT(1)
 
 /* XGMAC defines */
 #define MII_XGMAC_SADDR			BIT(18)
@@ -165,22 +158,34 @@ static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	unsigned int mii_address = priv->hw->mii.addr;
 	unsigned int mii_data = priv->hw->mii.data;
-	u32 v;
-	int data;
 	u32 value = MII_BUSY;
+	int data = 0;
+	u32 v;
 
 	value |= (phyaddr << priv->hw->mii.addr_shift)
 		& priv->hw->mii.addr_mask;
 	value |= (phyreg << priv->hw->mii.reg_shift) & priv->hw->mii.reg_mask;
 	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
 		& priv->hw->mii.clk_csr_mask;
-	if (priv->plat->has_gmac4)
+	if (priv->plat->has_gmac4) {
 		value |= MII_GMAC4_READ;
+		if (phyreg & MII_ADDR_C45) {
+			value |= MII_GMAC4_C45E;
+			value &= ~priv->hw->mii.reg_mask;
+			value |= ((phyreg >> MII_DEVADDR_C45_SHIFT) <<
+			       priv->hw->mii.reg_shift) &
+			       priv->hw->mii.reg_mask;
+
+			data |= (phyreg & MII_REGADDR_C45_MASK) <<
+				MII_GMAC4_REG_ADDR_SHIFT;
+		}
+	}
 
 	if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY),
 			       100, 10000))
 		return -EBUSY;
 
+	writel(data, priv->ioaddr + mii_data);
 	writel(value, priv->ioaddr + mii_address);
 
 	if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY),
@@ -188,7 +193,7 @@ static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
 		return -EBUSY;
 
 	/* Read the data from the MII data register */
-	data = (int)readl(priv->ioaddr + mii_data);
+	data = (int)readl(priv->ioaddr + mii_data) & MII_DATA_MASK;
 
 	return data;
 }
@@ -208,8 +213,9 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	unsigned int mii_address = priv->hw->mii.addr;
 	unsigned int mii_data = priv->hw->mii.data;
-	u32 v;
 	u32 value = MII_BUSY;
+	int data = phydata;
+	u32 v;
 
 	value |= (phyaddr << priv->hw->mii.addr_shift)
 		& priv->hw->mii.addr_mask;
@@ -217,10 +223,21 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
 
 	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
 		& priv->hw->mii.clk_csr_mask;
-	if (priv->plat->has_gmac4)
+	if (priv->plat->has_gmac4) {
 		value |= MII_GMAC4_WRITE;
-	else
+		if (phyreg & MII_ADDR_C45) {
+			value |= MII_GMAC4_C45E;
+			value &= ~priv->hw->mii.reg_mask;
+			value |= ((phyreg >> MII_DEVADDR_C45_SHIFT) <<
+			       priv->hw->mii.reg_shift) &
+			       priv->hw->mii.reg_mask;
+
+			data |= (phyreg & MII_REGADDR_C45_MASK) <<
+				MII_GMAC4_REG_ADDR_SHIFT;
+		}
+	} else {
 		value |= MII_WRITE;
+	}
 
 	/* Wait until any existing MII operation is complete */
 	if (readl_poll_timeout(priv->ioaddr + mii_address, v, !(v & MII_BUSY),
@@ -228,7 +245,7 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
 		return -EBUSY;
 
 	/* Set the MII address register to write */
-	writel(phydata, priv->ioaddr + mii_data);
+	writel(data, priv->ioaddr + mii_data);
 	writel(value, priv->ioaddr + mii_address);
 
 	/* Wait until any existing MII operation is complete */
@@ -247,50 +264,35 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 	struct net_device *ndev = bus->priv;
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	unsigned int mii_address = priv->hw->mii.addr;
-	struct stmmac_mdio_bus_data *data = priv->plat->mdio_bus_data;
 
 #ifdef CONFIG_OF
 	if (priv->device->of_node) {
-		if (data->reset_gpio < 0) {
-			struct device_node *np = priv->device->of_node;
-
-			if (!np)
-				return 0;
+		struct gpio_desc *reset_gpio;
+		u32 delays[3] = { 0, 0, 0 };
 
-			data->reset_gpio = of_get_named_gpio(np,
-						"snps,reset-gpio", 0);
-			if (data->reset_gpio < 0)
-				return 0;
+		reset_gpio = devm_gpiod_get_optional(priv->device,
+						     "snps,reset",
+						     GPIOD_OUT_LOW);
+		if (IS_ERR(reset_gpio))
+			return PTR_ERR(reset_gpio);
 
-			data->active_low = of_property_read_bool(np,
-						"snps,reset-active-low");
-			of_property_read_u32_array(np,
-				"snps,reset-delays-us", data->delays, 3);
+		device_property_read_u32_array(priv->device,
+					       "snps,reset-delays-us",
+					       delays, ARRAY_SIZE(delays));
 
-			if (gpio_request(data->reset_gpio, "mdio-reset"))
-				return 0;
-		}
+		if (delays[0])
+			msleep(DIV_ROUND_UP(delays[0], 1000));
 
-		gpio_direction_output(data->reset_gpio,
-				      data->active_low ? 1 : 0);
-		if (data->delays[0])
-			msleep(DIV_ROUND_UP(data->delays[0], 1000));
+		gpiod_set_value_cansleep(reset_gpio, 1);
+		if (delays[1])
+			msleep(DIV_ROUND_UP(delays[1], 1000));
 
-		gpio_set_value(data->reset_gpio, data->active_low ? 0 : 1);
-		if (data->delays[1])
-			msleep(DIV_ROUND_UP(data->delays[1], 1000));
-
-		gpio_set_value(data->reset_gpio, data->active_low ? 1 : 0);
-		if (data->delays[2])
-			msleep(DIV_ROUND_UP(data->delays[2], 1000));
+		gpiod_set_value_cansleep(reset_gpio, 0);
+		if (delays[2])
+			msleep(DIV_ROUND_UP(delays[2], 1000));
 	}
 #endif
 
-	if (data->phy_reset) {
-		netdev_dbg(ndev, "stmmac_mdio_reset: calling phy_reset\n");
-		data->phy_reset(priv->plat->bsp_priv);
-	}
-
 	/* This is a workaround for problems with the STE101P PHY.
 	 * It doesn't complete its reset until at least one clock cycle
 	 * on MDC, so perform a dummy mdio read. To be updated for GMAC4
@@ -327,11 +329,6 @@ int stmmac_mdio_register(struct net_device *ndev)
 	if (mdio_bus_data->irqs)
 		memcpy(new_bus->irq, mdio_bus_data->irqs, sizeof(new_bus->irq));
 
-#ifdef CONFIG_OF
-	if (priv->device->of_node)
-		mdio_bus_data->reset_gpio = -1;
-#endif
-
 	new_bus->name = "stmmac";
 
 	if (priv->plat->has_xgmac) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index d819e8eaba12..86f9c07a38cf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -1,19 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This contains the functions to handle the pci driver.
 
   Copyright (C) 2011-2012  Vayavya Labs Pvt Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Rayagond Kokatanur <rayagond@vayavyalabs.com>
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
@@ -73,7 +63,6 @@ static void common_default_data(struct plat_stmmacenet_data *plat)
 	plat->has_gmac = 1;
 	plat->force_sf_dma_mode = 1;
 
-	plat->mdio_bus_data->phy_reset = NULL;
 	plat->mdio_bus_data->phy_mask = 0;
 
 	/* Set default value for multicast hash bins */
@@ -159,6 +148,12 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 		},
 		.driver_data = (void *)&galileo_stmmac_dmi_data,
 	},
+	/*
+	 * There are 2 types of SIMATIC IOT2000: IOT2020 and IOT2040.
+	 * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
+	 * has only one pci network device while other asset tags are
+	 * for IOT2040 which has two.
+	 */
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
@@ -170,8 +165,6 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
-			DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG,
-					"6ES7647-0AA00-1YA2"),
 		},
 		.driver_data = (void *)&iot2040_stmmac_dmi_data,
 	},
@@ -204,7 +197,7 @@ static int quark_default_data(struct pci_dev *pdev,
 		ret = 1;
 	}
 
-	plat->bus_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
+	plat->bus_id = pci_dev_id(pdev);
 	plat->phy_addr = ret;
 	plat->interface = PHY_INTERFACE_MODE_RMII;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
index eba41c24b7a7..aefc121464b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h
@@ -1,13 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * stmmac_pcs.h: Physical Coding Sublayer Header File
  *
  * Copyright (C) 2016 STMicroelectronics (R&D) Limited
  * Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef __STMMAC_PCS_H__
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 2b800ce1d5bf..73fc2524372e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -1,19 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   This contains the functions to handle the platform driver.
 
   Copyright (C) 2007-2011  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
@@ -333,21 +323,6 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat,
 		{},
 	};
 
-	/* If phy-handle property is passed from DT, use it as the PHY */
-	plat->phy_node = of_parse_phandle(np, "phy-handle", 0);
-	if (plat->phy_node)
-		dev_dbg(dev, "Found phy-handle subnode\n");
-
-	/* If phy-handle is not specified, check if we have a fixed-phy */
-	if (!plat->phy_node && of_phy_is_fixed_link(np)) {
-		if ((of_phy_register_fixed_link(np) < 0))
-			return -ENODEV;
-
-		dev_dbg(dev, "Found fixed-link subnode\n");
-		plat->phy_node = of_node_get(np);
-		mdio = false;
-	}
-
 	if (of_match_node(need_mdio_ids, np)) {
 		plat->mdio_node = of_get_child_by_name(np, "mdio");
 	} else {
@@ -397,6 +372,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	*mac = of_get_mac_address(np);
 	plat->interface = of_get_phy_mode(np);
 
+	/* Some wrapper drivers still rely on phy_node. Let's save it while
+	 * they are not converted to phylink. */
+	plat->phy_node = of_parse_phandle(np, "phy-handle", 0);
+
+	/* PHYLINK automatically parses the phy-handle property */
+	plat->phylink_node = np;
+
 	/* Get max speed of operation from device tree */
 	if (of_property_read_u32(np, "max-speed", &plat->max_speed))
 		plat->max_speed = -1;
@@ -408,6 +390,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
 
+	/* Default to get clk_csr from stmmac_clk_crs_set(),
+	 * or get clk_csr from device tree.
+	 */
+	plat->clk_csr = -1;
+	of_property_read_u32(np, "clk_csr", &plat->clk_csr);
+
 	/* "snps,phy-addr" is not a standard property. Mark it as deprecated
 	 * and warn of its use. Remove this when phy node support is added.
 	 */
@@ -585,10 +573,6 @@ error_pclk_get:
 void stmmac_remove_config_dt(struct platform_device *pdev,
 			     struct plat_stmmacenet_data *plat)
 {
-	struct device_node *np = pdev->dev.of_node;
-
-	if (of_phy_is_fixed_link(np))
-		of_phy_deregister_fixed_link(np);
 	of_node_put(plat->phy_node);
 	of_node_put(plat->mdio_node);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
index b72eb0de57b7..3a4663b7b460 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
@@ -1,17 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*******************************************************************************
   Copyright (C) 2007-2009  STMicroelectronics Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 2293e21f789f..c48224973a37 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -1,19 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*******************************************************************************
   PTP 1588 clock using the STMMAC.
 
   Copyright (C) 2013  Vayavya Labs Pvt Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Rayagond Kokatanur <rayagond@vayavyalabs.com>
 *******************************************************************************/
@@ -105,7 +95,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts)
 	struct stmmac_priv *priv =
 	    container_of(ptp, struct stmmac_priv, ptp_clock_ops);
 	unsigned long flags;
-	u64 ns;
+	u64 ns = 0;
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 	stmmac_get_systime(priv, priv->ptpaddr, &ns);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index ecccf895fd7e..7abb1d47e7da 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -1,19 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /******************************************************************************
   PTP Header file
 
   Copyright (C) 2013  Vayavya Labs Pvt Ltd
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
 
   Author: Rayagond Kokatanur <rayagond@vayavyalabs.com>
 ******************************************************************************/
@@ -59,9 +49,14 @@
 #define	PTP_TCR_TSEVNTENA	BIT(14)
 /* Enable Snapshot for Messages Relevant to Master */
 #define	PTP_TCR_TSMSTRENA	BIT(15)
-/* Select PTP packets for Taking Snapshots */
+/* Select PTP packets for Taking Snapshots
+ * On gmac4 specifically:
+ * Enable SYNC, Pdelay_Req, Pdelay_Resp when TSEVNTENA is enabled.
+ * or
+ * Enable  SYNC, Follow_Up, Delay_Req, Delay_Resp, Pdelay_Req, Pdelay_Resp,
+ * Pdelay_Resp_Follow_Up if TSEVNTENA is disabled
+ */
 #define	PTP_TCR_SNAPTYPSEL_1	BIT(16)
-#define	PTP_GMAC4_TCR_SNAPTYPSEL_1	GENMASK(17, 16)
 /* Enable MAC address for PTP Frame Filtering */
 #define	PTP_TCR_TSENMACADDR	BIT(18)
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
new file mode 100644
index 000000000000..a97b1ea76438
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -0,0 +1,850 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Synopsys, Inc. and/or its affiliates.
+ * stmmac Selftests Support
+ *
+ * Author: Jose Abreu <joabreu@synopsys.com>
+ */
+
+#include <linux/completion.h>
+#include <linux/ethtool.h>
+#include <linux/ip.h>
+#include <linux/phy.h>
+#include <linux/udp.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include "stmmac.h"
+
+struct stmmachdr {
+	__be32 version;
+	__be64 magic;
+	u8 id;
+} __packed;
+
+#define STMMAC_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
+			      sizeof(struct stmmachdr))
+#define STMMAC_TEST_PKT_MAGIC	0xdeadcafecafedeadULL
+#define STMMAC_LB_TIMEOUT	msecs_to_jiffies(200)
+
+struct stmmac_packet_attrs {
+	int vlan;
+	int vlan_id_in;
+	int vlan_id_out;
+	unsigned char *src;
+	unsigned char *dst;
+	u32 ip_src;
+	u32 ip_dst;
+	int tcp;
+	int sport;
+	int dport;
+	u32 exp_hash;
+	int dont_wait;
+	int timeout;
+	int size;
+	int remove_sa;
+	u8 id;
+};
+
+static u8 stmmac_test_next_id;
+
+static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
+					       struct stmmac_packet_attrs *attr)
+{
+	struct sk_buff *skb = NULL;
+	struct udphdr *uhdr = NULL;
+	struct tcphdr *thdr = NULL;
+	struct stmmachdr *shdr;
+	struct ethhdr *ehdr;
+	struct iphdr *ihdr;
+	int iplen, size;
+
+	size = attr->size + STMMAC_TEST_PKT_SIZE;
+	if (attr->vlan) {
+		size += 4;
+		if (attr->vlan > 1)
+			size += 4;
+	}
+
+	if (attr->tcp)
+		size += sizeof(struct tcphdr);
+	else
+		size += sizeof(struct udphdr);
+
+	skb = netdev_alloc_skb(priv->dev, size);
+	if (!skb)
+		return NULL;
+
+	prefetchw(skb->data);
+	skb_reserve(skb, NET_IP_ALIGN);
+
+	if (attr->vlan > 1)
+		ehdr = skb_push(skb, ETH_HLEN + 8);
+	else if (attr->vlan)
+		ehdr = skb_push(skb, ETH_HLEN + 4);
+	else if (attr->remove_sa)
+		ehdr = skb_push(skb, ETH_HLEN - 6);
+	else
+		ehdr = skb_push(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+
+	skb_set_network_header(skb, skb->len);
+	ihdr = skb_put(skb, sizeof(*ihdr));
+
+	skb_set_transport_header(skb, skb->len);
+	if (attr->tcp)
+		thdr = skb_put(skb, sizeof(*thdr));
+	else
+		uhdr = skb_put(skb, sizeof(*uhdr));
+
+	if (!attr->remove_sa)
+		eth_zero_addr(ehdr->h_source);
+	eth_zero_addr(ehdr->h_dest);
+	if (attr->src && !attr->remove_sa)
+		ether_addr_copy(ehdr->h_source, attr->src);
+	if (attr->dst)
+		ether_addr_copy(ehdr->h_dest, attr->dst);
+
+	if (!attr->remove_sa) {
+		ehdr->h_proto = htons(ETH_P_IP);
+	} else {
+		__be16 *ptr = (__be16 *)ehdr;
+
+		/* HACK */
+		ptr[3] = htons(ETH_P_IP);
+	}
+
+	if (attr->vlan) {
+		__be16 *tag, *proto;
+
+		if (!attr->remove_sa) {
+			tag = (void *)ehdr + ETH_HLEN;
+			proto = (void *)ehdr + (2 * ETH_ALEN);
+		} else {
+			tag = (void *)ehdr + ETH_HLEN - 6;
+			proto = (void *)ehdr + ETH_ALEN;
+		}
+
+		proto[0] = htons(ETH_P_8021Q);
+		tag[0] = htons(attr->vlan_id_out);
+		tag[1] = htons(ETH_P_IP);
+		if (attr->vlan > 1) {
+			proto[0] = htons(ETH_P_8021AD);
+			tag[1] = htons(ETH_P_8021Q);
+			tag[2] = htons(attr->vlan_id_in);
+			tag[3] = htons(ETH_P_IP);
+		}
+	}
+
+	if (attr->tcp) {
+		thdr->source = htons(attr->sport);
+		thdr->dest = htons(attr->dport);
+		thdr->doff = sizeof(struct tcphdr) / 4;
+		thdr->check = 0;
+	} else {
+		uhdr->source = htons(attr->sport);
+		uhdr->dest = htons(attr->dport);
+		uhdr->len = htons(sizeof(*shdr) + sizeof(*uhdr) + attr->size);
+		uhdr->check = 0;
+	}
+
+	ihdr->ihl = 5;
+	ihdr->ttl = 32;
+	ihdr->version = 4;
+	if (attr->tcp)
+		ihdr->protocol = IPPROTO_TCP;
+	else
+		ihdr->protocol = IPPROTO_UDP;
+	iplen = sizeof(*ihdr) + sizeof(*shdr) + attr->size;
+	if (attr->tcp)
+		iplen += sizeof(*thdr);
+	else
+		iplen += sizeof(*uhdr);
+	ihdr->tot_len = htons(iplen);
+	ihdr->frag_off = 0;
+	ihdr->saddr = 0;
+	ihdr->daddr = htonl(attr->ip_dst);
+	ihdr->tos = 0;
+	ihdr->id = 0;
+	ip_send_check(ihdr);
+
+	shdr = skb_put(skb, sizeof(*shdr));
+	shdr->version = 0;
+	shdr->magic = cpu_to_be64(STMMAC_TEST_PKT_MAGIC);
+	attr->id = stmmac_test_next_id;
+	shdr->id = stmmac_test_next_id++;
+
+	if (attr->size)
+		skb_put(skb, attr->size);
+
+	skb->csum = 0;
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	if (attr->tcp) {
+		thdr->check = ~tcp_v4_check(skb->len, ihdr->saddr, ihdr->daddr, 0);
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct tcphdr, check);
+	} else {
+		udp4_hwcsum(skb, ihdr->saddr, ihdr->daddr);
+	}
+
+	skb->protocol = htons(ETH_P_IP);
+	skb->pkt_type = PACKET_HOST;
+	skb->dev = priv->dev;
+
+	return skb;
+}
+
+struct stmmac_test_priv {
+	struct stmmac_packet_attrs *packet;
+	struct packet_type pt;
+	struct completion comp;
+	int double_vlan;
+	int vlan_id;
+	int ok;
+};
+
+static int stmmac_test_loopback_validate(struct sk_buff *skb,
+					 struct net_device *ndev,
+					 struct packet_type *pt,
+					 struct net_device *orig_ndev)
+{
+	struct stmmac_test_priv *tpriv = pt->af_packet_priv;
+	struct stmmachdr *shdr;
+	struct ethhdr *ehdr;
+	struct udphdr *uhdr;
+	struct tcphdr *thdr;
+	struct iphdr *ihdr;
+
+	skb = skb_unshare(skb, GFP_ATOMIC);
+	if (!skb)
+		goto out;
+
+	if (skb_linearize(skb))
+		goto out;
+	if (skb_headlen(skb) < (STMMAC_TEST_PKT_SIZE - ETH_HLEN))
+		goto out;
+
+	ehdr = (struct ethhdr *)skb_mac_header(skb);
+	if (tpriv->packet->dst) {
+		if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst))
+			goto out;
+	}
+	if (tpriv->packet->src) {
+		if (!ether_addr_equal(ehdr->h_source, orig_ndev->dev_addr))
+			goto out;
+	}
+
+	ihdr = ip_hdr(skb);
+	if (tpriv->double_vlan)
+		ihdr = (struct iphdr *)(skb_network_header(skb) + 4);
+
+	if (tpriv->packet->tcp) {
+		if (ihdr->protocol != IPPROTO_TCP)
+			goto out;
+
+		thdr = (struct tcphdr *)((u8 *)ihdr + 4 * ihdr->ihl);
+		if (thdr->dest != htons(tpriv->packet->dport))
+			goto out;
+
+		shdr = (struct stmmachdr *)((u8 *)thdr + sizeof(*thdr));
+	} else {
+		if (ihdr->protocol != IPPROTO_UDP)
+			goto out;
+
+		uhdr = (struct udphdr *)((u8 *)ihdr + 4 * ihdr->ihl);
+		if (uhdr->dest != htons(tpriv->packet->dport))
+			goto out;
+
+		shdr = (struct stmmachdr *)((u8 *)uhdr + sizeof(*uhdr));
+	}
+
+	if (shdr->magic != cpu_to_be64(STMMAC_TEST_PKT_MAGIC))
+		goto out;
+	if (tpriv->packet->exp_hash && !skb->hash)
+		goto out;
+	if (tpriv->packet->id != shdr->id)
+		goto out;
+
+	tpriv->ok = true;
+	complete(&tpriv->comp);
+out:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int __stmmac_test_loopback(struct stmmac_priv *priv,
+				  struct stmmac_packet_attrs *attr)
+{
+	struct stmmac_test_priv *tpriv;
+	struct sk_buff *skb = NULL;
+	int ret = 0;
+
+	tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL);
+	if (!tpriv)
+		return -ENOMEM;
+
+	tpriv->ok = false;
+	init_completion(&tpriv->comp);
+
+	tpriv->pt.type = htons(ETH_P_IP);
+	tpriv->pt.func = stmmac_test_loopback_validate;
+	tpriv->pt.dev = priv->dev;
+	tpriv->pt.af_packet_priv = tpriv;
+	tpriv->packet = attr;
+	dev_add_pack(&tpriv->pt);
+
+	skb = stmmac_test_get_udp_skb(priv, attr);
+	if (!skb) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	skb_set_queue_mapping(skb, 0);
+	ret = dev_queue_xmit(skb);
+	if (ret)
+		goto cleanup;
+
+	if (attr->dont_wait)
+		goto cleanup;
+
+	if (!attr->timeout)
+		attr->timeout = STMMAC_LB_TIMEOUT;
+
+	wait_for_completion_timeout(&tpriv->comp, attr->timeout);
+	ret = !tpriv->ok;
+
+cleanup:
+	dev_remove_pack(&tpriv->pt);
+	kfree(tpriv);
+	return ret;
+}
+
+static int stmmac_test_mac_loopback(struct stmmac_priv *priv)
+{
+	struct stmmac_packet_attrs attr = { };
+
+	attr.dst = priv->dev->dev_addr;
+	return __stmmac_test_loopback(priv, &attr);
+}
+
+static int stmmac_test_phy_loopback(struct stmmac_priv *priv)
+{
+	struct stmmac_packet_attrs attr = { };
+	int ret;
+
+	if (!priv->dev->phydev)
+		return -EBUSY;
+
+	ret = phy_loopback(priv->dev->phydev, true);
+	if (ret)
+		return ret;
+
+	attr.dst = priv->dev->dev_addr;
+	ret = __stmmac_test_loopback(priv, &attr);
+
+	phy_loopback(priv->dev->phydev, false);
+	return ret;
+}
+
+static int stmmac_test_mmc(struct stmmac_priv *priv)
+{
+	struct stmmac_counters initial, final;
+	int ret;
+
+	memset(&initial, 0, sizeof(initial));
+	memset(&final, 0, sizeof(final));
+
+	if (!priv->dma_cap.rmon)
+		return -EOPNOTSUPP;
+
+	/* Save previous results into internal struct */
+	stmmac_mmc_read(priv, priv->mmcaddr, &priv->mmc);
+
+	ret = stmmac_test_mac_loopback(priv);
+	if (ret)
+		return ret;
+
+	/* These will be loopback results so no need to save them */
+	stmmac_mmc_read(priv, priv->mmcaddr, &final);
+
+	/*
+	 * The number of MMC counters available depends on HW configuration
+	 * so we just use this one to validate the feature. I hope there is
+	 * not a version without this counter.
+	 */
+	if (final.mmc_tx_framecount_g <= initial.mmc_tx_framecount_g)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int stmmac_test_eee(struct stmmac_priv *priv)
+{
+	struct stmmac_extra_stats *initial, *final;
+	int retries = 10;
+	int ret;
+
+	if (!priv->dma_cap.eee || !priv->eee_active)
+		return -EOPNOTSUPP;
+
+	initial = kzalloc(sizeof(*initial), GFP_KERNEL);
+	if (!initial)
+		return -ENOMEM;
+
+	final = kzalloc(sizeof(*final), GFP_KERNEL);
+	if (!final) {
+		ret = -ENOMEM;
+		goto out_free_initial;
+	}
+
+	memcpy(initial, &priv->xstats, sizeof(*initial));
+
+	ret = stmmac_test_mac_loopback(priv);
+	if (ret)
+		goto out_free_final;
+
+	/* We have no traffic in the line so, sooner or later it will go LPI */
+	while (--retries) {
+		memcpy(final, &priv->xstats, sizeof(*final));
+
+		if (final->irq_tx_path_in_lpi_mode_n >
+		    initial->irq_tx_path_in_lpi_mode_n)
+			break;
+		msleep(100);
+	}
+
+	if (!retries) {
+		ret = -ETIMEDOUT;
+		goto out_free_final;
+	}
+
+	if (final->irq_tx_path_in_lpi_mode_n <=
+	    initial->irq_tx_path_in_lpi_mode_n) {
+		ret = -EINVAL;
+		goto out_free_final;
+	}
+
+	if (final->irq_tx_path_exit_lpi_mode_n <=
+	    initial->irq_tx_path_exit_lpi_mode_n) {
+		ret = -EINVAL;
+		goto out_free_final;
+	}
+
+out_free_final:
+	kfree(final);
+out_free_initial:
+	kfree(initial);
+	return ret;
+}
+
+static int stmmac_filter_check(struct stmmac_priv *priv)
+{
+	if (!(priv->dev->flags & IFF_PROMISC))
+		return 0;
+
+	netdev_warn(priv->dev, "Test can't be run in promiscuous mode!\n");
+	return -EOPNOTSUPP;
+}
+
+static int stmmac_test_hfilt(struct stmmac_priv *priv)
+{
+	unsigned char gd_addr[ETH_ALEN] = {0x01, 0x00, 0xcc, 0xcc, 0xdd, 0xdd};
+	unsigned char bd_addr[ETH_ALEN] = {0x09, 0x00, 0xaa, 0xaa, 0xbb, 0xbb};
+	struct stmmac_packet_attrs attr = { };
+	int ret;
+
+	ret = stmmac_filter_check(priv);
+	if (ret)
+		return ret;
+
+	ret = dev_mc_add(priv->dev, gd_addr);
+	if (ret)
+		return ret;
+
+	attr.dst = gd_addr;
+
+	/* Shall receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	if (ret)
+		goto cleanup;
+
+	attr.dst = bd_addr;
+
+	/* Shall NOT receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	ret = !ret;
+
+cleanup:
+	dev_mc_del(priv->dev, gd_addr);
+	return ret;
+}
+
+static int stmmac_test_pfilt(struct stmmac_priv *priv)
+{
+	unsigned char gd_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77};
+	unsigned char bd_addr[ETH_ALEN] = {0x08, 0x00, 0x22, 0x33, 0x44, 0x55};
+	struct stmmac_packet_attrs attr = { };
+	int ret;
+
+	if (stmmac_filter_check(priv))
+		return -EOPNOTSUPP;
+
+	ret = dev_uc_add(priv->dev, gd_addr);
+	if (ret)
+		return ret;
+
+	attr.dst = gd_addr;
+
+	/* Shall receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	if (ret)
+		goto cleanup;
+
+	attr.dst = bd_addr;
+
+	/* Shall NOT receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	ret = !ret;
+
+cleanup:
+	dev_uc_del(priv->dev, gd_addr);
+	return ret;
+}
+
+static int stmmac_dummy_sync(struct net_device *netdev, const u8 *addr)
+{
+	return 0;
+}
+
+static void stmmac_test_set_rx_mode(struct net_device *netdev)
+{
+	/* As we are in test mode of ethtool we already own the rtnl lock
+	 * so no address will change from user. We can just call the
+	 * ndo_set_rx_mode() callback directly */
+	if (netdev->netdev_ops->ndo_set_rx_mode)
+		netdev->netdev_ops->ndo_set_rx_mode(netdev);
+}
+
+static int stmmac_test_mcfilt(struct stmmac_priv *priv)
+{
+	unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77};
+	unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77};
+	struct stmmac_packet_attrs attr = { };
+	int ret;
+
+	if (stmmac_filter_check(priv))
+		return -EOPNOTSUPP;
+
+	/* Remove all MC addresses */
+	__dev_mc_unsync(priv->dev, NULL);
+	stmmac_test_set_rx_mode(priv->dev);
+
+	ret = dev_uc_add(priv->dev, uc_addr);
+	if (ret)
+		goto cleanup;
+
+	attr.dst = uc_addr;
+
+	/* Shall receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	if (ret)
+		goto cleanup;
+
+	attr.dst = mc_addr;
+
+	/* Shall NOT receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	ret = !ret;
+
+cleanup:
+	dev_uc_del(priv->dev, uc_addr);
+	__dev_mc_sync(priv->dev, stmmac_dummy_sync, NULL);
+	stmmac_test_set_rx_mode(priv->dev);
+	return ret;
+}
+
+static int stmmac_test_ucfilt(struct stmmac_priv *priv)
+{
+	unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77};
+	unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77};
+	struct stmmac_packet_attrs attr = { };
+	int ret;
+
+	if (stmmac_filter_check(priv))
+		return -EOPNOTSUPP;
+
+	/* Remove all UC addresses */
+	__dev_uc_unsync(priv->dev, NULL);
+	stmmac_test_set_rx_mode(priv->dev);
+
+	ret = dev_mc_add(priv->dev, mc_addr);
+	if (ret)
+		goto cleanup;
+
+	attr.dst = mc_addr;
+
+	/* Shall receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	if (ret)
+		goto cleanup;
+
+	attr.dst = uc_addr;
+
+	/* Shall NOT receive packet */
+	ret = __stmmac_test_loopback(priv, &attr);
+	ret = !ret;
+
+cleanup:
+	dev_mc_del(priv->dev, mc_addr);
+	__dev_uc_sync(priv->dev, stmmac_dummy_sync, NULL);
+	stmmac_test_set_rx_mode(priv->dev);
+	return ret;
+}
+
+static int stmmac_test_flowctrl_validate(struct sk_buff *skb,
+					 struct net_device *ndev,
+					 struct packet_type *pt,
+					 struct net_device *orig_ndev)
+{
+	struct stmmac_test_priv *tpriv = pt->af_packet_priv;
+	struct ethhdr *ehdr;
+
+	ehdr = (struct ethhdr *)skb_mac_header(skb);
+	if (!ether_addr_equal(ehdr->h_source, orig_ndev->dev_addr))
+		goto out;
+	if (ehdr->h_proto != htons(ETH_P_PAUSE))
+		goto out;
+
+	tpriv->ok = true;
+	complete(&tpriv->comp);
+out:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int stmmac_test_flowctrl(struct stmmac_priv *priv)
+{
+	unsigned char paddr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00, 0x00, 0x01};
+	struct phy_device *phydev = priv->dev->phydev;
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	struct stmmac_test_priv *tpriv;
+	unsigned int pkt_count;
+	int i, ret = 0;
+
+	if (!phydev || !phydev->pause)
+		return -EOPNOTSUPP;
+
+	tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL);
+	if (!tpriv)
+		return -ENOMEM;
+
+	tpriv->ok = false;
+	init_completion(&tpriv->comp);
+	tpriv->pt.type = htons(ETH_P_PAUSE);
+	tpriv->pt.func = stmmac_test_flowctrl_validate;
+	tpriv->pt.dev = priv->dev;
+	tpriv->pt.af_packet_priv = tpriv;
+	dev_add_pack(&tpriv->pt);
+
+	/* Compute minimum number of packets to make FIFO full */
+	pkt_count = priv->plat->rx_fifo_size;
+	if (!pkt_count)
+		pkt_count = priv->dma_cap.rx_fifo_size;
+	pkt_count /= 1400;
+	pkt_count *= 2;
+
+	for (i = 0; i < rx_cnt; i++)
+		stmmac_stop_rx(priv, priv->ioaddr, i);
+
+	ret = dev_set_promiscuity(priv->dev, 1);
+	if (ret)
+		goto cleanup;
+
+	ret = dev_mc_add(priv->dev, paddr);
+	if (ret)
+		goto cleanup;
+
+	for (i = 0; i < pkt_count; i++) {
+		struct stmmac_packet_attrs attr = { };
+
+		attr.dst = priv->dev->dev_addr;
+		attr.dont_wait = true;
+		attr.size = 1400;
+
+		ret = __stmmac_test_loopback(priv, &attr);
+		if (ret)
+			goto cleanup;
+		if (tpriv->ok)
+			break;
+	}
+
+	/* Wait for some time in case RX Watchdog is enabled */
+	msleep(200);
+
+	for (i = 0; i < rx_cnt; i++) {
+		struct stmmac_channel *ch = &priv->channel[i];
+
+		stmmac_start_rx(priv, priv->ioaddr, i);
+		local_bh_disable();
+		napi_reschedule(&ch->rx_napi);
+		local_bh_enable();
+	}
+
+	wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT);
+	ret = !tpriv->ok;
+
+cleanup:
+	dev_mc_del(priv->dev, paddr);
+	dev_set_promiscuity(priv->dev, -1);
+	dev_remove_pack(&tpriv->pt);
+	kfree(tpriv);
+	return ret;
+}
+
+#define STMMAC_LOOPBACK_NONE	0
+#define STMMAC_LOOPBACK_MAC	1
+#define STMMAC_LOOPBACK_PHY	2
+
+static const struct stmmac_test {
+	char name[ETH_GSTRING_LEN];
+	int lb;
+	int (*fn)(struct stmmac_priv *priv);
+} stmmac_selftests[] = {
+	{
+		.name = "MAC Loopback         ",
+		.lb = STMMAC_LOOPBACK_MAC,
+		.fn = stmmac_test_mac_loopback,
+	}, {
+		.name = "PHY Loopback         ",
+		.lb = STMMAC_LOOPBACK_NONE, /* Test will handle it */
+		.fn = stmmac_test_phy_loopback,
+	}, {
+		.name = "MMC Counters         ",
+		.lb = STMMAC_LOOPBACK_PHY,
+		.fn = stmmac_test_mmc,
+	}, {
+		.name = "EEE                  ",
+		.lb = STMMAC_LOOPBACK_PHY,
+		.fn = stmmac_test_eee,
+	}, {
+		.name = "Hash Filter MC       ",
+		.lb = STMMAC_LOOPBACK_PHY,
+		.fn = stmmac_test_hfilt,
+	}, {
+		.name = "Perfect Filter UC    ",
+		.lb = STMMAC_LOOPBACK_PHY,
+		.fn = stmmac_test_pfilt,
+	}, {
+		.name = "MC Filter            ",
+		.lb = STMMAC_LOOPBACK_PHY,
+		.fn = stmmac_test_mcfilt,
+	}, {
+		.name = "UC Filter            ",
+		.lb = STMMAC_LOOPBACK_PHY,
+		.fn = stmmac_test_ucfilt,
+	}, {
+		.name = "Flow Control         ",
+		.lb = STMMAC_LOOPBACK_PHY,
+		.fn = stmmac_test_flowctrl,
+	},
+};
+
+void stmmac_selftest_run(struct net_device *dev,
+			 struct ethtool_test *etest, u64 *buf)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	int count = stmmac_selftest_get_count(priv);
+	int carrier = netif_carrier_ok(dev);
+	int i, ret;
+
+	memset(buf, 0, sizeof(*buf) * count);
+	stmmac_test_next_id = 0;
+
+	if (etest->flags != ETH_TEST_FL_OFFLINE) {
+		netdev_err(priv->dev, "Only offline tests are supported\n");
+		etest->flags |= ETH_TEST_FL_FAILED;
+		return;
+	} else if (!carrier) {
+		netdev_err(priv->dev, "You need valid Link to execute tests\n");
+		etest->flags |= ETH_TEST_FL_FAILED;
+		return;
+	}
+
+	/* We don't want extra traffic */
+	netif_carrier_off(dev);
+
+	/* Wait for queues drain */
+	msleep(200);
+
+	for (i = 0; i < count; i++) {
+		ret = 0;
+
+		switch (stmmac_selftests[i].lb) {
+		case STMMAC_LOOPBACK_PHY:
+			ret = -EOPNOTSUPP;
+			if (dev->phydev)
+				ret = phy_loopback(dev->phydev, true);
+			if (!ret)
+				break;
+			/* Fallthrough */
+		case STMMAC_LOOPBACK_MAC:
+			ret = stmmac_set_mac_loopback(priv, priv->ioaddr, true);
+			break;
+		case STMMAC_LOOPBACK_NONE:
+			break;
+		default:
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		/*
+		 * First tests will always be MAC / PHY loobpack. If any of
+		 * them is not supported we abort earlier.
+		 */
+		if (ret) {
+			netdev_err(priv->dev, "Loopback is not supported\n");
+			etest->flags |= ETH_TEST_FL_FAILED;
+			break;
+		}
+
+		ret = stmmac_selftests[i].fn(priv);
+		if (ret && (ret != -EOPNOTSUPP))
+			etest->flags |= ETH_TEST_FL_FAILED;
+		buf[i] = ret;
+
+		switch (stmmac_selftests[i].lb) {
+		case STMMAC_LOOPBACK_PHY:
+			ret = -EOPNOTSUPP;
+			if (dev->phydev)
+				ret = phy_loopback(dev->phydev, false);
+			if (!ret)
+				break;
+			/* Fallthrough */
+		case STMMAC_LOOPBACK_MAC:
+			stmmac_set_mac_loopback(priv, priv->ioaddr, false);
+			break;
+		default:
+			break;
+		}
+	}
+
+	/* Restart everything */
+	if (carrier)
+		netif_carrier_on(dev);
+}
+
+void stmmac_selftest_get_strings(struct stmmac_priv *priv, u8 *data)
+{
+	u8 *p = data;
+	int i;
+
+	for (i = 0; i < stmmac_selftest_get_count(priv); i++) {
+		snprintf(p, ETH_GSTRING_LEN, "%2d. %s", i + 1,
+			 stmmac_selftests[i].name);
+		p += ETH_GSTRING_LEN;
+	}
+}
+
+int stmmac_selftest_get_count(struct stmmac_priv *priv)
+{
+	return ARRAY_SIZE(stmmac_selftests);
+}
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 644e42c181ee..01ea0d6f8819 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -101,8 +101,7 @@ static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev,
-			    select_queue_fallback_t fallback)
+			    struct net_device *sb_dev)
 {
 	struct vnet_port *port = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index d84501441edd..0bc5863bffeb 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -1217,8 +1217,6 @@ static int link_status_1g_rgmii(struct niu *np, int *link_up_p)
 
 	spin_lock_irqsave(&np->lock, flags);
 
-	err = -EINVAL;
-
 	err = mii_read(np, np->phy_addr, MII_BMSR);
 	if (err < 0)
 		goto out;
@@ -7464,6 +7462,7 @@ static int niu_add_ethtool_tcam_entry(struct niu *np,
 					class = CLASS_CODE_USER_PROG4;
 					break;
 				default:
+					class = CLASS_CODE_UNRECOG;
 					break;
 				}
 				ret = tcam_user_ip_class_set(np, class, 0,
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index b9221fc1674d..3e7631160384 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -2760,7 +2760,7 @@ static void get_gem_mac_nonobp(struct pci_dev *pdev, unsigned char *dev_addr)
 	void __iomem *p = pci_map_rom(pdev, &size);
 
 	if (p) {
-			int found;
+		int found;
 
 		found = readb(p) == 0x55 &&
 			readb(p + 1) == 0xaa &&
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 590172818b92..96b883f965f6 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -234,8 +234,7 @@ static struct vnet_port *vnet_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	struct vnet *vp = netdev_priv(dev);
 	struct vnet_port *port = __tx_port_find(vp, skb);
diff --git a/drivers/net/ethernet/synopsys/Kconfig b/drivers/net/ethernet/synopsys/Kconfig
index a9503884e1c2..9e199772c1d7 100644
--- a/drivers/net/ethernet/synopsys/Kconfig
+++ b/drivers/net/ethernet/synopsys/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Synopsys network device configuration
 #
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
index 99d86e39ff54..bf6c1c6779ff 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
@@ -995,7 +995,7 @@ static void xlgmac_dev_xmit(struct xlgmac_channel *channel)
 	smp_wmb();
 
 	ring->cur = cur_index + 1;
-	if (!pkt_info->skb->xmit_more ||
+	if (!netdev_xmit_more() ||
 	    netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
 						   channel->queue_index)))
 		xlgmac_tx_start_xmit(channel, ring);
diff --git a/drivers/net/ethernet/tehuti/Kconfig b/drivers/net/ethernet/tehuti/Kconfig
index b17f0ca3f395..8ad1526f4bdd 100644
--- a/drivers/net/ethernet/tehuti/Kconfig
+++ b/drivers/net/ethernet/tehuti/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Tehuti network device configuration
 #
diff --git a/drivers/net/ethernet/tehuti/Makefile b/drivers/net/ethernet/tehuti/Makefile
index f995421ddbc8..13a0ddd62088 100644
--- a/drivers/net/ethernet/tehuti/Makefile
+++ b/drivers/net/ethernet/tehuti/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Tehuti network device drivers.
 #
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index b24c11187017..5d6960fe3309 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Tehuti Networks(R) Network Driver
  * ethtool interface implementation
  * Copyright (C) 2007 Tehuti Networks Ltd. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 /*
diff --git a/drivers/net/ethernet/tehuti/tehuti.h b/drivers/net/ethernet/tehuti/tehuti.h
index 8e7b4c9abf21..5fc03c8eba0c 100644
--- a/drivers/net/ethernet/tehuti/tehuti.h
+++ b/drivers/net/ethernet/tehuti/tehuti.h
@@ -1,11 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Tehuti Networks(R) Network Driver
  * Copyright (C) 2007 Tehuti Networks Ltd. All rights reserved
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #ifndef _TEHUTI_H
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index bb126be1eb72..834afca3a019 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # TI device configuration
 #
@@ -20,7 +21,6 @@ config TI_DAVINCI_EMAC
 	tristate "TI DaVinci EMAC Support"
 	depends on ARM && ( ARCH_DAVINCI || ARCH_OMAP3 ) || COMPILE_TEST
 	select TI_DAVINCI_MDIO
-	select TI_DAVINCI_CPDMA
 	select PHYLIB
 	---help---
 	  This driver supports TI's DaVinci Ethernet .
@@ -38,35 +38,19 @@ config TI_DAVINCI_MDIO
 	  To compile this driver as a module, choose M here: the module
 	  will be called davinci_mdio.  This is recommended.
 
-config TI_DAVINCI_CPDMA
-	tristate "TI DaVinci CPDMA Support"
-	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
-	select GENERIC_ALLOCATOR
-	---help---
-	  This driver supports TI's DaVinci CPDMA dma engine.
-
-	  To compile this driver as a module, choose M here: the module
-	  will be called davinci_cpdma.  This is recommended.
-
 config TI_CPSW_PHY_SEL
-	bool
+	bool "TI CPSW Phy mode Selection (DEPRECATED)"
+	default n
 	---help---
 	  This driver supports configuring of the phy mode connected to
-	  the CPSW.
-
-config TI_CPSW_ALE
-	tristate "TI CPSW ALE Support"
-	---help---
-	  This driver supports TI's CPSW ALE module.
+	  the CPSW. DEPRECATED: use PHY_TI_GMII_SEL.
 
 config TI_CPSW
 	tristate "TI CPSW Switch Support"
 	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
-	select TI_DAVINCI_CPDMA
 	select TI_DAVINCI_MDIO
-	select TI_CPSW_PHY_SEL
-	select TI_CPSW_ALE
 	select MFD_SYSCON
+	select PAGE_POOL
 	select REGMAP
 	---help---
 	  This driver supports TI's CPSW Ethernet Switch.
@@ -77,6 +61,7 @@ config TI_CPSW
 config TI_CPTS
 	bool "TI Common Platform Time Sync (CPTS) Support"
 	depends on TI_CPSW || TI_KEYSTONE_NETCP || COMPILE_TEST
+	depends on COMMON_CLK
 	depends on POSIX_TIMERS
 	---help---
 	  This driver supports the Common Platform Time Sync unit of
@@ -94,7 +79,6 @@ config TI_CPTS_MOD
 
 config TI_KEYSTONE_NETCP
 	tristate "TI Keystone NETCP Core Support"
-	select TI_CPSW_ALE
 	select TI_DAVINCI_MDIO
 	depends on OF
 	depends on KEYSTONE_NAVIGATOR_DMA && KEYSTONE_NAVIGATOR_QMSS
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 0be551de821c..ed12e1e5df2f 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -8,16 +8,15 @@ obj-$(CONFIG_TI_DAVINCI_EMAC) += cpsw-common.o
 
 obj-$(CONFIG_TLAN) += tlan.o
 obj-$(CONFIG_CPMAC) += cpmac.o
-obj-$(CONFIG_TI_DAVINCI_EMAC) += davinci_emac.o
+obj-$(CONFIG_TI_DAVINCI_EMAC) += ti_davinci_emac.o
+ti_davinci_emac-y := davinci_emac.o davinci_cpdma.o
 obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o
-obj-$(CONFIG_TI_DAVINCI_CPDMA) += davinci_cpdma.o
 obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o
-obj-$(CONFIG_TI_CPSW_ALE) += cpsw_ale.o
 obj-$(CONFIG_TI_CPTS_MOD) += cpts.o
 obj-$(CONFIG_TI_CPSW) += ti_cpsw.o
-ti_cpsw-y := cpsw.o
+ti_cpsw-y := cpsw.o davinci_cpdma.o cpsw_ale.o cpsw_priv.o cpsw_sl.o cpsw_ethtool.o
 
 obj-$(CONFIG_TI_KEYSTONE_NETCP) += keystone_netcp.o
-keystone_netcp-y := netcp_core.o
+keystone_netcp-y := netcp_core.o cpsw_ale.o
 obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o
-keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o
+keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.o
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index e2d47b24a869..3a655a4dc10e 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -1,19 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright (C) 2006, 2007 Eugene Konev
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c
index 38d1cc557c11..bfa81bbfce3f 100644
--- a/drivers/net/ethernet/ti/cpsw-common.c
+++ b/drivers/net/ethernet/ti/cpsw-common.c
@@ -1,14 +1,4 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index 396e1cd10667..4e184eecc8e1 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -1,17 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /* Texas Instruments Ethernet Switch Driver
  *
  * Copyright (C) 2013 Texas Instruments
  *
  * Module Author: Mugunthan V N <mugunthanvnm@ti.com>
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/platform_device.h>
@@ -78,7 +71,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv,
 	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
-	};
+	}
 
 	mask = GMII_SEL_MODE_MASK << (slave * 2) | BIT(slave + 6);
 	mask |= BIT(slave + 4);
@@ -133,7 +126,7 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv,
 	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
-	};
+	}
 
 	switch (slave) {
 	case 0:
@@ -158,9 +151,9 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv,
 }
 
 static struct platform_driver cpsw_phy_sel_driver;
-static int match(struct device *dev, void *data)
+static int match(struct device *dev, const void *data)
 {
-	struct device_node *node = (struct device_node *)data;
+	const struct device_node *node = (const struct device_node *)data;
 	return dev->of_node == node &&
 		dev->driver == &cpsw_phy_sel_driver.driver;
 }
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a591583d120e..f320f9a0de8b 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1,16 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Texas Instruments Ethernet Switch Driver
  *
  * Copyright (C) 2012 Texas Instruments
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
@@ -38,144 +31,23 @@
 #include <linux/if_vlan.h>
 #include <linux/kmemleak.h>
 #include <linux/sys_soc.h>
+#include <net/page_pool.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
 
 #include <linux/pinctrl/consumer.h>
 #include <net/pkt_cls.h>
 
 #include "cpsw.h"
 #include "cpsw_ale.h"
+#include "cpsw_priv.h"
+#include "cpsw_sl.h"
 #include "cpts.h"
 #include "davinci_cpdma.h"
 
 #include <net/pkt_sched.h>
 
-#define CPSW_DEBUG	(NETIF_MSG_HW		| NETIF_MSG_WOL		| \
-			 NETIF_MSG_DRV		| NETIF_MSG_LINK	| \
-			 NETIF_MSG_IFUP		| NETIF_MSG_INTR	| \
-			 NETIF_MSG_PROBE	| NETIF_MSG_TIMER	| \
-			 NETIF_MSG_IFDOWN	| NETIF_MSG_RX_ERR	| \
-			 NETIF_MSG_TX_ERR	| NETIF_MSG_TX_DONE	| \
-			 NETIF_MSG_PKTDATA	| NETIF_MSG_TX_QUEUED	| \
-			 NETIF_MSG_RX_STATUS)
-
-#define cpsw_info(priv, type, format, ...)		\
-do {								\
-	if (netif_msg_##type(priv) && net_ratelimit())		\
-		dev_info(priv->dev, format, ## __VA_ARGS__);	\
-} while (0)
-
-#define cpsw_err(priv, type, format, ...)		\
-do {								\
-	if (netif_msg_##type(priv) && net_ratelimit())		\
-		dev_err(priv->dev, format, ## __VA_ARGS__);	\
-} while (0)
-
-#define cpsw_dbg(priv, type, format, ...)		\
-do {								\
-	if (netif_msg_##type(priv) && net_ratelimit())		\
-		dev_dbg(priv->dev, format, ## __VA_ARGS__);	\
-} while (0)
-
-#define cpsw_notice(priv, type, format, ...)		\
-do {								\
-	if (netif_msg_##type(priv) && net_ratelimit())		\
-		dev_notice(priv->dev, format, ## __VA_ARGS__);	\
-} while (0)
-
-#define ALE_ALL_PORTS		0x7
-
-#define CPSW_MAJOR_VERSION(reg)		(reg >> 8 & 0x7)
-#define CPSW_MINOR_VERSION(reg)		(reg & 0xff)
-#define CPSW_RTL_VERSION(reg)		((reg >> 11) & 0x1f)
-
-#define CPSW_VERSION_1		0x19010a
-#define CPSW_VERSION_2		0x19010c
-#define CPSW_VERSION_3		0x19010f
-#define CPSW_VERSION_4		0x190112
-
-#define HOST_PORT_NUM		0
-#define CPSW_ALE_PORTS_NUM	3
-#define SLIVER_SIZE		0x40
-
-#define CPSW1_HOST_PORT_OFFSET	0x028
-#define CPSW1_SLAVE_OFFSET	0x050
-#define CPSW1_SLAVE_SIZE	0x040
-#define CPSW1_CPDMA_OFFSET	0x100
-#define CPSW1_STATERAM_OFFSET	0x200
-#define CPSW1_HW_STATS		0x400
-#define CPSW1_CPTS_OFFSET	0x500
-#define CPSW1_ALE_OFFSET	0x600
-#define CPSW1_SLIVER_OFFSET	0x700
-
-#define CPSW2_HOST_PORT_OFFSET	0x108
-#define CPSW2_SLAVE_OFFSET	0x200
-#define CPSW2_SLAVE_SIZE	0x100
-#define CPSW2_CPDMA_OFFSET	0x800
-#define CPSW2_HW_STATS		0x900
-#define CPSW2_STATERAM_OFFSET	0xa00
-#define CPSW2_CPTS_OFFSET	0xc00
-#define CPSW2_ALE_OFFSET	0xd00
-#define CPSW2_SLIVER_OFFSET	0xd80
-#define CPSW2_BD_OFFSET		0x2000
-
-#define CPDMA_RXTHRESH		0x0c0
-#define CPDMA_RXFREE		0x0e0
-#define CPDMA_TXHDP		0x00
-#define CPDMA_RXHDP		0x20
-#define CPDMA_TXCP		0x40
-#define CPDMA_RXCP		0x60
-
-#define CPSW_POLL_WEIGHT	64
-#define CPSW_RX_VLAN_ENCAP_HDR_SIZE		4
-#define CPSW_MIN_PACKET_SIZE	(VLAN_ETH_ZLEN)
-#define CPSW_MAX_PACKET_SIZE	(VLAN_ETH_FRAME_LEN +\
-				 ETH_FCS_LEN +\
-				 CPSW_RX_VLAN_ENCAP_HDR_SIZE)
-
-#define RX_PRIORITY_MAPPING	0x76543210
-#define TX_PRIORITY_MAPPING	0x33221100
-#define CPDMA_TX_PRIORITY_MAP	0x76543210
-
-#define CPSW_VLAN_AWARE		BIT(1)
-#define CPSW_RX_VLAN_ENCAP	BIT(2)
-#define CPSW_ALE_VLAN_AWARE	1
-
-#define CPSW_FIFO_NORMAL_MODE		(0 << 16)
-#define CPSW_FIFO_DUAL_MAC_MODE		(1 << 16)
-#define CPSW_FIFO_RATE_LIMIT_MODE	(2 << 16)
-
-#define CPSW_INTPACEEN		(0x3f << 16)
-#define CPSW_INTPRESCALE_MASK	(0x7FF << 0)
-#define CPSW_CMINTMAX_CNT	63
-#define CPSW_CMINTMIN_CNT	2
-#define CPSW_CMINTMAX_INTVL	(1000 / CPSW_CMINTMIN_CNT)
-#define CPSW_CMINTMIN_INTVL	((1000 / CPSW_CMINTMAX_CNT) + 1)
-
-#define cpsw_slave_index(cpsw, priv)				\
-		((cpsw->data.dual_emac) ? priv->emac_port :	\
-		cpsw->data.active_slave)
-#define IRQ_NUM			2
-#define CPSW_MAX_QUEUES		8
-#define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256
-#define CPSW_FIFO_QUEUE_TYPE_SHIFT	16
-#define CPSW_FIFO_SHAPE_EN_SHIFT	16
-#define CPSW_FIFO_RATE_EN_SHIFT		20
-#define CPSW_TC_NUM			4
-#define CPSW_FIFO_SHAPERS_NUM		(CPSW_TC_NUM - 1)
-#define CPSW_PCT_MASK			0x7f
-
-#define CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT	29
-#define CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK		GENMASK(2, 0)
-#define CPSW_RX_VLAN_ENCAP_HDR_VID_SHIFT	16
-#define CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_SHIFT	8
-#define CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_MSK	GENMASK(1, 0)
-enum {
-	CPSW_RX_VLAN_ENCAP_HDR_PKT_VLAN_TAG = 0,
-	CPSW_RX_VLAN_ENCAP_HDR_PKT_RESERV,
-	CPSW_RX_VLAN_ENCAP_HDR_PKT_PRIO_TAG,
-	CPSW_RX_VLAN_ENCAP_HDR_PKT_UNTAG,
-};
-
 static int debug_level;
 module_param(debug_level, int, 0);
 MODULE_PARM_DESC(debug_level, "cpsw debug level (NETIF_MSG bits)");
@@ -192,369 +64,10 @@ static int descs_pool_size = CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT;
 module_param(descs_pool_size, int, 0444);
 MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
 
-struct cpsw_wr_regs {
-	u32	id_ver;
-	u32	soft_reset;
-	u32	control;
-	u32	int_control;
-	u32	rx_thresh_en;
-	u32	rx_en;
-	u32	tx_en;
-	u32	misc_en;
-	u32	mem_allign1[8];
-	u32	rx_thresh_stat;
-	u32	rx_stat;
-	u32	tx_stat;
-	u32	misc_stat;
-	u32	mem_allign2[8];
-	u32	rx_imax;
-	u32	tx_imax;
-
-};
-
-struct cpsw_ss_regs {
-	u32	id_ver;
-	u32	control;
-	u32	soft_reset;
-	u32	stat_port_en;
-	u32	ptype;
-	u32	soft_idle;
-	u32	thru_rate;
-	u32	gap_thresh;
-	u32	tx_start_wds;
-	u32	flow_control;
-	u32	vlan_ltype;
-	u32	ts_ltype;
-	u32	dlr_ltype;
-};
-
-/* CPSW_PORT_V1 */
-#define CPSW1_MAX_BLKS      0x00 /* Maximum FIFO Blocks */
-#define CPSW1_BLK_CNT       0x04 /* FIFO Block Usage Count (Read Only) */
-#define CPSW1_TX_IN_CTL     0x08 /* Transmit FIFO Control */
-#define CPSW1_PORT_VLAN     0x0c /* VLAN Register */
-#define CPSW1_TX_PRI_MAP    0x10 /* Tx Header Priority to Switch Pri Mapping */
-#define CPSW1_TS_CTL        0x14 /* Time Sync Control */
-#define CPSW1_TS_SEQ_LTYPE  0x18 /* Time Sync Sequence ID Offset and Msg Type */
-#define CPSW1_TS_VLAN       0x1c /* Time Sync VLAN1 and VLAN2 */
-
-/* CPSW_PORT_V2 */
-#define CPSW2_CONTROL       0x00 /* Control Register */
-#define CPSW2_MAX_BLKS      0x08 /* Maximum FIFO Blocks */
-#define CPSW2_BLK_CNT       0x0c /* FIFO Block Usage Count (Read Only) */
-#define CPSW2_TX_IN_CTL     0x10 /* Transmit FIFO Control */
-#define CPSW2_PORT_VLAN     0x14 /* VLAN Register */
-#define CPSW2_TX_PRI_MAP    0x18 /* Tx Header Priority to Switch Pri Mapping */
-#define CPSW2_TS_SEQ_MTYPE  0x1c /* Time Sync Sequence ID Offset and Msg Type */
-
-/* CPSW_PORT_V1 and V2 */
-#define SA_LO               0x20 /* CPGMAC_SL Source Address Low */
-#define SA_HI               0x24 /* CPGMAC_SL Source Address High */
-#define SEND_PERCENT        0x28 /* Transmit Queue Send Percentages */
-
-/* CPSW_PORT_V2 only */
-#define RX_DSCP_PRI_MAP0    0x30 /* Rx DSCP Priority to Rx Packet Mapping */
-#define RX_DSCP_PRI_MAP1    0x34 /* Rx DSCP Priority to Rx Packet Mapping */
-#define RX_DSCP_PRI_MAP2    0x38 /* Rx DSCP Priority to Rx Packet Mapping */
-#define RX_DSCP_PRI_MAP3    0x3c /* Rx DSCP Priority to Rx Packet Mapping */
-#define RX_DSCP_PRI_MAP4    0x40 /* Rx DSCP Priority to Rx Packet Mapping */
-#define RX_DSCP_PRI_MAP5    0x44 /* Rx DSCP Priority to Rx Packet Mapping */
-#define RX_DSCP_PRI_MAP6    0x48 /* Rx DSCP Priority to Rx Packet Mapping */
-#define RX_DSCP_PRI_MAP7    0x4c /* Rx DSCP Priority to Rx Packet Mapping */
-
-/* Bit definitions for the CPSW2_CONTROL register */
-#define PASS_PRI_TAGGED     BIT(24) /* Pass Priority Tagged */
-#define VLAN_LTYPE2_EN      BIT(21) /* VLAN LTYPE 2 enable */
-#define VLAN_LTYPE1_EN      BIT(20) /* VLAN LTYPE 1 enable */
-#define DSCP_PRI_EN         BIT(16) /* DSCP Priority Enable */
-#define TS_107              BIT(15) /* Tyme Sync Dest IP Address 107 */
-#define TS_320              BIT(14) /* Time Sync Dest Port 320 enable */
-#define TS_319              BIT(13) /* Time Sync Dest Port 319 enable */
-#define TS_132              BIT(12) /* Time Sync Dest IP Addr 132 enable */
-#define TS_131              BIT(11) /* Time Sync Dest IP Addr 131 enable */
-#define TS_130              BIT(10) /* Time Sync Dest IP Addr 130 enable */
-#define TS_129              BIT(9)  /* Time Sync Dest IP Addr 129 enable */
-#define TS_TTL_NONZERO      BIT(8)  /* Time Sync Time To Live Non-zero enable */
-#define TS_ANNEX_F_EN       BIT(6)  /* Time Sync Annex F enable */
-#define TS_ANNEX_D_EN       BIT(4)  /* Time Sync Annex D enable */
-#define TS_LTYPE2_EN        BIT(3)  /* Time Sync LTYPE 2 enable */
-#define TS_LTYPE1_EN        BIT(2)  /* Time Sync LTYPE 1 enable */
-#define TS_TX_EN            BIT(1)  /* Time Sync Transmit Enable */
-#define TS_RX_EN            BIT(0)  /* Time Sync Receive Enable */
-
-#define CTRL_V2_TS_BITS \
-	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
-	 TS_TTL_NONZERO  | TS_ANNEX_D_EN | TS_LTYPE1_EN | VLAN_LTYPE1_EN)
-
-#define CTRL_V2_ALL_TS_MASK (CTRL_V2_TS_BITS | TS_TX_EN | TS_RX_EN)
-#define CTRL_V2_TX_TS_BITS  (CTRL_V2_TS_BITS | TS_TX_EN)
-#define CTRL_V2_RX_TS_BITS  (CTRL_V2_TS_BITS | TS_RX_EN)
-
-
-#define CTRL_V3_TS_BITS \
-	(TS_107 | TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
-	 TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
-	 TS_LTYPE1_EN | VLAN_LTYPE1_EN)
-
-#define CTRL_V3_ALL_TS_MASK (CTRL_V3_TS_BITS | TS_TX_EN | TS_RX_EN)
-#define CTRL_V3_TX_TS_BITS  (CTRL_V3_TS_BITS | TS_TX_EN)
-#define CTRL_V3_RX_TS_BITS  (CTRL_V3_TS_BITS | TS_RX_EN)
-
-/* Bit definitions for the CPSW2_TS_SEQ_MTYPE register */
-#define TS_SEQ_ID_OFFSET_SHIFT   (16)    /* Time Sync Sequence ID Offset */
-#define TS_SEQ_ID_OFFSET_MASK    (0x3f)
-#define TS_MSG_TYPE_EN_SHIFT     (0)     /* Time Sync Message Type Enable */
-#define TS_MSG_TYPE_EN_MASK      (0xffff)
-
-/* The PTP event messages - Sync, Delay_Req, Pdelay_Req, and Pdelay_Resp. */
-#define EVENT_MSG_BITS ((1<<0) | (1<<1) | (1<<2) | (1<<3))
-
-/* Bit definitions for the CPSW1_TS_CTL register */
-#define CPSW_V1_TS_RX_EN		BIT(0)
-#define CPSW_V1_TS_TX_EN		BIT(4)
-#define CPSW_V1_MSG_TYPE_OFS		16
-
-/* Bit definitions for the CPSW1_TS_SEQ_LTYPE register */
-#define CPSW_V1_SEQ_ID_OFS_SHIFT	16
-
-#define CPSW_MAX_BLKS_TX		15
-#define CPSW_MAX_BLKS_TX_SHIFT		4
-#define CPSW_MAX_BLKS_RX		5
-
-struct cpsw_host_regs {
-	u32	max_blks;
-	u32	blk_cnt;
-	u32	tx_in_ctl;
-	u32	port_vlan;
-	u32	tx_pri_map;
-	u32	cpdma_tx_pri_map;
-	u32	cpdma_rx_chan_map;
-};
-
-struct cpsw_sliver_regs {
-	u32	id_ver;
-	u32	mac_control;
-	u32	mac_status;
-	u32	soft_reset;
-	u32	rx_maxlen;
-	u32	__reserved_0;
-	u32	rx_pause;
-	u32	tx_pause;
-	u32	__reserved_1;
-	u32	rx_pri_map;
-};
-
-struct cpsw_hw_stats {
-	u32	rxgoodframes;
-	u32	rxbroadcastframes;
-	u32	rxmulticastframes;
-	u32	rxpauseframes;
-	u32	rxcrcerrors;
-	u32	rxaligncodeerrors;
-	u32	rxoversizedframes;
-	u32	rxjabberframes;
-	u32	rxundersizedframes;
-	u32	rxfragments;
-	u32	__pad_0[2];
-	u32	rxoctets;
-	u32	txgoodframes;
-	u32	txbroadcastframes;
-	u32	txmulticastframes;
-	u32	txpauseframes;
-	u32	txdeferredframes;
-	u32	txcollisionframes;
-	u32	txsinglecollframes;
-	u32	txmultcollframes;
-	u32	txexcessivecollisions;
-	u32	txlatecollisions;
-	u32	txunderrun;
-	u32	txcarriersenseerrors;
-	u32	txoctets;
-	u32	octetframes64;
-	u32	octetframes65t127;
-	u32	octetframes128t255;
-	u32	octetframes256t511;
-	u32	octetframes512t1023;
-	u32	octetframes1024tup;
-	u32	netoctets;
-	u32	rxsofoverruns;
-	u32	rxmofoverruns;
-	u32	rxdmaoverruns;
-};
-
-struct cpsw_slave_data {
-	struct device_node *phy_node;
-	char		phy_id[MII_BUS_ID_SIZE];
-	int		phy_if;
-	u8		mac_addr[ETH_ALEN];
-	u16		dual_emac_res_vlan;	/* Reserved VLAN for DualEMAC */
-	struct phy	*ifphy;
-};
-
-struct cpsw_platform_data {
-	struct cpsw_slave_data	*slave_data;
-	u32	ss_reg_ofs;	/* Subsystem control register offset */
-	u32	channels;	/* number of cpdma channels (symmetric) */
-	u32	slaves;		/* number of slave cpgmac ports */
-	u32	active_slave; /* time stamping, ethtool and SIOCGMIIPHY slave */
-	u32	ale_entries;	/* ale table size */
-	u32	bd_ram_size;  /*buffer descriptor ram size */
-	u32	mac_control;	/* Mac control register */
-	u16	default_vlan;	/* Def VLAN for ALE lookup in VLAN aware mode*/
-	bool	dual_emac;	/* Enable Dual EMAC mode */
-};
-
-struct cpsw_slave {
-	void __iomem			*regs;
-	struct cpsw_sliver_regs __iomem	*sliver;
-	int				slave_num;
-	u32				mac_control;
-	struct cpsw_slave_data		*data;
-	struct phy_device		*phy;
-	struct net_device		*ndev;
-	u32				port_vlan;
-};
-
-static inline u32 slave_read(struct cpsw_slave *slave, u32 offset)
-{
-	return readl_relaxed(slave->regs + offset);
-}
+/* The buf includes headroom compatible with both skb and xdpf */
+#define CPSW_HEADROOM_NA (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN)
+#define CPSW_HEADROOM  ALIGN(CPSW_HEADROOM_NA, sizeof(long))
 
-static inline void slave_write(struct cpsw_slave *slave, u32 val, u32 offset)
-{
-	writel_relaxed(val, slave->regs + offset);
-}
-
-struct cpsw_vector {
-	struct cpdma_chan *ch;
-	int budget;
-};
-
-struct cpsw_common {
-	struct device			*dev;
-	struct cpsw_platform_data	data;
-	struct napi_struct		napi_rx;
-	struct napi_struct		napi_tx;
-	struct cpsw_ss_regs __iomem	*regs;
-	struct cpsw_wr_regs __iomem	*wr_regs;
-	u8 __iomem			*hw_stats;
-	struct cpsw_host_regs __iomem	*host_port_regs;
-	u32				version;
-	u32				coal_intvl;
-	u32				bus_freq_mhz;
-	int				rx_packet_max;
-	struct cpsw_slave		*slaves;
-	struct cpdma_ctlr		*dma;
-	struct cpsw_vector		txv[CPSW_MAX_QUEUES];
-	struct cpsw_vector		rxv[CPSW_MAX_QUEUES];
-	struct cpsw_ale			*ale;
-	bool				quirk_irq;
-	bool				rx_irq_disabled;
-	bool				tx_irq_disabled;
-	u32 irqs_table[IRQ_NUM];
-	struct cpts			*cpts;
-	int				rx_ch_num, tx_ch_num;
-	int				speed;
-	int				usage_count;
-};
-
-struct cpsw_priv {
-	struct net_device		*ndev;
-	struct device			*dev;
-	u32				msg_enable;
-	u8				mac_addr[ETH_ALEN];
-	bool				rx_pause;
-	bool				tx_pause;
-	bool				mqprio_hw;
-	int				fifo_bw[CPSW_TC_NUM];
-	int				shp_cfg_speed;
-	int				tx_ts_enabled;
-	int				rx_ts_enabled;
-	u32 emac_port;
-	struct cpsw_common *cpsw;
-};
-
-struct cpsw_stats {
-	char stat_string[ETH_GSTRING_LEN];
-	int type;
-	int sizeof_stat;
-	int stat_offset;
-};
-
-enum {
-	CPSW_STATS,
-	CPDMA_RX_STATS,
-	CPDMA_TX_STATS,
-};
-
-#define CPSW_STAT(m)		CPSW_STATS,				\
-				FIELD_SIZEOF(struct cpsw_hw_stats, m), \
-				offsetof(struct cpsw_hw_stats, m)
-#define CPDMA_RX_STAT(m)	CPDMA_RX_STATS,				   \
-				FIELD_SIZEOF(struct cpdma_chan_stats, m), \
-				offsetof(struct cpdma_chan_stats, m)
-#define CPDMA_TX_STAT(m)	CPDMA_TX_STATS,				   \
-				FIELD_SIZEOF(struct cpdma_chan_stats, m), \
-				offsetof(struct cpdma_chan_stats, m)
-
-static const struct cpsw_stats cpsw_gstrings_stats[] = {
-	{ "Good Rx Frames", CPSW_STAT(rxgoodframes) },
-	{ "Broadcast Rx Frames", CPSW_STAT(rxbroadcastframes) },
-	{ "Multicast Rx Frames", CPSW_STAT(rxmulticastframes) },
-	{ "Pause Rx Frames", CPSW_STAT(rxpauseframes) },
-	{ "Rx CRC Errors", CPSW_STAT(rxcrcerrors) },
-	{ "Rx Align/Code Errors", CPSW_STAT(rxaligncodeerrors) },
-	{ "Oversize Rx Frames", CPSW_STAT(rxoversizedframes) },
-	{ "Rx Jabbers", CPSW_STAT(rxjabberframes) },
-	{ "Undersize (Short) Rx Frames", CPSW_STAT(rxundersizedframes) },
-	{ "Rx Fragments", CPSW_STAT(rxfragments) },
-	{ "Rx Octets", CPSW_STAT(rxoctets) },
-	{ "Good Tx Frames", CPSW_STAT(txgoodframes) },
-	{ "Broadcast Tx Frames", CPSW_STAT(txbroadcastframes) },
-	{ "Multicast Tx Frames", CPSW_STAT(txmulticastframes) },
-	{ "Pause Tx Frames", CPSW_STAT(txpauseframes) },
-	{ "Deferred Tx Frames", CPSW_STAT(txdeferredframes) },
-	{ "Collisions", CPSW_STAT(txcollisionframes) },
-	{ "Single Collision Tx Frames", CPSW_STAT(txsinglecollframes) },
-	{ "Multiple Collision Tx Frames", CPSW_STAT(txmultcollframes) },
-	{ "Excessive Collisions", CPSW_STAT(txexcessivecollisions) },
-	{ "Late Collisions", CPSW_STAT(txlatecollisions) },
-	{ "Tx Underrun", CPSW_STAT(txunderrun) },
-	{ "Carrier Sense Errors", CPSW_STAT(txcarriersenseerrors) },
-	{ "Tx Octets", CPSW_STAT(txoctets) },
-	{ "Rx + Tx 64 Octet Frames", CPSW_STAT(octetframes64) },
-	{ "Rx + Tx 65-127 Octet Frames", CPSW_STAT(octetframes65t127) },
-	{ "Rx + Tx 128-255 Octet Frames", CPSW_STAT(octetframes128t255) },
-	{ "Rx + Tx 256-511 Octet Frames", CPSW_STAT(octetframes256t511) },
-	{ "Rx + Tx 512-1023 Octet Frames", CPSW_STAT(octetframes512t1023) },
-	{ "Rx + Tx 1024-Up Octet Frames", CPSW_STAT(octetframes1024tup) },
-	{ "Net Octets", CPSW_STAT(netoctets) },
-	{ "Rx Start of Frame Overruns", CPSW_STAT(rxsofoverruns) },
-	{ "Rx Middle of Frame Overruns", CPSW_STAT(rxmofoverruns) },
-	{ "Rx DMA Overruns", CPSW_STAT(rxdmaoverruns) },
-};
-
-static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
-	{ "head_enqueue", CPDMA_RX_STAT(head_enqueue) },
-	{ "tail_enqueue", CPDMA_RX_STAT(tail_enqueue) },
-	{ "pad_enqueue", CPDMA_RX_STAT(pad_enqueue) },
-	{ "misqueued", CPDMA_RX_STAT(misqueued) },
-	{ "desc_alloc_fail", CPDMA_RX_STAT(desc_alloc_fail) },
-	{ "pad_alloc_fail", CPDMA_RX_STAT(pad_alloc_fail) },
-	{ "runt_receive_buf", CPDMA_RX_STAT(runt_receive_buff) },
-	{ "runt_transmit_buf", CPDMA_RX_STAT(runt_transmit_buff) },
-	{ "empty_dequeue", CPDMA_RX_STAT(empty_dequeue) },
-	{ "busy_dequeue", CPDMA_RX_STAT(busy_dequeue) },
-	{ "good_dequeue", CPDMA_RX_STAT(good_dequeue) },
-	{ "requeue", CPDMA_RX_STAT(requeue) },
-	{ "teardown_dequeue", CPDMA_RX_STAT(teardown_dequeue) },
-};
-
-#define CPSW_STATS_COMMON_LEN	ARRAY_SIZE(cpsw_gstrings_stats)
-#define CPSW_STATS_CH_LEN	ARRAY_SIZE(cpsw_gstrings_ch_stats)
-
-#define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw)
-#define napi_to_cpsw(napi)	container_of(napi, struct cpsw_common, napi)
 #define for_each_slave(priv, func, arg...)				\
 	do {								\
 		struct cpsw_slave *slave;				\
@@ -569,14 +82,14 @@ static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
 				(func)(slave++, ##arg);			\
 	} while (0)
 
+#define CPSW_XMETA_OFFSET	ALIGN(sizeof(struct xdp_frame), sizeof(long))
+
+#define CPSW_XDP_CONSUMED		1
+#define CPSW_XDP_PASS			0
+
 static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
 				    __be16 proto, u16 vid);
 
-static inline int cpsw_get_slave_port(u32 slave_num)
-{
-	return slave_num + 1;
-}
-
 static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
@@ -653,13 +166,6 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 	}
 }
 
-struct addr_sync_ctx {
-	struct net_device *ndev;
-	const u8 *addr;		/* address to be synched */
-	int consumed;		/* number of address instances */
-	int flush;		/* flush flag */
-};
-
 /**
  * cpsw_set_mc - adds multicast entry to the table if it's not added or deletes
  * if it's not deleted
@@ -800,12 +306,17 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num)
 
 static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 {
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_port = -1;
+
+	if (cpsw->data.dual_emac)
+		slave_port = priv->emac_port + 1;
 
 	if (ndev->flags & IFF_PROMISC) {
 		/* Enable promiscuous mode */
 		cpsw_set_promiscious(ndev, true);
-		cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI);
+		cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, slave_port);
 		return;
 	} else {
 		/* Disable promiscuous mode */
@@ -813,14 +324,15 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 	}
 
 	/* Restore allmulti on vlans if necessary */
-	cpsw_ale_set_allmulti(cpsw->ale, ndev->flags & IFF_ALLMULTI);
+	cpsw_ale_set_allmulti(cpsw->ale,
+			      ndev->flags & IFF_ALLMULTI, slave_port);
 
 	/* add/remove mcast address either for real netdev or for vlan */
 	__hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr,
 			       cpsw_del_mc_addr);
 }
 
-static void cpsw_intr_enable(struct cpsw_common *cpsw)
+void cpsw_intr_enable(struct cpsw_common *cpsw)
 {
 	writel_relaxed(0xFF, &cpsw->wr_regs->tx_en);
 	writel_relaxed(0xFF, &cpsw->wr_regs->rx_en);
@@ -829,7 +341,7 @@ static void cpsw_intr_enable(struct cpsw_common *cpsw)
 	return;
 }
 
-static void cpsw_intr_disable(struct cpsw_common *cpsw)
+void cpsw_intr_disable(struct cpsw_common *cpsw)
 {
 	writel_relaxed(0, &cpsw->wr_regs->tx_en);
 	writel_relaxed(0, &cpsw->wr_regs->rx_en);
@@ -838,24 +350,58 @@ static void cpsw_intr_disable(struct cpsw_common *cpsw)
 	return;
 }
 
-static void cpsw_tx_handler(void *token, int len, int status)
+static int cpsw_is_xdpf_handle(void *handle)
+{
+	return (unsigned long)handle & BIT(0);
+}
+
+static void *cpsw_xdpf_to_handle(struct xdp_frame *xdpf)
 {
+	return (void *)((unsigned long)xdpf | BIT(0));
+}
+
+static struct xdp_frame *cpsw_handle_to_xdpf(void *handle)
+{
+	return (struct xdp_frame *)((unsigned long)handle & ~BIT(0));
+}
+
+struct __aligned(sizeof(long)) cpsw_meta_xdp {
+	struct net_device *ndev;
+	int ch;
+};
+
+void cpsw_tx_handler(void *token, int len, int status)
+{
+	struct cpsw_meta_xdp	*xmeta;
+	struct xdp_frame	*xdpf;
+	struct net_device	*ndev;
 	struct netdev_queue	*txq;
-	struct sk_buff		*skb = token;
-	struct net_device	*ndev = skb->dev;
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct sk_buff		*skb;
+	int			ch;
+
+	if (cpsw_is_xdpf_handle(token)) {
+		xdpf = cpsw_handle_to_xdpf(token);
+		xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+		ndev = xmeta->ndev;
+		ch = xmeta->ch;
+		xdp_return_frame(xdpf);
+	} else {
+		skb = token;
+		ndev = skb->dev;
+		ch = skb_get_queue_mapping(skb);
+		cpts_tx_timestamp(ndev_to_cpsw(ndev)->cpts, skb);
+		dev_kfree_skb_any(skb);
+	}
 
 	/* Check whether the queue is stopped due to stalled tx dma, if the
 	 * queue is stopped then start the queue as we have free desc for tx
 	 */
-	txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
+	txq = netdev_get_tx_queue(ndev, ch);
 	if (unlikely(netif_tx_queue_stopped(txq)))
 		netif_tx_wake_queue(txq);
 
-	cpts_tx_timestamp(cpsw->cpts, skb);
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += len;
-	dev_kfree_skb_any(skb);
 }
 
 static void cpsw_rx_vlan_encap(struct sk_buff *skb)
@@ -901,24 +447,252 @@ static void cpsw_rx_vlan_encap(struct sk_buff *skb)
 	}
 }
 
+static int cpsw_xdp_tx_frame(struct cpsw_priv *priv, struct xdp_frame *xdpf,
+			     struct page *page)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_meta_xdp *xmeta;
+	struct cpdma_chan *txch;
+	dma_addr_t dma;
+	int ret, port;
+
+	xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+	xmeta->ndev = priv->ndev;
+	xmeta->ch = 0;
+	txch = cpsw->txv[0].ch;
+
+	port = priv->emac_port + cpsw->data.dual_emac;
+	if (page) {
+		dma = page_pool_get_dma_addr(page);
+		dma += xdpf->headroom + sizeof(struct xdp_frame);
+		ret = cpdma_chan_submit_mapped(txch, cpsw_xdpf_to_handle(xdpf),
+					       dma, xdpf->len, port);
+	} else {
+		if (sizeof(*xmeta) > xdpf->headroom) {
+			xdp_return_frame_rx_napi(xdpf);
+			return -EINVAL;
+		}
+
+		ret = cpdma_chan_submit(txch, cpsw_xdpf_to_handle(xdpf),
+					xdpf->data, xdpf->len, port);
+	}
+
+	if (ret) {
+		priv->ndev->stats.tx_dropped++;
+		xdp_return_frame_rx_napi(xdpf);
+	}
+
+	return ret;
+}
+
+static int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
+			struct page *page)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct net_device *ndev = priv->ndev;
+	int ret = CPSW_XDP_CONSUMED;
+	struct xdp_frame *xdpf;
+	struct bpf_prog *prog;
+	u32 act;
+
+	rcu_read_lock();
+
+	prog = READ_ONCE(priv->xdp_prog);
+	if (!prog) {
+		ret = CPSW_XDP_PASS;
+		goto out;
+	}
+
+	act = bpf_prog_run_xdp(prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		ret = CPSW_XDP_PASS;
+		break;
+	case XDP_TX:
+		xdpf = convert_to_xdp_frame(xdp);
+		if (unlikely(!xdpf))
+			goto drop;
+
+		cpsw_xdp_tx_frame(priv, xdpf, page);
+		break;
+	case XDP_REDIRECT:
+		if (xdp_do_redirect(ndev, xdp, prog))
+			goto drop;
+
+		/*  Have to flush here, per packet, instead of doing it in bulk
+		 *  at the end of the napi handler. The RX devices on this
+		 *  particular hardware is sharing a common queue, so the
+		 *  incoming device might change per packet.
+		 */
+		xdp_do_flush_map();
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(ndev, prog, act);
+		/* fall through -- handle aborts by dropping packet */
+	case XDP_DROP:
+		goto drop;
+	}
+out:
+	rcu_read_unlock();
+	return ret;
+drop:
+	rcu_read_unlock();
+	page_pool_recycle_direct(cpsw->page_pool[ch], page);
+	return ret;
+}
+
+static unsigned int cpsw_rxbuf_total_len(unsigned int len)
+{
+	len += CPSW_HEADROOM;
+	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	return SKB_DATA_ALIGN(len);
+}
+
+static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw,
+					       int size)
+{
+	struct page_pool_params pp_params;
+	struct page_pool *pool;
+
+	pp_params.order = 0;
+	pp_params.flags = PP_FLAG_DMA_MAP;
+	pp_params.pool_size = size;
+	pp_params.nid = NUMA_NO_NODE;
+	pp_params.dma_dir = DMA_BIDIRECTIONAL;
+	pp_params.dev = cpsw->dev;
+
+	pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool))
+		dev_err(cpsw->dev, "cannot create rx page pool\n");
+
+	return pool;
+}
+
+static int cpsw_ndev_create_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct xdp_rxq_info *rxq;
+	struct page_pool *pool;
+	int ret;
+
+	pool = cpsw->page_pool[ch];
+	rxq = &priv->xdp_rxq[ch];
+
+	ret = xdp_rxq_info_reg(rxq, priv->ndev, ch);
+	if (ret)
+		return ret;
+
+	ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
+	if (ret)
+		xdp_rxq_info_unreg(rxq);
+
+	return ret;
+}
+
+static void cpsw_ndev_destroy_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+	struct xdp_rxq_info *rxq = &priv->xdp_rxq[ch];
+
+	if (!xdp_rxq_info_is_reg(rxq))
+		return;
+
+	xdp_rxq_info_unreg(rxq);
+}
+
+static int cpsw_create_rx_pool(struct cpsw_common *cpsw, int ch)
+{
+	struct page_pool *pool;
+	int ret = 0, pool_size;
+
+	pool_size = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
+	pool = cpsw_create_page_pool(cpsw, pool_size);
+	if (IS_ERR(pool))
+		ret = PTR_ERR(pool);
+	else
+		cpsw->page_pool[ch] = pool;
+
+	return ret;
+}
+
+void cpsw_destroy_xdp_rxqs(struct cpsw_common *cpsw)
+{
+	struct net_device *ndev;
+	int i, ch;
+
+	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		for (i = 0; i < cpsw->data.slaves; i++) {
+			ndev = cpsw->slaves[i].ndev;
+			if (!ndev)
+				continue;
+
+			cpsw_ndev_destroy_xdp_rxq(netdev_priv(ndev), ch);
+		}
+
+		page_pool_destroy(cpsw->page_pool[ch]);
+		cpsw->page_pool[ch] = NULL;
+	}
+}
+
+int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw)
+{
+	struct net_device *ndev;
+	int i, ch, ret;
+
+	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		ret = cpsw_create_rx_pool(cpsw, ch);
+		if (ret)
+			goto err_cleanup;
+
+		/* using same page pool is allowed as no running rx handlers
+		 * simultaneously for both ndevs
+		 */
+		for (i = 0; i < cpsw->data.slaves; i++) {
+			ndev = cpsw->slaves[i].ndev;
+			if (!ndev)
+				continue;
+
+			ret = cpsw_ndev_create_xdp_rxq(netdev_priv(ndev), ch);
+			if (ret)
+				goto err_cleanup;
+		}
+	}
+
+	return 0;
+
+err_cleanup:
+	cpsw_destroy_xdp_rxqs(cpsw);
+
+	return ret;
+}
+
 static void cpsw_rx_handler(void *token, int len, int status)
 {
-	struct cpdma_chan	*ch;
-	struct sk_buff		*skb = token;
-	struct sk_buff		*new_skb;
-	struct net_device	*ndev = skb->dev;
-	int			ret = 0, port;
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct page		*new_page, *page = token;
+	void			*pa = page_address(page);
+	struct cpsw_meta_xdp	*xmeta = pa + CPSW_XMETA_OFFSET;
+	struct cpsw_common	*cpsw = ndev_to_cpsw(xmeta->ndev);
+	int			pkt_size = cpsw->rx_packet_max;
+	int			ret = 0, port, ch = xmeta->ch;
+	int			headroom = CPSW_HEADROOM;
+	struct net_device	*ndev = xmeta->ndev;
 	struct cpsw_priv	*priv;
+	struct page_pool	*pool;
+	struct sk_buff		*skb;
+	struct xdp_buff		xdp;
+	dma_addr_t		dma;
 
-	if (cpsw->data.dual_emac) {
+	if (cpsw->data.dual_emac && status >= 0) {
 		port = CPDMA_RX_SOURCE_PORT(status);
-		if (port) {
+		if (port)
 			ndev = cpsw->slaves[--port].ndev;
-			skb->dev = ndev;
-		}
 	}
 
+	priv = netdev_priv(ndev);
+	pool = cpsw->page_pool[ch];
 	if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
 		/* In dual emac mode check for all interfaces */
 		if (cpsw->data.dual_emac && cpsw->usage_count &&
@@ -927,54 +701,93 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			 * is already down and the other interface is up
 			 * and running, instead of freeing which results
 			 * in reducing of the number of rx descriptor in
-			 * DMA engine, requeue skb back to cpdma.
+			 * DMA engine, requeue page back to cpdma.
 			 */
-			new_skb = skb;
+			new_page = page;
 			goto requeue;
 		}
 
-		/* the interface is going down, skbs are purged */
-		dev_kfree_skb_any(skb);
+		/* the interface is going down, pages are purged */
+		page_pool_recycle_direct(pool, page);
 		return;
 	}
 
-	new_skb = netdev_alloc_skb_ip_align(ndev, cpsw->rx_packet_max);
-	if (new_skb) {
-		skb_copy_queue_mapping(new_skb, skb);
-		skb_put(skb, len);
-		if (status & CPDMA_RX_VLAN_ENCAP)
-			cpsw_rx_vlan_encap(skb);
-		priv = netdev_priv(ndev);
-		if (priv->rx_ts_enabled)
-			cpts_rx_timestamp(cpsw->cpts, skb);
-		skb->protocol = eth_type_trans(skb, ndev);
-		netif_receive_skb(skb);
-		ndev->stats.rx_bytes += len;
-		ndev->stats.rx_packets++;
-		kmemleak_not_leak(new_skb);
-	} else {
+	new_page = page_pool_dev_alloc_pages(pool);
+	if (unlikely(!new_page)) {
+		new_page = page;
 		ndev->stats.rx_dropped++;
-		new_skb = skb;
+		goto requeue;
 	}
 
-requeue:
-	if (netif_dormant(ndev)) {
-		dev_kfree_skb_any(new_skb);
-		return;
+	if (priv->xdp_prog) {
+		if (status & CPDMA_RX_VLAN_ENCAP) {
+			xdp.data = pa + CPSW_HEADROOM +
+				   CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+			xdp.data_end = xdp.data + len -
+				       CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+		} else {
+			xdp.data = pa + CPSW_HEADROOM;
+			xdp.data_end = xdp.data + len;
+		}
+
+		xdp_set_data_meta_invalid(&xdp);
+
+		xdp.data_hard_start = pa;
+		xdp.rxq = &priv->xdp_rxq[ch];
+
+		ret = cpsw_run_xdp(priv, ch, &xdp, page);
+		if (ret != CPSW_XDP_PASS)
+			goto requeue;
+
+		/* XDP prog might have changed packet data and boundaries */
+		len = xdp.data_end - xdp.data;
+		headroom = xdp.data - xdp.data_hard_start;
+
+		/* XDP prog can modify vlan tag, so can't use encap header */
+		status &= ~CPDMA_RX_VLAN_ENCAP;
+	}
+
+	/* pass skb to netstack if no XDP prog or returned XDP_PASS */
+	skb = build_skb(pa, cpsw_rxbuf_total_len(pkt_size));
+	if (!skb) {
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(pool, page);
+		goto requeue;
 	}
 
-	ch = cpsw->rxv[skb_get_queue_mapping(new_skb)].ch;
-	ret = cpdma_chan_submit(ch, new_skb, new_skb->data,
-				skb_tailroom(new_skb), 0);
-	if (WARN_ON(ret < 0))
-		dev_kfree_skb_any(new_skb);
+	skb_reserve(skb, headroom);
+	skb_put(skb, len);
+	skb->dev = ndev;
+	if (status & CPDMA_RX_VLAN_ENCAP)
+		cpsw_rx_vlan_encap(skb);
+	if (priv->rx_ts_enabled)
+		cpts_rx_timestamp(cpsw->cpts, skb);
+	skb->protocol = eth_type_trans(skb, ndev);
+
+	/* unmap page as no netstack skb page recycling */
+	page_pool_release_page(pool, page);
+	netif_receive_skb(skb);
+
+	ndev->stats.rx_bytes += len;
+	ndev->stats.rx_packets++;
+
+requeue:
+	xmeta = page_address(new_page) + CPSW_XMETA_OFFSET;
+	xmeta->ndev = ndev;
+	xmeta->ch = ch;
+
+	dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+	ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
+				       pkt_size, 0);
+	if (ret < 0) {
+		WARN_ON(ret == -ENOMEM);
+		page_pool_recycle_direct(pool, new_page);
+	}
 }
 
-static void cpsw_split_res(struct net_device *ndev)
+void cpsw_split_res(struct cpsw_common *cpsw)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
 	u32 consumed_rate = 0, bigest_rate = 0;
-	struct cpsw_common *cpsw = priv->cpsw;
 	struct cpsw_vector *txv = cpsw->txv;
 	int i, ch_weight, rlim_ch_num = 0;
 	int budget, bigest_rate_ch = 0;
@@ -1254,29 +1067,32 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 	slave_port = cpsw_get_slave_port(slave->slave_num);
 
 	if (phy->link) {
-		mac_control = cpsw->data.mac_control;
-
-		/* enable forwarding */
-		cpsw_ale_control_set(cpsw->ale, slave_port,
-				     ALE_PORT_STATE, ALE_PORT_STATE_FORWARD);
+		mac_control = CPSW_SL_CTL_GMII_EN;
 
 		if (phy->speed == 1000)
-			mac_control |= BIT(7);	/* GIGABITEN	*/
+			mac_control |= CPSW_SL_CTL_GIG;
 		if (phy->duplex)
-			mac_control |= BIT(0);	/* FULLDUPLEXEN	*/
+			mac_control |= CPSW_SL_CTL_FULLDUPLEX;
 
 		/* set speed_in input in case RMII mode is used in 100Mbps */
 		if (phy->speed == 100)
-			mac_control |= BIT(15);
+			mac_control |= CPSW_SL_CTL_IFCTL_A;
 		/* in band mode only works in 10Mbps RGMII mode */
 		else if ((phy->speed == 10) && phy_interface_is_rgmii(phy))
-			mac_control |= BIT(18); /* In Band mode */
+			mac_control |= CPSW_SL_CTL_EXT_EN; /* In Band mode */
 
 		if (priv->rx_pause)
-			mac_control |= BIT(3);
+			mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
 
 		if (priv->tx_pause)
-			mac_control |= BIT(4);
+			mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
+
+		if (mac_control != slave->mac_control)
+			cpsw_sl_ctl_set(slave->mac_sl, mac_control);
+
+		/* enable forwarding */
+		cpsw_ale_control_set(cpsw->ale, slave_port,
+				     ALE_PORT_STATE, ALE_PORT_STATE_FORWARD);
 
 		*link = true;
 
@@ -1290,12 +1106,14 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 		/* disable forwarding */
 		cpsw_ale_control_set(cpsw->ale, slave_port,
 				     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
+
+		cpsw_sl_wait_for_idle(slave->mac_sl, 100);
+
+		cpsw_sl_ctl_reset(slave->mac_sl);
 	}
 
-	if (mac_control != slave->mac_control) {
+	if (mac_control != slave->mac_control)
 		phy_print_status(phy);
-		writel_relaxed(mac_control, &slave->sliver->mac_control);
-	}
 
 	slave->mac_control = mac_control;
 }
@@ -1348,7 +1166,7 @@ static void cpsw_adjust_link(struct net_device *ndev)
 
 	if (link) {
 		if (cpsw_need_resplit(cpsw))
-			cpsw_split_res(ndev);
+			cpsw_split_res(cpsw);
 
 		netif_carrier_on(ndev);
 		if (netif_running(ndev))
@@ -1359,167 +1177,6 @@ static void cpsw_adjust_link(struct net_device *ndev)
 	}
 }
 
-static int cpsw_get_coalesce(struct net_device *ndev,
-				struct ethtool_coalesce *coal)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-
-	coal->rx_coalesce_usecs = cpsw->coal_intvl;
-	return 0;
-}
-
-static int cpsw_set_coalesce(struct net_device *ndev,
-				struct ethtool_coalesce *coal)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	u32 int_ctrl;
-	u32 num_interrupts = 0;
-	u32 prescale = 0;
-	u32 addnl_dvdr = 1;
-	u32 coal_intvl = 0;
-	struct cpsw_common *cpsw = priv->cpsw;
-
-	coal_intvl = coal->rx_coalesce_usecs;
-
-	int_ctrl =  readl(&cpsw->wr_regs->int_control);
-	prescale = cpsw->bus_freq_mhz * 4;
-
-	if (!coal->rx_coalesce_usecs) {
-		int_ctrl &= ~(CPSW_INTPRESCALE_MASK | CPSW_INTPACEEN);
-		goto update_return;
-	}
-
-	if (coal_intvl < CPSW_CMINTMIN_INTVL)
-		coal_intvl = CPSW_CMINTMIN_INTVL;
-
-	if (coal_intvl > CPSW_CMINTMAX_INTVL) {
-		/* Interrupt pacer works with 4us Pulse, we can
-		 * throttle further by dilating the 4us pulse.
-		 */
-		addnl_dvdr = CPSW_INTPRESCALE_MASK / prescale;
-
-		if (addnl_dvdr > 1) {
-			prescale *= addnl_dvdr;
-			if (coal_intvl > (CPSW_CMINTMAX_INTVL * addnl_dvdr))
-				coal_intvl = (CPSW_CMINTMAX_INTVL
-						* addnl_dvdr);
-		} else {
-			addnl_dvdr = 1;
-			coal_intvl = CPSW_CMINTMAX_INTVL;
-		}
-	}
-
-	num_interrupts = (1000 * addnl_dvdr) / coal_intvl;
-	writel(num_interrupts, &cpsw->wr_regs->rx_imax);
-	writel(num_interrupts, &cpsw->wr_regs->tx_imax);
-
-	int_ctrl |= CPSW_INTPACEEN;
-	int_ctrl &= (~CPSW_INTPRESCALE_MASK);
-	int_ctrl |= (prescale & CPSW_INTPRESCALE_MASK);
-
-update_return:
-	writel(int_ctrl, &cpsw->wr_regs->int_control);
-
-	cpsw_notice(priv, timer, "Set coalesce to %d usecs.\n", coal_intvl);
-	cpsw->coal_intvl = coal_intvl;
-
-	return 0;
-}
-
-static int cpsw_get_sset_count(struct net_device *ndev, int sset)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-
-	switch (sset) {
-	case ETH_SS_STATS:
-		return (CPSW_STATS_COMMON_LEN +
-		       (cpsw->rx_ch_num + cpsw->tx_ch_num) *
-		       CPSW_STATS_CH_LEN);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static void cpsw_add_ch_strings(u8 **p, int ch_num, int rx_dir)
-{
-	int ch_stats_len;
-	int line;
-	int i;
-
-	ch_stats_len = CPSW_STATS_CH_LEN * ch_num;
-	for (i = 0; i < ch_stats_len; i++) {
-		line = i % CPSW_STATS_CH_LEN;
-		snprintf(*p, ETH_GSTRING_LEN,
-			 "%s DMA chan %ld: %s", rx_dir ? "Rx" : "Tx",
-			 (long)(i / CPSW_STATS_CH_LEN),
-			 cpsw_gstrings_ch_stats[line].stat_string);
-		*p += ETH_GSTRING_LEN;
-	}
-}
-
-static void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	u8 *p = data;
-	int i;
-
-	switch (stringset) {
-	case ETH_SS_STATS:
-		for (i = 0; i < CPSW_STATS_COMMON_LEN; i++) {
-			memcpy(p, cpsw_gstrings_stats[i].stat_string,
-			       ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
-
-		cpsw_add_ch_strings(&p, cpsw->rx_ch_num, 1);
-		cpsw_add_ch_strings(&p, cpsw->tx_ch_num, 0);
-		break;
-	}
-}
-
-static void cpsw_get_ethtool_stats(struct net_device *ndev,
-				    struct ethtool_stats *stats, u64 *data)
-{
-	u8 *p;
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	struct cpdma_chan_stats ch_stats;
-	int i, l, ch;
-
-	/* Collect Davinci CPDMA stats for Rx and Tx Channel */
-	for (l = 0; l < CPSW_STATS_COMMON_LEN; l++)
-		data[l] = readl(cpsw->hw_stats +
-				cpsw_gstrings_stats[l].stat_offset);
-
-	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
-		cpdma_chan_get_stats(cpsw->rxv[ch].ch, &ch_stats);
-		for (i = 0; i < CPSW_STATS_CH_LEN; i++, l++) {
-			p = (u8 *)&ch_stats +
-				cpsw_gstrings_ch_stats[i].stat_offset;
-			data[l] = *(u32 *)p;
-		}
-	}
-
-	for (ch = 0; ch < cpsw->tx_ch_num; ch++) {
-		cpdma_chan_get_stats(cpsw->txv[ch].ch, &ch_stats);
-		for (i = 0; i < CPSW_STATS_CH_LEN; i++, l++) {
-			p = (u8 *)&ch_stats +
-				cpsw_gstrings_ch_stats[i].stat_offset;
-			data[l] = *(u32 *)p;
-		}
-	}
-}
-
-static inline int cpsw_tx_packet_submit(struct cpsw_priv *priv,
-					struct sk_buff *skb,
-					struct cpdma_chan *txch)
-{
-	struct cpsw_common *cpsw = priv->cpsw;
-
-	skb_tx_timestamp(skb);
-	return cpdma_chan_submit(txch, skb, skb->data, skb->len,
-				 priv->emac_port + cpsw->data.dual_emac);
-}
-
 static inline void cpsw_add_dual_emac_def_ale_entries(
 		struct cpsw_priv *priv, struct cpsw_slave *slave,
 		u32 slave_port)
@@ -1542,24 +1199,18 @@ static inline void cpsw_add_dual_emac_def_ale_entries(
 			     ALE_PORT_DROP_UNKNOWN_VLAN, 1);
 }
 
-static void soft_reset_slave(struct cpsw_slave *slave)
-{
-	char name[32];
-
-	snprintf(name, sizeof(name), "slave-%d", slave->slave_num);
-	soft_reset(name, &slave->sliver->soft_reset);
-}
-
 static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 {
 	u32 slave_port;
 	struct phy_device *phy;
 	struct cpsw_common *cpsw = priv->cpsw;
 
-	soft_reset_slave(slave);
+	cpsw_sl_reset(slave->mac_sl, 100);
+	cpsw_sl_ctl_reset(slave->mac_sl);
 
 	/* setup priority mapping */
-	writel_relaxed(RX_PRIORITY_MAPPING, &slave->sliver->rx_pri_map);
+	cpsw_sl_reg_write(slave->mac_sl, CPSW_SL_RX_PRI_MAP,
+			  RX_PRIORITY_MAPPING);
 
 	switch (cpsw->version) {
 	case CPSW_VERSION_1:
@@ -1585,7 +1236,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 	}
 
 	/* setup max packet size, and mac address */
-	writel_relaxed(cpsw->rx_packet_max, &slave->sliver->rx_maxlen);
+	cpsw_sl_reg_write(slave->mac_sl, CPSW_SL_RX_MAXLEN,
+			  cpsw->rx_packet_max);
 	cpsw_set_slave_mac(slave, priv);
 
 	slave->mac_control = 0;	/* no link yet */
@@ -1696,36 +1348,42 @@ static void cpsw_init_host_port(struct cpsw_priv *priv)
 	}
 }
 
-static int cpsw_fill_rx_channels(struct cpsw_priv *priv)
+int cpsw_fill_rx_channels(struct cpsw_priv *priv)
 {
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct sk_buff *skb;
+	struct cpsw_meta_xdp *xmeta;
+	struct page_pool *pool;
+	struct page *page;
 	int ch_buf_num;
 	int ch, i, ret;
+	dma_addr_t dma;
 
 	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		pool = cpsw->page_pool[ch];
 		ch_buf_num = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
 		for (i = 0; i < ch_buf_num; i++) {
-			skb = __netdev_alloc_skb_ip_align(priv->ndev,
-							  cpsw->rx_packet_max,
-							  GFP_KERNEL);
-			if (!skb) {
-				cpsw_err(priv, ifup, "cannot allocate skb\n");
+			page = page_pool_dev_alloc_pages(pool);
+			if (!page) {
+				cpsw_err(priv, ifup, "allocate rx page err\n");
 				return -ENOMEM;
 			}
 
-			skb_set_queue_mapping(skb, ch);
-			ret = cpdma_chan_submit(cpsw->rxv[ch].ch, skb,
-						skb->data, skb_tailroom(skb),
-						0);
+			xmeta = page_address(page) + CPSW_XMETA_OFFSET;
+			xmeta->ndev = priv->ndev;
+			xmeta->ch = ch;
+
+			dma = page_pool_get_dma_addr(page) + CPSW_HEADROOM;
+			ret = cpdma_chan_idle_submit_mapped(cpsw->rxv[ch].ch,
+							    page, dma,
+							    cpsw->rx_packet_max,
+							    0);
 			if (ret < 0) {
 				cpsw_err(priv, ifup,
-					 "cannot submit skb to channel %d rx, error %d\n",
+					 "cannot submit page to channel %d rx, error %d\n",
 					 ch, ret);
-				kfree_skb(skb);
+				page_pool_recycle_direct(pool, page);
 				return ret;
 			}
-			kmemleak_not_leak(skb);
 		}
 
 		cpsw_info(priv, ifup, "ch %d rx, submitted %d descriptors\n",
@@ -1748,7 +1406,8 @@ static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_common *cpsw)
 	slave->phy = NULL;
 	cpsw_ale_control_set(cpsw->ale, slave_port,
 			     ALE_PORT_STATE, ALE_PORT_STATE_DISABLE);
-	soft_reset_slave(slave);
+	cpsw_sl_reset(slave->mac_sl, 100);
+	cpsw_sl_ctl_reset(slave->mac_sl);
 }
 
 static int cpsw_tc_to_fifo(int tc, int num_tc)
@@ -2060,6 +1719,13 @@ static int cpsw_ndo_open(struct net_device *ndev)
 			enable_irq(cpsw->irqs_table[0]);
 		}
 
+		/* create rxqs for both infs in dual mac as they use same pool
+		 * and must be destroyed together when no users.
+		 */
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret < 0)
+			goto err_cleanup;
+
 		ret = cpsw_fill_rx_channels(priv);
 		if (ret < 0)
 			goto err_cleanup;
@@ -2086,7 +1752,11 @@ static int cpsw_ndo_open(struct net_device *ndev)
 	return 0;
 
 err_cleanup:
-	cpdma_ctlr_stop(cpsw->dma);
+	if (!cpsw->usage_count) {
+		cpdma_ctlr_stop(cpsw->dma);
+		cpsw_destroy_xdp_rxqs(cpsw);
+	}
+
 	for_each_slave(priv, cpsw_slave_stop, cpsw);
 	pm_runtime_put_sync(cpsw->dev);
 	netif_carrier_off(priv->ndev);
@@ -2110,11 +1780,12 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 		cpsw_intr_disable(cpsw);
 		cpdma_ctlr_stop(cpsw->dma);
 		cpsw_ale_stop(cpsw->ale);
+		cpsw_destroy_xdp_rxqs(cpsw);
 	}
 	for_each_slave(priv, cpsw_slave_stop, cpsw);
 
 	if (cpsw_need_resplit(cpsw))
-		cpsw_split_res(ndev);
+		cpsw_split_res(cpsw);
 
 	cpsw->usage_count--;
 	pm_runtime_put_sync(cpsw->dev);
@@ -2147,7 +1818,9 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 
 	txch = cpsw->txv[q_idx].ch;
 	txq = netdev_get_tx_queue(ndev, q_idx);
-	ret = cpsw_tx_packet_submit(priv, skb, txch);
+	skb_tx_timestamp(skb);
+	ret = cpdma_chan_submit(txch, skb, skb->data, skb->len,
+				priv->emac_port + cpsw->data.dual_emac);
 	if (unlikely(ret != 0)) {
 		cpsw_err(priv, tx_err, "desc submit failed\n");
 		goto fail;
@@ -2418,18 +2091,6 @@ static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
 	return 0;
 }
 
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void cpsw_ndo_poll_controller(struct net_device *ndev)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-
-	cpsw_intr_disable(cpsw);
-	cpsw_rx_interrupt(cpsw->irqs_table[0], cpsw);
-	cpsw_tx_interrupt(cpsw->irqs_table[1], cpsw);
-	cpsw_intr_enable(cpsw);
-}
-#endif
-
 static inline int cpsw_add_vlan_ale_entry(struct cpsw_priv *priv,
 				unsigned short vid)
 {
@@ -2601,7 +2262,7 @@ static int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate)
 		netdev_get_tx_queue(slave->ndev, queue)->tx_maxrate = rate;
 	}
 
-	cpsw_split_res(ndev);
+	cpsw_split_res(cpsw);
 	return ret;
 }
 
@@ -2677,165 +2338,105 @@ static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	}
 }
 
-static const struct net_device_ops cpsw_netdev_ops = {
-	.ndo_open		= cpsw_ndo_open,
-	.ndo_stop		= cpsw_ndo_stop,
-	.ndo_start_xmit		= cpsw_ndo_start_xmit,
-	.ndo_set_mac_address	= cpsw_ndo_set_mac_address,
-	.ndo_do_ioctl		= cpsw_ndo_ioctl,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_tx_timeout		= cpsw_ndo_tx_timeout,
-	.ndo_set_rx_mode	= cpsw_ndo_set_rx_mode,
-	.ndo_set_tx_maxrate	= cpsw_ndo_set_tx_maxrate,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= cpsw_ndo_poll_controller,
-#endif
-	.ndo_vlan_rx_add_vid	= cpsw_ndo_vlan_rx_add_vid,
-	.ndo_vlan_rx_kill_vid	= cpsw_ndo_vlan_rx_kill_vid,
-	.ndo_setup_tc           = cpsw_ndo_setup_tc,
-};
-
-static int cpsw_get_regs_len(struct net_device *ndev)
+static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf)
 {
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct bpf_prog *prog = bpf->prog;
 
-	return cpsw->data.ale_entries * ALE_ENTRY_WORDS * sizeof(u32);
-}
+	if (!priv->xdpi.prog && !prog)
+		return 0;
 
-static void cpsw_get_regs(struct net_device *ndev,
-			  struct ethtool_regs *regs, void *p)
-{
-	u32 *reg = p;
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	if (!xdp_attachment_flags_ok(&priv->xdpi, bpf))
+		return -EBUSY;
 
-	/* update CPSW IP version */
-	regs->version = cpsw->version;
+	WRITE_ONCE(priv->xdp_prog, prog);
 
-	cpsw_ale_dump(cpsw->ale, reg);
-}
+	xdp_attachment_setup(&priv->xdpi, bpf);
 
-static void cpsw_get_drvinfo(struct net_device *ndev,
-			     struct ethtool_drvinfo *info)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	struct platform_device	*pdev = to_platform_device(cpsw->dev);
-
-	strlcpy(info->driver, "cpsw", sizeof(info->driver));
-	strlcpy(info->version, "1.0", sizeof(info->version));
-	strlcpy(info->bus_info, pdev->name, sizeof(info->bus_info));
+	return 0;
 }
 
-static u32 cpsw_get_msglevel(struct net_device *ndev)
+static int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
-	return priv->msg_enable;
-}
 
-static void cpsw_set_msglevel(struct net_device *ndev, u32 value)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	priv->msg_enable = value;
-}
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return cpsw_xdp_prog_setup(priv, bpf);
 
-#if IS_ENABLED(CONFIG_TI_CPTS)
-static int cpsw_get_ts_info(struct net_device *ndev,
-			    struct ethtool_ts_info *info)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	case XDP_QUERY_PROG:
+		return xdp_attachment_query(&priv->xdpi, bpf);
 
-	info->so_timestamping =
-		SOF_TIMESTAMPING_TX_HARDWARE |
-		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
-		SOF_TIMESTAMPING_RAW_HARDWARE;
-	info->phc_index = cpsw->cpts->phc_index;
-	info->tx_types =
-		(1 << HWTSTAMP_TX_OFF) |
-		(1 << HWTSTAMP_TX_ON);
-	info->rx_filters =
-		(1 << HWTSTAMP_FILTER_NONE) |
-		(1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
-	return 0;
-}
-#else
-static int cpsw_get_ts_info(struct net_device *ndev,
-			    struct ethtool_ts_info *info)
-{
-	info->so_timestamping =
-		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE;
-	info->phc_index = -1;
-	info->tx_types = 0;
-	info->rx_filters = 0;
-	return 0;
+	default:
+		return -EINVAL;
+	}
 }
-#endif
 
-static int cpsw_get_link_ksettings(struct net_device *ndev,
-				   struct ethtool_link_ksettings *ecmd)
+static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+			     struct xdp_frame **frames, u32 flags)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
+	struct xdp_frame *xdpf;
+	int i, drops = 0;
 
-	if (!cpsw->slaves[slave_no].phy)
-		return -EOPNOTSUPP;
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
 
-	phy_ethtool_ksettings_get(cpsw->slaves[slave_no].phy, ecmd);
-	return 0;
-}
+	for (i = 0; i < n; i++) {
+		xdpf = frames[i];
+		if (xdpf->len < CPSW_MIN_PACKET_SIZE) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+			continue;
+		}
 
-static int cpsw_set_link_ksettings(struct net_device *ndev,
-				   const struct ethtool_link_ksettings *ecmd)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
+		if (cpsw_xdp_tx_frame(priv, xdpf, NULL))
+			drops++;
+	}
 
-	if (cpsw->slaves[slave_no].phy)
-		return phy_ethtool_ksettings_set(cpsw->slaves[slave_no].phy,
-						 ecmd);
-	else
-		return -EOPNOTSUPP;
+	return n - drops;
 }
 
-static void cpsw_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void cpsw_ndo_poll_controller(struct net_device *ndev)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-
-	wol->supported = 0;
-	wol->wolopts = 0;
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
 
-	if (cpsw->slaves[slave_no].phy)
-		phy_ethtool_get_wol(cpsw->slaves[slave_no].phy, wol);
+	cpsw_intr_disable(cpsw);
+	cpsw_rx_interrupt(cpsw->irqs_table[0], cpsw);
+	cpsw_tx_interrupt(cpsw->irqs_table[1], cpsw);
+	cpsw_intr_enable(cpsw);
 }
+#endif
 
-static int cpsw_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-
-	if (cpsw->slaves[slave_no].phy)
-		return phy_ethtool_set_wol(cpsw->slaves[slave_no].phy, wol);
-	else
-		return -EOPNOTSUPP;
-}
+static const struct net_device_ops cpsw_netdev_ops = {
+	.ndo_open		= cpsw_ndo_open,
+	.ndo_stop		= cpsw_ndo_stop,
+	.ndo_start_xmit		= cpsw_ndo_start_xmit,
+	.ndo_set_mac_address	= cpsw_ndo_set_mac_address,
+	.ndo_do_ioctl		= cpsw_ndo_ioctl,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_tx_timeout		= cpsw_ndo_tx_timeout,
+	.ndo_set_rx_mode	= cpsw_ndo_set_rx_mode,
+	.ndo_set_tx_maxrate	= cpsw_ndo_set_tx_maxrate,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= cpsw_ndo_poll_controller,
+#endif
+	.ndo_vlan_rx_add_vid	= cpsw_ndo_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= cpsw_ndo_vlan_rx_kill_vid,
+	.ndo_setup_tc           = cpsw_ndo_setup_tc,
+	.ndo_bpf		= cpsw_ndo_bpf,
+	.ndo_xdp_xmit		= cpsw_ndo_xdp_xmit,
+};
 
-static void cpsw_get_pauseparam(struct net_device *ndev,
-				struct ethtool_pauseparam *pause)
+static void cpsw_get_drvinfo(struct net_device *ndev,
+			     struct ethtool_drvinfo *info)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct platform_device	*pdev = to_platform_device(cpsw->dev);
 
-	pause->autoneg = AUTONEG_DISABLE;
-	pause->rx_pause = priv->rx_pause ? true : false;
-	pause->tx_pause = priv->tx_pause ? true : false;
+	strlcpy(info->driver, "cpsw", sizeof(info->driver));
+	strlcpy(info->version, "1.0", sizeof(info->version));
+	strlcpy(info->bus_info, pdev->name, sizeof(info->bus_info));
 }
 
 static int cpsw_set_pauseparam(struct net_device *ndev,
@@ -2851,316 +2452,10 @@ static int cpsw_set_pauseparam(struct net_device *ndev,
 	return 0;
 }
 
-static int cpsw_ethtool_op_begin(struct net_device *ndev)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int ret;
-
-	ret = pm_runtime_get_sync(cpsw->dev);
-	if (ret < 0) {
-		cpsw_err(priv, drv, "ethtool begin failed %d\n", ret);
-		pm_runtime_put_noidle(cpsw->dev);
-	}
-
-	return ret;
-}
-
-static void cpsw_ethtool_op_complete(struct net_device *ndev)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	int ret;
-
-	ret = pm_runtime_put(priv->cpsw->dev);
-	if (ret < 0)
-		cpsw_err(priv, drv, "ethtool complete failed %d\n", ret);
-}
-
-static void cpsw_get_channels(struct net_device *ndev,
-			      struct ethtool_channels *ch)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-
-	ch->max_rx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
-	ch->max_tx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
-	ch->max_combined = 0;
-	ch->max_other = 0;
-	ch->other_count = 0;
-	ch->rx_count = cpsw->rx_ch_num;
-	ch->tx_count = cpsw->tx_ch_num;
-	ch->combined_count = 0;
-}
-
-static int cpsw_check_ch_settings(struct cpsw_common *cpsw,
-				  struct ethtool_channels *ch)
-{
-	if (cpsw->quirk_irq) {
-		dev_err(cpsw->dev, "Maximum one tx/rx queue is allowed");
-		return -EOPNOTSUPP;
-	}
-
-	if (ch->combined_count)
-		return -EINVAL;
-
-	/* verify we have at least one channel in each direction */
-	if (!ch->rx_count || !ch->tx_count)
-		return -EINVAL;
-
-	if (ch->rx_count > cpsw->data.channels ||
-	    ch->tx_count > cpsw->data.channels)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx)
-{
-	struct cpsw_common *cpsw = priv->cpsw;
-	void (*handler)(void *, int, int);
-	struct netdev_queue *queue;
-	struct cpsw_vector *vec;
-	int ret, *ch, vch;
-
-	if (rx) {
-		ch = &cpsw->rx_ch_num;
-		vec = cpsw->rxv;
-		handler = cpsw_rx_handler;
-	} else {
-		ch = &cpsw->tx_ch_num;
-		vec = cpsw->txv;
-		handler = cpsw_tx_handler;
-	}
-
-	while (*ch < ch_num) {
-		vch = rx ? *ch : 7 - *ch;
-		vec[*ch].ch = cpdma_chan_create(cpsw->dma, vch, handler, rx);
-		queue = netdev_get_tx_queue(priv->ndev, *ch);
-		queue->tx_maxrate = 0;
-
-		if (IS_ERR(vec[*ch].ch))
-			return PTR_ERR(vec[*ch].ch);
-
-		if (!vec[*ch].ch)
-			return -EINVAL;
-
-		cpsw_info(priv, ifup, "created new %d %s channel\n", *ch,
-			  (rx ? "rx" : "tx"));
-		(*ch)++;
-	}
-
-	while (*ch > ch_num) {
-		(*ch)--;
-
-		ret = cpdma_chan_destroy(vec[*ch].ch);
-		if (ret)
-			return ret;
-
-		cpsw_info(priv, ifup, "destroyed %d %s channel\n", *ch,
-			  (rx ? "rx" : "tx"));
-	}
-
-	return 0;
-}
-
-static int cpsw_update_channels(struct cpsw_priv *priv,
-				struct ethtool_channels *ch)
-{
-	int ret;
-
-	ret = cpsw_update_channels_res(priv, ch->rx_count, 1);
-	if (ret)
-		return ret;
-
-	ret = cpsw_update_channels_res(priv, ch->tx_count, 0);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-static void cpsw_suspend_data_pass(struct net_device *ndev)
-{
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	struct cpsw_slave *slave;
-	int i;
-
-	/* Disable NAPI scheduling */
-	cpsw_intr_disable(cpsw);
-
-	/* Stop all transmit queues for every network device.
-	 * Disable re-using rx descriptors with dormant_on.
-	 */
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++) {
-		if (!(slave->ndev && netif_running(slave->ndev)))
-			continue;
-
-		netif_tx_stop_all_queues(slave->ndev);
-		netif_dormant_on(slave->ndev);
-	}
-
-	/* Handle rest of tx packets and stop cpdma channels */
-	cpdma_ctlr_stop(cpsw->dma);
-}
-
-static int cpsw_resume_data_pass(struct net_device *ndev)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	struct cpsw_slave *slave;
-	int i, ret;
-
-	/* Allow rx packets handling */
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++)
-		if (slave->ndev && netif_running(slave->ndev))
-			netif_dormant_off(slave->ndev);
-
-	/* After this receive is started */
-	if (cpsw->usage_count) {
-		ret = cpsw_fill_rx_channels(priv);
-		if (ret)
-			return ret;
-
-		cpdma_ctlr_start(cpsw->dma);
-		cpsw_intr_enable(cpsw);
-	}
-
-	/* Resume transmit for every affected interface */
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++)
-		if (slave->ndev && netif_running(slave->ndev))
-			netif_tx_start_all_queues(slave->ndev);
-
-	return 0;
-}
-
 static int cpsw_set_channels(struct net_device *ndev,
 			     struct ethtool_channels *chs)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	struct cpsw_slave *slave;
-	int i, ret;
-
-	ret = cpsw_check_ch_settings(cpsw, chs);
-	if (ret < 0)
-		return ret;
-
-	cpsw_suspend_data_pass(ndev);
-	ret = cpsw_update_channels(priv, chs);
-	if (ret)
-		goto err;
-
-	for (i = cpsw->data.slaves, slave = cpsw->slaves; i; i--, slave++) {
-		if (!(slave->ndev && netif_running(slave->ndev)))
-			continue;
-
-		/* Inform stack about new count of queues */
-		ret = netif_set_real_num_tx_queues(slave->ndev,
-						   cpsw->tx_ch_num);
-		if (ret) {
-			dev_err(priv->dev, "cannot set real number of tx queues\n");
-			goto err;
-		}
-
-		ret = netif_set_real_num_rx_queues(slave->ndev,
-						   cpsw->rx_ch_num);
-		if (ret) {
-			dev_err(priv->dev, "cannot set real number of rx queues\n");
-			goto err;
-		}
-	}
-
-	if (cpsw->usage_count)
-		cpsw_split_res(ndev);
-
-	ret = cpsw_resume_data_pass(ndev);
-	if (!ret)
-		return 0;
-err:
-	dev_err(priv->dev, "cannot update channels number, closing device\n");
-	dev_close(ndev);
-	return ret;
-}
-
-static int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-
-	if (cpsw->slaves[slave_no].phy)
-		return phy_ethtool_get_eee(cpsw->slaves[slave_no].phy, edata);
-	else
-		return -EOPNOTSUPP;
-}
-
-static int cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-
-	if (cpsw->slaves[slave_no].phy)
-		return phy_ethtool_set_eee(cpsw->slaves[slave_no].phy, edata);
-	else
-		return -EOPNOTSUPP;
-}
-
-static int cpsw_nway_reset(struct net_device *ndev)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int slave_no = cpsw_slave_index(cpsw, priv);
-
-	if (cpsw->slaves[slave_no].phy)
-		return genphy_restart_aneg(cpsw->slaves[slave_no].phy);
-	else
-		return -EOPNOTSUPP;
-}
-
-static void cpsw_get_ringparam(struct net_device *ndev,
-			       struct ethtool_ringparam *ering)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-
-	/* not supported */
-	ering->tx_max_pending = 0;
-	ering->tx_pending = cpdma_get_num_tx_descs(cpsw->dma);
-	ering->rx_max_pending = descs_pool_size - CPSW_MAX_QUEUES;
-	ering->rx_pending = cpdma_get_num_rx_descs(cpsw->dma);
-}
-
-static int cpsw_set_ringparam(struct net_device *ndev,
-			      struct ethtool_ringparam *ering)
-{
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int ret;
-
-	/* ignore ering->tx_pending - only rx_pending adjustment is supported */
-
-	if (ering->rx_mini_pending || ering->rx_jumbo_pending ||
-	    ering->rx_pending < CPSW_MAX_QUEUES ||
-	    ering->rx_pending > (descs_pool_size - CPSW_MAX_QUEUES))
-		return -EINVAL;
-
-	if (ering->rx_pending == cpdma_get_num_rx_descs(cpsw->dma))
-		return 0;
-
-	cpsw_suspend_data_pass(ndev);
-
-	cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
-
-	if (cpsw->usage_count)
-		cpdma_chan_split_pool(cpsw->dma);
-
-	ret = cpsw_resume_data_pass(ndev);
-	if (!ret)
-		return 0;
-
-	dev_err(&ndev->dev, "cannot set ring params, closing device\n");
-	dev_close(ndev);
-	return ret;
+	return cpsw_set_channels_common(ndev, chs, cpsw_rx_handler);
 }
 
 static const struct ethtool_ops cpsw_ethtool_ops = {
@@ -3193,19 +2488,6 @@ static const struct ethtool_ops cpsw_ethtool_ops = {
 	.set_ringparam = cpsw_set_ringparam,
 };
 
-static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_common *cpsw,
-			    u32 slave_reg_ofs, u32 sliver_reg_ofs)
-{
-	void __iomem		*regs = cpsw->regs;
-	int			slave_num = slave->slave_num;
-	struct cpsw_slave_data	*data = cpsw->data.slave_data + slave_num;
-
-	slave->data	= data;
-	slave->regs	= regs + slave_reg_ofs;
-	slave->sliver	= regs + sliver_reg_ofs;
-	slave->port_vlan = data->dual_emac_res_vlan;
-}
-
 static int cpsw_probe_dt(struct cpsw_platform_data *data,
 			 struct platform_device *pdev)
 {
@@ -3291,6 +2573,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 			return ret;
 		}
 
+		slave_data->slave_node = slave_node;
 		slave_data->phy_node = of_parse_phandle(slave_node,
 							"phy-handle", 0);
 		parp = of_get_property(slave_node, "phy_id", &lenp);
@@ -3344,8 +2627,8 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 
 no_phy_slave:
 		mac_addr = of_get_mac_address(slave_node);
-		if (mac_addr) {
-			memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN);
+		if (!IS_ERR(mac_addr)) {
+			ether_addr_copy(slave_data->mac_addr, mac_addr);
 		} else {
 			ret = ti_cm_get_macid(&pdev->dev, i,
 					      slave_data->mac_addr);
@@ -3374,8 +2657,7 @@ no_phy_slave:
 
 static void cpsw_remove_dt(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
 	struct cpsw_platform_data *data = &cpsw->data;
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *slave_node;
@@ -3408,7 +2690,8 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 	struct cpsw_priv		*priv_sl2;
 	int ret = 0;
 
-	ndev = alloc_etherdev_mq(sizeof(struct cpsw_priv), CPSW_MAX_QUEUES);
+	ndev = devm_alloc_etherdev_mqs(cpsw->dev, sizeof(struct cpsw_priv),
+				       CPSW_MAX_QUEUES, CPSW_MAX_QUEUES);
 	if (!ndev) {
 		dev_err(cpsw->dev, "cpsw: error allocating net_device\n");
 		return -ENOMEM;
@@ -3441,12 +2724,10 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 
 	/* register the network device */
 	SET_NETDEV_DEV(ndev, cpsw->dev);
+	ndev->dev.of_node = cpsw->slaves[1].data->slave_node;
 	ret = register_netdev(ndev);
-	if (ret) {
+	if (ret)
 		dev_err(cpsw->dev, "cpsw: error registering net device\n");
-		free_netdev(ndev);
-		ret = -ENODEV;
-	}
 
 	return ret;
 }
@@ -3467,63 +2748,74 @@ static const struct soc_device_attribute cpsw_soc_devices[] = {
 
 static int cpsw_probe(struct platform_device *pdev)
 {
+	struct device			*dev = &pdev->dev;
 	struct clk			*clk;
 	struct cpsw_platform_data	*data;
 	struct net_device		*ndev;
 	struct cpsw_priv		*priv;
-	struct cpdma_params		dma_params;
-	struct cpsw_ale_params		ale_params;
 	void __iomem			*ss_regs;
-	void __iomem			*cpts_regs;
 	struct resource			*res, *ss_res;
 	struct gpio_descs		*mode;
-	u32 slave_offset, sliver_offset, slave_size;
 	const struct soc_device_attribute *soc;
 	struct cpsw_common		*cpsw;
-	int ret = 0, i, ch;
+	int ret = 0, ch;
 	int irq;
 
-	cpsw = devm_kzalloc(&pdev->dev, sizeof(struct cpsw_common), GFP_KERNEL);
+	cpsw = devm_kzalloc(dev, sizeof(struct cpsw_common), GFP_KERNEL);
 	if (!cpsw)
 		return -ENOMEM;
 
-	cpsw->dev = &pdev->dev;
+	cpsw->dev = dev;
 
-	ndev = alloc_etherdev_mq(sizeof(struct cpsw_priv), CPSW_MAX_QUEUES);
-	if (!ndev) {
-		dev_err(&pdev->dev, "error allocating net_device\n");
-		return -ENOMEM;
-	}
-
-	platform_set_drvdata(pdev, ndev);
-	priv = netdev_priv(ndev);
-	priv->cpsw = cpsw;
-	priv->ndev = ndev;
-	priv->dev  = &ndev->dev;
-	priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG);
-	cpsw->rx_packet_max = max(rx_packet_max, 128);
-
-	mode = devm_gpiod_get_array_optional(&pdev->dev, "mode", GPIOD_OUT_LOW);
+	mode = devm_gpiod_get_array_optional(dev, "mode", GPIOD_OUT_LOW);
 	if (IS_ERR(mode)) {
 		ret = PTR_ERR(mode);
-		dev_err(&pdev->dev, "gpio request failed, ret %d\n", ret);
-		goto clean_ndev_ret;
+		dev_err(dev, "gpio request failed, ret %d\n", ret);
+		return ret;
 	}
 
+	clk = devm_clk_get(dev, "fck");
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(dev, "fck is not found %d\n", ret);
+		return ret;
+	}
+	cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000;
+
+	ss_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ss_regs = devm_ioremap_resource(dev, ss_res);
+	if (IS_ERR(ss_regs))
+		return PTR_ERR(ss_regs);
+	cpsw->regs = ss_regs;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	cpsw->wr_regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cpsw->wr_regs))
+		return PTR_ERR(cpsw->wr_regs);
+
+	/* RX IRQ */
+	irq = platform_get_irq(pdev, 1);
+	if (irq < 0)
+		return irq;
+	cpsw->irqs_table[0] = irq;
+
+	/* TX IRQ */
+	irq = platform_get_irq(pdev, 2);
+	if (irq < 0)
+		return irq;
+	cpsw->irqs_table[1] = irq;
+
 	/*
 	 * This may be required here for child devices.
 	 */
-	pm_runtime_enable(&pdev->dev);
-
-	/* Select default pin state */
-	pinctrl_pm_select_default_state(&pdev->dev);
+	pm_runtime_enable(dev);
 
 	/* Need to enable clocks with runtime PM api to access module
 	 * registers
 	 */
-	ret = pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
-		pm_runtime_put_noidle(&pdev->dev);
+		pm_runtime_put_noidle(dev);
 		goto clean_runtime_disable_ret;
 	}
 
@@ -3531,170 +2823,72 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (ret)
 		goto clean_dt_ret;
 
-	data = &cpsw->data;
-	cpsw->rx_ch_num = 1;
-	cpsw->tx_ch_num = 1;
-
-	if (is_valid_ether_addr(data->slave_data[0].mac_addr)) {
-		memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN);
-		dev_info(&pdev->dev, "Detected MACID = %pM\n", priv->mac_addr);
-	} else {
-		eth_random_addr(priv->mac_addr);
-		dev_info(&pdev->dev, "Random MACID = %pM\n", priv->mac_addr);
-	}
-
-	memcpy(ndev->dev_addr, priv->mac_addr, ETH_ALEN);
+	soc = soc_device_match(cpsw_soc_devices);
+	if (soc)
+		cpsw->quirk_irq = 1;
 
-	cpsw->slaves = devm_kcalloc(&pdev->dev,
+	data = &cpsw->data;
+	cpsw->slaves = devm_kcalloc(dev,
 				    data->slaves, sizeof(struct cpsw_slave),
 				    GFP_KERNEL);
 	if (!cpsw->slaves) {
 		ret = -ENOMEM;
 		goto clean_dt_ret;
 	}
-	for (i = 0; i < data->slaves; i++)
-		cpsw->slaves[i].slave_num = i;
 
-	cpsw->slaves[0].ndev = ndev;
-	priv->emac_port = 0;
+	cpsw->rx_packet_max = max(rx_packet_max, CPSW_MAX_PACKET_SIZE);
+	cpsw->descs_pool_size = descs_pool_size;
 
-	clk = devm_clk_get(&pdev->dev, "fck");
-	if (IS_ERR(clk)) {
-		dev_err(priv->dev, "fck is not found\n");
-		ret = -ENODEV;
-		goto clean_dt_ret;
-	}
-	cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000;
-
-	ss_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	ss_regs = devm_ioremap_resource(&pdev->dev, ss_res);
-	if (IS_ERR(ss_regs)) {
-		ret = PTR_ERR(ss_regs);
-		goto clean_dt_ret;
-	}
-	cpsw->regs = ss_regs;
-
-	cpsw->version = readl(&cpsw->regs->id_ver);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	cpsw->wr_regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(cpsw->wr_regs)) {
-		ret = PTR_ERR(cpsw->wr_regs);
-		goto clean_dt_ret;
-	}
-
-	memset(&dma_params, 0, sizeof(dma_params));
-	memset(&ale_params, 0, sizeof(ale_params));
-
-	switch (cpsw->version) {
-	case CPSW_VERSION_1:
-		cpsw->host_port_regs = ss_regs + CPSW1_HOST_PORT_OFFSET;
-		cpts_regs		= ss_regs + CPSW1_CPTS_OFFSET;
-		cpsw->hw_stats	     = ss_regs + CPSW1_HW_STATS;
-		dma_params.dmaregs   = ss_regs + CPSW1_CPDMA_OFFSET;
-		dma_params.txhdp     = ss_regs + CPSW1_STATERAM_OFFSET;
-		ale_params.ale_regs  = ss_regs + CPSW1_ALE_OFFSET;
-		slave_offset         = CPSW1_SLAVE_OFFSET;
-		slave_size           = CPSW1_SLAVE_SIZE;
-		sliver_offset        = CPSW1_SLIVER_OFFSET;
-		dma_params.desc_mem_phys = 0;
-		break;
-	case CPSW_VERSION_2:
-	case CPSW_VERSION_3:
-	case CPSW_VERSION_4:
-		cpsw->host_port_regs = ss_regs + CPSW2_HOST_PORT_OFFSET;
-		cpts_regs		= ss_regs + CPSW2_CPTS_OFFSET;
-		cpsw->hw_stats	     = ss_regs + CPSW2_HW_STATS;
-		dma_params.dmaregs   = ss_regs + CPSW2_CPDMA_OFFSET;
-		dma_params.txhdp     = ss_regs + CPSW2_STATERAM_OFFSET;
-		ale_params.ale_regs  = ss_regs + CPSW2_ALE_OFFSET;
-		slave_offset         = CPSW2_SLAVE_OFFSET;
-		slave_size           = CPSW2_SLAVE_SIZE;
-		sliver_offset        = CPSW2_SLIVER_OFFSET;
-		dma_params.desc_mem_phys =
-			(u32 __force) ss_res->start + CPSW2_BD_OFFSET;
-		break;
-	default:
-		dev_err(priv->dev, "unknown version 0x%08x\n", cpsw->version);
-		ret = -ENODEV;
-		goto clean_dt_ret;
-	}
-	for (i = 0; i < cpsw->data.slaves; i++) {
-		struct cpsw_slave *slave = &cpsw->slaves[i];
-
-		cpsw_slave_init(slave, cpsw, slave_offset, sliver_offset);
-		slave_offset  += slave_size;
-		sliver_offset += SLIVER_SIZE;
-	}
-
-	dma_params.dev		= &pdev->dev;
-	dma_params.rxthresh	= dma_params.dmaregs + CPDMA_RXTHRESH;
-	dma_params.rxfree	= dma_params.dmaregs + CPDMA_RXFREE;
-	dma_params.rxhdp	= dma_params.txhdp + CPDMA_RXHDP;
-	dma_params.txcp		= dma_params.txhdp + CPDMA_TXCP;
-	dma_params.rxcp		= dma_params.txhdp + CPDMA_RXCP;
-
-	dma_params.num_chan		= data->channels;
-	dma_params.has_soft_reset	= true;
-	dma_params.min_packet_size	= CPSW_MIN_PACKET_SIZE;
-	dma_params.desc_mem_size	= data->bd_ram_size;
-	dma_params.desc_align		= 16;
-	dma_params.has_ext_regs		= true;
-	dma_params.desc_hw_addr         = dma_params.desc_mem_phys;
-	dma_params.bus_freq_mhz		= cpsw->bus_freq_mhz;
-	dma_params.descs_pool_size	= descs_pool_size;
-
-	cpsw->dma = cpdma_ctlr_create(&dma_params);
-	if (!cpsw->dma) {
-		dev_err(priv->dev, "error initializing dma\n");
-		ret = -ENOMEM;
+	ret = cpsw_init_common(cpsw, ss_regs, ale_ageout,
+			       ss_res->start + CPSW2_BD_OFFSET,
+			       descs_pool_size);
+	if (ret)
 		goto clean_dt_ret;
-	}
-
-	soc = soc_device_match(cpsw_soc_devices);
-	if (soc)
-		cpsw->quirk_irq = 1;
 
 	ch = cpsw->quirk_irq ? 0 : 7;
 	cpsw->txv[0].ch = cpdma_chan_create(cpsw->dma, ch, cpsw_tx_handler, 0);
 	if (IS_ERR(cpsw->txv[0].ch)) {
-		dev_err(priv->dev, "error initializing tx dma channel\n");
+		dev_err(dev, "error initializing tx dma channel\n");
 		ret = PTR_ERR(cpsw->txv[0].ch);
-		goto clean_dma_ret;
+		goto clean_cpts;
 	}
 
 	cpsw->rxv[0].ch = cpdma_chan_create(cpsw->dma, 0, cpsw_rx_handler, 1);
 	if (IS_ERR(cpsw->rxv[0].ch)) {
-		dev_err(priv->dev, "error initializing rx dma channel\n");
+		dev_err(dev, "error initializing rx dma channel\n");
 		ret = PTR_ERR(cpsw->rxv[0].ch);
-		goto clean_dma_ret;
+		goto clean_cpts;
 	}
+	cpsw_split_res(cpsw);
 
-	ale_params.dev			= &pdev->dev;
-	ale_params.ale_ageout		= ale_ageout;
-	ale_params.ale_entries		= data->ale_entries;
-	ale_params.ale_ports		= CPSW_ALE_PORTS_NUM;
-
-	cpsw->ale = cpsw_ale_create(&ale_params);
-	if (!cpsw->ale) {
-		dev_err(priv->dev, "error initializing ale engine\n");
-		ret = -ENODEV;
-		goto clean_dma_ret;
+	/* setup netdev */
+	ndev = devm_alloc_etherdev_mqs(dev, sizeof(struct cpsw_priv),
+				       CPSW_MAX_QUEUES, CPSW_MAX_QUEUES);
+	if (!ndev) {
+		dev_err(dev, "error allocating net_device\n");
+		goto clean_cpts;
 	}
 
-	cpsw->cpts = cpts_create(cpsw->dev, cpts_regs, cpsw->dev->of_node);
-	if (IS_ERR(cpsw->cpts)) {
-		ret = PTR_ERR(cpsw->cpts);
-		goto clean_dma_ret;
-	}
+	platform_set_drvdata(pdev, cpsw);
+	priv = netdev_priv(ndev);
+	priv->cpsw = cpsw;
+	priv->ndev = ndev;
+	priv->dev  = dev;
+	priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG);
+	priv->emac_port = 0;
 
-	ndev->irq = platform_get_irq(pdev, 1);
-	if (ndev->irq < 0) {
-		dev_err(priv->dev, "error getting irq resource\n");
-		ret = ndev->irq;
-		goto clean_dma_ret;
+	if (is_valid_ether_addr(data->slave_data[0].mac_addr)) {
+		memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN);
+		dev_info(dev, "Detected MACID = %pM\n", priv->mac_addr);
+	} else {
+		eth_random_addr(priv->mac_addr);
+		dev_info(dev, "Random MACID = %pM\n", priv->mac_addr);
 	}
 
+	memcpy(ndev->dev_addr, priv->mac_addr, ETH_ALEN);
+
+	cpsw->slaves[0].ndev = ndev;
+
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
@@ -3705,15 +2899,15 @@ static int cpsw_probe(struct platform_device *pdev)
 	netif_tx_napi_add(ndev, &cpsw->napi_tx,
 			  cpsw->quirk_irq ? cpsw_tx_poll : cpsw_tx_mq_poll,
 			  CPSW_POLL_WEIGHT);
-	cpsw_split_res(ndev);
 
 	/* register the network device */
-	SET_NETDEV_DEV(ndev, &pdev->dev);
+	SET_NETDEV_DEV(ndev, dev);
+	ndev->dev.of_node = cpsw->slaves[0].data->slave_node;
 	ret = register_netdev(ndev);
 	if (ret) {
-		dev_err(priv->dev, "error registering net device\n");
+		dev_err(dev, "error registering net device\n");
 		ret = -ENODEV;
-		goto clean_dma_ret;
+		goto clean_cpts;
 	}
 
 	if (cpsw->data.dual_emac) {
@@ -3731,40 +2925,24 @@ static int cpsw_probe(struct platform_device *pdev)
 	 * If anyone wants to implement support for those, make sure to
 	 * first request and append them to irqs_table array.
 	 */
-
-	/* RX IRQ */
-	irq = platform_get_irq(pdev, 1);
-	if (irq < 0) {
-		ret = irq;
-		goto clean_dma_ret;
-	}
-
-	cpsw->irqs_table[0] = irq;
-	ret = devm_request_irq(&pdev->dev, irq, cpsw_rx_interrupt,
-			       0, dev_name(&pdev->dev), cpsw);
+	ret = devm_request_irq(dev, cpsw->irqs_table[0], cpsw_rx_interrupt,
+			       0, dev_name(dev), cpsw);
 	if (ret < 0) {
-		dev_err(priv->dev, "error attaching irq (%d)\n", ret);
-		goto clean_dma_ret;
+		dev_err(dev, "error attaching irq (%d)\n", ret);
+		goto clean_unregister_netdev_ret;
 	}
 
-	/* TX IRQ */
-	irq = platform_get_irq(pdev, 2);
-	if (irq < 0) {
-		ret = irq;
-		goto clean_dma_ret;
-	}
 
-	cpsw->irqs_table[1] = irq;
-	ret = devm_request_irq(&pdev->dev, irq, cpsw_tx_interrupt,
+	ret = devm_request_irq(dev, cpsw->irqs_table[1], cpsw_tx_interrupt,
 			       0, dev_name(&pdev->dev), cpsw);
 	if (ret < 0) {
-		dev_err(priv->dev, "error attaching irq (%d)\n", ret);
-		goto clean_dma_ret;
+		dev_err(dev, "error attaching irq (%d)\n", ret);
+		goto clean_unregister_netdev_ret;
 	}
 
 	cpsw_notice(priv, probe,
 		    "initialized device (regs %pa, irq %d, pool size %d)\n",
-		    &ss_res->start, ndev->irq, dma_params.descs_pool_size);
+		    &ss_res->start, cpsw->irqs_table[0], descs_pool_size);
 
 	pm_runtime_put(&pdev->dev);
 
@@ -3772,23 +2950,21 @@ static int cpsw_probe(struct platform_device *pdev)
 
 clean_unregister_netdev_ret:
 	unregister_netdev(ndev);
-clean_dma_ret:
+clean_cpts:
+	cpts_release(cpsw->cpts);
 	cpdma_ctlr_destroy(cpsw->dma);
 clean_dt_ret:
 	cpsw_remove_dt(pdev);
 	pm_runtime_put_sync(&pdev->dev);
 clean_runtime_disable_ret:
 	pm_runtime_disable(&pdev->dev);
-clean_ndev_ret:
-	free_netdev(priv->ndev);
 	return ret;
 }
 
 static int cpsw_remove(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
-	int ret;
+	struct cpsw_common *cpsw = platform_get_drvdata(pdev);
+	int i, ret;
 
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
@@ -3796,38 +2972,28 @@ static int cpsw_remove(struct platform_device *pdev)
 		return ret;
 	}
 
-	if (cpsw->data.dual_emac)
-		unregister_netdev(cpsw->slaves[1].ndev);
-	unregister_netdev(ndev);
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
+			unregister_netdev(cpsw->slaves[i].ndev);
 
 	cpts_release(cpsw->cpts);
 	cpdma_ctlr_destroy(cpsw->dma);
 	cpsw_remove_dt(pdev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	if (cpsw->data.dual_emac)
-		free_netdev(cpsw->slaves[1].ndev);
-	free_netdev(ndev);
 	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
 static int cpsw_suspend(struct device *dev)
 {
-	struct net_device	*ndev = dev_get_drvdata(dev);
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
-
-	if (cpsw->data.dual_emac) {
-		int i;
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
 
-		for (i = 0; i < cpsw->data.slaves; i++) {
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_stop(cpsw->slaves[i].ndev);
-		}
-	} else {
-		if (netif_running(ndev))
-			cpsw_ndo_stop(ndev);
-	}
 
 	/* Select sleep pin state */
 	pinctrl_pm_select_sleep_state(dev);
@@ -3837,25 +3003,20 @@ static int cpsw_suspend(struct device *dev)
 
 static int cpsw_resume(struct device *dev)
 {
-	struct net_device	*ndev = dev_get_drvdata(dev);
-	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_common *cpsw = dev_get_drvdata(dev);
+	int i;
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
 
 	/* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */
 	rtnl_lock();
-	if (cpsw->data.dual_emac) {
-		int i;
 
-		for (i = 0; i < cpsw->data.slaves; i++) {
+	for (i = 0; i < cpsw->data.slaves; i++)
+		if (cpsw->slaves[i].ndev)
 			if (netif_running(cpsw->slaves[i].ndev))
 				cpsw_ndo_open(cpsw->slaves[i].ndev);
-		}
-	} else {
-		if (netif_running(ndev))
-			cpsw_ndo_open(ndev);
-	}
+
 	rtnl_unlock();
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h
index cf111db3dc27..35d602f03281 100644
--- a/drivers/net/ethernet/ti/cpsw.h
+++ b/drivers/net/ethernet/ti/cpsw.h
@@ -1,15 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /* Texas Instruments Ethernet Switch Driver
  *
  * Copyright (C) 2013 Texas Instruments
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef __CPSW_H__
 #define __CPSW_H__
@@ -21,7 +14,13 @@
 			 ((mac)[2] << 16) | ((mac)[3] << 24))
 #define mac_lo(mac)	(((mac)[4] << 0) | ((mac)[5] << 8))
 
+#if IS_ENABLED(CONFIG_TI_CPSW_PHY_SEL)
 void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave);
+#else
+static inline
+void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave)
+{}
+#endif
 int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr);
 
 #endif /* __CPSW_H__ */
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 798c989d5d93..84025dcc78d5 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -1,16 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Texas Instruments N-Port Ethernet Switch Address Lookup Engine
  *
  * Copyright (C) 2012 Texas Instruments
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -287,6 +280,9 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
 		if (cpsw_ale_get_mcast(ale_entry)) {
 			u8 addr[6];
 
+			if (cpsw_ale_get_super(ale_entry))
+				continue;
+
 			cpsw_ale_get_addr(ale_entry, addr);
 			if (!is_broadcast_ether_addr(addr))
 				cpsw_ale_flush_mcast(ale, ale_entry, port_mask);
@@ -296,7 +292,6 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_flush_multicast);
 
 static inline void cpsw_ale_set_vlan_entry_type(u32 *ale_entry,
 						int flags, u16 vid)
@@ -334,7 +329,6 @@ int cpsw_ale_add_ucast(struct cpsw_ale *ale, const u8 *addr, int port,
 	cpsw_ale_write(ale, idx, ale_entry);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_add_ucast);
 
 int cpsw_ale_del_ucast(struct cpsw_ale *ale, const u8 *addr, int port,
 		       int flags, u16 vid)
@@ -350,7 +344,6 @@ int cpsw_ale_del_ucast(struct cpsw_ale *ale, const u8 *addr, int port,
 	cpsw_ale_write(ale, idx, ale_entry);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_del_ucast);
 
 int cpsw_ale_add_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask,
 		       int flags, u16 vid, int mcast_state)
@@ -365,7 +358,7 @@ int cpsw_ale_add_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask,
 	cpsw_ale_set_vlan_entry_type(ale_entry, flags, vid);
 
 	cpsw_ale_set_addr(ale_entry, addr);
-	cpsw_ale_set_super(ale_entry, (flags & ALE_BLOCKED) ? 1 : 0);
+	cpsw_ale_set_super(ale_entry, (flags & ALE_SUPER) ? 1 : 0);
 	cpsw_ale_set_mcast_state(ale_entry, mcast_state);
 
 	mask = cpsw_ale_get_port_mask(ale_entry,
@@ -384,7 +377,6 @@ int cpsw_ale_add_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask,
 	cpsw_ale_write(ale, idx, ale_entry);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_add_mcast);
 
 int cpsw_ale_del_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask,
 		       int flags, u16 vid)
@@ -407,7 +399,6 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask,
 	cpsw_ale_write(ale, idx, ale_entry);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_del_mcast);
 
 /* ALE NetCP NU switch specific vlan functions */
 static void cpsw_ale_set_vlan_mcast(struct cpsw_ale *ale, u32 *ale_entry,
@@ -458,7 +449,6 @@ int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port, int untag,
 	cpsw_ale_write(ale, idx, ale_entry);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_add_vlan);
 
 int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask)
 {
@@ -480,40 +470,39 @@ int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask)
 	cpsw_ale_write(ale, idx, ale_entry);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_del_vlan);
 
-void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti)
+void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti, int port)
 {
 	u32 ale_entry[ALE_ENTRY_WORDS];
-	int type, idx;
 	int unreg_mcast = 0;
-
-	/* Only bother doing the work if the setting is actually changing */
-	if (ale->allmulti == allmulti)
-		return;
-
-	/* Remember the new setting to check against next time */
-	ale->allmulti = allmulti;
+	int type, idx;
 
 	for (idx = 0; idx < ale->params.ale_entries; idx++) {
+		int vlan_members;
+
 		cpsw_ale_read(ale, idx, ale_entry);
 		type = cpsw_ale_get_entry_type(ale_entry);
 		if (type != ALE_TYPE_VLAN)
 			continue;
+		vlan_members =
+			cpsw_ale_get_vlan_member_list(ale_entry,
+						      ale->vlan_field_bits);
+
+		if (port != -1 && !(vlan_members & BIT(port)))
+			continue;
 
 		unreg_mcast =
 			cpsw_ale_get_vlan_unreg_mcast(ale_entry,
 						      ale->vlan_field_bits);
 		if (allmulti)
-			unreg_mcast |= 1;
+			unreg_mcast |= ALE_PORT_HOST;
 		else
-			unreg_mcast &= ~1;
+			unreg_mcast &= ~ALE_PORT_HOST;
 		cpsw_ale_set_vlan_unreg_mcast(ale_entry, unreg_mcast,
 					      ale->vlan_field_bits);
 		cpsw_ale_write(ale, idx, ale_entry);
 	}
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_set_allmulti);
 
 struct ale_control_info {
 	const char	*name;
@@ -739,7 +728,6 @@ int cpsw_ale_control_set(struct cpsw_ale *ale, int port, int control,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_control_set);
 
 int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control)
 {
@@ -763,7 +751,6 @@ int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control)
 	tmp = readl_relaxed(ale->params.ale_regs + offset) >> shift;
 	return tmp & BITMASK(info->bits);
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_control_get);
 
 static void cpsw_ale_timer(struct timer_list *t)
 {
@@ -788,14 +775,12 @@ void cpsw_ale_start(struct cpsw_ale *ale)
 		add_timer(&ale->timer);
 	}
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_start);
 
 void cpsw_ale_stop(struct cpsw_ale *ale)
 {
 	del_timer_sync(&ale->timer);
 	cpsw_ale_control_set(ale, 0, ALE_ENABLE, 0);
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_stop);
 
 struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params)
 {
@@ -879,7 +864,6 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params)
 
 	return ale;
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_create);
 
 void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data)
 {
@@ -890,8 +874,3 @@ void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data)
 		data += ALE_ENTRY_WORDS;
 	}
 }
-EXPORT_SYMBOL_GPL(cpsw_ale_dump);
-
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("TI CPSW ALE driver");
-MODULE_AUTHOR("Texas Instruments");
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index cd07a3e96d57..370df254eb12 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -1,16 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Texas Instruments N-Port Ethernet Switch Address Lookup Engine APIs
  *
  * Copyright (C) 2012 Texas Instruments
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef __TI_CPSW_ALE_H__
 #define __TI_CPSW_ALE_H__
@@ -37,7 +30,6 @@ struct cpsw_ale {
 	struct cpsw_ale_params	params;
 	struct timer_list	timer;
 	unsigned long		ageout;
-	int			allmulti;
 	u32			version;
 	/* These bits are different on NetCP NU Switch ALE */
 	u32			port_mask_bits;
@@ -116,7 +108,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, const u8 *addr, int port_mask,
 int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port, int untag,
 			int reg_mcast, int unreg_mcast);
 int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port);
-void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti);
+void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti, int port);
 
 int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control);
 int cpsw_ale_control_set(struct cpsw_ale *ale, int port,
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
new file mode 100644
index 000000000000..31248a6cc642
--- /dev/null
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -0,0 +1,746 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Texas Instruments Ethernet Switch Driver ethtool intf
+ *
+ * Copyright (C) 2019 Texas Instruments
+ */
+
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/kmemleak.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/phy.h>
+#include <linux/pm_runtime.h>
+#include <linux/skbuff.h>
+
+#include "cpsw.h"
+#include "cpts.h"
+#include "cpsw_ale.h"
+#include "cpsw_priv.h"
+#include "davinci_cpdma.h"
+
+struct cpsw_hw_stats {
+	u32	rxgoodframes;
+	u32	rxbroadcastframes;
+	u32	rxmulticastframes;
+	u32	rxpauseframes;
+	u32	rxcrcerrors;
+	u32	rxaligncodeerrors;
+	u32	rxoversizedframes;
+	u32	rxjabberframes;
+	u32	rxundersizedframes;
+	u32	rxfragments;
+	u32	__pad_0[2];
+	u32	rxoctets;
+	u32	txgoodframes;
+	u32	txbroadcastframes;
+	u32	txmulticastframes;
+	u32	txpauseframes;
+	u32	txdeferredframes;
+	u32	txcollisionframes;
+	u32	txsinglecollframes;
+	u32	txmultcollframes;
+	u32	txexcessivecollisions;
+	u32	txlatecollisions;
+	u32	txunderrun;
+	u32	txcarriersenseerrors;
+	u32	txoctets;
+	u32	octetframes64;
+	u32	octetframes65t127;
+	u32	octetframes128t255;
+	u32	octetframes256t511;
+	u32	octetframes512t1023;
+	u32	octetframes1024tup;
+	u32	netoctets;
+	u32	rxsofoverruns;
+	u32	rxmofoverruns;
+	u32	rxdmaoverruns;
+};
+
+struct cpsw_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int type;
+	int sizeof_stat;
+	int stat_offset;
+};
+
+enum {
+	CPSW_STATS,
+	CPDMA_RX_STATS,
+	CPDMA_TX_STATS,
+};
+
+#define CPSW_STAT(m)		CPSW_STATS,				\
+				FIELD_SIZEOF(struct cpsw_hw_stats, m), \
+				offsetof(struct cpsw_hw_stats, m)
+#define CPDMA_RX_STAT(m)	CPDMA_RX_STATS,				   \
+				FIELD_SIZEOF(struct cpdma_chan_stats, m), \
+				offsetof(struct cpdma_chan_stats, m)
+#define CPDMA_TX_STAT(m)	CPDMA_TX_STATS,				   \
+				FIELD_SIZEOF(struct cpdma_chan_stats, m), \
+				offsetof(struct cpdma_chan_stats, m)
+
+static const struct cpsw_stats cpsw_gstrings_stats[] = {
+	{ "Good Rx Frames", CPSW_STAT(rxgoodframes) },
+	{ "Broadcast Rx Frames", CPSW_STAT(rxbroadcastframes) },
+	{ "Multicast Rx Frames", CPSW_STAT(rxmulticastframes) },
+	{ "Pause Rx Frames", CPSW_STAT(rxpauseframes) },
+	{ "Rx CRC Errors", CPSW_STAT(rxcrcerrors) },
+	{ "Rx Align/Code Errors", CPSW_STAT(rxaligncodeerrors) },
+	{ "Oversize Rx Frames", CPSW_STAT(rxoversizedframes) },
+	{ "Rx Jabbers", CPSW_STAT(rxjabberframes) },
+	{ "Undersize (Short) Rx Frames", CPSW_STAT(rxundersizedframes) },
+	{ "Rx Fragments", CPSW_STAT(rxfragments) },
+	{ "Rx Octets", CPSW_STAT(rxoctets) },
+	{ "Good Tx Frames", CPSW_STAT(txgoodframes) },
+	{ "Broadcast Tx Frames", CPSW_STAT(txbroadcastframes) },
+	{ "Multicast Tx Frames", CPSW_STAT(txmulticastframes) },
+	{ "Pause Tx Frames", CPSW_STAT(txpauseframes) },
+	{ "Deferred Tx Frames", CPSW_STAT(txdeferredframes) },
+	{ "Collisions", CPSW_STAT(txcollisionframes) },
+	{ "Single Collision Tx Frames", CPSW_STAT(txsinglecollframes) },
+	{ "Multiple Collision Tx Frames", CPSW_STAT(txmultcollframes) },
+	{ "Excessive Collisions", CPSW_STAT(txexcessivecollisions) },
+	{ "Late Collisions", CPSW_STAT(txlatecollisions) },
+	{ "Tx Underrun", CPSW_STAT(txunderrun) },
+	{ "Carrier Sense Errors", CPSW_STAT(txcarriersenseerrors) },
+	{ "Tx Octets", CPSW_STAT(txoctets) },
+	{ "Rx + Tx 64 Octet Frames", CPSW_STAT(octetframes64) },
+	{ "Rx + Tx 65-127 Octet Frames", CPSW_STAT(octetframes65t127) },
+	{ "Rx + Tx 128-255 Octet Frames", CPSW_STAT(octetframes128t255) },
+	{ "Rx + Tx 256-511 Octet Frames", CPSW_STAT(octetframes256t511) },
+	{ "Rx + Tx 512-1023 Octet Frames", CPSW_STAT(octetframes512t1023) },
+	{ "Rx + Tx 1024-Up Octet Frames", CPSW_STAT(octetframes1024tup) },
+	{ "Net Octets", CPSW_STAT(netoctets) },
+	{ "Rx Start of Frame Overruns", CPSW_STAT(rxsofoverruns) },
+	{ "Rx Middle of Frame Overruns", CPSW_STAT(rxmofoverruns) },
+	{ "Rx DMA Overruns", CPSW_STAT(rxdmaoverruns) },
+};
+
+static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
+	{ "head_enqueue", CPDMA_RX_STAT(head_enqueue) },
+	{ "tail_enqueue", CPDMA_RX_STAT(tail_enqueue) },
+	{ "pad_enqueue", CPDMA_RX_STAT(pad_enqueue) },
+	{ "misqueued", CPDMA_RX_STAT(misqueued) },
+	{ "desc_alloc_fail", CPDMA_RX_STAT(desc_alloc_fail) },
+	{ "pad_alloc_fail", CPDMA_RX_STAT(pad_alloc_fail) },
+	{ "runt_receive_buf", CPDMA_RX_STAT(runt_receive_buff) },
+	{ "runt_transmit_buf", CPDMA_RX_STAT(runt_transmit_buff) },
+	{ "empty_dequeue", CPDMA_RX_STAT(empty_dequeue) },
+	{ "busy_dequeue", CPDMA_RX_STAT(busy_dequeue) },
+	{ "good_dequeue", CPDMA_RX_STAT(good_dequeue) },
+	{ "requeue", CPDMA_RX_STAT(requeue) },
+	{ "teardown_dequeue", CPDMA_RX_STAT(teardown_dequeue) },
+};
+
+#define CPSW_STATS_COMMON_LEN	ARRAY_SIZE(cpsw_gstrings_stats)
+#define CPSW_STATS_CH_LEN	ARRAY_SIZE(cpsw_gstrings_ch_stats)
+
+u32 cpsw_get_msglevel(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	return priv->msg_enable;
+}
+
+void cpsw_set_msglevel(struct net_device *ndev, u32 value)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	priv->msg_enable = value;
+}
+
+int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	coal->rx_coalesce_usecs = cpsw->coal_intvl;
+	return 0;
+}
+
+int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	u32 int_ctrl;
+	u32 num_interrupts = 0;
+	u32 prescale = 0;
+	u32 addnl_dvdr = 1;
+	u32 coal_intvl = 0;
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	coal_intvl = coal->rx_coalesce_usecs;
+
+	int_ctrl =  readl(&cpsw->wr_regs->int_control);
+	prescale = cpsw->bus_freq_mhz * 4;
+
+	if (!coal->rx_coalesce_usecs) {
+		int_ctrl &= ~(CPSW_INTPRESCALE_MASK | CPSW_INTPACEEN);
+		goto update_return;
+	}
+
+	if (coal_intvl < CPSW_CMINTMIN_INTVL)
+		coal_intvl = CPSW_CMINTMIN_INTVL;
+
+	if (coal_intvl > CPSW_CMINTMAX_INTVL) {
+		/* Interrupt pacer works with 4us Pulse, we can
+		 * throttle further by dilating the 4us pulse.
+		 */
+		addnl_dvdr = CPSW_INTPRESCALE_MASK / prescale;
+
+		if (addnl_dvdr > 1) {
+			prescale *= addnl_dvdr;
+			if (coal_intvl > (CPSW_CMINTMAX_INTVL * addnl_dvdr))
+				coal_intvl = (CPSW_CMINTMAX_INTVL
+						* addnl_dvdr);
+		} else {
+			addnl_dvdr = 1;
+			coal_intvl = CPSW_CMINTMAX_INTVL;
+		}
+	}
+
+	num_interrupts = (1000 * addnl_dvdr) / coal_intvl;
+	writel(num_interrupts, &cpsw->wr_regs->rx_imax);
+	writel(num_interrupts, &cpsw->wr_regs->tx_imax);
+
+	int_ctrl |= CPSW_INTPACEEN;
+	int_ctrl &= (~CPSW_INTPRESCALE_MASK);
+	int_ctrl |= (prescale & CPSW_INTPRESCALE_MASK);
+
+update_return:
+	writel(int_ctrl, &cpsw->wr_regs->int_control);
+
+	cpsw_notice(priv, timer, "Set coalesce to %d usecs.\n", coal_intvl);
+	cpsw->coal_intvl = coal_intvl;
+
+	return 0;
+}
+
+int cpsw_get_sset_count(struct net_device *ndev, int sset)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return (CPSW_STATS_COMMON_LEN +
+		       (cpsw->rx_ch_num + cpsw->tx_ch_num) *
+		       CPSW_STATS_CH_LEN);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void cpsw_add_ch_strings(u8 **p, int ch_num, int rx_dir)
+{
+	int ch_stats_len;
+	int line;
+	int i;
+
+	ch_stats_len = CPSW_STATS_CH_LEN * ch_num;
+	for (i = 0; i < ch_stats_len; i++) {
+		line = i % CPSW_STATS_CH_LEN;
+		snprintf(*p, ETH_GSTRING_LEN,
+			 "%s DMA chan %ld: %s", rx_dir ? "Rx" : "Tx",
+			 (long)(i / CPSW_STATS_CH_LEN),
+			 cpsw_gstrings_ch_stats[line].stat_string);
+		*p += ETH_GSTRING_LEN;
+	}
+}
+
+void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	u8 *p = data;
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < CPSW_STATS_COMMON_LEN; i++) {
+			memcpy(p, cpsw_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
+		cpsw_add_ch_strings(&p, cpsw->rx_ch_num, 1);
+		cpsw_add_ch_strings(&p, cpsw->tx_ch_num, 0);
+		break;
+	}
+}
+
+void cpsw_get_ethtool_stats(struct net_device *ndev,
+			    struct ethtool_stats *stats, u64 *data)
+{
+	u8 *p;
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpdma_chan_stats ch_stats;
+	int i, l, ch;
+
+	/* Collect Davinci CPDMA stats for Rx and Tx Channel */
+	for (l = 0; l < CPSW_STATS_COMMON_LEN; l++)
+		data[l] = readl(cpsw->hw_stats +
+				cpsw_gstrings_stats[l].stat_offset);
+
+	for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+		cpdma_chan_get_stats(cpsw->rxv[ch].ch, &ch_stats);
+		for (i = 0; i < CPSW_STATS_CH_LEN; i++, l++) {
+			p = (u8 *)&ch_stats +
+				cpsw_gstrings_ch_stats[i].stat_offset;
+			data[l] = *(u32 *)p;
+		}
+	}
+
+	for (ch = 0; ch < cpsw->tx_ch_num; ch++) {
+		cpdma_chan_get_stats(cpsw->txv[ch].ch, &ch_stats);
+		for (i = 0; i < CPSW_STATS_CH_LEN; i++, l++) {
+			p = (u8 *)&ch_stats +
+				cpsw_gstrings_ch_stats[i].stat_offset;
+			data[l] = *(u32 *)p;
+		}
+	}
+}
+
+void cpsw_get_pauseparam(struct net_device *ndev,
+			 struct ethtool_pauseparam *pause)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+
+	pause->autoneg = AUTONEG_DISABLE;
+	pause->rx_pause = priv->rx_pause ? true : false;
+	pause->tx_pause = priv->tx_pause ? true : false;
+}
+
+void cpsw_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	wol->supported = 0;
+	wol->wolopts = 0;
+
+	if (cpsw->slaves[slave_no].phy)
+		phy_ethtool_get_wol(cpsw->slaves[slave_no].phy, wol);
+}
+
+int cpsw_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return phy_ethtool_set_wol(cpsw->slaves[slave_no].phy, wol);
+	else
+		return -EOPNOTSUPP;
+}
+
+int cpsw_get_regs_len(struct net_device *ndev)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	return cpsw->data.ale_entries * ALE_ENTRY_WORDS * sizeof(u32);
+}
+
+void cpsw_get_regs(struct net_device *ndev, struct ethtool_regs *regs, void *p)
+{
+	u32 *reg = p;
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	/* update CPSW IP version */
+	regs->version = cpsw->version;
+
+	cpsw_ale_dump(cpsw->ale, reg);
+}
+
+int cpsw_ethtool_op_begin(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int ret;
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		cpsw_err(priv, drv, "ethtool begin failed %d\n", ret);
+		pm_runtime_put_noidle(cpsw->dev);
+	}
+
+	return ret;
+}
+
+void cpsw_ethtool_op_complete(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = pm_runtime_put(priv->cpsw->dev);
+	if (ret < 0)
+		cpsw_err(priv, drv, "ethtool complete failed %d\n", ret);
+}
+
+void cpsw_get_channels(struct net_device *ndev, struct ethtool_channels *ch)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	ch->max_rx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
+	ch->max_tx = cpsw->quirk_irq ? 1 : CPSW_MAX_QUEUES;
+	ch->max_combined = 0;
+	ch->max_other = 0;
+	ch->other_count = 0;
+	ch->rx_count = cpsw->rx_ch_num;
+	ch->tx_count = cpsw->tx_ch_num;
+	ch->combined_count = 0;
+}
+
+int cpsw_get_link_ksettings(struct net_device *ndev,
+			    struct ethtool_link_ksettings *ecmd)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (!cpsw->slaves[slave_no].phy)
+		return -EOPNOTSUPP;
+
+	phy_ethtool_ksettings_get(cpsw->slaves[slave_no].phy, ecmd);
+	return 0;
+}
+
+int cpsw_set_link_ksettings(struct net_device *ndev,
+			    const struct ethtool_link_ksettings *ecmd)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (!cpsw->slaves[slave_no].phy)
+		return -EOPNOTSUPP;
+
+	return phy_ethtool_ksettings_set(cpsw->slaves[slave_no].phy, ecmd);
+}
+
+int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return phy_ethtool_get_eee(cpsw->slaves[slave_no].phy, edata);
+	else
+		return -EOPNOTSUPP;
+}
+
+int cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return phy_ethtool_set_eee(cpsw->slaves[slave_no].phy, edata);
+	else
+		return -EOPNOTSUPP;
+}
+
+int cpsw_nway_reset(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int slave_no = cpsw_slave_index(cpsw, priv);
+
+	if (cpsw->slaves[slave_no].phy)
+		return genphy_restart_aneg(cpsw->slaves[slave_no].phy);
+	else
+		return -EOPNOTSUPP;
+}
+
+static void cpsw_suspend_data_pass(struct net_device *ndev)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	int i;
+
+	/* Disable NAPI scheduling */
+	cpsw_intr_disable(cpsw);
+
+	/* Stop all transmit queues for every network device.
+	 */
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (!(ndev && netif_running(ndev)))
+			continue;
+
+		netif_tx_stop_all_queues(ndev);
+
+		/* Barrier, so that stop_queue visible to other cpus */
+		smp_mb__after_atomic();
+	}
+
+	/* Handle rest of tx packets and stop cpdma channels */
+	cpdma_ctlr_stop(cpsw->dma);
+}
+
+static int cpsw_resume_data_pass(struct net_device *ndev)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int i, ret;
+
+	/* After this receive is started */
+	if (cpsw->usage_count) {
+		ret = cpsw_fill_rx_channels(priv);
+		if (ret)
+			return ret;
+
+		cpdma_ctlr_start(cpsw->dma);
+		cpsw_intr_enable(cpsw);
+	}
+
+	/* Resume transmit for every affected interface */
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (ndev && netif_running(ndev))
+			netif_tx_start_all_queues(ndev);
+	}
+
+	return 0;
+}
+
+static int cpsw_check_ch_settings(struct cpsw_common *cpsw,
+				  struct ethtool_channels *ch)
+{
+	if (cpsw->quirk_irq) {
+		dev_err(cpsw->dev, "Maximum one tx/rx queue is allowed");
+		return -EOPNOTSUPP;
+	}
+
+	if (ch->combined_count)
+		return -EINVAL;
+
+	/* verify we have at least one channel in each direction */
+	if (!ch->rx_count || !ch->tx_count)
+		return -EINVAL;
+
+	if (ch->rx_count > cpsw->data.channels ||
+	    ch->tx_count > cpsw->data.channels)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
+				    cpdma_handler_fn rx_handler)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	void (*handler)(void *, int, int);
+	struct netdev_queue *queue;
+	struct cpsw_vector *vec;
+	int ret, *ch, vch;
+
+	if (rx) {
+		ch = &cpsw->rx_ch_num;
+		vec = cpsw->rxv;
+		handler = rx_handler;
+	} else {
+		ch = &cpsw->tx_ch_num;
+		vec = cpsw->txv;
+		handler = cpsw_tx_handler;
+	}
+
+	while (*ch < ch_num) {
+		vch = rx ? *ch : 7 - *ch;
+		vec[*ch].ch = cpdma_chan_create(cpsw->dma, vch, handler, rx);
+		queue = netdev_get_tx_queue(priv->ndev, *ch);
+		queue->tx_maxrate = 0;
+
+		if (IS_ERR(vec[*ch].ch))
+			return PTR_ERR(vec[*ch].ch);
+
+		if (!vec[*ch].ch)
+			return -EINVAL;
+
+		cpsw_info(priv, ifup, "created new %d %s channel\n", *ch,
+			  (rx ? "rx" : "tx"));
+		(*ch)++;
+	}
+
+	while (*ch > ch_num) {
+		(*ch)--;
+
+		ret = cpdma_chan_destroy(vec[*ch].ch);
+		if (ret)
+			return ret;
+
+		cpsw_info(priv, ifup, "destroyed %d %s channel\n", *ch,
+			  (rx ? "rx" : "tx"));
+	}
+
+	return 0;
+}
+
+static void cpsw_fail(struct cpsw_common *cpsw)
+{
+	struct net_device *ndev;
+	int i;
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		ndev = cpsw->slaves[i].ndev;
+		if (ndev)
+			dev_close(ndev);
+	}
+}
+
+int cpsw_set_channels_common(struct net_device *ndev,
+			     struct ethtool_channels *chs,
+			     cpdma_handler_fn rx_handler)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct net_device *sl_ndev;
+	int i, new_pools, ret;
+
+	ret = cpsw_check_ch_settings(cpsw, chs);
+	if (ret < 0)
+		return ret;
+
+	cpsw_suspend_data_pass(ndev);
+
+	new_pools = (chs->rx_count != cpsw->rx_ch_num) && cpsw->usage_count;
+
+	ret = cpsw_update_channels_res(priv, chs->rx_count, 1, rx_handler);
+	if (ret)
+		goto err;
+
+	ret = cpsw_update_channels_res(priv, chs->tx_count, 0, rx_handler);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		sl_ndev = cpsw->slaves[i].ndev;
+		if (!(sl_ndev && netif_running(sl_ndev)))
+			continue;
+
+		/* Inform stack about new count of queues */
+		ret = netif_set_real_num_tx_queues(sl_ndev, cpsw->tx_ch_num);
+		if (ret) {
+			dev_err(priv->dev, "cannot set real number of tx queues\n");
+			goto err;
+		}
+
+		ret = netif_set_real_num_rx_queues(sl_ndev, cpsw->rx_ch_num);
+		if (ret) {
+			dev_err(priv->dev, "cannot set real number of rx queues\n");
+			goto err;
+		}
+	}
+
+	cpsw_split_res(cpsw);
+
+	if (new_pools) {
+		cpsw_destroy_xdp_rxqs(cpsw);
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret)
+			goto err;
+	}
+
+	ret = cpsw_resume_data_pass(ndev);
+	if (!ret)
+		return 0;
+err:
+	dev_err(priv->dev, "cannot update channels number, closing device\n");
+	cpsw_fail(cpsw);
+	return ret;
+}
+
+void cpsw_get_ringparam(struct net_device *ndev,
+			struct ethtool_ringparam *ering)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	/* not supported */
+	ering->tx_max_pending = cpsw->descs_pool_size - CPSW_MAX_QUEUES;
+	ering->tx_pending = cpdma_get_num_tx_descs(cpsw->dma);
+	ering->rx_max_pending = cpsw->descs_pool_size - CPSW_MAX_QUEUES;
+	ering->rx_pending = cpdma_get_num_rx_descs(cpsw->dma);
+}
+
+int cpsw_set_ringparam(struct net_device *ndev,
+		       struct ethtool_ringparam *ering)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	int descs_num, ret;
+
+	/* ignore ering->tx_pending - only rx_pending adjustment is supported */
+
+	if (ering->rx_mini_pending || ering->rx_jumbo_pending ||
+	    ering->rx_pending < CPSW_MAX_QUEUES ||
+	    ering->rx_pending > (cpsw->descs_pool_size - CPSW_MAX_QUEUES))
+		return -EINVAL;
+
+	descs_num = cpdma_get_num_rx_descs(cpsw->dma);
+	if (ering->rx_pending == descs_num)
+		return 0;
+
+	cpsw_suspend_data_pass(ndev);
+
+	ret = cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
+	if (ret) {
+		if (cpsw_resume_data_pass(ndev))
+			goto err;
+
+		return ret;
+	}
+
+	if (cpsw->usage_count) {
+		cpsw_destroy_xdp_rxqs(cpsw);
+		ret = cpsw_create_xdp_rxqs(cpsw);
+		if (ret)
+			goto err;
+	}
+
+	ret = cpsw_resume_data_pass(ndev);
+	if (!ret)
+		return 0;
+err:
+	cpdma_set_num_rx_descs(cpsw->dma, descs_num);
+	dev_err(cpsw->dev, "cannot set ring params, closing device\n");
+	cpsw_fail(cpsw);
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_TI_CPTS)
+int cpsw_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *info)
+{
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->phc_index = cpsw->cpts->phc_index;
+	info->tx_types =
+		(1 << HWTSTAMP_TX_OFF) |
+		(1 << HWTSTAMP_TX_ON);
+	info->rx_filters =
+		(1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
+	return 0;
+}
+#else
+int cpsw_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *info)
+{
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE;
+	info->phc_index = -1;
+	info->tx_types = 0;
+	info->rx_filters = 0;
+	return 0;
+}
+#endif
diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c
new file mode 100644
index 000000000000..476d050a022c
--- /dev/null
+++ b/drivers/net/ethernet/ti/cpsw_priv.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Texas Instruments Ethernet Switch Driver
+ *
+ * Copyright (C) 2019 Texas Instruments
+ */
+
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/skbuff.h>
+
+#include "cpts.h"
+#include "cpsw_ale.h"
+#include "cpsw_priv.h"
+#include "cpsw_sl.h"
+#include "davinci_cpdma.h"
+
+int cpsw_init_common(struct cpsw_common *cpsw, void __iomem *ss_regs,
+		     int ale_ageout, phys_addr_t desc_mem_phys,
+		     int descs_pool_size)
+{
+	u32 slave_offset, sliver_offset, slave_size;
+	struct cpsw_ale_params ale_params;
+	struct cpsw_platform_data *data;
+	struct cpdma_params dma_params;
+	struct device *dev = cpsw->dev;
+	void __iomem *cpts_regs;
+	int ret = 0, i;
+
+	data = &cpsw->data;
+	cpsw->rx_ch_num = 1;
+	cpsw->tx_ch_num = 1;
+
+	cpsw->version = readl(&cpsw->regs->id_ver);
+
+	memset(&dma_params, 0, sizeof(dma_params));
+	memset(&ale_params, 0, sizeof(ale_params));
+
+	switch (cpsw->version) {
+	case CPSW_VERSION_1:
+		cpsw->host_port_regs = ss_regs + CPSW1_HOST_PORT_OFFSET;
+		cpts_regs	     = ss_regs + CPSW1_CPTS_OFFSET;
+		cpsw->hw_stats	     = ss_regs + CPSW1_HW_STATS;
+		dma_params.dmaregs   = ss_regs + CPSW1_CPDMA_OFFSET;
+		dma_params.txhdp     = ss_regs + CPSW1_STATERAM_OFFSET;
+		ale_params.ale_regs  = ss_regs + CPSW1_ALE_OFFSET;
+		slave_offset         = CPSW1_SLAVE_OFFSET;
+		slave_size           = CPSW1_SLAVE_SIZE;
+		sliver_offset        = CPSW1_SLIVER_OFFSET;
+		dma_params.desc_mem_phys = 0;
+		break;
+	case CPSW_VERSION_2:
+	case CPSW_VERSION_3:
+	case CPSW_VERSION_4:
+		cpsw->host_port_regs = ss_regs + CPSW2_HOST_PORT_OFFSET;
+		cpts_regs	     = ss_regs + CPSW2_CPTS_OFFSET;
+		cpsw->hw_stats	     = ss_regs + CPSW2_HW_STATS;
+		dma_params.dmaregs   = ss_regs + CPSW2_CPDMA_OFFSET;
+		dma_params.txhdp     = ss_regs + CPSW2_STATERAM_OFFSET;
+		ale_params.ale_regs  = ss_regs + CPSW2_ALE_OFFSET;
+		slave_offset         = CPSW2_SLAVE_OFFSET;
+		slave_size           = CPSW2_SLAVE_SIZE;
+		sliver_offset        = CPSW2_SLIVER_OFFSET;
+		dma_params.desc_mem_phys = desc_mem_phys;
+		break;
+	default:
+		dev_err(dev, "unknown version 0x%08x\n", cpsw->version);
+		return -ENODEV;
+	}
+
+	for (i = 0; i < cpsw->data.slaves; i++) {
+		struct cpsw_slave *slave = &cpsw->slaves[i];
+		void __iomem		*regs = cpsw->regs;
+
+		slave->slave_num = i;
+		slave->data	= &cpsw->data.slave_data[i];
+		slave->regs	= regs + slave_offset;
+		slave->port_vlan = slave->data->dual_emac_res_vlan;
+		slave->mac_sl = cpsw_sl_get("cpsw", dev, regs + sliver_offset);
+		if (IS_ERR(slave->mac_sl))
+			return PTR_ERR(slave->mac_sl);
+
+		slave_offset  += slave_size;
+		sliver_offset += SLIVER_SIZE;
+	}
+
+	ale_params.dev			= dev;
+	ale_params.ale_ageout		= ale_ageout;
+	ale_params.ale_entries		= data->ale_entries;
+	ale_params.ale_ports		= CPSW_ALE_PORTS_NUM;
+
+	cpsw->ale = cpsw_ale_create(&ale_params);
+	if (!cpsw->ale) {
+		dev_err(dev, "error initializing ale engine\n");
+		return -ENODEV;
+	}
+
+	dma_params.dev		= dev;
+	dma_params.rxthresh	= dma_params.dmaregs + CPDMA_RXTHRESH;
+	dma_params.rxfree	= dma_params.dmaregs + CPDMA_RXFREE;
+	dma_params.rxhdp	= dma_params.txhdp + CPDMA_RXHDP;
+	dma_params.txcp		= dma_params.txhdp + CPDMA_TXCP;
+	dma_params.rxcp		= dma_params.txhdp + CPDMA_RXCP;
+
+	dma_params.num_chan		= data->channels;
+	dma_params.has_soft_reset	= true;
+	dma_params.min_packet_size	= CPSW_MIN_PACKET_SIZE;
+	dma_params.desc_mem_size	= data->bd_ram_size;
+	dma_params.desc_align		= 16;
+	dma_params.has_ext_regs		= true;
+	dma_params.desc_hw_addr         = dma_params.desc_mem_phys;
+	dma_params.bus_freq_mhz		= cpsw->bus_freq_mhz;
+	dma_params.descs_pool_size	= descs_pool_size;
+
+	cpsw->dma = cpdma_ctlr_create(&dma_params);
+	if (!cpsw->dma) {
+		dev_err(dev, "error initializing dma\n");
+		return -ENOMEM;
+	}
+
+	cpsw->cpts = cpts_create(cpsw->dev, cpts_regs, cpsw->dev->of_node);
+	if (IS_ERR(cpsw->cpts)) {
+		ret = PTR_ERR(cpsw->cpts);
+		cpdma_ctlr_destroy(cpsw->dma);
+	}
+
+	return ret;
+}
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
new file mode 100644
index 000000000000..362c5a986869
--- /dev/null
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -0,0 +1,437 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Texas Instruments Ethernet Switch Driver
+ */
+
+#ifndef DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
+#define DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_
+
+#include "davinci_cpdma.h"
+
+#define CPSW_DEBUG	(NETIF_MSG_HW		| NETIF_MSG_WOL		| \
+			 NETIF_MSG_DRV		| NETIF_MSG_LINK	| \
+			 NETIF_MSG_IFUP		| NETIF_MSG_INTR	| \
+			 NETIF_MSG_PROBE	| NETIF_MSG_TIMER	| \
+			 NETIF_MSG_IFDOWN	| NETIF_MSG_RX_ERR	| \
+			 NETIF_MSG_TX_ERR	| NETIF_MSG_TX_DONE	| \
+			 NETIF_MSG_PKTDATA	| NETIF_MSG_TX_QUEUED	| \
+			 NETIF_MSG_RX_STATUS)
+
+#define cpsw_info(priv, type, format, ...)		\
+do {								\
+	if (netif_msg_##type(priv) && net_ratelimit())		\
+		dev_info(priv->dev, format, ## __VA_ARGS__);	\
+} while (0)
+
+#define cpsw_err(priv, type, format, ...)		\
+do {								\
+	if (netif_msg_##type(priv) && net_ratelimit())		\
+		dev_err(priv->dev, format, ## __VA_ARGS__);	\
+} while (0)
+
+#define cpsw_dbg(priv, type, format, ...)		\
+do {								\
+	if (netif_msg_##type(priv) && net_ratelimit())		\
+		dev_dbg(priv->dev, format, ## __VA_ARGS__);	\
+} while (0)
+
+#define cpsw_notice(priv, type, format, ...)		\
+do {								\
+	if (netif_msg_##type(priv) && net_ratelimit())		\
+		dev_notice(priv->dev, format, ## __VA_ARGS__);	\
+} while (0)
+
+#define ALE_ALL_PORTS		0x7
+
+#define CPSW_MAJOR_VERSION(reg)		(reg >> 8 & 0x7)
+#define CPSW_MINOR_VERSION(reg)		(reg & 0xff)
+#define CPSW_RTL_VERSION(reg)		((reg >> 11) & 0x1f)
+
+#define CPSW_VERSION_1		0x19010a
+#define CPSW_VERSION_2		0x19010c
+#define CPSW_VERSION_3		0x19010f
+#define CPSW_VERSION_4		0x190112
+
+#define HOST_PORT_NUM		0
+#define CPSW_ALE_PORTS_NUM	3
+#define SLIVER_SIZE		0x40
+
+#define CPSW1_HOST_PORT_OFFSET	0x028
+#define CPSW1_SLAVE_OFFSET	0x050
+#define CPSW1_SLAVE_SIZE	0x040
+#define CPSW1_CPDMA_OFFSET	0x100
+#define CPSW1_STATERAM_OFFSET	0x200
+#define CPSW1_HW_STATS		0x400
+#define CPSW1_CPTS_OFFSET	0x500
+#define CPSW1_ALE_OFFSET	0x600
+#define CPSW1_SLIVER_OFFSET	0x700
+
+#define CPSW2_HOST_PORT_OFFSET	0x108
+#define CPSW2_SLAVE_OFFSET	0x200
+#define CPSW2_SLAVE_SIZE	0x100
+#define CPSW2_CPDMA_OFFSET	0x800
+#define CPSW2_HW_STATS		0x900
+#define CPSW2_STATERAM_OFFSET	0xa00
+#define CPSW2_CPTS_OFFSET	0xc00
+#define CPSW2_ALE_OFFSET	0xd00
+#define CPSW2_SLIVER_OFFSET	0xd80
+#define CPSW2_BD_OFFSET		0x2000
+
+#define CPDMA_RXTHRESH		0x0c0
+#define CPDMA_RXFREE		0x0e0
+#define CPDMA_TXHDP		0x00
+#define CPDMA_RXHDP		0x20
+#define CPDMA_TXCP		0x40
+#define CPDMA_RXCP		0x60
+
+#define CPSW_POLL_WEIGHT	64
+#define CPSW_RX_VLAN_ENCAP_HDR_SIZE		4
+#define CPSW_MIN_PACKET_SIZE	(VLAN_ETH_ZLEN)
+#define CPSW_MAX_PACKET_SIZE	(VLAN_ETH_FRAME_LEN +\
+				 ETH_FCS_LEN +\
+				 CPSW_RX_VLAN_ENCAP_HDR_SIZE)
+
+#define RX_PRIORITY_MAPPING	0x76543210
+#define TX_PRIORITY_MAPPING	0x33221100
+#define CPDMA_TX_PRIORITY_MAP	0x76543210
+
+#define CPSW_VLAN_AWARE		BIT(1)
+#define CPSW_RX_VLAN_ENCAP	BIT(2)
+#define CPSW_ALE_VLAN_AWARE	1
+
+#define CPSW_FIFO_NORMAL_MODE		(0 << 16)
+#define CPSW_FIFO_DUAL_MAC_MODE		(1 << 16)
+#define CPSW_FIFO_RATE_LIMIT_MODE	(2 << 16)
+
+#define CPSW_INTPACEEN		(0x3f << 16)
+#define CPSW_INTPRESCALE_MASK	(0x7FF << 0)
+#define CPSW_CMINTMAX_CNT	63
+#define CPSW_CMINTMIN_CNT	2
+#define CPSW_CMINTMAX_INTVL	(1000 / CPSW_CMINTMIN_CNT)
+#define CPSW_CMINTMIN_INTVL	((1000 / CPSW_CMINTMAX_CNT) + 1)
+
+#define IRQ_NUM			2
+#define CPSW_MAX_QUEUES		8
+#define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256
+#define CPSW_FIFO_QUEUE_TYPE_SHIFT	16
+#define CPSW_FIFO_SHAPE_EN_SHIFT	16
+#define CPSW_FIFO_RATE_EN_SHIFT		20
+#define CPSW_TC_NUM			4
+#define CPSW_FIFO_SHAPERS_NUM		(CPSW_TC_NUM - 1)
+#define CPSW_PCT_MASK			0x7f
+
+#define CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT	29
+#define CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK		GENMASK(2, 0)
+#define CPSW_RX_VLAN_ENCAP_HDR_VID_SHIFT	16
+#define CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_SHIFT	8
+#define CPSW_RX_VLAN_ENCAP_HDR_PKT_TYPE_MSK	GENMASK(1, 0)
+enum {
+	CPSW_RX_VLAN_ENCAP_HDR_PKT_VLAN_TAG = 0,
+	CPSW_RX_VLAN_ENCAP_HDR_PKT_RESERV,
+	CPSW_RX_VLAN_ENCAP_HDR_PKT_PRIO_TAG,
+	CPSW_RX_VLAN_ENCAP_HDR_PKT_UNTAG,
+};
+
+struct cpsw_wr_regs {
+	u32	id_ver;
+	u32	soft_reset;
+	u32	control;
+	u32	int_control;
+	u32	rx_thresh_en;
+	u32	rx_en;
+	u32	tx_en;
+	u32	misc_en;
+	u32	mem_allign1[8];
+	u32	rx_thresh_stat;
+	u32	rx_stat;
+	u32	tx_stat;
+	u32	misc_stat;
+	u32	mem_allign2[8];
+	u32	rx_imax;
+	u32	tx_imax;
+
+};
+
+struct cpsw_ss_regs {
+	u32	id_ver;
+	u32	control;
+	u32	soft_reset;
+	u32	stat_port_en;
+	u32	ptype;
+	u32	soft_idle;
+	u32	thru_rate;
+	u32	gap_thresh;
+	u32	tx_start_wds;
+	u32	flow_control;
+	u32	vlan_ltype;
+	u32	ts_ltype;
+	u32	dlr_ltype;
+};
+
+/* CPSW_PORT_V1 */
+#define CPSW1_MAX_BLKS      0x00 /* Maximum FIFO Blocks */
+#define CPSW1_BLK_CNT       0x04 /* FIFO Block Usage Count (Read Only) */
+#define CPSW1_TX_IN_CTL     0x08 /* Transmit FIFO Control */
+#define CPSW1_PORT_VLAN     0x0c /* VLAN Register */
+#define CPSW1_TX_PRI_MAP    0x10 /* Tx Header Priority to Switch Pri Mapping */
+#define CPSW1_TS_CTL        0x14 /* Time Sync Control */
+#define CPSW1_TS_SEQ_LTYPE  0x18 /* Time Sync Sequence ID Offset and Msg Type */
+#define CPSW1_TS_VLAN       0x1c /* Time Sync VLAN1 and VLAN2 */
+
+/* CPSW_PORT_V2 */
+#define CPSW2_CONTROL       0x00 /* Control Register */
+#define CPSW2_MAX_BLKS      0x08 /* Maximum FIFO Blocks */
+#define CPSW2_BLK_CNT       0x0c /* FIFO Block Usage Count (Read Only) */
+#define CPSW2_TX_IN_CTL     0x10 /* Transmit FIFO Control */
+#define CPSW2_PORT_VLAN     0x14 /* VLAN Register */
+#define CPSW2_TX_PRI_MAP    0x18 /* Tx Header Priority to Switch Pri Mapping */
+#define CPSW2_TS_SEQ_MTYPE  0x1c /* Time Sync Sequence ID Offset and Msg Type */
+
+/* CPSW_PORT_V1 and V2 */
+#define SA_LO               0x20 /* CPGMAC_SL Source Address Low */
+#define SA_HI               0x24 /* CPGMAC_SL Source Address High */
+#define SEND_PERCENT        0x28 /* Transmit Queue Send Percentages */
+
+/* CPSW_PORT_V2 only */
+#define RX_DSCP_PRI_MAP0    0x30 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP1    0x34 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP2    0x38 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP3    0x3c /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP4    0x40 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP5    0x44 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP6    0x48 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP7    0x4c /* Rx DSCP Priority to Rx Packet Mapping */
+
+/* Bit definitions for the CPSW2_CONTROL register */
+#define PASS_PRI_TAGGED     BIT(24) /* Pass Priority Tagged */
+#define VLAN_LTYPE2_EN      BIT(21) /* VLAN LTYPE 2 enable */
+#define VLAN_LTYPE1_EN      BIT(20) /* VLAN LTYPE 1 enable */
+#define DSCP_PRI_EN         BIT(16) /* DSCP Priority Enable */
+#define TS_107              BIT(15) /* Tyme Sync Dest IP Address 107 */
+#define TS_320              BIT(14) /* Time Sync Dest Port 320 enable */
+#define TS_319              BIT(13) /* Time Sync Dest Port 319 enable */
+#define TS_132              BIT(12) /* Time Sync Dest IP Addr 132 enable */
+#define TS_131              BIT(11) /* Time Sync Dest IP Addr 131 enable */
+#define TS_130              BIT(10) /* Time Sync Dest IP Addr 130 enable */
+#define TS_129              BIT(9)  /* Time Sync Dest IP Addr 129 enable */
+#define TS_TTL_NONZERO      BIT(8)  /* Time Sync Time To Live Non-zero enable */
+#define TS_ANNEX_F_EN       BIT(6)  /* Time Sync Annex F enable */
+#define TS_ANNEX_D_EN       BIT(4)  /* Time Sync Annex D enable */
+#define TS_LTYPE2_EN        BIT(3)  /* Time Sync LTYPE 2 enable */
+#define TS_LTYPE1_EN        BIT(2)  /* Time Sync LTYPE 1 enable */
+#define TS_TX_EN            BIT(1)  /* Time Sync Transmit Enable */
+#define TS_RX_EN            BIT(0)  /* Time Sync Receive Enable */
+
+#define CTRL_V2_TS_BITS \
+	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
+	 TS_TTL_NONZERO  | TS_ANNEX_D_EN | TS_LTYPE1_EN | VLAN_LTYPE1_EN)
+
+#define CTRL_V2_ALL_TS_MASK (CTRL_V2_TS_BITS | TS_TX_EN | TS_RX_EN)
+#define CTRL_V2_TX_TS_BITS  (CTRL_V2_TS_BITS | TS_TX_EN)
+#define CTRL_V2_RX_TS_BITS  (CTRL_V2_TS_BITS | TS_RX_EN)
+
+
+#define CTRL_V3_TS_BITS \
+	(TS_107 | TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
+	 TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
+	 TS_LTYPE1_EN | VLAN_LTYPE1_EN)
+
+#define CTRL_V3_ALL_TS_MASK (CTRL_V3_TS_BITS | TS_TX_EN | TS_RX_EN)
+#define CTRL_V3_TX_TS_BITS  (CTRL_V3_TS_BITS | TS_TX_EN)
+#define CTRL_V3_RX_TS_BITS  (CTRL_V3_TS_BITS | TS_RX_EN)
+
+/* Bit definitions for the CPSW2_TS_SEQ_MTYPE register */
+#define TS_SEQ_ID_OFFSET_SHIFT   (16)    /* Time Sync Sequence ID Offset */
+#define TS_SEQ_ID_OFFSET_MASK    (0x3f)
+#define TS_MSG_TYPE_EN_SHIFT     (0)     /* Time Sync Message Type Enable */
+#define TS_MSG_TYPE_EN_MASK      (0xffff)
+
+/* The PTP event messages - Sync, Delay_Req, Pdelay_Req, and Pdelay_Resp. */
+#define EVENT_MSG_BITS ((1<<0) | (1<<1) | (1<<2) | (1<<3))
+
+/* Bit definitions for the CPSW1_TS_CTL register */
+#define CPSW_V1_TS_RX_EN		BIT(0)
+#define CPSW_V1_TS_TX_EN		BIT(4)
+#define CPSW_V1_MSG_TYPE_OFS		16
+
+/* Bit definitions for the CPSW1_TS_SEQ_LTYPE register */
+#define CPSW_V1_SEQ_ID_OFS_SHIFT	16
+
+#define CPSW_MAX_BLKS_TX		15
+#define CPSW_MAX_BLKS_TX_SHIFT		4
+#define CPSW_MAX_BLKS_RX		5
+
+struct cpsw_host_regs {
+	u32	max_blks;
+	u32	blk_cnt;
+	u32	tx_in_ctl;
+	u32	port_vlan;
+	u32	tx_pri_map;
+	u32	cpdma_tx_pri_map;
+	u32	cpdma_rx_chan_map;
+};
+
+struct cpsw_slave_data {
+	struct device_node *slave_node;
+	struct device_node *phy_node;
+	char		phy_id[MII_BUS_ID_SIZE];
+	int		phy_if;
+	u8		mac_addr[ETH_ALEN];
+	u16		dual_emac_res_vlan;	/* Reserved VLAN for DualEMAC */
+	struct phy	*ifphy;
+};
+
+struct cpsw_platform_data {
+	struct cpsw_slave_data	*slave_data;
+	u32	ss_reg_ofs;	/* Subsystem control register offset */
+	u32	channels;	/* number of cpdma channels (symmetric) */
+	u32	slaves;		/* number of slave cpgmac ports */
+	u32	active_slave; /* time stamping, ethtool and SIOCGMIIPHY slave */
+	u32	ale_entries;	/* ale table size */
+	u32	bd_ram_size;  /*buffer descriptor ram size */
+	u32	mac_control;	/* Mac control register */
+	u16	default_vlan;	/* Def VLAN for ALE lookup in VLAN aware mode*/
+	bool	dual_emac;	/* Enable Dual EMAC mode */
+};
+
+struct cpsw_slave {
+	void __iomem			*regs;
+	int				slave_num;
+	u32				mac_control;
+	struct cpsw_slave_data		*data;
+	struct phy_device		*phy;
+	struct net_device		*ndev;
+	u32				port_vlan;
+	struct cpsw_sl			*mac_sl;
+};
+
+static inline u32 slave_read(struct cpsw_slave *slave, u32 offset)
+{
+	return readl_relaxed(slave->regs + offset);
+}
+
+static inline void slave_write(struct cpsw_slave *slave, u32 val, u32 offset)
+{
+	writel_relaxed(val, slave->regs + offset);
+}
+
+struct cpsw_vector {
+	struct cpdma_chan *ch;
+	int budget;
+};
+
+struct cpsw_common {
+	struct device			*dev;
+	struct cpsw_platform_data	data;
+	struct napi_struct		napi_rx;
+	struct napi_struct		napi_tx;
+	struct cpsw_ss_regs __iomem	*regs;
+	struct cpsw_wr_regs __iomem	*wr_regs;
+	u8 __iomem			*hw_stats;
+	struct cpsw_host_regs __iomem	*host_port_regs;
+	u32				version;
+	u32				coal_intvl;
+	u32				bus_freq_mhz;
+	int				rx_packet_max;
+	int				descs_pool_size;
+	struct cpsw_slave		*slaves;
+	struct cpdma_ctlr		*dma;
+	struct cpsw_vector		txv[CPSW_MAX_QUEUES];
+	struct cpsw_vector		rxv[CPSW_MAX_QUEUES];
+	struct cpsw_ale			*ale;
+	bool				quirk_irq;
+	bool				rx_irq_disabled;
+	bool				tx_irq_disabled;
+	u32 irqs_table[IRQ_NUM];
+	struct cpts			*cpts;
+	int				rx_ch_num, tx_ch_num;
+	int				speed;
+	int				usage_count;
+	struct page_pool		*page_pool[CPSW_MAX_QUEUES];
+};
+
+struct cpsw_priv {
+	struct net_device		*ndev;
+	struct device			*dev;
+	u32				msg_enable;
+	u8				mac_addr[ETH_ALEN];
+	bool				rx_pause;
+	bool				tx_pause;
+	bool				mqprio_hw;
+	int				fifo_bw[CPSW_TC_NUM];
+	int				shp_cfg_speed;
+	int				tx_ts_enabled;
+	int				rx_ts_enabled;
+	struct bpf_prog			*xdp_prog;
+	struct xdp_rxq_info		xdp_rxq[CPSW_MAX_QUEUES];
+	struct xdp_attachment_info	xdpi;
+
+	u32 emac_port;
+	struct cpsw_common *cpsw;
+};
+
+#define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw)
+#define napi_to_cpsw(napi)	container_of(napi, struct cpsw_common, napi)
+
+#define cpsw_slave_index(cpsw, priv)				\
+		((cpsw->data.dual_emac) ? priv->emac_port :	\
+		cpsw->data.active_slave)
+
+static inline int cpsw_get_slave_port(u32 slave_num)
+{
+	return slave_num + 1;
+}
+
+struct addr_sync_ctx {
+	struct net_device *ndev;
+	const u8 *addr;		/* address to be synched */
+	int consumed;		/* number of address instances */
+	int flush;		/* flush flag */
+};
+
+int cpsw_init_common(struct cpsw_common *cpsw, void __iomem *ss_regs,
+		     int ale_ageout, phys_addr_t desc_mem_phys,
+		     int descs_pool_size);
+void cpsw_split_res(struct cpsw_common *cpsw);
+int cpsw_fill_rx_channels(struct cpsw_priv *priv);
+void cpsw_intr_enable(struct cpsw_common *cpsw);
+void cpsw_intr_disable(struct cpsw_common *cpsw);
+void cpsw_tx_handler(void *token, int len, int status);
+int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw);
+void cpsw_destroy_xdp_rxqs(struct cpsw_common *cpsw);
+
+/* ethtool */
+u32 cpsw_get_msglevel(struct net_device *ndev);
+void cpsw_set_msglevel(struct net_device *ndev, u32 value);
+int cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal);
+int cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal);
+int cpsw_get_sset_count(struct net_device *ndev, int sset);
+void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data);
+void cpsw_get_ethtool_stats(struct net_device *ndev,
+			    struct ethtool_stats *stats, u64 *data);
+void cpsw_get_pauseparam(struct net_device *ndev,
+			 struct ethtool_pauseparam *pause);
+void cpsw_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol);
+int cpsw_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol);
+int cpsw_get_regs_len(struct net_device *ndev);
+void cpsw_get_regs(struct net_device *ndev, struct ethtool_regs *regs, void *p);
+int cpsw_ethtool_op_begin(struct net_device *ndev);
+void cpsw_ethtool_op_complete(struct net_device *ndev);
+void cpsw_get_channels(struct net_device *ndev, struct ethtool_channels *ch);
+int cpsw_get_link_ksettings(struct net_device *ndev,
+			    struct ethtool_link_ksettings *ecmd);
+int cpsw_set_link_ksettings(struct net_device *ndev,
+			    const struct ethtool_link_ksettings *ecmd);
+int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata);
+int cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata);
+int cpsw_nway_reset(struct net_device *ndev);
+void cpsw_get_ringparam(struct net_device *ndev,
+			struct ethtool_ringparam *ering);
+int cpsw_set_ringparam(struct net_device *ndev,
+		       struct ethtool_ringparam *ering);
+int cpsw_set_channels_common(struct net_device *ndev,
+			     struct ethtool_channels *chs,
+			     cpdma_handler_fn rx_handler);
+int cpsw_get_ts_info(struct net_device *ndev, struct ethtool_ts_info *info);
+
+#endif /* DRIVERS_NET_ETHERNET_TI_CPSW_PRIV_H_ */
diff --git a/drivers/net/ethernet/ti/cpsw_sl.c b/drivers/net/ethernet/ti/cpsw_sl.c
new file mode 100644
index 000000000000..0c7531cb0f39
--- /dev/null
+++ b/drivers/net/ethernet/ti/cpsw_sl.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Texas Instruments Ethernet Switch media-access-controller (MAC) submodule/
+ * Ethernet MAC Sliver (CPGMAC_SL)
+ *
+ * Copyright (C) 2019 Texas Instruments
+ *
+ */
+
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+
+#include "cpsw_sl.h"
+
+#define CPSW_SL_REG_NOTUSED U16_MAX
+
+static const u16 cpsw_sl_reg_map_cpsw[] = {
+	[CPSW_SL_IDVER] = 0x00,
+	[CPSW_SL_MACCONTROL] = 0x04,
+	[CPSW_SL_MACSTATUS] = 0x08,
+	[CPSW_SL_SOFT_RESET] = 0x0c,
+	[CPSW_SL_RX_MAXLEN] = 0x10,
+	[CPSW_SL_BOFFTEST] = 0x14,
+	[CPSW_SL_RX_PAUSE] = 0x18,
+	[CPSW_SL_TX_PAUSE] = 0x1c,
+	[CPSW_SL_EMCONTROL] = 0x20,
+	[CPSW_SL_RX_PRI_MAP] = 0x24,
+	[CPSW_SL_TX_GAP] = 0x28,
+};
+
+static const u16 cpsw_sl_reg_map_66ak2hk[] = {
+	[CPSW_SL_IDVER] = 0x00,
+	[CPSW_SL_MACCONTROL] = 0x04,
+	[CPSW_SL_MACSTATUS] = 0x08,
+	[CPSW_SL_SOFT_RESET] = 0x0c,
+	[CPSW_SL_RX_MAXLEN] = 0x10,
+	[CPSW_SL_BOFFTEST] = CPSW_SL_REG_NOTUSED,
+	[CPSW_SL_RX_PAUSE] = 0x18,
+	[CPSW_SL_TX_PAUSE] = 0x1c,
+	[CPSW_SL_EMCONTROL] = 0x20,
+	[CPSW_SL_RX_PRI_MAP] = 0x24,
+	[CPSW_SL_TX_GAP] = CPSW_SL_REG_NOTUSED,
+};
+
+static const u16 cpsw_sl_reg_map_66ak2x_xgbe[] = {
+	[CPSW_SL_IDVER] = 0x00,
+	[CPSW_SL_MACCONTROL] = 0x04,
+	[CPSW_SL_MACSTATUS] = 0x08,
+	[CPSW_SL_SOFT_RESET] = 0x0c,
+	[CPSW_SL_RX_MAXLEN] = 0x10,
+	[CPSW_SL_BOFFTEST] = CPSW_SL_REG_NOTUSED,
+	[CPSW_SL_RX_PAUSE] = 0x18,
+	[CPSW_SL_TX_PAUSE] = 0x1c,
+	[CPSW_SL_EMCONTROL] = 0x20,
+	[CPSW_SL_RX_PRI_MAP] = CPSW_SL_REG_NOTUSED,
+	[CPSW_SL_TX_GAP] = 0x28,
+};
+
+static const u16 cpsw_sl_reg_map_66ak2elg_am65[] = {
+	[CPSW_SL_IDVER] = CPSW_SL_REG_NOTUSED,
+	[CPSW_SL_MACCONTROL] = 0x00,
+	[CPSW_SL_MACSTATUS] = 0x04,
+	[CPSW_SL_SOFT_RESET] = 0x08,
+	[CPSW_SL_RX_MAXLEN] = CPSW_SL_REG_NOTUSED,
+	[CPSW_SL_BOFFTEST] = 0x0c,
+	[CPSW_SL_RX_PAUSE] = 0x10,
+	[CPSW_SL_TX_PAUSE] = 0x40,
+	[CPSW_SL_EMCONTROL] = 0x70,
+	[CPSW_SL_RX_PRI_MAP] = CPSW_SL_REG_NOTUSED,
+	[CPSW_SL_TX_GAP] = 0x74,
+};
+
+#define CPSW_SL_SOFT_RESET_BIT		BIT(0)
+
+#define CPSW_SL_STATUS_PN_IDLE		BIT(31)
+#define CPSW_SL_AM65_STATUS_PN_E_IDLE	BIT(30)
+#define CPSW_SL_AM65_STATUS_PN_P_IDLE	BIT(29)
+#define CPSW_SL_AM65_STATUS_PN_TX_IDLE	BIT(28)
+
+#define CPSW_SL_STATUS_IDLE_MASK_BASE (CPSW_SL_STATUS_PN_IDLE)
+
+#define CPSW_SL_STATUS_IDLE_MASK_K3 \
+	(CPSW_SL_STATUS_IDLE_MASK_BASE | CPSW_SL_AM65_STATUS_PN_E_IDLE | \
+	 CPSW_SL_AM65_STATUS_PN_P_IDLE | CPSW_SL_AM65_STATUS_PN_TX_IDLE)
+
+#define CPSW_SL_CTL_FUNC_BASE \
+	(CPSW_SL_CTL_FULLDUPLEX |\
+	CPSW_SL_CTL_LOOPBACK |\
+	CPSW_SL_CTL_RX_FLOW_EN |\
+	CPSW_SL_CTL_TX_FLOW_EN |\
+	CPSW_SL_CTL_GMII_EN |\
+	CPSW_SL_CTL_TX_PACE |\
+	CPSW_SL_CTL_GIG |\
+	CPSW_SL_CTL_CMD_IDLE |\
+	CPSW_SL_CTL_IFCTL_A |\
+	CPSW_SL_CTL_IFCTL_B |\
+	CPSW_SL_CTL_GIG_FORCE |\
+	CPSW_SL_CTL_EXT_EN |\
+	CPSW_SL_CTL_RX_CEF_EN |\
+	CPSW_SL_CTL_RX_CSF_EN |\
+	CPSW_SL_CTL_RX_CMF_EN)
+
+struct cpsw_sl {
+	struct device *dev;
+	void __iomem *sl_base;
+	const u16 *regs;
+	u32 control_features;
+	u32 idle_mask;
+};
+
+struct cpsw_sl_dev_id {
+	const char *device_id;
+	const u16 *regs;
+	const u32 control_features;
+	const u32 regs_offset;
+	const u32 idle_mask;
+};
+
+static const struct cpsw_sl_dev_id cpsw_sl_id_match[] = {
+	{
+		.device_id = "cpsw",
+		.regs = cpsw_sl_reg_map_cpsw,
+		.control_features = CPSW_SL_CTL_FUNC_BASE |
+				    CPSW_SL_CTL_MTEST |
+				    CPSW_SL_CTL_TX_SHORT_GAP_EN |
+				    CPSW_SL_CTL_TX_SG_LIM_EN,
+		.idle_mask = CPSW_SL_STATUS_IDLE_MASK_BASE,
+	},
+	{
+		.device_id = "66ak2hk",
+		.regs = cpsw_sl_reg_map_66ak2hk,
+		.control_features = CPSW_SL_CTL_FUNC_BASE |
+				    CPSW_SL_CTL_TX_SHORT_GAP_EN,
+		.idle_mask = CPSW_SL_STATUS_IDLE_MASK_BASE,
+	},
+	{
+		.device_id = "66ak2x_xgbe",
+		.regs = cpsw_sl_reg_map_66ak2x_xgbe,
+		.control_features = CPSW_SL_CTL_FUNC_BASE |
+				    CPSW_SL_CTL_XGIG |
+				    CPSW_SL_CTL_TX_SHORT_GAP_EN |
+				    CPSW_SL_CTL_CRC_TYPE |
+				    CPSW_SL_CTL_XGMII_EN,
+		.idle_mask = CPSW_SL_STATUS_IDLE_MASK_BASE,
+	},
+	{
+		.device_id = "66ak2el",
+		.regs = cpsw_sl_reg_map_66ak2elg_am65,
+		.regs_offset = 0x330,
+		.control_features = CPSW_SL_CTL_FUNC_BASE |
+				    CPSW_SL_CTL_MTEST |
+				    CPSW_SL_CTL_TX_SHORT_GAP_EN |
+				    CPSW_SL_CTL_CRC_TYPE |
+				    CPSW_SL_CTL_EXT_EN_RX_FLO |
+				    CPSW_SL_CTL_EXT_EN_TX_FLO |
+				    CPSW_SL_CTL_TX_SG_LIM_EN,
+		.idle_mask = CPSW_SL_STATUS_IDLE_MASK_BASE,
+	},
+	{
+		.device_id = "66ak2g",
+		.regs = cpsw_sl_reg_map_66ak2elg_am65,
+		.regs_offset = 0x330,
+		.control_features = CPSW_SL_CTL_FUNC_BASE |
+				    CPSW_SL_CTL_MTEST |
+				    CPSW_SL_CTL_CRC_TYPE |
+				    CPSW_SL_CTL_EXT_EN_RX_FLO |
+				    CPSW_SL_CTL_EXT_EN_TX_FLO,
+	},
+	{
+		.device_id = "am65",
+		.regs = cpsw_sl_reg_map_66ak2elg_am65,
+		.regs_offset = 0x330,
+		.control_features = CPSW_SL_CTL_FUNC_BASE |
+				    CPSW_SL_CTL_MTEST |
+				    CPSW_SL_CTL_XGIG |
+				    CPSW_SL_CTL_TX_SHORT_GAP_EN |
+				    CPSW_SL_CTL_CRC_TYPE |
+				    CPSW_SL_CTL_XGMII_EN |
+				    CPSW_SL_CTL_EXT_EN_RX_FLO |
+				    CPSW_SL_CTL_EXT_EN_TX_FLO |
+				    CPSW_SL_CTL_TX_SG_LIM_EN |
+				    CPSW_SL_CTL_EXT_EN_XGIG,
+		.idle_mask = CPSW_SL_STATUS_IDLE_MASK_K3,
+	},
+	{ },
+};
+
+u32 cpsw_sl_reg_read(struct cpsw_sl *sl, enum cpsw_sl_regs reg)
+{
+	int val;
+
+	if (sl->regs[reg] == CPSW_SL_REG_NOTUSED) {
+		dev_err(sl->dev, "cpsw_sl: not sup r reg: %04X\n",
+			sl->regs[reg]);
+		return 0;
+	}
+
+	val = readl(sl->sl_base + sl->regs[reg]);
+	dev_dbg(sl->dev, "cpsw_sl: reg: %04X r 0x%08X\n", sl->regs[reg], val);
+	return val;
+}
+
+void cpsw_sl_reg_write(struct cpsw_sl *sl, enum cpsw_sl_regs reg, u32 val)
+{
+	if (sl->regs[reg] == CPSW_SL_REG_NOTUSED) {
+		dev_err(sl->dev, "cpsw_sl: not sup w reg: %04X\n",
+			sl->regs[reg]);
+		return;
+	}
+
+	dev_dbg(sl->dev, "cpsw_sl: reg: %04X w 0x%08X\n", sl->regs[reg], val);
+	writel(val, sl->sl_base + sl->regs[reg]);
+}
+
+static const struct cpsw_sl_dev_id *cpsw_sl_match_id(
+		const struct cpsw_sl_dev_id *id,
+		const char *device_id)
+{
+	if (!id || !device_id)
+		return NULL;
+
+	while (id->device_id) {
+		if (strcmp(device_id, id->device_id) == 0)
+			return id;
+		id++;
+	}
+	return NULL;
+}
+
+struct cpsw_sl *cpsw_sl_get(const char *device_id, struct device *dev,
+			    void __iomem *sl_base)
+{
+	const struct cpsw_sl_dev_id *sl_dev_id;
+	struct cpsw_sl *sl;
+
+	sl = devm_kzalloc(dev, sizeof(struct cpsw_sl), GFP_KERNEL);
+	if (!sl)
+		return ERR_PTR(-ENOMEM);
+	sl->dev = dev;
+	sl->sl_base = sl_base;
+
+	sl_dev_id = cpsw_sl_match_id(cpsw_sl_id_match, device_id);
+	if (!sl_dev_id) {
+		dev_err(sl->dev, "cpsw_sl: dev_id %s not found.\n", device_id);
+		return ERR_PTR(-EINVAL);
+	}
+	sl->regs = sl_dev_id->regs;
+	sl->control_features = sl_dev_id->control_features;
+	sl->idle_mask = sl_dev_id->idle_mask;
+	sl->sl_base += sl_dev_id->regs_offset;
+
+	return sl;
+}
+
+void cpsw_sl_reset(struct cpsw_sl *sl, unsigned long tmo)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(tmo);
+
+	/* Set the soft reset bit */
+	cpsw_sl_reg_write(sl, CPSW_SL_SOFT_RESET, CPSW_SL_SOFT_RESET_BIT);
+
+	/* Wait for the bit to clear */
+	do {
+		usleep_range(100, 200);
+	} while ((cpsw_sl_reg_read(sl, CPSW_SL_SOFT_RESET) &
+		  CPSW_SL_SOFT_RESET_BIT) &&
+		  time_after(timeout, jiffies));
+
+	if (cpsw_sl_reg_read(sl, CPSW_SL_SOFT_RESET) & CPSW_SL_SOFT_RESET_BIT)
+		dev_err(sl->dev, "cpsw_sl failed to soft-reset.\n");
+}
+
+u32 cpsw_sl_ctl_set(struct cpsw_sl *sl, u32 ctl_funcs)
+{
+	u32 val;
+
+	if (ctl_funcs & ~sl->control_features) {
+		dev_err(sl->dev, "cpsw_sl: unsupported func 0x%08X\n",
+			ctl_funcs & (~sl->control_features));
+		return -EINVAL;
+	}
+
+	val = cpsw_sl_reg_read(sl, CPSW_SL_MACCONTROL);
+	val |= ctl_funcs;
+	cpsw_sl_reg_write(sl, CPSW_SL_MACCONTROL, val);
+
+	return 0;
+}
+
+u32 cpsw_sl_ctl_clr(struct cpsw_sl *sl, u32 ctl_funcs)
+{
+	u32 val;
+
+	if (ctl_funcs & ~sl->control_features) {
+		dev_err(sl->dev, "cpsw_sl: unsupported func 0x%08X\n",
+			ctl_funcs & (~sl->control_features));
+		return -EINVAL;
+	}
+
+	val = cpsw_sl_reg_read(sl, CPSW_SL_MACCONTROL);
+	val &= ~ctl_funcs;
+	cpsw_sl_reg_write(sl, CPSW_SL_MACCONTROL, val);
+
+	return 0;
+}
+
+void cpsw_sl_ctl_reset(struct cpsw_sl *sl)
+{
+	cpsw_sl_reg_write(sl, CPSW_SL_MACCONTROL, 0);
+}
+
+int cpsw_sl_wait_for_idle(struct cpsw_sl *sl, unsigned long tmo)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(tmo);
+
+	do {
+		usleep_range(100, 200);
+	} while (!(cpsw_sl_reg_read(sl, CPSW_SL_MACSTATUS) &
+		  sl->idle_mask) && time_after(timeout, jiffies));
+
+	if (!(cpsw_sl_reg_read(sl, CPSW_SL_MACSTATUS) & sl->idle_mask)) {
+		dev_err(sl->dev, "cpsw_sl failed to soft-reset.\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/ti/cpsw_sl.h b/drivers/net/ethernet/ti/cpsw_sl.h
new file mode 100644
index 000000000000..a6d06a5a420f
--- /dev/null
+++ b/drivers/net/ethernet/ti/cpsw_sl.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Texas Instruments Ethernet Switch media-access-controller (MAC) submodule/
+ * Ethernet MAC Sliver (CPGMAC_SL) APIs
+ *
+ * Copyright (C) 2019 Texas Instruments
+ *
+ */
+
+#ifndef __TI_CPSW_SL_H__
+#define __TI_CPSW_SL_H__
+
+#include <linux/device.h>
+
+enum cpsw_sl_regs {
+	CPSW_SL_IDVER,
+	CPSW_SL_MACCONTROL,
+	CPSW_SL_MACSTATUS,
+	CPSW_SL_SOFT_RESET,
+	CPSW_SL_RX_MAXLEN,
+	CPSW_SL_BOFFTEST,
+	CPSW_SL_RX_PAUSE,
+	CPSW_SL_TX_PAUSE,
+	CPSW_SL_EMCONTROL,
+	CPSW_SL_RX_PRI_MAP,
+	CPSW_SL_TX_GAP,
+};
+
+enum {
+	CPSW_SL_CTL_FULLDUPLEX = BIT(0), /* Full Duplex mode */
+	CPSW_SL_CTL_LOOPBACK = BIT(1), /* Loop Back Mode */
+	CPSW_SL_CTL_MTEST = BIT(2), /* Manufacturing Test mode */
+	CPSW_SL_CTL_RX_FLOW_EN = BIT(3), /* Receive Flow Control Enable */
+	CPSW_SL_CTL_TX_FLOW_EN = BIT(4), /* Transmit Flow Control Enable */
+	CPSW_SL_CTL_GMII_EN = BIT(5), /* GMII Enable */
+	CPSW_SL_CTL_TX_PACE = BIT(6), /* Transmit Pacing Enable */
+	CPSW_SL_CTL_GIG = BIT(7), /* Gigabit Mode */
+	CPSW_SL_CTL_XGIG = BIT(8), /* 10 Gigabit Mode */
+	CPSW_SL_CTL_TX_SHORT_GAP_EN = BIT(10), /* Transmit Short Gap Enable */
+	CPSW_SL_CTL_CMD_IDLE = BIT(11), /* Command Idle */
+	CPSW_SL_CTL_CRC_TYPE = BIT(12), /* Port CRC Type */
+	CPSW_SL_CTL_XGMII_EN = BIT(13), /* XGMII Enable */
+	CPSW_SL_CTL_IFCTL_A = BIT(15), /* Interface Control A */
+	CPSW_SL_CTL_IFCTL_B = BIT(16), /* Interface Control B */
+	CPSW_SL_CTL_GIG_FORCE = BIT(17), /* Gigabit Mode Force */
+	CPSW_SL_CTL_EXT_EN = BIT(18), /* External Control Enable */
+	CPSW_SL_CTL_EXT_EN_RX_FLO = BIT(19), /* Ext RX Flow Control Enable */
+	CPSW_SL_CTL_EXT_EN_TX_FLO = BIT(20), /* Ext TX Flow Control Enable */
+	CPSW_SL_CTL_TX_SG_LIM_EN = BIT(21), /* TXt Short Gap Limit Enable */
+	CPSW_SL_CTL_RX_CEF_EN = BIT(22), /* RX Copy Error Frames Enable */
+	CPSW_SL_CTL_RX_CSF_EN = BIT(23), /* RX Copy Short Frames Enable */
+	CPSW_SL_CTL_RX_CMF_EN = BIT(24), /* RX Copy MAC Control Frames Enable */
+	CPSW_SL_CTL_EXT_EN_XGIG = BIT(25),  /* Ext XGIG Control En, k3 only */
+
+	CPSW_SL_CTL_FUNCS_COUNT
+};
+
+struct cpsw_sl;
+
+struct cpsw_sl *cpsw_sl_get(const char *device_id, struct device *dev,
+			    void __iomem *sl_base);
+
+void cpsw_sl_reset(struct cpsw_sl *sl, unsigned long tmo);
+
+u32 cpsw_sl_ctl_set(struct cpsw_sl *sl, u32 ctl_funcs);
+u32 cpsw_sl_ctl_clr(struct cpsw_sl *sl, u32 ctl_funcs);
+void cpsw_sl_ctl_reset(struct cpsw_sl *sl);
+int cpsw_sl_wait_for_idle(struct cpsw_sl *sl, unsigned long tmo);
+
+u32 cpsw_sl_reg_read(struct cpsw_sl *sl, enum cpsw_sl_regs reg);
+void cpsw_sl_reg_write(struct cpsw_sl *sl, enum cpsw_sl_regs reg, u32 val);
+
+#endif /* __TI_CPSW_SL_H__ */
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 2a9ba4acd7fa..61136428e2c0 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -1,22 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * TI Common Platform Time Sync
  *
  * Copyright (C) 2012 Richard Cochran <richardcochran@gmail.com>
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
+#include <linux/clk-provider.h>
 #include <linux/err.h>
 #include <linux/if.h>
 #include <linux/hrtimer.h>
@@ -544,6 +533,82 @@ static void cpts_calc_mult_shift(struct cpts *cpts)
 		 freq, cpts->cc.mult, cpts->cc.shift, (ns - NSEC_PER_SEC));
 }
 
+static int cpts_of_mux_clk_setup(struct cpts *cpts, struct device_node *node)
+{
+	struct device_node *refclk_np;
+	const char **parent_names;
+	unsigned int num_parents;
+	struct clk_hw *clk_hw;
+	int ret = -EINVAL;
+	u32 *mux_table;
+
+	refclk_np = of_get_child_by_name(node, "cpts-refclk-mux");
+	if (!refclk_np)
+		/* refclk selection supported not for all SoCs */
+		return 0;
+
+	num_parents = of_clk_get_parent_count(refclk_np);
+	if (num_parents < 1) {
+		dev_err(cpts->dev, "mux-clock %s must have parents\n",
+			refclk_np->name);
+		goto mux_fail;
+	}
+
+	parent_names = devm_kzalloc(cpts->dev, (sizeof(char *) * num_parents),
+				    GFP_KERNEL);
+
+	mux_table = devm_kzalloc(cpts->dev, sizeof(*mux_table) * num_parents,
+				 GFP_KERNEL);
+	if (!mux_table || !parent_names) {
+		ret = -ENOMEM;
+		goto mux_fail;
+	}
+
+	of_clk_parent_fill(refclk_np, parent_names, num_parents);
+
+	ret = of_property_read_variable_u32_array(refclk_np, "ti,mux-tbl",
+						  mux_table,
+						  num_parents, num_parents);
+	if (ret < 0)
+		goto mux_fail;
+
+	clk_hw = clk_hw_register_mux_table(cpts->dev, refclk_np->name,
+					   parent_names, num_parents,
+					   0,
+					   &cpts->reg->rftclk_sel, 0, 0x1F,
+					   0, mux_table, NULL);
+	if (IS_ERR(clk_hw)) {
+		ret = PTR_ERR(clk_hw);
+		goto mux_fail;
+	}
+
+	ret = devm_add_action_or_reset(cpts->dev,
+				       (void(*)(void *))clk_hw_unregister_mux,
+				       clk_hw);
+	if (ret) {
+		dev_err(cpts->dev, "add clkmux unreg action %d", ret);
+		goto mux_fail;
+	}
+
+	ret = of_clk_add_hw_provider(refclk_np, of_clk_hw_simple_get, clk_hw);
+	if (ret)
+		goto mux_fail;
+
+	ret = devm_add_action_or_reset(cpts->dev,
+				       (void(*)(void *))of_clk_del_provider,
+				       refclk_np);
+	if (ret) {
+		dev_err(cpts->dev, "add clkmux provider unreg action %d", ret);
+		goto mux_fail;
+	}
+
+	return ret;
+
+mux_fail:
+	of_node_put(refclk_np);
+	return ret;
+}
+
 static int cpts_of_parse(struct cpts *cpts, struct device_node *node)
 {
 	int ret = -EINVAL;
@@ -559,7 +624,7 @@ static int cpts_of_parse(struct cpts *cpts, struct device_node *node)
 	    (!cpts->cc.mult && cpts->cc.shift))
 		goto of_error;
 
-	return 0;
+	return cpts_of_mux_clk_setup(cpts, node);
 
 of_error:
 	dev_err(cpts->dev, "CPTS: Missing property in the DT.\n");
@@ -584,9 +649,14 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 	if (ret)
 		return ERR_PTR(ret);
 
-	cpts->refclk = devm_clk_get(dev, "cpts");
+	cpts->refclk = devm_get_clk_from_child(dev, node, "cpts");
+	if (IS_ERR(cpts->refclk))
+		/* try get clk from dev node for compatibility */
+		cpts->refclk = devm_clk_get(dev, "cpts");
+
 	if (IS_ERR(cpts->refclk)) {
-		dev_err(dev, "Failed to get cpts refclk\n");
+		dev_err(dev, "Failed to get cpts refclk %ld\n",
+			PTR_ERR(cpts->refclk));
 		return ERR_CAST(cpts->refclk);
 	}
 
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index d2c7decd59b6..bb997c11ee15 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * TI Common Platform Time Sync
  *
  * Copyright (C) 2012 Richard Cochran <richardcochran@gmail.com>
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #ifndef _TI_CPTS_H_
 #define _TI_CPTS_H_
@@ -36,7 +24,7 @@
 struct cpsw_cpts {
 	u32 idver;                /* Identification and version */
 	u32 control;              /* Time sync control */
-	u32 res1;
+	u32 rftclk_sel;		  /* Reference Clock Select Register */
 	u32 ts_push;              /* Time stamp event push */
 	u32 ts_load_val;          /* Time stamp load value */
 	u32 ts_load_en;           /* Time stamp load enable */
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 4236dcdd5634..a65edd2770e6 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -1,16 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Texas Instruments CPDMA Driver
  *
  * Copyright (C) 2010 Texas Instruments
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
@@ -141,6 +134,15 @@ struct cpdma_control_info {
 #define ACCESS_RW	(ACCESS_RO | ACCESS_WO)
 };
 
+struct submit_info {
+	struct cpdma_chan *chan;
+	int directed;
+	void *token;
+	void *data_virt;
+	dma_addr_t data_dma;
+	int len;
+};
+
 static struct cpdma_control_info controls[] = {
 	[CPDMA_TX_RLIM]		  = {CPDMA_DMACONTROL,	8,  0xffff, ACCESS_RW},
 	[CPDMA_CMD_IDLE]	  = {CPDMA_DMACONTROL,	3,  1,      ACCESS_WO},
@@ -183,6 +185,8 @@ static struct cpdma_control_info controls[] = {
 				 (directed << CPDMA_TO_PORT_SHIFT));	\
 	} while (0)
 
+#define CPDMA_DMA_EXT_MAP		BIT(16)
+
 static void cpdma_desc_pool_destroy(struct cpdma_ctlr *ctlr)
 {
 	struct cpdma_desc_pool *pool = ctlr->pool;
@@ -527,7 +531,6 @@ struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params)
 		ctlr->num_chan = CPDMA_MAX_CHANNELS;
 	return ctlr;
 }
-EXPORT_SYMBOL_GPL(cpdma_ctlr_create);
 
 int cpdma_ctlr_start(struct cpdma_ctlr *ctlr)
 {
@@ -588,7 +591,6 @@ int cpdma_ctlr_start(struct cpdma_ctlr *ctlr)
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_ctlr_start);
 
 int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr)
 {
@@ -621,7 +623,6 @@ int cpdma_ctlr_stop(struct cpdma_ctlr *ctlr)
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_ctlr_stop);
 
 int cpdma_ctlr_destroy(struct cpdma_ctlr *ctlr)
 {
@@ -639,7 +640,6 @@ int cpdma_ctlr_destroy(struct cpdma_ctlr *ctlr)
 	cpdma_desc_pool_destroy(ctlr);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(cpdma_ctlr_destroy);
 
 int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable)
 {
@@ -660,25 +660,21 @@ int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable)
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_ctlr_int_ctrl);
 
 void cpdma_ctlr_eoi(struct cpdma_ctlr *ctlr, u32 value)
 {
 	dma_reg_write(ctlr, CPDMA_MACEOIVECTOR, value);
 }
-EXPORT_SYMBOL_GPL(cpdma_ctlr_eoi);
 
 u32 cpdma_ctrl_rxchs_state(struct cpdma_ctlr *ctlr)
 {
 	return dma_reg_read(ctlr, CPDMA_RXINTSTATMASKED);
 }
-EXPORT_SYMBOL_GPL(cpdma_ctrl_rxchs_state);
 
 u32 cpdma_ctrl_txchs_state(struct cpdma_ctlr *ctlr)
 {
 	return dma_reg_read(ctlr, CPDMA_TXINTSTATMASKED);
 }
-EXPORT_SYMBOL_GPL(cpdma_ctrl_txchs_state);
 
 static void cpdma_chan_set_descs(struct cpdma_ctlr *ctlr,
 				 int rx, int desc_num,
@@ -774,7 +770,6 @@ int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_split_pool);
 
 
 /* cpdma_chan_set_weight - set weight of a channel in percentage.
@@ -807,7 +802,6 @@ int cpdma_chan_set_weight(struct cpdma_chan *ch, int weight)
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_set_weight);
 
 /* cpdma_chan_get_min_rate - get minimum allowed rate for channel
  * Should be called before cpdma_chan_set_rate.
@@ -822,7 +816,6 @@ u32 cpdma_chan_get_min_rate(struct cpdma_ctlr *ctlr)
 
 	return DIV_ROUND_UP(divident, divisor);
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_get_min_rate);
 
 /* cpdma_chan_set_rate - limits bandwidth for transmit channel.
  * The bandwidth * limited channels have to be in order beginning from lowest.
@@ -867,7 +860,6 @@ err:
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_set_rate);
 
 u32 cpdma_chan_get_rate(struct cpdma_chan *ch)
 {
@@ -880,7 +872,6 @@ u32 cpdma_chan_get_rate(struct cpdma_chan *ch)
 
 	return rate;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_get_rate);
 
 struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 				     cpdma_handler_fn handler, int rx_type)
@@ -940,7 +931,6 @@ struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return chan;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_create);
 
 int cpdma_chan_get_rx_buf_num(struct cpdma_chan *chan)
 {
@@ -953,7 +943,6 @@ int cpdma_chan_get_rx_buf_num(struct cpdma_chan *chan)
 
 	return desc_num;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_get_rx_buf_num);
 
 int cpdma_chan_destroy(struct cpdma_chan *chan)
 {
@@ -975,7 +964,6 @@ int cpdma_chan_destroy(struct cpdma_chan *chan)
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_destroy);
 
 int cpdma_chan_get_stats(struct cpdma_chan *chan,
 			 struct cpdma_chan_stats *stats)
@@ -988,7 +976,6 @@ int cpdma_chan_get_stats(struct cpdma_chan *chan,
 	spin_unlock_irqrestore(&chan->lock, flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_get_stats);
 
 static void __cpdma_chan_submit(struct cpdma_chan *chan,
 				struct cpdma_desc __iomem *desc)
@@ -1026,34 +1013,26 @@ static void __cpdma_chan_submit(struct cpdma_chan *chan,
 	}
 }
 
-int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
-		      int len, int directed)
+static int cpdma_chan_submit_si(struct submit_info *si)
 {
+	struct cpdma_chan		*chan = si->chan;
 	struct cpdma_ctlr		*ctlr = chan->ctlr;
+	int				len = si->len;
+	int				swlen = len;
 	struct cpdma_desc __iomem	*desc;
 	dma_addr_t			buffer;
-	unsigned long			flags;
 	u32				mode;
-	int				ret = 0;
-
-	spin_lock_irqsave(&chan->lock, flags);
-
-	if (chan->state == CPDMA_STATE_TEARDOWN) {
-		ret = -EINVAL;
-		goto unlock_ret;
-	}
+	int				ret;
 
 	if (chan->count >= chan->desc_num)	{
 		chan->stats.desc_alloc_fail++;
-		ret = -ENOMEM;
-		goto unlock_ret;
+		return -ENOMEM;
 	}
 
 	desc = cpdma_desc_alloc(ctlr->pool);
 	if (!desc) {
 		chan->stats.desc_alloc_fail++;
-		ret = -ENOMEM;
-		goto unlock_ret;
+		return -ENOMEM;
 	}
 
 	if (len < ctlr->params.min_packet_size) {
@@ -1061,16 +1040,21 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		chan->stats.runt_transmit_buff++;
 	}
 
-	buffer = dma_map_single(ctlr->dev, data, len, chan->dir);
-	ret = dma_mapping_error(ctlr->dev, buffer);
-	if (ret) {
-		cpdma_desc_free(ctlr->pool, desc, 1);
-		ret = -EINVAL;
-		goto unlock_ret;
-	}
-
 	mode = CPDMA_DESC_OWNER | CPDMA_DESC_SOP | CPDMA_DESC_EOP;
-	cpdma_desc_to_port(chan, mode, directed);
+	cpdma_desc_to_port(chan, mode, si->directed);
+
+	if (si->data_dma) {
+		buffer = si->data_dma;
+		dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir);
+		swlen |= CPDMA_DMA_EXT_MAP;
+	} else {
+		buffer = dma_map_single(ctlr->dev, si->data_virt, len, chan->dir);
+		ret = dma_mapping_error(ctlr->dev, buffer);
+		if (ret) {
+			cpdma_desc_free(ctlr->pool, desc, 1);
+			return -EINVAL;
+		}
+	}
 
 	/* Relaxed IO accessors can be used here as there is read barrier
 	 * at the end of write sequence.
@@ -1079,9 +1063,9 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 	writel_relaxed(buffer, &desc->hw_buffer);
 	writel_relaxed(len, &desc->hw_len);
 	writel_relaxed(mode | len, &desc->hw_mode);
-	writel_relaxed((uintptr_t)token, &desc->sw_token);
+	writel_relaxed((uintptr_t)si->token, &desc->sw_token);
 	writel_relaxed(buffer, &desc->sw_buffer);
-	writel_relaxed(len, &desc->sw_len);
+	writel_relaxed(swlen, &desc->sw_len);
 	desc_read(desc, sw_len);
 
 	__cpdma_chan_submit(chan, desc);
@@ -1090,12 +1074,108 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		chan_write(chan, rxfree, 1);
 
 	chan->count++;
+	return 0;
+}
 
-unlock_ret:
+int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
+			   int len, int directed)
+{
+	struct submit_info si;
+	unsigned long flags;
+	int ret;
+
+	si.chan = chan;
+	si.token = token;
+	si.data_virt = data;
+	si.data_dma = 0;
+	si.len = len;
+	si.directed = directed;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (chan->state == CPDMA_STATE_TEARDOWN) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -EINVAL;
+	}
+
+	ret = cpdma_chan_submit_si(&si);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	return ret;
+}
+
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+				  dma_addr_t data, int len, int directed)
+{
+	struct submit_info si;
+	unsigned long flags;
+	int ret;
+
+	si.chan = chan;
+	si.token = token;
+	si.data_virt = NULL;
+	si.data_dma = data;
+	si.len = len;
+	si.directed = directed;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (chan->state == CPDMA_STATE_TEARDOWN) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -EINVAL;
+	}
+
+	ret = cpdma_chan_submit_si(&si);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	return ret;
+}
+
+int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
+		      int len, int directed)
+{
+	struct submit_info si;
+	unsigned long flags;
+	int ret;
+
+	si.chan = chan;
+	si.token = token;
+	si.data_virt = data;
+	si.data_dma = 0;
+	si.len = len;
+	si.directed = directed;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (chan->state != CPDMA_STATE_ACTIVE) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -EINVAL;
+	}
+
+	ret = cpdma_chan_submit_si(&si);
+	spin_unlock_irqrestore(&chan->lock, flags);
+	return ret;
+}
+
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+			     dma_addr_t data, int len, int directed)
+{
+	struct submit_info si;
+	unsigned long flags;
+	int ret;
+
+	si.chan = chan;
+	si.token = token;
+	si.data_virt = NULL;
+	si.data_dma = data;
+	si.len = len;
+	si.directed = directed;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	if (chan->state != CPDMA_STATE_ACTIVE) {
+		spin_unlock_irqrestore(&chan->lock, flags);
+		return -EINVAL;
+	}
+
+	ret = cpdma_chan_submit_si(&si);
 	spin_unlock_irqrestore(&chan->lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_submit);
 
 bool cpdma_check_free_tx_desc(struct cpdma_chan *chan)
 {
@@ -1110,7 +1190,6 @@ bool cpdma_check_free_tx_desc(struct cpdma_chan *chan)
 	spin_unlock_irqrestore(&chan->lock, flags);
 	return free_tx_desc;
 }
-EXPORT_SYMBOL_GPL(cpdma_check_free_tx_desc);
 
 static void __cpdma_chan_free(struct cpdma_chan *chan,
 			      struct cpdma_desc __iomem *desc,
@@ -1123,10 +1202,17 @@ static void __cpdma_chan_free(struct cpdma_chan *chan,
 	uintptr_t			token;
 
 	token      = desc_read(desc, sw_token);
-	buff_dma   = desc_read(desc, sw_buffer);
 	origlen    = desc_read(desc, sw_len);
 
-	dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+	buff_dma   = desc_read(desc, sw_buffer);
+	if (origlen & CPDMA_DMA_EXT_MAP) {
+		origlen &= ~CPDMA_DMA_EXT_MAP;
+		dma_sync_single_for_cpu(ctlr->dev, buff_dma, origlen,
+					chan->dir);
+	} else {
+		dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+	}
+
 	cpdma_desc_free(pool, desc, 1);
 	(*chan->handler)((void *)token, outlen, status);
 }
@@ -1204,7 +1290,6 @@ int cpdma_chan_process(struct cpdma_chan *chan, int quota)
 	}
 	return used;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_process);
 
 int cpdma_chan_start(struct cpdma_chan *chan)
 {
@@ -1224,7 +1309,6 @@ int cpdma_chan_start(struct cpdma_chan *chan)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_start);
 
 int cpdma_chan_stop(struct cpdma_chan *chan)
 {
@@ -1287,7 +1371,6 @@ int cpdma_chan_stop(struct cpdma_chan *chan)
 	spin_unlock_irqrestore(&chan->lock, flags);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cpdma_chan_stop);
 
 int cpdma_chan_int_ctrl(struct cpdma_chan *chan, bool enable)
 {
@@ -1329,25 +1412,34 @@ int cpdma_control_set(struct cpdma_ctlr *ctlr, int control, int value)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(cpdma_control_set);
 
 int cpdma_get_num_rx_descs(struct cpdma_ctlr *ctlr)
 {
 	return ctlr->num_rx_desc;
 }
-EXPORT_SYMBOL_GPL(cpdma_get_num_rx_descs);
 
 int cpdma_get_num_tx_descs(struct cpdma_ctlr *ctlr)
 {
 	return ctlr->num_tx_desc;
 }
-EXPORT_SYMBOL_GPL(cpdma_get_num_tx_descs);
 
-void cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc)
+int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc)
 {
+	unsigned long flags;
+	int temp, ret;
+
+	spin_lock_irqsave(&ctlr->lock, flags);
+
+	temp = ctlr->num_rx_desc;
 	ctlr->num_rx_desc = num_rx_desc;
 	ctlr->num_tx_desc = ctlr->pool->num_desc - ctlr->num_rx_desc;
-}
-EXPORT_SYMBOL_GPL(cpdma_set_num_rx_descs);
+	ret = cpdma_chan_split_pool(ctlr);
+	if (ret) {
+		ctlr->num_rx_desc = temp;
+		ctlr->num_tx_desc = ctlr->pool->num_desc - ctlr->num_rx_desc;
+	}
+
+	spin_unlock_irqrestore(&ctlr->lock, flags);
 
-MODULE_LICENSE("GPL");
+	return ret;
+}
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index d399af5389b8..d3cfe234d16a 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -1,16 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Texas Instruments CPDMA Driver
  *
  * Copyright (C) 2010 Texas Instruments
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef __DAVINCI_CPDMA_H__
 #define __DAVINCI_CPDMA_H__
@@ -34,8 +27,8 @@ struct cpdma_params {
 	int			num_chan;
 	bool			has_soft_reset;
 	int			min_packet_size;
-	u32			desc_mem_phys;
-	u32			desc_hw_addr;
+	dma_addr_t		desc_mem_phys;
+	dma_addr_t		desc_hw_addr;
 	int			desc_mem_size;
 	int			desc_align;
 	u32			bus_freq_mhz;
@@ -84,8 +77,14 @@ int cpdma_chan_stop(struct cpdma_chan *chan);
 
 int cpdma_chan_get_stats(struct cpdma_chan *chan,
 			 struct cpdma_chan_stats *stats);
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+			     dma_addr_t data, int len, int directed);
 int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
 		      int len, int directed);
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+				  dma_addr_t data, int len, int directed);
+int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
+			   int len, int directed);
 int cpdma_chan_process(struct cpdma_chan *chan, int quota);
 
 int cpdma_ctlr_int_ctrl(struct cpdma_ctlr *ctlr, bool enable);
@@ -117,8 +116,7 @@ enum cpdma_control {
 int cpdma_control_get(struct cpdma_ctlr *ctlr, int control);
 int cpdma_control_set(struct cpdma_ctlr *ctlr, int control, int value);
 int cpdma_get_num_rx_descs(struct cpdma_ctlr *ctlr);
-void cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc);
+int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc);
 int cpdma_get_num_tx_descs(struct cpdma_ctlr *ctlr);
-int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr);
 
 #endif
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 840820402cd0..ae27be85e363 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * DaVinci Ethernet Medium Access Controller
  *
@@ -6,21 +7,6 @@
  * Copyright (C) 2009 Texas Instruments.
  *
  * ---------------------------------------------------------------------------
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- * ---------------------------------------------------------------------------
  * History:
  * 0-5 A number of folks worked on this driver in bits and pieces but the major
  *     contribution came from Suraj Iyer and Anant Gole
@@ -1385,7 +1371,7 @@ static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd)
 		return -EOPNOTSUPP;
 }
 
-static int match_first_device(struct device *dev, void *data)
+static int match_first_device(struct device *dev, const void *data)
 {
 	if (dev->parent && dev->parent->of_node)
 		return of_device_is_compatible(dev->parent->of_node,
@@ -1442,8 +1428,8 @@ static int emac_dev_open(struct net_device *ndev)
 		if (!skb)
 			break;
 
-		ret = cpdma_chan_submit(priv->rxchan, skb, skb->data,
-					skb_tailroom(skb), 0);
+		ret = cpdma_chan_idle_submit(priv->rxchan, skb, skb->data,
+					     skb_tailroom(skb), 0);
 		if (WARN_ON(ret < 0))
 			break;
 	}
@@ -1714,7 +1700,7 @@ davinci_emac_of_get_pdata(struct platform_device *pdev, struct emac_priv *priv)
 
 	if (!is_valid_ether_addr(pdata->mac_addr)) {
 		mac_addr = of_get_mac_address(np);
-		if (mac_addr)
+		if (!IS_ERR(mac_addr))
 			ether_addr_copy(pdata->mac_addr, mac_addr);
 	}
 
@@ -1912,15 +1898,11 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		ether_addr_copy(ndev->dev_addr, priv->mac_addr);
 
 	if (!is_valid_ether_addr(priv->mac_addr)) {
-		/* Try nvmem if MAC wasn't passed over pdata or DT. */
-		rc = nvmem_get_mac_address(&pdev->dev, priv->mac_addr);
-		if (rc) {
-			/* Use random MAC if still none obtained. */
-			eth_hw_addr_random(ndev);
-			memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len);
-			dev_warn(&pdev->dev, "using random MAC addr: %pM\n",
-				 priv->mac_addr);
-		}
+		/* Use random MAC if still none obtained. */
+		eth_hw_addr_random(ndev);
+		memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len);
+		dev_warn(&pdev->dev, "using random MAC addr: %pM\n",
+			 priv->mac_addr);
 	}
 
 	ndev->netdev_ops = &emac_netdev_ops;
@@ -2029,7 +2011,6 @@ static const struct dev_pm_ops davinci_emac_pm_ops = {
 	.resume		= davinci_emac_resume,
 };
 
-#if IS_ENABLED(CONFIG_OF)
 static const struct emac_platform_data am3517_emac_data = {
 	.version		= EMAC_VERSION_2,
 	.hw_ram_addr		= 0x01e20000,
@@ -2046,14 +2027,13 @@ static const struct of_device_id davinci_emac_of_match[] = {
 	{},
 };
 MODULE_DEVICE_TABLE(of, davinci_emac_of_match);
-#endif
 
 /* davinci_emac_driver: EMAC platform driver structure */
 static struct platform_driver davinci_emac_driver = {
 	.driver = {
 		.name	 = "davinci_emac",
 		.pm	 = &davinci_emac_pm_ops,
-		.of_match_table = of_match_ptr(davinci_emac_of_match),
+		.of_match_table = davinci_emac_of_match,
 	},
 	.probe = davinci_emac_probe,
 	.remove = davinci_emac_remove,
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index a98aedae1b41..38b7f6d35759 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * DaVinci MDIO Module driver
  *
@@ -7,22 +8,6 @@
  *
  * Copyright (C) 2009 Texas Instruments.
  *
- * ---------------------------------------------------------------------------
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- * ---------------------------------------------------------------------------
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -140,7 +125,7 @@ static void davinci_mdio_init_clk(struct davinci_mdio_data *data)
 static void davinci_mdio_enable(struct davinci_mdio_data *data)
 {
 	/* set enable and clock divider */
-	__raw_writel(data->clk_div | CONTROL_ENABLE, &data->regs->control);
+	writel(data->clk_div | CONTROL_ENABLE, &data->regs->control);
 }
 
 static int davinci_mdio_reset(struct mii_bus *bus)
@@ -159,7 +144,7 @@ static int davinci_mdio_reset(struct mii_bus *bus)
 	msleep(PHY_MAX_ADDR * data->access_time);
 
 	/* dump hardware version info */
-	ver = __raw_readl(&data->regs->version);
+	ver = readl(&data->regs->version);
 	dev_info(data->dev,
 		 "davinci mdio revision %d.%d, bus freq %ld\n",
 		 (ver >> 8) & 0xff, ver & 0xff,
@@ -169,7 +154,7 @@ static int davinci_mdio_reset(struct mii_bus *bus)
 		goto done;
 
 	/* get phy mask from the alive register */
-	phy_mask = __raw_readl(&data->regs->alive);
+	phy_mask = readl(&data->regs->alive);
 	if (phy_mask) {
 		/* restrict mdio bus to live phys only */
 		dev_info(data->dev, "detected phy mask %x\n", ~phy_mask);
@@ -196,11 +181,11 @@ static inline int wait_for_user_access(struct davinci_mdio_data *data)
 	u32 reg;
 
 	while (time_after(timeout, jiffies)) {
-		reg = __raw_readl(&regs->user[0].access);
+		reg = readl(&regs->user[0].access);
 		if ((reg & USERACCESS_GO) == 0)
 			return 0;
 
-		reg = __raw_readl(&regs->control);
+		reg = readl(&regs->control);
 		if ((reg & CONTROL_IDLE) == 0) {
 			usleep_range(100, 200);
 			continue;
@@ -216,7 +201,7 @@ static inline int wait_for_user_access(struct davinci_mdio_data *data)
 		return -EAGAIN;
 	}
 
-	reg = __raw_readl(&regs->user[0].access);
+	reg = readl(&regs->user[0].access);
 	if ((reg & USERACCESS_GO) == 0)
 		return 0;
 
@@ -263,7 +248,7 @@ static int davinci_mdio_read(struct mii_bus *bus, int phy_id, int phy_reg)
 		if (ret < 0)
 			break;
 
-		__raw_writel(reg, &data->regs->user[0].access);
+		writel(reg, &data->regs->user[0].access);
 
 		ret = wait_for_user_access(data);
 		if (ret == -EAGAIN)
@@ -271,7 +256,7 @@ static int davinci_mdio_read(struct mii_bus *bus, int phy_id, int phy_reg)
 		if (ret < 0)
 			break;
 
-		reg = __raw_readl(&data->regs->user[0].access);
+		reg = readl(&data->regs->user[0].access);
 		ret = (reg & USERACCESS_ACK) ? (reg & USERACCESS_DATA) : -EIO;
 		break;
 	}
@@ -307,7 +292,7 @@ static int davinci_mdio_write(struct mii_bus *bus, int phy_id,
 		if (ret < 0)
 			break;
 
-		__raw_writel(reg, &data->regs->user[0].access);
+		writel(reg, &data->regs->user[0].access);
 
 		ret = wait_for_user_access(data);
 		if (ret == -EAGAIN)
@@ -412,9 +397,9 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	data->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	data->regs = devm_ioremap_resource(dev, res);
-	if (IS_ERR(data->regs))
-		return PTR_ERR(data->regs);
+	data->regs = devm_ioremap(dev, res->start, resource_size(res));
+	if (!data->regs)
+		return -ENOMEM;
 
 	davinci_mdio_init_clk(data);
 
@@ -472,9 +457,9 @@ static int davinci_mdio_runtime_suspend(struct device *dev)
 	u32 ctrl;
 
 	/* shutdown the scan state machine */
-	ctrl = __raw_readl(&data->regs->control);
+	ctrl = readl(&data->regs->control);
 	ctrl &= ~CONTROL_ENABLE;
-	__raw_writel(ctrl, &data->regs->control);
+	writel(ctrl, &data->regs->control);
 	wait_for_idle(data);
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index c4ffdf47bad5..43d5cd59b56b 100644
--- a/drivers/net/ethernet/ti/netcp.h
+++ b/drivers/net/ethernet/ti/netcp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * NetCP driver local header
  *
@@ -8,15 +9,6 @@
  *		Santosh Shilimkar <santosh.shilimkar@ti.com>
  *		Wingman Kwok <w-kwok2@ti.com>
  *		Murali Karicheri <m-karicheri2@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef __NETCP_H__
 #define __NETCP_H__
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 1f612268c998..642843945031 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Keystone NetCP Core driver
  *
@@ -8,15 +9,6 @@
  *		Santosh Shilimkar <santosh.shilimkar@ti.com>
  *		Murali Karicheri <m-karicheri2@ti.com>
  *		Wingman Kwok <w-kwok2@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/io.h>
@@ -259,7 +251,7 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 		const char *name;
 		char node_name[32];
 
-		if (of_property_read_string(node, "label", &name) < 0) {
+		if (of_property_read_string(child, "label", &name) < 0) {
 			snprintf(node_name, sizeof(node_name), "%pOFn", child);
 			name = node_name;
 		}
@@ -2045,7 +2037,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device,
 		devm_release_mem_region(dev, res.start, size);
 	} else {
 		mac_addr = of_get_mac_address(node_interface);
-		if (mac_addr)
+		if (!IS_ERR(mac_addr))
 			ether_addr_copy(ndev->dev_addr, mac_addr);
 		else
 			eth_random_addr(ndev->dev_addr);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 5174d318901e..2c1fac33136c 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Keystone GBE and XGBE subsystem code
  *
@@ -7,15 +8,6 @@
  *		Cyril Chemparathy <cyril@ti.com>
  *		Santosh Shilimkar <santosh.shilimkar@ti.com>
  *		Wingman Kwok <w-kwok2@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/io.h>
@@ -3562,7 +3554,7 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev,
 static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		     struct device_node *node, void **inst_priv)
 {
-	struct device_node *interfaces, *interface;
+	struct device_node *interfaces, *interface, *cpts_node;
 	struct device_node *secondary_ports;
 	struct cpsw_ale_params ale_params;
 	struct gbe_priv *gbe_dev;
@@ -3657,12 +3649,16 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 
 	ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
 				gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
-	if (ret)
+	if (ret) {
+		of_node_put(interfaces);
 		return ret;
+	}
 
 	ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
-	if (ret)
+	if (ret) {
+		of_node_put(interfaces);
 		return ret;
+	}
 
 	/* Create network interfaces */
 	INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
@@ -3717,7 +3713,12 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n");
 	}
 
-	gbe_dev->cpts = cpts_create(gbe_dev->dev, gbe_dev->cpts_reg, node);
+	cpts_node = of_get_child_by_name(node, "cpts");
+	if (!cpts_node)
+		cpts_node = of_node_get(node);
+
+	gbe_dev->cpts = cpts_create(gbe_dev->dev, gbe_dev->cpts_reg, cpts_node);
+	of_node_put(cpts_node);
 	if (IS_ENABLED(CONFIG_TI_CPTS) && IS_ERR(gbe_dev->cpts)) {
 		ret = PTR_ERR(gbe_dev->cpts);
 		goto free_sec_ports;
diff --git a/drivers/net/ethernet/ti/netcp_sgmii.c b/drivers/net/ethernet/ti/netcp_sgmii.c
index 5d8419f658d0..f7cf56d6351d 100644
--- a/drivers/net/ethernet/ti/netcp_sgmii.c
+++ b/drivers/net/ethernet/ti/netcp_sgmii.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SGMI module initialisation
  *
@@ -6,14 +7,6 @@
  *		Sandeep Paulraj <s-paulraj@ti.com>
  *		Wingman Kwok <w-kwok2@ti.com>
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include "netcp.h"
diff --git a/drivers/net/ethernet/ti/netcp_xgbepcsr.c b/drivers/net/ethernet/ti/netcp_xgbepcsr.c
index 33571acc52b6..112778aedd8a 100644
--- a/drivers/net/ethernet/ti/netcp_xgbepcsr.c
+++ b/drivers/net/ethernet/ti/netcp_xgbepcsr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * XGE PCSR module initialisation
  *
@@ -5,14 +6,6 @@
  * Authors:	Sandeep Nair <sandeep_n@ti.com>
  *		WingMan Kwok <w-kwok2@ti.com>
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include "netcp.h"
 
diff --git a/drivers/net/ethernet/toshiba/Kconfig b/drivers/net/ethernet/toshiba/Kconfig
index 6f1d5b623768..9ccdf032404e 100644
--- a/drivers/net/ethernet/toshiba/Kconfig
+++ b/drivers/net/ethernet/toshiba/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Toshiba network device configuration
 #
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index 75237c81c63d..9d9f8acb7ee3 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  PS3 gelic network driver.
  *
@@ -10,20 +11,6 @@
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
  *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #undef DEBUG
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h
index fbbf9b54b173..051033580f0a 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  PS3 Platfom gelic network driver.
  *
@@ -10,20 +11,6 @@
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
  *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef _GELIC_NET_H
 #define _GELIC_NET_H
@@ -314,7 +301,7 @@ struct gelic_card {
 	 */
 	unsigned int irq;
 	struct gelic_descr *tx_top, *rx_top;
-	struct gelic_descr descr[0]; /* must be the last */
+	struct gelic_descr descr[]; /* must be the last */
 };
 
 struct gelic_port {
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
index 00ab417694ad..2db546b27ee0 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c
@@ -1,21 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  PS3 gelic network driver.
  *
  * Copyright (C) 2007 Sony Computer Entertainment Inc.
  * Copyright 2007 Sony Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #undef DEBUG
 
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h
index 11f443d8e4ea..4041d946b649 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h
@@ -1,21 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  PS3 gelic network driver.
  *
  * Copyright (C) 2007 Sony Computer Entertainment Inc.
  * Copyright 2007 Sony Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation version 2.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef _GELIC_WIRELESS_H
 #define _GELIC_WIRELESS_H
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 23417266b7ec..5b196ebfed49 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Network device driver for Cell Processor-Based Blade and Celleb platform
  *
@@ -6,20 +7,6 @@
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
  *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/compiler.h>
diff --git a/drivers/net/ethernet/toshiba/spider_net.h b/drivers/net/ethernet/toshiba/spider_net.h
index 9b6af0845a11..c0c68cbc898c 100644
--- a/drivers/net/ethernet/toshiba/spider_net.h
+++ b/drivers/net/ethernet/toshiba/spider_net.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Network device driver for Cell Processor-Based Blade and Celleb platform
  *
@@ -6,20 +7,6 @@
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
  *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef _SPIDER_NET_H
diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
index 16bd036d0682..54f655a68148 100644
--- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c
+++ b/drivers/net/ethernet/toshiba/spider_net_ethtool.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Network device driver for Cell Processor-Based Blade
  *
@@ -5,20 +6,6 @@
  *
  * Authors : Utz Bacher <utz.bacher@de.ibm.com>
  *           Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/netdevice.h>
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index c50a9772f4af..8479a440527b 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -694,10 +694,10 @@ err_out:
  * should provide a "tc35815-mac" device with a MAC address in its
  * platform_data.
  */
-static int tc35815_mac_match(struct device *dev, void *data)
+static int tc35815_mac_match(struct device *dev, const void *data)
 {
 	struct platform_device *plat_dev = to_platform_device(dev);
-	struct pci_dev *pci_dev = data;
+	const struct pci_dev *pci_dev = data;
 	unsigned int id = pci_dev->irq;
 	return !strcmp(plat_dev->name, "tc35815-mac") && plat_dev->id == id;
 }
diff --git a/drivers/net/ethernet/tundra/Kconfig b/drivers/net/ethernet/tundra/Kconfig
index 81d845e4e23b..5c909df0c3b9 100644
--- a/drivers/net/ethernet/tundra/Kconfig
+++ b/drivers/net/ethernet/tundra/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Tundra network device configuration
 #
diff --git a/drivers/net/ethernet/tundra/Makefile b/drivers/net/ethernet/tundra/Makefile
index 439f6930235b..78fee6b5b665 100644
--- a/drivers/net/ethernet/tundra/Makefile
+++ b/drivers/net/ethernet/tundra/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Tundra network device drivers.
 #
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index 37925a1d58de..78a7de3fb622 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*******************************************************************************
 
   Copyright(c) 2006 Tundra Semiconductor Corporation.
 
-  This program is free software; you can redistribute it and/or modify it
-  under the terms of the GNU General Public License as published by the Free
-  Software Foundation; either version 2 of the License, or (at your option)
-  any later version.
-
-  This program is distributed in the hope that it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, write to the Free Software Foundation, Inc., 59
-  Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 
 *******************************************************************************/
 
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.h b/drivers/net/ethernet/tundra/tsi108_eth.h
index 4a03c594b2b1..00980fdf0323 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.h
+++ b/drivers/net/ethernet/tundra/tsi108_eth.h
@@ -1,22 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * (C) Copyright 2005 Tundra Semiconductor Corp.
  * Kong Lai, <kong.lai@tundra.com).
  *
  * See file CREDITS for list of people who contributed to this
  * project.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of
- * the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 /*
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index d3d094742a7e..a962097b58c6 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # VIA device configuration
 #
diff --git a/drivers/net/ethernet/via/Makefile b/drivers/net/ethernet/via/Makefile
index 46c5d4a3d8f1..4ca40f9739b5 100644
--- a/drivers/net/ethernet/via/Makefile
+++ b/drivers/net/ethernet/via/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the VIA device drivers.
 #
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 33949248c829..ab55416a10fa 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -571,7 +571,6 @@ static void rhine_ack_events(struct rhine_private *rp, u32 mask)
 	if (rp->quirks & rqStatusWBRace)
 		iowrite8(mask >> 16, ioaddr + IntrStatus2);
 	iowrite16(mask, ioaddr + IntrStatus);
-	mmiowb();
 }
 
 /*
@@ -863,7 +862,6 @@ static int rhine_napipoll(struct napi_struct *napi, int budget)
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
 		iowrite16(enable_mask, ioaddr + IntrEnable);
-		mmiowb();
 	}
 	return work_done;
 }
@@ -1893,7 +1891,6 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 static void rhine_irq_disable(struct rhine_private *rp)
 {
 	iowrite16(0x0000, rp->base + IntrEnable);
-	mmiowb();
 }
 
 /* The interrupt handler does all of the Rx thread work and cleans up
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 27f6cf140845..346e44115c4e 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * This code is derived from the VIA reference driver (copyright message
  * below) provided to Red Hat by VIA Networking Technologies, Inc. for
@@ -24,22 +25,11 @@
  * Copyright (c) 1996, 2003 VIA Networking Technologies, Inc.
  * All rights reserved.
  *
- * This software may be redistributed and/or modified under
- * the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
- * for more details.
- *
  * Author: Chuang Liang-Shing, AJ Jiang
  *
  * Date: Jan 24, 2003
  *
  * MODULE_LICENSE("GPL");
- *
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/via/via-velocity.h b/drivers/net/ethernet/via/via-velocity.h
index 9453bfa9324a..cdfe7809e3c1 100644
--- a/drivers/net/ethernet/via/via-velocity.h
+++ b/drivers/net/ethernet/via/via-velocity.h
@@ -1,17 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Copyright (c) 1996, 2003 VIA Networking Technologies, Inc.
  * All rights reserved.
  *
- * This software may be redistributed and/or modified under
- * the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or
- * any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
- * for more details.
- *
  * File: via-velocity.h
  *
  * Purpose: Header file to define driver's private structures.
@@ -1518,7 +1509,7 @@ static inline int velocity_get_ip(struct velocity_info *vptr)
 	rcu_read_lock();
 	in_dev = __in_dev_get_rcu(vptr->netdev);
 	if (in_dev != NULL) {
-		ifa = (struct in_ifaddr *) in_dev->ifa_list;
+		ifa = rcu_dereference(in_dev->ifa_list);
 		if (ifa != NULL) {
 			memcpy(vptr->ip_addr, &ifa->ifa_address, 4);
 			res = 0;
diff --git a/drivers/net/ethernet/wiznet/Kconfig b/drivers/net/ethernet/wiznet/Kconfig
index 1981e88c18dc..0422775e1659 100644
--- a/drivers/net/ethernet/wiznet/Kconfig
+++ b/drivers/net/ethernet/wiznet/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # WIZnet devices configuration
 #
diff --git a/drivers/net/ethernet/wiznet/Makefile b/drivers/net/ethernet/wiznet/Makefile
index 1e05e1a84208..78104f0bf415 100644
--- a/drivers/net/ethernet/wiznet/Makefile
+++ b/drivers/net/ethernet/wiznet/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_WIZNET_W5100) += w5100.o
 obj-$(CONFIG_WIZNET_W5100_SPI) += w5100-spi.o
 obj-$(CONFIG_WIZNET_W5300) += w5300.o
diff --git a/drivers/net/ethernet/wiznet/w5100-spi.c b/drivers/net/ethernet/wiznet/w5100-spi.c
index 93a2d3c07303..2b4126d2427d 100644
--- a/drivers/net/ethernet/wiznet/w5100-spi.c
+++ b/drivers/net/ethernet/wiznet/w5100-spi.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Ethernet driver for the WIZnet W5100/W5200/W5500 chip.
  *
  * Copyright (C) 2016 Akinobu Mita <akinobu.mita@gmail.com>
  *
- * Licensed under the GPL-2 or later.
- *
  * Datasheet:
  * http://www.wiznet.co.kr/wp-content/uploads/wiznethome/Chip/W5100/Document/W5100_Datasheet_v1.2.6.pdf
  * http://wiznethome.cafe24.com/wp-content/uploads/wiznethome/Chip/W5200/Documents/W5200_DS_V140E.pdf
@@ -16,6 +15,7 @@
 #include <linux/delay.h>
 #include <linux/netdevice.h>
 #include <linux/of_net.h>
+#include <linux/of_device.h>
 #include <linux/spi/spi.h>
 
 #include "w5100.h"
@@ -410,14 +410,32 @@ static const struct w5100_ops w5500_ops = {
 	.init = w5500_spi_init,
 };
 
+static const struct of_device_id w5100_of_match[] = {
+	{ .compatible = "wiznet,w5100", .data = (const void*)W5100, },
+	{ .compatible = "wiznet,w5200", .data = (const void*)W5200, },
+	{ .compatible = "wiznet,w5500", .data = (const void*)W5500, },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, w5100_of_match);
+
 static int w5100_spi_probe(struct spi_device *spi)
 {
-	const struct spi_device_id *id = spi_get_device_id(spi);
+	const struct of_device_id *of_id;
 	const struct w5100_ops *ops;
+	kernel_ulong_t driver_data;
 	int priv_size;
 	const void *mac = of_get_mac_address(spi->dev.of_node);
 
-	switch (id->driver_data) {
+	if (spi->dev.of_node) {
+		of_id = of_match_device(w5100_of_match, &spi->dev);
+		if (!of_id)
+			return -ENODEV;
+		driver_data = (kernel_ulong_t)of_id->data;
+	} else {
+		driver_data = spi_get_device_id(spi)->driver_data;
+	}
+
+	switch (driver_data) {
 	case W5100:
 		ops = &w5100_spi_ops;
 		priv_size = 0;
@@ -454,6 +472,7 @@ static struct spi_driver w5100_spi_driver = {
 	.driver		= {
 		.name	= "w5100",
 		.pm	= &w5100_pm_ops,
+		.of_match_table = w5100_of_match,
 	},
 	.probe		= w5100_spi_probe,
 	.remove		= w5100_spi_remove,
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index d8ba512f166a..bede1ff289c5 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Ethernet driver for the WIZnet W5100 chip.
  *
  * Copyright (C) 2006-2008 WIZnet Co.,Ltd.
  * Copyright (C) 2012 Mike Sinkovsky <msink@permonline.ru>
- *
- * Licensed under the GPL-2 or later.
  */
 
 #include <linux/kernel.h>
@@ -219,7 +218,6 @@ static inline int __w5100_write_direct(struct net_device *ndev, u32 addr,
 static inline int w5100_write_direct(struct net_device *ndev, u32 addr, u8 data)
 {
 	__w5100_write_direct(ndev, addr, data);
-	mmiowb();
 
 	return 0;
 }
@@ -236,7 +234,6 @@ static int w5100_write16_direct(struct net_device *ndev, u32 addr, u16 data)
 {
 	__w5100_write_direct(ndev, addr, data >> 8);
 	__w5100_write_direct(ndev, addr + 1, data);
-	mmiowb();
 
 	return 0;
 }
@@ -260,8 +257,6 @@ static int w5100_writebulk_direct(struct net_device *ndev, u32 addr,
 	for (i = 0; i < len; i++, addr++)
 		__w5100_write_direct(ndev, addr, *buf++);
 
-	mmiowb();
-
 	return 0;
 }
 
@@ -375,7 +370,6 @@ static int w5100_readbulk_indirect(struct net_device *ndev, u32 addr, u8 *buf,
 	for (i = 0; i < len; i++)
 		*buf++ = w5100_read_direct(ndev, W5100_IDM_DR);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mmio_priv->reg_lock, flags);
 
 	return 0;
@@ -394,7 +388,6 @@ static int w5100_writebulk_indirect(struct net_device *ndev, u32 addr,
 	for (i = 0; i < len; i++)
 		__w5100_write_direct(ndev, W5100_IDM_DR, *buf++);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mmio_priv->reg_lock, flags);
 
 	return 0;
@@ -1164,7 +1157,7 @@ int w5100_probe(struct device *dev, const struct w5100_ops *ops,
 	INIT_WORK(&priv->setrx_work, w5100_setrx_work);
 	INIT_WORK(&priv->restart_work, w5100_restart_work);
 
-	if (mac_addr)
+	if (!IS_ERR_OR_NULL(mac_addr))
 		memcpy(ndev->dev_addr, mac_addr, ETH_ALEN);
 	else
 		eth_hw_addr_random(ndev);
diff --git a/drivers/net/ethernet/wiznet/w5100.h b/drivers/net/ethernet/wiznet/w5100.h
index 17983a3b8d6c..5d3d4b541fec 100644
--- a/drivers/net/ethernet/wiznet/w5100.h
+++ b/drivers/net/ethernet/wiznet/w5100.h
@@ -1,10 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  * Ethernet driver for the WIZnet W5100 chip.
  *
  * Copyright (C) 2006-2008 WIZnet Co.,Ltd.
  * Copyright (C) 2012 Mike Sinkovsky <msink@permonline.ru>
- *
- * Licensed under the GPL-2 or later.
  */
 
 enum {
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index f9da5d6172e3..6ba2747779ce 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Ethernet driver for the WIZnet W5300 chip.
  *
  * Copyright (C) 2008-2009 WIZnet Co.,Ltd.
  * Copyright (C) 2011 Taehun Kim <kth3321 <at> gmail.com>
  * Copyright (C) 2012 Mike Sinkovsky <msink@permonline.ru>
- *
- * Licensed under the GPL-2 or later.
  */
 
 #include <linux/kernel.h>
@@ -141,7 +140,6 @@ static u16 w5300_read_indirect(struct w5300_priv *priv, u16 addr)
 
 	spin_lock_irqsave(&priv->reg_lock, flags);
 	w5300_write_direct(priv, W5300_IDM_AR, addr);
-	mmiowb();
 	data = w5300_read_direct(priv, W5300_IDM_DR);
 	spin_unlock_irqrestore(&priv->reg_lock, flags);
 
@@ -154,9 +152,7 @@ static void w5300_write_indirect(struct w5300_priv *priv, u16 addr, u16 data)
 
 	spin_lock_irqsave(&priv->reg_lock, flags);
 	w5300_write_direct(priv, W5300_IDM_AR, addr);
-	mmiowb();
 	w5300_write_direct(priv, W5300_IDM_DR, data);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->reg_lock, flags);
 }
 
@@ -192,7 +188,6 @@ static int w5300_command(struct w5300_priv *priv, u16 cmd)
 	unsigned long timeout = jiffies + msecs_to_jiffies(100);
 
 	w5300_write(priv, W5300_S0_CR, cmd);
-	mmiowb();
 
 	while (w5300_read(priv, W5300_S0_CR) != 0) {
 		if (time_after(jiffies, timeout))
@@ -241,18 +236,15 @@ static void w5300_write_macaddr(struct w5300_priv *priv)
 	w5300_write(priv, W5300_SHARH,
 		      ndev->dev_addr[4] << 8 |
 		      ndev->dev_addr[5]);
-	mmiowb();
 }
 
 static void w5300_hw_reset(struct w5300_priv *priv)
 {
 	w5300_write_direct(priv, W5300_MR, MR_RST);
-	mmiowb();
 	mdelay(5);
 	w5300_write_direct(priv, W5300_MR, priv->indirect ?
 				 MR_WDF(7) | MR_PB | MR_IND :
 				 MR_WDF(7) | MR_PB);
-	mmiowb();
 	w5300_write(priv, W5300_IMR, 0);
 	w5300_write_macaddr(priv);
 
@@ -264,24 +256,20 @@ static void w5300_hw_reset(struct w5300_priv *priv)
 	w5300_write32(priv, W5300_TMSRL, 64 << 24);
 	w5300_write32(priv, W5300_TMSRH, 0);
 	w5300_write(priv, W5300_MTYPE, 0x00ff);
-	mmiowb();
 }
 
 static void w5300_hw_start(struct w5300_priv *priv)
 {
 	w5300_write(priv, W5300_S0_MR, priv->promisc ?
 			  S0_MR_MACRAW : S0_MR_MACRAW_MF);
-	mmiowb();
 	w5300_command(priv, S0_CR_OPEN);
 	w5300_write(priv, W5300_S0_IMR, S0_IR_RECV | S0_IR_SENDOK);
 	w5300_write(priv, W5300_IMR, IR_S0);
-	mmiowb();
 }
 
 static void w5300_hw_close(struct w5300_priv *priv)
 {
 	w5300_write(priv, W5300_IMR, 0);
-	mmiowb();
 	w5300_command(priv, S0_CR_CLOSE);
 }
 
@@ -372,7 +360,6 @@ static netdev_tx_t w5300_start_tx(struct sk_buff *skb, struct net_device *ndev)
 	netif_stop_queue(ndev);
 
 	w5300_write_frame(priv, skb->data, skb->len);
-	mmiowb();
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += skb->len;
 	dev_kfree_skb(skb);
@@ -419,7 +406,6 @@ static int w5300_napi_poll(struct napi_struct *napi, int budget)
 	if (rx_count < budget) {
 		napi_complete_done(napi, rx_count);
 		w5300_write(priv, W5300_IMR, IR_S0);
-		mmiowb();
 	}
 
 	return rx_count;
@@ -434,7 +420,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance)
 	if (!ir)
 		return IRQ_NONE;
 	w5300_write(priv, W5300_S0_IR, ir);
-	mmiowb();
 
 	if (ir & S0_IR_SENDOK) {
 		netif_dbg(priv, tx_done, ndev, "tx done\n");
@@ -444,7 +429,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance)
 	if (ir & S0_IR_RECV) {
 		if (napi_schedule_prep(&priv->napi)) {
 			w5300_write(priv, W5300_IMR, 0);
-			mmiowb();
 			__napi_schedule(&priv->napi);
 		}
 	}
diff --git a/drivers/net/ethernet/xilinx/Kconfig b/drivers/net/ethernet/xilinx/Kconfig
index da4ec575ccf9..8d994cebb6b0 100644
--- a/drivers/net/ethernet/xilinx/Kconfig
+++ b/drivers/net/ethernet/xilinx/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Xilink device configuration
 #
@@ -5,7 +6,7 @@
 config NET_VENDOR_XILINX
 	bool "Xilinx devices"
 	default y
-	depends on PPC || PPC32 || MICROBLAZE || ARCH_ZYNQ || MIPS
+	depends on PPC || PPC32 || MICROBLAZE || ARCH_ZYNQ || MIPS || X86 || ARM || COMPILE_TEST
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -25,16 +26,15 @@ config XILINX_EMACLITE
 
 config XILINX_AXI_EMAC
 	tristate "Xilinx 10/100/1000 AXI Ethernet support"
-	depends on MICROBLAZE
-	select PHYLIB
+	depends on MICROBLAZE || X86 || ARM || COMPILE_TEST
+	select PHYLINK
 	---help---
 	  This driver supports the 10/100/1000 Ethernet from Xilinx for the
 	  AXI bus interface used in Xilinx Virtex FPGAs.
 
 config XILINX_LL_TEMAC
 	tristate "Xilinx LL TEMAC (LocalLink Tri-mode Ethernet MAC) driver"
-	depends on (PPC || MICROBLAZE)
-	depends on !64BIT || BROKEN
+	depends on PPC || MICROBLAZE || X86 || COMPILE_TEST
 	select PHYLIB
 	---help---
 	  This driver supports the Xilinx 10/100/1000 LocalLink TEMAC
diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h
index 107575225383..276292bca334 100644
--- a/drivers/net/ethernet/xilinx/ll_temac.h
+++ b/drivers/net/ethernet/xilinx/ll_temac.h
@@ -334,6 +334,9 @@ struct temac_local {
 
 	/* Connection to PHY device */
 	struct device_node *phy_node;
+	/* For non-device-tree devices */
+	char phy_name[MII_BUS_ID_SIZE + 3];
+	phy_interface_t phy_interface;
 
 	/* MDIO bus data */
 	struct mii_bus *mii_bus;	/* MII bus reference */
@@ -344,8 +347,10 @@ struct temac_local {
 #ifdef CONFIG_PPC_DCR
 	dcr_host_t sdma_dcrs;
 #endif
-	u32 (*dma_in)(struct temac_local *, int);
-	void (*dma_out)(struct temac_local *, int, u32);
+	u32 (*temac_ior)(struct temac_local *lp, int offset);
+	void (*temac_iow)(struct temac_local *lp, int offset, u32 value);
+	u32 (*dma_in)(struct temac_local *lp, int reg);
+	void (*dma_out)(struct temac_local *lp, int reg, u32 value);
 
 	int tx_irq;
 	int rx_irq;
@@ -353,7 +358,10 @@ struct temac_local {
 
 	struct sk_buff **rx_skb;
 	spinlock_t rx_lock;
-	struct mutex indirect_mutex;
+	/* For synchronization of indirect register access.  Must be
+	 * shared mutex between interfaces in same TEMAC block.
+	 */
+	spinlock_t *indirect_lock;
 	u32 options;			/* Current options word */
 	int last_link;
 	unsigned int temac_features;
@@ -367,18 +375,25 @@ struct temac_local {
 	int tx_bd_next;
 	int tx_bd_tail;
 	int rx_bd_ci;
+
+	/* DMA channel control setup */
+	u32 tx_chnl_ctrl;
+	u32 rx_chnl_ctrl;
 };
 
+/* Wrappers for temac_ior()/temac_iow() function pointers above */
+#define temac_ior(lp, o) ((lp)->temac_ior(lp, o))
+#define temac_iow(lp, o, v) ((lp)->temac_iow(lp, o, v))
+
 /* xilinx_temac.c */
-u32 temac_ior(struct temac_local *lp, int offset);
-void temac_iow(struct temac_local *lp, int offset, u32 value);
 int temac_indirect_busywait(struct temac_local *lp);
 u32 temac_indirect_in32(struct temac_local *lp, int reg);
+u32 temac_indirect_in32_locked(struct temac_local *lp, int reg);
 void temac_indirect_out32(struct temac_local *lp, int reg, u32 value);
-
+void temac_indirect_out32_locked(struct temac_local *lp, int reg, u32 value);
 
 /* xilinx_temac_mdio.c */
-int temac_mdio_setup(struct temac_local *lp, struct device_node *np);
+int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev);
 void temac_mdio_teardown(struct temac_local *lp);
 
 #endif /* XILINX_LL_TEMAC_H */
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 15bb058db392..21c1b4322ea7 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Driver for Xilinx TEMAC Ethernet device
  *
@@ -21,7 +22,6 @@
  *
  * TODO:
  * - Factor out locallink DMA code into separate driver
- * - Fix multicast assignment.
  * - Fix support for hardware checksumming.
  * - Testing.  Lots and lots of testing.
  *
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
+#include <linux/if_ether.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
@@ -51,6 +52,8 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
+#include <linux/processor.h>
+#include <linux/platform_data/xilinx-ll-temac.h>
 
 #include "ll_temac.h"
 
@@ -61,81 +64,170 @@
  * Low level register access functions
  */
 
-u32 temac_ior(struct temac_local *lp, int offset)
+static u32 _temac_ior_be(struct temac_local *lp, int offset)
 {
-	return in_be32(lp->regs + offset);
+	return ioread32be(lp->regs + offset);
 }
 
-void temac_iow(struct temac_local *lp, int offset, u32 value)
+static void _temac_iow_be(struct temac_local *lp, int offset, u32 value)
 {
-	out_be32(lp->regs + offset, value);
+	return iowrite32be(value, lp->regs + offset);
 }
 
+static u32 _temac_ior_le(struct temac_local *lp, int offset)
+{
+	return ioread32(lp->regs + offset);
+}
+
+static void _temac_iow_le(struct temac_local *lp, int offset, u32 value)
+{
+	return iowrite32(value, lp->regs + offset);
+}
+
+static bool hard_acs_rdy(struct temac_local *lp)
+{
+	return temac_ior(lp, XTE_RDY0_OFFSET) & XTE_RDY0_HARD_ACS_RDY_MASK;
+}
+
+static bool hard_acs_rdy_or_timeout(struct temac_local *lp, ktime_t timeout)
+{
+	ktime_t cur = ktime_get();
+
+	return hard_acs_rdy(lp) || ktime_after(cur, timeout);
+}
+
+/* Poll for maximum 20 ms.  This is similar to the 2 jiffies @ 100 Hz
+ * that was used before, and should cover MDIO bus speed down to 3200
+ * Hz.
+ */
+#define HARD_ACS_RDY_POLL_NS (20 * NSEC_PER_MSEC)
+
+/**
+ * temac_indirect_busywait - Wait for current indirect register access
+ * to complete.
+ */
 int temac_indirect_busywait(struct temac_local *lp)
 {
-	unsigned long end = jiffies + 2;
+	ktime_t timeout = ktime_add_ns(ktime_get(), HARD_ACS_RDY_POLL_NS);
 
-	while (!(temac_ior(lp, XTE_RDY0_OFFSET) & XTE_RDY0_HARD_ACS_RDY_MASK)) {
-		if (time_before_eq(end, jiffies)) {
-			WARN_ON(1);
-			return -ETIMEDOUT;
-		}
-		msleep(1);
-	}
-	return 0;
+	spin_until_cond(hard_acs_rdy_or_timeout(lp, timeout));
+	if (WARN_ON(!hard_acs_rdy(lp)))
+		return -ETIMEDOUT;
+	else
+		return 0;
 }
 
 /**
- * temac_indirect_in32
- *
- * lp->indirect_mutex must be held when calling this function
+ * temac_indirect_in32 - Indirect register read access.  This function
+ * must be called without lp->indirect_lock being held.
  */
 u32 temac_indirect_in32(struct temac_local *lp, int reg)
 {
-	u32 val;
+	unsigned long flags;
+	int val;
 
-	if (temac_indirect_busywait(lp))
+	spin_lock_irqsave(lp->indirect_lock, flags);
+	val = temac_indirect_in32_locked(lp, reg);
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
+	return val;
+}
+
+/**
+ * temac_indirect_in32_locked - Indirect register read access.  This
+ * function must be called with lp->indirect_lock being held.  Use
+ * this together with spin_lock_irqsave/spin_lock_irqrestore to avoid
+ * repeated lock/unlock and to ensure uninterrupted access to indirect
+ * registers.
+ */
+u32 temac_indirect_in32_locked(struct temac_local *lp, int reg)
+{
+	/* This initial wait should normally not spin, as we always
+	 * try to wait for indirect access to complete before
+	 * releasing the indirect_lock.
+	 */
+	if (WARN_ON(temac_indirect_busywait(lp)))
 		return -ETIMEDOUT;
+	/* Initiate read from indirect register */
 	temac_iow(lp, XTE_CTL0_OFFSET, reg);
-	if (temac_indirect_busywait(lp))
+	/* Wait for indirect register access to complete.  We really
+	 * should not see timeouts, and could even end up causing
+	 * problem for following indirect access, so let's make a bit
+	 * of WARN noise.
+	 */
+	if (WARN_ON(temac_indirect_busywait(lp)))
 		return -ETIMEDOUT;
-	val = temac_ior(lp, XTE_LSW0_OFFSET);
-
-	return val;
+	/* Value is ready now */
+	return temac_ior(lp, XTE_LSW0_OFFSET);
 }
 
 /**
- * temac_indirect_out32
- *
- * lp->indirect_mutex must be held when calling this function
+ * temac_indirect_out32 - Indirect register write access.  This function
+ * must be called without lp->indirect_lock being held.
  */
 void temac_indirect_out32(struct temac_local *lp, int reg, u32 value)
 {
-	if (temac_indirect_busywait(lp))
+	unsigned long flags;
+
+	spin_lock_irqsave(lp->indirect_lock, flags);
+	temac_indirect_out32_locked(lp, reg, value);
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
+}
+
+/**
+ * temac_indirect_out32_locked - Indirect register write access.  This
+ * function must be called with lp->indirect_lock being held.  Use
+ * this together with spin_lock_irqsave/spin_lock_irqrestore to avoid
+ * repeated lock/unlock and to ensure uninterrupted access to indirect
+ * registers.
+ */
+void temac_indirect_out32_locked(struct temac_local *lp, int reg, u32 value)
+{
+	/* As in temac_indirect_in32_locked(), we should normally not
+	 * spin here.  And if it happens, we actually end up silently
+	 * ignoring the write request.  Ouch.
+	 */
+	if (WARN_ON(temac_indirect_busywait(lp)))
 		return;
+	/* Initiate write to indirect register */
 	temac_iow(lp, XTE_LSW0_OFFSET, value);
 	temac_iow(lp, XTE_CTL0_OFFSET, CNTLREG_WRITE_ENABLE_MASK | reg);
-	temac_indirect_busywait(lp);
+	/* As in temac_indirect_in32_locked(), we should not see timeouts
+	 * here.  And if it happens, we continue before the write has
+	 * completed.  Not good.
+	 */
+	WARN_ON(temac_indirect_busywait(lp));
 }
 
 /**
- * temac_dma_in32 - Memory mapped DMA read, this function expects a
- * register input that is based on DCR word addresses which
- * are then converted to memory mapped byte addresses
+ * temac_dma_in32_* - Memory mapped DMA read, these function expects a
+ * register input that is based on DCR word addresses which are then
+ * converted to memory mapped byte addresses.  To be assigned to
+ * lp->dma_in32.
  */
-static u32 temac_dma_in32(struct temac_local *lp, int reg)
+static u32 temac_dma_in32_be(struct temac_local *lp, int reg)
 {
-	return in_be32(lp->sdma_regs + (reg << 2));
+	return ioread32be(lp->sdma_regs + (reg << 2));
+}
+
+static u32 temac_dma_in32_le(struct temac_local *lp, int reg)
+{
+	return ioread32(lp->sdma_regs + (reg << 2));
 }
 
 /**
- * temac_dma_out32 - Memory mapped DMA read, this function expects a
- * register input that is based on DCR word addresses which
- * are then converted to memory mapped byte addresses
+ * temac_dma_out32_* - Memory mapped DMA read, these function expects
+ * a register input that is based on DCR word addresses which are then
+ * converted to memory mapped byte addresses.  To be assigned to
+ * lp->dma_out32.
  */
-static void temac_dma_out32(struct temac_local *lp, int reg, u32 value)
+static void temac_dma_out32_be(struct temac_local *lp, int reg, u32 value)
+{
+	iowrite32be(value, lp->sdma_regs + (reg << 2));
+}
+
+static void temac_dma_out32_le(struct temac_local *lp, int reg, u32 value)
 {
-	out_be32(lp->sdma_regs + (reg << 2), value);
+	iowrite32(value, lp->sdma_regs + (reg << 2));
 }
 
 /* DMA register access functions can be DCR based or memory mapped.
@@ -187,7 +279,7 @@ static int temac_dcr_setup(struct temac_local *lp, struct platform_device *op,
 
 /*
  * temac_dcr_setup - This is a stub for when DCR is not supported,
- * such as with MicroBlaze
+ * such as with MicroBlaze and x86
  */
 static int temac_dcr_setup(struct temac_local *lp, struct platform_device *op,
 				struct device_node *np)
@@ -225,7 +317,6 @@ static void temac_dma_bd_release(struct net_device *ndev)
 		dma_free_coherent(ndev->dev.parent,
 				sizeof(*lp->tx_bd_v) * TX_BD_NUM,
 				lp->tx_bd_v, lp->tx_bd_p);
-	kfree(lp->rx_skb);
 }
 
 /**
@@ -235,9 +326,11 @@ static int temac_dma_bd_init(struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
 	struct sk_buff *skb;
+	dma_addr_t skb_dma_addr;
 	int i;
 
-	lp->rx_skb = kcalloc(RX_BD_NUM, sizeof(*lp->rx_skb), GFP_KERNEL);
+	lp->rx_skb = devm_kcalloc(&ndev->dev, RX_BD_NUM, sizeof(*lp->rx_skb),
+				  GFP_KERNEL);
 	if (!lp->rx_skb)
 		goto out;
 
@@ -256,13 +349,13 @@ static int temac_dma_bd_init(struct net_device *ndev)
 		goto out;
 
 	for (i = 0; i < TX_BD_NUM; i++) {
-		lp->tx_bd_v[i].next = lp->tx_bd_p +
-				sizeof(*lp->tx_bd_v) * ((i + 1) % TX_BD_NUM);
+		lp->tx_bd_v[i].next = cpu_to_be32(lp->tx_bd_p
+				+ sizeof(*lp->tx_bd_v) * ((i + 1) % TX_BD_NUM));
 	}
 
 	for (i = 0; i < RX_BD_NUM; i++) {
-		lp->rx_bd_v[i].next = lp->rx_bd_p +
-				sizeof(*lp->rx_bd_v) * ((i + 1) % RX_BD_NUM);
+		lp->rx_bd_v[i].next = cpu_to_be32(lp->rx_bd_p
+				+ sizeof(*lp->rx_bd_v) * ((i + 1) % RX_BD_NUM));
 
 		skb = netdev_alloc_skb_ip_align(ndev,
 						XTE_MAX_JUMBO_FRAME_SIZE);
@@ -271,31 +364,23 @@ static int temac_dma_bd_init(struct net_device *ndev)
 
 		lp->rx_skb[i] = skb;
 		/* returns physical address of skb->data */
-		lp->rx_bd_v[i].phys = dma_map_single(ndev->dev.parent,
-						     skb->data,
-						     XTE_MAX_JUMBO_FRAME_SIZE,
-						     DMA_FROM_DEVICE);
-		lp->rx_bd_v[i].len = XTE_MAX_JUMBO_FRAME_SIZE;
-		lp->rx_bd_v[i].app0 = STS_CTRL_APP0_IRQONEND;
+		skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
+					      XTE_MAX_JUMBO_FRAME_SIZE,
+					      DMA_FROM_DEVICE);
+		lp->rx_bd_v[i].phys = cpu_to_be32(skb_dma_addr);
+		lp->rx_bd_v[i].len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
+		lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
 	}
 
-	lp->dma_out(lp, TX_CHNL_CTRL, 0x10220400 |
-					  CHNL_CTRL_IRQ_EN |
-					  CHNL_CTRL_IRQ_DLY_EN |
-					  CHNL_CTRL_IRQ_COAL_EN);
-	/* 0x10220483 */
-	/* 0x00100483 */
-	lp->dma_out(lp, RX_CHNL_CTRL, 0xff070000 |
-					  CHNL_CTRL_IRQ_EN |
-					  CHNL_CTRL_IRQ_DLY_EN |
-					  CHNL_CTRL_IRQ_COAL_EN |
-					  CHNL_CTRL_IRQ_IOE);
-	/* 0xff010283 */
-
-	lp->dma_out(lp, RX_CURDESC_PTR,  lp->rx_bd_p);
-	lp->dma_out(lp, RX_TAILDESC_PTR,
-		       lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
-	lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p);
+	/* Configure DMA channel (irq setup) */
+	lp->dma_out(lp, TX_CHNL_CTRL, lp->tx_chnl_ctrl |
+		    0x00000400 | // Use 1 Bit Wide Counters. Currently Not Used!
+		    CHNL_CTRL_IRQ_EN | CHNL_CTRL_IRQ_ERR_EN |
+		    CHNL_CTRL_IRQ_DLY_EN | CHNL_CTRL_IRQ_COAL_EN);
+	lp->dma_out(lp, RX_CHNL_CTRL, lp->rx_chnl_ctrl |
+		    CHNL_CTRL_IRQ_IOE |
+		    CHNL_CTRL_IRQ_EN | CHNL_CTRL_IRQ_ERR_EN |
+		    CHNL_CTRL_IRQ_DLY_EN | CHNL_CTRL_IRQ_COAL_EN);
 
 	/* Init descriptor indexes */
 	lp->tx_bd_ci = 0;
@@ -303,6 +388,15 @@ static int temac_dma_bd_init(struct net_device *ndev)
 	lp->tx_bd_tail = 0;
 	lp->rx_bd_ci = 0;
 
+	/* Enable RX DMA transfers */
+	wmb();
+	lp->dma_out(lp, RX_CURDESC_PTR,  lp->rx_bd_p);
+	lp->dma_out(lp, RX_TAILDESC_PTR,
+		       lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
+
+	/* Prepare for TX DMA transfer */
+	lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p);
+
 	return 0;
 
 out:
@@ -317,25 +411,26 @@ out:
 static void temac_do_set_mac_address(struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
+	unsigned long flags;
 
 	/* set up unicast MAC address filter set its mac address */
-	mutex_lock(&lp->indirect_mutex);
-	temac_indirect_out32(lp, XTE_UAW0_OFFSET,
-			     (ndev->dev_addr[0]) |
-			     (ndev->dev_addr[1] << 8) |
-			     (ndev->dev_addr[2] << 16) |
-			     (ndev->dev_addr[3] << 24));
+	spin_lock_irqsave(lp->indirect_lock, flags);
+	temac_indirect_out32_locked(lp, XTE_UAW0_OFFSET,
+				    (ndev->dev_addr[0]) |
+				    (ndev->dev_addr[1] << 8) |
+				    (ndev->dev_addr[2] << 16) |
+				    (ndev->dev_addr[3] << 24));
 	/* There are reserved bits in EUAW1
 	 * so don't affect them Set MAC bits [47:32] in EUAW1 */
-	temac_indirect_out32(lp, XTE_UAW1_OFFSET,
-			     (ndev->dev_addr[4] & 0x000000ff) |
-			     (ndev->dev_addr[5] << 8));
-	mutex_unlock(&lp->indirect_mutex);
+	temac_indirect_out32_locked(lp, XTE_UAW1_OFFSET,
+				    (ndev->dev_addr[4] & 0x000000ff) |
+				    (ndev->dev_addr[5] << 8));
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
 }
 
 static int temac_init_mac_address(struct net_device *ndev, const void *address)
 {
-	memcpy(ndev->dev_addr, address, ETH_ALEN);
+	ether_addr_copy(ndev->dev_addr, address);
 	if (!is_valid_ether_addr(ndev->dev_addr))
 		eth_hw_addr_random(ndev);
 	temac_do_set_mac_address(ndev);
@@ -356,49 +451,58 @@ static int temac_set_mac_address(struct net_device *ndev, void *p)
 static void temac_set_multicast_list(struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
-	u32 multi_addr_msw, multi_addr_lsw, val;
-	int i;
+	u32 multi_addr_msw, multi_addr_lsw;
+	int i = 0;
+	unsigned long flags;
+	bool promisc_mode_disabled = false;
 
-	mutex_lock(&lp->indirect_mutex);
-	if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) ||
-	    netdev_mc_count(ndev) > MULTICAST_CAM_TABLE_NUM) {
-		/*
-		 *	We must make the kernel realise we had to move
-		 *	into promisc mode or we start all out war on
-		 *	the cable. If it was a promisc request the
-		 *	flag is already set. If not we assert it.
-		 */
-		ndev->flags |= IFF_PROMISC;
+	if (ndev->flags & (IFF_PROMISC | IFF_ALLMULTI) ||
+	    (netdev_mc_count(ndev) > MULTICAST_CAM_TABLE_NUM)) {
 		temac_indirect_out32(lp, XTE_AFM_OFFSET, XTE_AFM_EPPRM_MASK);
 		dev_info(&ndev->dev, "Promiscuous mode enabled.\n");
-	} else if (!netdev_mc_empty(ndev)) {
+		return;
+	}
+
+	spin_lock_irqsave(lp->indirect_lock, flags);
+
+	if (!netdev_mc_empty(ndev)) {
 		struct netdev_hw_addr *ha;
 
-		i = 0;
 		netdev_for_each_mc_addr(ha, ndev) {
-			if (i >= MULTICAST_CAM_TABLE_NUM)
+			if (WARN_ON(i >= MULTICAST_CAM_TABLE_NUM))
 				break;
 			multi_addr_msw = ((ha->addr[3] << 24) |
 					  (ha->addr[2] << 16) |
 					  (ha->addr[1] << 8) |
 					  (ha->addr[0]));
-			temac_indirect_out32(lp, XTE_MAW0_OFFSET,
-					     multi_addr_msw);
+			temac_indirect_out32_locked(lp, XTE_MAW0_OFFSET,
+						    multi_addr_msw);
 			multi_addr_lsw = ((ha->addr[5] << 8) |
 					  (ha->addr[4]) | (i << 16));
-			temac_indirect_out32(lp, XTE_MAW1_OFFSET,
-					     multi_addr_lsw);
+			temac_indirect_out32_locked(lp, XTE_MAW1_OFFSET,
+						    multi_addr_lsw);
 			i++;
 		}
-	} else {
-		val = temac_indirect_in32(lp, XTE_AFM_OFFSET);
-		temac_indirect_out32(lp, XTE_AFM_OFFSET,
-				     val & ~XTE_AFM_EPPRM_MASK);
-		temac_indirect_out32(lp, XTE_MAW0_OFFSET, 0);
-		temac_indirect_out32(lp, XTE_MAW1_OFFSET, 0);
-		dev_info(&ndev->dev, "Promiscuous mode disabled.\n");
 	}
-	mutex_unlock(&lp->indirect_mutex);
+
+	/* Clear all or remaining/unused address table entries */
+	while (i < MULTICAST_CAM_TABLE_NUM) {
+		temac_indirect_out32_locked(lp, XTE_MAW0_OFFSET, 0);
+		temac_indirect_out32_locked(lp, XTE_MAW1_OFFSET, i << 16);
+		i++;
+	}
+
+	/* Enable address filter block if currently disabled */
+	if (temac_indirect_in32_locked(lp, XTE_AFM_OFFSET)
+	    & XTE_AFM_EPPRM_MASK) {
+		temac_indirect_out32_locked(lp, XTE_AFM_OFFSET, 0);
+		promisc_mode_disabled = true;
+	}
+
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
+
+	if (promisc_mode_disabled)
+		dev_info(&ndev->dev, "Promiscuous mode disabled.\n");
 }
 
 static struct temac_option {
@@ -489,17 +593,19 @@ static u32 temac_setoptions(struct net_device *ndev, u32 options)
 	struct temac_local *lp = netdev_priv(ndev);
 	struct temac_option *tp = &temac_options[0];
 	int reg;
+	unsigned long flags;
 
-	mutex_lock(&lp->indirect_mutex);
+	spin_lock_irqsave(lp->indirect_lock, flags);
 	while (tp->opt) {
-		reg = temac_indirect_in32(lp, tp->reg) & ~tp->m_or;
-		if (options & tp->opt)
+		reg = temac_indirect_in32_locked(lp, tp->reg) & ~tp->m_or;
+		if (options & tp->opt) {
 			reg |= tp->m_or;
-		temac_indirect_out32(lp, tp->reg, reg);
+			temac_indirect_out32_locked(lp, tp->reg, reg);
+		}
 		tp++;
 	}
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
 	lp->options |= options;
-	mutex_unlock(&lp->indirect_mutex);
 
 	return 0;
 }
@@ -510,6 +616,7 @@ static void temac_device_reset(struct net_device *ndev)
 	struct temac_local *lp = netdev_priv(ndev);
 	u32 timeout;
 	u32 val;
+	unsigned long flags;
 
 	/* Perform a software reset */
 
@@ -518,7 +625,6 @@ static void temac_device_reset(struct net_device *ndev)
 
 	dev_dbg(&ndev->dev, "%s()\n", __func__);
 
-	mutex_lock(&lp->indirect_mutex);
 	/* Reset the receiver and wait for it to finish reset */
 	temac_indirect_out32(lp, XTE_RXC1_OFFSET, XTE_RXC1_RXRST_MASK);
 	timeout = 1000;
@@ -544,8 +650,11 @@ static void temac_device_reset(struct net_device *ndev)
 	}
 
 	/* Disable the receiver */
-	val = temac_indirect_in32(lp, XTE_RXC1_OFFSET);
-	temac_indirect_out32(lp, XTE_RXC1_OFFSET, val & ~XTE_RXC1_RXEN_MASK);
+	spin_lock_irqsave(lp->indirect_lock, flags);
+	val = temac_indirect_in32_locked(lp, XTE_RXC1_OFFSET);
+	temac_indirect_out32_locked(lp, XTE_RXC1_OFFSET,
+				    val & ~XTE_RXC1_RXEN_MASK);
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
 
 	/* Reset Local Link (DMA) */
 	lp->dma_out(lp, DMA_CONTROL_REG, DMA_CONTROL_RST);
@@ -565,12 +674,12 @@ static void temac_device_reset(struct net_device *ndev)
 				"temac_device_reset descriptor allocation failed\n");
 	}
 
-	temac_indirect_out32(lp, XTE_RXC0_OFFSET, 0);
-	temac_indirect_out32(lp, XTE_RXC1_OFFSET, 0);
-	temac_indirect_out32(lp, XTE_TXC_OFFSET, 0);
-	temac_indirect_out32(lp, XTE_FCC_OFFSET, XTE_FCC_RXFLO_MASK);
-
-	mutex_unlock(&lp->indirect_mutex);
+	spin_lock_irqsave(lp->indirect_lock, flags);
+	temac_indirect_out32_locked(lp, XTE_RXC0_OFFSET, 0);
+	temac_indirect_out32_locked(lp, XTE_RXC1_OFFSET, 0);
+	temac_indirect_out32_locked(lp, XTE_TXC_OFFSET, 0);
+	temac_indirect_out32_locked(lp, XTE_FCC_OFFSET, XTE_FCC_RXFLO_MASK);
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
 
 	/* Sync default options with HW
 	 * but leave receiver and transmitter disabled.  */
@@ -594,13 +703,14 @@ static void temac_adjust_link(struct net_device *ndev)
 	struct phy_device *phy = ndev->phydev;
 	u32 mii_speed;
 	int link_state;
+	unsigned long flags;
 
 	/* hash together the state values to decide if something has changed */
 	link_state = phy->speed | (phy->duplex << 1) | phy->link;
 
-	mutex_lock(&lp->indirect_mutex);
 	if (lp->last_link != link_state) {
-		mii_speed = temac_indirect_in32(lp, XTE_EMCFG_OFFSET);
+		spin_lock_irqsave(lp->indirect_lock, flags);
+		mii_speed = temac_indirect_in32_locked(lp, XTE_EMCFG_OFFSET);
 		mii_speed &= ~XTE_EMCFG_LINKSPD_MASK;
 
 		switch (phy->speed) {
@@ -610,27 +720,57 @@ static void temac_adjust_link(struct net_device *ndev)
 		}
 
 		/* Write new speed setting out to TEMAC */
-		temac_indirect_out32(lp, XTE_EMCFG_OFFSET, mii_speed);
+		temac_indirect_out32_locked(lp, XTE_EMCFG_OFFSET, mii_speed);
+		spin_unlock_irqrestore(lp->indirect_lock, flags);
+
 		lp->last_link = link_state;
 		phy_print_status(phy);
 	}
-	mutex_unlock(&lp->indirect_mutex);
 }
 
+#ifdef CONFIG_64BIT
+
+static void ptr_to_txbd(void *p, struct cdmac_bd *bd)
+{
+	bd->app3 = (u32)(((u64)p) >> 32);
+	bd->app4 = (u32)((u64)p & 0xFFFFFFFF);
+}
+
+static void *ptr_from_txbd(struct cdmac_bd *bd)
+{
+	return (void *)(((u64)(bd->app3) << 32) | bd->app4);
+}
+
+#else
+
+static void ptr_to_txbd(void *p, struct cdmac_bd *bd)
+{
+	bd->app4 = (u32)p;
+}
+
+static void *ptr_from_txbd(struct cdmac_bd *bd)
+{
+	return (void *)(bd->app4);
+}
+
+#endif
+
 static void temac_start_xmit_done(struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
 	struct cdmac_bd *cur_p;
 	unsigned int stat = 0;
+	struct sk_buff *skb;
 
 	cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
-	stat = cur_p->app0;
+	stat = be32_to_cpu(cur_p->app0);
 
 	while (stat & STS_CTRL_APP0_CMPLT) {
-		dma_unmap_single(ndev->dev.parent, cur_p->phys, cur_p->len,
-				 DMA_TO_DEVICE);
-		if (cur_p->app4)
-			dev_kfree_skb_irq((struct sk_buff *)cur_p->app4);
+		dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys),
+				 be32_to_cpu(cur_p->len), DMA_TO_DEVICE);
+		skb = (struct sk_buff *)ptr_from_txbd(cur_p);
+		if (skb)
+			dev_consume_skb_irq(skb);
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
 		cur_p->app2 = 0;
@@ -638,14 +778,14 @@ static void temac_start_xmit_done(struct net_device *ndev)
 		cur_p->app4 = 0;
 
 		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += cur_p->len;
+		ndev->stats.tx_bytes += be32_to_cpu(cur_p->len);
 
 		lp->tx_bd_ci++;
 		if (lp->tx_bd_ci >= TX_BD_NUM)
 			lp->tx_bd_ci = 0;
 
 		cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
-		stat = cur_p->app0;
+		stat = be32_to_cpu(cur_p->app0);
 	}
 
 	netif_wake_queue(ndev);
@@ -679,7 +819,7 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
 	struct cdmac_bd *cur_p;
-	dma_addr_t start_p, tail_p;
+	dma_addr_t start_p, tail_p, skb_dma_addr;
 	int ii;
 	unsigned long num_frag;
 	skb_frag_t *frag;
@@ -689,7 +829,7 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	start_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
 	cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 
-	if (temac_check_tx_bd_space(lp, num_frag)) {
+	if (temac_check_tx_bd_space(lp, num_frag + 1)) {
 		if (!netif_queue_stopped(ndev))
 			netif_stop_queue(ndev);
 		return NETDEV_TX_BUSY;
@@ -700,16 +840,18 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		unsigned int csum_start_off = skb_checksum_start_offset(skb);
 		unsigned int csum_index_off = csum_start_off + skb->csum_offset;
 
-		cur_p->app0 |= 1; /* TX Checksum Enabled */
-		cur_p->app1 = (csum_start_off << 16) | csum_index_off;
+		cur_p->app0 |= cpu_to_be32(0x000001); /* TX Checksum Enabled */
+		cur_p->app1 = cpu_to_be32((csum_start_off << 16)
+					  | csum_index_off);
 		cur_p->app2 = 0;  /* initial checksum seed */
 	}
 
-	cur_p->app0 |= STS_CTRL_APP0_SOP;
-	cur_p->len = skb_headlen(skb);
-	cur_p->phys = dma_map_single(ndev->dev.parent, skb->data,
-				     skb_headlen(skb), DMA_TO_DEVICE);
-	cur_p->app4 = (unsigned long)skb;
+	cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_SOP);
+	skb_dma_addr = dma_map_single(ndev->dev.parent, skb->data,
+				      skb_headlen(skb), DMA_TO_DEVICE);
+	cur_p->len = cpu_to_be32(skb_headlen(skb));
+	cur_p->phys = cpu_to_be32(skb_dma_addr);
+	ptr_to_txbd((void *)skb, cur_p);
 
 	for (ii = 0; ii < num_frag; ii++) {
 		lp->tx_bd_tail++;
@@ -717,14 +859,16 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 			lp->tx_bd_tail = 0;
 
 		cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
-		cur_p->phys = dma_map_single(ndev->dev.parent,
-					     skb_frag_address(frag),
-					     skb_frag_size(frag), DMA_TO_DEVICE);
-		cur_p->len = skb_frag_size(frag);
+		skb_dma_addr = dma_map_single(ndev->dev.parent,
+					      skb_frag_address(frag),
+					      skb_frag_size(frag),
+					      DMA_TO_DEVICE);
+		cur_p->phys = cpu_to_be32(skb_dma_addr);
+		cur_p->len = cpu_to_be32(skb_frag_size(frag));
 		cur_p->app0 = 0;
 		frag++;
 	}
-	cur_p->app0 |= STS_CTRL_APP0_EOP;
+	cur_p->app0 |= cpu_to_be32(STS_CTRL_APP0_EOP);
 
 	tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
 	lp->tx_bd_tail++;
@@ -734,6 +878,7 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	skb_tx_timestamp(skb);
 
 	/* Kick off the transfer */
+	wmb();
 	lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */
 
 	return NETDEV_TX_OK;
@@ -746,7 +891,7 @@ static void ll_temac_recv(struct net_device *ndev)
 	struct sk_buff *skb, *new_skb;
 	unsigned int bdstat;
 	struct cdmac_bd *cur_p;
-	dma_addr_t tail_p;
+	dma_addr_t tail_p, skb_dma_addr;
 	int length;
 	unsigned long flags;
 
@@ -755,14 +900,14 @@ static void ll_temac_recv(struct net_device *ndev)
 	tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
 	cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
 
-	bdstat = cur_p->app0;
+	bdstat = be32_to_cpu(cur_p->app0);
 	while ((bdstat & STS_CTRL_APP0_CMPLT)) {
 
 		skb = lp->rx_skb[lp->rx_bd_ci];
-		length = cur_p->app4 & 0x3FFF;
+		length = be32_to_cpu(cur_p->app4) & 0x3FFF;
 
-		dma_unmap_single(ndev->dev.parent, cur_p->phys, length,
-				 DMA_FROM_DEVICE);
+		dma_unmap_single(ndev->dev.parent, be32_to_cpu(cur_p->phys),
+				 XTE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE);
 
 		skb_put(skb, length);
 		skb->protocol = eth_type_trans(skb, ndev);
@@ -773,7 +918,12 @@ static void ll_temac_recv(struct net_device *ndev)
 		    (skb->protocol == htons(ETH_P_IP)) &&
 		    (skb->len > 64)) {
 
-			skb->csum = cur_p->app3 & 0xFFFF;
+			/* Convert from device endianness (be32) to cpu
+			 * endiannes, and if necessary swap the bytes
+			 * (back) for proper IP checksum byte order
+			 * (be16).
+			 */
+			skb->csum = htons(be32_to_cpu(cur_p->app3) & 0xFFFF);
 			skb->ip_summed = CHECKSUM_COMPLETE;
 		}
 
@@ -790,11 +940,12 @@ static void ll_temac_recv(struct net_device *ndev)
 			return;
 		}
 
-		cur_p->app0 = STS_CTRL_APP0_IRQONEND;
-		cur_p->phys = dma_map_single(ndev->dev.parent, new_skb->data,
-					     XTE_MAX_JUMBO_FRAME_SIZE,
-					     DMA_FROM_DEVICE);
-		cur_p->len = XTE_MAX_JUMBO_FRAME_SIZE;
+		cur_p->app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
+		skb_dma_addr = dma_map_single(ndev->dev.parent, new_skb->data,
+					      XTE_MAX_JUMBO_FRAME_SIZE,
+					      DMA_FROM_DEVICE);
+		cur_p->phys = cpu_to_be32(skb_dma_addr);
+		cur_p->len = cpu_to_be32(XTE_MAX_JUMBO_FRAME_SIZE);
 		lp->rx_skb[lp->rx_bd_ci] = new_skb;
 
 		lp->rx_bd_ci++;
@@ -802,7 +953,7 @@ static void ll_temac_recv(struct net_device *ndev)
 			lp->rx_bd_ci = 0;
 
 		cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
-		bdstat = cur_p->app0;
+		bdstat = be32_to_cpu(cur_p->app0);
 	}
 	lp->dma_out(lp, RX_TAILDESC_PTR, tail_p);
 
@@ -820,8 +971,10 @@ static irqreturn_t ll_temac_tx_irq(int irq, void *_ndev)
 
 	if (status & (IRQ_COAL | IRQ_DLY))
 		temac_start_xmit_done(lp->ndev);
-	if (status & 0x080)
-		dev_err(&ndev->dev, "DMA error 0x%x\n", status);
+	if (status & (IRQ_ERR | IRQ_DMAERR))
+		dev_err_ratelimited(&ndev->dev,
+				    "TX error 0x%x TX_CHNL_STS=0x%08x\n",
+				    status, lp->dma_in(lp, TX_CHNL_STS));
 
 	return IRQ_HANDLED;
 }
@@ -838,6 +991,10 @@ static irqreturn_t ll_temac_rx_irq(int irq, void *_ndev)
 
 	if (status & (IRQ_COAL | IRQ_DLY))
 		ll_temac_recv(lp->ndev);
+	if (status & (IRQ_ERR | IRQ_DMAERR))
+		dev_err_ratelimited(&ndev->dev,
+				    "RX error 0x%x RX_CHNL_STS=0x%08x\n",
+				    status, lp->dma_in(lp, RX_CHNL_STS));
 
 	return IRQ_HANDLED;
 }
@@ -857,7 +1014,14 @@ static int temac_open(struct net_device *ndev)
 			dev_err(lp->dev, "of_phy_connect() failed\n");
 			return -ENODEV;
 		}
-
+		phy_start(phydev);
+	} else if (strlen(lp->phy_name) > 0) {
+		phydev = phy_connect(lp->ndev, lp->phy_name, temac_adjust_link,
+				     lp->phy_interface);
+		if (IS_ERR(phydev)) {
+			dev_err(lp->dev, "phy_connect() failed\n");
+			return PTR_ERR(phydev);
+		}
 		phy_start(phydev);
 	}
 
@@ -931,6 +1095,7 @@ static const struct net_device_ops temac_netdev_ops = {
 	.ndo_open = temac_open,
 	.ndo_stop = temac_stop,
 	.ndo_start_xmit = temac_start_xmit,
+	.ndo_set_rx_mode = temac_set_multicast_list,
 	.ndo_set_mac_address = temac_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_do_ioctl = temac_ioctl,
@@ -977,23 +1142,25 @@ static const struct ethtool_ops temac_ethtool_ops = {
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
-static int temac_of_probe(struct platform_device *op)
+static int temac_probe(struct platform_device *pdev)
 {
-	struct device_node *np;
+	struct ll_temac_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct device_node *temac_np = dev_of_node(&pdev->dev), *dma_np;
 	struct temac_local *lp;
 	struct net_device *ndev;
+	struct resource *res;
 	const void *addr;
 	__be32 *p;
+	bool little_endian;
 	int rc = 0;
 
 	/* Init network device structure */
-	ndev = alloc_etherdev(sizeof(*lp));
+	ndev = devm_alloc_etherdev(&pdev->dev, sizeof(*lp));
 	if (!ndev)
 		return -ENOMEM;
 
-	platform_set_drvdata(op, ndev);
-	SET_NETDEV_DEV(ndev, &op->dev);
-	ndev->flags &= ~IFF_MULTICAST;  /* clear multicast */
+	platform_set_drvdata(pdev, ndev);
+	SET_NETDEV_DEV(ndev, &pdev->dev);
 	ndev->features = NETIF_F_SG;
 	ndev->netdev_ops = &temac_netdev_ops;
 	ndev->ethtool_ops = &temac_ethtool_ops;
@@ -1014,89 +1181,196 @@ static int temac_of_probe(struct platform_device *op)
 	/* setup temac private info structure */
 	lp = netdev_priv(ndev);
 	lp->ndev = ndev;
-	lp->dev = &op->dev;
+	lp->dev = &pdev->dev;
 	lp->options = XTE_OPTION_DEFAULTS;
 	spin_lock_init(&lp->rx_lock);
-	mutex_init(&lp->indirect_mutex);
+
+	/* Setup mutex for synchronization of indirect register access */
+	if (pdata) {
+		if (!pdata->indirect_lock) {
+			dev_err(&pdev->dev,
+				"indirect_lock missing in platform_data\n");
+			return -EINVAL;
+		}
+		lp->indirect_lock = pdata->indirect_lock;
+	} else {
+		lp->indirect_lock = devm_kmalloc(&pdev->dev,
+						 sizeof(*lp->indirect_lock),
+						 GFP_KERNEL);
+		spin_lock_init(lp->indirect_lock);
+	}
 
 	/* map device registers */
-	lp->regs = of_iomap(op->dev.of_node, 0);
-	if (!lp->regs) {
-		dev_err(&op->dev, "could not map temac regs.\n");
-		rc = -ENOMEM;
-		goto nodev;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	lp->regs = devm_ioremap_nocache(&pdev->dev, res->start,
+					resource_size(res));
+	if (IS_ERR(lp->regs)) {
+		dev_err(&pdev->dev, "could not map TEMAC registers\n");
+		return PTR_ERR(lp->regs);
+	}
+
+	/* Select register access functions with the specified
+	 * endianness mode.  Default for OF devices is big-endian.
+	 */
+	little_endian = false;
+	if (temac_np) {
+		if (of_get_property(temac_np, "little-endian", NULL))
+			little_endian = true;
+	} else if (pdata) {
+		little_endian = pdata->reg_little_endian;
+	}
+	if (little_endian) {
+		lp->temac_ior = _temac_ior_le;
+		lp->temac_iow = _temac_iow_le;
+	} else {
+		lp->temac_ior = _temac_ior_be;
+		lp->temac_iow = _temac_iow_be;
 	}
 
 	/* Setup checksum offload, but default to off if not specified */
 	lp->temac_features = 0;
-	p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,txcsum", NULL);
-	if (p && be32_to_cpu(*p)) {
-		lp->temac_features |= TEMAC_FEATURE_TX_CSUM;
+	if (temac_np) {
+		p = (__be32 *)of_get_property(temac_np, "xlnx,txcsum", NULL);
+		if (p && be32_to_cpu(*p))
+			lp->temac_features |= TEMAC_FEATURE_TX_CSUM;
+		p = (__be32 *)of_get_property(temac_np, "xlnx,rxcsum", NULL);
+		if (p && be32_to_cpu(*p))
+			lp->temac_features |= TEMAC_FEATURE_RX_CSUM;
+	} else if (pdata) {
+		if (pdata->txcsum)
+			lp->temac_features |= TEMAC_FEATURE_TX_CSUM;
+		if (pdata->rxcsum)
+			lp->temac_features |= TEMAC_FEATURE_RX_CSUM;
+	}
+	if (lp->temac_features & TEMAC_FEATURE_TX_CSUM)
 		/* Can checksum TCP/UDP over IPv4. */
 		ndev->features |= NETIF_F_IP_CSUM;
-	}
-	p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,rxcsum", NULL);
-	if (p && be32_to_cpu(*p))
-		lp->temac_features |= TEMAC_FEATURE_RX_CSUM;
-
-	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
-	np = of_parse_phandle(op->dev.of_node, "llink-connected", 0);
-	if (!np) {
-		dev_err(&op->dev, "could not find DMA node\n");
-		rc = -ENODEV;
-		goto err_iounmap;
-	}
 
-	/* Setup the DMA register accesses, could be DCR or memory mapped */
-	if (temac_dcr_setup(lp, op, np)) {
+	/* Setup LocalLink DMA */
+	if (temac_np) {
+		/* Find the DMA node, map the DMA registers, and
+		 * decode the DMA IRQs.
+		 */
+		dma_np = of_parse_phandle(temac_np, "llink-connected", 0);
+		if (!dma_np) {
+			dev_err(&pdev->dev, "could not find DMA node\n");
+			return -ENODEV;
+		}
 
-		/* no DCR in the device tree, try non-DCR */
-		lp->sdma_regs = of_iomap(np, 0);
-		if (lp->sdma_regs) {
-			lp->dma_in = temac_dma_in32;
-			lp->dma_out = temac_dma_out32;
-			dev_dbg(&op->dev, "MEM base: %p\n", lp->sdma_regs);
-		} else {
-			dev_err(&op->dev, "unable to map DMA registers\n");
-			of_node_put(np);
-			goto err_iounmap;
+		/* Setup the DMA register accesses, could be DCR or
+		 * memory mapped.
+		 */
+		if (temac_dcr_setup(lp, pdev, dma_np)) {
+			/* no DCR in the device tree, try non-DCR */
+			lp->sdma_regs = devm_of_iomap(&pdev->dev, dma_np, 0,
+						      NULL);
+			if (IS_ERR(lp->sdma_regs)) {
+				dev_err(&pdev->dev,
+					"unable to map DMA registers\n");
+				of_node_put(dma_np);
+				return PTR_ERR(lp->sdma_regs);
+			}
+			if (of_get_property(dma_np, "little-endian", NULL)) {
+				lp->dma_in = temac_dma_in32_le;
+				lp->dma_out = temac_dma_out32_le;
+			} else {
+				lp->dma_in = temac_dma_in32_be;
+				lp->dma_out = temac_dma_out32_be;
+			}
+			dev_dbg(&pdev->dev, "MEM base: %p\n", lp->sdma_regs);
 		}
-	}
 
-	lp->rx_irq = irq_of_parse_and_map(np, 0);
-	lp->tx_irq = irq_of_parse_and_map(np, 1);
+		/* Get DMA RX and TX interrupts */
+		lp->rx_irq = irq_of_parse_and_map(dma_np, 0);
+		lp->tx_irq = irq_of_parse_and_map(dma_np, 1);
 
-	of_node_put(np); /* Finished with the DMA node; drop the reference */
+		/* Use defaults for IRQ delay/coalescing setup.  These
+		 * are configuration values, so does not belong in
+		 * device-tree.
+		 */
+		lp->tx_chnl_ctrl = 0x10220000;
+		lp->rx_chnl_ctrl = 0xff070000;
+
+		/* Finished with the DMA node; drop the reference */
+		of_node_put(dma_np);
+	} else if (pdata) {
+		/* 2nd memory resource specifies DMA registers */
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		lp->sdma_regs = devm_ioremap_nocache(&pdev->dev, res->start,
+						     resource_size(res));
+		if (IS_ERR(lp->sdma_regs)) {
+			dev_err(&pdev->dev,
+				"could not map DMA registers\n");
+			return PTR_ERR(lp->sdma_regs);
+		}
+		if (pdata->dma_little_endian) {
+			lp->dma_in = temac_dma_in32_le;
+			lp->dma_out = temac_dma_out32_le;
+		} else {
+			lp->dma_in = temac_dma_in32_be;
+			lp->dma_out = temac_dma_out32_be;
+		}
 
-	if (!lp->rx_irq || !lp->tx_irq) {
-		dev_err(&op->dev, "could not determine irqs\n");
-		rc = -ENOMEM;
-		goto err_iounmap_2;
+		/* Get DMA RX and TX interrupts */
+		lp->rx_irq = platform_get_irq(pdev, 0);
+		lp->tx_irq = platform_get_irq(pdev, 1);
+
+		/* IRQ delay/coalescing setup */
+		if (pdata->tx_irq_timeout || pdata->tx_irq_count)
+			lp->tx_chnl_ctrl = (pdata->tx_irq_timeout << 24) |
+				(pdata->tx_irq_count << 16);
+		else
+			lp->tx_chnl_ctrl = 0x10220000;
+		if (pdata->rx_irq_timeout || pdata->rx_irq_count)
+			lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) |
+				(pdata->rx_irq_count << 16);
+		else
+			lp->rx_chnl_ctrl = 0xff070000;
 	}
 
+	/* Error handle returned DMA RX and TX interrupts */
+	if (lp->rx_irq < 0) {
+		if (lp->rx_irq != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "could not get DMA RX irq\n");
+		return lp->rx_irq;
+	}
+	if (lp->tx_irq < 0) {
+		if (lp->tx_irq != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "could not get DMA TX irq\n");
+		return lp->tx_irq;
+	}
 
-	/* Retrieve the MAC address */
-	addr = of_get_mac_address(op->dev.of_node);
-	if (!addr) {
-		dev_err(&op->dev, "could not find MAC address\n");
-		rc = -ENODEV;
-		goto err_iounmap_2;
+	if (temac_np) {
+		/* Retrieve the MAC address */
+		addr = of_get_mac_address(temac_np);
+		if (IS_ERR(addr)) {
+			dev_err(&pdev->dev, "could not find MAC address\n");
+			return -ENODEV;
+		}
+		temac_init_mac_address(ndev, addr);
+	} else if (pdata) {
+		temac_init_mac_address(ndev, pdata->mac_addr);
 	}
-	temac_init_mac_address(ndev, addr);
 
-	rc = temac_mdio_setup(lp, op->dev.of_node);
+	rc = temac_mdio_setup(lp, pdev);
 	if (rc)
-		dev_warn(&op->dev, "error registering MDIO bus\n");
-
-	lp->phy_node = of_parse_phandle(op->dev.of_node, "phy-handle", 0);
-	if (lp->phy_node)
-		dev_dbg(lp->dev, "using PHY node %pOF (%p)\n", np, np);
+		dev_warn(&pdev->dev, "error registering MDIO bus\n");
+
+	if (temac_np) {
+		lp->phy_node = of_parse_phandle(temac_np, "phy-handle", 0);
+		if (lp->phy_node)
+			dev_dbg(lp->dev, "using PHY node %pOF\n", temac_np);
+	} else if (pdata) {
+		snprintf(lp->phy_name, sizeof(lp->phy_name),
+			 PHY_ID_FMT, lp->mii_bus->id, pdata->phy_addr);
+		lp->phy_interface = pdata->phy_interface;
+	}
 
 	/* Add the device attributes */
 	rc = sysfs_create_group(&lp->dev->kobj, &temac_attr_group);
 	if (rc) {
 		dev_err(lp->dev, "Error creating sysfs files\n");
-		goto err_iounmap_2;
+		goto err_sysfs_create;
 	}
 
 	rc = register_netdev(lp->ndev);
@@ -1107,33 +1381,25 @@ static int temac_of_probe(struct platform_device *op)
 
 	return 0;
 
- err_register_ndev:
+err_register_ndev:
 	sysfs_remove_group(&lp->dev->kobj, &temac_attr_group);
- err_iounmap_2:
-	if (lp->sdma_regs)
-		iounmap(lp->sdma_regs);
- err_iounmap:
-	iounmap(lp->regs);
- nodev:
-	free_netdev(ndev);
-	ndev = NULL;
+err_sysfs_create:
+	if (lp->phy_node)
+		of_node_put(lp->phy_node);
+	temac_mdio_teardown(lp);
 	return rc;
 }
 
-static int temac_of_remove(struct platform_device *op)
+static int temac_remove(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(op);
+	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct temac_local *lp = netdev_priv(ndev);
 
-	temac_mdio_teardown(lp);
 	unregister_netdev(ndev);
 	sysfs_remove_group(&lp->dev->kobj, &temac_attr_group);
-	of_node_put(lp->phy_node);
-	lp->phy_node = NULL;
-	iounmap(lp->regs);
-	if (lp->sdma_regs)
-		iounmap(lp->sdma_regs);
-	free_netdev(ndev);
+	if (lp->phy_node)
+		of_node_put(lp->phy_node);
+	temac_mdio_teardown(lp);
 	return 0;
 }
 
@@ -1146,16 +1412,16 @@ static const struct of_device_id temac_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, temac_of_match);
 
-static struct platform_driver temac_of_driver = {
-	.probe = temac_of_probe,
-	.remove = temac_of_remove,
+static struct platform_driver temac_driver = {
+	.probe = temac_probe,
+	.remove = temac_remove,
 	.driver = {
 		.name = "xilinx_temac",
 		.of_match_table = temac_of_match,
 	},
 };
 
-module_platform_driver(temac_of_driver);
+module_platform_driver(temac_driver);
 
 MODULE_DESCRIPTION("Xilinx LL_TEMAC Ethernet driver");
 MODULE_AUTHOR("Yoshio Kashiwagi");
diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
index f5e83ac6f7e2..6fd2dea4e60f 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
@@ -14,6 +14,7 @@
 #include <linux/of_address.h>
 #include <linux/slab.h>
 #include <linux/of_mdio.h>
+#include <linux/platform_data/xilinx-ll-temac.h>
 
 #include "ll_temac.h"
 
@@ -24,14 +25,15 @@ static int temac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 {
 	struct temac_local *lp = bus->priv;
 	u32 rc;
+	unsigned long flags;
 
 	/* Write the PHY address to the MIIM Access Initiator register.
 	 * When the transfer completes, the PHY register value will appear
 	 * in the LSW0 register */
-	mutex_lock(&lp->indirect_mutex);
+	spin_lock_irqsave(lp->indirect_lock, flags);
 	temac_iow(lp, XTE_LSW0_OFFSET, (phy_id << 5) | reg);
-	rc = temac_indirect_in32(lp, XTE_MIIMAI_OFFSET);
-	mutex_unlock(&lp->indirect_mutex);
+	rc = temac_indirect_in32_locked(lp, XTE_MIIMAI_OFFSET);
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
 
 	dev_dbg(lp->dev, "temac_mdio_read(phy_id=%i, reg=%x) == %x\n",
 		phy_id, reg, rc);
@@ -42,6 +44,7 @@ static int temac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
 {
 	struct temac_local *lp = bus->priv;
+	unsigned long flags;
 
 	dev_dbg(lp->dev, "temac_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
 		phy_id, reg, val);
@@ -49,25 +52,34 @@ static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
 	/* First write the desired value into the write data register
 	 * and then write the address into the access initiator register
 	 */
-	mutex_lock(&lp->indirect_mutex);
-	temac_indirect_out32(lp, XTE_MGTDR_OFFSET, val);
-	temac_indirect_out32(lp, XTE_MIIMAI_OFFSET, (phy_id << 5) | reg);
-	mutex_unlock(&lp->indirect_mutex);
+	spin_lock_irqsave(lp->indirect_lock, flags);
+	temac_indirect_out32_locked(lp, XTE_MGTDR_OFFSET, val);
+	temac_indirect_out32_locked(lp, XTE_MIIMAI_OFFSET, (phy_id << 5) | reg);
+	spin_unlock_irqrestore(lp->indirect_lock, flags);
 
 	return 0;
 }
 
-int temac_mdio_setup(struct temac_local *lp, struct device_node *np)
+int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev)
 {
+	struct ll_temac_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct device_node *np = dev_of_node(&pdev->dev);
 	struct mii_bus *bus;
 	u32 bus_hz;
 	int clk_div;
 	int rc;
 	struct resource res;
 
+	/* Get MDIO bus frequency (if specified) */
+	bus_hz = 0;
+	if (np)
+		of_property_read_u32(np, "clock-frequency", &bus_hz);
+	else if (pdata)
+		bus_hz = pdata->mdio_clk_freq;
+
 	/* Calculate a reasonable divisor for the clock rate */
 	clk_div = 0x3f; /* worst-case default setting */
-	if (of_property_read_u32(np, "clock-frequency", &bus_hz) == 0) {
+	if (bus_hz != 0) {
 		clk_div = bus_hz / (2500 * 1000 * 2) - 1;
 		if (clk_div < 1)
 			clk_div = 1;
@@ -77,17 +89,21 @@ int temac_mdio_setup(struct temac_local *lp, struct device_node *np)
 
 	/* Enable the MDIO bus by asserting the enable bit and writing
 	 * in the clock config */
-	mutex_lock(&lp->indirect_mutex);
 	temac_indirect_out32(lp, XTE_MC_OFFSET, 1 << 6 | clk_div);
-	mutex_unlock(&lp->indirect_mutex);
 
-	bus = mdiobus_alloc();
+	bus = devm_mdiobus_alloc(&pdev->dev);
 	if (!bus)
 		return -ENOMEM;
 
-	of_address_to_resource(np, 0, &res);
-	snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx",
-		 (unsigned long long)res.start);
+	if (np) {
+		of_address_to_resource(np, 0, &res);
+		snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx",
+			 (unsigned long long)res.start);
+	} else if (pdata) {
+		snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx",
+			 pdata->mdio_bus_id);
+	}
+
 	bus->priv = lp;
 	bus->name = "Xilinx TEMAC MDIO";
 	bus->read = temac_mdio_read;
@@ -98,23 +114,14 @@ int temac_mdio_setup(struct temac_local *lp, struct device_node *np)
 
 	rc = of_mdiobus_register(bus, np);
 	if (rc)
-		goto err_register;
+		return rc;
 
-	mutex_lock(&lp->indirect_mutex);
 	dev_dbg(lp->dev, "MDIO bus registered;  MC:%x\n",
 		temac_indirect_in32(lp, XTE_MC_OFFSET));
-	mutex_unlock(&lp->indirect_mutex);
 	return 0;
-
- err_register:
-	mdiobus_free(bus);
-	return rc;
 }
 
 void temac_mdio_teardown(struct temac_local *lp)
 {
 	mdiobus_unregister(lp->mii_bus);
-	mdiobus_free(lp->mii_bus);
-	lp->mii_bus = NULL;
 }
-
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index c337400485da..2dacfc85b3ba 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -13,6 +13,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/if_vlan.h>
+#include <linux/phylink.h>
 
 /* Packet size info */
 #define XAE_HDR_SIZE			14 /* Size of Ethernet header */
@@ -83,6 +84,8 @@
 #define XAXIDMA_CR_RUNSTOP_MASK	0x00000001 /* Start/stop DMA channel */
 #define XAXIDMA_CR_RESET_MASK	0x00000004 /* Reset DMA engine */
 
+#define XAXIDMA_SR_HALT_MASK	0x00000001 /* Indicates DMA channel halted */
+
 #define XAXIDMA_BD_NDESC_OFFSET		0x00 /* Next descriptor pointer */
 #define XAXIDMA_BD_BUFA_OFFSET		0x08 /* Buffer address */
 #define XAXIDMA_BD_CTRL_LEN_OFFSET	0x18 /* Control/buffer length */
@@ -356,9 +359,6 @@
  * @app2:         MM2S/S2MM User Application Field 2.
  * @app3:         MM2S/S2MM User Application Field 3.
  * @app4:         MM2S/S2MM User Application Field 4.
- * @sw_id_offset: MM2S/S2MM Sw ID
- * @reserved5:    Reserved and not used
- * @reserved6:    Reserved and not used
  */
 struct axidma_bd {
 	u32 next;	/* Physical address of next buffer descriptor */
@@ -373,11 +373,9 @@ struct axidma_bd {
 	u32 app1;	/* TX start << 16 | insert */
 	u32 app2;	/* TX csum seed */
 	u32 app3;
-	u32 app4;
-	u32 sw_id_offset;
-	u32 reserved5;
-	u32 reserved6;
-};
+	u32 app4;   /* Last field used by HW */
+	struct sk_buff *skb;
+} __aligned(XAXIDMA_BD_MINIMUM_ALIGNMENT);
 
 /**
  * struct axienet_local - axienet private per device data
@@ -385,6 +383,7 @@ struct axidma_bd {
  * @dev:	Pointer to device structure
  * @phy_node:	Pointer to device node structure
  * @mii_bus:	Pointer to MII bus structure
+ * @regs_start: Resource start for axienet device addresses
  * @regs:	Base address for the axienet_local device address space
  * @dma_regs:	Base address for the axidma device address space
  * @dma_err_tasklet: Tasklet structure to process Axi DMA errors
@@ -422,10 +421,17 @@ struct axienet_local {
 	/* Connection to PHY device */
 	struct device_node *phy_node;
 
+	struct phylink *phylink;
+	struct phylink_config phylink_config;
+
+	/* Clock for AXI bus */
+	struct clk *clk;
+
 	/* MDIO bus data */
 	struct mii_bus *mii_bus;	/* MII bus reference */
 
 	/* IO registers, dma functions and IRQs */
+	resource_size_t regs_start;
 	void __iomem *regs;
 	void __iomem *dma_regs;
 
@@ -433,17 +439,19 @@ struct axienet_local {
 
 	int tx_irq;
 	int rx_irq;
+	int eth_irq;
 	phy_interface_t phy_mode;
 
 	u32 options;			/* Current options word */
-	u32 last_link;
 	u32 features;
 
 	/* Buffer descriptors */
 	struct axidma_bd *tx_bd_v;
 	dma_addr_t tx_bd_p;
+	u32 tx_bd_num;
 	struct axidma_bd *rx_bd_v;
 	dma_addr_t rx_bd_p;
+	u32 rx_bd_num;
 	u32 tx_bd_ci;
 	u32 tx_bd_tail;
 	u32 rx_bd_ci;
@@ -481,7 +489,12 @@ struct axienet_option {
  */
 static inline u32 axienet_ior(struct axienet_local *lp, off_t offset)
 {
-	return in_be32(lp->regs + offset);
+	return ioread32(lp->regs + offset);
+}
+
+static inline u32 axinet_ior_read_mcr(struct axienet_local *lp)
+{
+	return axienet_ior(lp, XAE_MDIO_MCR_OFFSET);
 }
 
 /**
@@ -496,12 +509,13 @@ static inline u32 axienet_ior(struct axienet_local *lp, off_t offset)
 static inline void axienet_iow(struct axienet_local *lp, off_t offset,
 			       u32 value)
 {
-	out_be32((lp->regs + offset), value);
+	iowrite32(value, lp->regs + offset);
 }
 
 /* Function prototypes visible in xilinx_axienet_mdio.c for other files */
-int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np);
-int axienet_mdio_wait_until_ready(struct axienet_local *lp);
+int axienet_mdio_enable(struct axienet_local *lp);
+void axienet_mdio_disable(struct axienet_local *lp);
+int axienet_mdio_setup(struct axienet_local *lp);
 void axienet_mdio_teardown(struct axienet_local *lp);
 
 #endif /* XILINX_AXI_ENET_H */
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 0789d8af7d72..4fc627fb4d11 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Xilinx Axi Ethernet device driver
  *
@@ -6,6 +7,7 @@
  * Copyright (c) 2008-2009 Secret Lab Technologies Ltd.
  * Copyright (c) 2010 - 2011 Michal Simek <monstr@monstr.eu>
  * Copyright (c) 2010 - 2011 PetaLogix
+ * Copyright (c) 2019 SED Systems, a division of Calian Ltd.
  * Copyright (c) 2010 - 2012 Xilinx, Inc. All rights reserved.
  *
  * This is a driver for the Xilinx Axi Ethernet which is used in the Virtex6
@@ -20,6 +22,7 @@
  *  - Add support for extended VLAN support.
  */
 
+#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/etherdevice.h>
 #include <linux/module.h>
@@ -37,16 +40,18 @@
 
 #include "xilinx_axienet.h"
 
-/* Descriptors defines for Tx and Rx DMA - 2^n for the best performance */
-#define TX_BD_NUM		64
-#define RX_BD_NUM		128
+/* Descriptors defines for Tx and Rx DMA */
+#define TX_BD_NUM_DEFAULT		64
+#define RX_BD_NUM_DEFAULT		1024
+#define TX_BD_NUM_MAX			4096
+#define RX_BD_NUM_MAX			4096
 
 /* Must be shorter than length of ethtool_drvinfo.driver field to fit */
 #define DRIVER_NAME		"xaxienet"
 #define DRIVER_DESCRIPTION	"Xilinx Axi Ethernet driver"
 #define DRIVER_VERSION		"1.00a"
 
-#define AXIENET_REGS_N		32
+#define AXIENET_REGS_N		40
 
 /* Match table for of_platform binding */
 static const struct of_device_id axienet_of_match[] = {
@@ -124,7 +129,7 @@ static struct axienet_option axienet_options[] = {
  */
 static inline u32 axienet_dma_in32(struct axienet_local *lp, off_t reg)
 {
-	return in_be32(lp->dma_regs + reg);
+	return ioread32(lp->dma_regs + reg);
 }
 
 /**
@@ -139,7 +144,7 @@ static inline u32 axienet_dma_in32(struct axienet_local *lp, off_t reg)
 static inline void axienet_dma_out32(struct axienet_local *lp,
 				     off_t reg, u32 value)
 {
-	out_be32((lp->dma_regs + reg), value);
+	iowrite32(value, lp->dma_regs + reg);
 }
 
 /**
@@ -155,22 +160,21 @@ static void axienet_dma_bd_release(struct net_device *ndev)
 	int i;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	for (i = 0; i < RX_BD_NUM; i++) {
+	for (i = 0; i < lp->rx_bd_num; i++) {
 		dma_unmap_single(ndev->dev.parent, lp->rx_bd_v[i].phys,
 				 lp->max_frm_size, DMA_FROM_DEVICE);
-		dev_kfree_skb((struct sk_buff *)
-			      (lp->rx_bd_v[i].sw_id_offset));
+		dev_kfree_skb(lp->rx_bd_v[i].skb);
 	}
 
 	if (lp->rx_bd_v) {
 		dma_free_coherent(ndev->dev.parent,
-				  sizeof(*lp->rx_bd_v) * RX_BD_NUM,
+				  sizeof(*lp->rx_bd_v) * lp->rx_bd_num,
 				  lp->rx_bd_v,
 				  lp->rx_bd_p);
 	}
 	if (lp->tx_bd_v) {
 		dma_free_coherent(ndev->dev.parent,
-				  sizeof(*lp->tx_bd_v) * TX_BD_NUM,
+				  sizeof(*lp->tx_bd_v) * lp->tx_bd_num,
 				  lp->tx_bd_v,
 				  lp->tx_bd_p);
 	}
@@ -200,33 +204,33 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 
 	/* Allocate the Tx and Rx buffer descriptors. */
 	lp->tx_bd_v = dma_alloc_coherent(ndev->dev.parent,
-					 sizeof(*lp->tx_bd_v) * TX_BD_NUM,
+					 sizeof(*lp->tx_bd_v) * lp->tx_bd_num,
 					 &lp->tx_bd_p, GFP_KERNEL);
 	if (!lp->tx_bd_v)
 		goto out;
 
 	lp->rx_bd_v = dma_alloc_coherent(ndev->dev.parent,
-					 sizeof(*lp->rx_bd_v) * RX_BD_NUM,
+					 sizeof(*lp->rx_bd_v) * lp->rx_bd_num,
 					 &lp->rx_bd_p, GFP_KERNEL);
 	if (!lp->rx_bd_v)
 		goto out;
 
-	for (i = 0; i < TX_BD_NUM; i++) {
+	for (i = 0; i < lp->tx_bd_num; i++) {
 		lp->tx_bd_v[i].next = lp->tx_bd_p +
 				      sizeof(*lp->tx_bd_v) *
-				      ((i + 1) % TX_BD_NUM);
+				      ((i + 1) % lp->tx_bd_num);
 	}
 
-	for (i = 0; i < RX_BD_NUM; i++) {
+	for (i = 0; i < lp->rx_bd_num; i++) {
 		lp->rx_bd_v[i].next = lp->rx_bd_p +
 				      sizeof(*lp->rx_bd_v) *
-				      ((i + 1) % RX_BD_NUM);
+				      ((i + 1) % lp->rx_bd_num);
 
 		skb = netdev_alloc_skb_ip_align(ndev, lp->max_frm_size);
 		if (!skb)
 			goto out;
 
-		lp->rx_bd_v[i].sw_id_offset = (u32) skb;
+		lp->rx_bd_v[i].skb = skb;
 		lp->rx_bd_v[i].phys = dma_map_single(ndev->dev.parent,
 						     skb->data,
 						     lp->max_frm_size,
@@ -268,7 +272,7 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
 			  cr | XAXIDMA_CR_RUNSTOP_MASK);
 	axienet_dma_out32(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
-			  (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
+			  (sizeof(*lp->rx_bd_v) * (lp->rx_bd_num - 1)));
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
@@ -433,17 +437,20 @@ static void axienet_setoptions(struct net_device *ndev, u32 options)
 	lp->options |= options;
 }
 
-static void __axienet_device_reset(struct axienet_local *lp, off_t offset)
+static void __axienet_device_reset(struct axienet_local *lp)
 {
 	u32 timeout;
 	/* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset
 	 * process of Axi DMA takes a while to complete as all pending
 	 * commands/transfers will be flushed or completed during this
 	 * reset process.
+	 * Note that even though both TX and RX have their own reset register,
+	 * they both reset the entire DMA core, so only one needs to be used.
 	 */
-	axienet_dma_out32(lp, offset, XAXIDMA_CR_RESET_MASK);
+	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, XAXIDMA_CR_RESET_MASK);
 	timeout = DELAY_OF_ONE_MILLISEC;
-	while (axienet_dma_in32(lp, offset) & XAXIDMA_CR_RESET_MASK) {
+	while (axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET) &
+				XAXIDMA_CR_RESET_MASK) {
 		udelay(1);
 		if (--timeout == 0) {
 			netdev_err(lp->ndev, "%s: DMA reset timeout!\n",
@@ -469,8 +476,7 @@ static void axienet_device_reset(struct net_device *ndev)
 	u32 axienet_status;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	__axienet_device_reset(lp, XAXIDMA_TX_CR_OFFSET);
-	__axienet_device_reset(lp, XAXIDMA_RX_CR_OFFSET);
+	__axienet_device_reset(lp);
 
 	lp->max_frm_size = XAE_MAX_VLAN_FRAME_SIZE;
 	lp->options |= XAE_OPTION_VLAN;
@@ -497,6 +503,8 @@ static void axienet_device_reset(struct net_device *ndev)
 	axienet_status = axienet_ior(lp, XAE_IP_OFFSET);
 	if (axienet_status & XAE_INT_RXRJECT_MASK)
 		axienet_iow(lp, XAE_IS_OFFSET, XAE_INT_RXRJECT_MASK);
+	axienet_iow(lp, XAE_IE_OFFSET, lp->eth_irq > 0 ?
+		    XAE_INT_RECV_ERROR_MASK : 0);
 
 	axienet_iow(lp, XAE_FCC_OFFSET, XAE_FCC_FCRX_MASK);
 
@@ -513,63 +521,6 @@ static void axienet_device_reset(struct net_device *ndev)
 }
 
 /**
- * axienet_adjust_link - Adjust the PHY link speed/duplex.
- * @ndev:	Pointer to the net_device structure
- *
- * This function is called to change the speed and duplex setting after
- * auto negotiation is done by the PHY. This is the function that gets
- * registered with the PHY interface through the "of_phy_connect" call.
- */
-static void axienet_adjust_link(struct net_device *ndev)
-{
-	u32 emmc_reg;
-	u32 link_state;
-	u32 setspeed = 1;
-	struct axienet_local *lp = netdev_priv(ndev);
-	struct phy_device *phy = ndev->phydev;
-
-	link_state = phy->speed | (phy->duplex << 1) | phy->link;
-	if (lp->last_link != link_state) {
-		if ((phy->speed == SPEED_10) || (phy->speed == SPEED_100)) {
-			if (lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX)
-				setspeed = 0;
-		} else {
-			if ((phy->speed == SPEED_1000) &&
-			    (lp->phy_mode == PHY_INTERFACE_MODE_MII))
-				setspeed = 0;
-		}
-
-		if (setspeed == 1) {
-			emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET);
-			emmc_reg &= ~XAE_EMMC_LINKSPEED_MASK;
-
-			switch (phy->speed) {
-			case SPEED_1000:
-				emmc_reg |= XAE_EMMC_LINKSPD_1000;
-				break;
-			case SPEED_100:
-				emmc_reg |= XAE_EMMC_LINKSPD_100;
-				break;
-			case SPEED_10:
-				emmc_reg |= XAE_EMMC_LINKSPD_10;
-				break;
-			default:
-				dev_err(&ndev->dev, "Speed other than 10, 100 "
-					"or 1Gbps is not supported\n");
-				break;
-			}
-
-			axienet_iow(lp, XAE_EMMC_OFFSET, emmc_reg);
-			lp->last_link = link_state;
-			phy_print_status(phy);
-		} else {
-			netdev_err(ndev,
-				   "Error setting Axi Ethernet mac speed\n");
-		}
-	}
-}
-
-/**
  * axienet_start_xmit_done - Invoked once a transmit is completed by the
  * Axi DMA Tx channel.
  * @ndev:	Pointer to the net_device structure
@@ -594,26 +545,31 @@ static void axienet_start_xmit_done(struct net_device *ndev)
 		dma_unmap_single(ndev->dev.parent, cur_p->phys,
 				(cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
 				DMA_TO_DEVICE);
-		if (cur_p->app4)
-			dev_kfree_skb_irq((struct sk_buff *)cur_p->app4);
+		if (cur_p->skb)
+			dev_consume_skb_irq(cur_p->skb);
 		/*cur_p->phys = 0;*/
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
 		cur_p->app2 = 0;
 		cur_p->app4 = 0;
 		cur_p->status = 0;
+		cur_p->skb = NULL;
 
 		size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 		packets++;
 
-		++lp->tx_bd_ci;
-		lp->tx_bd_ci %= TX_BD_NUM;
+		if (++lp->tx_bd_ci >= lp->tx_bd_num)
+			lp->tx_bd_ci = 0;
 		cur_p = &lp->tx_bd_v[lp->tx_bd_ci];
 		status = cur_p->status;
 	}
 
 	ndev->stats.tx_packets += packets;
 	ndev->stats.tx_bytes += size;
+
+	/* Matches barrier in axienet_start_xmit */
+	smp_mb();
+
 	netif_wake_queue(ndev);
 }
 
@@ -634,7 +590,7 @@ static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
 					    int num_frag)
 {
 	struct axidma_bd *cur_p;
-	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % TX_BD_NUM];
+	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % lp->tx_bd_num];
 	if (cur_p->status & XAXIDMA_BD_STS_ALL_MASK)
 		return NETDEV_TX_BUSY;
 	return 0;
@@ -669,9 +625,19 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 
 	if (axienet_check_tx_bd_space(lp, num_frag)) {
-		if (!netif_queue_stopped(ndev))
-			netif_stop_queue(ndev);
-		return NETDEV_TX_BUSY;
+		if (netif_queue_stopped(ndev))
+			return NETDEV_TX_BUSY;
+
+		netif_stop_queue(ndev);
+
+		/* Matches barrier in axienet_start_xmit_done */
+		smp_mb();
+
+		/* Space might have just been freed - check again */
+		if (axienet_check_tx_bd_space(lp, num_frag))
+			return NETDEV_TX_BUSY;
+
+		netif_wake_queue(ndev);
 	}
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -694,8 +660,8 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 				     skb_headlen(skb), DMA_TO_DEVICE);
 
 	for (ii = 0; ii < num_frag; ii++) {
-		++lp->tx_bd_tail;
-		lp->tx_bd_tail %= TX_BD_NUM;
+		if (++lp->tx_bd_tail >= lp->tx_bd_num)
+			lp->tx_bd_tail = 0;
 		cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 		frag = &skb_shinfo(skb)->frags[ii];
 		cur_p->phys = dma_map_single(ndev->dev.parent,
@@ -706,13 +672,13 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	}
 
 	cur_p->cntrl |= XAXIDMA_BD_CTRL_TXEOF_MASK;
-	cur_p->app4 = (unsigned long)skb;
+	cur_p->skb = skb;
 
 	tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail;
 	/* Start the transfer */
 	axienet_dma_out32(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
-	++lp->tx_bd_tail;
-	lp->tx_bd_tail %= TX_BD_NUM;
+	if (++lp->tx_bd_tail >= lp->tx_bd_num)
+		lp->tx_bd_tail = 0;
 
 	return NETDEV_TX_OK;
 }
@@ -741,13 +707,15 @@ static void axienet_recv(struct net_device *ndev)
 
 	while ((cur_p->status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
 		tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
-		skb = (struct sk_buff *) (cur_p->sw_id_offset);
-		length = cur_p->app4 & 0x0000FFFF;
 
 		dma_unmap_single(ndev->dev.parent, cur_p->phys,
 				 lp->max_frm_size,
 				 DMA_FROM_DEVICE);
 
+		skb = cur_p->skb;
+		cur_p->skb = NULL;
+		length = cur_p->app4 & 0x0000FFFF;
+
 		skb_put(skb, length);
 		skb->protocol = eth_type_trans(skb, ndev);
 		/*skb_checksum_none_assert(skb);*/
@@ -782,10 +750,10 @@ static void axienet_recv(struct net_device *ndev)
 					     DMA_FROM_DEVICE);
 		cur_p->cntrl = lp->max_frm_size;
 		cur_p->status = 0;
-		cur_p->sw_id_offset = (u32) new_skb;
+		cur_p->skb = new_skb;
 
-		++lp->rx_bd_ci;
-		lp->rx_bd_ci %= RX_BD_NUM;
+		if (++lp->rx_bd_ci >= lp->rx_bd_num)
+			lp->rx_bd_ci = 0;
 		cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
 	}
 
@@ -801,7 +769,7 @@ static void axienet_recv(struct net_device *ndev)
  * @irq:	irq number
  * @_ndev:	net_device pointer
  *
- * Return: IRQ_HANDLED for all cases.
+ * Return: IRQ_HANDLED if device generated a TX interrupt, IRQ_NONE otherwise.
  *
  * This is the Axi DMA Tx done Isr. It invokes "axienet_start_xmit_done"
  * to complete the BD processing.
@@ -820,7 +788,7 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
 		goto out;
 	}
 	if (!(status & XAXIDMA_IRQ_ALL_MASK))
-		dev_err(&ndev->dev, "No interrupts asserted in Tx path\n");
+		return IRQ_NONE;
 	if (status & XAXIDMA_IRQ_ERROR_MASK) {
 		dev_err(&ndev->dev, "DMA Tx error 0x%x\n", status);
 		dev_err(&ndev->dev, "Current BD is at: 0x%x\n",
@@ -850,7 +818,7 @@ out:
  * @irq:	irq number
  * @_ndev:	net_device pointer
  *
- * Return: IRQ_HANDLED for all cases.
+ * Return: IRQ_HANDLED if device generated a RX interrupt, IRQ_NONE otherwise.
  *
  * This is the Axi DMA Rx Isr. It invokes "axienet_recv" to complete the BD
  * processing.
@@ -869,7 +837,7 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 		goto out;
 	}
 	if (!(status & XAXIDMA_IRQ_ALL_MASK))
-		dev_err(&ndev->dev, "No interrupts asserted in Rx path\n");
+		return IRQ_NONE;
 	if (status & XAXIDMA_IRQ_ERROR_MASK) {
 		dev_err(&ndev->dev, "DMA Rx error 0x%x\n", status);
 		dev_err(&ndev->dev, "Current BD is at: 0x%x\n",
@@ -894,6 +862,35 @@ out:
 	return IRQ_HANDLED;
 }
 
+/**
+ * axienet_eth_irq - Ethernet core Isr.
+ * @irq:	irq number
+ * @_ndev:	net_device pointer
+ *
+ * Return: IRQ_HANDLED if device generated a core interrupt, IRQ_NONE otherwise.
+ *
+ * Handle miscellaneous conditions indicated by Ethernet core IRQ.
+ */
+static irqreturn_t axienet_eth_irq(int irq, void *_ndev)
+{
+	struct net_device *ndev = _ndev;
+	struct axienet_local *lp = netdev_priv(ndev);
+	unsigned int pending;
+
+	pending = axienet_ior(lp, XAE_IP_OFFSET);
+	if (!pending)
+		return IRQ_NONE;
+
+	if (pending & XAE_INT_RXFIFOOVR_MASK)
+		ndev->stats.rx_missed_errors++;
+
+	if (pending & XAE_INT_RXRJECT_MASK)
+		ndev->stats.rx_frame_errors++;
+
+	axienet_iow(lp, XAE_IS_OFFSET, pending);
+	return IRQ_HANDLED;
+}
+
 static void axienet_dma_err_handler(unsigned long data);
 
 /**
@@ -903,67 +900,72 @@ static void axienet_dma_err_handler(unsigned long data);
  * Return: 0, on success.
  *	    non-zero error value on failure
  *
- * This is the driver open routine. It calls phy_start to start the PHY device.
+ * This is the driver open routine. It calls phylink_start to start the
+ * PHY device.
  * It also allocates interrupt service routines, enables the interrupt lines
  * and ISR handling. Axi Ethernet core is reset through Axi DMA core. Buffer
  * descriptors are initialized.
  */
 static int axienet_open(struct net_device *ndev)
 {
-	int ret, mdio_mcreg;
+	int ret;
 	struct axienet_local *lp = netdev_priv(ndev);
-	struct phy_device *phydev = NULL;
 
 	dev_dbg(&ndev->dev, "axienet_open()\n");
 
-	mdio_mcreg = axienet_ior(lp, XAE_MDIO_MC_OFFSET);
-	ret = axienet_mdio_wait_until_ready(lp);
-	if (ret < 0)
-		return ret;
 	/* Disable the MDIO interface till Axi Ethernet Reset is completed.
 	 * When we do an Axi Ethernet reset, it resets the complete core
-	 * including the MDIO. If MDIO is not disabled when the reset
-	 * process is started, MDIO will be broken afterwards.
+	 * including the MDIO. MDIO must be disabled before resetting
+	 * and re-enabled afterwards.
+	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
 	 */
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET,
-		    (mdio_mcreg & (~XAE_MDIO_MC_MDIOEN_MASK)));
+	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_mdio_disable(lp);
 	axienet_device_reset(ndev);
-	/* Enable the MDIO */
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET, mdio_mcreg);
-	ret = axienet_mdio_wait_until_ready(lp);
+	ret = axienet_mdio_enable(lp);
+	mutex_unlock(&lp->mii_bus->mdio_lock);
 	if (ret < 0)
 		return ret;
 
-	if (lp->phy_node) {
-		phydev = of_phy_connect(lp->ndev, lp->phy_node,
-					axienet_adjust_link, 0, lp->phy_mode);
-
-		if (!phydev)
-			dev_err(lp->dev, "of_phy_connect() failed\n");
-		else
-			phy_start(phydev);
+	ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0);
+	if (ret) {
+		dev_err(lp->dev, "phylink_of_phy_connect() failed: %d\n", ret);
+		return ret;
 	}
 
+	phylink_start(lp->phylink);
+
 	/* Enable tasklets for Axi DMA error handling */
 	tasklet_init(&lp->dma_err_tasklet, axienet_dma_err_handler,
 		     (unsigned long) lp);
 
 	/* Enable interrupts for Axi DMA Tx */
-	ret = request_irq(lp->tx_irq, axienet_tx_irq, 0, ndev->name, ndev);
+	ret = request_irq(lp->tx_irq, axienet_tx_irq, IRQF_SHARED,
+			  ndev->name, ndev);
 	if (ret)
 		goto err_tx_irq;
 	/* Enable interrupts for Axi DMA Rx */
-	ret = request_irq(lp->rx_irq, axienet_rx_irq, 0, ndev->name, ndev);
+	ret = request_irq(lp->rx_irq, axienet_rx_irq, IRQF_SHARED,
+			  ndev->name, ndev);
 	if (ret)
 		goto err_rx_irq;
+	/* Enable interrupts for Axi Ethernet core (if defined) */
+	if (lp->eth_irq > 0) {
+		ret = request_irq(lp->eth_irq, axienet_eth_irq, IRQF_SHARED,
+				  ndev->name, ndev);
+		if (ret)
+			goto err_eth_irq;
+	}
 
 	return 0;
 
+err_eth_irq:
+	free_irq(lp->rx_irq, ndev);
 err_rx_irq:
 	free_irq(lp->tx_irq, ndev);
 err_tx_irq:
-	if (phydev)
-		phy_disconnect(phydev);
+	phylink_stop(lp->phylink);
+	phylink_disconnect_phy(lp->phylink);
 	tasklet_kill(&lp->dma_err_tasklet);
 	dev_err(lp->dev, "request_irq() failed\n");
 	return ret;
@@ -975,34 +977,61 @@ err_tx_irq:
  *
  * Return: 0, on success.
  *
- * This is the driver stop routine. It calls phy_disconnect to stop the PHY
+ * This is the driver stop routine. It calls phylink_disconnect to stop the PHY
  * device. It also removes the interrupt handlers and disables the interrupts.
  * The Axi DMA Tx/Rx BDs are released.
  */
 static int axienet_stop(struct net_device *ndev)
 {
-	u32 cr;
+	u32 cr, sr;
+	int count;
 	struct axienet_local *lp = netdev_priv(ndev);
 
 	dev_dbg(&ndev->dev, "axienet_close()\n");
 
-	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
-	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
-			  cr & (~XAXIDMA_CR_RUNSTOP_MASK));
-	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
-	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET,
-			  cr & (~XAXIDMA_CR_RUNSTOP_MASK));
+	phylink_stop(lp->phylink);
+	phylink_disconnect_phy(lp->phylink);
+
 	axienet_setoptions(ndev, lp->options &
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 
+	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
+	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+
+	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
+	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+
+	axienet_iow(lp, XAE_IE_OFFSET, 0);
+
+	/* Give DMAs a chance to halt gracefully */
+	sr = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
+	for (count = 0; !(sr & XAXIDMA_SR_HALT_MASK) && count < 5; ++count) {
+		msleep(20);
+		sr = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
+	}
+
+	sr = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
+	for (count = 0; !(sr & XAXIDMA_SR_HALT_MASK) && count < 5; ++count) {
+		msleep(20);
+		sr = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
+	}
+
+	/* Do a reset to ensure DMA is really stopped */
+	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_mdio_disable(lp);
+	__axienet_device_reset(lp);
+	axienet_mdio_enable(lp);
+	mutex_unlock(&lp->mii_bus->mdio_lock);
+
 	tasklet_kill(&lp->dma_err_tasklet);
 
+	if (lp->eth_irq > 0)
+		free_irq(lp->eth_irq, ndev);
 	free_irq(lp->tx_irq, ndev);
 	free_irq(lp->rx_irq, ndev);
 
-	if (ndev->phydev)
-		phy_disconnect(ndev->phydev);
-
 	axienet_dma_bd_release(ndev);
 	return 0;
 }
@@ -1150,6 +1179,48 @@ static void axienet_ethtools_get_regs(struct net_device *ndev,
 	data[29] = axienet_ior(lp, XAE_FMI_OFFSET);
 	data[30] = axienet_ior(lp, XAE_AF0_OFFSET);
 	data[31] = axienet_ior(lp, XAE_AF1_OFFSET);
+	data[32] = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
+	data[33] = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
+	data[34] = axienet_dma_in32(lp, XAXIDMA_TX_CDESC_OFFSET);
+	data[35] = axienet_dma_in32(lp, XAXIDMA_TX_TDESC_OFFSET);
+	data[36] = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
+	data[37] = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
+	data[38] = axienet_dma_in32(lp, XAXIDMA_RX_CDESC_OFFSET);
+	data[39] = axienet_dma_in32(lp, XAXIDMA_RX_TDESC_OFFSET);
+}
+
+static void axienet_ethtools_get_ringparam(struct net_device *ndev,
+					   struct ethtool_ringparam *ering)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	ering->rx_max_pending = RX_BD_NUM_MAX;
+	ering->rx_mini_max_pending = 0;
+	ering->rx_jumbo_max_pending = 0;
+	ering->tx_max_pending = TX_BD_NUM_MAX;
+	ering->rx_pending = lp->rx_bd_num;
+	ering->rx_mini_pending = 0;
+	ering->rx_jumbo_pending = 0;
+	ering->tx_pending = lp->tx_bd_num;
+}
+
+static int axienet_ethtools_set_ringparam(struct net_device *ndev,
+					  struct ethtool_ringparam *ering)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	if (ering->rx_pending > RX_BD_NUM_MAX ||
+	    ering->rx_mini_pending ||
+	    ering->rx_jumbo_pending ||
+	    ering->rx_pending > TX_BD_NUM_MAX)
+		return -EINVAL;
+
+	if (netif_running(ndev))
+		return -EBUSY;
+
+	lp->rx_bd_num = ering->rx_pending;
+	lp->tx_bd_num = ering->tx_pending;
+	return 0;
 }
 
 /**
@@ -1165,12 +1236,9 @@ static void
 axienet_ethtools_get_pauseparam(struct net_device *ndev,
 				struct ethtool_pauseparam *epauseparm)
 {
-	u32 regval;
 	struct axienet_local *lp = netdev_priv(ndev);
-	epauseparm->autoneg  = 0;
-	regval = axienet_ior(lp, XAE_FCC_OFFSET);
-	epauseparm->tx_pause = regval & XAE_FCC_FCTX_MASK;
-	epauseparm->rx_pause = regval & XAE_FCC_FCRX_MASK;
+
+	phylink_ethtool_get_pauseparam(lp->phylink, epauseparm);
 }
 
 /**
@@ -1189,27 +1257,9 @@ static int
 axienet_ethtools_set_pauseparam(struct net_device *ndev,
 				struct ethtool_pauseparam *epauseparm)
 {
-	u32 regval = 0;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	if (netif_running(ndev)) {
-		netdev_err(ndev,
-			   "Please stop netif before applying configuration\n");
-		return -EFAULT;
-	}
-
-	regval = axienet_ior(lp, XAE_FCC_OFFSET);
-	if (epauseparm->tx_pause)
-		regval |= XAE_FCC_FCTX_MASK;
-	else
-		regval &= ~XAE_FCC_FCTX_MASK;
-	if (epauseparm->rx_pause)
-		regval |= XAE_FCC_FCRX_MASK;
-	else
-		regval &= ~XAE_FCC_FCRX_MASK;
-	axienet_iow(lp, XAE_FCC_OFFSET, regval);
-
-	return 0;
+	return phylink_ethtool_set_pauseparam(lp->phylink, epauseparm);
 }
 
 /**
@@ -1288,17 +1338,170 @@ static int axienet_ethtools_set_coalesce(struct net_device *ndev,
 	return 0;
 }
 
+static int
+axienet_ethtools_get_link_ksettings(struct net_device *ndev,
+				    struct ethtool_link_ksettings *cmd)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	return phylink_ethtool_ksettings_get(lp->phylink, cmd);
+}
+
+static int
+axienet_ethtools_set_link_ksettings(struct net_device *ndev,
+				    const struct ethtool_link_ksettings *cmd)
+{
+	struct axienet_local *lp = netdev_priv(ndev);
+
+	return phylink_ethtool_ksettings_set(lp->phylink, cmd);
+}
+
 static const struct ethtool_ops axienet_ethtool_ops = {
 	.get_drvinfo    = axienet_ethtools_get_drvinfo,
 	.get_regs_len   = axienet_ethtools_get_regs_len,
 	.get_regs       = axienet_ethtools_get_regs,
 	.get_link       = ethtool_op_get_link,
+	.get_ringparam	= axienet_ethtools_get_ringparam,
+	.set_ringparam	= axienet_ethtools_set_ringparam,
 	.get_pauseparam = axienet_ethtools_get_pauseparam,
 	.set_pauseparam = axienet_ethtools_set_pauseparam,
 	.get_coalesce   = axienet_ethtools_get_coalesce,
 	.set_coalesce   = axienet_ethtools_set_coalesce,
-	.get_link_ksettings = phy_ethtool_get_link_ksettings,
-	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+	.get_link_ksettings = axienet_ethtools_get_link_ksettings,
+	.set_link_ksettings = axienet_ethtools_set_link_ksettings,
+};
+
+static void axienet_validate(struct phylink_config *config,
+			     unsigned long *supported,
+			     struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+
+	/* Only support the mode we are configured for */
+	if (state->interface != PHY_INTERFACE_MODE_NA &&
+	    state->interface != lp->phy_mode) {
+		netdev_warn(ndev, "Cannot use PHY mode %s, supported: %s\n",
+			    phy_modes(state->interface),
+			    phy_modes(lp->phy_mode));
+		bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
+		return;
+	}
+
+	phylink_set(mask, Autoneg);
+	phylink_set_port_modes(mask);
+
+	phylink_set(mask, Asym_Pause);
+	phylink_set(mask, Pause);
+	phylink_set(mask, 1000baseX_Full);
+	phylink_set(mask, 10baseT_Full);
+	phylink_set(mask, 100baseT_Full);
+	phylink_set(mask, 1000baseT_Full);
+
+	bitmap_and(supported, supported, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static int axienet_mac_link_state(struct phylink_config *config,
+				  struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+	u32 emmc_reg, fcc_reg;
+
+	state->interface = lp->phy_mode;
+
+	emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET);
+	if (emmc_reg & XAE_EMMC_LINKSPD_1000)
+		state->speed = SPEED_1000;
+	else if (emmc_reg & XAE_EMMC_LINKSPD_100)
+		state->speed = SPEED_100;
+	else
+		state->speed = SPEED_10;
+
+	state->pause = 0;
+	fcc_reg = axienet_ior(lp, XAE_FCC_OFFSET);
+	if (fcc_reg & XAE_FCC_FCTX_MASK)
+		state->pause |= MLO_PAUSE_TX;
+	if (fcc_reg & XAE_FCC_FCRX_MASK)
+		state->pause |= MLO_PAUSE_RX;
+
+	state->an_complete = 0;
+	state->duplex = 1;
+
+	return 1;
+}
+
+static void axienet_mac_an_restart(struct phylink_config *config)
+{
+	/* Unsupported, do nothing */
+}
+
+static void axienet_mac_config(struct phylink_config *config, unsigned int mode,
+			       const struct phylink_link_state *state)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct axienet_local *lp = netdev_priv(ndev);
+	u32 emmc_reg, fcc_reg;
+
+	emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET);
+	emmc_reg &= ~XAE_EMMC_LINKSPEED_MASK;
+
+	switch (state->speed) {
+	case SPEED_1000:
+		emmc_reg |= XAE_EMMC_LINKSPD_1000;
+		break;
+	case SPEED_100:
+		emmc_reg |= XAE_EMMC_LINKSPD_100;
+		break;
+	case SPEED_10:
+		emmc_reg |= XAE_EMMC_LINKSPD_10;
+		break;
+	default:
+		dev_err(&ndev->dev,
+			"Speed other than 10, 100 or 1Gbps is not supported\n");
+		break;
+	}
+
+	axienet_iow(lp, XAE_EMMC_OFFSET, emmc_reg);
+
+	fcc_reg = axienet_ior(lp, XAE_FCC_OFFSET);
+	if (state->pause & MLO_PAUSE_TX)
+		fcc_reg |= XAE_FCC_FCTX_MASK;
+	else
+		fcc_reg &= ~XAE_FCC_FCTX_MASK;
+	if (state->pause & MLO_PAUSE_RX)
+		fcc_reg |= XAE_FCC_FCRX_MASK;
+	else
+		fcc_reg &= ~XAE_FCC_FCRX_MASK;
+	axienet_iow(lp, XAE_FCC_OFFSET, fcc_reg);
+}
+
+static void axienet_mac_link_down(struct phylink_config *config,
+				  unsigned int mode,
+				  phy_interface_t interface)
+{
+	/* nothing meaningful to do */
+}
+
+static void axienet_mac_link_up(struct phylink_config *config,
+				unsigned int mode,
+				phy_interface_t interface,
+				struct phy_device *phy)
+{
+	/* nothing meaningful to do */
+}
+
+static const struct phylink_mac_ops axienet_phylink_ops = {
+	.validate = axienet_validate,
+	.mac_link_state = axienet_mac_link_state,
+	.mac_an_restart = axienet_mac_an_restart,
+	.mac_config = axienet_mac_config,
+	.mac_link_down = axienet_mac_link_down,
+	.mac_link_up = axienet_mac_link_up,
 };
 
 /**
@@ -1312,38 +1515,33 @@ static void axienet_dma_err_handler(unsigned long data)
 {
 	u32 axienet_status;
 	u32 cr, i;
-	int mdio_mcreg;
 	struct axienet_local *lp = (struct axienet_local *) data;
 	struct net_device *ndev = lp->ndev;
 	struct axidma_bd *cur_p;
 
 	axienet_setoptions(ndev, lp->options &
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
-	mdio_mcreg = axienet_ior(lp, XAE_MDIO_MC_OFFSET);
-	axienet_mdio_wait_until_ready(lp);
 	/* Disable the MDIO interface till Axi Ethernet Reset is completed.
 	 * When we do an Axi Ethernet reset, it resets the complete core
-	 * including the MDIO. So if MDIO is not disabled when the reset
-	 * process is started, MDIO will be broken afterwards.
+	 * including the MDIO. MDIO must be disabled before resetting
+	 * and re-enabled afterwards.
+	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
 	 */
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET, (mdio_mcreg &
-		    ~XAE_MDIO_MC_MDIOEN_MASK));
-
-	__axienet_device_reset(lp, XAXIDMA_TX_CR_OFFSET);
-	__axienet_device_reset(lp, XAXIDMA_RX_CR_OFFSET);
-
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET, mdio_mcreg);
-	axienet_mdio_wait_until_ready(lp);
+	mutex_lock(&lp->mii_bus->mdio_lock);
+	axienet_mdio_disable(lp);
+	__axienet_device_reset(lp);
+	axienet_mdio_enable(lp);
+	mutex_unlock(&lp->mii_bus->mdio_lock);
 
-	for (i = 0; i < TX_BD_NUM; i++) {
+	for (i = 0; i < lp->tx_bd_num; i++) {
 		cur_p = &lp->tx_bd_v[i];
 		if (cur_p->phys)
 			dma_unmap_single(ndev->dev.parent, cur_p->phys,
 					 (cur_p->cntrl &
 					  XAXIDMA_BD_CTRL_LENGTH_MASK),
 					 DMA_TO_DEVICE);
-		if (cur_p->app4)
-			dev_kfree_skb_irq((struct sk_buff *) cur_p->app4);
+		if (cur_p->skb)
+			dev_kfree_skb_irq(cur_p->skb);
 		cur_p->phys = 0;
 		cur_p->cntrl = 0;
 		cur_p->status = 0;
@@ -1352,10 +1550,10 @@ static void axienet_dma_err_handler(unsigned long data)
 		cur_p->app2 = 0;
 		cur_p->app3 = 0;
 		cur_p->app4 = 0;
-		cur_p->sw_id_offset = 0;
+		cur_p->skb = NULL;
 	}
 
-	for (i = 0; i < RX_BD_NUM; i++) {
+	for (i = 0; i < lp->rx_bd_num; i++) {
 		cur_p = &lp->rx_bd_v[i];
 		cur_p->status = 0;
 		cur_p->app0 = 0;
@@ -1403,7 +1601,7 @@ static void axienet_dma_err_handler(unsigned long data)
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
 			  cr | XAXIDMA_CR_RUNSTOP_MASK);
 	axienet_dma_out32(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
-			  (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
+			  (sizeof(*lp->rx_bd_v) * (lp->rx_bd_num - 1)));
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
@@ -1421,6 +1619,8 @@ static void axienet_dma_err_handler(unsigned long data)
 	axienet_status = axienet_ior(lp, XAE_IP_OFFSET);
 	if (axienet_status & XAE_INT_RXRJECT_MASK)
 		axienet_iow(lp, XAE_IS_OFFSET, XAE_INT_RXRJECT_MASK);
+	axienet_iow(lp, XAE_IE_OFFSET, lp->eth_irq > 0 ?
+		    XAE_INT_RECV_ERROR_MASK : 0);
 	axienet_iow(lp, XAE_FCC_OFFSET, XAE_FCC_FCRX_MASK);
 
 	/* Sync default options with HW but leave receiver and
@@ -1452,7 +1652,7 @@ static int axienet_probe(struct platform_device *pdev)
 	struct axienet_local *lp;
 	struct net_device *ndev;
 	const void *mac_addr;
-	struct resource *ethres, dmares;
+	struct resource *ethres;
 	u32 value;
 
 	ndev = alloc_etherdev(sizeof(*lp));
@@ -1475,6 +1675,8 @@ static int axienet_probe(struct platform_device *pdev)
 	lp->ndev = ndev;
 	lp->dev = &pdev->dev;
 	lp->options = XAE_OPTION_DEFAULTS;
+	lp->rx_bd_num = RX_BD_NUM_DEFAULT;
+	lp->tx_bd_num = TX_BD_NUM_DEFAULT;
 	/* Map device registers */
 	ethres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	lp->regs = devm_ioremap_resource(&pdev->dev, ethres);
@@ -1483,6 +1685,7 @@ static int axienet_probe(struct platform_device *pdev)
 		ret = PTR_ERR(lp->regs);
 		goto free_netdev;
 	}
+	lp->regs_start = ethres->start;
 
 	/* Setup checksum offload, but default to off if not specified */
 	lp->features = 0;
@@ -1567,36 +1770,56 @@ static int axienet_probe(struct platform_device *pdev)
 
 	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
 	np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0);
-	if (!np) {
-		dev_err(&pdev->dev, "could not find DMA node\n");
-		ret = -ENODEV;
-		goto free_netdev;
-	}
-	ret = of_address_to_resource(np, 0, &dmares);
-	if (ret) {
-		dev_err(&pdev->dev, "unable to get DMA resource\n");
-		goto free_netdev;
+	if (np) {
+		struct resource dmares;
+
+		ret = of_address_to_resource(np, 0, &dmares);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"unable to get DMA resource\n");
+			of_node_put(np);
+			goto free_netdev;
+		}
+		lp->dma_regs = devm_ioremap_resource(&pdev->dev,
+						     &dmares);
+		lp->rx_irq = irq_of_parse_and_map(np, 1);
+		lp->tx_irq = irq_of_parse_and_map(np, 0);
+		of_node_put(np);
+		lp->eth_irq = platform_get_irq(pdev, 0);
+	} else {
+		/* Check for these resources directly on the Ethernet node. */
+		struct resource *res = platform_get_resource(pdev,
+							     IORESOURCE_MEM, 1);
+		if (!res) {
+			dev_err(&pdev->dev, "unable to get DMA memory resource\n");
+			goto free_netdev;
+		}
+		lp->dma_regs = devm_ioremap_resource(&pdev->dev, res);
+		lp->rx_irq = platform_get_irq(pdev, 1);
+		lp->tx_irq = platform_get_irq(pdev, 0);
+		lp->eth_irq = platform_get_irq(pdev, 2);
 	}
-	lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares);
 	if (IS_ERR(lp->dma_regs)) {
 		dev_err(&pdev->dev, "could not map DMA regs\n");
 		ret = PTR_ERR(lp->dma_regs);
 		goto free_netdev;
 	}
-	lp->rx_irq = irq_of_parse_and_map(np, 1);
-	lp->tx_irq = irq_of_parse_and_map(np, 0);
-	of_node_put(np);
 	if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) {
 		dev_err(&pdev->dev, "could not determine irqs\n");
 		ret = -ENOMEM;
 		goto free_netdev;
 	}
 
+	/* Check for Ethernet core IRQ (optional) */
+	if (lp->eth_irq <= 0)
+		dev_info(&pdev->dev, "Ethernet core IRQ not defined\n");
+
 	/* Retrieve the MAC address */
 	mac_addr = of_get_mac_address(pdev->dev.of_node);
-	if (!mac_addr) {
-		dev_err(&pdev->dev, "could not find MAC address\n");
-		goto free_netdev;
+	if (IS_ERR(mac_addr)) {
+		dev_warn(&pdev->dev, "could not find MAC address property: %ld\n",
+			 PTR_ERR(mac_addr));
+		mac_addr = NULL;
 	}
 	axienet_set_mac_address(ndev, mac_addr);
 
@@ -1605,9 +1828,36 @@ static int axienet_probe(struct platform_device *pdev)
 
 	lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
 	if (lp->phy_node) {
-		ret = axienet_mdio_setup(lp, pdev->dev.of_node);
+		lp->clk = devm_clk_get(&pdev->dev, NULL);
+		if (IS_ERR(lp->clk)) {
+			dev_warn(&pdev->dev, "Failed to get clock: %ld\n",
+				 PTR_ERR(lp->clk));
+			lp->clk = NULL;
+		} else {
+			ret = clk_prepare_enable(lp->clk);
+			if (ret) {
+				dev_err(&pdev->dev, "Unable to enable clock: %d\n",
+					ret);
+				goto free_netdev;
+			}
+		}
+
+		ret = axienet_mdio_setup(lp);
 		if (ret)
-			dev_warn(&pdev->dev, "error registering MDIO bus\n");
+			dev_warn(&pdev->dev,
+				 "error registering MDIO bus: %d\n", ret);
+	}
+
+	lp->phylink_config.dev = &ndev->dev;
+	lp->phylink_config.type = PHYLINK_NETDEV;
+
+	lp->phylink = phylink_create(&lp->phylink_config, pdev->dev.fwnode,
+				     lp->phy_mode,
+				     &axienet_phylink_ops);
+	if (IS_ERR(lp->phylink)) {
+		ret = PTR_ERR(lp->phylink);
+		dev_err(&pdev->dev, "phylink_create error (%i)\n", ret);
+		goto free_netdev;
 	}
 
 	ret = register_netdev(lp->ndev);
@@ -1629,9 +1879,16 @@ static int axienet_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	axienet_mdio_teardown(lp);
 	unregister_netdev(ndev);
 
+	if (lp->phylink)
+		phylink_destroy(lp->phylink);
+
+	axienet_mdio_teardown(lp);
+
+	if (lp->clk)
+		clk_disable_unprepare(lp->clk);
+
 	of_node_put(lp->phy_node);
 	lp->phy_node = NULL;
 
@@ -1640,9 +1897,23 @@ static int axienet_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void axienet_shutdown(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+
+	rtnl_lock();
+	netif_device_detach(ndev);
+
+	if (netif_running(ndev))
+		dev_close(ndev);
+
+	rtnl_unlock();
+}
+
 static struct platform_driver axienet_driver = {
 	.probe = axienet_probe,
 	.remove = axienet_remove,
+	.shutdown = axienet_shutdown,
 	.driver = {
 		 .name = "xilinx_axienet",
 		 .of_match_table = axienet_of_match,
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
index 757a3b37ae8a..435ed308d990 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
@@ -5,31 +5,29 @@
  * Copyright (c) 2009 Secret Lab Technologies, Ltd.
  * Copyright (c) 2010 - 2011 Michal Simek <monstr@monstr.eu>
  * Copyright (c) 2010 - 2011 PetaLogix
+ * Copyright (c) 2019 SED Systems, a division of Calian Ltd.
  * Copyright (c) 2010 - 2012 Xilinx, Inc. All rights reserved.
  */
 
+#include <linux/clk.h>
 #include <linux/of_address.h>
 #include <linux/of_mdio.h>
 #include <linux/jiffies.h>
+#include <linux/iopoll.h>
 
 #include "xilinx_axienet.h"
 
 #define MAX_MDIO_FREQ		2500000 /* 2.5 MHz */
-#define DEFAULT_CLOCK_DIVISOR	XAE_MDIO_DIV_DFT
+#define DEFAULT_HOST_CLOCK	150000000 /* 150 MHz */
 
 /* Wait till MDIO interface is ready to accept a new transaction.*/
-int axienet_mdio_wait_until_ready(struct axienet_local *lp)
+static int axienet_mdio_wait_until_ready(struct axienet_local *lp)
 {
-	unsigned long end = jiffies + 2;
-	while (!(axienet_ior(lp, XAE_MDIO_MCR_OFFSET) &
-		 XAE_MDIO_MCR_READY_MASK)) {
-		if (time_before_eq(end, jiffies)) {
-			WARN_ON(1);
-			return -ETIMEDOUT;
-		}
-		udelay(1);
-	}
-	return 0;
+	u32 val;
+
+	return readx_poll_timeout(axinet_ior_read_mcr, lp,
+				  val, val & XAE_MDIO_MCR_READY_MASK,
+				  1, 20000);
 }
 
 /**
@@ -116,23 +114,42 @@ static int axienet_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 }
 
 /**
- * axienet_mdio_setup - MDIO setup function
+ * axienet_mdio_enable - MDIO hardware setup function
  * @lp:		Pointer to axienet local data structure.
- * @np:		Pointer to device node
  *
- * Return:	0 on success, -ETIMEDOUT on a timeout, -ENOMEM when
- *		mdiobus_alloc (to allocate memory for mii bus structure) fails.
+ * Return:	0 on success, -ETIMEDOUT on a timeout.
  *
  * Sets up the MDIO interface by initializing the MDIO clock and enabling the
- * MDIO interface in hardware. Register the MDIO interface.
+ * MDIO interface in hardware.
  **/
-int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np)
+int axienet_mdio_enable(struct axienet_local *lp)
 {
-	int ret;
 	u32 clk_div, host_clock;
-	struct mii_bus *bus;
-	struct resource res;
-	struct device_node *np1;
+
+	if (lp->clk) {
+		host_clock = clk_get_rate(lp->clk);
+	} else {
+		struct device_node *np1;
+
+		/* Legacy fallback: detect CPU clock frequency and use as AXI
+		 * bus clock frequency. This only works on certain platforms.
+		 */
+		np1 = of_find_node_by_name(NULL, "cpu");
+		if (!np1) {
+			netdev_warn(lp->ndev, "Could not find CPU device node.\n");
+			host_clock = DEFAULT_HOST_CLOCK;
+		} else {
+			int ret = of_property_read_u32(np1, "clock-frequency",
+						       &host_clock);
+			if (ret) {
+				netdev_warn(lp->ndev, "CPU clock-frequency property not found.\n");
+				host_clock = DEFAULT_HOST_CLOCK;
+			}
+			of_node_put(np1);
+		}
+		netdev_info(lp->ndev, "Setting assumed host clock to %u\n",
+			    host_clock);
+	}
 
 	/* clk_div can be calculated by deriving it from the equation:
 	 * fMDIO = fHOST / ((1 + clk_div) * 2)
@@ -159,25 +176,6 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np)
 	 * "clock-frequency" from the CPU
 	 */
 
-	np1 = of_find_node_by_name(NULL, "cpu");
-	if (!np1) {
-		netdev_warn(lp->ndev, "Could not find CPU device node.\n");
-		netdev_warn(lp->ndev,
-			    "Setting MDIO clock divisor to default %d\n",
-			    DEFAULT_CLOCK_DIVISOR);
-		clk_div = DEFAULT_CLOCK_DIVISOR;
-		goto issue;
-	}
-	if (of_property_read_u32(np1, "clock-frequency", &host_clock)) {
-		netdev_warn(lp->ndev, "clock-frequency property not found.\n");
-		netdev_warn(lp->ndev,
-			    "Setting MDIO clock divisor to default %d\n",
-			    DEFAULT_CLOCK_DIVISOR);
-		clk_div = DEFAULT_CLOCK_DIVISOR;
-		of_node_put(np1);
-		goto issue;
-	}
-
 	clk_div = (host_clock / (MAX_MDIO_FREQ * 2)) - 1;
 	/* If there is any remainder from the division of
 	 * fHOST / (MAX_MDIO_FREQ * 2), then we need to add
@@ -190,12 +188,39 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np)
 		   "Setting MDIO clock divisor to %u/%u Hz host clock.\n",
 		   clk_div, host_clock);
 
-	of_node_put(np1);
-issue:
-	axienet_iow(lp, XAE_MDIO_MC_OFFSET,
-		    (((u32) clk_div) | XAE_MDIO_MC_MDIOEN_MASK));
+	axienet_iow(lp, XAE_MDIO_MC_OFFSET, clk_div | XAE_MDIO_MC_MDIOEN_MASK);
 
-	ret = axienet_mdio_wait_until_ready(lp);
+	return axienet_mdio_wait_until_ready(lp);
+}
+
+/**
+ * axienet_mdio_disable - MDIO hardware disable function
+ * @lp:		Pointer to axienet local data structure.
+ *
+ * Disable the MDIO interface in hardware.
+ **/
+void axienet_mdio_disable(struct axienet_local *lp)
+{
+	axienet_iow(lp, XAE_MDIO_MC_OFFSET, 0);
+}
+
+/**
+ * axienet_mdio_setup - MDIO setup function
+ * @lp:		Pointer to axienet local data structure.
+ *
+ * Return:	0 on success, -ETIMEDOUT on a timeout, -ENOMEM when
+ *		mdiobus_alloc (to allocate memory for mii bus structure) fails.
+ *
+ * Sets up the MDIO interface by initializing the MDIO clock and enabling the
+ * MDIO interface in hardware. Register the MDIO interface.
+ **/
+int axienet_mdio_setup(struct axienet_local *lp)
+{
+	struct device_node *mdio_node;
+	struct mii_bus *bus;
+	int ret;
+
+	ret = axienet_mdio_enable(lp);
 	if (ret < 0)
 		return ret;
 
@@ -203,10 +228,8 @@ issue:
 	if (!bus)
 		return -ENOMEM;
 
-	np1 = of_get_parent(lp->phy_node);
-	of_address_to_resource(np1, 0, &res);
-	snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx",
-		 (unsigned long long) res.start);
+	snprintf(bus->id, MII_BUS_ID_SIZE, "axienet-%.8llx",
+		 (unsigned long long)lp->regs_start);
 
 	bus->priv = lp;
 	bus->name = "Xilinx Axi Ethernet MDIO";
@@ -215,7 +238,9 @@ issue:
 	bus->parent = lp->dev;
 	lp->mii_bus = bus;
 
-	ret = of_mdiobus_register(bus, np1);
+	mdio_node = of_get_child_by_name(lp->dev->of_node, "mdio");
+	ret = of_mdiobus_register(bus, mdio_node);
+	of_node_put(mdio_node);
 	if (ret) {
 		mdiobus_free(bus);
 		lp->mii_bus = NULL;
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 639e3e99af46..0de52e70abcc 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Xilinx EmacLite Linux driver for the Xilinx Ethernet MAC Lite device.
  *
@@ -5,11 +6,6 @@
  * driver from John Williams <john.williams@xilinx.com>.
  *
  * 2007 - 2013 (c) Xilinx, Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
  */
 
 #include <linux/module.h>
@@ -17,6 +13,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
+#include <linux/ethtool.h>
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/of_address.h>
@@ -26,6 +23,7 @@
 #include <linux/of_net.h>
 #include <linux/phy.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 
 #define DRIVER_NAME "xilinx_emaclite"
 
@@ -581,7 +579,7 @@ static void xemaclite_tx_handler(struct net_device *dev)
 		return;
 
 	dev->stats.tx_bytes += lp->deferred_skb->len;
-	dev_kfree_skb_irq(lp->deferred_skb);
+	dev_consume_skb_irq(lp->deferred_skb);
 	lp->deferred_skb = NULL;
 	netif_trans_update(dev); /* prevent tx timeout */
 	netif_wake_queue(dev);
@@ -713,20 +711,15 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
 
 static int xemaclite_mdio_wait(struct net_local *lp)
 {
-	unsigned long end = jiffies + 2;
+	u32 val;
 
 	/* wait for the MDIO interface to not be busy or timeout
 	 * after some time.
 	 */
-	while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
-			XEL_MDIOCTRL_MDIOSTS_MASK) {
-		if (time_before_eq(end, jiffies)) {
-			WARN_ON(1);
-			return -ETIMEDOUT;
-		}
-		msleep(1);
-	}
-	return 0;
+	return readx_poll_timeout(xemaclite_readl,
+				  lp->base_addr + XEL_MDIOCTRL_OFFSET,
+				  val, !(val & XEL_MDIOCTRL_MDIOSTS_MASK),
+				  1000, 20000);
 }
 
 /**
@@ -1078,6 +1071,27 @@ static bool get_bool(struct platform_device *ofdev, const char *s)
 	return (bool)*p;
 }
 
+/**
+ * xemaclite_ethtools_get_drvinfo - Get various Axi Emac Lite driver info
+ * @ndev:       Pointer to net_device structure
+ * @ed:         Pointer to ethtool_drvinfo structure
+ *
+ * This implements ethtool command for getting the driver information.
+ * Issue "ethtool -i ethX" under linux prompt to execute this function.
+ */
+static void xemaclite_ethtools_get_drvinfo(struct net_device *ndev,
+					   struct ethtool_drvinfo *ed)
+{
+	strlcpy(ed->driver, DRIVER_NAME, sizeof(ed->driver));
+}
+
+static const struct ethtool_ops xemaclite_ethtool_ops = {
+	.get_drvinfo    = xemaclite_ethtools_get_drvinfo,
+	.get_link       = ethtool_op_get_link,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+};
+
 static const struct net_device_ops xemaclite_netdev_ops;
 
 /**
@@ -1143,9 +1157,9 @@ static int xemaclite_of_probe(struct platform_device *ofdev)
 	lp->rx_ping_pong = get_bool(ofdev, "xlnx,rx-ping-pong");
 	mac_address = of_get_mac_address(ofdev->dev.of_node);
 
-	if (mac_address) {
+	if (!IS_ERR(mac_address)) {
 		/* Set the MAC address. */
-		memcpy(ndev->dev_addr, mac_address, ETH_ALEN);
+		ether_addr_copy(ndev->dev_addr, mac_address);
 	} else {
 		dev_warn(dev, "No MAC address found, using random\n");
 		eth_hw_addr_random(ndev);
@@ -1164,6 +1178,7 @@ static int xemaclite_of_probe(struct platform_device *ofdev)
 	dev_info(dev, "MAC address is now %pM\n", ndev->dev_addr);
 
 	ndev->netdev_ops = &xemaclite_netdev_ops;
+	ndev->ethtool_ops = &xemaclite_ethtool_ops;
 	ndev->flags &= ~IFF_MULTICAST;
 	ndev->watchdog_timeo = TX_TIMEOUT;
 
@@ -1229,12 +1244,29 @@ xemaclite_poll_controller(struct net_device *ndev)
 }
 #endif
 
+/* Ioctl MII Interface */
+static int xemaclite_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	if (!dev->phydev || !netif_running(dev))
+		return -EINVAL;
+
+	switch (cmd) {
+	case SIOCGMIIPHY:
+	case SIOCGMIIREG:
+	case SIOCSMIIREG:
+		return phy_mii_ioctl(dev->phydev, rq, cmd);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops xemaclite_netdev_ops = {
 	.ndo_open		= xemaclite_open,
 	.ndo_stop		= xemaclite_close,
 	.ndo_start_xmit		= xemaclite_send,
 	.ndo_set_mac_address	= xemaclite_set_mac_address,
 	.ndo_tx_timeout		= xemaclite_tx_timeout,
+	.ndo_do_ioctl		= xemaclite_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = xemaclite_poll_controller,
 #endif
diff --git a/drivers/net/ethernet/xircom/Kconfig b/drivers/net/ethernet/xircom/Kconfig
index d6208a4c9866..ad5390079b13 100644
--- a/drivers/net/ethernet/xircom/Kconfig
+++ b/drivers/net/ethernet/xircom/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Xircom network device configuration
 #
diff --git a/drivers/net/ethernet/xircom/Makefile b/drivers/net/ethernet/xircom/Makefile
index 3b7aebd8b849..07667fefafc2 100644
--- a/drivers/net/ethernet/xircom/Makefile
+++ b/drivers/net/ethernet/xircom/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Xircom network device drivers.
 #
diff --git a/drivers/net/ethernet/xscale/Kconfig b/drivers/net/ethernet/xscale/Kconfig
index af3432fe9a5e..2f354ba029a6 100644
--- a/drivers/net/ethernet/xscale/Kconfig
+++ b/drivers/net/ethernet/xscale/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Intel XScale IXP device configuration
 #
diff --git a/drivers/net/ethernet/xscale/Makefile b/drivers/net/ethernet/xscale/Makefile
index abc3b031fba7..794a519d07b3 100644
--- a/drivers/net/ethernet/xscale/Makefile
+++ b/drivers/net/ethernet/xscale/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
 #
 # Makefile for the Intel XScale IXP device drivers.
 #
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index aee55c03def0..6fc04ffb22c2 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Intel IXP4xx Ethernet driver for Linux
  *
  * Copyright (C) 2007 Krzysztof Halasa <khc@pm.waw.pl>
  *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
- *
  * Ethernet port config (0x00 is not present on IXP42X):
  *
  * logical port		0x00		0x10		0x20
@@ -16,7 +13,6 @@
  * RX-free queue	26		27		28
  * TX-done queue is always 31, per-port RX and TX-ready queues are configurable
  *
- *
  * Queue entries:
  * bits 0 -> 1	- NPE ID (RX and TX-done)
  * bits 0 -> 2	- priority (TX, per 802.1D)
@@ -31,14 +27,15 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/net_tstamp.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
 #include <linux/ptp_classify.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <mach/ixp46x_ts.h>
-#include <mach/npe.h>
-#include <mach/qmgr.h>
+#include <linux/soc/ixp4xx/npe.h>
+#include <linux/soc/ixp4xx/qmgr.h>
 
 #define DEBUG_DESC		0
 #define DEBUG_RX		0
@@ -139,7 +136,7 @@
 #ifdef __ARMEB__
 typedef struct sk_buff buffer_t;
 #define free_buffer dev_kfree_skb
-#define free_buffer_irq dev_kfree_skb_irq
+#define free_buffer_irq dev_consume_skb_irq
 #else
 typedef void buffer_t;
 #define free_buffer kfree
@@ -1497,6 +1494,15 @@ static struct platform_driver ixp4xx_eth_driver = {
 static int __init eth_init_module(void)
 {
 	int err;
+
+	/*
+	 * FIXME: we bail out on device tree boot but this really needs
+	 * to be fixed in a nicer way: this registers the MDIO bus before
+	 * even matching the driver infrastructure, we should only probe
+	 * detected hardware.
+	 */
+	if (of_have_populated_dt())
+		return -ENODEV;
 	if ((err = ixp4xx_mdio_register()))
 		return err;
 	return platform_driver_register(&ixp4xx_eth_driver);